High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

PGM-MVS		96.81 40	96.53 44	97.65 44	99.35 21	93.53 63	97.65 84	98.98 1	92.22 109	97.14 41	98.44 28	91.17 64	99.85 14	94.35 91	99.46 38	99.57 19

MVS_111021_HR		96.68 47	96.58 42	96.99 73	98.46 74	92.31 97	96.20 220	98.90 2	94.30 44	95.86 86	97.74 87	92.33 35	99.38 111	96.04 44	99.42 43	99.28 65

ACMMP		96.27 58	95.93 60	97.28 59	99.24 28	92.62 87	98.25 28	98.81 3	92.99 84	94.56 114	98.39 35	88.96 89	99.85 14	94.57 90	97.63 119	99.36 58
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MVS_111021_LR		96.24 59	96.19 57	96.39 98	98.23 97	91.35 128	96.24 218	98.79 4	93.99 49	95.80 88	97.65 94	89.92 84	99.24 120	95.87 47	99.20 70	98.58 118

FC-MVSNet-test		93.94 120	93.57 114	95.04 162	95.48 221	91.45 125	98.12 38	98.71 5	93.37 70	90.23 201	96.70 141	87.66 106	97.85 256	91.49 148	90.39 240	95.83 225

UniMVSNet (Re)		93.31 138	92.55 146	95.61 138	95.39 224	93.34 70	97.39 109	98.71 5	93.14 80	90.10 211	94.83 235	87.71 105	98.03 233	91.67 146	83.99 307	95.46 243

FIs		94.09 114	93.70 110	95.27 154	95.70 213	92.03 107	98.10 39	98.68 7	93.36 72	90.39 198	96.70 141	87.63 108	97.94 247	92.25 128	90.50 239	95.84 224

WR-MVS_H		92.00 187	91.35 183	93.95 212	95.09 248	89.47 186	98.04 45	98.68 7	91.46 132	88.34 258	94.68 243	85.86 134	97.56 282	85.77 255	84.24 304	94.82 284

VPA-MVSNet		93.24 140	92.48 151	95.51 144	95.70 213	92.39 93	97.86 59	98.66 9	92.30 107	92.09 168	95.37 215	80.49 219	98.40 192	93.95 99	85.86 280	95.75 232

UniMVSNet_NR-MVSNet		93.37 136	92.67 141	95.47 150	95.34 230	92.83 80	97.17 133	98.58 10	92.98 89	90.13 207	95.80 191	88.37 99	97.85 256	91.71 142	83.93 308	95.73 234

CSCG		96.05 63	95.91 61	96.46 93	99.24 28	90.47 159	98.30 23	98.57 11	89.01 200	93.97 126	97.57 103	92.62 28	99.76 30	94.66 87	99.27 61	99.15 72

MSLP-MVS++		96.94 32	97.06 13	96.59 83	98.72 59	91.86 112	97.67 81	98.49 12	94.66 35	97.24 36	98.41 34	92.31 37	98.94 150	96.61 21	99.46 38	98.96 91

HyFIR lowres test		93.66 128	92.92 133	95.87 124	98.24 93	89.88 174	94.58 274	98.49 12	85.06 290	93.78 129	95.78 195	82.86 177	98.67 173	91.77 140	95.71 162	99.07 82

CHOSEN 1792x2688		94.15 110	93.51 118	96.06 116	98.27 89	89.38 191	95.18 266	98.48 14	85.60 281	93.76 130	97.11 123	83.15 168	99.61 62	91.33 151	98.72 92	99.19 68

PHI-MVS		96.77 42	96.46 48	97.71 41	98.40 78	94.07 48	98.21 34	98.45 15	89.86 178	97.11 44	98.01 68	92.52 32	99.69 44	96.03 45	99.53 24	99.36 58

PVSNet_BlendedMVS		94.06 115	93.92 105	94.47 189	98.27 89	89.46 188	96.73 171	98.36 16	90.17 172	94.36 117	95.24 220	88.02 100	99.58 70	93.44 111	90.72 235	94.36 303

PVSNet_Blended		94.87 97	94.56 93	95.81 126	98.27 89	89.46 188	95.47 252	98.36 16	88.84 208	94.36 117	96.09 179	88.02 100	99.58 70	93.44 111	98.18 106	98.40 138

3Dnovator	91.36 5	95.19 87	94.44 100	97.44 52	96.56 173	93.36 69	98.65 6	98.36 16	94.12 46	89.25 240	98.06 64	82.20 193	99.77 29	93.41 113	99.32 53	99.18 69

DPE-MVS		97.86 3	97.65 4	98.47 3	99.17 32	95.78 5	97.21 130	98.35 19	95.16 14	98.71 10	98.80 9	95.05 7	99.89 3	96.70 19	99.73 1	99.73 7

HFP-MVS		97.14 19	96.92 20	97.83 26	99.42 6	94.12 45	98.52 10	98.32 20	93.21 75	97.18 38	98.29 50	92.08 39	99.83 22	95.63 57	99.59 15	99.54 29

#test#		97.02 26	96.75 33	97.83 26	99.42 6	94.12 45	98.15 37	98.32 20	92.57 102	97.18 38	98.29 50	92.08 39	99.83 22	95.12 71	99.59 15	99.54 29

ACMMPR		97.07 22	96.84 25	97.79 32	99.44 5	93.88 52	98.52 10	98.31 22	93.21 75	97.15 40	98.33 44	91.35 59	99.86 8	95.63 57	99.59 15	99.62 13

APDe-MVS		97.82 4	97.73 3	98.08 15	99.15 33	94.82 25	98.81 2	98.30 23	94.76 32	98.30 13	98.90 3	93.77 14	99.68 47	97.93 1	99.69 3	99.75 3

test0726					99.45 2	95.36 10	98.31 22	98.29 24	94.92 22	98.99 4	98.92 2	95.08 5

MSP-MVS		97.59 7	97.54 5	97.73 38	99.40 11	93.77 58	98.53 9	98.29 24	95.55 5	98.56 12	97.81 82	93.90 12	99.65 53	96.62 20	99.21 69	99.77 1
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
test_0728_SECOND				98.51 2	99.45 2	95.93 3	98.21 34	98.28 26					99.86 8	97.52 2	99.67 6	99.75 3

CP-MVS		97.02 26	96.81 28	97.64 46	99.33 22	93.54 62	98.80 3	98.28 26	92.99 84	96.45 66	98.30 49	91.90 45	99.85 14	95.61 59	99.68 4	99.54 29

SED-MVS		98.05 1	97.99 1	98.24 7	99.42 6	95.30 15	98.25 28	98.27 28	95.13 15	99.19 1	98.89 4	95.54 3	99.85 14	97.52 2	99.66 8	99.56 22

test_241102_TWO								98.27 28	95.13 15	98.93 6	98.89 4	94.99 8	99.85 14	97.52 2	99.65 10	99.74 5

test_241102_ONE					99.42 6	95.30 15		98.27 28	95.09 18	99.19 1	98.81 8	95.54 3	99.65 53

SF-MVS		97.39 10	97.13 11	98.17 11	99.02 43	95.28 17	98.23 31	98.27 28	92.37 106	98.27 14	98.65 13	93.33 17	99.72 35	96.49 25	99.52 25	99.51 34

SteuartSystems-ACMMP		97.62 6	97.53 6	97.87 24	98.39 80	94.25 38	98.43 17	98.27 28	95.34 10	98.11 16	98.56 17	94.53 9	99.71 38	96.57 23	99.62 13	99.65 9
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_Blended_VisFu		95.27 82	94.91 85	96.38 99	98.20 98	90.86 148	97.27 121	98.25 33	90.21 171	94.18 121	97.27 115	87.48 112	99.73 32	93.53 108	97.77 117	98.55 119

ETH3D-3000-0.1		97.07 22	96.71 36	98.14 13	98.90 51	95.33 14	97.68 80	98.24 34	91.57 128	97.90 21	98.37 36	92.61 29	99.66 52	95.59 62	99.51 29	99.43 49

region2R		97.07 22	96.84 25	97.77 35	99.46 1	93.79 55	98.52 10	98.24 34	93.19 78	97.14 41	98.34 41	91.59 54	99.87 7	95.46 65	99.59 15	99.64 10

PS-CasMVS		91.55 202	90.84 204	93.69 226	94.96 253	88.28 221	97.84 63	98.24 34	91.46 132	88.04 268	95.80 191	79.67 235	97.48 290	87.02 235	84.54 301	95.31 255

DU-MVS		92.90 155	92.04 160	95.49 147	94.95 254	92.83 80	97.16 134	98.24 34	93.02 83	90.13 207	95.71 199	83.47 162	97.85 256	91.71 142	83.93 308	95.78 228

9.14			96.75 33		98.93 47		97.73 73	98.23 38	91.28 142	97.88 22	98.44 28	93.00 21	99.65 53	95.76 51	99.47 36

testtj		96.93 33	96.56 43	98.05 17	99.10 34	94.66 27	97.78 68	98.22 39	92.74 97	97.59 24	98.20 57	91.96 44	99.86 8	94.21 93	99.25 65	99.63 11

ETH3 D test6400		96.16 61	95.52 68	98.07 16	98.90 51	95.06 22	97.03 140	98.21 40	88.16 231	96.64 55	97.70 89	91.18 63	99.67 49	92.44 125	99.47 36	99.48 41

D2MVS		91.30 218	90.95 198	92.35 271	94.71 268	85.52 277	96.18 221	98.21 40	88.89 206	86.60 293	93.82 284	79.92 231	97.95 246	89.29 187	90.95 232	93.56 317

XVS		97.18 16	96.96 18	97.81 30	99.38 14	94.03 50	98.59 7	98.20 42	94.85 24	96.59 58	98.29 50	91.70 50	99.80 27	95.66 52	99.40 45	99.62 13

X-MVStestdata		91.71 194	89.67 253	97.81 30	99.38 14	94.03 50	98.59 7	98.20 42	94.85 24	96.59 58	32.69 357	91.70 50	99.80 27	95.66 52	99.40 45	99.62 13

ACMMP_NAP		97.20 15	96.86 22	98.23 8	99.09 36	95.16 20	97.60 90	98.19 44	92.82 94	97.93 20	98.74 11	91.60 53	99.86 8	96.26 30	99.52 25	99.67 8

CP-MVSNet		91.89 190	91.24 190	93.82 219	95.05 249	88.57 214	97.82 64	98.19 44	91.70 125	88.21 264	95.76 196	81.96 197	97.52 288	87.86 211	84.65 297	95.37 252

ZNCC-MVS		96.96 30	96.67 38	97.85 25	99.37 16	94.12 45	98.49 14	98.18 46	92.64 101	96.39 68	98.18 58	91.61 52	99.88 4	95.59 62	99.55 21	99.57 19

SMA-MVS		97.35 12	97.03 14	98.30 6	99.06 40	95.42 8	97.94 54	98.18 46	90.57 166	98.85 7	98.94 1	93.33 17	99.83 22	96.72 18	99.68 4	99.63 11
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
PEN-MVS		91.20 222	90.44 219	93.48 235	94.49 276	87.91 234	97.76 69	98.18 46	91.29 139	87.78 273	95.74 198	80.35 222	97.33 301	85.46 259	82.96 318	95.19 265

DELS-MVS		96.61 48	96.38 51	97.30 57	97.79 120	93.19 72	95.96 232	98.18 46	95.23 12	95.87 85	97.65 94	91.45 55	99.70 43	95.87 47	99.44 42	99.00 89
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
tfpnnormal		89.70 266	88.40 271	93.60 229	95.15 244	90.10 165	97.56 93	98.16 50	87.28 257	86.16 297	94.63 246	77.57 270	98.05 229	74.48 330	84.59 300	92.65 329

VNet		95.89 68	95.45 71	97.21 65	98.07 107	92.94 79	97.50 97	98.15 51	93.87 51	97.52 25	97.61 100	85.29 140	99.53 88	95.81 50	95.27 168	99.16 70

DeepPCF-MVS	93.97 1	96.61 48	97.09 12	95.15 158	98.09 105	86.63 261	96.00 230	98.15 51	95.43 6	97.95 19	98.56 17	93.40 16	99.36 112	96.77 17	99.48 35	99.45 45

SD-MVS		97.41 9	97.53 6	97.06 71	98.57 72	94.46 30	97.92 56	98.14 53	94.82 28	99.01 3	98.55 19	94.18 11	97.41 297	96.94 10	99.64 11	99.32 60
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
GST-MVS		96.85 38	96.52 45	97.82 29	99.36 19	94.14 44	98.29 24	98.13 54	92.72 98	96.70 50	98.06 64	91.35 59	99.86 8	94.83 81	99.28 59	99.47 44

UA-Net		95.95 67	95.53 67	97.20 66	97.67 125	92.98 78	97.65 84	98.13 54	94.81 29	96.61 56	98.35 38	88.87 90	99.51 93	90.36 165	97.35 129	99.11 78

QAPM		93.45 135	92.27 156	96.98 74	96.77 163	92.62 87	98.39 19	98.12 56	84.50 298	88.27 262	97.77 85	82.39 190	99.81 26	85.40 260	98.81 89	98.51 124

Vis-MVSNet		95.23 84	94.81 86	96.51 88	97.18 141	91.58 120	98.26 27	98.12 56	94.38 42	94.90 109	98.15 59	82.28 191	98.92 151	91.45 150	98.58 98	99.01 87
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 157	91.68 173	96.40 96	95.34 230	92.73 83	98.27 26	98.12 56	84.86 293	85.78 299	97.75 86	78.89 251	99.74 31	87.50 226	98.65 95	96.73 198

TranMVSNet+NR-MVSNet		92.50 165	91.63 174	95.14 159	94.76 265	92.07 105	97.53 95	98.11 59	92.90 92	89.56 228	96.12 175	83.16 167	97.60 280	89.30 186	83.20 317	95.75 232

CPTT-MVS		95.57 76	95.19 79	96.70 77	99.27 26	91.48 122	98.33 21	98.11 59	87.79 242	95.17 106	98.03 66	87.09 118	99.61 62	93.51 109	99.42 43	99.02 83

Regformer-2		97.16 18	96.99 16	97.67 43	98.32 86	93.84 53	96.83 163	98.10 61	95.24 11	97.49 26	98.25 54	92.57 30	99.61 62	96.80 14	99.29 57	99.56 22

APD-MVS		96.95 31	96.60 40	98.01 19	99.03 42	94.93 24	97.72 76	98.10 61	91.50 130	98.01 18	98.32 46	92.33 35	99.58 70	94.85 79	99.51 29	99.53 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 37	96.60 40	97.64 46	99.40 11	93.44 65	98.50 13	98.09 63	93.27 74	95.95 84	98.33 44	91.04 66	99.88 4	95.20 68	99.57 20	99.60 16

ZD-MVS					99.05 41	94.59 28		98.08 64	89.22 195	97.03 47	98.10 60	92.52 32	99.65 53	94.58 89	99.31 55

zzz-MVS		97.07 22	96.77 32	97.97 22	99.37 16	94.42 32	97.15 136	98.08 64	95.07 19	96.11 75	98.59 15	90.88 70	99.90 1	96.18 39	99.50 32	99.58 17

MTGPA								98.08 64

MTAPA		97.08 21	96.78 31	97.97 22	99.37 16	94.42 32	97.24 123	98.08 64	95.07 19	96.11 75	98.59 15	90.88 70	99.90 1	96.18 39	99.50 32	99.58 17

CNVR-MVS		97.68 5	97.44 8	98.37 5	98.90 51	95.86 4	97.27 121	98.08 64	95.81 3	97.87 23	98.31 47	94.26 10	99.68 47	97.02 9	99.49 34	99.57 19

DP-MVS Recon		95.68 72	95.12 82	97.37 54	99.19 31	94.19 40	97.03 140	98.08 64	88.35 224	95.09 108	97.65 94	89.97 83	99.48 98	92.08 135	98.59 97	98.44 135

SR-MVS		97.01 28	96.86 22	97.47 51	99.09 36	93.27 71	97.98 48	98.07 70	93.75 56	97.45 28	98.48 25	91.43 56	99.59 67	96.22 33	99.27 61	99.54 29

MCST-MVS		97.18 16	96.84 25	98.20 10	99.30 24	95.35 12	97.12 138	98.07 70	93.54 65	96.08 77	97.69 90	93.86 13	99.71 38	96.50 24	99.39 47	99.55 26

NR-MVSNet		92.34 172	91.27 189	95.53 143	94.95 254	93.05 75	97.39 109	98.07 70	92.65 100	84.46 310	95.71 199	85.00 144	97.77 266	89.71 175	83.52 314	95.78 228

MP-MVS-pluss		96.70 44	96.27 53	97.98 21	99.23 30	94.71 26	96.96 151	98.06 73	90.67 157	95.55 99	98.78 10	91.07 65	99.86 8	96.58 22	99.55 21	99.38 56
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 40	96.71 36	97.12 69	99.01 46	92.31 97	97.98 48	98.06 73	93.11 81	97.44 29	98.55 19	90.93 68	99.55 83	96.06 41	99.25 65	99.51 34

MP-MVS		96.77 42	96.45 49	97.72 39	99.39 13	93.80 54	98.41 18	98.06 73	93.37 70	95.54 101	98.34 41	90.59 75	99.88 4	94.83 81	99.54 23	99.49 39
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 51	96.27 53	97.22 64	99.32 23	92.74 82	98.74 4	98.06 73	90.57 166	96.77 49	98.35 38	90.21 79	99.53 88	94.80 84	99.63 12	99.38 56

HPM-MVS		96.69 45	96.45 49	97.40 53	99.36 19	93.11 74	98.87 1	98.06 73	91.17 146	96.40 67	97.99 69	90.99 67	99.58 70	95.61 59	99.61 14	99.49 39
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 104	93.80 108	96.64 78	97.07 147	91.97 110	96.32 209	98.06 73	88.94 204	94.50 115	96.78 136	84.60 148	99.27 118	91.90 136	96.02 153	98.68 116

DeepC-MVS	93.07 3	96.06 62	95.66 65	97.29 58	97.96 109	93.17 73	97.30 119	98.06 73	93.92 50	93.38 139	98.66 12	86.83 120	99.73 32	95.60 61	99.22 68	98.96 91
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ETH3D cwj APD-0.16		96.56 50	96.06 58	98.05 17	98.26 92	95.19 18	96.99 148	98.05 80	89.85 180	97.26 35	98.22 56	91.80 47	99.69 44	94.84 80	99.28 59	99.27 66

test1172		96.93 33	96.86 22	97.15 67	99.10 34	92.34 94	97.96 53	98.04 81	93.79 55	97.35 33	98.53 21	91.40 57	99.56 80	96.30 29	99.30 56	99.55 26

NCCC		97.30 14	97.03 14	98.11 14	98.77 57	95.06 22	97.34 113	98.04 81	95.96 2	97.09 45	97.88 74	93.18 20	99.71 38	95.84 49	99.17 72	99.56 22

DeepC-MVS_fast	93.89 2	96.93 33	96.64 39	97.78 33	98.64 67	94.30 34	97.41 105	98.04 81	94.81 29	96.59 58	98.37 36	91.24 61	99.64 61	95.16 69	99.52 25	99.42 52
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 36	96.80 29	97.11 70	99.02 43	92.34 94	97.98 48	98.03 84	93.52 66	97.43 31	98.51 22	91.40 57	99.56 80	96.05 42	99.26 63	99.43 49

RE-MVS-def			96.72 35		99.02 43	92.34 94	97.98 48	98.03 84	93.52 66	97.43 31	98.51 22	90.71 73		96.05 42	99.26 63	99.43 49

abl_6		96.40 54	96.21 55	96.98 74	98.89 54	92.20 102	97.89 57	98.03 84	93.34 73	97.22 37	98.42 31	87.93 103	99.72 35	95.10 72	99.07 80	99.02 83

RPMNet		88.98 271	87.05 286	94.77 179	94.45 278	87.19 247	90.23 338	98.03 84	77.87 341	92.40 156	87.55 342	80.17 226	99.51 93	68.84 345	93.95 189	97.60 177

save fliter					98.91 49	94.28 35	97.02 143	98.02 88	95.35 8

TEST9					98.70 60	94.19 40	96.41 197	98.02 88	88.17 229	96.03 78	97.56 105	92.74 24	99.59 67

train_agg		96.30 57	95.83 63	97.72 39	98.70 60	94.19 40	96.41 197	98.02 88	88.58 217	96.03 78	97.56 105	92.73 25	99.59 67	95.04 73	99.37 52	99.39 54

test_8					98.67 62	94.06 49	96.37 204	98.01 91	88.58 217	95.98 83	97.55 107	92.73 25	99.58 70

Regformer-4		96.97 29	96.87 21	97.25 61	98.34 83	92.66 85	96.96 151	98.01 91	95.12 17	97.14 41	98.42 31	91.82 46	99.61 62	96.90 11	99.13 75	99.50 37

agg_prior1		96.22 60	95.77 64	97.56 48	98.67 62	93.79 55	96.28 213	98.00 93	88.76 214	95.68 93	97.55 107	92.70 27	99.57 78	95.01 74	99.32 53	99.32 60

agg_prior					98.67 62	93.79 55		98.00 93		95.68 93			99.57 78

test_prior3		96.46 53	96.20 56	97.23 62	98.67 62	92.99 76	96.35 205	98.00 93	92.80 95	96.03 78	97.59 101	92.01 41	99.41 106	95.01 74	99.38 48	99.29 62

test_prior				97.23 62	98.67 62	92.99 76		98.00 93					99.41 106			99.29 62

Regformer-1		97.10 20	96.96 18	97.54 49	98.32 86	93.48 64	96.83 163	97.99 97	95.20 13	97.46 27	98.25 54	92.48 34	99.58 70	96.79 16	99.29 57	99.55 26

WR-MVS		92.34 172	91.53 178	94.77 179	95.13 246	90.83 149	96.40 200	97.98 98	91.88 122	89.29 237	95.54 210	82.50 186	97.80 261	89.79 174	85.27 288	95.69 235

HPM-MVS++		97.34 13	96.97 17	98.47 3	99.08 38	96.16 2	97.55 94	97.97 99	95.59 4	96.61 56	97.89 72	92.57 30	99.84 19	95.95 46	99.51 29	99.40 53

CANet		96.39 55	96.02 59	97.50 50	97.62 128	93.38 67	97.02 143	97.96 100	95.42 7	94.86 110	97.81 82	87.38 114	99.82 25	96.88 12	99.20 70	99.29 62

114514_t		93.95 119	93.06 130	96.63 80	99.07 39	91.61 117	97.46 104	97.96 100	77.99 339	93.00 147	97.57 103	86.14 132	99.33 113	89.22 190	99.15 73	98.94 94

IU-MVS					99.42 6	95.39 9		97.94 102	90.40 170	98.94 5				97.41 7	99.66 8	99.74 5

CS-MVS		95.80 70	95.65 66	96.24 110	97.32 136	91.43 126	98.10 39	97.91 103	93.38 69	95.16 107	94.57 248	90.21 79	98.98 147	95.53 64	98.67 94	98.30 145

Anonymous20231211		90.63 246	89.42 257	94.27 198	98.24 93	89.19 202	98.05 44	97.89 104	79.95 331	88.25 263	94.96 227	72.56 300	98.13 213	89.70 176	85.14 290	95.49 239

原ACMM1				96.38 99	98.59 69	91.09 141		97.89 104	87.41 253	95.22 105	97.68 91	90.25 77	99.54 85	87.95 210	99.12 78	98.49 127

CDPH-MVS		95.97 66	95.38 74	97.77 35	98.93 47	94.44 31	96.35 205	97.88 106	86.98 261	96.65 54	97.89 72	91.99 43	99.47 99	92.26 126	99.46 38	99.39 54

test11								97.88 106

EIA-MVS		95.53 77	95.47 70	95.71 133	97.06 150	89.63 177	97.82 64	97.87 108	93.57 61	93.92 127	95.04 226	90.61 74	98.95 149	94.62 88	98.68 93	98.54 120

无先验							95.79 240	97.87 108	83.87 306				99.65 53	87.68 219		98.89 100

3Dnovator+	91.43 4	95.40 78	94.48 98	98.16 12	96.90 156	95.34 13	98.48 15	97.87 108	94.65 36	88.53 256	98.02 67	83.69 160	99.71 38	93.18 117	98.96 85	99.44 47

VPNet		92.23 180	91.31 186	94.99 164	95.56 217	90.96 144	97.22 129	97.86 111	92.96 90	90.96 190	96.62 153	75.06 287	98.20 206	91.90 136	83.65 313	95.80 227

DVP-MVS		97.91 2	97.81 2	98.22 9	99.45 2	95.36 10	98.21 34	97.85 112	94.92 22	98.73 8	98.87 6	95.08 5	99.84 19	97.52 2	99.67 6	99.48 41
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
TSAR-MVS + MP.		97.42 8	97.33 9	97.69 42	99.25 27	94.24 39	98.07 43	97.85 112	93.72 57	98.57 11	98.35 38	93.69 15	99.40 108	97.06 8	99.46 38	99.44 47
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
AdaColmap		94.34 106	93.68 112	96.31 103	98.59 69	91.68 116	96.59 188	97.81 114	89.87 177	92.15 165	97.06 126	83.62 161	99.54 85	89.34 185	98.07 109	97.70 170

ETV-MVS		96.02 64	95.89 62	96.40 96	97.16 142	92.44 92	97.47 102	97.77 115	94.55 37	96.48 63	94.51 250	91.23 62	98.92 151	95.65 55	98.19 105	97.82 166

Regformer-3		96.85 38	96.80 29	97.01 72	98.34 83	92.02 108	96.96 151	97.76 116	95.01 21	97.08 46	98.42 31	91.71 49	99.54 85	96.80 14	99.13 75	99.48 41

新几何1				97.32 56	98.60 68	93.59 61		97.75 117	81.58 322	95.75 90	97.85 78	90.04 82	99.67 49	86.50 241	99.13 75	98.69 115

旧先验1					98.38 81	93.38 67		97.75 117			98.09 62	92.30 38			99.01 83	99.16 70

EI-MVSNet-Vis-set		96.51 51	96.47 47	96.63 80	98.24 93	91.20 135	96.89 158	97.73 119	94.74 33	96.49 62	98.49 24	90.88 70	99.58 70	96.44 27	98.32 102	99.13 74

1121		94.71 102	93.83 107	97.34 55	98.57 72	93.64 60	96.04 226	97.73 119	81.56 323	95.68 93	97.85 78	90.23 78	99.65 53	87.68 219	99.12 78	98.73 111

PAPM_NR		95.01 89	94.59 92	96.26 108	98.89 54	90.68 154	97.24 123	97.73 119	91.80 123	92.93 152	96.62 153	89.13 88	99.14 130	89.21 191	97.78 116	98.97 90

Anonymous20240529		91.98 188	90.73 209	95.73 132	98.14 103	89.40 190	97.99 47	97.72 122	79.63 333	93.54 134	97.41 111	69.94 317	99.56 80	91.04 156	91.11 228	98.22 146

CHOSEN 280x420		93.12 144	92.72 140	94.34 196	96.71 166	87.27 243	90.29 337	97.72 122	86.61 268	91.34 179	95.29 217	84.29 154	98.41 191	93.25 116	98.94 86	97.35 184

EI-MVSNet-UG-set		96.34 56	96.30 52	96.47 91	98.20 98	90.93 146	96.86 159	97.72 122	94.67 34	96.16 74	98.46 26	90.43 76	99.58 70	96.23 32	97.96 112	98.90 98

LS3D		93.57 132	92.61 144	96.47 91	97.59 131	91.61 117	97.67 81	97.72 122	85.17 288	90.29 200	98.34 41	84.60 148	99.73 32	83.85 279	98.27 103	98.06 154

PAPR		94.18 109	93.42 124	96.48 90	97.64 127	91.42 127	95.55 248	97.71 126	88.99 201	92.34 161	95.82 190	89.19 86	99.11 132	86.14 247	97.38 127	98.90 98

test_part1		92.21 182	91.10 196	95.51 144	97.80 119	92.66 85	98.02 46	97.68 127	89.79 183	88.80 250	96.02 180	76.85 274	98.18 209	90.86 157	84.11 306	95.69 235

UGNet		94.04 117	93.28 127	96.31 103	96.85 157	91.19 136	97.88 58	97.68 127	94.40 40	93.00 147	96.18 172	73.39 299	99.61 62	91.72 141	98.46 99	98.13 149
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
testdata				95.46 151	98.18 102	88.90 208		97.66 129	82.73 315	97.03 47	98.07 63	90.06 81	98.85 157	89.67 177	98.98 84	98.64 117

test12				97.65 44	98.46 74	94.26 37		97.66 129		95.52 102		90.89 69	99.46 100		99.25 65	99.22 67

DTE-MVSNet		90.56 247	89.75 251	93.01 253	93.95 291	87.25 244	97.64 88	97.65 131	90.74 154	87.12 284	95.68 202	79.97 230	97.00 312	83.33 280	81.66 323	94.78 291

TAPA-MVS	90.10 7	92.30 175	91.22 192	95.56 140	98.33 85	89.60 179	96.79 167	97.65 131	81.83 320	91.52 175	97.23 118	87.94 102	98.91 153	71.31 341	98.37 101	98.17 148
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
cdsmvs_eth3d_5k		23.24 329	30.99 331	0.00 345	0.00 366	0.00 367	0.00 357	97.63 133	0.00 362	0.00 363	96.88 134	84.38 151	0.00 363	0.00 361	0.00 361	0.00 359

DPM-MVS		95.69 71	94.92 84	98.01 19	98.08 106	95.71 7	95.27 262	97.62 134	90.43 169	95.55 99	97.07 125	91.72 48	99.50 96	89.62 179	98.94 86	98.82 106

canonicalmvs		96.02 64	95.45 71	97.75 37	97.59 131	95.15 21	98.28 25	97.60 135	94.52 38	96.27 71	96.12 175	87.65 107	99.18 125	96.20 38	94.82 176	98.91 97

test222					98.24 93	92.21 100	95.33 257	97.60 135	79.22 335	95.25 104	97.84 81	88.80 92			99.15 73	98.72 112

cascas		91.20 222	90.08 236	94.58 187	94.97 252	89.16 203	93.65 305	97.59 137	79.90 332	89.40 232	92.92 303	75.36 286	98.36 195	92.14 131	94.75 178	96.23 207

MVSFormer		95.37 79	95.16 80	95.99 120	96.34 186	91.21 133	98.22 32	97.57 138	91.42 134	96.22 72	97.32 113	86.20 130	97.92 250	94.07 96	99.05 81	98.85 103

test_djsdf		93.07 146	92.76 136	94.00 207	93.49 306	88.70 212	98.22 32	97.57 138	91.42 134	90.08 213	95.55 209	82.85 178	97.92 250	94.07 96	91.58 220	95.40 249

OMC-MVS		95.09 88	94.70 90	96.25 109	98.46 74	91.28 129	96.43 195	97.57 138	92.04 118	94.77 112	97.96 71	87.01 119	99.09 136	91.31 152	96.77 141	98.36 142

PS-MVSNAJss		93.74 126	93.51 118	94.44 190	93.91 293	89.28 198	97.75 70	97.56 141	92.50 103	89.94 215	96.54 156	88.65 94	98.18 209	93.83 105	90.90 233	95.86 221

jajsoiax		92.42 169	91.89 167	94.03 206	93.33 311	88.50 217	97.73 73	97.53 142	92.00 120	88.85 247	96.50 158	75.62 285	98.11 217	93.88 103	91.56 221	95.48 240

mvs_tets		92.31 174	91.76 169	93.94 214	93.41 308	88.29 220	97.63 89	97.53 142	92.04 118	88.76 251	96.45 160	74.62 289	98.09 222	93.91 101	91.48 222	95.45 245

HQP_MVS		93.78 125	93.43 122	94.82 173	96.21 190	89.99 169	97.74 71	97.51 144	94.85 24	91.34 179	96.64 146	81.32 207	98.60 179	93.02 120	92.23 208	95.86 221

plane_prior5								97.51 144					98.60 179	93.02 120	92.23 208	95.86 221

PS-MVSNAJ		95.37 79	95.33 76	95.49 147	97.35 135	90.66 155	95.31 259	97.48 146	93.85 52	96.51 61	95.70 201	88.65 94	99.65 53	94.80 84	98.27 103	96.17 210

API-MVS		94.84 98	94.49 97	95.90 123	97.90 115	92.00 109	97.80 66	97.48 146	89.19 196	94.81 111	96.71 139	88.84 91	99.17 126	88.91 197	98.76 91	96.53 201

MG-MVS		95.61 74	95.38 74	96.31 103	98.42 77	90.53 157	96.04 226	97.48 146	93.47 68	95.67 96	98.10 60	89.17 87	99.25 119	91.27 153	98.77 90	99.13 74

MAR-MVS		94.22 108	93.46 120	96.51 88	98.00 108	92.19 103	97.67 81	97.47 149	88.13 233	93.00 147	95.84 188	84.86 146	99.51 93	87.99 209	98.17 107	97.83 165
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
CLD-MVS		92.98 150	92.53 148	94.32 197	96.12 199	89.20 200	95.28 260	97.47 149	92.66 99	89.90 216	95.62 204	80.58 217	98.40 192	92.73 123	92.40 206	95.38 251
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 216	90.22 232	94.68 182	94.86 261	87.86 235	97.23 128	97.46 151	87.99 234	89.90 216	96.92 132	66.35 333	98.23 202	90.30 166	90.99 231	97.96 155

nrg030		94.05 116	93.31 126	96.27 107	95.22 241	94.59 28	98.34 20	97.46 151	92.93 91	91.21 188	96.64 146	87.23 117	98.22 203	94.99 77	85.80 281	95.98 219

RRT_test8_iter05		91.19 225	90.78 206	92.41 270	95.76 212	83.14 306	97.32 116	97.46 151	91.37 138	89.07 243	95.57 206	70.33 312	98.21 204	93.56 107	86.62 275	95.89 220

XVG-OURS		93.72 127	93.35 125	94.80 177	97.07 147	88.61 213	94.79 270	97.46 151	91.97 121	93.99 124	97.86 77	81.74 202	98.88 156	92.64 124	92.67 203	96.92 192

LPG-MVS_test		92.94 153	92.56 145	94.10 202	96.16 195	88.26 222	97.65 84	97.46 151	91.29 139	90.12 209	97.16 120	79.05 244	98.73 167	92.25 128	91.89 216	95.31 255

LGP-MVS_train				94.10 202	96.16 195	88.26 222		97.46 151	91.29 139	90.12 209	97.16 120	79.05 244	98.73 167	92.25 128	91.89 216	95.31 255

MVS		91.71 194	90.44 219	95.51 144	95.20 243	91.59 119	96.04 226	97.45 157	73.44 346	87.36 281	95.60 205	85.42 139	99.10 133	85.97 252	97.46 122	95.83 225

XVG-OURS-SEG-HR		93.86 122	93.55 115	94.81 175	97.06 150	88.53 216	95.28 260	97.45 157	91.68 126	94.08 123	97.68 91	82.41 189	98.90 154	93.84 104	92.47 205	96.98 188

baseline		95.58 75	95.42 73	96.08 114	96.78 162	90.41 162	97.16 134	97.45 157	93.69 60	95.65 97	97.85 78	87.29 115	98.68 172	95.66 52	97.25 133	99.13 74

ab-mvs		93.57 132	92.55 146	96.64 78	97.28 137	91.96 111	95.40 254	97.45 157	89.81 182	93.22 145	96.28 169	79.62 237	99.46 100	90.74 160	93.11 197	98.50 125

xiu_mvs_v2_base		95.32 81	95.29 77	95.40 152	97.22 138	90.50 158	95.44 253	97.44 161	93.70 59	96.46 65	96.18 172	88.59 97	99.53 88	94.79 86	97.81 115	96.17 210

1314		92.81 161	92.03 161	95.14 159	95.33 233	89.52 185	96.04 226	97.44 161	87.72 246	86.25 296	95.33 216	83.84 158	98.79 161	89.26 188	97.05 138	97.11 186

casdiffmvs		95.64 73	95.49 69	96.08 114	96.76 165	90.45 160	97.29 120	97.44 161	94.00 48	95.46 103	97.98 70	87.52 111	98.73 167	95.64 56	97.33 130	99.08 80

XXY-MVS		92.16 183	91.23 191	94.95 169	94.75 266	90.94 145	97.47 102	97.43 164	89.14 197	88.90 244	96.43 161	79.71 234	98.24 201	89.56 180	87.68 263	95.67 237

anonymousdsp		92.16 183	91.55 177	93.97 210	92.58 323	89.55 182	97.51 96	97.42 165	89.42 190	88.40 257	94.84 234	80.66 216	97.88 255	91.87 138	91.28 226	94.48 299

Effi-MVS+		94.93 94	94.45 99	96.36 101	96.61 167	91.47 123	96.41 197	97.41 166	91.02 151	94.50 115	95.92 184	87.53 110	98.78 162	93.89 102	96.81 140	98.84 105

HQP3-MVS								97.39 167							92.10 213

HQP-MVS		93.19 143	92.74 139	94.54 188	95.86 205	89.33 194	96.65 179	97.39 167	93.55 62	90.14 203	95.87 186	80.95 210	98.50 186	92.13 132	92.10 213	95.78 228

PLC	91.00 6	94.11 113	93.43 122	96.13 113	98.58 71	91.15 140	96.69 176	97.39 167	87.29 256	91.37 178	96.71 139	88.39 98	99.52 92	87.33 229	97.13 137	97.73 168
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 239	89.86 244	93.45 238	93.54 303	87.60 240	97.70 79	97.37 170	88.85 207	87.65 275	94.08 276	81.08 209	98.10 218	84.68 268	83.79 312	94.66 296

UnsupCasMVSNet_eth		85.99 300	84.45 304	90.62 308	89.97 339	82.40 312	93.62 306	97.37 170	89.86 178	78.59 340	92.37 311	65.25 339	95.35 336	82.27 291	70.75 344	94.10 310

ACMM	89.79 8	92.96 151	92.50 150	94.35 195	96.30 188	88.71 211	97.58 91	97.36 172	91.40 137	90.53 194	96.65 145	79.77 233	98.75 166	91.24 154	91.64 218	95.59 238
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 89	94.76 87	95.75 129	96.58 170	91.71 113	96.25 215	97.35 173	92.99 84	96.70 50	96.63 150	82.67 181	99.44 103	96.22 33	97.46 122	96.11 215

xiu_mvs_v1_base		95.01 89	94.76 87	95.75 129	96.58 170	91.71 113	96.25 215	97.35 173	92.99 84	96.70 50	96.63 150	82.67 181	99.44 103	96.22 33	97.46 122	96.11 215

xiu_mvs_v1_base_debi		95.01 89	94.76 87	95.75 129	96.58 170	91.71 113	96.25 215	97.35 173	92.99 84	96.70 50	96.63 150	82.67 181	99.44 103	96.22 33	97.46 122	96.11 215

diffmvs		95.25 83	95.13 81	95.63 136	96.43 182	89.34 193	95.99 231	97.35 173	92.83 93	96.31 69	97.37 112	86.44 125	98.67 173	96.26 30	97.19 135	98.87 102

WTY-MVS		94.71 102	94.02 104	96.79 76	97.71 124	92.05 106	96.59 188	97.35 173	90.61 163	94.64 113	96.93 129	86.41 126	99.39 109	91.20 155	94.71 180	98.94 94

F-COLMAP		93.58 131	92.98 131	95.37 153	98.40 78	88.98 206	97.18 132	97.29 178	87.75 245	90.49 195	97.10 124	85.21 141	99.50 96	86.70 238	96.72 144	97.63 172

XVG-ACMP-BASELINE		90.93 235	90.21 233	93.09 251	94.31 284	85.89 272	95.33 257	97.26 179	91.06 150	89.38 233	95.44 214	68.61 321	98.60 179	89.46 182	91.05 229	94.79 289

PCF-MVS	89.48 11	91.56 201	89.95 241	96.36 101	96.60 168	92.52 90	92.51 324	97.26 179	79.41 334	88.90 244	96.56 155	84.04 157	99.55 83	77.01 324	97.30 131	97.01 187
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 164	92.14 158	94.05 205	96.40 183	88.20 225	97.36 112	97.25 181	91.52 129	88.30 260	96.64 146	78.46 256	98.72 170	91.86 139	91.48 222	95.23 263
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
xxxxxxxxxxxxxcwj		97.36 11	97.20 10	97.83 26	98.91 49	94.28 35	97.02 143	97.22 182	95.35 8	98.27 14	98.65 13	93.33 17	99.72 35	96.49 25	99.52 25	99.51 34

OPM-MVS		93.28 139	92.76 136	94.82 173	94.63 272	90.77 152	96.65 179	97.18 183	93.72 57	91.68 173	97.26 116	79.33 241	98.63 176	92.13 132	92.28 207	95.07 267

PatchMatch-RL		92.90 155	92.02 162	95.56 140	98.19 100	90.80 150	95.27 262	97.18 183	87.96 235	91.86 172	95.68 202	80.44 220	98.99 146	84.01 275	97.54 121	96.89 193

MVS_0304		88.79 276	87.57 278	92.46 267	94.65 270	86.15 271	96.40 200	97.17 185	86.44 269	88.02 269	91.71 323	56.68 349	97.03 308	84.47 271	92.58 204	94.19 309

alignmvs		95.87 69	95.23 78	97.78 33	97.56 133	95.19 18	97.86 59	97.17 185	94.39 41	96.47 64	96.40 164	85.89 133	99.20 122	96.21 37	95.11 172	98.95 93

MVS_Test		94.89 96	94.62 91	95.68 134	96.83 160	89.55 182	96.70 174	97.17 185	91.17 146	95.60 98	96.11 178	87.87 104	98.76 165	93.01 122	97.17 136	98.72 112

Fast-Effi-MVS+		93.46 134	92.75 138	95.59 139	96.77 163	90.03 166	96.81 166	97.13 188	88.19 227	91.30 182	94.27 266	86.21 129	98.63 176	87.66 221	96.46 151	98.12 150

EI-MVSNet		93.03 148	92.88 134	93.48 235	95.77 210	86.98 252	96.44 193	97.12 189	90.66 159	91.30 182	97.64 97	86.56 122	98.05 229	89.91 170	90.55 237	95.41 246

MVSTER		93.20 142	92.81 135	94.37 194	96.56 173	89.59 180	97.06 139	97.12 189	91.24 143	91.30 182	95.96 182	82.02 196	98.05 229	93.48 110	90.55 237	95.47 242

test_yl		94.78 100	94.23 102	96.43 94	97.74 122	91.22 131	96.85 160	97.10 191	91.23 144	95.71 91	96.93 129	84.30 152	99.31 115	93.10 118	95.12 170	98.75 108

DCV-MVSNet		94.78 100	94.23 102	96.43 94	97.74 122	91.22 131	96.85 160	97.10 191	91.23 144	95.71 91	96.93 129	84.30 152	99.31 115	93.10 118	95.12 170	98.75 108

LTVRE_ROB	88.41 13	90.99 231	89.92 242	94.19 199	96.18 193	89.55 182	96.31 210	97.09 193	87.88 238	85.67 300	95.91 185	78.79 252	98.57 182	81.50 294	89.98 243	94.44 301
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
v10		91.04 229	90.23 230	93.49 234	94.12 287	88.16 228	97.32 116	97.08 194	88.26 226	88.29 261	94.22 271	82.17 194	97.97 240	86.45 242	84.12 305	94.33 304

v144192		91.06 228	90.28 226	93.39 239	93.66 301	87.23 246	96.83 163	97.07 195	87.43 252	89.69 223	94.28 265	81.48 205	98.00 236	87.18 233	84.92 296	94.93 275

v1192		91.07 227	90.23 230	93.58 231	93.70 299	87.82 236	96.73 171	97.07 195	87.77 243	89.58 226	94.32 263	80.90 214	97.97 240	86.52 240	85.48 284	94.95 271

v8		91.29 219	90.53 218	93.57 232	94.15 286	88.12 229	97.34 113	97.06 197	88.99 201	88.32 259	94.26 268	83.08 170	98.01 235	87.62 223	83.92 310	94.57 298

mvs_anonymous		93.82 123	93.74 109	94.06 204	96.44 181	85.41 279	95.81 239	97.05 198	89.85 180	90.09 212	96.36 166	87.44 113	97.75 267	93.97 98	96.69 145	99.02 83

IterMVS-LS		92.29 176	91.94 165	93.34 242	96.25 189	86.97 253	96.57 191	97.05 198	90.67 157	89.50 231	94.80 237	86.59 121	97.64 275	89.91 170	86.11 279	95.40 249
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 237	90.03 240	93.29 244	93.55 302	86.96 254	96.74 170	97.04 200	87.36 254	89.52 230	94.34 260	80.23 225	97.97 240	86.27 243	85.21 289	94.94 273

CDS-MVSNet		94.14 112	93.54 116	95.93 121	96.18 193	91.46 124	96.33 208	97.04 200	88.97 203	93.56 132	96.51 157	87.55 109	97.89 254	89.80 173	95.95 155	98.44 135
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 213	90.60 213	93.68 227	93.89 294	88.23 224	96.84 162	97.03 202	88.37 223	89.69 223	94.39 257	82.04 195	97.98 237	87.80 213	85.37 286	94.84 281

v1240		90.70 244	89.85 245	93.23 246	93.51 305	86.80 255	96.61 185	97.02 203	87.16 259	89.58 226	94.31 264	79.55 238	97.98 237	85.52 258	85.44 285	94.90 278

EPP-MVSNet		95.22 85	95.04 83	95.76 127	97.49 134	89.56 181	98.67 5	97.00 204	90.69 156	94.24 120	97.62 99	89.79 85	98.81 160	93.39 114	96.49 149	98.92 96

V42		91.58 200	90.87 200	93.73 222	94.05 290	88.50 217	97.32 116	96.97 205	88.80 213	89.71 221	94.33 261	82.54 185	98.05 229	89.01 195	85.07 292	94.64 297

FMVSNet2		91.31 217	90.08 236	94.99 164	96.51 176	92.21 100	97.41 105	96.95 206	88.82 210	88.62 253	94.75 239	73.87 293	97.42 296	85.20 263	88.55 257	95.35 253

ACMH	87.59 16	90.53 248	89.42 257	93.87 217	96.21 190	87.92 232	97.24 123	96.94 207	88.45 221	83.91 319	96.27 170	71.92 301	98.62 178	84.43 272	89.43 248	95.05 269
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 214	90.27 227	94.59 183	96.51 176	91.18 137	97.50 97	96.93 208	88.82 210	89.35 234	94.51 250	73.87 293	97.29 303	86.12 248	88.82 252	95.31 255

test1		91.35 214	90.27 227	94.59 183	96.51 176	91.18 137	97.50 97	96.93 208	88.82 210	89.35 234	94.51 250	73.87 293	97.29 303	86.12 248	88.82 252	95.31 255

FMVSNet3		91.78 192	90.69 211	95.03 163	96.53 175	92.27 99	97.02 143	96.93 208	89.79 183	89.35 234	94.65 245	77.01 273	97.47 291	86.12 248	88.82 252	95.35 253

FMVSNet1		89.88 263	88.31 272	94.59 183	95.41 223	91.18 137	97.50 97	96.93 208	86.62 267	87.41 279	94.51 250	65.94 337	97.29 303	83.04 283	87.43 266	95.31 255

miper_enhance_ethall		91.54 204	91.01 197	93.15 249	95.35 229	87.07 251	93.97 295	96.90 212	86.79 265	89.17 241	93.43 299	86.55 123	97.64 275	89.97 169	86.93 270	94.74 293

eth_miper_zixun_eth		91.02 230	90.59 214	92.34 272	95.33 233	84.35 292	94.10 292	96.90 212	88.56 219	88.84 248	94.33 261	84.08 156	97.60 280	88.77 200	84.37 303	95.06 268

TAMVS		94.01 118	93.46 120	95.64 135	96.16 195	90.45 160	96.71 173	96.89 214	89.27 194	93.46 137	96.92 132	87.29 115	97.94 247	88.70 201	95.74 160	98.53 121

miper_ehance_all_eth		91.59 198	91.13 195	92.97 255	95.55 218	86.57 262	94.47 277	96.88 215	87.77 243	88.88 246	94.01 277	86.22 128	97.54 284	89.49 181	86.93 270	94.79 289

v2v482		91.59 198	90.85 203	93.80 220	93.87 295	88.17 227	96.94 154	96.88 215	89.54 186	89.53 229	94.90 231	81.70 203	98.02 234	89.25 189	85.04 294	95.20 264

CNLPA		94.28 107	93.53 117	96.52 85	98.38 81	92.55 89	96.59 188	96.88 215	90.13 174	91.91 170	97.24 117	85.21 141	99.09 136	87.64 222	97.83 114	97.92 158

RRT_MVS		93.21 141	92.32 155	95.91 122	94.92 256	94.15 43	96.92 155	96.86 218	91.42 134	91.28 185	96.43 161	79.66 236	98.10 218	93.29 115	90.06 242	95.46 243

PAPM		91.52 205	90.30 225	95.20 156	95.30 236	89.83 175	93.38 310	96.85 219	86.26 272	88.59 254	95.80 191	84.88 145	98.15 212	75.67 328	95.93 156	97.63 172

cl_fuxian		91.38 211	90.89 199	92.88 258	95.58 216	86.30 265	94.68 272	96.84 220	88.17 229	88.83 249	94.23 269	85.65 137	97.47 291	89.36 184	84.63 298	94.89 279

pm-mvs1		90.72 243	89.65 255	93.96 211	94.29 285	89.63 177	97.79 67	96.82 221	89.07 198	86.12 298	95.48 213	78.61 254	97.78 264	86.97 236	81.67 322	94.46 300

CMPMVS	62.92 21	85.62 304	84.92 301	87.74 324	89.14 344	73.12 348	94.17 290	96.80 222	73.98 344	73.65 345	94.93 229	66.36 332	97.61 279	83.95 277	91.28 226	92.48 332
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 253	89.77 249	91.78 286	94.33 282	84.72 290	95.55 248	96.73 223	86.17 274	86.36 295	95.28 219	71.28 306	97.80 261	84.09 274	98.14 108	92.81 326

Effi-MVS+-dtu		93.08 145	93.21 128	92.68 265	96.02 202	83.25 305	97.14 137	96.72 224	93.85 52	91.20 189	93.44 297	83.08 170	98.30 199	91.69 144	95.73 161	96.50 203

mvs-test1		93.63 129	93.69 111	93.46 237	96.02 202	84.61 291	97.24 123	96.72 224	93.85 52	92.30 162	95.76 196	83.08 170	98.89 155	91.69 144	96.54 148	96.87 194

TSAR-MVS + GP.		96.69 45	96.49 46	97.27 60	98.31 88	93.39 66	96.79 167	96.72 224	94.17 45	97.44 29	97.66 93	92.76 23	99.33 113	96.86 13	97.76 118	99.08 80

1112_ss		93.37 136	92.42 152	96.21 111	97.05 152	90.99 142	96.31 210	96.72 224	86.87 264	89.83 219	96.69 143	86.51 124	99.14 130	88.12 207	93.67 191	98.50 125

PVSNet	86.66 18	92.24 179	91.74 172	93.73 222	97.77 121	83.69 302	92.88 318	96.72 224	87.91 237	93.00 147	94.86 233	78.51 255	99.05 142	86.53 239	97.45 126	98.47 130

miper_lstm_enhance		90.50 250	90.06 239	91.83 282	95.33 233	83.74 298	93.86 298	96.70 229	87.56 250	87.79 272	93.81 285	83.45 164	96.92 314	87.39 227	84.62 299	94.82 284

v148		90.99 231	90.38 221	92.81 261	93.83 296	85.80 273	96.78 169	96.68 230	89.45 189	88.75 252	93.93 281	82.96 176	97.82 260	87.83 212	83.25 315	94.80 287

ACMH+	87.92 14	90.20 256	89.18 262	93.25 245	96.48 179	86.45 263	96.99 148	96.68 230	88.83 209	84.79 309	96.22 171	70.16 315	98.53 184	84.42 273	88.04 259	94.77 292

CANet_DTU		94.37 105	93.65 113	96.55 84	96.46 180	92.13 104	96.21 219	96.67 232	94.38 42	93.53 135	97.03 127	79.34 240	99.71 38	90.76 159	98.45 100	97.82 166

cl-mvsnet_		90.96 234	90.32 223	92.89 257	95.37 227	86.21 268	94.46 279	96.64 233	87.82 239	88.15 266	94.18 272	82.98 174	97.54 284	87.70 216	85.59 282	94.92 277

HY-MVS	89.66 9	93.87 121	92.95 132	96.63 80	97.10 146	92.49 91	95.64 246	96.64 233	89.05 199	93.00 147	95.79 194	85.77 136	99.45 102	89.16 194	94.35 182	97.96 155

Test_1112_low_res		92.84 159	91.84 168	95.85 125	97.04 153	89.97 172	95.53 250	96.64 233	85.38 284	89.65 225	95.18 221	85.86 134	99.10 133	87.70 216	93.58 196	98.49 127

cl-mvsnet1		90.97 233	90.33 222	92.88 258	95.36 228	86.19 269	94.46 279	96.63 236	87.82 239	88.18 265	94.23 269	82.99 173	97.53 286	87.72 214	85.57 283	94.93 275

Fast-Effi-MVS+-dtu		92.29 176	91.99 163	93.21 248	95.27 237	85.52 277	97.03 140	96.63 236	92.09 116	89.11 242	95.14 223	80.33 223	98.08 223	87.54 225	94.74 179	96.03 218

UnsupCasMVSNet_bld		82.13 315	79.46 318	90.14 314	88.00 348	82.47 310	90.89 335	96.62 238	78.94 336	75.61 342	84.40 345	56.63 350	96.31 322	77.30 321	66.77 348	91.63 338

cl-mvsnet2		91.21 221	90.56 217	93.14 250	96.09 201	86.80 255	94.41 281	96.58 239	87.80 241	88.58 255	93.99 279	80.85 215	97.62 278	89.87 172	86.93 270	94.99 270

jason		94.84 98	94.39 101	96.18 112	95.52 219	90.93 146	96.09 224	96.52 240	89.28 193	96.01 82	97.32 113	84.70 147	98.77 164	95.15 70	98.91 88	98.85 103
jason: jason.
AUN-MVS		91.76 193	90.75 208	94.81 175	97.00 154	88.57 214	96.65 179	96.49 241	89.63 185	92.15 165	96.12 175	78.66 253	98.50 186	90.83 158	79.18 330	97.36 183

EG-PatchMatch MVS		87.02 292	85.44 296	91.76 288	92.67 321	85.00 285	96.08 225	96.45 242	83.41 311	79.52 337	93.49 295	57.10 348	97.72 269	79.34 313	90.87 234	92.56 330

DIV-MVS_2432*1600		85.95 301	84.95 300	88.96 319	89.55 343	79.11 337	95.13 267	96.42 243	85.91 277	84.07 317	90.48 327	70.03 316	94.82 338	80.04 305	72.94 342	92.94 324

pmmvs6		87.81 287	86.19 291	92.69 264	91.32 332	86.30 265	97.34 113	96.41 244	80.59 330	84.05 318	94.37 259	67.37 328	97.67 272	84.75 267	79.51 329	94.09 312

PMMVS		92.86 157	92.34 153	94.42 193	94.92 256	86.73 257	94.53 276	96.38 245	84.78 295	94.27 119	95.12 225	83.13 169	98.40 192	91.47 149	96.49 149	98.12 150

RPSCF		90.75 241	90.86 201	90.42 311	96.84 158	76.29 343	95.61 247	96.34 246	83.89 304	91.38 177	97.87 75	76.45 277	98.78 162	87.16 234	92.23 208	96.20 208

MSDG		91.42 209	90.24 229	94.96 168	97.15 144	88.91 207	93.69 303	96.32 247	85.72 280	86.93 290	96.47 159	80.24 224	98.98 147	80.57 302	95.05 173	96.98 188

OurMVSNet-221017-0		90.51 249	90.19 234	91.44 294	93.41 308	81.25 318	96.98 150	96.28 248	91.68 126	86.55 294	96.30 168	74.20 292	97.98 237	88.96 196	87.40 268	95.09 266

MVP-Stereo		90.74 242	90.08 236	92.71 263	93.19 313	88.20 225	95.86 236	96.27 249	86.07 275	84.86 308	94.76 238	77.84 268	97.75 267	83.88 278	98.01 110	92.17 336
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 93	94.56 93	96.29 106	96.34 186	91.21 133	95.83 238	96.27 249	88.93 205	96.22 72	96.88 134	86.20 130	98.85 157	95.27 67	99.05 81	98.82 106

BH-untuned		92.94 153	92.62 143	93.92 216	97.22 138	86.16 270	96.40 200	96.25 251	90.06 175	89.79 220	96.17 174	83.19 166	98.35 196	87.19 232	97.27 132	97.24 185

CL-MVSNet_2432*1600		86.31 297	85.15 299	89.80 317	88.83 345	81.74 316	93.93 297	96.22 252	86.67 266	85.03 306	90.80 326	78.09 264	94.50 339	74.92 329	71.86 343	93.15 322

IS-MVSNet		94.90 95	94.52 96	96.05 117	97.67 125	90.56 156	98.44 16	96.22 252	93.21 75	93.99 124	97.74 87	85.55 138	98.45 190	89.98 168	97.86 113	99.14 73

GA-MVS		91.38 211	90.31 224	94.59 183	94.65 270	87.62 239	94.34 284	96.19 254	90.73 155	90.35 199	93.83 282	71.84 302	97.96 244	87.22 231	93.61 194	98.21 147

IterMVS-SCA-FT		90.31 252	89.81 247	91.82 283	95.52 219	84.20 295	94.30 286	96.15 255	90.61 163	87.39 280	94.27 266	75.80 282	96.44 320	87.34 228	86.88 274	94.82 284

IterMVS		90.15 258	89.67 253	91.61 290	95.48 221	83.72 299	94.33 285	96.12 256	89.99 176	87.31 283	94.15 274	75.78 284	96.27 323	86.97 236	86.89 273	94.83 282
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 162	91.51 181	96.52 85	98.77 57	90.99 142	97.38 111	96.08 257	82.38 316	89.29 237	97.87 75	83.77 159	99.69 44	81.37 299	96.69 145	98.89 100

pmmvs4		90.93 235	89.85 245	94.17 200	93.34 310	90.79 151	94.60 273	96.02 258	84.62 296	87.45 277	95.15 222	81.88 200	97.45 293	87.70 216	87.87 261	94.27 308

ppachtmachnet_test		88.35 282	87.29 281	91.53 291	92.45 325	83.57 303	93.75 301	95.97 259	84.28 299	85.32 305	94.18 272	79.00 250	96.93 313	75.71 327	84.99 295	94.10 310

ITE_SJBPF				92.43 269	95.34 230	85.37 280		95.92 260	91.47 131	87.75 274	96.39 165	71.00 308	97.96 244	82.36 290	89.86 245	93.97 313

USDC		88.94 272	87.83 277	92.27 273	94.66 269	84.96 286	93.86 298	95.90 261	87.34 255	83.40 321	95.56 208	67.43 327	98.19 208	82.64 289	89.67 247	93.66 316

COLMAP_ROB	87.81 15	90.40 251	89.28 260	93.79 221	97.95 110	87.13 250	96.92 155	95.89 262	82.83 314	86.88 292	97.18 119	73.77 296	99.29 117	78.44 316	93.62 193	94.95 271
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 123	93.08 129	96.02 118	97.88 116	89.96 173	97.72 76	95.85 263	92.43 104	95.86 86	98.44 28	68.42 323	99.39 109	96.31 28	94.85 174	98.71 114

VDDNet		93.05 147	92.07 159	96.02 118	96.84 158	90.39 163	98.08 42	95.85 263	86.22 273	95.79 89	98.46 26	67.59 326	99.19 123	94.92 78	94.85 174	98.47 130

Vis-MVSNet (Re-imp)		94.15 110	93.88 106	94.95 169	97.61 129	87.92 232	98.10 39	95.80 265	92.22 109	93.02 146	97.45 109	84.53 150	97.91 253	88.24 205	97.97 111	99.02 83

KD-MVS_2432*1600		84.81 308	82.64 311	91.31 296	91.07 334	85.34 281	91.22 330	95.75 266	85.56 282	83.09 322	90.21 329	67.21 329	95.89 325	77.18 322	62.48 349	92.69 327

miper_refine_blended		84.81 308	82.64 311	91.31 296	91.07 334	85.34 281	91.22 330	95.75 266	85.56 282	83.09 322	90.21 329	67.21 329	95.89 325	77.18 322	62.48 349	92.69 327

tpm cat1		88.36 281	87.21 284	91.81 284	95.13 246	80.55 324	92.58 323	95.70 268	74.97 343	87.45 277	91.96 319	78.01 267	98.17 211	80.39 304	88.74 255	96.72 199

our_test_3		88.78 277	87.98 276	91.20 299	92.45 325	82.53 309	93.61 307	95.69 269	85.77 279	84.88 307	93.71 287	79.99 229	96.78 318	79.47 310	86.24 276	94.28 307

BH-w/o		92.14 185	91.75 170	93.31 243	96.99 155	85.73 274	95.67 243	95.69 269	88.73 215	89.26 239	94.82 236	82.97 175	98.07 226	85.26 262	96.32 152	96.13 214

CR-MVSNet		90.82 238	89.77 249	93.95 212	94.45 278	87.19 247	90.23 338	95.68 271	86.89 263	92.40 156	92.36 314	80.91 212	97.05 307	81.09 301	93.95 189	97.60 177

Patchmtry		88.64 279	87.25 282	92.78 262	94.09 288	86.64 258	89.82 341	95.68 271	80.81 328	87.63 276	92.36 314	80.91 212	97.03 308	78.86 314	85.12 291	94.67 295

BH-RMVSNet		92.72 163	91.97 164	94.97 167	97.16 142	87.99 231	96.15 222	95.60 273	90.62 162	91.87 171	97.15 122	78.41 258	98.57 182	83.16 281	97.60 120	98.36 142

PVSNet_0	82.17 19	85.46 305	83.64 308	90.92 302	95.27 237	79.49 333	90.55 336	95.60 273	83.76 307	83.00 324	89.95 331	71.09 307	97.97 240	82.75 287	60.79 351	95.31 255

SCA		91.84 191	91.18 194	93.83 218	95.59 215	84.95 287	94.72 271	95.58 275	90.82 152	92.25 163	93.69 288	75.80 282	98.10 218	86.20 245	95.98 154	98.45 132

AllTest		90.23 255	88.98 264	93.98 208	97.94 111	86.64 258	96.51 192	95.54 276	85.38 284	85.49 302	96.77 137	70.28 313	99.15 128	80.02 306	92.87 198	96.15 212

TestCases				93.98 208	97.94 111	86.64 258		95.54 276	85.38 284	85.49 302	96.77 137	70.28 313	99.15 128	80.02 306	92.87 198	96.15 212

tpmvs		89.83 265	89.15 263	91.89 280	94.92 256	80.30 327	93.11 315	95.46 278	86.28 271	88.08 267	92.65 306	80.44 220	98.52 185	81.47 295	89.92 244	96.84 195

pmmvs5		89.86 264	88.87 266	92.82 260	92.86 317	86.23 267	96.26 214	95.39 279	84.24 300	87.12 284	94.51 250	74.27 291	97.36 300	87.61 224	87.57 264	94.86 280

PatchmatchNet		91.91 189	91.35 183	93.59 230	95.38 225	84.11 296	93.15 314	95.39 279	89.54 186	92.10 167	93.68 290	82.82 179	98.13 213	84.81 266	95.32 167	98.52 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 208	91.32 185	91.79 285	95.15 244	79.20 336	93.42 309	95.37 281	88.55 220	93.49 136	93.67 291	82.49 187	98.27 200	90.41 163	89.34 249	97.90 159

Anonymous20231206		87.09 291	86.14 292	89.93 316	91.22 333	80.35 325	96.11 223	95.35 282	83.57 309	84.16 314	93.02 302	73.54 298	95.61 331	72.16 338	86.14 278	93.84 315

MIMVSNet1		84.93 307	83.05 309	90.56 309	89.56 342	84.84 289	95.40 254	95.35 282	83.91 303	80.38 333	92.21 318	57.23 347	93.34 346	70.69 344	82.75 321	93.50 318

TDRefinement		86.53 294	84.76 303	91.85 281	82.23 353	84.25 293	96.38 203	95.35 282	84.97 292	84.09 316	94.94 228	65.76 338	98.34 198	84.60 270	74.52 338	92.97 323

TR-MVS		91.48 207	90.59 214	94.16 201	96.40 183	87.33 241	95.67 243	95.34 285	87.68 247	91.46 176	95.52 211	76.77 275	98.35 196	82.85 285	93.61 194	96.79 197

EPNet_dtu		91.71 194	91.28 188	92.99 254	93.76 298	83.71 300	96.69 176	95.28 286	93.15 79	87.02 288	95.95 183	83.37 165	97.38 299	79.46 311	96.84 139	97.88 161
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 290	85.79 294	91.78 286	94.80 264	87.28 242	95.49 251	95.28 286	84.09 302	83.85 320	91.82 320	62.95 342	94.17 342	78.48 315	85.34 287	93.91 314

MDTV_nov1_ep13			90.76 207		95.22 241	80.33 326	93.03 317	95.28 286	88.14 232	92.84 153	93.83 282	81.34 206	98.08 223	82.86 284	94.34 183

LF4IMVS		87.94 285	87.25 282	89.98 315	92.38 327	80.05 331	94.38 282	95.25 289	87.59 249	84.34 311	94.74 240	64.31 340	97.66 274	84.83 265	87.45 265	92.23 334

TransMVSNet (Re)		88.94 272	87.56 279	93.08 252	94.35 281	88.45 219	97.73 73	95.23 290	87.47 251	84.26 313	95.29 217	79.86 232	97.33 301	79.44 312	74.44 339	93.45 320

test20.03		86.14 299	85.40 297	88.35 320	90.12 337	80.06 330	95.90 235	95.20 291	88.59 216	81.29 328	93.62 293	71.43 305	92.65 348	71.26 342	81.17 325	92.34 333

new-patchmatchnet		83.18 312	81.87 314	87.11 326	86.88 350	75.99 344	93.70 302	95.18 292	85.02 291	77.30 341	88.40 337	65.99 336	93.88 344	74.19 334	70.18 345	91.47 341

MDA-MVSNet_test_wron		85.87 302	84.23 306	90.80 306	92.38 327	82.57 308	93.17 312	95.15 293	82.15 317	67.65 347	92.33 317	78.20 260	95.51 334	77.33 319	79.74 327	94.31 306

YYNet1		85.87 302	84.23 306	90.78 307	92.38 327	82.46 311	93.17 312	95.14 294	82.12 318	67.69 346	92.36 314	78.16 263	95.50 335	77.31 320	79.73 328	94.39 302

Baseline_NR-MVSNet		91.20 222	90.62 212	92.95 256	93.83 296	88.03 230	97.01 147	95.12 295	88.42 222	89.70 222	95.13 224	83.47 162	97.44 294	89.66 178	83.24 316	93.37 321

thres200		92.23 180	91.39 182	94.75 181	97.61 129	89.03 205	96.60 187	95.09 296	92.08 117	93.28 142	94.00 278	78.39 259	99.04 144	81.26 300	94.18 184	96.19 209

ADS-MVSNet		89.89 262	88.68 268	93.53 233	95.86 205	84.89 288	90.93 333	95.07 297	83.23 312	91.28 185	91.81 321	79.01 248	97.85 256	79.52 308	91.39 224	97.84 163

pmmvs-eth3d		86.22 298	84.45 304	91.53 291	88.34 347	87.25 244	94.47 277	95.01 298	83.47 310	79.51 338	89.61 334	69.75 318	95.71 330	83.13 282	76.73 335	91.64 337

Anonymous202405211		92.07 186	90.83 205	95.76 127	98.19 100	88.75 210	97.58 91	95.00 299	86.00 276	93.64 131	97.45 109	66.24 335	99.53 88	90.68 162	92.71 201	99.01 87

MDA-MVSNet-bldmvs		85.00 306	82.95 310	91.17 300	93.13 315	83.33 304	94.56 275	95.00 299	84.57 297	65.13 350	92.65 306	70.45 311	95.85 327	73.57 335	77.49 332	94.33 304

ambc				86.56 328	83.60 351	70.00 351	85.69 348	94.97 301		80.60 332	88.45 336	37.42 355	96.84 316	82.69 288	75.44 337	92.86 325

testgi		87.97 284	87.21 284	90.24 313	92.86 317	80.76 320	96.67 178	94.97 301	91.74 124	85.52 301	95.83 189	62.66 343	94.47 341	76.25 325	88.36 258	95.48 240

dp		88.90 274	88.26 274	90.81 304	94.58 275	76.62 342	92.85 319	94.93 303	85.12 289	90.07 214	93.07 301	75.81 281	98.12 216	80.53 303	87.42 267	97.71 169

test_0402		86.46 295	84.79 302	91.45 293	95.02 251	85.55 276	96.29 212	94.89 304	80.90 325	82.21 325	93.97 280	68.21 324	97.29 303	62.98 349	88.68 256	91.51 339

tfpn200view9		92.38 171	91.52 179	94.95 169	97.85 117	89.29 196	97.41 105	94.88 305	92.19 113	93.27 143	94.46 255	78.17 261	99.08 138	81.40 296	94.08 185	96.48 204

CVMVSNet		91.23 220	91.75 170	89.67 318	95.77 210	74.69 345	96.44 193	94.88 305	85.81 278	92.18 164	97.64 97	79.07 243	95.58 333	88.06 208	95.86 158	98.74 110

thres400		92.42 169	91.52 179	95.12 161	97.85 117	89.29 196	97.41 105	94.88 305	92.19 113	93.27 143	94.46 255	78.17 261	99.08 138	81.40 296	94.08 185	96.98 188

EPNet		95.20 86	94.56 93	97.14 68	92.80 319	92.68 84	97.85 62	94.87 308	96.64 1	92.46 155	97.80 84	86.23 127	99.65 53	93.72 106	98.62 96	99.10 79
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SixPastTwentyTwo		89.15 270	88.54 270	90.98 301	93.49 306	80.28 328	96.70 174	94.70 309	90.78 153	84.15 315	95.57 206	71.78 303	97.71 270	84.63 269	85.07 292	94.94 273

thres100view900		92.43 168	91.58 176	94.98 166	97.92 113	89.37 192	97.71 78	94.66 310	92.20 111	93.31 141	94.90 231	78.06 265	99.08 138	81.40 296	94.08 185	96.48 204

thres600view7		92.49 167	91.60 175	95.18 157	97.91 114	89.47 186	97.65 84	94.66 310	92.18 115	93.33 140	94.91 230	78.06 265	99.10 133	81.61 293	94.06 188	96.98 188

PatchT		88.87 275	87.42 280	93.22 247	94.08 289	85.10 284	89.51 342	94.64 312	81.92 319	92.36 159	88.15 340	80.05 228	97.01 311	72.43 337	93.65 192	97.54 180

baseline1		92.82 160	91.90 166	95.55 142	97.20 140	90.77 152	97.19 131	94.58 313	92.20 111	92.36 159	96.34 167	84.16 155	98.21 204	89.20 192	83.90 311	97.68 171

Gipuma		67.86 321	65.41 324	75.18 335	92.66 322	73.45 347	66.50 355	94.52 314	53.33 353	57.80 353	66.07 353	30.81 356	89.20 350	48.15 353	78.88 331	62.90 352
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CostFormer		91.18 226	90.70 210	92.62 266	94.84 262	81.76 315	94.09 293	94.43 315	84.15 301	92.72 154	93.77 286	79.43 239	98.20 206	90.70 161	92.18 211	97.90 159

tpm2		89.96 260	89.21 261	92.23 274	94.91 259	81.25 318	93.78 300	94.42 316	80.62 329	91.56 174	93.44 297	76.44 278	97.94 247	85.60 257	92.08 215	97.49 181

JIA-IIPM		88.26 283	87.04 287	91.91 279	93.52 304	81.42 317	89.38 343	94.38 317	80.84 327	90.93 191	80.74 347	79.22 242	97.92 250	82.76 286	91.62 219	96.38 206

Patchmatch-test		89.42 268	87.99 275	93.70 225	95.27 237	85.11 283	88.98 344	94.37 318	81.11 324	87.10 286	93.69 288	82.28 191	97.50 289	74.37 332	94.76 177	98.48 129

LCM-MVSNet		72.55 318	69.39 322	82.03 330	70.81 359	65.42 355	90.12 340	94.36 319	55.02 352	65.88 349	81.72 346	24.16 362	89.96 349	74.32 333	68.10 347	90.71 343

ADS-MVSNet2		89.45 267	88.59 269	92.03 277	95.86 205	82.26 313	90.93 333	94.32 320	83.23 312	91.28 185	91.81 321	79.01 248	95.99 324	79.52 308	91.39 224	97.84 163

DWT-MVSNet_test		90.76 239	89.89 243	93.38 240	95.04 250	83.70 301	95.85 237	94.30 321	88.19 227	90.46 196	92.80 304	73.61 297	98.50 186	88.16 206	90.58 236	97.95 157

EU-MVSNet		88.72 278	88.90 265	88.20 322	93.15 314	74.21 346	96.63 184	94.22 322	85.18 287	87.32 282	95.97 181	76.16 280	94.98 337	85.27 261	86.17 277	95.41 246

MIMVSNet		88.50 280	86.76 288	93.72 224	94.84 262	87.77 237	91.39 328	94.05 323	86.41 270	87.99 270	92.59 308	63.27 341	95.82 329	77.44 318	92.84 200	97.57 179

OpenMVS_ROB	81.14 20	84.42 310	82.28 313	90.83 303	90.06 338	84.05 297	95.73 242	94.04 324	73.89 345	80.17 336	91.53 325	59.15 346	97.64 275	66.92 347	89.05 251	90.80 342

TinyColmap		86.82 293	85.35 298	91.21 298	94.91 259	82.99 307	93.94 296	94.02 325	83.58 308	81.56 327	94.68 243	62.34 344	98.13 213	75.78 326	87.35 269	92.52 331

IB-MVS	87.33 17	89.91 261	88.28 273	94.79 178	95.26 240	87.70 238	95.12 268	93.95 326	89.35 192	87.03 287	92.49 309	70.74 310	99.19 123	89.18 193	81.37 324	97.49 181
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
LCM-MVSNet-Re		92.50 165	92.52 149	92.44 268	96.82 161	81.89 314	96.92 155	93.71 327	92.41 105	84.30 312	94.60 247	85.08 143	97.03 308	91.51 147	97.36 128	98.40 138

tpm		90.25 254	89.74 252	91.76 288	93.92 292	79.73 332	93.98 294	93.54 328	88.28 225	91.99 169	93.25 300	77.51 271	97.44 294	87.30 230	87.94 260	98.12 150

ET-MVSNet_ETH3D		91.49 206	90.11 235	95.63 136	96.40 183	91.57 121	95.34 256	93.48 329	90.60 165	75.58 343	95.49 212	80.08 227	96.79 317	94.25 92	89.76 246	98.52 122

bset_n11_16_dypcd		91.55 202	90.59 214	94.44 190	91.51 331	90.25 164	92.70 321	93.42 330	92.27 108	90.22 202	94.74 240	78.42 257	97.80 261	94.19 94	87.86 262	95.29 262

LFMVS		93.60 130	92.63 142	96.52 85	98.13 104	91.27 130	97.94 54	93.39 331	90.57 166	96.29 70	98.31 47	69.00 319	99.16 127	94.18 95	95.87 157	99.12 77

Patchmatch-RL test		87.38 289	86.24 290	90.81 304	88.74 346	78.40 340	88.12 346	93.17 332	87.11 260	82.17 326	89.29 335	81.95 198	95.60 332	88.64 202	77.02 333	98.41 137

test-LLR		91.42 209	91.19 193	92.12 275	94.59 273	80.66 321	94.29 287	92.98 333	91.11 148	90.76 192	92.37 311	79.02 246	98.07 226	88.81 198	96.74 142	97.63 172

test-mter		90.19 257	89.54 256	92.12 275	94.59 273	80.66 321	94.29 287	92.98 333	87.68 247	90.76 192	92.37 311	67.67 325	98.07 226	88.81 198	96.74 142	97.63 172

test0.0.03 1		89.37 269	88.70 267	91.41 295	92.47 324	85.63 275	95.22 265	92.70 335	91.11 148	86.91 291	93.65 292	79.02 246	93.19 347	78.00 317	89.18 250	95.41 246

new_pmnet		82.89 313	81.12 317	88.18 323	89.63 341	80.18 329	91.77 327	92.57 336	76.79 342	75.56 344	88.23 339	61.22 345	94.48 340	71.43 340	82.92 319	89.87 344

thisisatest0515		92.29 176	91.30 187	95.25 155	96.60 168	88.90 208	94.36 283	92.32 337	87.92 236	93.43 138	94.57 248	77.28 272	99.00 145	89.42 183	95.86 158	97.86 162

thisisatest0530		93.03 148	92.21 157	95.49 147	97.07 147	89.11 204	97.49 101	92.19 338	90.16 173	94.09 122	96.41 163	76.43 279	99.05 142	90.38 164	95.68 163	98.31 144

tttt0517		92.96 151	92.33 154	94.87 172	97.11 145	87.16 249	97.97 52	92.09 339	90.63 161	93.88 128	97.01 128	76.50 276	99.06 141	90.29 167	95.45 165	98.38 140

K. test v3		87.64 288	86.75 289	90.32 312	93.02 316	79.48 334	96.61 185	92.08 340	90.66 159	80.25 335	94.09 275	67.21 329	96.65 319	85.96 253	80.83 326	94.83 282

TESTMET0.1,1		90.06 259	89.42 257	91.97 278	94.41 280	80.62 323	94.29 287	91.97 341	87.28 257	90.44 197	92.47 310	68.79 320	97.67 272	88.50 204	96.60 147	97.61 176

PM-MVS		83.48 311	81.86 315	88.31 321	87.83 349	77.59 341	93.43 308	91.75 342	86.91 262	80.63 331	89.91 332	44.42 354	95.84 328	85.17 264	76.73 335	91.50 340

baseline2		91.63 197	90.86 201	93.94 214	94.33 282	86.32 264	95.92 234	91.64 343	89.37 191	86.94 289	94.69 242	81.62 204	98.69 171	88.64 202	94.57 181	96.81 196

FPMVS		71.27 319	69.85 321	75.50 334	74.64 355	59.03 357	91.30 329	91.50 344	58.80 351	57.92 352	88.28 338	29.98 358	85.53 353	53.43 351	82.84 320	81.95 348

door								91.13 345

door-mid								91.06 346

pmmvs3		79.97 316	77.50 320	87.39 325	82.80 352	79.38 335	92.70 321	90.75 347	70.69 347	78.66 339	87.47 343	51.34 352	93.40 345	73.39 336	69.65 346	89.38 345

DSMNet-mixed		86.34 296	86.12 293	87.00 327	89.88 340	70.43 349	94.93 269	90.08 348	77.97 340	85.42 304	92.78 305	74.44 290	93.96 343	74.43 331	95.14 169	96.62 200

MVS-HIRNet		82.47 314	81.21 316	86.26 329	95.38 225	69.21 352	88.96 345	89.49 349	66.28 348	80.79 330	74.08 351	68.48 322	97.39 298	71.93 339	95.47 164	92.18 335

EPMVS		90.70 244	89.81 247	93.37 241	94.73 267	84.21 294	93.67 304	88.02 350	89.50 188	92.38 158	93.49 295	77.82 269	97.78 264	86.03 251	92.68 202	98.11 153

ANet_high		63.94 322	59.58 325	77.02 333	61.24 361	66.06 353	85.66 349	87.93 351	78.53 338	42.94 355	71.04 352	25.42 361	80.71 354	52.60 352	30.83 355	84.28 347

PMMVS2		70.19 320	66.92 323	80.01 331	76.35 354	65.67 354	86.22 347	87.58 352	64.83 350	62.38 351	80.29 348	26.78 360	88.49 351	63.79 348	54.07 352	85.88 346

lessismore_v0				90.45 310	91.96 330	79.09 338		87.19 353		80.32 334	94.39 257	66.31 334	97.55 283	84.00 276	76.84 334	94.70 294

PMVS	53.92 22	58.58 323	55.40 326	68.12 337	51.00 362	48.64 359	78.86 352	87.10 354	46.77 354	35.84 359	74.28 350	8.76 363	86.34 352	42.07 354	73.91 340	69.38 350
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
gg-mvs-nofinetune		87.82 286	85.61 295	94.44 190	94.46 277	89.27 199	91.21 332	84.61 355	80.88 326	89.89 218	74.98 349	71.50 304	97.53 286	85.75 256	97.21 134	96.51 202

GG-mvs-BLEND				93.62 228	93.69 300	89.20 200	92.39 326	83.33 356		87.98 271	89.84 333	71.00 308	96.87 315	82.08 292	95.40 166	94.80 287

MTMP							97.86 59	82.03 357

DeepMVS_CX				74.68 336	90.84 336	64.34 356		81.61 358	65.34 349	67.47 348	88.01 341	48.60 353	80.13 355	62.33 350	73.68 341	79.58 349

E-PMN		53.28 324	52.56 328	55.43 339	74.43 356	47.13 360	83.63 351	76.30 359	42.23 355	42.59 356	62.22 355	28.57 359	74.40 356	31.53 356	31.51 354	44.78 353

EMVS		52.08 326	51.31 329	54.39 340	72.62 358	45.39 362	83.84 350	75.51 360	41.13 356	40.77 357	59.65 356	30.08 357	73.60 357	28.31 357	29.90 356	44.18 354

MVE	50.73 23	53.25 325	48.81 330	66.58 338	65.34 360	57.50 358	72.49 354	70.94 361	40.15 357	39.28 358	63.51 354	6.89 365	73.48 358	38.29 355	42.38 353	68.76 351
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 327	53.82 327	46.29 341	33.73 363	45.30 363	78.32 353	67.24 362	18.02 358	50.93 354	87.05 344	52.99 351	53.11 359	70.76 343	25.29 357	40.46 355

N_pmnet		78.73 317	78.71 319	78.79 332	92.80 319	46.50 361	94.14 291	43.71 363	78.61 337	80.83 329	91.66 324	74.94 288	96.36 321	67.24 346	84.45 302	93.50 318

wuyk23d		25.11 328	24.57 332	26.74 342	73.98 357	39.89 364	57.88 356	9.80 364	12.27 359	10.39 360	6.97 362	7.03 364	36.44 360	25.43 358	17.39 358	3.89 358

testmvs		13.36 330	16.33 333	4.48 344	5.04 364	2.26 366	93.18 311	3.28 365	2.70 360	8.24 361	21.66 358	2.29 367	2.19 361	7.58 359	2.96 359	9.00 357

test123		13.04 331	15.66 334	5.18 343	4.51 365	3.45 365	92.50 325	1.81 366	2.50 361	7.58 362	20.15 359	3.67 366	2.18 362	7.13 360	1.07 360	9.90 356

uanet_test		0.00 334	0.00 337	0.00 345	0.00 366	0.00 367	0.00 357	0.00 367	0.00 362	0.00 363	0.00 363	0.00 368	0.00 363	0.00 361	0.00 361	0.00 359

pcd_1.5k_mvsjas		7.39 333	9.85 336	0.00 345	0.00 366	0.00 367	0.00 357	0.00 367	0.00 362	0.00 363	0.00 363	88.65 94	0.00 363	0.00 361	0.00 361	0.00 359

sosnet-low-res		0.00 334	0.00 337	0.00 345	0.00 366	0.00 367	0.00 357	0.00 367	0.00 362	0.00 363	0.00 363	0.00 368	0.00 363	0.00 361	0.00 361	0.00 359

sosnet		0.00 334	0.00 337	0.00 345	0.00 366	0.00 367	0.00 357	0.00 367	0.00 362	0.00 363	0.00 363	0.00 368	0.00 363	0.00 361	0.00 361	0.00 359

uncertanet		0.00 334	0.00 337	0.00 345	0.00 366	0.00 367	0.00 357	0.00 367	0.00 362	0.00 363	0.00 363	0.00 368	0.00 363	0.00 361	0.00 361	0.00 359

Regformer		0.00 334	0.00 337	0.00 345	0.00 366	0.00 367	0.00 357	0.00 367	0.00 362	0.00 363	0.00 363	0.00 368	0.00 363	0.00 361	0.00 361	0.00 359

n2								0.00 367

nn								0.00 367

ab-mvs-re		8.06 332	10.74 335	0.00 345	0.00 366	0.00 367	0.00 357	0.00 367	0.00 362	0.00 363	96.69 143	0.00 368	0.00 363	0.00 361	0.00 361	0.00 359

uanet		0.00 334	0.00 337	0.00 345	0.00 366	0.00 367	0.00 357	0.00 367	0.00 362	0.00 363	0.00 363	0.00 368	0.00 363	0.00 361	0.00 361	0.00 359

OPU-MVS				98.55 1	98.82 56	96.86 1	98.25 28				98.26 53	96.04 1	99.24 120	95.36 66	99.59 15	99.56 22

test_0728_THIRD									94.78 31	98.73 8	98.87 6	95.87 2	99.84 19	97.45 6	99.72 2	99.77 1

GSMVS																98.45 132

test_part2					99.28 25	95.74 6				98.10 17

sam_mvs1												82.76 180				98.45 132

sam_mvs												81.94 199

test_post1							92.81 320				16.58 361	80.53 218	97.68 271	86.20 245

test_post											17.58 360	81.76 201	98.08 223

patchmatchnet-post											90.45 328	82.65 184	98.10 218

gm-plane-assit					93.22 312	78.89 339			84.82 294		93.52 294		98.64 175	87.72 214

test9_res														94.81 83	99.38 48	99.45 45

agg_prior2														93.94 100	99.38 48	99.50 37

test_prior4						93.66 59	96.42 196

test_prior2							96.35 205		92.80 95	96.03 78	97.59 101	92.01 41		95.01 74	99.38 48

旧先验2							95.94 233		81.66 321	97.34 34			98.82 159	92.26 126

新几何2							95.79 240

原ACMM2							95.67 243

testdata2													99.67 49	85.96 253

segment_acmp												92.89 22

testdata1							95.26 264		93.10 82

plane_prior7					96.21 190	89.98 171

plane_prior6					96.10 200	90.00 167						81.32 207

plane_prior4											96.64 146

plane_prior3						90.00 167			94.46 39	91.34 179

plane_prior2							97.74 71		94.85 24

plane_prior1					96.14 198

plane_prior						89.99 169	97.24 123		94.06 47						92.16 212

HQP5-MVS						89.33 194

HQP-NCC					95.86 205		96.65 179		93.55 62	90.14 203

ACMP_Plane					95.86 205		96.65 179		93.55 62	90.14 203

BP-MVS														92.13 132

HQP4-MVS										90.14 203			98.50 186			95.78 228

HQP2-MVS												80.95 210

NP-MVS					95.99 204	89.81 176					95.87 186

MDTV_nov1_ep13_2view						70.35 350	93.10 316		83.88 305	93.55 133		82.47 188		86.25 244		98.38 140

ACMMP++_ref															90.30 241

ACMMP++															91.02 230

Test By Simon												88.73 93

High-resolution multi-view benchmark