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.

EPNet		91.79 61	91.02 69	94.10 46	90.10 296	85.25 55	96.03 37	92.05 257	92.83 1	87.39 128	95.78 76	79.39 98	99.01 56	88.13 84	97.48 60	98.05 48
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
NCCC		94.81 10	94.69 11	95.17 7	97.83 33	87.46 10	95.66 55	96.93 41	92.34 2	93.94 21	96.58 46	87.74 15	99.44 21	92.83 23	98.40 40	98.62 8

CNVR-MVS		95.40 2	95.37 4	95.50 4	98.11 26	88.51 3	95.29 68	96.96 38	92.09 3	95.32 10	97.08 26	89.49 6	99.33 27	95.10 2	98.85 9	98.66 7

UA-Net		92.83 53	92.54 53	93.68 57	96.10 87	84.71 60	95.66 55	96.39 78	91.92 4	93.22 33	96.49 50	83.16 56	98.87 68	84.47 125	95.47 89	97.45 75

CANet		93.54 38	93.20 41	94.55 33	95.65 103	85.73 51	94.94 94	96.69 61	91.89 5	90.69 80	95.88 73	81.99 73	99.54 11	93.14 21	97.95 52	98.39 22

Regformer-2		94.33 20	94.22 18	94.68 28	95.54 106	86.75 21	94.57 123	96.70 59	91.84 6	94.41 13	96.56 48	87.19 21	99.13 41	93.50 12	97.65 58	98.16 39

MVS_0304		93.25 47	92.62 51	95.14 9	95.72 100	87.58 8	94.71 114	96.59 68	91.78 7	91.46 71	96.18 64	75.45 148	99.55 8	93.53 11	98.19 45	98.28 29

HPM-MVS++		95.14 7	94.91 9	95.83 1	98.25 21	89.65 1	95.92 44	96.96 38	91.75 8	94.02 20	96.83 33	88.12 12	99.55 8	93.41 16	98.94 6	98.28 29

HSP-MVS		95.30 4	95.48 2	94.76 25	98.49 10	86.52 29	96.91 15	96.73 55	91.73 9	96.10 6	96.69 39	89.90 3	99.30 30	94.70 3	98.04 50	98.45 19

Regformer-1		94.22 24	94.13 23	94.51 35	95.54 106	86.36 34	94.57 123	96.44 73	91.69 10	94.32 15	96.56 48	87.05 23	99.03 51	93.35 17	97.65 58	98.15 40

Regformer-4		93.91 31	93.81 29	94.19 45	95.36 112	85.47 52	94.68 115	96.41 76	91.60 11	93.75 23	96.71 37	85.95 33	99.10 44	93.21 18	96.65 73	98.01 52

SteuartSystems-ACMMP		95.20 5	95.32 6	94.85 17	96.99 56	86.33 35	97.33 3	97.30 17	91.38 12	95.39 9	97.46 10	88.98 10	99.40 22	94.12 8	98.89 8	98.82 2
Skip Steuart: Steuart Systems R&D Blog.
Regformer-3		93.68 35	93.64 35	93.81 54	95.36 112	84.61 61	94.68 115	95.83 118	91.27 13	93.60 27	96.71 37	85.75 35	98.86 71	92.87 22	96.65 73	97.96 54

zzz-MVS		94.47 13	94.30 15	95.00 10	98.42 14	86.95 13	95.06 87	96.97 35	91.07 14	93.14 35	97.56 7	84.30 50	99.56 3	93.43 14	98.75 17	98.47 15

MTAPA		94.42 18	94.22 18	95.00 10	98.42 14	86.95 13	94.36 144	96.97 35	91.07 14	93.14 35	97.56 7	84.30 50	99.56 3	93.43 14	98.75 17	98.47 15

EI-MVSNet-Vis-set		93.01 52	92.92 47	93.29 60	95.01 128	83.51 92	94.48 126	95.77 122	90.87 16	92.52 50	96.67 41	84.50 49	99.00 59	91.99 39	94.44 108	97.36 76

3Dnovator+	87.14 4	92.42 57	91.37 61	95.55 3	95.63 104	88.73 2	97.07 8	96.77 53	90.84 17	84.02 217	96.62 44	75.95 137	99.34 24	87.77 88	97.68 56	98.59 10

HQP_MVS		90.60 86	90.19 81	91.82 121	94.70 142	82.73 114	95.85 46	96.22 87	90.81 18	86.91 134	94.86 100	74.23 161	98.12 114	88.15 82	89.99 168	94.63 175

plane_prior2							95.85 46		90.81 18

DELS-MVS		93.43 41	93.25 39	93.97 47	95.42 111	85.04 56	93.06 222	97.13 26	90.74 20	91.84 63	95.09 95	86.32 29	99.21 33	91.22 54	98.45 39	97.65 67
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
EI-MVSNet-UG-set		92.74 55	92.62 51	93.12 66	94.86 136	83.20 98	94.40 134	95.74 125	90.71 21	92.05 60	96.60 45	84.00 52	98.99 60	91.55 49	93.63 119	97.17 85

XVS		94.45 14	94.32 14	94.85 17	98.54 7	86.60 27	96.93 12	97.19 23	90.66 22	92.85 37	97.16 24	85.02 44	99.49 17	91.99 39	98.56 36	98.47 15

X-MVStestdata		88.31 139	86.13 187	94.85 17	98.54 7	86.60 27	96.93 12	97.19 23	90.66 22	92.85 37	23.41 359	85.02 44	99.49 17	91.99 39	98.56 36	98.47 15

SD-MVS		94.96 8	95.33 5	93.88 50	97.25 53	86.69 22	96.19 30	97.11 29	90.42 24	96.95 2	97.27 14	89.53 5	96.91 223	94.38 6	98.85 9	98.03 50

plane_prior3						82.75 111			90.26 25	86.91 134

DeepPCF-MVS	89.96 1	94.20 26	94.77 10	92.49 92	96.52 69	80.00 178	94.00 175	97.08 30	90.05 26	95.65 8	97.29 13	89.66 4	98.97 62	93.95 9	98.71 20	98.50 12

MSLP-MVS++		93.72 34	94.08 24	92.65 85	97.31 47	83.43 93	95.79 48	97.33 14	90.03 27	93.58 28	96.96 29	84.87 46	97.76 144	92.19 34	98.66 29	96.76 99

canonicalmvs		93.27 45	92.75 50	94.85 17	95.70 102	87.66 6	96.33 25	96.41 76	90.00 28	94.09 18	94.60 110	82.33 63	98.62 86	92.40 29	92.86 136	98.27 32

Vis-MVSNet		91.75 63	91.23 65	93.29 60	95.32 115	83.78 83	96.14 32	95.98 105	89.89 29	90.45 82	96.58 46	75.09 152	98.31 104	84.75 122	96.90 67	97.78 66
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TranMVSNet+NR-MVSNet		88.84 128	87.95 131	91.49 130	92.68 208	83.01 105	94.92 96	96.31 81	89.88 30	85.53 168	93.85 138	76.63 122	96.96 218	81.91 164	79.87 300	94.50 186

UniMVSNet_NR-MVSNet		89.92 100	89.29 99	91.81 123	93.39 187	83.72 85	94.43 132	97.12 27	89.80 31	86.46 141	93.32 148	83.16 56	97.23 199	84.92 118	81.02 281	94.49 188

alignmvs		93.08 51	92.50 54	94.81 22	95.62 105	87.61 7	95.99 38	96.07 98	89.77 32	94.12 17	94.87 99	80.56 82	98.66 82	92.42 28	93.10 132	98.15 40

TSAR-MVS + GP.		93.66 36	93.41 37	94.41 39	96.59 65	86.78 19	94.40 134	93.93 223	89.77 32	94.21 16	95.59 82	87.35 19	98.61 87	92.72 24	96.15 81	97.83 63

IS-MVSNet		91.43 69	91.09 68	92.46 93	95.87 97	81.38 142	96.95 9	93.69 228	89.72 34	89.50 92	95.98 69	78.57 105	97.77 143	83.02 143	96.50 77	98.22 36

plane_prior						82.73 114	95.21 78		89.66 35						89.88 172

DU-MVS		89.34 118	88.50 116	91.85 119	93.04 197	83.72 85	94.47 129	96.59 68	89.50 36	86.46 141	93.29 151	77.25 115	97.23 199	84.92 118	81.02 281	94.59 179

CANet_DTU		90.26 92	89.41 96	92.81 79	93.46 186	83.01 105	93.48 202	94.47 200	89.43 37	87.76 123	94.23 121	70.54 215	99.03 51	84.97 117	96.39 79	96.38 107

DeepC-MVS_fast	89.43 2	94.04 27	93.79 30	94.80 23	97.48 42	86.78 19	95.65 58	96.89 43	89.40 38	92.81 40	96.97 28	85.37 39	99.24 32	90.87 60	98.69 22	98.38 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
UGNet		89.95 98	88.95 107	92.95 75	94.51 150	83.31 96	95.70 52	95.23 169	89.37 39	87.58 125	93.94 131	64.00 284	98.78 79	83.92 135	96.31 80	96.74 101
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
FC-MVSNet-test		90.27 91	90.18 82	90.53 159	93.71 180	79.85 182	95.77 49	97.59 2	89.31 40	86.27 147	94.67 107	81.93 74	97.01 214	84.26 130	88.09 207	94.71 170

UniMVSNet (Re)		89.80 102	89.07 104	92.01 109	93.60 183	84.52 64	94.78 106	97.47 5	89.26 41	86.44 144	92.32 185	82.10 68	97.39 185	84.81 121	80.84 285	94.12 200

3Dnovator	86.66 5	91.73 64	90.82 73	94.44 36	94.59 147	86.37 33	97.18 6	97.02 32	89.20 42	84.31 213	96.66 42	73.74 172	99.17 36	86.74 103	97.96 51	97.79 65

VNet		92.24 58	91.91 57	93.24 62	96.59 65	83.43 93	94.84 102	96.44 73	89.19 43	94.08 19	95.90 72	77.85 114	98.17 110	88.90 74	93.38 126	98.13 42

FIs		90.51 87	90.35 77	90.99 149	93.99 170	80.98 153	95.73 50	97.54 3	89.15 44	86.72 138	94.68 106	81.83 75	97.24 197	85.18 115	88.31 204	94.76 169

NR-MVSNet		88.58 134	87.47 138	91.93 115	93.04 197	84.16 77	94.77 107	96.25 85	89.05 45	80.04 275	93.29 151	79.02 99	97.05 212	81.71 168	80.05 295	94.59 179

MP-MVS		94.25 22	94.07 25	94.77 24	98.47 11	86.31 37	96.71 20	96.98 34	89.04 46	91.98 61	97.19 21	85.43 38	99.56 3	92.06 38	98.79 12	98.44 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APDe-MVS		95.46 1	95.64 1	94.91 13	98.26 20	86.29 39	97.46 2	97.40 9	89.03 47	96.20 5	98.10 1	89.39 7	99.34 24	95.88 1	99.03 2	99.10 1

DeepC-MVS	88.79 3	93.31 43	92.99 45	94.26 43	96.07 89	85.83 49	94.89 97	96.99 33	89.02 48	89.56 90	97.37 11	82.51 61	99.38 23	92.20 33	98.30 42	97.57 71
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OPM-MVS		90.12 93	89.56 92	91.82 121	93.14 193	83.90 80	94.16 157	95.74 125	88.96 49	87.86 114	95.43 85	72.48 189	97.91 139	88.10 85	90.18 167	93.65 234

HQP-NCC					94.17 160		94.39 136		88.81 50	85.43 177

ACMP_Plane					94.17 160		94.39 136		88.81 50	85.43 177

HQP-MVS		89.80 102	89.28 100	91.34 134	94.17 160	81.56 133	94.39 136	96.04 102	88.81 50	85.43 177	93.97 129	73.83 170	97.96 135	87.11 100	89.77 174	94.50 186

MVS_111021_HR		93.45 39	93.31 38	93.84 51	96.99 56	84.84 57	93.24 215	97.24 20	88.76 53	91.60 69	95.85 74	86.07 32	98.66 82	91.91 43	98.16 46	98.03 50

mPP-MVS		93.99 29	93.78 31	94.63 30	98.50 9	85.90 48	96.87 16	96.91 42	88.70 54	91.83 65	97.17 23	83.96 53	99.55 8	91.44 53	98.64 32	98.43 21

VPNet		88.20 142	87.47 138	90.39 173	93.56 184	79.46 191	94.04 171	95.54 139	88.67 55	86.96 132	94.58 111	69.33 227	97.15 203	84.05 134	80.53 290	94.56 182

HFP-MVS		94.52 12	94.40 13	94.86 15	98.61 3	86.81 17	96.94 10	97.34 11	88.63 56	93.65 24	97.21 19	86.10 30	99.49 17	92.35 30	98.77 15	98.30 27

ACMMPR		94.43 16	94.28 16	94.91 13	98.63 2	86.69 22	96.94 10	97.32 16	88.63 56	93.53 31	97.26 16	85.04 43	99.54 11	92.35 30	98.78 14	98.50 12

region2R		94.43 16	94.27 17	94.92 12	98.65 1	86.67 24	96.92 14	97.23 22	88.60 58	93.58 28	97.27 14	85.22 40	99.54 11	92.21 32	98.74 19	98.56 11

WR-MVS		88.38 136	87.67 135	90.52 165	93.30 190	80.18 170	93.26 213	95.96 107	88.57 59	85.47 173	92.81 172	76.12 126	96.91 223	81.24 171	82.29 257	94.47 191

CP-MVS		94.34 19	94.21 20	94.74 27	98.39 16	86.64 26	97.60 1	97.24 20	88.53 60	92.73 44	97.23 17	85.20 41	99.32 28	92.15 35	98.83 11	98.25 35

CP-MVSNet		87.63 168	87.26 144	88.74 242	93.12 194	76.59 272	95.29 68	96.58 70	88.43 61	83.49 231	92.98 166	75.28 149	95.83 273	78.97 212	81.15 278	93.79 220

VDD-MVS		90.74 79	89.92 89	93.20 63	96.27 75	83.02 104	95.73 50	93.86 224	88.42 62	92.53 49	96.84 32	62.09 292	98.64 84	90.95 59	92.62 138	97.93 58

ACMMP		93.24 48	92.88 49	94.30 42	98.09 28	85.33 54	96.86 17	97.45 6	88.33 63	90.15 86	97.03 27	81.44 76	99.51 15	90.85 61	95.74 84	98.04 49
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
nrg030		91.08 76	90.39 76	93.17 65	93.07 195	86.91 15	96.41 24	96.26 83	88.30 64	88.37 105	94.85 102	82.19 67	97.64 151	91.09 55	82.95 251	94.96 155

ACMMP_Plus		94.74 11	94.56 12	95.28 5	98.02 31	87.70 5	95.68 53	97.34 11	88.28 65	95.30 11	97.67 4	85.90 34	99.54 11	93.91 10	98.95 5	98.60 9

test_part3							95.99 38		88.25 66		97.60 5		99.62 1	93.18 19

ESAPD		95.32 3	95.38 3	95.17 7	98.55 5	87.22 11	95.99 38	97.45 6	88.25 66	96.40 3	97.60 5	91.93 1	99.62 1	93.18 19	99.02 3	98.67 4

PS-CasMVS		87.32 184	86.88 156	88.63 245	92.99 201	76.33 275	95.33 63	96.61 67	88.22 68	83.30 234	93.07 160	73.03 181	95.79 276	78.36 217	81.00 283	93.75 226

MVS_111021_LR		92.47 56	92.29 56	92.98 74	95.99 92	84.43 72	93.08 220	96.09 96	88.20 69	91.12 76	95.72 79	81.33 78	97.76 144	91.74 47	97.37 62	96.75 100

TSAR-MVS + MP.		94.85 9	94.94 8	94.58 32	98.25 21	86.33 35	96.11 34	96.62 66	88.14 70	96.10 6	96.96 29	89.09 9	98.94 66	94.48 5	98.68 25	98.48 14

PEN-MVS		86.80 198	86.27 185	88.40 258	92.32 213	75.71 279	95.18 79	96.38 79	87.97 71	82.82 238	93.15 156	73.39 177	95.92 269	76.15 240	79.03 304	93.59 241

testdata1							92.15 249		87.94 72

VPA-MVSNet		89.62 104	88.96 106	91.60 128	93.86 174	82.89 109	95.46 62	97.33 14	87.91 73	88.43 104	93.31 149	74.17 164	97.40 181	87.32 96	82.86 253	94.52 184

WR-MVS_H		87.80 159	87.37 140	89.10 237	93.23 191	78.12 243	95.61 59	97.30 17	87.90 74	83.72 223	92.01 202	79.65 97	96.01 266	76.36 236	80.54 289	93.16 255

CLD-MVS		89.47 110	88.90 109	91.18 138	94.22 159	82.07 127	92.13 250	96.09 96	87.90 74	85.37 184	92.45 180	74.38 159	97.56 154	87.15 98	90.43 161	93.93 210
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
abl_6		93.18 50	93.05 43	93.57 59	97.52 39	84.27 75	95.53 61	96.67 62	87.85 76	93.20 34	97.22 18	80.35 84	99.18 35	91.91 43	97.21 63	97.26 79

MG-MVS		91.77 62	91.70 59	92.00 111	97.08 55	80.03 177	93.60 199	95.18 172	87.85 76	90.89 78	96.47 51	82.06 71	98.36 98	85.07 116	97.04 66	97.62 68

LCM-MVSNet-Re		88.30 140	88.32 123	88.27 261	94.71 141	72.41 306	93.15 216	90.98 292	87.77 78	79.25 281	91.96 203	78.35 108	95.75 277	83.04 142	95.62 85	96.65 102

Effi-MVS+-dtu		88.65 132	88.35 120	89.54 217	93.33 188	76.39 273	94.47 129	94.36 203	87.70 79	85.43 177	89.56 272	73.45 175	97.26 195	85.57 113	91.28 146	94.97 152

mvs-test1		89.45 111	89.14 102	90.38 175	93.33 188	77.63 258	94.95 93	94.36 203	87.70 79	87.10 131	92.81 172	73.45 175	98.03 132	85.57 113	93.04 133	95.48 139

test_prior3		93.60 37	93.53 36	93.82 52	97.29 49	84.49 65	94.12 158	96.88 44	87.67 81	92.63 46	96.39 53	86.62 26	98.87 68	91.50 50	98.67 27	98.11 44

test_prior2							94.12 158		87.67 81	92.63 46	96.39 53	86.62 26		91.50 50	98.67 27

Vis-MVSNet (Re-imp)		89.59 106	89.44 95	90.03 197	95.74 99	75.85 278	95.61 59	90.80 297	87.66 83	87.83 120	95.40 86	76.79 119	96.46 249	78.37 216	96.73 70	97.80 64

#test#		94.32 21	94.14 22	94.86 15	98.61 3	86.81 17	96.43 23	97.34 11	87.51 84	93.65 24	97.21 19	86.10 30	99.49 17	91.68 48	98.77 15	98.30 27

PGM-MVS		93.96 30	93.72 33	94.68 28	98.43 13	86.22 40	95.30 66	97.78 1	87.45 85	93.26 32	97.33 12	84.62 48	99.51 15	90.75 62	98.57 35	98.32 26

DTE-MVSNet		86.11 212	85.48 205	87.98 268	91.65 229	74.92 282	94.93 95	95.75 124	87.36 86	82.26 243	93.04 161	72.85 182	95.82 274	74.04 256	77.46 310	93.20 253

diffmvs		90.50 88	90.33 78	91.02 146	93.04 197	78.59 223	92.85 229	95.07 178	87.32 87	88.32 106	93.34 145	80.46 83	97.40 181	88.50 78	94.06 112	97.07 90

tfpn111		87.63 168	86.68 168	90.47 169	96.12 82	78.55 224	95.03 88	91.58 270	87.15 88	88.06 110	92.29 187	68.91 235	98.15 113	69.88 283	91.10 147	94.71 170

conf200view11		87.65 164	86.71 165	90.46 171	96.12 82	78.55 224	95.03 88	91.58 270	87.15 88	88.06 110	92.29 187	68.91 235	98.10 120	70.13 278	91.10 147	94.71 170

thres100view900		87.63 168	86.71 165	90.38 175	96.12 82	78.55 224	95.03 88	91.58 270	87.15 88	88.06 110	92.29 187	68.91 235	98.10 120	70.13 278	91.10 147	94.48 189

MCST-MVS		94.45 14	94.20 21	95.19 6	98.46 12	87.50 9	95.00 91	97.12 27	87.13 91	92.51 51	96.30 55	89.24 8	99.34 24	93.46 13	98.62 33	98.73 3

Effi-MVS+		91.59 68	91.11 66	93.01 73	94.35 158	83.39 95	94.60 120	95.10 175	87.10 92	90.57 81	93.10 159	81.43 77	98.07 129	89.29 71	94.48 105	97.59 70

view600		87.62 171	86.65 170	90.53 159	96.19 77	78.52 228	95.29 68	91.09 284	87.08 93	87.84 116	93.03 162	68.86 239	98.11 116	69.44 285	91.02 155	94.96 155

view800		87.62 171	86.65 170	90.53 159	96.19 77	78.52 228	95.29 68	91.09 284	87.08 93	87.84 116	93.03 162	68.86 239	98.11 116	69.44 285	91.02 155	94.96 155

conf0.05thres1000		87.62 171	86.65 170	90.53 159	96.19 77	78.52 228	95.29 68	91.09 284	87.08 93	87.84 116	93.03 162	68.86 239	98.11 116	69.44 285	91.02 155	94.96 155

tfpn		87.62 171	86.65 170	90.53 159	96.19 77	78.52 228	95.29 68	91.09 284	87.08 93	87.84 116	93.03 162	68.86 239	98.11 116	69.44 285	91.02 155	94.96 155

thres600view7		87.65 164	86.67 169	90.59 156	96.08 88	78.72 219	94.88 99	91.58 270	87.06 97	88.08 109	92.30 186	68.91 235	98.10 120	70.05 282	91.10 147	94.96 155

APD-MVS_3200maxsize		93.78 33	93.77 32	93.80 55	97.92 32	84.19 76	96.30 26	96.87 46	86.96 98	93.92 22	97.47 9	83.88 54	98.96 65	92.71 25	97.87 53	98.26 34

OMC-MVS		91.23 72	90.62 75	93.08 69	96.27 75	84.07 78	93.52 201	95.93 108	86.95 99	89.51 91	96.13 66	78.50 106	98.35 100	85.84 111	92.90 135	96.83 98

tfpn200view9		87.58 177	86.64 174	90.41 172	95.99 92	78.64 221	94.58 121	91.98 261	86.94 100	88.09 107	91.77 208	69.18 232	98.10 120	70.13 278	91.10 147	94.48 189

thres400		87.62 171	86.64 174	90.57 157	95.99 92	78.64 221	94.58 121	91.98 261	86.94 100	88.09 107	91.77 208	69.18 232	98.10 120	70.13 278	91.10 147	94.96 155

HPM-MVS		94.02 28	93.88 28	94.43 38	98.39 16	85.78 50	97.25 5	97.07 31	86.90 102	92.62 48	96.80 36	84.85 47	99.17 36	92.43 27	98.65 31	98.33 25
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
LFMVS		90.08 94	89.13 103	92.95 75	96.71 61	82.32 124	96.08 35	89.91 313	86.79 103	92.15 59	96.81 34	62.60 289	98.34 101	87.18 97	93.90 114	98.19 37

LPG-MVS_test		89.45 111	88.90 109	91.12 139	94.47 151	81.49 137	95.30 66	96.14 92	86.73 104	85.45 174	95.16 92	69.89 220	98.10 120	87.70 89	89.23 183	93.77 224

LGP-MVS_train				91.12 139	94.47 151	81.49 137		96.14 92	86.73 104	85.45 174	95.16 92	69.89 220	98.10 120	87.70 89	89.23 183	93.77 224

EPNet_dtu		86.49 208	85.94 196	88.14 266	90.24 294	72.82 298	94.11 160	92.20 252	86.66 106	79.42 280	92.36 184	73.52 173	95.81 275	71.26 269	93.66 118	95.80 131
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMP	84.23 8	89.01 126	88.35 120	90.99 149	94.73 139	81.27 143	95.07 85	95.89 114	86.48 107	83.67 225	94.30 116	69.33 227	97.99 134	87.10 102	88.55 196	93.72 228
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS_Test		91.31 71	91.11 66	91.93 115	94.37 155	80.14 172	93.46 204	95.80 120	86.46 108	91.35 73	93.77 140	82.21 66	98.09 127	87.57 91	94.95 96	97.55 73

thres200		87.21 190	86.24 186	90.12 188	95.36 112	78.53 227	93.26 213	92.10 254	86.42 109	88.00 113	91.11 243	69.24 231	98.00 133	69.58 284	91.04 154	93.83 219

PAPM_NR		91.22 73	90.78 74	92.52 91	97.60 36	81.46 139	94.37 140	96.24 86	86.39 110	87.41 126	94.80 104	82.06 71	98.48 93	82.80 148	95.37 91	97.61 69

PS-MVSNAJ		91.18 74	90.92 70	91.96 113	95.26 118	82.60 120	92.09 252	95.70 127	86.27 111	91.84 63	92.46 179	79.70 93	98.99 60	89.08 72	95.86 83	94.29 194

MP-MVS-pluss		94.21 25	94.00 27	94.85 17	98.17 24	86.65 25	94.82 103	97.17 25	86.26 112	92.83 39	97.87 3	85.57 37	99.56 3	94.37 7	98.92 7	98.34 24
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PS-MVSNAJss		89.97 97	89.62 91	91.02 146	91.90 219	80.85 158	95.26 75	95.98 105	86.26 112	86.21 148	94.29 117	79.70 93	97.65 149	88.87 75	88.10 205	94.57 181

EPP-MVSNet		91.70 66	91.56 60	92.13 108	95.88 95	80.50 168	97.33 3	95.25 165	86.15 114	89.76 89	95.60 81	83.42 55	98.32 103	87.37 95	93.25 129	97.56 72

XVG-OURS		89.40 116	88.70 112	91.52 129	94.06 163	81.46 139	91.27 267	96.07 98	86.14 115	88.89 100	95.77 77	68.73 244	97.26 195	87.39 94	89.96 170	95.83 129

xiu_mvs_v2_base		91.13 75	90.89 72	91.86 118	94.97 131	82.42 121	92.24 246	95.64 133	86.11 116	91.74 68	93.14 157	79.67 96	98.89 67	89.06 73	95.46 90	94.28 195

SMA-MVS		95.19 6	95.06 7	95.57 2	98.12 25	88.48 4	96.26 28	97.28 19	85.90 117	97.67 1	98.07 2	88.41 11	99.56 3	94.66 4	99.19 1	98.67 4

Fast-Effi-MVS+-dtu		87.44 181	86.72 164	89.63 215	92.04 218	77.68 257	94.03 172	93.94 222	85.81 118	82.42 241	91.32 232	70.33 217	97.06 211	80.33 189	90.23 166	94.14 199

XVG-OURS-SEG-HR		89.95 98	89.45 94	91.47 131	94.00 169	81.21 147	91.87 254	96.06 100	85.78 119	88.55 102	95.73 78	74.67 157	97.27 193	88.71 76	89.64 176	95.91 124

HPM-MVS_fast		93.40 42	93.22 40	93.94 49	98.36 18	84.83 58	97.15 7	96.80 50	85.77 120	92.47 52	97.13 25	82.38 62	99.07 45	90.51 64	98.40 40	97.92 59

EI-MVSNet		89.10 121	88.86 111	89.80 207	91.84 221	78.30 238	93.70 194	95.01 179	85.73 121	87.15 129	95.28 87	79.87 90	97.21 201	83.81 137	87.36 214	93.88 214

IterMVS-LS		88.36 138	87.91 133	89.70 212	93.80 177	78.29 239	93.73 190	95.08 177	85.73 121	84.75 199	91.90 206	79.88 89	96.92 222	83.83 136	82.51 255	93.89 212
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
APD-MVS		94.24 23	94.07 25	94.75 26	98.06 29	86.90 16	95.88 45	96.94 40	85.68 123	95.05 12	97.18 22	87.31 20	99.07 45	91.90 46	98.61 34	98.28 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
0601test		90.69 81	90.02 88	92.71 83	95.72 100	82.41 123	94.11 160	95.12 174	85.63 124	91.49 70	94.70 105	74.75 155	98.42 97	86.13 110	92.53 139	97.31 78

K. test v3		81.59 283	80.15 283	85.91 302	89.89 302	69.42 325	92.57 237	87.71 336	85.56 125	73.44 320	89.71 269	55.58 320	95.52 283	77.17 230	69.76 335	92.78 269

SixPastTwentyTwo		83.91 262	82.90 261	86.92 291	90.99 267	70.67 318	93.48 202	91.99 260	85.54 126	77.62 291	92.11 196	60.59 304	96.87 225	76.05 241	77.75 307	93.20 253

ITE_SJBPF				88.24 263	91.88 220	77.05 268		92.92 237	85.54 126	80.13 274	93.30 150	57.29 317	96.20 259	72.46 265	84.71 234	91.49 296

BH-RMVSNet		88.37 137	87.48 137	91.02 146	95.28 116	79.45 193	92.89 228	93.07 236	85.45 128	86.91 134	94.84 103	70.35 216	97.76 144	73.97 257	94.59 102	95.85 127

semantic-postprocess				88.18 265	91.71 226	76.87 270		92.65 245	85.40 129	81.44 256	90.54 254	66.21 271	95.00 305	81.04 173	81.05 279	92.66 271

GA-MVS		86.61 203	85.27 210	90.66 155	91.33 248	78.71 220	90.40 273	93.81 227	85.34 130	85.12 188	89.57 271	61.25 299	97.11 207	80.99 176	89.59 177	96.15 112

ACMM	84.12 9	89.14 120	88.48 119	91.12 139	94.65 146	81.22 146	95.31 64	96.12 95	85.31 131	85.92 152	94.34 113	70.19 219	98.06 130	85.65 112	88.86 194	94.08 204
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		90.64 83	90.05 85	92.40 95	93.97 171	84.46 68	93.32 206	95.46 146	85.17 132	92.25 54	94.03 123	70.59 211	98.57 89	90.97 56	94.67 98	94.18 196

xiu_mvs_v1_base		90.64 83	90.05 85	92.40 95	93.97 171	84.46 68	93.32 206	95.46 146	85.17 132	92.25 54	94.03 123	70.59 211	98.57 89	90.97 56	94.67 98	94.18 196

xiu_mvs_v1_base_debi		90.64 83	90.05 85	92.40 95	93.97 171	84.46 68	93.32 206	95.46 146	85.17 132	92.25 54	94.03 123	70.59 211	98.57 89	90.97 56	94.67 98	94.18 196

PHI-MVS		93.89 32	93.65 34	94.62 31	96.84 59	86.43 32	96.69 21	97.49 4	85.15 135	93.56 30	96.28 56	85.60 36	99.31 29	92.45 26	98.79 12	98.12 43

mvs_tets		88.06 148	87.28 143	90.38 175	90.94 271	79.88 180	95.22 77	95.66 130	85.10 136	84.21 216	93.94 131	63.53 286	97.40 181	88.50 78	88.40 203	93.87 215

XVG-ACMP-BASELINE		86.00 216	84.84 221	89.45 222	91.20 258	78.00 245	91.70 259	95.55 137	85.05 137	82.97 236	92.25 191	54.49 326	97.48 159	82.93 144	87.45 213	92.89 264

jajsoiax		88.24 141	87.50 136	90.48 168	90.89 275	80.14 172	95.31 64	95.65 132	84.97 138	84.24 215	94.02 126	65.31 278	97.42 174	88.56 77	88.52 198	93.89 212

v2v482		87.84 155	87.06 152	90.17 181	90.99 267	79.23 213	94.00 175	95.13 173	84.87 139	85.53 168	92.07 200	74.45 158	97.45 163	84.71 123	81.75 270	93.85 218

v148		87.04 194	86.32 183	89.21 233	90.94 271	77.26 266	93.71 193	94.43 201	84.84 140	84.36 211	90.80 248	76.04 132	97.05 212	82.12 159	79.60 301	93.31 250

v8		87.50 180	86.71 165	89.89 202	91.37 242	79.40 199	94.50 125	95.38 156	84.81 141	83.60 228	91.33 230	76.05 130	97.42 174	82.84 146	80.51 292	92.84 266

Anonymous20240521		86.87 196	85.95 195	89.64 214	92.89 204	78.88 218	95.66 55	96.05 101	84.77 142	81.92 251	92.39 182	71.54 197	96.96 218	76.46 235	81.87 267	93.08 260

BH-untuned		88.60 133	88.13 128	90.01 199	95.24 125	78.50 233	93.29 211	94.15 210	84.75 143	84.46 205	93.40 144	75.76 142	97.40 181	77.59 225	94.52 104	94.12 200

OurMVSNet-221017-0		85.35 234	84.64 226	87.49 278	90.77 278	72.59 304	94.01 174	94.40 202	84.72 144	79.62 279	93.17 155	61.91 294	96.72 234	81.99 162	81.16 276	93.16 255

MVSFormer		91.68 67	91.30 62	92.80 80	93.86 174	83.88 81	95.96 42	95.90 112	84.66 145	91.76 66	94.91 97	77.92 111	97.30 189	89.64 69	97.11 64	97.24 80

test_djsdf		89.03 124	88.64 113	90.21 180	90.74 280	79.28 207	95.96 42	95.90 112	84.66 145	85.33 186	92.94 167	74.02 167	97.30 189	89.64 69	88.53 197	94.05 206

MVSTER		88.84 128	88.29 124	90.51 166	92.95 202	80.44 169	93.73 190	95.01 179	84.66 145	87.15 129	93.12 158	72.79 183	97.21 201	87.86 87	87.36 214	93.87 215

v1neww		87.98 149	87.25 145	90.16 182	91.38 240	79.41 195	94.37 140	95.28 161	84.48 148	85.77 155	91.53 220	76.12 126	97.45 163	84.45 127	81.89 264	93.61 239

v7new		87.98 149	87.25 145	90.16 182	91.38 240	79.41 195	94.37 140	95.28 161	84.48 148	85.77 155	91.53 220	76.12 126	97.45 163	84.45 127	81.89 264	93.61 239

v6		87.98 149	87.25 145	90.16 182	91.36 243	79.39 200	94.37 140	95.27 164	84.48 148	85.78 154	91.51 222	76.15 125	97.46 161	84.46 126	81.88 266	93.62 238

v7n		86.81 197	85.76 199	89.95 201	90.72 281	79.25 209	95.07 85	95.92 109	84.45 151	82.29 242	90.86 247	72.60 187	97.53 156	79.42 209	80.52 291	93.08 260

v1141		87.84 155	87.09 149	90.11 193	91.23 255	79.25 209	94.08 165	95.24 166	84.44 152	85.69 162	91.31 233	75.91 138	97.44 170	84.17 132	81.74 271	93.63 237

divwei89l23v2f112		87.84 155	87.09 149	90.10 195	91.23 255	79.24 211	94.09 163	95.24 166	84.44 152	85.70 160	91.31 233	75.91 138	97.44 170	84.17 132	81.73 273	93.64 235

v1		87.85 154	87.10 148	90.11 193	91.21 257	79.24 211	94.09 163	95.24 166	84.44 152	85.70 160	91.31 233	75.96 136	97.45 163	84.18 131	81.73 273	93.64 235

v748		86.27 210	85.28 209	89.25 232	90.26 293	77.58 265	94.89 97	95.50 144	84.28 155	81.41 257	90.46 258	72.57 188	97.32 188	79.81 201	78.36 305	92.84 266

CSCG		93.23 49	93.05 43	93.76 56	98.04 30	84.07 78	96.22 29	97.37 10	84.15 156	90.05 87	95.66 80	87.77 14	99.15 39	89.91 67	98.27 43	98.07 46

Baseline_NR-MVSNet		87.07 193	86.63 176	88.40 258	91.44 233	77.87 250	94.23 149	92.57 246	84.12 157	85.74 159	92.08 198	77.25 115	96.04 263	82.29 157	79.94 298	91.30 300

casdiffmvs		91.72 65	91.26 64	93.10 67	94.66 144	83.75 84	94.77 107	96.00 104	83.98 158	90.74 79	93.96 130	82.08 69	98.19 109	91.47 52	93.68 117	97.36 76

ab-mvs		89.41 114	88.35 120	92.60 86	95.15 126	82.65 118	92.20 248	95.60 134	83.97 159	88.55 102	93.70 143	74.16 165	98.21 108	82.46 154	89.37 179	96.94 95

FMVSNet3		87.40 183	86.11 189	91.30 135	93.79 179	83.64 88	94.20 156	94.81 192	83.89 160	84.37 208	91.87 207	68.45 250	96.56 242	78.23 219	85.36 228	93.70 229

test_normal		88.13 145	86.78 163	92.18 105	90.55 288	81.19 148	92.74 232	94.64 196	83.84 161	77.49 292	90.51 257	68.49 248	98.16 111	88.22 81	94.55 103	97.21 83

pm-mvs1		86.61 203	85.54 201	89.82 204	91.44 233	80.18 170	95.28 74	94.85 189	83.84 161	81.66 254	92.62 177	72.45 191	96.48 247	79.67 203	78.06 306	92.82 268

DI_MVS_plusplus_test		88.15 144	86.82 159	92.14 107	90.67 283	81.07 150	93.01 223	94.59 197	83.83 163	77.78 288	90.63 251	68.51 247	98.16 111	88.02 86	94.37 109	97.17 85

v10		87.25 187	86.38 180	89.85 203	91.19 260	79.50 186	94.48 126	95.45 150	83.79 164	83.62 227	91.19 238	75.13 150	97.42 174	81.94 163	80.60 287	92.63 272

testgi		80.94 293	80.20 282	83.18 317	87.96 323	66.29 332	91.28 266	90.70 300	83.70 165	78.12 285	92.84 169	51.37 332	90.82 335	63.34 322	82.46 256	92.43 277

V42		87.68 162	86.86 157	90.15 186	90.58 285	80.14 172	94.24 148	95.28 161	83.66 166	85.67 163	91.33 230	74.73 156	97.41 179	84.43 129	81.83 268	92.89 264

v52		86.50 206	85.53 204	89.39 224	89.17 306	78.99 216	94.72 112	95.54 139	83.59 167	82.10 246	90.60 253	71.59 196	97.45 163	82.52 150	79.99 297	91.73 291

V4		86.50 206	85.54 201	89.39 224	89.13 307	78.99 216	94.73 109	95.54 139	83.59 167	82.10 246	90.61 252	71.60 195	97.45 163	82.52 150	80.01 296	91.74 290

GBi-Net		87.26 185	85.98 193	91.08 142	94.01 166	83.10 100	95.14 82	94.94 182	83.57 169	84.37 208	91.64 211	66.59 267	96.34 255	78.23 219	85.36 228	93.79 220

test1		87.26 185	85.98 193	91.08 142	94.01 166	83.10 100	95.14 82	94.94 182	83.57 169	84.37 208	91.64 211	66.59 267	96.34 255	78.23 219	85.36 228	93.79 220

FMVSNet2		87.19 191	85.82 198	91.30 135	94.01 166	83.67 87	94.79 105	94.94 182	83.57 169	83.88 219	92.05 201	66.59 267	96.51 245	77.56 226	85.01 232	93.73 227

Patchmatch-test1		85.81 223	84.71 223	89.12 235	92.15 214	76.60 271	91.12 270	91.69 268	83.53 172	85.50 171	88.56 285	66.79 265	95.00 305	72.69 264	90.35 163	95.76 132

PVSNet_BlendedMVS		89.98 96	89.70 90	90.82 153	96.12 82	81.25 144	93.92 178	96.83 47	83.49 173	89.10 96	92.26 190	81.04 80	98.85 74	86.72 106	87.86 209	92.35 281

v7		87.75 160	86.96 155	90.12 188	91.20 258	79.50 186	94.28 146	95.46 146	83.45 174	85.75 157	91.56 219	75.13 150	97.43 172	83.60 139	82.18 259	93.42 248

test-LLR		85.87 218	85.41 206	87.25 283	90.95 269	71.67 309	89.55 284	89.88 314	83.41 175	84.54 203	87.95 294	67.25 261	95.11 302	81.82 165	93.37 127	94.97 152

test0.0.03 1		82.41 275	81.69 268	84.59 311	88.23 318	72.89 297	90.24 275	87.83 335	83.41 175	79.86 276	89.78 268	67.25 261	88.99 338	65.18 316	83.42 249	91.90 288

Test4		85.75 225	83.72 243	91.83 120	88.08 321	81.03 152	92.48 239	95.54 139	83.38 177	73.40 321	88.57 284	50.99 333	97.37 186	86.61 108	94.47 106	97.09 89

v1144		87.61 176	86.79 162	90.06 196	91.01 266	79.34 203	93.95 177	95.42 155	83.36 178	85.66 164	91.31 233	74.98 154	97.42 174	83.37 140	82.06 260	93.42 248

PVSNet_Blended_VisFu		91.38 70	90.91 71	92.80 80	96.39 72	83.17 99	94.87 100	96.66 63	83.29 179	89.27 94	94.46 112	80.29 86	99.17 36	87.57 91	95.37 91	96.05 121

IB-MVS	80.51 15	85.24 237	83.26 256	91.19 137	92.13 216	79.86 181	91.75 256	91.29 282	83.28 180	80.66 266	88.49 286	61.28 298	98.46 94	80.99 176	79.46 302	95.25 146
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
IterMVS		84.88 246	83.98 238	87.60 274	91.44 233	76.03 277	90.18 277	92.41 248	83.24 181	81.06 262	90.42 259	66.60 266	94.28 311	79.46 205	80.98 284	92.48 275
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		89.41 114	88.64 113	91.71 125	94.74 138	80.81 159	93.54 200	95.10 175	83.11 182	86.82 137	90.67 250	79.74 92	97.75 147	80.51 185	93.55 120	96.57 104

WTY-MVS		89.60 105	88.92 108	91.67 126	95.47 110	81.15 149	92.38 243	94.78 193	83.11 182	89.06 98	94.32 115	78.67 103	96.61 241	81.57 169	90.89 159	97.24 80

V9		84.77 250	83.50 251	88.58 249	91.33 248	79.46 191	93.75 188	94.00 219	83.07 184	76.07 306	86.43 309	75.97 135	95.37 293	79.91 198	70.93 331	90.91 310

v15		84.79 248	83.53 249	88.57 252	91.30 254	79.41 195	93.70 194	94.01 216	83.06 185	76.27 300	86.42 312	76.03 133	95.38 292	80.01 193	71.00 328	90.92 309

v12		84.74 251	83.46 252	88.58 249	91.32 250	79.50 186	93.75 188	94.01 216	83.06 185	75.98 308	86.41 313	75.82 141	95.36 296	79.87 199	70.89 332	90.89 312

V14		84.79 248	83.52 250	88.57 252	91.32 250	79.43 194	93.72 192	94.01 216	83.06 185	76.22 301	86.43 309	76.01 134	95.37 293	79.96 195	70.99 329	90.91 310

v17		84.93 245	83.70 244	88.62 246	91.36 243	79.48 189	93.83 181	94.03 215	83.04 188	76.51 299	86.57 308	76.05 130	95.42 290	80.31 191	71.65 325	90.96 306

v16		84.96 243	83.74 242	88.62 246	91.40 238	79.48 189	93.83 181	94.04 213	83.03 189	76.54 298	86.59 307	76.11 129	95.42 290	80.33 189	71.80 323	90.95 308

v13		84.72 253	83.44 254	88.58 249	91.31 253	79.52 185	93.77 186	94.00 219	83.03 189	75.85 309	86.38 314	75.84 140	95.35 297	79.83 200	70.95 330	90.87 313

LTVRE_ROB	82.13 13	86.26 211	84.90 219	90.34 178	94.44 154	81.50 135	92.31 245	94.89 187	83.03 189	79.63 278	92.67 175	69.69 223	97.79 142	71.20 270	86.26 222	91.72 292
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
v18		84.97 242	83.76 240	88.60 248	91.36 243	79.41 195	93.82 183	94.04 213	83.00 192	76.61 297	86.60 306	76.19 124	95.43 289	80.39 186	71.79 324	90.96 306

UnsupCasMVSNet_eth		80.07 296	78.27 298	85.46 305	85.24 331	72.63 303	88.45 303	94.87 188	82.99 193	71.64 329	88.07 293	56.34 319	91.75 332	73.48 261	63.36 345	92.01 287

XXY-MVS		87.65 164	86.85 158	90.03 197	92.14 215	80.60 165	93.76 187	95.23 169	82.94 194	84.60 201	94.02 126	74.27 160	95.49 287	81.04 173	83.68 244	94.01 209

testing_2		83.40 268	81.02 273	90.56 158	85.06 332	80.51 167	91.37 265	95.57 135	82.92 195	67.06 336	85.54 320	49.47 336	97.24 197	86.74 103	85.44 227	93.93 210

mvs_anonymous		89.37 117	89.32 98	89.51 220	93.47 185	74.22 285	91.65 261	94.83 191	82.91 196	85.45 174	93.79 139	81.23 79	96.36 254	86.47 109	94.09 111	97.94 55

BH-w/o		87.57 178	87.05 153	89.12 235	94.90 135	77.90 248	92.41 241	93.51 230	82.89 197	83.70 224	91.34 229	75.75 143	97.07 210	75.49 243	93.49 122	92.39 279

v11		84.67 256	83.41 255	88.44 257	91.32 250	79.13 214	93.69 197	93.99 221	82.81 198	76.20 302	86.24 316	75.48 146	95.35 297	79.53 204	71.48 327	90.85 314

AdaColmap		89.89 101	89.07 104	92.37 98	97.41 43	83.03 103	94.42 133	95.92 109	82.81 198	86.34 146	94.65 108	73.89 168	99.02 54	80.69 180	95.51 87	95.05 149

TransMVSNet (Re)		84.43 258	83.06 259	88.54 254	91.72 225	78.44 234	95.18 79	92.82 240	82.73 200	79.67 277	92.12 194	73.49 174	95.96 268	71.10 273	68.73 339	91.21 301

PatchFormer-LS_test		86.02 215	85.13 211	88.70 243	91.52 230	74.12 288	91.19 269	92.09 255	82.71 201	84.30 214	87.24 303	70.87 206	96.98 216	81.04 173	85.17 231	95.00 151

DP-MVS Recon		91.95 60	91.28 63	93.96 48	98.33 19	85.92 45	94.66 118	96.66 63	82.69 202	90.03 88	95.82 75	82.30 64	99.03 51	84.57 124	96.48 78	96.91 96

v1192		87.25 187	86.33 182	90.00 200	90.76 279	79.04 215	93.80 184	95.48 145	82.57 203	85.48 172	91.18 239	73.38 178	97.42 174	82.30 156	82.06 260	93.53 243

API-MVS		90.66 82	90.07 84	92.45 94	96.36 73	84.57 63	96.06 36	95.22 171	82.39 204	89.13 95	94.27 120	80.32 85	98.46 94	80.16 192	96.71 71	94.33 193

tfpnnormal		84.72 253	83.23 257	89.20 234	92.79 206	80.05 175	94.48 126	95.81 119	82.38 205	81.08 261	91.21 237	69.01 234	96.95 220	61.69 327	80.59 288	90.58 319

MAR-MVS		90.30 90	89.37 97	93.07 71	96.61 64	84.48 67	95.68 53	95.67 128	82.36 206	87.85 115	92.85 168	76.63 122	98.80 78	80.01 193	96.68 72	95.91 124
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
TAMVS		89.21 119	88.29 124	91.96 113	93.71 180	82.62 119	93.30 210	94.19 208	82.22 207	87.78 122	93.94 131	78.83 100	96.95 220	77.70 224	92.98 134	96.32 108

ACMH+	81.04 14	85.05 240	83.46 252	89.82 204	94.66 144	79.37 201	94.44 131	94.12 212	82.19 208	78.04 286	92.82 171	58.23 314	97.54 155	73.77 259	82.90 252	92.54 273

ACMH	80.38 17	85.36 233	83.68 245	90.39 173	94.45 153	80.63 163	94.73 109	94.85 189	82.09 209	77.24 293	92.65 176	60.01 308	97.58 152	72.25 266	84.87 233	92.96 262
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tfpn1000		86.06 214	84.92 218	89.49 221	95.54 106	77.79 252	94.72 112	89.07 327	82.05 210	85.36 185	91.94 204	68.32 258	96.65 237	67.04 301	90.24 165	94.02 208

anonymousdsp		87.84 155	87.09 149	90.12 188	89.13 307	80.54 166	94.67 117	95.55 137	82.05 210	83.82 221	92.12 194	71.47 200	97.15 203	87.15 98	87.80 210	92.67 270

PVSNet_Blended		90.73 80	90.32 79	91.98 112	96.12 82	81.25 144	92.55 238	96.83 47	82.04 212	89.10 96	92.56 178	81.04 80	98.85 74	86.72 106	95.91 82	95.84 128

agg_prior1		93.29 44	92.97 46	94.26 43	97.38 44	85.92 45	93.92 178	96.72 57	81.96 213	92.16 57	96.23 58	87.85 13	98.97 62	91.95 42	98.55 38	97.90 60

CDS-MVSNet		89.45 111	88.51 115	92.29 102	93.62 182	83.61 90	93.01 223	94.68 195	81.95 214	87.82 121	93.24 153	78.69 102	96.99 215	80.34 188	93.23 130	96.28 109
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v144192		87.19 191	86.35 181	89.74 208	90.64 284	78.24 241	93.92 178	95.43 153	81.93 215	85.51 170	91.05 245	74.21 163	97.45 163	82.86 145	81.56 275	93.53 243

PAPR		90.02 95	89.27 101	92.29 102	95.78 98	80.95 155	92.68 233	96.22 87	81.91 216	86.66 139	93.75 142	82.23 65	98.44 96	79.40 210	94.79 97	97.48 74

v1921920		86.97 195	86.06 192	89.69 213	90.53 289	78.11 244	93.80 184	95.43 153	81.90 217	85.33 186	91.05 245	72.66 185	97.41 179	82.05 161	81.80 269	93.53 243

conf0.01		85.83 221	84.54 227	89.71 210	95.26 118	77.63 258	94.21 150	89.33 320	81.89 218	84.94 192	91.51 222	68.43 251	96.80 228	66.05 307	89.23 183	94.71 170

conf0.002		85.83 221	84.54 227	89.71 210	95.26 118	77.63 258	94.21 150	89.33 320	81.89 218	84.94 192	91.51 222	68.43 251	96.80 228	66.05 307	89.23 183	94.71 170

thresconf0.02		85.75 225	84.54 227	89.38 226	95.26 118	77.63 258	94.21 150	89.33 320	81.89 218	84.94 192	91.51 222	68.43 251	96.80 228	66.05 307	89.23 183	93.70 229

tfpn_n400		85.75 225	84.54 227	89.38 226	95.26 118	77.63 258	94.21 150	89.33 320	81.89 218	84.94 192	91.51 222	68.43 251	96.80 228	66.05 307	89.23 183	93.70 229

tfpnconf		85.75 225	84.54 227	89.38 226	95.26 118	77.63 258	94.21 150	89.33 320	81.89 218	84.94 192	91.51 222	68.43 251	96.80 228	66.05 307	89.23 183	93.70 229

tfpnview11		85.75 225	84.54 227	89.38 226	95.26 118	77.63 258	94.21 150	89.33 320	81.89 218	84.94 192	91.51 222	68.43 251	96.80 228	66.05 307	89.23 183	93.70 229

CPTT-MVS		91.99 59	91.80 58	92.55 89	98.24 23	81.98 129	96.76 19	96.49 72	81.89 218	90.24 84	96.44 52	78.59 104	98.61 87	89.68 68	97.85 54	97.06 91

tfpn_ndepth		86.10 213	84.98 214	89.43 223	95.52 109	78.29 239	94.62 119	89.60 319	81.88 225	85.43 177	90.54 254	68.47 249	96.85 227	68.46 294	90.34 164	93.15 257

train_agg		93.44 40	93.08 42	94.52 34	97.53 37	86.49 30	94.07 167	96.78 51	81.86 226	92.77 41	96.20 60	87.63 17	99.12 42	92.14 36	98.69 22	97.94 55

test_8					97.49 40	86.30 38	94.02 173	96.76 54	81.86 226	92.70 45	96.20 60	87.63 17	99.02 54

v1240		86.78 199	85.85 197	89.56 216	90.45 290	77.79 252	93.61 198	95.37 158	81.65 228	85.43 177	91.15 241	71.50 199	97.43 172	81.47 170	82.05 262	93.47 247

FMVSNet1		85.85 219	84.11 235	91.08 142	92.81 205	83.10 100	95.14 82	94.94 182	81.64 229	82.68 239	91.64 211	59.01 312	96.34 255	75.37 245	83.78 241	93.79 220

PatchmatchNet		85.85 219	84.70 224	89.29 231	91.76 224	75.54 280	88.49 301	91.30 281	81.63 230	85.05 189	88.70 282	71.71 193	96.24 258	74.61 253	89.05 192	96.08 118
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TEST9					97.53 37	86.49 30	94.07 167	96.78 51	81.61 231	92.77 41	96.20 60	87.71 16	99.12 42

sss		88.93 127	88.26 126	90.94 152	94.05 164	80.78 160	91.71 258	95.38 156	81.55 232	88.63 101	93.91 135	75.04 153	95.47 288	82.47 153	91.61 144	96.57 104

HY-MVS	83.01 12	89.03 124	87.94 132	92.29 102	94.86 136	82.77 110	92.08 253	94.49 199	81.52 233	86.93 133	92.79 174	78.32 109	98.23 105	79.93 196	90.55 160	95.88 126

agg_prior3		93.27 45	92.89 48	94.40 40	97.49 40	86.12 42	94.07 167	96.73 55	81.46 234	92.46 53	96.05 68	86.90 24	99.15 39	92.14 36	98.69 22	97.94 55

CNLPA		89.07 122	87.98 130	92.34 99	96.87 58	84.78 59	94.08 165	93.24 233	81.41 235	84.46 205	95.13 94	75.57 145	96.62 239	77.21 229	93.84 116	95.61 137

EPMVS		83.90 263	82.70 264	87.51 276	90.23 295	72.67 301	88.62 300	81.96 350	81.37 236	85.01 190	88.34 288	66.31 270	94.45 308	75.30 246	87.12 217	95.43 141

test20.03		79.95 297	79.08 294	82.55 319	85.79 329	67.74 330	91.09 271	91.08 288	81.23 237	74.48 316	89.96 266	61.63 295	90.15 336	60.08 331	76.38 312	89.76 321

TR-MVS		86.78 199	85.76 199	89.82 204	94.37 155	78.41 235	92.47 240	92.83 239	81.11 238	86.36 145	92.40 181	68.73 244	97.48 159	73.75 260	89.85 173	93.57 242

VDDNet		89.56 107	88.49 118	92.76 82	95.07 127	82.09 126	96.30 26	93.19 234	81.05 239	91.88 62	96.86 31	61.16 302	98.33 102	88.43 80	92.49 140	97.84 62

tpm		84.73 252	84.02 236	86.87 294	90.33 291	68.90 326	89.06 294	89.94 312	80.85 240	85.75 157	89.86 267	68.54 246	95.97 267	77.76 223	84.05 240	95.75 133

DWT-MVSNet_test		84.95 244	83.68 245	88.77 240	91.43 236	73.75 291	91.74 257	90.98 292	80.66 241	83.84 220	87.36 301	62.44 290	97.11 207	78.84 214	85.81 224	95.46 140

Anonymous202405211		87.68 162	86.13 187	92.31 100	96.66 62	80.74 161	94.87 100	91.49 277	80.47 242	89.46 93	95.44 83	54.72 325	98.23 105	82.19 158	89.89 171	97.97 53

jason		90.80 78	90.10 83	92.90 77	93.04 197	83.53 91	93.08 220	94.15 210	80.22 243	91.41 72	94.91 97	76.87 117	97.93 138	90.28 66	96.90 67	97.24 80
jason: jason.
tpmrst		85.35 234	84.99 213	86.43 297	90.88 276	67.88 329	88.71 298	91.43 279	80.13 244	86.08 151	88.80 280	73.05 180	96.02 265	82.48 152	83.40 250	95.40 142

CDPH-MVS		92.83 53	92.30 55	94.44 36	97.79 34	86.11 43	94.06 170	96.66 63	80.09 245	92.77 41	96.63 43	86.62 26	99.04 50	87.40 93	98.66 29	98.17 38

PM-MVS		78.11 305	76.12 307	84.09 316	83.54 337	70.08 322	88.97 296	85.27 344	79.93 246	74.73 314	86.43 309	34.70 351	93.48 318	79.43 208	72.06 322	88.72 331

lupinMVS		90.92 77	90.21 80	93.03 72	93.86 174	83.88 81	92.81 230	93.86 224	79.84 247	91.76 66	94.29 117	77.92 111	98.04 131	90.48 65	97.11 64	97.17 85

PatchMatch-RL		86.77 201	85.54 201	90.47 169	95.88 95	82.71 116	90.54 272	92.31 249	79.82 248	84.32 212	91.57 218	68.77 243	96.39 252	73.16 262	93.48 124	92.32 282

PLC	84.53 7	89.06 123	88.03 129	92.15 106	97.27 51	82.69 117	94.29 145	95.44 152	79.71 249	84.01 218	94.18 122	76.68 121	98.75 80	77.28 228	93.41 125	95.02 150
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
F-COLMAP		87.95 152	86.80 161	91.40 133	96.35 74	80.88 157	94.73 109	95.45 150	79.65 250	82.04 249	94.61 109	71.13 202	98.50 92	76.24 239	91.05 153	94.80 168

MIMVSNet		82.59 274	80.53 277	88.76 241	91.51 231	78.32 237	86.57 316	90.13 307	79.32 251	80.70 265	88.69 283	52.98 330	93.07 325	66.03 313	88.86 194	94.90 163

test-mter		84.54 257	83.64 247	87.25 283	90.95 269	71.67 309	89.55 284	89.88 314	79.17 252	84.54 203	87.95 294	55.56 321	95.11 302	81.82 165	93.37 127	94.97 152

MDA-MVSNet-bldmvs		78.85 304	76.31 305	86.46 296	89.76 303	73.88 290	88.79 297	90.42 301	79.16 253	59.18 344	88.33 289	60.20 306	94.04 313	62.00 326	68.96 337	91.48 297

tpmvs		83.35 269	82.07 266	87.20 287	91.07 265	71.00 316	88.31 304	91.70 267	78.91 254	80.49 269	87.18 304	69.30 230	97.08 209	68.12 299	83.56 246	93.51 246

原ACMM1				92.01 109	97.34 46	81.05 151		96.81 49	78.89 255	90.45 82	95.92 71	82.65 60	98.84 76	80.68 181	98.26 44	96.14 113

MSDG		84.86 247	83.09 258	90.14 187	93.80 177	80.05 175	89.18 293	93.09 235	78.89 255	78.19 284	91.91 205	65.86 277	97.27 193	68.47 293	88.45 200	93.11 258

PAPM		86.68 202	85.39 207	90.53 159	93.05 196	79.33 206	89.79 283	94.77 194	78.82 257	81.95 250	93.24 153	76.81 118	97.30 189	66.94 302	93.16 131	94.95 162

PVSNet	78.82 18	85.55 231	84.65 225	88.23 264	94.72 140	71.93 307	87.12 313	92.75 242	78.80 258	84.95 191	90.53 256	64.43 283	96.71 236	74.74 251	93.86 115	96.06 120

MVP-Stereo		85.97 217	84.86 220	89.32 230	90.92 273	82.19 125	92.11 251	94.19 208	78.76 259	78.77 283	91.63 214	68.38 257	96.56 242	75.01 250	93.95 113	89.20 326
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
OpenMVS	83.78 11	88.74 131	87.29 142	93.08 69	92.70 207	85.39 53	96.57 22	96.43 75	78.74 260	80.85 263	96.07 67	69.64 224	99.01 56	78.01 222	96.65 73	94.83 166

MDTV_nov1_ep13			83.56 248		91.69 228	69.93 323	87.75 309	91.54 275	78.60 261	84.86 198	88.90 278	69.54 225	96.03 264	70.25 275	88.93 193

Patchmatch-RL test		81.67 281	79.96 285	86.81 295	85.42 330	71.23 312	82.17 340	87.50 339	78.47 262	77.19 294	82.50 330	70.81 208	93.48 318	82.66 149	72.89 320	95.71 134

QAPM		89.51 108	88.15 127	93.59 58	94.92 133	84.58 62	96.82 18	96.70 59	78.43 263	83.41 232	96.19 63	73.18 179	99.30 30	77.11 231	96.54 76	96.89 97

1314		87.51 179	86.57 178	90.34 178	92.42 211	79.74 184	92.63 234	95.35 160	78.35 264	80.14 273	91.62 215	74.05 166	97.15 203	81.05 172	93.53 121	94.12 200

CR-MVSNet		85.35 234	83.76 240	90.12 188	90.58 285	79.34 203	85.24 325	91.96 263	78.27 265	85.55 166	87.87 297	71.03 204	95.61 279	73.96 258	89.36 180	95.40 142

USDC		82.76 271	81.26 272	87.26 282	91.17 261	74.55 283	89.27 290	93.39 232	78.26 266	75.30 311	92.08 198	54.43 327	96.63 238	71.64 267	85.79 226	90.61 316

new-patchmatchnet		76.41 308	75.17 308	80.13 322	82.65 340	59.61 342	87.66 310	91.08 288	78.23 267	69.85 331	83.22 327	54.76 324	91.63 334	64.14 321	64.89 342	89.16 327

1112_ss		88.42 135	87.33 141	91.72 124	94.92 133	80.98 153	92.97 226	94.54 198	78.16 268	83.82 221	93.88 136	78.78 101	97.91 139	79.45 206	89.41 178	96.26 110

MIMVSNet1		79.38 301	77.28 301	85.69 303	86.35 328	73.67 292	91.61 262	92.75 242	78.11 269	72.64 325	88.12 292	48.16 338	91.97 331	60.32 330	77.49 309	91.43 298

MS-PatchMatch		85.05 240	84.16 234	87.73 272	91.42 237	78.51 232	91.25 268	93.53 229	77.50 270	80.15 272	91.58 216	61.99 293	95.51 284	75.69 242	94.35 110	89.16 327

AllTest		83.42 266	81.39 270	89.52 218	95.01 128	77.79 252	93.12 217	90.89 295	77.41 271	76.12 304	93.34 145	54.08 328	97.51 157	68.31 296	84.27 238	93.26 251

TestCases				89.52 218	95.01 128	77.79 252		90.89 295	77.41 271	76.12 304	93.34 145	54.08 328	97.51 157	68.31 296	84.27 238	93.26 251

TESTMET0.1,1		83.74 265	82.85 262	86.42 298	89.96 300	71.21 313	89.55 284	87.88 334	77.41 271	83.37 233	87.31 302	56.71 318	93.65 317	80.62 182	92.85 137	94.40 192

gm-plane-assit					89.60 305	68.00 328			77.28 274		88.99 276		97.57 153	79.44 207

EG-PatchMatch MVS		82.37 276	80.34 279	88.46 256	90.27 292	79.35 202	92.80 231	94.33 205	77.14 275	73.26 322	90.18 262	47.47 340	96.72 234	70.25 275	87.32 216	89.30 324

FMVSNet5		81.52 285	79.60 289	87.27 281	91.17 261	77.95 246	91.49 263	92.26 251	76.87 276	76.16 303	87.91 296	51.67 331	92.34 327	67.74 300	81.16 276	91.52 295

our_test_3		81.93 278	80.46 278	86.33 299	88.46 315	73.48 293	88.46 302	91.11 283	76.46 277	76.69 295	88.25 290	66.89 264	94.36 310	68.75 291	79.08 303	91.14 303

TDRefinement		79.81 298	77.34 300	87.22 286	79.24 346	75.48 281	93.12 217	92.03 258	76.45 278	75.01 312	91.58 216	49.19 337	96.44 250	70.22 277	69.18 336	89.75 322

LF4IMVS		80.37 295	79.07 295	84.27 315	86.64 327	69.87 324	89.39 289	91.05 290	76.38 279	74.97 313	90.00 264	47.85 339	94.25 312	74.55 254	80.82 286	88.69 332

TAPA-MVS	84.62 6	88.16 143	87.01 154	91.62 127	96.64 63	80.65 162	94.39 136	96.21 90	76.38 279	86.19 149	95.44 83	79.75 91	98.08 128	62.75 325	95.29 93	96.13 114
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dp		81.47 286	80.23 281	85.17 308	89.92 301	65.49 335	86.74 314	90.10 308	76.30 281	81.10 260	87.12 305	62.81 288	95.92 269	68.13 298	79.88 299	94.09 203

CostFormer		85.77 224	84.94 217	88.26 262	91.16 263	72.58 305	89.47 288	91.04 291	76.26 282	86.45 143	89.97 265	70.74 209	96.86 226	82.35 155	87.07 219	95.34 145

RPSCF		85.07 239	84.27 233	87.48 279	92.91 203	70.62 319	91.69 260	92.46 247	76.20 283	82.67 240	95.22 90	63.94 285	97.29 192	77.51 227	85.80 225	94.53 183

Test_1112_low_res		87.65 164	86.51 179	91.08 142	94.94 132	79.28 207	91.77 255	94.30 206	76.04 284	83.51 230	92.37 183	77.86 113	97.73 148	78.69 215	89.13 191	96.22 111

pmmvs4		85.43 232	83.86 239	90.16 182	90.02 299	82.97 107	90.27 274	92.67 244	75.93 285	80.73 264	91.74 210	71.05 203	95.73 278	78.85 213	83.46 248	91.78 289

LS3D		87.89 153	86.32 183	92.59 87	96.07 89	82.92 108	95.23 76	94.92 186	75.66 286	82.89 237	95.98 69	72.48 189	99.21 33	68.43 295	95.23 95	95.64 136

pmmvs5		84.21 259	82.84 263	88.34 260	88.95 310	76.94 269	92.41 241	91.91 265	75.63 287	80.28 270	91.18 239	64.59 282	95.57 281	77.09 232	83.47 247	92.53 274

pmmvs-eth3d		80.97 292	78.72 297	87.74 271	84.99 333	79.97 179	90.11 278	91.65 269	75.36 288	73.51 319	86.03 317	59.45 310	93.96 314	75.17 247	72.21 321	89.29 325

ppachtmachnet_test		81.84 279	80.07 284	87.15 288	88.46 315	74.43 284	89.04 295	92.16 253	75.33 289	77.75 289	88.99 276	66.20 272	95.37 293	65.12 317	77.60 308	91.65 293

test_0402		81.30 289	79.17 293	87.67 273	93.19 192	78.17 242	92.98 225	91.71 266	75.25 290	76.02 307	90.31 260	59.23 311	96.37 253	50.22 342	83.63 245	88.47 336

COLMAP_ROB	80.39 16	83.96 261	82.04 267	89.74 208	95.28 116	79.75 183	94.25 147	92.28 250	75.17 291	78.02 287	93.77 140	58.60 313	97.84 141	65.06 318	85.92 223	91.63 294
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TinyColmap		79.76 299	77.69 299	85.97 301	91.71 226	73.12 295	89.55 284	90.36 303	75.03 292	72.03 327	90.19 261	46.22 342	96.19 260	63.11 323	81.03 280	88.59 333

DP-MVS		87.25 187	85.36 208	92.90 77	97.65 35	83.24 97	94.81 104	92.00 259	74.99 293	81.92 251	95.00 96	72.66 185	99.05 47	66.92 304	92.33 141	96.40 106

PatchT		82.68 273	81.27 271	86.89 293	90.09 297	70.94 317	84.06 332	90.15 306	74.91 294	85.63 165	83.57 326	69.37 226	94.87 307	65.19 315	88.50 199	94.84 165

CHOSEN 280x420		85.15 238	83.99 237	88.65 244	92.47 210	78.40 236	79.68 345	92.76 241	74.90 295	81.41 257	89.59 270	69.85 222	95.51 284	79.92 197	95.29 93	92.03 286

gg-mvs-nofinetune		81.77 280	79.37 290	88.99 238	90.85 277	77.73 256	86.29 317	79.63 354	74.88 296	83.19 235	69.05 347	60.34 305	96.11 262	75.46 244	94.64 101	93.11 258

pmmvs6		83.42 266	81.60 269	88.87 239	88.01 322	77.87 250	94.96 92	94.24 207	74.67 297	78.80 282	91.09 244	60.17 307	96.49 246	77.06 233	75.40 315	92.23 284

CHOSEN 1792x2688		88.84 128	87.69 134	92.30 101	96.14 81	81.42 141	90.01 279	95.86 116	74.52 298	87.41 126	93.94 131	75.46 147	98.36 98	80.36 187	95.53 86	97.12 88

MDA-MVSNet_test_wron		79.21 303	77.19 303	85.29 306	88.22 319	72.77 300	85.87 320	90.06 309	74.34 299	62.62 343	87.56 300	66.14 274	91.99 330	66.90 305	73.01 318	91.10 305

YYNet1		79.22 302	77.20 302	85.28 307	88.20 320	72.66 302	85.87 320	90.05 311	74.33 300	62.70 342	87.61 299	66.09 275	92.03 329	66.94 302	72.97 319	91.15 302

Anonymous20240529		88.09 146	86.59 177	92.58 88	96.53 68	81.92 130	95.99 38	95.84 117	74.11 301	89.06 98	95.21 91	61.44 297	98.81 77	83.67 138	87.47 211	97.01 92

无先验							93.28 212	96.26 83	73.95 302				99.05 47	80.56 183		96.59 103

Anonymous20231211		86.59 205	85.13 211	90.98 151	96.52 69	81.50 135	96.14 32	96.16 91	73.78 303	83.65 226	92.15 192	63.26 287	97.37 186	82.82 147	81.74 271	94.06 205

Anonymous20231206		81.03 291	79.77 287	84.82 310	87.85 325	70.26 321	91.42 264	92.08 256	73.67 304	77.75 289	89.25 274	62.43 291	93.08 324	61.50 328	82.00 263	91.12 304

PCF-MVS	84.11 10	87.74 161	86.08 191	92.70 84	94.02 165	84.43 72	89.27 290	95.87 115	73.62 305	84.43 207	94.33 114	78.48 107	98.86 71	70.27 274	94.45 107	94.81 167
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HyFIR lowres test		88.09 146	86.81 160	91.93 115	96.00 91	80.63 163	90.01 279	95.79 121	73.42 306	87.68 124	92.10 197	73.86 169	97.96 135	80.75 179	91.70 143	97.19 84

MDTV_nov1_ep13_2view						55.91 350	87.62 311		73.32 307	84.59 202		70.33 217		74.65 252		95.50 138

JIA-IIPM		81.04 290	78.98 296	87.25 283	88.64 312	73.48 293	81.75 341	89.61 318	73.19 308	82.05 248	73.71 344	66.07 276	95.87 272	71.18 272	84.60 235	92.41 278

cascas		86.43 209	84.98 214	90.80 154	92.10 217	80.92 156	90.24 275	95.91 111	73.10 309	83.57 229	88.39 287	65.15 279	97.46 161	84.90 120	91.43 145	94.03 207

ANet_high		58.88 326	54.22 329	72.86 333	56.50 362	56.67 347	80.75 343	86.00 341	73.09 310	37.39 353	64.63 351	22.17 358	79.49 356	43.51 351	23.96 357	82.43 345

tpmp4_e23		83.87 264	82.33 265	88.48 255	91.46 232	72.82 298	89.82 282	91.57 274	73.02 311	81.86 253	89.05 275	66.20 272	96.97 217	71.57 268	86.39 221	95.66 135

ADS-MVSNet2		81.66 282	79.71 288	87.50 277	91.35 246	74.19 286	83.33 336	88.48 331	72.90 312	82.24 244	85.77 318	64.98 280	93.20 322	64.57 319	83.74 242	95.12 147

ADS-MVSNet		81.56 284	79.78 286	86.90 292	91.35 246	71.82 308	83.33 336	89.16 326	72.90 312	82.24 244	85.77 318	64.98 280	93.76 315	64.57 319	83.74 242	95.12 147

PVSNet_0	73.20 20	77.22 306	74.83 309	84.37 313	90.70 282	71.10 314	83.09 338	89.67 317	72.81 314	73.93 318	83.13 328	60.79 303	93.70 316	68.54 292	50.84 350	88.30 337

testdata				90.49 167	96.40 71	77.89 249		95.37 158	72.51 315	93.63 26	96.69 39	82.08 69	97.65 149	83.08 141	97.39 61	95.94 123

PMMVS		85.71 230	84.96 216	87.95 269	88.90 311	77.09 267	88.68 299	90.06 309	72.32 316	86.47 140	90.76 249	72.15 192	94.40 309	81.78 167	93.49 122	92.36 280

testus		74.41 312	73.35 310	77.59 328	82.49 341	57.08 345	86.02 318	90.21 305	72.28 317	72.89 324	84.32 323	37.08 349	86.96 344	52.24 339	82.65 254	88.73 330

Patchmtry		82.71 272	80.93 275	88.06 267	90.05 298	76.37 274	84.74 327	91.96 263	72.28 317	81.32 259	87.87 297	71.03 204	95.50 286	68.97 290	80.15 294	92.32 282

tpm2		84.08 260	82.94 260	87.48 279	91.39 239	71.27 311	89.23 292	90.37 302	71.95 319	84.64 200	89.33 273	67.30 260	96.55 244	75.17 247	87.09 218	94.63 175

UnsupCasMVSNet_bld		76.23 309	73.27 311	85.09 309	83.79 336	72.92 296	85.65 324	93.47 231	71.52 320	68.84 333	79.08 340	49.77 334	93.21 321	66.81 306	60.52 347	89.13 329

RPMNet		83.18 270	80.87 276	90.12 188	90.58 285	79.34 203	85.24 325	90.78 298	71.44 321	85.55 166	82.97 329	70.87 206	95.61 279	61.01 329	89.36 180	95.40 142

test2356		74.50 311	73.27 311	78.20 324	80.81 342	59.84 340	83.76 335	88.33 333	71.43 322	72.37 326	81.84 333	45.60 343	86.26 346	50.97 340	84.32 236	88.50 334

旧先验2							93.36 205		71.25 323	94.37 14			97.13 206	86.74 103

testpf		71.41 317	72.11 315	69.30 337	84.53 334	59.79 341	62.74 355	83.14 347	71.11 324	68.83 334	81.57 335	46.70 341	84.83 351	74.51 255	75.86 314	63.30 351

新几何1				93.10 67	97.30 48	84.35 74		95.56 136	71.09 325	91.26 74	96.24 57	82.87 59	98.86 71	79.19 211	98.10 48	96.07 119

1121		90.42 89	89.49 93	93.20 63	97.27 51	84.46 68	92.63 234	95.51 143	71.01 326	91.20 75	96.21 59	82.92 58	99.05 47	80.56 183	98.07 49	96.10 117

Patchmatch-test		81.37 287	79.30 291	87.58 275	90.92 273	74.16 287	80.99 342	87.68 337	70.52 327	76.63 296	88.81 279	71.21 201	92.76 326	60.01 333	86.93 220	95.83 129

114514_t		89.51 108	88.50 116	92.54 90	98.11 26	81.99 128	95.16 81	96.36 80	70.19 328	85.81 153	95.25 89	76.70 120	98.63 85	82.07 160	96.86 69	97.00 93

test1235678		72.22 314	70.31 316	77.93 327	78.04 347	58.04 344	85.76 322	89.80 316	70.15 329	63.43 341	80.20 338	42.24 346	87.24 343	48.68 344	74.50 316	88.50 334

N_pmnet		68.89 319	68.44 320	70.23 335	89.07 309	28.79 364	88.06 305	19.50 365	69.47 330	71.86 328	84.93 321	61.24 300	91.75 332	54.70 337	77.15 311	90.15 320

OpenMVS_ROB	74.94 19	79.51 300	77.03 304	86.93 290	87.00 326	76.23 276	92.33 244	90.74 299	68.93 331	74.52 315	88.23 291	49.58 335	96.62 239	57.64 335	84.29 237	87.94 338

test222					96.55 67	81.70 132	92.22 247	95.01 179	68.36 332	90.20 85	96.14 65	80.26 87			97.80 55	96.05 121

LP		75.51 310	72.15 314	85.61 304	87.86 324	73.93 289	80.20 344	88.43 332	67.39 333	70.05 330	80.56 337	58.18 315	93.18 323	46.28 348	70.36 334	89.71 323

1111		70.54 318	69.71 318	73.04 332	79.30 344	44.83 357	84.23 330	88.96 328	67.33 334	65.42 338	82.28 331	41.11 347	88.11 341	47.12 346	71.60 326	86.19 340

.test1245		57.63 328	61.79 325	45.14 346	79.30 344	44.83 357	84.23 330	88.96 328	67.33 334	65.42 338	82.28 331	41.11 347	88.11 341	47.12 346	0.39 361	2.46 362

MVS		87.44 181	86.10 190	91.44 132	92.61 209	83.62 89	92.63 234	95.66 130	67.26 336	81.47 255	92.15 192	77.95 110	98.22 107	79.71 202	95.48 88	92.47 276

tpm cat1		81.96 277	80.27 280	87.01 289	91.09 264	71.02 315	87.38 312	91.53 276	66.25 337	80.17 271	86.35 315	68.22 259	96.15 261	69.16 289	82.29 257	93.86 217

CVMVSNet		84.69 255	84.79 222	84.37 313	91.84 221	64.92 336	93.70 194	91.47 278	66.19 338	86.16 150	95.28 87	67.18 263	93.33 320	80.89 178	90.42 162	94.88 164

testmv		65.49 321	62.66 322	73.96 331	68.78 353	53.14 352	84.70 328	88.56 330	65.94 339	52.35 347	74.65 343	25.02 356	85.14 349	43.54 350	60.40 348	83.60 341

test12356		64.99 322	63.78 321	68.61 339	72.69 350	39.14 360	78.46 346	87.61 338	64.91 340	55.77 345	77.48 341	28.10 353	85.59 348	44.69 349	64.35 343	81.12 346

CMPMVS	59.16 21	80.52 294	79.20 292	84.48 312	83.98 335	67.63 331	89.95 281	93.84 226	64.79 341	66.81 337	91.14 242	57.93 316	95.17 300	76.25 238	88.10 205	90.65 315
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		81.32 288	80.95 274	82.42 320	88.50 314	63.67 337	93.32 206	91.33 280	64.02 342	80.57 268	92.83 170	61.21 301	92.27 328	76.34 237	80.38 293	91.32 299

no-one		61.56 324	56.58 326	76.49 330	67.80 356	62.76 339	78.13 347	86.11 340	63.16 343	43.24 351	64.70 350	26.12 355	88.95 339	50.84 341	29.15 353	77.77 348

new_pmnet		72.15 315	70.13 317	78.20 324	82.95 339	65.68 333	83.91 333	82.40 349	62.94 344	64.47 340	79.82 339	42.85 345	86.26 346	57.41 336	74.44 317	82.65 344

DSMNet-mixed		76.94 307	76.29 306	78.89 323	83.10 338	56.11 349	87.78 308	79.77 353	60.65 345	75.64 310	88.71 281	61.56 296	88.34 340	60.07 332	89.29 182	92.21 285

pmmvs3		71.81 316	68.71 319	81.11 321	75.86 348	70.42 320	86.74 314	83.66 346	58.95 346	68.64 335	80.89 336	36.93 350	89.52 337	63.10 324	63.59 344	83.39 342

MVS-HIRNet		73.70 313	72.20 313	78.18 326	91.81 223	56.42 348	82.94 339	82.58 348	55.24 347	68.88 332	66.48 348	55.32 323	95.13 301	58.12 334	88.42 202	83.01 343

PMMVS2		59.60 325	56.40 327	69.21 338	68.83 352	46.58 355	73.02 353	77.48 357	55.07 348	49.21 349	72.95 346	17.43 362	80.04 354	49.32 343	44.33 351	80.99 347

FPMVS		64.63 323	62.55 323	70.88 334	70.80 351	56.71 346	84.42 329	84.42 345	51.78 349	49.57 348	81.61 334	23.49 357	81.48 353	40.61 353	76.25 313	74.46 350

LCM-MVSNet		66.00 320	62.16 324	77.51 329	64.51 358	58.29 343	83.87 334	90.90 294	48.17 350	54.69 346	73.31 345	16.83 363	86.75 345	65.47 314	61.67 346	87.48 339

DeepMVS_CX				56.31 344	74.23 349	51.81 353		56.67 363	44.85 351	48.54 350	75.16 342	27.87 354	58.74 361	40.92 352	52.22 349	58.39 355

PNet_i23d		50.48 331	47.18 331	60.36 342	68.59 354	44.56 359	72.75 354	72.61 358	43.92 352	33.91 355	60.19 353	6.16 364	73.52 357	38.50 354	28.04 354	63.01 352

Gipuma		57.99 327	54.91 328	67.24 340	88.51 313	65.59 334	52.21 358	90.33 304	43.58 353	42.84 352	51.18 355	20.29 360	85.07 350	34.77 355	70.45 333	51.05 356
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	47.18 22	52.22 329	48.46 330	63.48 341	45.72 363	46.20 356	73.41 351	78.31 355	41.03 354	30.06 356	65.68 349	6.05 365	83.43 352	30.04 356	65.86 340	60.80 353
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuykxyi23d		50.55 330	44.13 332	69.81 336	56.77 360	54.58 351	73.22 352	80.78 351	39.79 355	22.08 360	46.69 357	4.03 367	79.71 355	47.65 345	26.13 355	75.14 349

E-PMN		43.23 333	42.29 333	46.03 345	65.58 357	37.41 361	73.51 350	64.62 359	33.99 356	28.47 358	47.87 356	19.90 361	67.91 358	22.23 358	24.45 356	32.77 357

EMVS		42.07 334	41.12 334	44.92 347	63.45 359	35.56 363	73.65 349	63.48 360	33.05 357	26.88 359	45.45 358	21.27 359	67.14 359	19.80 359	23.02 358	32.06 358

MVE	39.65 23	43.39 332	38.59 337	57.77 343	56.52 361	48.77 354	55.38 357	58.64 362	29.33 358	28.96 357	52.65 354	4.68 366	64.62 360	28.11 357	33.07 352	59.93 354
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 338	20.48 339	23.63 350	68.59 354	36.41 362	49.57 359	6.85 366	9.37 359	7.89 361	4.46 364	4.03 367	31.37 362	17.47 360	16.07 360	3.12 360

tmp_tt		35.64 336	39.24 335	24.84 349	14.87 364	23.90 365	62.71 356	51.51 364	6.58 360	36.66 354	62.08 352	44.37 344	30.34 363	52.40 338	22.00 359	20.27 359

testmvs		8.92 339	11.52 340	1.12 352	1.06 365	0.46 367	86.02 318	0.65 367	0.62 361	2.74 362	9.52 362	0.31 370	0.45 365	2.38 361	0.39 361	2.46 362

test123		8.76 340	11.22 341	1.39 351	0.85 366	0.97 366	85.76 322	0.35 368	0.54 362	2.45 363	8.14 363	0.60 369	0.48 364	2.16 362	0.17 363	2.71 361

cdsmvs_eth3d_5k		22.14 337	29.52 338	0.00 353	0.00 367	0.00 368	0.00 360	95.76 123	0.00 363	0.00 364	94.29 117	75.66 144	0.00 366	0.00 363	0.00 364	0.00 364

pcd_1.5k_mvsjas		6.64 342	8.86 343	0.00 353	0.00 367	0.00 368	0.00 360	0.00 369	0.00 363	0.00 364	0.00 365	79.70 93	0.00 366	0.00 363	0.00 364	0.00 364

pcd1.5k->3k		37.02 335	38.84 336	31.53 348	92.33 212	0.00 368	0.00 360	96.13 94	0.00 363	0.00 364	0.00 365	72.70 184	0.00 366	0.00 363	88.43 201	94.60 178

sosnet-low-res		0.00 343	0.00 344	0.00 353	0.00 367	0.00 368	0.00 360	0.00 369	0.00 363	0.00 364	0.00 365	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

sosnet		0.00 343	0.00 344	0.00 353	0.00 367	0.00 368	0.00 360	0.00 369	0.00 363	0.00 364	0.00 365	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

uncertanet		0.00 343	0.00 344	0.00 353	0.00 367	0.00 368	0.00 360	0.00 369	0.00 363	0.00 364	0.00 365	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

Regformer		0.00 343	0.00 344	0.00 353	0.00 367	0.00 368	0.00 360	0.00 369	0.00 363	0.00 364	0.00 365	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

ab-mvs-re		7.82 341	10.43 342	0.00 353	0.00 367	0.00 368	0.00 360	0.00 369	0.00 363	0.00 364	93.88 136	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

uanet		0.00 343	0.00 344	0.00 353	0.00 367	0.00 368	0.00 360	0.00 369	0.00 363	0.00 364	0.00 365	0.00 371	0.00 366	0.00 363	0.00 364	0.00 364

GSMVS																96.12 115

test_part2					98.55 5	87.22 11				96.40 3

test_part1								97.45 6				91.93 1			99.02 3	98.67 4

sam_mvs1												71.70 194				96.12 115

sam_mvs												70.60 210

ambc				83.06 318	79.99 343	63.51 338	77.47 348	92.86 238		74.34 317	84.45 322	28.74 352	95.06 304	73.06 263	68.89 338	90.61 316

MTGPA								96.97 35

test_post1							88.00 306				9.81 361	69.31 229	95.53 282	76.65 234

test_post											10.29 360	70.57 214	95.91 271

patchmatchnet-post											83.76 325	71.53 198	96.48 247

GG-mvs-BLEND				87.94 270	89.73 304	77.91 247	87.80 307	78.23 356		80.58 267	83.86 324	59.88 309	95.33 299	71.20 270	92.22 142	90.60 318

MTMP							96.16 31	60.64 361

test9_res														91.91 43	98.71 20	98.07 46

agg_prior2														90.54 63	98.68 25	98.27 32

agg_prior					97.38 44	85.92 45		96.72 57		92.16 57			98.97 62

test_prior4						85.96 44	94.11 160

test_prior				93.82 52	97.29 49	84.49 65		96.88 44					98.87 68			98.11 44

新几何2							93.11 219

旧先验1					96.79 60	81.81 131		95.67 128			96.81 34	86.69 25			97.66 57	96.97 94

原ACMM2							92.94 227

testdata2													98.75 80	78.30 218

segment_acmp												87.16 22

test12				94.34 41	97.13 54	86.15 41		96.29 82		91.04 77		85.08 42	99.01 56		98.13 47	97.86 61

plane_prior7					94.70 142	82.74 113

plane_prior6					94.52 149	82.75 111						74.23 161

plane_prior5								96.22 87					98.12 114	88.15 82	89.99 168	94.63 175

plane_prior4											94.86 100

plane_prior1					94.59 147

n2								0.00 369

nn								0.00 369

door-mid								85.49 342

lessismore_v0				86.04 300	88.46 315	68.78 327		80.59 352		73.01 323	90.11 263	55.39 322	96.43 251	75.06 249	65.06 341	92.90 263

test11								96.57 71

door								85.33 343

HQP5-MVS						81.56 133

BP-MVS														87.11 100

HQP4-MVS										85.43 177			97.96 135			94.51 185

HQP3-MVS								96.04 102							89.77 174

HQP2-MVS												73.83 170

NP-MVS					94.37 155	82.42 121					93.98 128

ACMMP++_ref															87.47 211

ACMMP++															88.01 208

Test By Simon												80.02 88

High-resolution multi-view benchmark