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		97.98 2	98.36 2	97.54 4	98.94 18	99.29 2	98.81 4	96.64 3	97.14 3	95.16 5	97.96 2	99.61 2	96.92 12	98.00 1	97.24 8	98.75 18	99.25 3

DVP-MVS++		98.07 1	98.46 1	97.62 1	99.08 4	99.29 2	98.84 3	96.63 4	97.89 1	95.35 3	97.83 4	99.48 3	96.98 9	97.99 2	97.14 11	98.82 11	99.60 1

CNVR-MVS		97.30 10	97.41 11	97.18 9	99.02 11	98.60 22	98.15 17	96.24 14	96.12 18	94.10 13	95.54 26	97.99 12	96.99 7	97.97 3	97.17 9	98.57 25	98.50 30

DVP-MVS		97.93 3	98.23 3	97.58 3	99.05 7	99.31 1	98.64 6	96.62 5	97.56 2	95.08 6	96.61 14	99.64 1	97.32 1	97.91 4	97.31 6	98.77 16	99.26 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
SMA-MVS		97.53 7	97.93 7	97.07 12	99.21 1	99.02 8	98.08 20	96.25 12	96.36 12	93.57 17	96.56 15	99.27 5	96.78 17	97.91 4	97.43 3	98.51 27	98.94 12
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
SteuartSystems-ACMMP		97.10 15	97.49 10	96.65 20	98.97 14	98.95 9	98.43 9	95.96 19	95.12 30	91.46 30	96.85 10	97.60 18	96.37 25	97.76 6	97.16 10	98.68 19	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
DPE-MVS		97.83 4	98.13 4	97.48 5	98.83 24	99.19 4	98.99 1	96.70 1	96.05 20	94.39 11	98.30 1	99.47 4	97.02 6	97.75 7	97.02 14	98.98 3	99.10 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		97.79 5	97.96 6	97.60 2	99.20 2	99.10 6	98.88 2	96.68 2	96.81 7	94.64 7	97.84 3	98.02 11	97.24 3	97.74 8	97.02 14	98.97 5	99.16 6

DeepPCF-MVS	92.65 2	95.50 35	96.96 19	93.79 54	96.44 59	98.21 44	93.51 97	94.08 38	96.94 4	89.29 46	93.08 32	96.77 28	93.82 57	97.68 9	97.40 4	95.59 178	98.65 16

ACMMP_NAP		96.93 17	97.27 15	96.53 25	99.06 6	98.95 9	98.24 14	96.06 16	95.66 23	90.96 35	95.63 25	97.71 16	96.53 21	97.66 10	96.68 20	98.30 55	98.61 20

DeepC-MVS_fast	93.32 1	96.48 23	96.42 28	96.56 22	98.70 27	98.31 40	97.97 23	95.76 22	96.31 14	92.01 29	91.43 41	95.42 41	96.46 23	97.65 11	97.69 1	98.49 31	98.12 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + MP.		97.31 9	97.64 9	96.92 15	97.28 48	98.56 24	98.61 7	95.48 30	96.72 8	94.03 15	96.73 13	98.29 9	97.15 4	97.61 12	96.42 26	98.96 6	99.13 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CS-MVS		94.53 46	94.73 43	94.31 45	96.30 62	98.53 27	94.98 62	89.24 83	93.37 51	90.24 42	88.96 56	89.76 72	96.09 30	97.48 13	96.42 26	98.99 2	98.59 21

NCCC		96.75 20	96.67 25	96.85 18	99.03 10	98.44 36	98.15 17	96.28 11	96.32 13	92.39 27	92.16 36	97.55 20	96.68 20	97.32 14	96.65 22	98.55 26	98.26 40

DELS-MVS		93.71 54	93.47 54	94.00 47	96.82 55	98.39 38	96.80 40	91.07 59	89.51 100	89.94 43	83.80 86	89.29 73	90.95 89	97.32 14	97.65 2	98.42 41	98.32 38
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
HPM-MVS++		97.22 11	97.40 12	97.01 13	99.08 4	98.55 25	98.19 15	96.48 7	96.02 21	93.28 22	96.26 18	98.71 8	96.76 18	97.30 16	96.25 37	98.30 55	98.68 15

MSP-MVS		97.70 6	98.09 5	97.24 7	99.00 12	99.17 5	98.76 5	96.41 10	96.91 5	93.88 16	97.72 5	99.04 7	96.93 11	97.29 17	97.31 6	98.45 37	99.23 4
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
DROMVSNet		94.19 50	95.05 39	93.18 61	93.56 104	97.65 64	95.34 59	86.37 117	92.05 62	88.71 52	89.91 50	93.32 49	96.14 29	97.29 17	96.42 26	98.98 3	98.70 14

ETV-MVS		93.80 53	94.57 45	92.91 68	93.98 90	97.50 67	93.62 94	88.70 88	91.95 63	87.57 62	90.21 49	90.79 63	94.56 44	97.20 19	96.35 31	99.02 1	97.98 53

zzz-MVS		96.98 16	96.68 24	97.33 6	99.09 3	98.71 13	98.43 9	96.01 17	96.11 19	95.19 4	92.89 34	97.32 23	96.84 13	97.20 19	96.09 47	98.44 38	98.46 34

TSAR-MVS + ACMM		96.19 24	97.39 13	94.78 39	97.70 41	98.41 37	97.72 28	95.49 29	96.47 11	86.66 71	96.35 16	97.85 13	93.99 53	97.19 21	96.37 30	97.12 132	99.13 7

IS_MVSNet		91.87 71	93.35 56	90.14 104	94.09 87	97.73 61	93.09 105	88.12 96	88.71 107	79.98 117	84.49 81	90.63 66	87.49 130	97.07 22	96.96 16	98.07 79	97.88 62

APD-MVS		97.12 13	97.05 18	97.19 8	99.04 8	98.63 20	98.45 8	96.54 6	94.81 38	93.50 18	96.10 20	97.40 22	96.81 14	97.05 23	96.82 19	98.80 12	98.56 22
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CS-MVS-test		94.63 45	95.28 37	93.88 52	96.56 58	98.67 14	93.41 99	89.31 81	94.27 43	89.64 44	90.84 45	91.64 58	95.58 35	97.04 24	96.17 39	98.77 16	98.32 38

CANet		94.85 40	94.92 40	94.78 39	97.25 49	98.52 29	97.20 34	91.81 50	93.25 52	91.06 34	86.29 68	94.46 45	92.99 67	97.02 25	96.68 20	98.34 49	98.20 43

MCST-MVS		96.83 19	97.06 17	96.57 21	98.88 22	98.47 34	98.02 22	96.16 15	95.58 25	90.96 35	95.78 24	97.84 14	96.46 23	97.00 26	96.17 39	98.94 7	98.55 27

SD-MVS		97.35 8	97.73 8	96.90 16	97.35 46	98.66 15	97.85 26	96.25 12	96.86 6	94.54 10	96.75 12	99.13 6	96.99 7	96.94 27	96.58 23	98.39 45	99.20 5
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
MVS_0304		94.30 49	94.68 44	93.86 53	96.33 61	98.48 32	97.41 32	91.20 56	92.75 56	86.96 68	86.03 71	93.81 48	92.64 71	96.89 28	96.54 25	98.61 23	98.24 41

DeepC-MVS	92.10 3	95.22 36	94.77 42	95.75 32	97.77 39	98.54 26	97.63 29	95.96 19	95.07 33	88.85 50	85.35 76	91.85 55	95.82 32	96.88 29	97.10 12	98.44 38	98.63 17
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
xxxxxxxxxxxxxcwj		95.62 32	94.35 49	97.10 10	98.95 16	98.51 30	97.51 30	96.48 7	96.17 16	94.64 7	97.32 6	76.98 140	96.23 27	96.78 30	96.15 41	98.79 14	98.55 27

SF-MVS		97.20 12	97.29 14	97.10 10	98.95 16	98.51 30	97.51 30	96.48 7	96.17 16	94.64 7	97.32 6	97.57 19	96.23 27	96.78 30	96.15 41	98.79 14	98.55 27

test1111		90.47 94	89.10 106	92.07 77	94.92 79	98.30 41	94.17 80	90.30 66	89.56 99	83.92 96	73.25 152	73.66 149	90.26 98	96.77 32	96.14 43	98.87 8	96.04 123

MP-MVS		96.56 22	96.72 23	96.37 26	98.93 20	98.48 32	98.04 21	95.55 25	94.32 42	90.95 37	95.88 23	97.02 26	96.29 26	96.77 32	96.01 49	98.47 32	98.56 22
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test2506		90.93 85	89.20 104	92.95 66	94.97 77	98.30 41	94.53 67	90.25 67	89.91 93	88.39 55	83.23 90	64.17 193	90.69 92	96.75 34	96.10 45	98.87 8	95.97 125

ECVR-MVS		90.77 89	89.27 102	92.52 70	94.97 77	98.30 41	94.53 67	90.25 67	89.91 93	85.80 80	73.64 145	74.31 148	90.69 92	96.75 34	96.10 45	98.87 8	95.91 128

X-MVS		96.07 27	96.33 29	95.77 31	98.94 18	98.66 15	97.94 24	95.41 32	95.12 30	88.03 56	93.00 33	96.06 33	95.85 31	96.65 36	96.35 31	98.47 32	98.48 31

HFP-MVS		97.11 14	97.19 16	97.00 14	98.97 14	98.73 12	98.37 12	95.69 23	96.60 9	93.28 22	96.87 9	96.64 29	97.27 2	96.64 37	96.33 35	98.44 38	98.56 22

MVS_111021_HR		94.84 41	95.91 31	93.60 55	97.35 46	98.46 35	95.08 61	91.19 57	94.18 44	85.97 75	95.38 27	92.56 53	93.61 60	96.61 38	96.25 37	98.40 43	97.92 58

ACMMPR		96.92 18	96.96 19	96.87 17	98.99 13	98.78 11	98.38 11	95.52 26	96.57 10	92.81 26	96.06 21	95.90 37	97.07 5	96.60 39	96.34 34	98.46 34	98.42 35

UA-Net		90.81 86	92.58 64	88.74 116	94.87 81	97.44 69	92.61 110	88.22 94	82.35 160	78.93 121	85.20 78	95.61 39	79.56 186	96.52 40	96.57 24	98.23 64	94.37 154

3Dnovator+	90.56 5	95.06 38	94.56 46	95.65 33	98.11 33	98.15 47	97.19 35	91.59 54	95.11 32	93.23 24	81.99 103	94.71 44	95.43 38	96.48 41	96.88 18	98.35 47	98.63 17

PGM-MVS		96.16 25	96.33 29	95.95 28	99.04 8	98.63 20	98.32 13	92.76 44	93.42 50	90.49 40	96.30 17	95.31 42	96.71 19	96.46 42	96.02 48	98.38 46	98.19 44

PHI-MVS		95.86 29	96.93 22	94.61 43	97.60 43	98.65 19	96.49 42	93.13 42	94.07 45	87.91 60	97.12 8	97.17 25	93.90 56	96.46 42	96.93 17	98.64 21	98.10 51

CP-MVS		96.68 21	96.59 27	96.77 19	98.85 23	98.58 23	98.18 16	95.51 28	95.34 27	92.94 25	95.21 29	96.25 32	96.79 16	96.44 44	95.77 51	98.35 47	98.56 22

PVSNet_BlendedMVS		92.80 59	92.44 67	93.23 58	96.02 64	97.83 57	93.74 91	90.58 62	91.86 64	90.69 38	85.87 74	82.04 108	90.01 99	96.39 45	95.26 59	98.34 49	97.81 63

PVSNet_Blended		92.80 59	92.44 67	93.23 58	96.02 64	97.83 57	93.74 91	90.58 62	91.86 64	90.69 38	85.87 74	82.04 108	90.01 99	96.39 45	95.26 59	98.34 49	97.81 63

Vis-MVSNet (Re-imp)		90.54 93	92.76 62	87.94 125	93.73 101	96.94 85	92.17 119	87.91 99	88.77 106	76.12 131	83.68 87	90.80 62	79.49 187	96.34 47	96.35 31	98.21 66	96.46 106

PVSNet_Blended_VisFu		91.92 70	92.39 69	91.36 90	95.45 74	97.85 56	92.25 116	89.54 78	88.53 110	87.47 63	79.82 113	90.53 67	85.47 151	96.31 48	95.16 62	97.99 87	98.56 22

train_agg		96.15 26	96.64 26	95.58 35	98.44 29	98.03 50	98.14 19	95.40 33	93.90 47	87.72 61	96.26 18	98.10 10	95.75 33	96.25 49	95.45 56	98.01 85	98.47 32

3Dnovator	90.28 7	94.70 44	94.34 50	95.11 37	98.06 34	98.21 44	96.89 39	91.03 60	94.72 39	91.45 31	82.87 94	93.10 51	94.61 43	96.24 50	97.08 13	98.63 22	98.16 45

gg-mvs-nofinetune		81.83 190	83.58 163	79.80 198	91.57 131	96.54 92	93.79 89	68.80 214	62.71 218	43.01 223	55.28 209	85.06 89	83.65 165	96.13 51	94.86 66	97.98 90	94.46 152

CDPH-MVS		94.80 43	95.50 34	93.98 49	98.34 30	98.06 49	97.41 32	93.23 41	92.81 55	82.98 100	92.51 35	94.82 43	93.53 61	96.08 52	96.30 36	98.42 41	97.94 56

EIA-MVS		92.72 61	92.96 60	92.44 72	93.86 97	97.76 59	93.13 104	88.65 90	89.78 96	86.68 70	86.69 65	87.57 74	93.74 58	96.07 53	95.32 57	98.58 24	97.53 73

TSAR-MVS + GP.		95.86 29	96.95 21	94.60 44	94.07 88	98.11 48	96.30 45	91.76 52	95.67 22	91.07 33	96.82 11	97.69 17	95.71 34	95.96 54	95.75 52	98.68 19	98.63 17

MVS_111021_LR		94.84 41	95.57 33	94.00 47	97.11 51	97.72 63	94.88 65	91.16 58	95.24 29	88.74 51	96.03 22	91.52 60	94.33 49	95.96 54	95.01 63	97.79 97	97.49 75

Vis-MVSNet		89.36 109	91.49 82	86.88 136	92.10 125	97.60 66	92.16 120	85.89 120	84.21 146	75.20 133	82.58 98	87.13 76	77.40 191	95.90 56	95.63 53	98.51 27	97.36 79
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DPM-MVS		95.07 37	94.84 41	95.34 36	97.44 45	97.49 68	97.76 27	95.52 26	94.88 36	88.92 49	87.25 61	96.44 31	94.41 45	95.78 57	96.11 44	97.99 87	95.95 126

MVSTER		91.73 74	91.61 80	91.86 79	93.18 107	94.56 114	94.37 71	87.90 100	90.16 88	88.69 53	89.23 53	81.28 113	88.92 119	95.75 58	93.95 81	98.12 74	96.37 110

QAPM		94.13 51	94.33 51	93.90 50	97.82 38	98.37 39	96.47 43	90.89 61	92.73 58	85.63 83	85.35 76	93.87 46	94.17 51	95.71 59	95.90 50	98.40 43	98.42 35

MSLP-MVS++		96.05 28	95.63 32	96.55 23	98.33 31	98.17 46	96.94 38	94.61 36	94.70 40	94.37 12	89.20 54	95.96 36	96.81 14	95.57 60	97.33 5	98.24 63	98.47 32

ACMMP		95.54 33	95.49 35	95.61 34	98.27 32	98.53 27	97.16 36	94.86 34	94.88 36	89.34 45	95.36 28	91.74 56	95.50 37	95.51 61	94.16 75	98.50 29	98.22 42
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
CANet_DTU		90.74 91	92.93 61	88.19 121	94.36 83	96.61 89	94.34 73	84.66 133	90.66 74	68.75 170	90.41 48	86.89 78	89.78 101	95.46 62	94.87 65	97.25 124	95.62 133

FA-MVS(training)		90.79 88	91.33 83	90.17 102	93.76 100	97.22 75	92.74 109	77.79 190	90.60 78	88.03 56	78.80 117	87.41 75	91.00 88	95.40 63	93.43 94	97.70 106	96.46 106

casdiffmvs		91.72 75	91.16 86	92.38 74	93.16 108	97.15 77	93.95 83	89.49 79	91.58 69	86.03 74	80.75 110	80.95 114	93.16 65	95.25 64	95.22 61	98.50 29	97.23 84

EPNet		93.92 52	94.40 47	93.36 57	97.89 36	96.55 91	96.08 48	92.14 47	91.65 67	89.16 47	94.07 31	90.17 71	87.78 126	95.24 65	94.97 64	97.09 134	98.15 46
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gm-plane-assit		77.65 202	78.50 200	76.66 203	87.96 170	85.43 213	64.70 219	74.50 198	64.15 217	51.26 218	61.32 201	58.17 214	84.11 163	95.16 66	93.83 82	97.45 119	91.41 179

baseline1		90.81 86	90.29 92	91.42 86	93.67 102	95.86 106	93.94 85	89.69 76	89.29 102	82.85 101	82.91 93	80.30 117	89.60 102	95.05 67	94.79 67	98.80 12	93.82 162

OpenMVS	88.18 11	92.51 63	91.61 80	93.55 56	97.74 40	98.02 51	95.66 55	90.46 64	89.14 103	86.50 72	75.80 136	90.38 70	92.69 70	94.99 68	95.30 58	98.27 59	97.63 67

MAR-MVS		92.71 62	92.63 63	92.79 69	97.70 41	97.15 77	93.75 90	87.98 98	90.71 73	85.76 81	86.28 69	86.38 80	94.35 48	94.95 69	95.49 55	97.22 125	97.44 76
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
CHOSEN 280x420		90.77 89	92.14 72	89.17 112	93.86 97	92.81 164	93.16 103	80.22 180	90.21 85	84.67 95	89.89 51	91.38 61	90.57 96	94.94 70	92.11 125	92.52 200	93.65 164

tfpn200view9		89.55 106	87.86 121	91.53 84	93.90 95	97.26 72	94.31 75	89.74 73	85.87 130	81.15 108	76.46 131	70.38 160	91.76 80	94.92 71	93.51 88	98.28 58	96.61 101

thres600view7		89.28 112	87.47 131	91.39 87	94.12 86	97.25 73	93.94 85	89.74 73	85.62 135	80.63 114	75.24 140	69.33 165	91.66 82	94.92 71	93.23 99	98.27 59	96.72 98

thres200		89.49 107	87.72 123	91.55 83	93.95 92	97.25 73	94.34 73	89.74 73	85.66 133	81.18 107	76.12 135	70.19 163	91.80 78	94.92 71	93.51 88	98.27 59	96.40 109

OMC-MVS		94.49 47	94.36 48	94.64 42	97.17 50	97.73 61	95.49 57	92.25 46	96.18 15	90.34 41	88.51 57	92.88 52	94.90 42	94.92 71	94.17 74	97.69 108	96.15 119

tttt0517		91.01 84	91.71 78	90.19 101	92.98 110	97.07 81	91.96 125	87.63 109	90.61 77	81.42 105	86.76 64	82.26 107	89.23 111	94.86 75	93.03 109	97.90 92	97.36 79

EPP-MVSNet		92.13 67	93.06 58	91.05 92	93.66 103	97.30 71	92.18 117	87.90 100	90.24 84	83.63 97	86.14 70	90.52 69	90.76 91	94.82 76	94.38 71	98.18 69	97.98 53

thisisatest0530		91.04 83	91.74 77	90.21 99	92.93 114	97.00 82	92.06 122	87.63 109	90.74 72	81.51 104	86.81 63	82.48 103	89.23 111	94.81 77	93.03 109	97.90 92	97.33 81

thres400		89.40 108	87.58 128	91.53 84	94.06 89	97.21 76	94.19 79	89.83 72	85.69 132	81.08 110	75.50 138	69.76 164	91.80 78	94.79 78	93.51 88	98.20 67	96.60 102

FC-MVSNet-train		90.55 92	90.19 94	90.97 93	93.78 99	95.16 110	92.11 121	88.85 85	87.64 115	83.38 99	84.36 83	78.41 129	89.53 103	94.69 79	93.15 104	98.15 70	97.92 58

UGNet		91.52 77	93.41 55	89.32 110	94.13 85	97.15 77	91.83 126	89.01 84	90.62 76	85.86 79	86.83 62	91.73 57	77.40 191	94.68 80	94.43 70	97.71 104	98.40 37
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
OPM-MVS		91.08 81	89.34 101	93.11 64	96.18 63	96.13 102	96.39 44	92.39 45	82.97 157	81.74 103	82.55 100	80.20 118	93.97 55	94.62 81	93.23 99	98.00 86	95.73 131
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Effi-MVS+		89.79 103	89.83 99	89.74 106	92.98 110	96.45 96	93.48 98	84.24 138	87.62 116	76.45 129	81.76 104	77.56 137	93.48 62	94.61 82	93.59 87	97.82 96	97.22 86

CSCG		95.68 31	95.46 36	95.93 29	98.71 26	99.07 7	97.13 37	93.55 39	95.48 26	93.35 21	90.61 47	93.82 47	95.16 39	94.60 83	95.57 54	97.70 106	99.08 10

CPTT-MVS		95.54 33	95.07 38	96.10 27	97.88 37	97.98 53	97.92 25	94.86 34	94.56 41	92.16 28	91.01 43	95.71 38	96.97 10	94.56 84	93.50 91	96.81 155	98.14 47

PLC	90.69 4	94.32 48	92.99 59	95.87 30	97.91 35	96.49 93	95.95 52	94.12 37	94.94 34	94.09 14	85.90 72	90.77 64	95.58 35	94.52 85	93.32 98	97.55 115	95.00 147
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
AdaColmap		95.02 39	93.71 52	96.54 24	98.51 28	97.76 59	96.69 41	95.94 21	93.72 48	93.50 18	89.01 55	90.53 67	96.49 22	94.51 86	93.76 84	98.07 79	96.69 99

TSAR-MVS + COLMAP		92.39 65	92.31 70	92.47 71	95.35 76	96.46 95	96.13 47	92.04 49	95.33 28	80.11 116	94.95 30	77.35 138	94.05 52	94.49 87	93.08 105	97.15 129	94.53 151

LS3D		91.97 69	90.98 88	93.12 63	97.03 53	97.09 80	95.33 60	95.59 24	92.47 59	79.26 120	81.60 106	82.77 101	94.39 47	94.28 88	94.23 73	97.14 131	94.45 153

LGP-MVS_train		91.83 72	92.04 74	91.58 82	95.46 72	96.18 101	95.97 51	89.85 71	90.45 80	77.76 123	91.92 39	80.07 119	92.34 75	94.27 89	93.47 92	98.11 76	97.90 61

FMVSNet2		89.61 105	89.14 105	90.16 103	88.66 161	93.65 137	94.25 76	85.44 127	88.57 109	84.96 94	73.53 147	83.82 93	89.38 106	94.23 90	94.68 69	98.31 52	95.47 137

Fast-Effi-MVS+		88.56 116	87.99 119	89.22 111	91.56 132	95.21 109	92.29 115	82.69 156	86.82 121	77.73 124	76.24 134	73.39 150	93.36 64	94.22 91	93.64 85	97.65 111	96.43 108

DI_MVS_plusplus_trai		91.05 82	90.15 95	92.11 76	92.67 120	96.61 89	96.03 49	88.44 92	90.25 83	85.92 77	73.73 144	84.89 90	91.92 77	94.17 92	94.07 79	97.68 109	97.31 82

thres100view900		89.36 109	87.61 126	91.39 87	93.90 95	96.86 87	94.35 72	89.66 77	85.87 130	81.15 108	76.46 131	70.38 160	91.17 85	94.09 93	93.43 94	98.13 73	96.16 118

ACMM	88.76 10	91.70 76	90.43 91	93.19 60	95.56 69	95.14 111	93.35 101	91.48 55	92.26 61	87.12 66	84.02 84	79.34 121	93.99 53	94.07 94	92.68 113	97.62 114	95.50 136
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS_Test		91.81 73	92.19 71	91.37 89	93.24 106	96.95 84	94.43 69	86.25 118	91.45 70	83.45 98	86.31 67	85.15 88	92.93 68	93.99 95	94.71 68	97.92 91	96.77 97

GBi-Net		90.21 97	90.11 96	90.32 97	88.66 161	93.65 137	94.25 76	85.78 123	90.03 89	85.56 85	77.38 122	86.13 81	89.38 106	93.97 96	94.16 75	98.31 52	95.47 137

test1		90.21 97	90.11 96	90.32 97	88.66 161	93.65 137	94.25 76	85.78 123	90.03 89	85.56 85	77.38 122	86.13 81	89.38 106	93.97 96	94.16 75	98.31 52	95.47 137

FMVSNet1		87.33 125	86.00 143	88.89 113	87.13 187	92.83 163	93.08 106	84.46 137	81.35 165	82.20 102	66.33 180	77.96 132	88.96 116	93.97 96	94.16 75	97.54 116	95.38 142

canonicalmvs		93.08 57	93.09 57	93.07 65	94.24 84	97.86 55	95.45 58	87.86 104	94.00 46	87.47 63	88.32 58	82.37 106	95.13 40	93.96 99	96.41 29	98.27 59	98.73 13

TAPA-MVS	90.35 6	93.69 55	93.52 53	93.90 50	96.89 54	97.62 65	96.15 46	91.67 53	94.94 34	85.97 75	87.72 60	91.96 54	94.40 46	93.76 100	93.06 107	98.30 55	95.58 135
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CLD-MVS		92.50 64	91.96 75	93.13 62	93.93 94	96.24 99	95.69 54	88.77 87	92.92 53	89.01 48	88.19 59	81.74 111	93.13 66	93.63 101	93.08 105	98.23 64	97.91 60
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CNLPA		93.69 55	92.50 65	95.06 38	97.11 51	97.36 70	93.88 87	93.30 40	95.64 24	93.44 20	80.32 111	90.73 65	94.99 41	93.58 102	93.33 96	97.67 110	96.57 104

GA-MVS		85.08 151	85.65 148	84.42 163	89.77 150	94.25 123	89.26 159	84.62 134	81.19 166	62.25 200	75.72 137	68.44 169	84.14 162	93.57 103	91.68 137	96.49 158	94.71 150

PatchMatch-RL		90.30 96	88.93 108	91.89 78	95.41 75	95.68 107	90.94 129	88.67 89	89.80 95	86.95 69	85.90 72	72.51 151	92.46 72	93.56 104	92.18 122	96.93 147	92.89 172

baseline2		88.97 113	89.50 100	88.36 118	91.14 137	95.30 108	90.13 143	85.17 130	87.24 117	80.80 112	84.46 82	78.44 128	85.60 148	93.54 105	91.87 131	97.31 122	95.66 132

pm-mvs1		84.55 157	83.46 164	85.82 144	88.16 168	93.39 143	89.05 164	85.36 129	74.03 203	72.43 146	65.08 188	71.11 157	82.30 173	93.48 106	91.70 135	97.64 112	95.43 140

HQP-MVS		92.39 65	92.49 66	92.29 75	95.65 68	95.94 105	95.64 56	92.12 48	92.46 60	79.65 118	91.97 38	82.68 102	92.92 69	93.47 107	92.77 112	97.74 102	98.12 49

CHOSEN 1792x2688		88.57 115	87.82 122	89.44 109	95.46 72	96.89 86	93.74 91	85.87 121	89.63 97	77.42 126	61.38 200	83.31 96	88.80 121	93.44 108	93.16 103	95.37 183	96.95 93

diffmvs		91.37 78	91.09 87	91.70 81	92.71 119	96.47 94	94.03 81	88.78 86	92.74 57	85.43 90	83.63 88	80.37 116	91.76 80	93.39 109	93.78 83	97.50 117	97.23 84

CDS-MVSNet		88.34 117	88.71 109	87.90 126	90.70 145	94.54 115	92.38 112	86.02 119	80.37 169	79.42 119	79.30 114	83.43 95	82.04 174	93.39 109	94.01 80	96.86 153	95.93 127
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
GeoE		89.29 111	88.68 110	89.99 105	92.75 118	96.03 104	93.07 107	83.79 145	86.98 120	81.34 106	74.72 141	78.92 123	91.22 84	93.31 111	93.21 101	97.78 98	97.60 72

FMVSNet3		90.19 99	90.06 98	90.34 96	88.69 160	93.85 129	94.58 66	85.78 123	90.03 89	85.56 85	77.38 122	86.13 81	89.22 113	93.29 112	94.36 72	98.20 67	95.40 141

ACMP	89.13 9	92.03 68	91.70 79	92.41 73	94.92 79	96.44 97	93.95 83	89.96 70	91.81 66	85.48 88	90.97 44	79.12 122	92.42 73	93.28 113	92.55 116	97.76 100	97.74 66
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
anonymousdsp		84.51 158	85.85 147	82.95 183	86.30 198	93.51 140	85.77 192	80.38 179	78.25 184	63.42 198	73.51 148	72.20 153	84.64 157	93.21 114	92.16 124	97.19 127	98.14 47

DCV-MVSNet		91.24 79	91.26 84	91.22 91	92.84 115	93.44 141	93.82 88	86.75 114	91.33 71	85.61 84	84.00 85	85.46 87	91.27 83	92.91 115	93.62 86	97.02 138	98.05 52

EPNet_dtu		88.32 118	90.61 90	85.64 148	96.79 56	92.27 176	92.03 123	90.31 65	89.05 104	65.44 191	89.43 52	85.90 85	74.22 200	92.76 116	92.09 126	95.02 189	92.76 173
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpnnormal		83.80 170	81.26 192	86.77 138	89.60 152	93.26 150	89.72 154	87.60 111	72.78 204	70.44 158	60.53 203	61.15 205	85.55 149	92.72 117	91.44 139	97.71 104	96.92 94

Anonymous202405211			88.00 118		93.16 108	96.38 98	93.58 95	89.34 80	87.92 114		65.04 189	83.03 98	92.07 76	92.67 118	93.33 96	96.96 142	97.63 67

GG-mvs-BLEND		62.84 211	90.21 93	30.91 220	0.57 228	94.45 118	86.99 182	0.34 226	88.71 107	0.98 228	81.55 108	91.58 59	0.86 225	92.66 119	91.43 140	95.73 172	91.11 183

Effi-MVS+-dtu		87.51 124	88.13 117	86.77 138	91.10 138	94.90 113	90.91 130	82.67 157	83.47 153	71.55 149	81.11 109	77.04 139	89.41 105	92.65 120	91.68 137	95.00 190	96.09 121

MSDG		90.42 95	88.25 115	92.94 67	96.67 57	94.41 120	93.96 82	92.91 43	89.59 98	86.26 73	76.74 129	80.92 115	90.43 97	92.60 121	92.08 127	97.44 120	91.41 179

thisisatest0515		85.70 142	87.00 132	84.19 166	88.16 168	93.67 136	84.20 197	84.14 141	83.39 155	72.91 142	76.79 128	74.75 147	78.82 189	92.57 122	91.26 142	96.94 144	96.56 105

FC-MVSNet-test		86.15 136	89.10 106	82.71 186	89.83 149	93.18 152	87.88 175	84.69 132	86.54 125	62.18 201	82.39 101	83.31 96	74.18 201	92.52 123	91.86 132	97.50 117	93.88 161

test-mter		86.09 139	88.38 112	83.43 176	87.89 171	92.61 168	86.89 183	77.11 193	84.30 144	68.62 172	82.57 99	82.45 104	84.34 158	92.40 124	90.11 167	95.74 171	94.21 157

PMMVS		89.88 101	91.19 85	88.35 119	89.73 151	91.97 184	90.62 132	81.92 167	90.57 79	80.58 115	92.16 36	86.85 79	91.17 85	92.31 125	91.35 141	96.11 166	93.11 171

test-LLR		86.88 128	88.28 113	85.24 152	91.22 135	92.07 180	87.41 178	83.62 147	84.58 139	69.33 166	83.00 91	82.79 99	84.24 159	92.26 126	89.81 173	95.64 176	93.44 165

TESTMET0.1,1		86.11 138	88.28 113	83.59 173	87.80 172	92.07 180	87.41 178	77.12 192	84.58 139	69.33 166	83.00 91	82.79 99	84.24 159	92.26 126	89.81 173	95.64 176	93.44 165

Anonymous20231211		89.82 102	88.18 116	91.74 80	92.52 121	96.09 103	93.38 100	89.30 82	88.95 105	85.90 78	64.55 193	84.39 91	92.41 74	92.24 128	93.06 107	96.93 147	97.95 55

MS-PatchMatch		87.63 121	87.61 126	87.65 129	93.95 92	94.09 125	92.60 111	81.52 172	86.64 123	76.41 130	73.46 149	85.94 84	85.01 155	92.23 129	90.00 170	96.43 162	90.93 185

MIMVSNet		82.97 181	84.00 161	81.77 194	82.23 209	92.25 177	87.40 180	72.73 208	81.48 164	69.55 164	68.79 169	72.42 152	81.82 177	92.23 129	92.25 120	96.89 150	88.61 199

HyFIR lowres test		87.87 120	86.42 137	89.57 107	95.56 69	96.99 83	92.37 113	84.15 140	86.64 123	77.17 127	57.65 206	83.97 92	91.08 87	92.09 131	92.44 117	97.09 134	95.16 144

baseline		91.19 80	91.89 76	90.38 95	92.76 116	95.04 112	93.55 96	84.54 136	92.92 53	85.71 82	86.68 66	86.96 77	89.28 109	92.00 132	92.62 115	96.46 160	96.99 91

PCF-MVS	90.19 8	92.98 58	92.07 73	94.04 46	96.39 60	97.87 54	96.03 49	95.47 31	87.16 118	85.09 93	84.81 80	93.21 50	93.46 63	91.98 133	91.98 130	97.78 98	97.51 74
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
USDC		86.73 131	85.96 144	87.63 130	91.64 129	93.97 127	92.76 108	84.58 135	88.19 111	70.67 157	80.10 112	67.86 172	89.43 104	91.81 134	89.77 175	96.69 157	90.05 192

NR-MVSNet		85.46 147	84.54 157	86.52 141	88.33 166	93.78 131	90.45 134	87.87 102	84.40 141	71.61 148	70.59 161	62.09 200	82.79 170	91.75 135	91.75 134	98.10 77	97.44 76

Fast-Effi-MVS+-dtu		86.25 133	87.70 124	84.56 161	90.37 148	93.70 134	90.54 133	78.14 187	83.50 152	65.37 192	81.59 107	75.83 146	86.09 147	91.70 136	91.70 135	96.88 151	95.84 129

TransMVSNet (Re)		82.67 184	80.93 195	84.69 159	88.71 159	91.50 191	87.90 174	87.15 112	71.54 209	68.24 174	63.69 195	64.67 192	78.51 190	91.65 137	90.73 151	97.64 112	92.73 175

EG-PatchMatch MVS		81.70 192	81.31 191	82.15 191	88.75 158	93.81 130	87.14 181	78.89 185	71.57 207	64.12 197	61.20 202	68.46 168	76.73 195	91.48 138	90.77 148	97.28 123	91.90 176

CR-MVSNet		85.48 146	86.29 138	84.53 162	91.08 140	92.10 178	89.18 160	73.30 205	84.75 137	71.08 154	73.12 154	77.91 133	86.27 143	91.48 138	90.75 149	96.27 164	93.94 159

PatchT		83.86 168	85.51 150	81.94 192	88.41 164	91.56 190	78.79 209	71.57 209	84.08 149	71.08 154	70.62 160	76.13 145	86.27 143	91.48 138	90.75 149	95.52 181	93.94 159

ET-MVSNet_ETH3D		89.93 100	90.84 89	88.87 114	79.60 213	96.19 100	94.43 69	86.56 115	90.63 75	80.75 113	90.71 46	77.78 134	93.73 59	91.36 141	93.45 93	98.15 70	95.77 130

ACMH	85.51 13	87.31 126	86.59 135	88.14 122	93.96 91	94.51 116	89.00 165	87.99 97	81.58 163	70.15 160	78.41 120	71.78 156	90.60 95	91.30 142	91.99 129	97.17 128	96.58 103
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS-SCA-FT		85.44 148	86.71 133	83.97 170	90.59 146	90.84 197	89.73 153	78.34 186	84.07 150	66.40 186	77.27 127	78.66 125	83.06 167	91.20 143	90.10 168	95.72 173	94.78 148

FMVSNet5		84.47 161	84.72 156	84.18 167	83.30 208	88.43 205	88.09 173	79.42 183	84.25 145	74.14 137	73.15 153	78.74 124	83.65 165	91.19 144	91.19 143	96.46 160	86.07 206

UniMVSNet (Re)		86.22 135	85.46 151	87.11 133	88.34 165	94.42 119	89.65 155	87.10 113	84.39 143	74.61 134	70.41 164	68.10 170	85.10 154	91.17 145	91.79 133	97.84 95	97.94 56

test0.0.03 1		85.58 144	87.69 125	83.11 179	91.22 135	92.54 171	85.60 194	83.62 147	85.66 133	67.84 177	82.79 96	79.70 120	73.51 204	91.15 146	90.79 146	96.88 151	91.23 182

v7n		82.25 188	81.54 188	83.07 181	85.55 202	92.58 169	86.68 186	81.10 177	76.54 192	65.97 188	62.91 196	60.56 207	82.36 172	91.07 147	90.35 158	96.77 156	96.80 96

IterMVS		85.25 150	86.49 136	83.80 171	90.42 147	90.77 200	90.02 145	78.04 188	84.10 148	66.27 187	77.28 126	78.41 129	83.01 168	90.88 148	89.72 177	95.04 188	94.24 155
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v10		84.18 163	83.17 173	85.37 149	87.34 181	92.68 166	90.32 136	81.33 173	79.93 176	69.23 168	66.33 180	65.74 183	87.03 134	90.84 149	90.38 157	96.97 140	96.29 115

pmmvs5		83.37 175	82.68 176	84.18 167	87.13 187	93.18 152	86.74 184	82.08 166	76.48 193	67.28 181	71.26 158	62.70 197	84.71 156	90.77 150	90.12 166	97.15 129	94.24 155

v1144		84.03 167	82.88 175	85.37 149	87.17 185	93.15 155	90.18 140	83.31 152	78.83 180	67.85 176	65.99 182	64.99 188	86.79 137	90.75 151	90.33 159	96.90 149	96.15 119

v1192		83.56 173	82.35 178	84.98 154	86.84 192	92.84 161	90.01 146	82.70 155	78.54 181	66.48 184	64.88 190	62.91 195	86.91 136	90.72 152	90.25 161	96.94 144	96.32 113

LTVRE_ROB	81.71 16	82.44 187	81.84 185	83.13 178	89.01 156	92.99 157	88.90 166	82.32 163	66.26 215	54.02 215	74.68 142	59.62 212	88.87 120	90.71 153	92.02 128	95.68 175	96.62 100
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
IterMVS-LS		88.60 114	88.45 111	88.78 115	92.02 126	92.44 174	92.00 124	83.57 149	86.52 126	78.90 122	78.61 119	81.34 112	89.12 114	90.68 154	93.18 102	97.10 133	96.35 111
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_part1		87.53 123	84.97 152	90.52 94	92.11 124	93.31 146	93.32 102	85.79 122	79.56 177	87.38 65	62.89 197	78.60 126	89.25 110	90.65 155	92.17 123	95.24 185	97.62 69

TAMVS		84.94 154	84.95 153	84.93 156	88.82 157	93.18 152	88.44 171	81.28 174	77.16 189	73.76 139	75.43 139	76.57 143	82.04 174	90.59 156	90.79 146	95.22 186	90.94 184

TinyColmap		84.04 166	82.01 183	86.42 142	90.87 141	91.84 185	88.89 167	84.07 142	82.11 162	69.89 162	71.08 159	60.81 206	89.04 115	90.52 157	89.19 181	95.76 170	88.50 200

pmmvs6		80.90 193	78.77 199	83.38 177	85.84 199	91.61 189	86.01 190	82.54 159	64.17 216	70.43 159	54.14 213	67.06 176	80.73 183	90.50 158	89.17 182	94.74 191	94.75 149

v1921920		83.30 176	82.09 182	84.70 158	86.59 196	92.67 167	89.82 152	82.23 164	78.32 182	65.76 189	64.64 192	62.35 198	86.78 138	90.34 159	90.02 169	97.02 138	96.31 114

UniMVSNet_NR-MVSNet		86.80 129	85.86 146	87.89 127	88.17 167	94.07 126	90.15 141	88.51 91	84.20 147	73.45 140	72.38 156	70.30 162	88.95 117	90.25 160	92.21 121	98.12 74	97.62 69

DU-MVS		86.12 137	84.81 155	87.66 128	87.77 174	93.78 131	90.15 141	87.87 102	84.40 141	73.45 140	70.59 161	64.82 190	88.95 117	90.14 161	92.33 118	97.76 100	97.62 69

Baseline_NR-MVSNet		85.28 149	83.42 167	87.46 132	87.77 174	90.80 199	89.90 151	87.69 106	83.93 151	74.16 136	64.72 191	66.43 180	87.48 131	90.14 161	90.83 145	97.73 103	97.11 89

v1240		82.88 182	81.66 186	84.29 164	86.46 197	92.52 173	89.06 163	81.82 169	77.16 189	65.09 193	64.17 194	61.50 203	86.36 140	90.12 163	90.13 163	96.95 143	96.04 123

testgi		81.94 189	84.09 160	79.43 199	89.53 154	90.83 198	82.49 201	81.75 170	80.59 167	59.46 207	82.82 95	65.75 182	67.97 206	90.10 164	89.52 178	95.39 182	89.03 195

RPMNet		84.82 155	85.90 145	83.56 174	91.10 138	92.10 178	88.73 169	71.11 210	84.75 137	68.79 169	73.56 146	77.62 136	85.33 152	90.08 165	89.43 179	96.32 163	93.77 163

COLMAP_ROB	84.39 15	87.61 122	86.03 141	89.46 108	95.54 71	94.48 117	91.77 127	90.14 69	87.16 118	75.50 132	73.41 150	76.86 142	87.33 132	90.05 166	89.76 176	96.48 159	90.46 188
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	85.75 12	87.19 127	86.02 142	88.56 117	93.42 105	94.41 120	89.91 149	87.66 108	83.45 154	72.25 147	76.42 133	71.99 155	90.78 90	89.86 167	90.94 144	97.32 121	95.11 146

CVMVSNet		83.83 169	85.53 149	81.85 193	89.60 152	90.92 195	87.81 176	83.21 153	80.11 172	60.16 205	76.47 130	78.57 127	76.79 193	89.76 168	90.13 163	93.51 192	92.75 174

TranMVSNet+NR-MVSNet		85.57 145	84.41 158	86.92 135	87.67 177	93.34 144	90.31 137	88.43 93	83.07 156	70.11 161	69.99 167	65.28 185	86.96 135	89.73 169	92.27 119	98.06 81	97.17 88

v144192		83.48 174	82.23 179	84.94 155	86.65 193	92.84 161	89.63 156	82.48 160	77.87 185	67.36 180	65.33 187	63.50 194	86.51 139	89.72 170	89.99 171	97.03 137	96.35 111

TDRefinement		84.97 153	83.39 168	86.81 137	92.97 112	94.12 124	92.18 117	87.77 105	82.78 158	71.31 152	68.43 170	68.07 171	81.10 182	89.70 171	89.03 183	95.55 180	91.62 177

IB-MVS	85.10 14	87.98 119	87.97 120	87.99 124	94.55 82	96.86 87	84.52 195	88.21 95	86.48 128	88.54 54	74.41 143	77.74 135	74.10 202	89.65 172	92.85 111	98.06 81	97.80 65
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
V42		84.48 160	83.36 170	85.79 146	87.14 186	93.28 148	90.03 144	83.98 143	80.30 170	71.20 153	66.90 177	67.17 174	85.55 149	89.35 173	90.27 160	96.82 154	96.27 116

WR-MVS_H		82.86 183	82.66 177	83.10 180	87.44 180	93.33 145	85.71 193	83.20 154	77.36 188	68.20 175	66.37 179	65.23 186	76.05 197	89.35 173	90.13 163	97.99 87	96.89 95

pmmvs4		86.00 140	84.28 159	88.00 123	87.80 172	92.01 183	89.94 148	84.91 131	86.79 122	80.98 111	73.41 150	66.34 181	88.12 124	89.31 175	88.90 184	96.24 165	93.20 170

v8		84.45 162	83.30 171	85.80 145	87.53 179	92.95 158	90.31 137	82.46 161	80.46 168	71.43 150	66.99 175	67.16 175	86.14 145	89.26 176	90.22 162	96.94 144	96.06 122

CP-MVSNet		83.11 180	82.15 180	84.23 165	87.20 184	92.70 165	86.42 187	83.53 150	77.83 186	67.67 178	66.89 178	60.53 208	82.47 171	89.23 177	90.65 153	98.08 78	97.20 87

v2v482		84.51 158	83.05 174	86.20 143	87.25 183	93.28 148	90.22 139	85.40 128	79.94 175	69.78 163	67.74 172	65.15 187	87.57 128	89.12 178	90.55 155	96.97 140	95.60 134

PS-CasMVS		82.53 185	81.54 188	83.68 172	87.08 189	92.54 171	86.20 189	83.46 151	76.46 194	65.73 190	65.71 185	59.41 213	81.61 179	89.06 179	90.55 155	98.03 83	97.07 90

WR-MVS		83.14 178	83.38 169	82.87 184	87.55 178	93.29 147	86.36 188	84.21 139	80.05 173	66.41 185	66.91 176	66.92 177	75.66 198	88.96 180	90.56 154	97.05 136	96.96 92

Anonymous20231206		78.09 201	78.11 202	78.07 202	85.19 204	89.17 203	80.99 204	81.24 176	75.46 200	58.25 209	54.78 212	59.90 211	66.73 209	88.94 181	88.26 185	96.01 167	90.25 190

UniMVSNet_ETH3D		84.57 156	81.40 190	88.28 120	89.34 155	94.38 122	90.33 135	86.50 116	74.74 202	77.52 125	59.90 204	62.04 201	88.78 122	88.82 182	92.65 114	97.22 125	97.24 83

test20.03		76.41 204	78.49 201	73.98 206	85.64 201	87.50 208	75.89 211	80.71 178	70.84 210	51.07 219	68.06 171	61.40 204	54.99 215	88.28 183	87.20 188	95.58 179	86.15 205

SixPastTwentyTwo		83.12 179	83.44 166	82.74 185	87.71 176	93.11 156	82.30 202	82.33 162	79.24 178	64.33 195	78.77 118	62.75 196	84.11 163	88.11 184	87.89 186	95.70 174	94.21 157

v148		83.61 172	82.10 181	85.37 149	87.34 181	92.94 159	87.48 177	85.72 126	78.92 179	73.87 138	65.71 185	64.69 191	81.78 178	87.82 185	89.35 180	96.01 167	95.26 143

PEN-MVS		82.49 186	81.58 187	83.56 174	86.93 190	92.05 182	86.71 185	83.84 144	76.94 191	64.68 194	67.24 173	60.11 209	81.17 181	87.78 186	90.70 152	98.02 84	96.21 117

pmmvs-eth3d		79.78 198	77.58 203	82.34 190	81.57 211	87.46 209	82.92 199	81.28 174	75.33 201	71.34 151	61.88 198	52.41 217	81.59 180	87.56 187	86.90 189	95.36 184	91.48 178

PM-MVS		80.29 195	79.30 198	81.45 195	81.91 210	88.23 206	82.61 200	79.01 184	79.99 174	67.15 182	69.07 168	51.39 218	82.92 169	87.55 188	85.59 193	95.08 187	93.28 168

RPSCF		89.68 104	89.24 103	90.20 100	92.97 112	92.93 160	92.30 114	87.69 106	90.44 81	85.12 92	91.68 40	85.84 86	90.69 92	87.34 189	86.07 191	92.46 201	90.37 189

DTE-MVSNet		81.76 191	81.04 193	82.60 188	86.63 194	91.48 193	85.97 191	83.70 146	76.45 195	62.44 199	67.16 174	59.98 210	78.98 188	87.15 190	89.93 172	97.88 94	95.12 145

MIMVSNet1		73.19 206	73.70 207	72.60 209	65.42 221	86.69 212	75.56 212	79.65 181	67.87 214	55.30 211	45.24 217	56.41 215	63.79 211	86.98 191	87.66 187	95.85 169	85.04 208

ambc			67.96 212		73.69 216	79.79 217	73.82 214		71.61 206	59.80 206	46.00 216	20.79 226	66.15 210	86.92 192	80.11 211	89.13 215	90.50 187

MDTV_nov1_ep13		86.64 132	87.50 130	85.65 147	90.73 143	93.69 135	89.96 147	78.03 189	89.48 101	76.85 128	84.92 79	82.42 105	86.14 145	86.85 193	86.15 190	92.17 202	88.97 197

MVS-HIRNet		78.16 200	77.57 204	78.83 200	85.83 200	87.76 207	76.67 210	70.22 212	75.82 199	67.39 179	55.61 208	70.52 159	81.96 176	86.67 194	85.06 198	90.93 209	81.58 212

EU-MVSNet		78.43 199	80.25 196	76.30 204	83.81 207	87.27 211	80.99 204	79.52 182	76.01 196	54.12 214	70.44 163	64.87 189	67.40 208	86.23 195	85.54 195	91.95 205	91.41 179

SCA		86.25 133	87.52 129	84.77 157	91.59 130	93.90 128	89.11 162	73.25 207	90.38 82	72.84 143	83.26 89	83.79 94	88.49 123	86.07 196	85.56 194	93.33 193	89.67 194

tpm		83.16 177	83.64 162	82.60 188	90.75 142	91.05 194	88.49 170	73.99 200	82.36 159	67.08 183	78.10 121	68.79 166	84.17 161	85.95 197	85.96 192	91.09 207	93.23 169

EPMVS		85.77 141	86.24 139	85.23 153	92.76 116	93.78 131	89.91 149	73.60 203	90.19 86	74.22 135	82.18 102	78.06 131	87.55 129	85.61 198	85.38 196	93.32 194	88.48 201

PatchmatchNet		85.70 142	86.65 134	84.60 160	91.79 127	93.40 142	89.27 158	73.62 202	90.19 86	72.63 145	82.74 97	81.93 110	87.64 127	84.99 199	84.29 201	92.64 199	89.00 196
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13_2view		80.43 194	80.94 194	79.84 197	84.82 205	90.87 196	84.23 196	73.80 201	80.28 171	64.33 195	70.05 166	68.77 167	79.67 184	84.83 200	83.50 203	92.17 202	88.25 203

CostFormer		86.78 130	86.05 140	87.62 131	92.15 123	93.20 151	91.55 128	75.83 195	88.11 113	85.29 91	81.76 104	76.22 144	87.80 125	84.45 201	85.21 197	93.12 195	93.42 167

dps		85.00 152	83.21 172	87.08 134	90.73 143	92.55 170	89.34 157	75.29 197	84.94 136	87.01 67	79.27 115	67.69 173	87.27 133	84.22 202	83.56 202	92.83 198	90.25 190

ADS-MVSNet		84.08 165	84.95 153	83.05 182	91.53 134	91.75 187	88.16 172	70.70 211	89.96 92	69.51 165	78.83 116	76.97 141	86.29 142	84.08 203	84.60 199	92.13 204	88.48 201

CMPMVS	61.19 17	79.86 197	77.46 205	82.66 187	91.54 133	91.82 186	83.25 198	81.57 171	70.51 211	68.64 171	59.89 205	66.77 178	79.63 185	84.00 204	84.30 200	91.34 206	84.89 209
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs3		71.13 209	71.06 211	71.21 210	73.54 217	80.19 216	71.69 217	64.86 216	62.04 219	52.10 216	54.92 211	48.00 222	75.03 199	83.75 205	83.24 204	90.04 213	85.27 207

tpmrst		83.72 171	83.45 165	84.03 169	92.21 122	91.66 188	88.74 168	73.58 204	88.14 112	72.67 144	77.37 125	72.11 154	86.34 141	82.94 206	82.05 205	90.63 210	89.86 193

pmnet_mix02		80.14 196	80.21 197	80.06 196	86.61 195	89.66 202	80.40 206	82.20 165	82.29 161	61.35 202	71.52 157	66.67 179	76.75 194	82.55 207	80.18 210	93.05 196	88.62 198

N_pmnet		77.55 203	76.68 206	78.56 201	85.43 203	87.30 210	78.84 208	81.88 168	78.30 183	60.61 203	61.46 199	62.15 199	74.03 203	82.04 208	80.69 209	90.59 211	84.81 210

new_pmnet		72.29 208	73.25 208	71.16 211	75.35 215	81.38 215	73.72 215	69.27 213	75.97 197	49.84 220	56.27 207	56.12 216	69.08 205	81.73 209	80.86 208	89.72 214	80.44 214

tpm cat1		84.13 164	81.99 184	86.63 140	91.74 128	91.50 191	90.68 131	75.69 196	86.12 129	85.44 89	72.39 155	70.72 158	85.16 153	80.89 210	81.56 206	91.07 208	90.71 186

test_method		58.10 214	64.61 214	50.51 215	28.26 226	41.71 225	61.28 220	32.07 222	75.92 198	52.04 217	47.94 215	61.83 202	51.80 216	79.83 211	63.95 219	77.60 220	81.05 213

new-patchmatchnet		72.32 207	71.09 210	73.74 207	81.17 212	84.86 214	72.21 216	77.48 191	68.32 213	54.89 213	55.10 210	49.31 221	63.68 212	79.30 212	76.46 213	93.03 197	84.32 211

Gipuma		58.52 213	56.17 216	61.27 213	67.14 220	58.06 221	52.16 223	68.40 215	69.00 212	45.02 222	22.79 220	20.57 227	55.11 214	76.27 213	79.33 212	79.80 219	67.16 219
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt				50.24 216	68.55 219	46.86 224	48.90 224	18.28 223	86.51 127	68.32 173	70.19 165	65.33 184	26.69 222	74.37 214	66.80 216	70.72 222

FPMVS		69.87 210	67.10 213	73.10 208	84.09 206	78.35 218	79.40 207	76.41 194	71.92 205	57.71 210	54.06 214	50.04 219	56.72 213	71.19 215	68.70 215	84.25 216	75.43 216

MDA-MVSNet-bldmvs		73.81 205	72.56 209	75.28 205	72.52 218	88.87 204	74.95 213	82.67 157	71.57 207	55.02 212	65.96 183	42.84 224	76.11 196	70.61 216	81.47 207	90.38 212	86.59 204

PMVS	56.77 18	61.27 212	58.64 215	64.35 212	75.66 214	54.60 222	53.62 222	74.23 199	53.69 220	58.37 208	44.27 218	49.38 220	44.16 219	69.51 217	65.35 217	80.07 218	73.66 217
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		53.68 215	55.72 217	51.30 214	58.84 222	67.02 220	54.23 221	60.97 219	47.50 221	19.42 225	34.81 219	31.97 225	30.88 221	65.84 218	69.99 214	83.47 217	72.92 218

DeepMVS_CX						71.82 219	68.37 218	48.05 221	77.38 187	46.88 221	65.77 184	47.03 223	67.48 207	64.27 219		76.89 221	76.72 215

MVE	39.81 19	39.52 217	41.58 218	37.11 219	33.93 225	49.06 223	26.45 227	54.22 220	29.46 224	24.15 224	20.77 222	10.60 230	34.42 220	51.12 220	65.27 218	49.49 225	64.81 220
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		40.00 216	35.74 219	44.98 217	57.69 224	39.15 227	28.05 225	62.70 217	35.52 223	17.78 226	20.90 221	14.36 229	44.47 218	35.89 221	47.86 220	59.15 223	56.47 221

EMVS		39.04 218	34.32 220	44.54 218	58.25 223	39.35 226	27.61 226	62.55 218	35.99 222	16.40 227	20.04 223	14.77 228	44.80 217	33.12 222	44.10 221	57.61 224	52.89 222

testmvs		4.35 219	6.54 221	1.79 221	0.60 227	1.82 228	3.06 229	0.95 224	7.22 225	0.88 229	12.38 224	1.25 231	3.87 224	6.09 223	5.58 222	1.40 226	11.42 224

test123		3.48 220	5.31 222	1.34 222	0.20 229	1.52 229	2.17 230	0.58 225	6.13 226	0.31 230	9.85 225	0.31 232	3.90 223	2.65 224	5.28 223	0.87 227	11.46 223

uanet_test		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

RE-MVS-def										60.19 204

9.14												97.28 24

SR-MVS					98.93 20			96.00 18				97.75 15

our_test_3					86.93 190	89.77 201	81.61 203

MTAPA										95.36 2		97.46 21

MTMP										95.70 1		96.90 27

Patchmatch-RL test							18.47 228

XVS					95.68 66	98.66 15	94.96 63			88.03 56		96.06 33				98.46 34

X-MVStestdata					95.68 66	98.66 15	94.96 63			88.03 56		96.06 33				98.46 34

abl_6				94.78 39	97.46 44	97.99 52	95.76 53	91.80 51	93.72 48	91.25 32	91.33 42	96.47 30	94.28 50			98.14 72	97.39 78

mPP-MVS					98.76 25							95.49 40

NP-MVS									91.63 68

Patchmtry						92.39 175	89.18 160	73.30 205		71.08 154

High-resolution multi-view benchmark