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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

SED-MVS		88.94 1	90.98 1	86.56 1	92.53 6	95.09 1	88.55 5	76.83 7	94.16 1	86.57 1	90.85 6	87.07 1	86.18 1	86.36 7	85.08 12	88.67 21	98.21 3

DVP-MVS		88.07 2	90.73 2	84.97 4	91.98 9	95.01 2	87.86 9	76.88 6	93.90 2	85.15 2	90.11 8	86.90 2	79.46 11	86.26 10	84.67 17	88.50 28	98.25 2
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
xxxxxxxxxxxxxcwj		84.33 14	83.20 26	85.64 2	94.57 1	94.55 3	91.01 1	79.94 1	89.15 11	79.85 6	92.37 3	44.71 141	79.75 7	83.52 25	82.72 31	88.75 19	95.37 23

SF-MVS		87.30 5	88.71 5	85.64 2	94.57 1	94.55 3	91.01 1	79.94 1	89.15 11	79.85 6	92.37 3	83.29 9	79.75 7	83.52 25	82.72 31	88.75 19	95.37 23

DPE-MVS		87.60 4	90.44 4	84.29 7	92.09 8	93.44 5	88.69 4	75.11 9	93.06 5	80.80 5	94.23 2	86.70 3	81.44 5	84.84 17	83.52 26	87.64 46	97.28 5

CSCG		82.90 20	84.52 22	81.02 18	91.85 10	93.43 6	87.14 11	74.01 14	81.96 33	76.14 15	70.84 38	82.49 12	69.71 61	82.32 41	85.18 11	87.26 56	95.40 22

MCST-MVS		85.75 8	86.99 12	84.31 6	94.07 3	92.80 7	88.15 8	79.10 3	85.66 23	70.72 30	76.50 32	80.45 20	82.17 3	88.35 2	87.49 3	91.63 2	97.65 4

DELS-MVS		79.49 31	79.84 41	79.08 28	88.26 37	92.49 8	84.12 25	70.63 27	65.27 80	69.60 36	61.29 62	66.50 60	72.75 42	88.07 3	88.03 2	89.13 12	97.22 6
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
CHOSEN 1792x2688		72.55 69	71.98 78	73.22 60	86.57 46	92.41 9	75.63 71	66.77 51	62.08 86	52.32 87	30.27 187	50.74 128	66.14 82	86.22 11	85.41 7	91.90 1	96.75 12

CNVR-MVS		85.96 7	87.58 10	84.06 8	92.58 5	92.40 10	87.62 10	77.77 5	88.44 14	75.93 17	79.49 25	81.97 16	81.65 4	87.04 6	86.58 4	88.79 17	97.18 7

CANet		80.90 28	82.93 29	78.53 31	86.83 45	92.26 11	81.19 42	66.95 49	81.60 36	69.90 33	66.93 46	74.80 32	76.79 20	84.68 18	84.77 16	89.50 9	95.50 19

abl_6				79.06 29	89.68 24	92.14 12	77.70 62	69.68 33	86.87 19	71.88 25	74.29 35	80.06 22	76.56 22			88.84 16	95.82 13

QAPM		77.50 45	77.43 50	77.59 36	91.52 13	92.00 13	81.41 40	70.63 27	66.22 73	58.05 70	54.70 79	71.79 44	74.49 32	82.46 37	82.04 36	89.46 10	92.79 52

DPM-MVS		85.41 10	86.72 15	83.89 10	91.66 12	91.92 14	90.49 3	78.09 4	86.90 18	73.95 20	74.52 34	82.01 15	79.29 12	90.24 1	90.65 1	89.86 6	90.78 70

APDe-MVS		86.37 6	88.41 7	84.00 9	91.43 14	91.83 15	88.34 6	74.67 10	91.19 6	81.76 4	91.13 5	81.94 17	80.07 6	83.38 27	82.58 34	87.69 44	96.78 10

MVS_0304		79.43 33	82.20 31	76.20 42	84.22 53	91.79 16	81.82 37	63.81 70	76.83 51	61.71 56	66.37 49	75.52 31	76.38 23	85.54 13	85.03 13	89.28 11	94.32 34

MSP-MVS		87.87 3	90.57 3	84.73 5	89.38 27	91.60 17	88.24 7	74.15 12	93.55 3	82.28 3	94.99 1	83.21 10	85.96 2	87.67 4	84.67 17	88.32 31	98.29 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
PHI-MVS		79.43 33	84.06 24	74.04 56	86.15 48	91.57 18	80.85 46	68.90 40	82.22 32	51.81 90	78.10 27	74.28 33	70.39 58	84.01 23	84.00 21	86.14 78	94.24 35

DeepPCF-MVS	76.94 1	83.08 19	87.77 9	77.60 35	90.11 19	90.96 19	78.48 54	72.63 22	93.10 4	65.84 42	80.67 23	81.55 18	74.80 29	85.94 12	85.39 8	83.75 137	96.77 11

SMA-MVS		85.24 11	88.27 8	81.72 15	91.74 11	90.71 20	86.71 12	73.16 19	90.56 9	74.33 19	83.07 18	85.88 4	77.16 19	86.28 9	85.58 6	87.23 57	95.77 14
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
MVS_111021_HR		77.42 46	78.40 47	76.28 41	86.95 43	90.68 21	77.41 64	70.56 30	66.21 74	62.48 52	66.17 50	63.98 67	72.08 47	82.87 32	83.15 27	88.24 34	95.71 16

MAR-MVS		77.19 48	78.37 48	75.81 46	89.87 21	90.58 22	79.33 53	65.56 60	77.62 49	58.33 69	59.24 70	67.98 54	74.83 28	82.37 40	83.12 28	86.95 63	87.67 104
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
NCCC		84.16 16	85.46 20	82.64 11	92.34 7	90.57 23	86.57 13	76.51 8	86.85 20	72.91 23	77.20 31	78.69 26	79.09 14	84.64 19	84.88 15	88.44 29	95.41 21

OpenMVS	67.62 8	74.92 59	73.91 69	76.09 44	90.10 20	90.38 24	78.01 58	66.35 54	66.09 75	62.80 49	46.33 120	64.55 66	71.77 49	79.92 63	80.88 59	87.52 49	89.20 88

3Dnovator	70.49 5	78.42 39	76.77 56	80.35 20	91.43 14	90.27 25	81.84 36	70.79 26	72.10 57	71.95 24	50.02 97	67.86 56	77.47 18	82.89 31	84.24 19	88.61 24	89.99 79

HPM-MVS++		85.64 9	88.43 6	82.39 12	92.65 4	90.24 26	85.83 16	74.21 11	90.68 8	75.63 18	86.77 13	84.15 7	78.68 15	86.33 8	85.26 9	87.32 53	95.60 18

EPNet		79.28 37	82.25 30	75.83 45	88.31 36	90.14 27	79.43 52	68.07 43	81.76 35	61.26 58	77.26 30	70.08 50	70.06 59	82.43 39	82.00 38	87.82 40	92.09 56
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		83.54 17	86.37 17	80.25 21	89.57 26	90.10 28	85.27 20	71.66 23	87.38 15	73.08 22	84.23 17	80.16 21	75.31 25	84.85 16	83.64 23	86.57 69	94.21 37

GG-mvs-BLEND		54.54 176	77.58 49	27.67 205	0.03 218	90.09 29	77.20 66	0.02 215	66.83 72	0.05 219	59.90 67	73.33 36	0.04 214	78.40 75	79.30 68	88.65 22	95.20 26

PVSNet_BlendedMVS		76.84 50	78.47 45	74.95 51	82.37 58	89.90 30	75.45 75	65.45 61	74.99 54	70.66 31	63.07 55	58.27 96	67.60 76	84.24 21	81.70 42	88.18 35	97.10 8

PVSNet_Blended		76.84 50	78.47 45	74.95 51	82.37 58	89.90 30	75.45 75	65.45 61	74.99 54	70.66 31	63.07 55	58.27 96	67.60 76	84.24 21	81.70 42	88.18 35	97.10 8

canonicalmvs		77.65 43	79.59 42	75.39 47	81.52 64	89.83 32	81.32 41	60.74 103	80.05 41	66.72 40	68.43 42	65.09 63	74.72 31	78.87 70	82.73 30	87.32 53	92.16 55

SteuartSystems-ACMMP		82.51 21	85.35 21	79.20 26	90.25 17	89.39 33	84.79 21	70.95 25	82.86 29	68.32 38	86.44 14	77.19 27	73.07 39	83.63 24	83.64 23	87.82 40	94.34 33
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		84.83 12	87.00 11	82.30 13	89.61 25	89.21 34	86.51 14	73.64 16	90.98 7	77.99 12	89.89 9	80.04 23	79.18 13	82.00 46	81.37 47	86.88 65	95.49 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
casdiffmvs		75.20 57	75.69 63	74.63 55	79.26 78	89.07 35	78.47 55	63.59 73	67.05 71	63.79 47	55.72 76	60.32 84	73.58 35	82.16 43	81.78 40	89.08 13	93.72 43

IB-MVS	64.48 11	69.02 87	68.97 97	69.09 86	81.75 63	89.01 36	64.50 145	64.91 64	56.65 104	62.59 51	47.89 104	45.23 139	51.99 149	69.18 164	81.88 39	88.77 18	92.93 49
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
MVS_Test		75.22 56	76.69 57	73.51 57	79.30 77	88.82 37	80.06 49	58.74 111	69.77 64	57.50 74	59.78 69	61.35 78	75.31 25	82.07 44	83.60 25	90.13 5	91.41 63

SD-MVS		84.31 15	86.96 13	81.22 16	88.98 31	88.68 38	85.65 17	73.85 15	89.09 13	79.63 8	87.34 12	84.84 5	73.71 34	82.66 34	81.60 44	85.48 100	94.51 31
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
gg-mvs-nofinetune		62.34 133	66.19 116	57.86 158	76.15 102	88.61 39	71.18 107	41.24 203	25.74 205	13.16 207	22.91 200	63.97 68	54.52 144	85.06 15	85.25 10	90.92 3	91.78 60

DeepC-MVS	74.46 3	80.30 30	81.05 36	79.42 24	87.42 41	88.50 40	83.23 28	73.27 18	82.78 30	71.01 29	62.86 57	69.93 51	74.80 29	84.30 20	84.20 20	86.79 67	94.77 27
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
train_agg		83.35 18	86.93 14	79.17 27	89.70 23	88.41 41	85.60 19	72.89 21	86.31 21	66.58 41	90.48 7	82.24 14	73.06 40	83.10 30	82.64 33	87.21 61	95.30 25

CDPH-MVS		79.39 36	82.13 32	76.19 43	89.22 30	88.34 42	84.20 24	71.00 24	79.67 43	56.97 75	77.77 28	72.24 42	68.50 73	81.33 51	82.74 29	87.23 57	92.84 50

3Dnovator+	70.16 6	77.87 42	77.29 52	78.55 30	89.25 29	88.32 43	80.09 48	67.95 44	74.89 56	71.83 26	52.05 91	70.68 48	76.27 24	82.27 42	82.04 36	85.92 83	90.77 71

TSAR-MVS + GP.		82.27 23	85.98 18	77.94 33	80.72 71	88.25 44	81.12 43	67.71 45	87.10 16	73.31 21	85.23 15	83.68 8	76.64 21	80.43 60	81.47 46	88.15 37	95.66 17

MP-MVS		80.94 27	83.49 25	77.96 32	88.48 32	88.16 45	82.82 32	69.34 36	80.79 39	69.67 34	82.35 20	77.13 28	71.60 51	80.97 57	80.96 57	85.87 86	94.06 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HyFIR lowres test		68.39 91	68.28 102	68.52 89	80.85 68	88.11 46	71.08 109	58.09 116	54.87 119	47.80 108	27.55 193	55.80 107	64.97 86	79.11 68	79.14 69	88.31 32	93.35 44

CLD-MVS		77.36 47	77.29 52	77.45 37	82.21 60	88.11 46	81.92 35	68.96 39	77.97 47	69.62 35	62.08 58	59.44 89	73.57 36	81.75 48	81.27 50	88.41 30	90.39 75
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ET-MVSNet_ETH3D		71.38 76	74.70 67	67.51 96	51.61 202	88.06 48	77.29 65	60.95 102	63.61 82	48.36 105	66.60 48	60.67 82	79.55 9	73.56 120	80.58 61	87.30 55	89.80 81

PCF-MVS	70.85 4	75.73 54	76.55 59	74.78 54	83.67 54	88.04 49	81.47 38	70.62 29	69.24 68	57.52 73	60.59 66	69.18 52	70.65 56	77.11 84	77.65 82	84.75 120	94.01 39
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		76.25 52	80.22 39	71.63 69	78.23 82	87.95 50	72.75 92	60.27 107	77.50 50	57.73 71	71.53 37	66.60 59	73.16 38	80.99 56	81.23 51	87.63 47	95.73 15

DeepC-MVS_fast	75.41 2	81.69 24	82.10 33	81.20 17	91.04 16	87.81 51	83.42 27	74.04 13	83.77 27	71.09 28	66.88 47	72.44 38	79.48 10	85.08 14	84.97 14	88.12 39	93.78 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CS-MVS		75.18 58	78.59 44	71.20 70	77.74 86	87.69 52	73.93 89	58.81 110	69.17 69	55.73 77	67.86 43	66.89 57	72.87 41	82.50 35	81.29 49	88.15 37	94.71 29

zzz-MVS		81.65 25	83.10 27	79.97 23	88.14 38	87.62 53	83.96 26	69.90 31	86.92 17	77.67 14	72.47 36	78.74 25	74.13 33	81.59 50	81.15 53	86.01 82	93.19 47

HFP-MVS		82.48 22	84.12 23	80.56 19	90.15 18	87.55 54	84.28 23	69.67 34	85.22 24	77.95 13	84.69 16	75.94 30	75.04 27	81.85 47	81.17 52	86.30 74	92.40 54

baseline		72.89 66	74.46 68	71.07 71	75.99 103	87.50 55	74.57 81	60.49 105	70.72 61	57.60 72	60.63 65	60.97 80	70.79 55	75.27 101	76.33 94	86.94 64	89.79 82

diffmvs		74.32 60	75.42 64	73.04 61	75.60 107	87.27 56	78.20 56	62.96 78	68.66 70	61.89 54	59.79 68	59.84 87	71.80 48	78.30 77	79.87 64	87.80 42	94.23 36

EIA-MVS		73.48 64	76.05 60	70.47 76	78.12 83	87.21 57	71.78 98	60.63 104	69.66 65	55.56 80	64.86 52	60.69 81	69.53 64	77.35 83	78.59 72	87.22 59	94.01 39

PVSNet_Blended_VisFu		71.76 73	73.54 72	69.69 80	79.01 79	87.16 58	72.05 95	61.80 91	56.46 106	59.66 66	53.88 87	62.48 70	59.08 124	81.17 53	78.90 70	86.53 71	94.74 28

ACMMPR		80.62 29	82.98 28	77.87 34	88.41 33	87.05 59	83.02 29	69.18 37	83.91 26	68.35 37	82.89 19	73.64 35	72.16 46	80.78 58	81.13 54	86.10 79	91.43 61

DI_MVS_plusplus_trai		73.94 63	74.85 66	72.88 62	76.57 99	86.80 60	80.41 47	61.47 94	62.35 85	59.44 67	47.91 103	68.12 53	72.24 45	82.84 33	81.50 45	87.15 62	94.42 32

PGM-MVS		79.42 35	81.84 34	76.60 40	88.38 35	86.69 61	82.97 31	65.75 58	80.39 40	64.94 44	81.95 22	72.11 43	71.41 52	80.45 59	80.55 62	86.18 76	90.76 72

CANet_DTU		72.84 67	76.63 58	68.43 90	76.81 97	86.62 62	75.54 74	54.71 156	72.06 58	43.54 123	67.11 45	58.46 93	72.40 44	81.13 55	80.82 60	87.57 48	90.21 77

TSAR-MVS + ACMM		81.59 26	85.84 19	76.63 39	89.82 22	86.53 63	86.32 15	66.72 52	85.96 22	65.43 43	88.98 11	82.29 13	67.57 78	82.06 45	81.33 48	83.93 135	93.75 42

TSAR-MVS + MP.		84.39 13	86.58 16	81.83 14	88.09 39	86.47 64	85.63 18	73.62 17	90.13 10	79.24 9	89.67 10	82.99 11	77.72 17	81.22 52	80.92 58	86.68 68	94.66 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
baseline2		71.22 78	73.01 75	69.13 84	75.76 105	86.34 65	71.23 105	62.78 84	62.62 83	52.85 86	57.32 72	54.31 114	63.27 96	79.74 64	79.31 67	88.89 15	91.43 61

XVS					82.43 56	86.27 66	75.70 69			61.07 60		72.27 39				85.67 94

X-MVStestdata					82.43 56	86.27 66	75.70 69			61.07 60		72.27 39				85.67 94

X-MVS		78.16 41	80.55 38	75.38 48	87.99 40	86.27 66	81.05 44	68.98 38	78.33 45	61.07 60	75.25 33	72.27 39	67.52 79	80.03 62	80.52 63	85.66 97	91.20 65

CostFormer		72.18 70	73.90 70	70.18 78	79.47 75	86.19 69	76.94 67	48.62 175	66.07 76	60.40 65	54.14 85	65.82 61	67.98 74	75.84 96	76.41 93	87.67 45	92.83 51

CP-MVS		79.44 32	81.51 35	77.02 38	86.95 43	85.96 70	82.00 34	68.44 42	81.82 34	67.39 39	77.43 29	73.68 34	71.62 50	79.56 66	79.58 65	85.73 90	92.51 53

ACMMP		77.61 44	79.59 42	75.30 49	85.87 49	85.58 71	81.42 39	67.38 48	79.38 44	62.61 50	78.53 26	65.79 62	68.80 72	78.56 73	78.50 75	85.75 87	90.80 69
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
MS-PatchMatch		70.34 83	69.00 96	71.91 68	85.20 52	85.35 72	77.84 61	61.77 92	58.01 100	55.40 81	41.26 138	58.34 95	61.69 105	81.70 49	78.29 76	89.56 8	80.02 155

Effi-MVS+		70.42 79	71.23 84	69.47 81	78.04 84	85.24 73	75.57 73	58.88 109	59.56 94	48.47 104	52.73 90	54.94 112	69.69 62	78.34 76	77.06 86	86.18 76	90.73 73

MVS_111021_LR		74.26 61	75.95 61	72.27 65	79.43 76	85.04 74	72.71 93	65.27 63	70.92 60	63.58 48	69.32 40	60.31 85	69.43 66	77.01 85	77.15 85	83.22 144	91.93 59

AdaColmap		76.23 53	73.55 71	79.35 25	89.38 27	85.00 75	79.99 50	73.04 20	76.60 52	71.17 27	55.18 78	57.99 98	77.87 16	76.82 87	76.82 88	84.67 122	86.45 112

MSLP-MVS++		78.57 38	77.33 51	80.02 22	88.39 34	84.79 76	84.62 22	66.17 56	75.96 53	78.40 10	61.59 60	71.47 45	73.54 37	78.43 74	78.88 71	88.97 14	90.18 78

Vis-MVSNet		65.53 111	69.83 93	60.52 141	70.80 133	84.59 77	66.37 142	55.47 147	48.40 139	40.62 141	57.67 71	58.43 94	45.37 173	77.49 79	76.24 96	84.47 126	85.99 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
baseline1		71.47 74	72.02 77	70.82 73	80.56 72	84.51 78	76.61 68	66.93 50	56.22 108	48.66 103	55.40 77	60.43 83	62.55 100	83.35 28	80.99 55	89.60 7	83.28 138

thisisatest0530		68.38 92	70.98 86	65.35 104	72.61 120	84.42 79	68.21 126	57.98 117	59.77 93	50.80 95	54.63 80	58.48 92	57.92 130	76.99 86	77.47 83	84.60 123	85.07 123

Anonymous202405211			66.35 115		78.00 85	84.41 80	74.85 79	63.18 76	51.00 128		31.37 184	53.73 119	69.67 63	76.28 90	76.84 87	83.21 146	90.85 68

OPM-MVS		72.74 68	70.93 87	74.85 53	85.30 51	84.34 81	82.82 32	69.79 32	49.96 132	55.39 82	54.09 86	60.14 86	70.04 60	80.38 61	79.43 66	85.74 89	88.20 100

HQP-MVS		78.26 40	80.91 37	75.17 50	85.67 50	84.33 82	83.01 30	69.38 35	79.88 42	55.83 76	79.85 24	64.90 65	70.81 54	82.46 37	81.78 40	86.30 74	93.18 48

IS_MVSNet		67.29 101	71.98 78	61.82 135	76.92 96	84.32 83	65.90 143	58.22 114	55.75 112	39.22 145	54.51 82	62.47 71	45.99 170	78.83 71	78.52 74	84.70 121	89.47 85

EPMVS		66.21 105	67.49 107	64.73 109	75.81 104	84.20 84	68.94 122	44.37 190	61.55 87	48.07 107	49.21 100	54.87 113	62.88 97	71.82 140	71.40 153	88.28 33	79.37 158

tttt0517		67.99 95	70.61 88	64.94 107	71.94 125	83.96 85	67.62 130	57.98 117	59.30 95	49.90 100	54.50 83	57.98 99	57.92 130	76.48 89	77.47 83	84.24 130	84.58 126

thres100view900		67.14 103	66.09 117	68.38 91	77.70 87	83.84 86	74.52 85	66.33 55	49.16 136	43.40 125	43.24 123	41.34 147	62.59 99	79.31 67	75.92 99	85.73 90	89.81 80

Anonymous20231211		68.44 90	66.37 114	70.86 72	77.58 90	83.49 87	75.15 78	61.89 89	52.54 125	58.50 68	28.89 189	56.78 102	69.29 69	74.96 105	76.61 89	82.73 150	91.36 64

EPP-MVSNet		67.58 97	71.10 85	63.48 121	75.71 106	83.35 88	66.85 136	57.83 122	53.02 124	41.15 137	55.82 74	67.89 55	56.01 139	74.40 109	72.92 139	83.33 142	90.30 76

MVSTER		76.92 49	79.92 40	73.42 59	74.98 110	82.97 89	78.15 57	63.41 74	78.02 46	64.41 46	67.54 44	72.80 37	71.05 53	83.29 29	83.73 22	88.53 27	91.12 66

PatchmatchNet		65.43 112	67.71 105	62.78 127	73.49 117	82.83 90	66.42 141	45.40 185	60.40 92	45.27 114	49.22 99	57.60 100	60.01 116	70.61 150	71.38 154	86.08 80	81.91 149
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres400		65.18 114	64.44 125	66.04 101	76.40 100	82.63 91	71.52 102	64.27 67	44.93 154	40.69 140	41.86 135	40.79 153	58.12 128	77.67 78	74.64 112	85.26 103	88.56 96

UGNet		67.57 98	71.69 81	62.76 128	69.88 135	82.58 92	66.43 140	58.64 112	54.71 120	51.87 89	61.74 59	62.01 75	45.46 172	74.78 106	74.99 107	84.24 130	91.02 67
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
CPTT-MVS		75.43 55	77.13 54	73.44 58	81.43 65	82.55 93	80.96 45	64.35 66	77.95 48	61.39 57	69.20 41	70.94 47	69.38 68	73.89 116	73.32 131	83.14 147	92.06 57

TSAR-MVS + COLMAP		73.09 65	76.86 55	68.71 87	74.97 111	82.49 94	74.51 86	61.83 90	83.16 28	49.31 102	82.22 21	51.62 125	68.94 71	78.76 72	75.52 105	82.67 152	84.23 130

PMMVS		70.37 82	75.06 65	64.90 108	71.46 126	81.88 95	64.10 147	55.64 143	71.31 59	46.69 109	70.69 39	58.56 90	69.53 64	79.03 69	75.63 102	81.96 162	88.32 99

MDTV_nov1_ep13		65.21 113	67.28 108	62.79 126	70.91 131	81.72 96	69.28 121	49.50 174	58.08 99	43.94 122	50.50 96	56.02 105	58.86 125	70.72 149	73.37 129	84.24 130	80.52 154

thres600view7		63.77 124	63.14 132	64.51 111	75.49 108	81.61 97	69.59 118	62.95 79	43.96 158	38.90 147	41.09 139	40.24 158	55.25 142	76.24 91	71.54 148	84.89 113	87.30 105

thres200		65.58 109	64.74 123	66.56 100	77.52 92	81.61 97	73.44 91	62.95 79	46.23 148	42.45 132	42.76 125	41.18 149	58.12 128	76.24 91	75.59 103	84.89 113	89.58 83

tfpn200view9		65.90 108	64.96 121	67.00 99	77.70 87	81.58 99	71.71 100	62.94 81	49.16 136	43.40 125	43.24 123	41.34 147	61.42 107	76.24 91	74.63 113	84.84 115	88.52 97

GA-MVS		64.55 118	65.76 120	63.12 123	69.68 136	81.56 100	69.59 118	58.16 115	45.23 153	35.58 165	47.01 115	41.82 146	59.41 120	79.62 65	78.54 73	86.32 73	86.56 111

tpm cat1		67.47 99	67.05 109	67.98 92	76.63 98	81.51 101	74.49 87	47.65 180	61.18 88	61.12 59	42.51 130	53.02 123	64.74 89	70.11 158	71.50 149	83.22 144	89.49 84

UA-Net		64.62 116	68.23 103	60.42 142	77.53 91	81.38 102	60.08 169	57.47 127	47.01 143	44.75 118	60.68 64	71.32 46	41.84 180	73.27 122	72.25 145	80.83 172	71.68 182

CNLPA		71.37 77	70.27 91	72.66 64	80.79 70	81.33 103	71.07 110	65.75 58	82.36 31	64.80 45	42.46 131	56.49 103	72.70 43	73.00 127	70.52 162	80.84 171	85.76 120

test-LLR		68.23 93	71.61 82	64.28 115	71.37 127	81.32 104	63.98 150	61.03 97	58.62 97	42.96 128	52.74 88	61.65 76	57.74 133	75.64 98	78.09 80	88.61 24	93.21 45

TESTMET0.1,1		67.38 100	71.61 82	62.45 131	66.05 160	81.32 104	63.98 150	55.36 148	58.62 97	42.96 128	52.74 88	61.65 76	57.74 133	75.64 98	78.09 80	88.61 24	93.21 45

Fast-Effi-MVS+		67.59 96	67.56 106	67.62 95	73.67 115	81.14 106	71.12 108	54.79 155	58.88 96	50.61 97	46.70 118	47.05 135	69.12 70	76.06 94	76.44 92	86.43 72	86.65 110

tpmrst		67.15 102	68.12 104	66.03 102	76.21 101	80.98 107	71.27 104	45.05 186	60.69 91	50.63 96	46.95 116	54.15 116	65.30 84	71.80 141	71.77 147	87.72 43	90.48 74

OMC-MVS		74.03 62	75.82 62	71.95 67	79.56 74	80.98 107	75.35 77	63.21 75	84.48 25	61.83 55	61.54 61	66.89 57	69.41 67	76.60 88	74.07 121	82.34 158	86.15 115

ACMP	68.86 7	72.15 71	72.25 76	72.03 66	80.96 67	80.87 109	77.93 59	64.13 68	69.29 66	60.79 63	64.04 53	53.54 120	63.91 91	73.74 119	75.27 106	84.45 127	88.98 90
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TAPA-MVS	67.10 9	71.45 75	73.47 73	69.10 85	77.04 95	80.78 110	73.81 90	62.10 86	80.80 38	51.28 91	60.91 63	63.80 69	67.98 74	74.59 107	72.42 143	82.37 157	80.97 152
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDS-MVSNet		64.22 120	65.89 119	62.28 133	70.05 134	80.59 111	69.91 117	57.98 117	43.53 159	46.58 110	48.22 102	50.76 127	46.45 167	75.68 97	76.08 97	82.70 151	86.34 114
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EG-PatchMatch MVS		58.73 161	58.03 168	59.55 147	72.32 121	80.49 112	63.44 156	55.55 145	32.49 194	38.31 150	28.87 190	37.22 168	42.84 178	74.30 113	75.70 101	84.84 115	77.14 164

v2v482		63.68 125	62.85 137	64.65 110	68.01 146	80.46 113	71.90 96	57.60 124	44.26 156	42.82 130	39.80 147	38.62 163	61.56 106	73.06 125	74.86 109	86.03 81	88.90 93

v1144		63.00 130	62.39 141	63.70 120	67.72 149	80.27 114	71.23 105	56.40 133	42.51 161	40.81 139	38.12 155	37.73 164	60.42 114	74.46 108	74.55 115	85.64 98	89.12 89

LGP-MVS_train		72.02 72	73.18 74	70.67 75	82.13 61	80.26 115	79.58 51	63.04 77	70.09 62	51.98 88	65.06 51	55.62 109	62.49 101	75.97 95	76.32 95	84.80 119	88.93 91

FC-MVSNet-train		68.83 88	68.29 101	69.47 81	78.35 81	79.94 116	64.72 144	66.38 53	54.96 116	54.51 84	56.75 73	47.91 134	66.91 80	75.57 100	75.75 100	85.92 83	87.12 106

v144192		62.05 140	61.46 148	62.73 130	66.59 158	79.87 117	69.30 120	55.88 139	41.50 168	39.41 144	37.23 158	36.45 172	59.62 118	72.69 132	73.51 126	85.61 99	88.93 91

v1192		62.25 136	61.64 146	62.96 124	66.88 154	79.72 118	69.96 116	55.77 141	41.58 166	39.42 143	37.05 160	35.96 177	60.50 113	74.30 113	74.09 120	85.24 104	88.76 94

dps		64.08 121	63.22 131	65.08 106	75.27 109	79.65 119	66.68 138	46.63 184	56.94 102	55.67 79	43.96 122	43.63 144	64.00 90	69.50 163	69.82 164	82.25 159	79.02 159

v1921920		61.66 143	61.10 151	62.31 132	66.32 159	79.57 120	68.41 125	55.49 146	41.03 169	38.69 148	36.64 166	35.27 180	59.60 119	73.23 123	73.41 128	85.37 101	88.51 98

v148		62.00 141	61.19 150	62.96 124	67.46 152	79.49 121	67.87 127	57.66 123	42.30 162	45.02 117	38.20 154	38.89 162	54.77 143	69.83 160	72.60 142	84.96 109	87.01 107

FMVSNet3		70.41 81	71.89 80	68.68 88	70.89 132	79.42 122	75.63 71	60.97 99	65.32 77	51.06 92	47.37 108	62.05 72	64.90 87	82.49 36	82.27 35	88.64 23	84.34 129

v1240		61.09 146	60.55 155	61.72 136	65.92 163	79.28 123	67.16 135	54.91 152	39.79 175	38.10 151	36.08 168	34.64 182	59.15 123	72.86 128	73.36 130	85.10 106	87.84 102

CMPMVS	43.63 17	57.67 167	55.43 175	60.28 143	72.01 123	79.00 124	62.77 160	53.23 164	41.77 165	45.42 113	30.74 186	39.03 160	53.01 147	64.81 178	64.65 184	75.26 193	68.03 190
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
V42		62.86 132	62.97 134	62.74 129	60.84 183	78.99 125	71.46 103	57.13 131	46.85 144	44.28 121	38.87 149	40.73 155	57.63 135	72.60 133	74.14 119	85.09 108	88.63 95

Vis-MVSNet (Re-imp)		62.25 136	68.74 98	54.68 173	73.70 114	78.74 126	56.51 178	57.49 126	55.22 114	26.86 186	54.56 81	61.35 78	31.06 188	73.10 124	74.90 108	82.49 155	83.31 136

GBi-Net		69.21 84	70.40 89	67.81 93	69.49 137	78.65 127	74.54 82	60.97 99	65.32 77	51.06 92	47.37 108	62.05 72	63.43 93	77.49 79	78.22 77	87.37 50	83.73 132

test1		69.21 84	70.40 89	67.81 93	69.49 137	78.65 127	74.54 82	60.97 99	65.32 77	51.06 92	47.37 108	62.05 72	63.43 93	77.49 79	78.22 77	87.37 50	83.73 132

FMVSNet2		68.06 94	68.57 99	67.45 97	69.49 137	78.65 127	74.54 82	60.23 108	56.29 107	49.64 101	42.13 134	57.08 101	63.43 93	81.15 54	80.99 55	87.37 50	83.73 132

tpm		64.85 115	66.02 118	63.48 121	74.52 112	78.38 130	70.98 111	44.99 188	51.61 127	43.28 127	47.66 106	53.18 121	60.57 111	70.58 152	71.30 156	86.54 70	89.45 86

test_part1		66.32 104	63.35 130	69.77 79	77.40 93	78.35 131	77.85 60	56.25 136	44.52 155	62.15 53	33.05 178	53.91 118	62.38 103	72.19 136	74.65 111	82.59 153	86.81 108

ACMH	59.42 14	61.59 144	59.22 163	64.36 114	78.92 80	78.26 132	67.65 129	67.48 47	39.81 174	30.98 180	38.25 153	34.59 183	61.37 109	70.55 153	73.47 127	79.74 178	79.59 156
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v8		63.44 127	62.58 139	64.43 112	68.28 145	78.07 133	71.82 97	54.85 153	46.70 146	45.20 115	39.40 148	40.91 152	60.54 112	72.85 129	74.39 118	85.92 83	85.76 120

Patchmtry						78.06 134	67.53 131	43.18 193		41.40 134

UniMVSNet (Re)		60.62 149	62.93 136	57.92 157	67.64 150	77.90 135	61.75 163	61.24 96	49.83 133	29.80 182	42.57 128	40.62 156	43.36 176	70.49 154	73.27 133	83.76 136	85.81 119

UniMVSNet_NR-MVSNet		62.30 135	63.51 129	60.89 139	69.48 140	77.83 136	64.07 148	63.94 69	50.03 131	31.17 178	44.82 121	41.12 150	51.37 152	71.02 146	74.81 110	85.30 102	84.95 124

v10		63.00 130	62.22 142	63.90 119	67.88 148	77.78 137	71.59 101	54.34 157	45.37 152	42.76 131	38.53 150	38.93 161	61.05 110	74.39 110	74.52 116	85.75 87	86.04 116

ACMM	66.70 10	70.42 79	68.49 100	72.67 63	82.85 55	77.76 138	77.70 62	64.76 65	64.61 81	60.74 64	49.29 98	53.97 117	65.86 83	74.97 103	75.57 104	84.13 134	83.29 137
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		58.86 159	60.91 152	56.47 168	62.38 179	77.57 139	58.97 173	52.98 165	38.76 178	36.17 161	42.26 133	47.94 133	46.45 167	70.23 157	70.79 159	81.86 163	78.82 160

DCV-MVSNet		69.13 86	69.07 95	69.21 83	77.65 89	77.52 140	74.68 80	57.85 121	54.92 117	55.34 83	55.74 75	55.56 110	66.35 81	75.05 102	76.56 91	83.35 141	88.13 101

test-mter		64.06 122	69.24 94	58.01 156	59.07 189	77.40 141	59.13 172	48.11 178	55.64 113	39.18 146	51.56 93	58.54 91	55.38 141	73.52 121	76.00 98	87.22 59	92.05 58

EPNet_dtu		66.17 106	70.13 92	61.54 137	81.04 66	77.39 142	68.87 123	62.50 85	69.78 63	33.51 173	63.77 54	56.22 104	37.65 186	72.20 135	72.18 146	85.69 93	79.38 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs5		59.72 153	60.24 157	59.11 152	62.77 177	77.33 143	63.17 158	54.00 159	40.21 173	37.23 155	40.41 143	35.99 176	51.75 150	72.55 134	72.74 141	85.72 92	82.45 145

MIMVSNet		57.78 166	59.71 161	55.53 170	54.79 197	77.10 144	63.89 152	45.02 187	46.59 147	36.79 158	28.36 191	40.77 154	45.84 171	74.97 103	76.58 90	86.87 66	73.60 175

pm-mvs1		59.21 157	59.58 162	58.77 154	67.97 147	77.07 145	64.12 146	57.20 129	34.73 190	36.86 156	35.34 171	40.54 157	43.34 177	74.32 112	73.30 132	83.13 148	81.77 150

Fast-Effi-MVS+-dtu		63.05 129	64.72 124	61.11 138	71.21 130	76.81 146	70.72 113	43.13 195	52.51 126	35.34 166	46.55 119	46.36 136	61.40 108	71.57 144	71.44 151	84.84 115	87.79 103

MSDG		65.57 110	61.57 147	70.24 77	82.02 62	76.47 147	74.46 88	68.73 41	56.52 105	50.33 98	38.47 151	41.10 151	62.42 102	72.12 137	72.94 138	83.47 140	73.37 177

pmmvs4		63.14 128	62.46 140	63.94 118	66.03 161	76.40 148	66.82 137	57.60 124	56.74 103	50.26 99	40.81 142	37.51 166	59.26 122	71.75 142	71.48 150	83.68 139	82.53 143

FMVSNet1		63.48 126	63.07 133	63.97 117	65.31 165	76.37 149	71.77 99	57.90 120	43.32 160	45.66 112	35.06 174	49.43 130	58.57 126	77.49 79	78.22 77	84.59 124	81.60 151

tfpnnormal		58.97 158	56.48 173	61.89 134	71.27 129	76.21 150	66.65 139	61.76 93	32.90 193	36.41 160	27.83 192	29.14 199	50.64 156	73.06 125	73.05 137	84.58 125	83.15 141

DU-MVS		60.87 148	61.82 145	59.76 146	66.69 155	75.87 151	64.07 148	61.96 87	49.31 134	31.17 178	42.76 125	36.95 169	51.37 152	69.67 161	73.20 136	83.30 143	84.95 124

NR-MVSNet		61.08 147	62.09 144	59.90 144	71.96 124	75.87 151	63.60 154	61.96 87	49.31 134	27.95 183	42.76 125	33.85 187	48.82 159	74.35 111	74.05 122	85.13 105	84.45 127

LS3D		64.54 119	62.14 143	67.34 98	80.85 68	75.79 153	69.99 115	65.87 57	60.77 90	44.35 120	42.43 132	45.95 138	65.01 85	69.88 159	68.69 169	77.97 186	71.43 184

PatchMatch-RL		62.22 139	60.69 153	64.01 116	68.74 142	75.75 154	59.27 171	60.35 106	56.09 109	53.80 85	47.06 114	36.45 172	64.80 88	68.22 166	67.22 173	77.10 188	74.02 172

PatchT		60.46 150	63.85 127	56.51 167	65.95 162	75.68 155	47.34 192	41.39 200	53.89 123	41.40 134	37.84 156	50.30 129	57.29 136	72.76 130	73.27 133	85.67 94	83.23 139

thisisatest0515		59.37 156	60.68 154	57.84 159	64.39 169	75.65 156	58.56 174	53.86 160	41.55 167	42.12 133	40.40 144	39.59 159	47.09 165	71.69 143	73.79 123	81.02 170	82.08 148

TranMVSNet+NR-MVSNet		60.38 151	61.30 149	59.30 150	68.34 144	75.57 157	63.38 157	63.78 71	46.74 145	27.73 184	42.56 129	36.84 170	47.66 162	70.36 155	74.59 114	84.91 112	82.46 144

Effi-MVS+-dtu		64.58 117	64.08 126	65.16 105	73.04 119	75.17 158	70.68 114	56.23 137	54.12 122	44.71 119	47.42 107	51.10 126	63.82 92	68.08 167	66.32 178	82.47 156	86.38 113

IterMVS-LS		66.08 107	66.56 113	65.51 103	73.67 115	74.88 159	70.89 112	53.55 162	50.42 130	48.32 106	50.59 95	55.66 108	61.83 104	73.93 115	74.42 117	84.82 118	86.01 117
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PLC	64.00 12	68.54 89	66.66 111	70.74 74	80.28 73	74.88 159	72.64 94	63.70 72	69.26 67	55.71 78	47.24 111	55.31 111	70.42 57	72.05 139	70.67 160	81.66 165	77.19 163
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		57.04 169	56.64 172	57.52 161	62.85 176	74.75 161	61.76 162	51.80 170	35.58 189	36.02 163	32.33 181	33.61 188	50.16 157	67.73 168	70.34 163	82.51 154	82.12 147

TransMVSNet (Re)		57.83 164	56.90 171	58.91 153	72.26 122	74.69 162	63.57 155	61.42 95	32.30 195	32.65 174	33.97 176	35.96 177	39.17 184	73.84 118	72.84 140	84.37 128	74.69 170

ADS-MVSNet		58.40 163	59.16 164	57.52 161	65.80 164	74.57 163	60.26 167	40.17 204	50.51 129	38.01 152	40.11 146	44.72 140	59.36 121	64.91 176	66.55 176	81.53 166	72.72 180

ACMH+	60.36 13	61.16 145	58.38 165	64.42 113	77.37 94	74.35 164	68.45 124	62.81 83	45.86 150	38.48 149	35.71 169	37.35 167	59.81 117	67.24 169	69.80 166	79.58 179	78.32 161

Baseline_NR-MVSNet		59.47 155	60.28 156	58.54 155	66.69 155	73.90 165	61.63 164	62.90 82	49.15 138	26.87 185	35.18 173	37.62 165	48.20 160	69.67 161	73.61 125	84.92 110	82.82 142

MDTV_nov1_ep13_2view		54.47 177	54.61 176	54.30 177	60.50 184	73.82 166	57.92 175	43.38 192	39.43 177	32.51 175	33.23 177	34.05 185	47.26 164	62.36 184	66.21 179	84.24 130	73.19 178

test0.0.03 1		57.35 168	59.89 160	54.38 176	71.37 127	73.45 167	52.71 184	61.03 97	46.11 149	26.33 187	41.73 136	44.08 142	29.72 190	71.43 145	70.90 157	85.10 106	71.56 183

UniMVSNet_ETH3D		57.83 164	56.46 174	59.43 149	63.24 174	73.22 168	67.70 128	55.58 144	36.17 185	36.84 157	32.64 179	35.14 181	51.50 151	65.81 172	69.81 165	81.73 164	82.44 146

pmmvs6		54.20 178	53.54 180	54.97 171	63.22 175	72.98 169	60.17 168	52.32 169	26.77 204	34.30 170	23.29 199	36.23 174	40.33 183	68.77 165	68.76 168	79.47 181	78.00 162

MVS-HIRNet		53.86 180	53.02 182	54.85 172	60.30 185	72.36 170	44.63 200	42.20 198	39.45 176	43.47 124	21.66 203	34.00 186	55.47 140	65.42 174	67.16 174	83.02 149	71.08 186

IterMVS		61.87 142	63.55 128	59.90 144	67.29 153	72.20 171	67.34 134	48.56 176	47.48 142	37.86 154	47.07 113	48.27 131	54.08 145	72.12 137	73.71 124	84.30 129	83.99 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		60.21 152	62.97 134	57.00 165	66.64 157	71.84 172	67.53 131	46.93 183	47.56 141	36.77 159	46.85 117	48.21 132	52.51 148	70.36 155	72.40 144	71.63 201	83.53 135

USDC		59.69 154	60.03 159	59.28 151	64.04 170	71.84 172	63.15 159	55.36 148	54.90 118	35.02 167	48.34 101	29.79 198	58.16 127	70.60 151	71.33 155	79.99 176	73.42 176

SCA		63.90 123	66.67 110	60.66 140	73.75 113	71.78 174	59.87 170	43.66 191	61.13 89	45.03 116	51.64 92	59.45 88	57.92 130	70.96 147	70.80 158	83.71 138	80.92 153

anonymousdsp		54.99 173	57.24 170	52.36 179	53.82 199	71.75 175	51.49 185	48.14 177	33.74 191	33.66 172	38.34 152	36.13 175	47.54 163	64.53 180	70.60 161	79.53 180	85.59 122

pmnet_mix02		53.92 179	53.30 181	54.65 175	61.89 180	71.33 176	54.54 182	54.17 158	40.38 171	34.65 168	34.76 175	30.68 197	40.44 182	60.97 186	63.71 186	82.19 160	71.24 185

CR-MVSNet		62.31 134	64.75 122	59.47 148	68.63 143	71.29 177	67.53 131	43.18 193	55.83 110	41.40 134	41.04 140	55.85 106	57.29 136	72.76 130	73.27 133	78.77 183	83.23 139

RPMNet		58.63 162	62.80 138	53.76 178	67.59 151	71.29 177	54.60 181	38.13 205	55.83 110	35.70 164	41.58 137	53.04 122	47.89 161	66.10 171	67.38 171	78.65 185	84.40 128

our_test_3					63.32 172	71.07 179	55.90 179

LTVRE_ROB	47.26 16	49.41 191	49.91 194	48.82 186	64.76 167	69.79 180	49.05 188	47.12 182	20.36 211	16.52 199	36.65 165	26.96 202	50.76 155	60.47 187	63.16 189	64.73 204	72.00 181
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
Anonymous20231206		52.23 183	52.80 185	51.56 181	64.70 168	69.41 181	51.01 186	58.60 113	36.63 182	22.44 193	21.80 202	31.42 193	30.52 189	66.79 170	67.83 170	82.10 161	75.73 166

WR-MVS		51.02 185	54.56 177	46.90 192	63.84 171	69.23 182	44.78 199	56.38 134	38.19 179	14.19 203	37.38 157	36.82 171	22.39 199	60.14 188	66.20 180	79.81 177	73.95 174

CHOSEN 280x420		62.23 138	66.57 112	57.17 164	59.88 186	68.92 183	61.20 166	42.28 197	54.17 121	39.57 142	47.78 105	64.97 64	62.68 98	73.85 117	69.52 167	77.43 187	86.75 109

CVMVSNet		54.92 175	58.16 166	51.13 183	62.61 178	68.44 184	55.45 180	52.38 168	42.28 163	21.45 194	47.10 112	46.10 137	37.96 185	64.42 181	63.81 185	76.92 189	75.01 169

pmmvs-eth3d		55.20 170	53.95 179	56.65 166	57.34 195	67.77 185	57.54 176	53.74 161	40.93 170	41.09 138	31.19 185	29.10 200	49.07 158	65.54 173	67.28 172	81.14 168	75.81 165

WR-MVS_H		49.62 190	52.63 186	46.11 195	58.80 190	67.58 186	46.14 197	54.94 150	36.51 183	13.63 206	36.75 164	35.67 179	22.10 200	56.43 196	62.76 190	81.06 169	72.73 179

COLMAP_ROB	51.17 15	55.13 171	52.90 184	57.73 160	73.47 118	67.21 187	62.13 161	55.82 140	47.83 140	34.39 169	31.60 183	34.24 184	44.90 174	63.88 183	62.52 191	75.67 191	63.02 199
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testgi		48.51 193	50.53 191	46.16 194	64.78 166	67.15 188	41.54 202	54.81 154	29.12 200	17.03 197	32.07 182	31.98 190	20.15 203	65.26 175	67.00 175	78.67 184	61.10 203

FMVSNet5		58.86 159	60.24 157	57.25 163	52.66 201	66.25 189	63.77 153	52.86 167	57.85 101	37.92 153	36.12 167	52.22 124	51.37 152	70.88 148	71.43 152	84.92 110	66.91 192

PEN-MVS		51.04 184	52.94 183	48.82 186	61.45 182	66.00 190	48.68 189	57.20 129	36.87 181	15.36 201	36.98 161	32.72 189	28.77 194	57.63 192	66.37 177	81.44 167	74.00 173

CP-MVSNet		50.57 186	52.60 187	48.21 189	58.77 191	65.82 191	48.17 190	56.29 135	37.41 180	16.59 198	37.14 159	31.95 191	29.21 191	56.60 195	63.71 186	80.22 174	75.56 167

PS-CasMVS		50.17 187	52.02 188	48.02 190	58.60 192	65.54 192	48.04 191	56.19 138	36.42 184	16.42 200	35.68 170	31.33 194	28.85 193	56.42 197	63.54 188	80.01 175	75.18 168

TDRefinement		52.70 181	51.02 190	54.66 174	57.41 194	65.06 193	61.47 165	54.94 150	44.03 157	33.93 171	30.13 188	27.57 201	46.17 169	61.86 185	62.48 192	74.01 197	66.06 193

test20.03		47.23 196	48.69 196	45.53 196	63.28 173	64.39 194	41.01 203	56.93 132	29.16 199	15.21 202	23.90 196	30.76 196	17.51 206	64.63 179	65.26 181	79.21 182	62.71 200

DTE-MVSNet		49.82 189	51.92 189	47.37 191	61.75 181	64.38 195	45.89 198	57.33 128	36.11 186	12.79 208	36.87 162	31.93 192	25.73 197	58.01 190	65.22 182	80.75 173	70.93 187

SixPastTwentyTwo		49.11 192	49.22 195	48.99 185	58.54 193	64.14 196	47.18 193	47.75 179	31.15 197	24.42 189	41.01 141	26.55 203	44.04 175	54.76 200	58.70 197	71.99 200	68.21 188

TinyColmap		52.66 182	50.09 193	55.65 169	59.72 187	64.02 197	57.15 177	52.96 166	40.28 172	32.51 175	32.42 180	20.97 209	56.65 138	63.95 182	65.15 183	74.91 194	63.87 197

N_pmnet		47.67 194	47.00 198	48.45 188	54.72 198	62.78 198	46.95 194	51.25 171	36.01 187	26.09 188	26.59 195	25.93 206	35.50 187	55.67 199	59.01 195	76.22 190	63.04 198

MDA-MVSNet-bldmvs		44.15 198	42.27 203	46.34 193	38.34 209	62.31 199	46.28 195	55.74 142	29.83 198	20.98 195	27.11 194	16.45 214	41.98 179	41.11 207	57.47 198	74.72 195	61.65 202

PM-MVS		50.11 188	50.38 192	49.80 184	47.23 207	62.08 200	50.91 187	44.84 189	41.90 164	36.10 162	35.22 172	26.05 205	46.83 166	57.64 191	55.42 202	72.90 198	74.32 171

new-patchmatchnet		42.21 199	42.97 200	41.33 199	53.05 200	59.89 201	39.38 204	49.61 173	28.26 202	12.10 209	22.17 201	21.54 208	19.22 204	50.96 202	56.04 200	74.61 196	61.92 201

RPSCF		55.07 172	58.06 167	51.57 180	48.87 205	58.95 202	53.68 183	41.26 202	62.42 84	45.88 111	54.38 84	54.26 115	53.75 146	57.15 193	53.53 203	66.01 203	65.75 194

MIMVSNet1		40.84 201	43.46 199	37.79 202	32.14 210	58.92 203	39.24 205	50.83 172	27.00 203	11.29 210	16.76 209	26.53 204	17.75 205	57.14 194	61.12 194	75.46 192	56.78 204

FC-MVSNet-test		47.24 195	54.37 178	38.93 201	59.49 188	58.25 204	34.48 208	53.36 163	45.66 151	6.66 213	50.62 94	42.02 145	16.62 207	58.39 189	61.21 193	62.99 205	64.40 196

EU-MVSNet		44.84 197	47.85 197	41.32 200	49.26 204	56.59 205	43.07 201	47.64 181	33.03 192	13.82 204	36.78 163	30.99 195	24.37 198	53.80 201	55.57 201	69.78 202	68.21 188

gm-plane-assit		54.99 173	57.99 169	51.49 182	69.27 141	54.42 206	32.32 209	42.59 196	21.18 209	13.71 205	23.61 197	43.84 143	60.21 115	87.09 5	86.55 5	90.81 4	89.28 87

pmmvs3		41.86 200	42.29 202	41.36 198	39.80 208	52.66 207	38.93 206	35.85 209	23.40 208	20.22 196	19.30 204	20.84 210	40.56 181	55.98 198	58.79 196	72.80 199	65.03 195

ambc			42.30 201		50.36 203	49.51 208	35.47 207		32.04 196	23.53 190	17.36 206	8.95 216	29.06 192	64.88 177	56.26 199	61.29 206	67.12 191

FPMVS		39.11 202	36.39 204	42.28 197	55.97 196	45.94 209	46.23 196	41.57 199	35.73 188	22.61 191	23.46 198	19.82 211	28.32 195	43.57 204	40.67 206	58.96 207	45.54 206

new_pmnet		33.19 203	35.52 205	30.47 204	27.55 214	45.31 210	29.29 210	30.92 210	29.00 201	9.88 212	18.77 205	17.64 213	26.77 196	44.07 203	45.98 205	58.41 208	47.87 205

PMMVS2		20.45 206	22.31 208	18.27 209	20.52 215	26.73 211	14.85 214	28.43 212	13.69 212	0.79 218	10.35 210	9.10 215	3.83 213	27.64 209	32.87 208	41.17 210	35.81 208

PMVS	27.44 18	32.08 204	29.07 206	35.60 203	48.33 206	24.79 212	26.97 211	41.34 201	20.45 210	22.50 192	17.11 208	18.64 212	20.44 202	41.99 206	38.06 207	54.02 209	42.44 207
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		24.91 205	24.61 207	25.26 206	31.47 211	21.59 213	18.06 212	37.53 206	25.43 206	10.03 211	4.18 214	4.25 218	14.85 208	43.20 205	47.03 204	39.62 211	26.55 211
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	15.98 19	14.37 209	16.36 209	12.04 211	7.72 217	20.24 214	5.90 218	29.05 211	8.28 215	3.92 215	4.72 213	2.42 219	9.57 211	18.89 211	31.46 209	16.07 216	28.53 210
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						19.81 215	17.01 213	10.02 213	23.61 207	5.85 214	17.21 207	8.03 217	21.13 201	22.60 210		21.42 215	30.01 209

E-PMN		15.08 207	11.65 210	19.08 207	28.73 212	12.31 216	6.95 217	36.87 208	10.71 214	3.63 216	5.13 211	2.22 221	13.81 210	11.34 212	18.50 211	24.49 213	21.32 212

EMVS		14.40 208	10.71 211	18.70 208	28.15 213	12.09 217	7.06 216	36.89 207	11.00 213	3.56 217	4.95 212	2.27 220	13.91 209	10.13 213	16.06 212	22.63 214	18.51 213

tmp_tt				16.09 210	13.07 216	8.12 218	13.61 215	2.08 214	55.09 115	30.10 181	40.26 145	22.83 207	5.35 212	29.91 208	25.25 210	32.33 212

testmvs		0.05 210	0.08 212	0.01 212	0.00 219	0.01 219	0.03 220	0.01 216	0.05 216	0.00 220	0.14 216	0.01 222	0.03 216	0.05 214	0.05 213	0.01 217	0.24 215

test123		0.05 210	0.08 212	0.01 212	0.00 219	0.01 219	0.01 221	0.00 217	0.05 216	0.00 220	0.16 215	0.00 223	0.04 214	0.02 215	0.05 213	0.00 218	0.26 214

uanet_test		0.00 212	0.00 214	0.00 214	0.00 219	0.00 221	0.00 222	0.00 217	0.00 218	0.00 220	0.00 217	0.00 223	0.00 217	0.00 216	0.00 215	0.00 218	0.00 216

sosnet-low-res		0.00 212	0.00 214	0.00 214	0.00 219	0.00 221	0.00 222	0.00 217	0.00 218	0.00 220	0.00 217	0.00 223	0.00 217	0.00 216	0.00 215	0.00 218	0.00 216

sosnet		0.00 212	0.00 214	0.00 214	0.00 219	0.00 221	0.00 222	0.00 217	0.00 218	0.00 220	0.00 217	0.00 223	0.00 217	0.00 216	0.00 215	0.00 218	0.00 216

RE-MVS-def										31.47 177

9.14												84.47 6

SR-MVS					86.33 47			67.54 46				80.78 19

MTAPA										78.32 11		79.42 24

MTMP										76.04 16		76.65 29

Patchmatch-RL test							2.17 219

mPP-MVS					86.96 42							70.61 49

NP-MVS									81.60 36

High-resolution multi-view benchmark