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.

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 60	95.06 1	94.23 3	78.38 36	92.78 4	95.74 6	82.45 3	97.49 4	89.42 16	96.68 2	94.95 11

FOURS1					95.00 10	72.39 40	95.06 1	93.84 16	74.49 132	91.30 15

CP-MVS		87.11 34	86.92 39	87.68 34	94.20 34	73.86 7	93.98 3	92.82 64	76.62 80	83.68 103	94.46 30	67.93 105	95.95 58	84.20 70	94.39 56	93.23 104

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 53	93.83 4	93.96 14	75.70 100	91.06 16	96.03 1	76.84 14	97.03 17	89.09 18	95.65 27	94.47 39
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 73	72.96 25	93.73 5	93.67 21	80.19 12	88.10 35	94.80 22	73.76 33	97.11 15	87.51 39	95.82 21	94.90 14
Skip Steuart: Steuart Systems R&D Blog.
lecture		88.09 14	88.59 13	86.58 57	93.26 52	69.77 91	93.70 6	94.16 5	77.13 63	89.76 20	95.52 14	72.26 47	96.27 44	86.87 43	94.65 48	93.70 80

test0726					95.27 5	71.25 60	93.60 7	94.11 7	77.33 55	92.81 3	95.79 3	80.98 9

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 67	93.57 8	94.06 11	77.24 58	93.10 1	95.72 8	82.99 1	97.44 7	89.07 21	96.63 4	94.88 15

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 53	82.45 3	96.87 20	83.77 74	96.48 8	94.88 15

DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 60	93.49 10	92.73 65	77.33 55	92.12 9	95.78 4	80.98 9	97.40 9	89.08 19	96.41 12	93.33 101
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
test_0728_SECOND				87.71 32	95.34 1	71.43 59	93.49 10	94.23 3					97.49 4	89.08 19	96.41 12	94.21 51

3Dnovator+	77.84 4	85.48 65	84.47 84	88.51 7	91.08 88	73.49 16	93.18 12	93.78 19	80.79 8	76.66 220	93.37 75	60.40 207	96.75 26	77.20 140	93.73 65	95.29 5

HFP-MVS		87.58 23	87.47 27	87.94 19	94.58 16	73.54 15	93.04 13	93.24 34	76.78 74	84.91 74	94.44 33	70.78 69	96.61 32	84.53 64	94.89 42	93.66 81

ACMMPR		87.44 26	87.23 32	88.08 15	94.64 13	73.59 12	93.04 13	93.20 35	76.78 74	84.66 81	94.52 26	68.81 95	96.65 30	84.53 64	94.90 41	94.00 61

ZNCC-MVS		87.94 19	87.85 20	88.20 12	94.39 24	73.33 19	93.03 15	93.81 18	76.81 72	85.24 69	94.32 38	71.76 54	96.93 19	85.53 53	95.79 22	94.32 47

region2R		87.42 28	87.20 33	88.09 14	94.63 14	73.55 13	93.03 15	93.12 41	76.73 77	84.45 86	94.52 26	69.09 89	96.70 27	84.37 66	94.83 45	94.03 59

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 17	94.11 7	80.27 10	91.35 14	94.16 46	78.35 13	96.77 24	89.59 14	94.22 61	94.67 28
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
CS-MVS		86.69 40	86.95 38	85.90 73	90.76 98	67.57 153	92.83 18	93.30 33	79.67 18	84.57 85	92.27 99	71.47 59	95.02 95	84.24 69	93.46 68	95.13 8

XVS		87.18 33	86.91 40	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 24	83.67 104	94.17 45	67.45 110	96.60 33	83.06 79	94.50 52	94.07 57

X-MVStestdata		80.37 171	77.83 208	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 24	83.67 104	12.47 445	67.45 110	96.60 33	83.06 79	94.50 52	94.07 57

mPP-MVS		86.67 42	86.32 46	87.72 30	94.41 22	73.55 13	92.74 21	92.22 89	76.87 71	82.81 116	94.25 42	66.44 121	96.24 45	82.88 84	94.28 59	93.38 97

ACMMP		85.89 58	85.39 68	87.38 39	93.59 45	72.63 33	92.74 21	93.18 40	76.78 74	80.73 145	93.82 64	64.33 142	96.29 42	82.67 90	90.69 107	93.23 104
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
MP-MVS		87.71 20	87.64 22	87.93 21	94.36 26	73.88 6	92.71 23	92.65 71	77.57 47	83.84 100	94.40 35	72.24 48	96.28 43	85.65 51	95.30 35	93.62 88
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MM		89.16 6	89.23 7	88.97 4	90.79 97	73.65 10	92.66 24	91.17 131	86.57 1	87.39 50	94.97 20	71.70 56	97.68 1	92.19 1	95.63 28	95.57 1

SF-MVS		88.46 12	88.74 12	87.64 35	92.78 65	71.95 50	92.40 25	94.74 2	75.71 98	89.16 22	95.10 17	75.65 21	96.19 47	87.07 42	96.01 17	94.79 22

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 25	93.63 22	74.77 126	92.29 7	95.97 2	74.28 29	97.24 13	88.58 29	96.91 1	94.87 17
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
GST-MVS		87.42 28	87.26 30	87.89 24	94.12 36	72.97 24	92.39 27	93.43 29	76.89 70	84.68 78	93.99 57	70.67 71	96.82 22	84.18 71	95.01 37	93.90 67

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 28	92.85 60	80.26 11	87.78 41	94.27 40	75.89 19	96.81 23	87.45 40	96.44 9	93.05 118

SR-MVS		86.73 39	86.67 42	86.91 50	94.11 37	72.11 48	92.37 29	92.56 76	74.50 131	86.84 57	94.65 25	67.31 112	95.77 60	84.80 60	92.85 73	92.84 127

SPE-MVS-test		86.29 49	86.48 44	85.71 75	91.02 90	67.21 168	92.36 30	93.78 19	78.97 31	83.51 107	91.20 132	70.65 72	95.15 86	81.96 93	94.89 42	94.77 24

EC-MVSNet		86.01 51	86.38 45	84.91 102	89.31 141	66.27 181	92.32 31	93.63 22	79.37 22	84.17 93	91.88 108	69.04 93	95.43 72	83.93 73	93.77 64	93.01 121

EPP-MVSNet		83.40 103	83.02 103	84.57 111	90.13 109	64.47 227	92.32 31	90.73 143	74.45 134	79.35 162	91.10 135	69.05 92	95.12 87	72.78 190	87.22 164	94.13 54

PHI-MVS		86.43 45	86.17 52	87.24 41	90.88 94	70.96 69	92.27 33	94.07 10	72.45 180	85.22 70	91.90 107	69.47 84	96.42 40	83.28 78	95.94 19	94.35 45

HPM-MVS		87.11 34	86.98 37	87.50 38	93.88 39	72.16 46	92.19 34	93.33 32	76.07 93	83.81 101	93.95 60	69.77 81	96.01 54	85.15 54	94.66 47	94.32 47
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MTMP							92.18 35	32.83 450

HPM-MVS_fast		85.35 71	84.95 77	86.57 58	93.69 42	70.58 79	92.15 36	91.62 117	73.89 149	82.67 118	94.09 49	62.60 161	95.54 66	80.93 102	92.93 72	93.57 90

CPTT-MVS		83.73 92	83.33 99	84.92 101	93.28 49	70.86 73	92.09 37	90.38 153	68.75 266	79.57 159	92.83 89	60.60 203	93.04 191	80.92 103	91.56 93	90.86 193

APD-MVS_3200maxsize		85.97 54	85.88 58	86.22 62	92.69 67	69.53 94	91.93 38	92.99 50	73.54 159	85.94 61	94.51 29	65.80 131	95.61 63	83.04 81	92.51 78	93.53 94

SR-MVS-dyc-post		85.77 59	85.61 64	86.23 61	93.06 59	70.63 77	91.88 39	92.27 85	73.53 160	85.69 65	94.45 31	65.00 139	95.56 64	82.75 85	91.87 86	92.50 139

RE-MVS-def			85.48 67		93.06 59	70.63 77	91.88 39	92.27 85	73.53 160	85.69 65	94.45 31	63.87 146		82.75 85	91.87 86	92.50 139

APD-MVS		87.44 26	87.52 26	87.19 42	94.24 32	72.39 40	91.86 41	92.83 61	73.01 174	88.58 27	94.52 26	73.36 34	96.49 38	84.26 67	95.01 37	92.70 129
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		88.06 15	88.50 15	86.71 55	92.60 70	72.71 29	91.81 42	93.19 36	77.87 40	90.32 17	94.00 55	74.83 23	93.78 147	87.63 38	94.27 60	93.65 85
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
SymmetryMVS		85.38 70	84.81 78	87.07 45	91.47 82	72.47 38	91.65 43	88.06 233	79.31 23	84.39 88	92.18 101	64.64 141	95.53 67	80.70 107	90.91 104	93.21 107

reproduce_model		87.28 31	87.39 29	86.95 49	93.10 57	71.24 64	91.60 44	93.19 36	74.69 127	88.80 26	95.61 11	70.29 75	96.44 39	86.20 49	93.08 70	93.16 111

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 45	94.10 9	75.90 96	92.29 7	95.66 10	81.67 6	97.38 11	87.44 41	96.34 15	93.95 64
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
QAPM		80.88 150	79.50 168	85.03 95	88.01 196	68.97 109	91.59 45	92.00 99	66.63 295	75.15 264	92.16 102	57.70 221	95.45 70	63.52 270	88.76 141	90.66 202

IS-MVSNet		83.15 109	82.81 107	84.18 132	89.94 118	63.30 254	91.59 45	88.46 226	79.04 28	79.49 160	92.16 102	65.10 136	94.28 121	67.71 237	91.86 88	94.95 11

reproduce-ours		87.47 24	87.61 23	87.07 45	93.27 50	71.60 54	91.56 48	93.19 36	74.98 118	88.96 23	95.54 12	71.20 64	96.54 36	86.28 47	93.49 66	93.06 116

our_new_method		87.47 24	87.61 23	87.07 45	93.27 50	71.60 54	91.56 48	93.19 36	74.98 118	88.96 23	95.54 12	71.20 64	96.54 36	86.28 47	93.49 66	93.06 116

9.14			88.26 16		92.84 64		91.52 50	94.75 1	73.93 148	88.57 28	94.67 24	75.57 22	95.79 59	86.77 44	95.76 23

MVS_0304		87.69 21	87.55 25	88.12 13	89.45 132	71.76 52	91.47 51	89.54 184	82.14 3	86.65 58	94.28 39	68.28 102	97.46 6	90.81 5	95.31 34	95.15 7

TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 47	91.41 52	92.35 83	74.62 130	88.90 25	93.85 63	75.75 20	96.00 55	87.80 36	94.63 49	95.04 9
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DeepC-MVS_fast	79.65 3	86.91 37	86.62 43	87.76 27	93.52 46	72.37 42	91.26 53	93.04 42	76.62 80	84.22 91	93.36 76	71.44 60	96.76 25	80.82 104	95.33 33	94.16 52
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HQP_MVS		83.64 95	83.14 100	85.14 90	90.08 111	68.71 118	91.25 54	92.44 78	79.12 26	78.92 168	91.00 142	60.42 205	95.38 77	78.71 123	86.32 178	91.33 176

plane_prior2							91.25 54		79.12 26

NCCC		88.06 15	88.01 19	88.24 11	94.41 22	73.62 11	91.22 56	92.83 61	81.50 5	85.79 64	93.47 72	73.02 41	97.00 18	84.90 56	94.94 40	94.10 55

API-MVS		81.99 127	81.23 131	84.26 129	90.94 92	70.18 86	91.10 57	89.32 191	71.51 198	78.66 173	88.28 209	65.26 134	95.10 92	64.74 264	91.23 98	87.51 310

EPNet		83.72 93	82.92 106	86.14 67	84.22 300	69.48 96	91.05 58	85.27 286	81.30 6	76.83 215	91.65 115	66.09 126	95.56 64	76.00 156	93.85 63	93.38 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		88.05 17	88.08 18	87.94 19	93.70 41	73.05 22	90.86 59	93.59 24	76.27 90	88.14 34	95.09 18	71.06 66	96.67 29	87.67 37	96.37 14	94.09 56

CSCG		86.41 47	86.19 51	87.07 45	92.91 62	72.48 37	90.81 60	93.56 25	73.95 146	83.16 110	91.07 137	75.94 18	95.19 84	79.94 114	94.38 57	93.55 92

MSLP-MVS++		85.43 67	85.76 61	84.45 116	91.93 76	70.24 80	90.71 61	92.86 59	77.46 53	84.22 91	92.81 91	67.16 114	92.94 193	80.36 109	94.35 58	90.16 223

3Dnovator	76.31 5	83.38 104	82.31 116	86.59 56	87.94 198	72.94 28	90.64 62	92.14 96	77.21 60	75.47 246	92.83 89	58.56 214	94.72 109	73.24 186	92.71 76	92.13 157

OpenMVS	72.83 10	79.77 180	78.33 195	84.09 138	85.17 277	69.91 88	90.57 63	90.97 136	66.70 289	72.17 309	91.91 106	54.70 249	93.96 134	61.81 291	90.95 103	88.41 292

balanced_conf03		86.78 38	86.99 36	86.15 65	91.24 85	67.61 151	90.51 64	92.90 57	77.26 57	87.44 49	91.63 117	71.27 63	96.06 50	85.62 52	95.01 37	94.78 23

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 64	93.00 47	80.90 7	88.06 36	94.06 51	76.43 16	96.84 21	88.48 32	95.99 18	94.34 46

MVSFormer		82.85 115	82.05 121	85.24 88	87.35 220	70.21 81	90.50 66	90.38 153	68.55 269	81.32 134	89.47 176	61.68 177	93.46 164	78.98 120	90.26 114	92.05 159

test_djsdf		80.30 172	79.32 173	83.27 173	83.98 306	65.37 204	90.50 66	90.38 153	68.55 269	76.19 233	88.70 195	56.44 236	93.46 164	78.98 120	80.14 269	90.97 189

save fliter					93.80 40	72.35 43	90.47 68	91.17 131	74.31 137

nrg030		83.88 88	83.53 94	84.96 98	86.77 240	69.28 104	90.46 69	92.67 68	74.79 125	82.95 111	91.33 128	72.70 45	93.09 186	80.79 106	79.28 279	92.50 139

sasdasda		85.91 56	85.87 59	86.04 69	89.84 120	69.44 100	90.45 70	93.00 47	76.70 78	88.01 38	91.23 129	73.28 36	93.91 141	81.50 96	88.80 139	94.77 24

canonicalmvs		85.91 56	85.87 59	86.04 69	89.84 120	69.44 100	90.45 70	93.00 47	76.70 78	88.01 38	91.23 129	73.28 36	93.91 141	81.50 96	88.80 139	94.77 24

plane_prior						68.71 118	90.38 72		77.62 45						86.16 182

DeepC-MVS	79.81 2	87.08 36	86.88 41	87.69 33	91.16 86	72.32 44	90.31 73	93.94 15	77.12 64	82.82 115	94.23 43	72.13 50	97.09 16	84.83 59	95.37 31	93.65 85
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
Vis-MVSNet		83.46 101	82.80 108	85.43 83	90.25 107	68.74 116	90.30 74	90.13 165	76.33 89	80.87 142	92.89 87	61.00 194	94.20 126	72.45 195	90.97 102	93.35 100
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PGM-MVS		86.68 41	86.27 48	87.90 22	94.22 33	73.38 18	90.22 75	93.04 42	75.53 102	83.86 99	94.42 34	67.87 107	96.64 31	82.70 89	94.57 51	93.66 81

LPG-MVS_test		82.08 124	81.27 130	84.50 113	89.23 145	68.76 114	90.22 75	91.94 103	75.37 107	76.64 221	91.51 121	54.29 252	94.91 97	78.44 125	83.78 214	89.83 244

Anonymous20231211		78.97 203	77.69 216	82.81 197	90.54 101	64.29 231	90.11 77	91.51 121	65.01 315	76.16 237	88.13 218	50.56 298	93.03 192	69.68 220	77.56 298	91.11 182

ACMM	73.20 8	80.78 159	79.84 160	83.58 163	89.31 141	68.37 129	89.99 78	91.60 118	70.28 227	77.25 204	89.66 169	53.37 263	93.53 160	74.24 175	82.85 234	88.85 276
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	74.13 6	81.51 141	80.57 142	84.36 119	89.42 133	68.69 121	89.97 79	91.50 124	74.46 133	75.04 268	90.41 152	53.82 258	94.54 113	77.56 136	82.91 233	89.86 243
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LFMVS		81.82 130	81.23 131	83.57 164	91.89 77	63.43 252	89.84 80	81.85 338	77.04 67	83.21 108	93.10 80	52.26 272	93.43 166	71.98 196	89.95 121	93.85 69

MCST-MVS		87.37 30	87.25 31	87.73 28	94.53 17	72.46 39	89.82 81	93.82 17	73.07 172	84.86 77	92.89 87	76.22 17	96.33 41	84.89 58	95.13 36	94.40 42

MAR-MVS		81.84 129	80.70 139	85.27 87	91.32 84	71.53 57	89.82 81	90.92 137	69.77 241	78.50 177	86.21 270	62.36 167	94.52 115	65.36 258	92.05 84	89.77 247
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
MP-MVS-pluss		87.67 22	87.72 21	87.54 36	93.64 44	72.04 49	89.80 83	93.50 26	75.17 115	86.34 60	95.29 16	70.86 68	96.00 55	88.78 27	96.04 16	94.58 33
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
UA-Net		85.08 76	84.96 76	85.45 82	92.07 74	68.07 139	89.78 84	90.86 141	82.48 2	84.60 84	93.20 79	69.35 85	95.22 83	71.39 201	90.88 105	93.07 115

alignmvs		85.48 65	85.32 71	85.96 72	89.51 129	69.47 97	89.74 85	92.47 77	76.17 91	87.73 45	91.46 124	70.32 74	93.78 147	81.51 95	88.95 136	94.63 32

VDDNet		81.52 139	80.67 140	84.05 145	90.44 103	64.13 234	89.73 86	85.91 279	71.11 207	83.18 109	93.48 70	50.54 299	93.49 161	73.40 183	88.25 150	94.54 37

CANet		86.45 44	86.10 54	87.51 37	90.09 110	70.94 71	89.70 87	92.59 75	81.78 4	81.32 134	91.43 125	70.34 73	97.23 14	84.26 67	93.36 69	94.37 44

test_fmvsmconf0.1_n		85.61 63	85.65 63	85.50 81	82.99 333	69.39 102	89.65 88	90.29 160	73.31 166	87.77 42	94.15 47	71.72 55	93.23 173	90.31 7	90.67 108	93.89 68

114514_t		80.68 160	79.51 167	84.20 131	94.09 38	67.27 164	89.64 89	91.11 134	58.75 381	74.08 283	90.72 146	58.10 217	95.04 94	69.70 219	89.42 131	90.30 219

MVSMamba_PlusPlus		85.99 52	85.96 57	86.05 68	91.09 87	67.64 150	89.63 90	92.65 71	72.89 177	84.64 82	91.71 113	71.85 52	96.03 51	84.77 61	94.45 55	94.49 38

test_fmvsmconf_n		85.92 55	86.04 56	85.57 80	85.03 284	69.51 95	89.62 91	90.58 146	73.42 163	87.75 43	94.02 53	72.85 43	93.24 172	90.37 6	90.75 106	93.96 62

fmvsm_l_conf0.5_n_3		86.02 50	86.32 46	85.14 90	87.20 229	68.54 125	89.57 92	90.44 151	75.31 109	87.49 47	94.39 36	72.86 42	92.72 199	89.04 23	90.56 109	94.16 52

DeepPCF-MVS	80.84 1	88.10 13	88.56 14	86.73 54	92.24 72	69.03 105	89.57 92	93.39 31	77.53 51	89.79 19	94.12 48	78.98 12	96.58 35	85.66 50	95.72 24	94.58 33

test_fmvsmconf0.01_n		84.73 81	84.52 83	85.34 85	80.25 374	69.03 105	89.47 94	89.65 180	73.24 170	86.98 55	94.27 40	66.62 117	93.23 173	90.26 8	89.95 121	93.78 77

fmvsm_s_conf0.5_n		83.80 90	83.71 92	84.07 140	86.69 243	67.31 162	89.46 95	83.07 321	71.09 208	86.96 56	93.70 67	69.02 94	91.47 255	88.79 26	84.62 200	93.44 96

MGCFI-Net		85.06 77	85.51 66	83.70 159	89.42 133	63.01 260	89.43 96	92.62 74	76.43 82	87.53 46	91.34 127	72.82 44	93.42 167	81.28 99	88.74 142	94.66 31

fmvsm_s_conf0.5_n_a		83.63 96	83.41 96	84.28 125	86.14 253	68.12 137	89.43 96	82.87 326	70.27 228	87.27 52	93.80 65	69.09 89	91.58 245	88.21 34	83.65 221	93.14 113

UGNet		80.83 152	79.59 166	84.54 112	88.04 193	68.09 138	89.42 98	88.16 228	76.95 68	76.22 232	89.46 178	49.30 315	93.94 137	68.48 232	90.31 112	91.60 166
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
tt0805		78.73 207	77.83 208	81.43 228	85.17 277	60.30 300	89.41 99	90.90 138	71.21 205	77.17 211	88.73 194	46.38 337	93.21 175	72.57 193	78.96 281	90.79 195

fmvsm_s_conf0.1_n		83.56 98	83.38 97	84.10 134	84.86 286	67.28 163	89.40 100	83.01 322	70.67 216	87.08 53	93.96 59	68.38 100	91.45 256	88.56 30	84.50 201	93.56 91

BP-MVS1		84.32 83	83.71 92	86.17 63	87.84 203	67.85 144	89.38 101	89.64 181	77.73 43	83.98 97	92.12 104	56.89 232	95.43 72	84.03 72	91.75 89	95.24 6

AdaColmap		80.58 166	79.42 169	84.06 142	93.09 58	68.91 110	89.36 102	88.97 210	69.27 250	75.70 242	89.69 167	57.20 229	95.77 60	63.06 275	88.41 149	87.50 311

fmvsm_s_conf0.1_n_a		83.32 106	82.99 104	84.28 125	83.79 310	68.07 139	89.34 103	82.85 327	69.80 239	87.36 51	94.06 51	68.34 101	91.56 248	87.95 35	83.46 227	93.21 107

PS-MVSNAJss		82.07 125	81.31 129	84.34 121	86.51 247	67.27 164	89.27 104	91.51 121	71.75 191	79.37 161	90.22 157	63.15 155	94.27 122	77.69 135	82.36 241	91.49 172

jajsoiax		79.29 194	77.96 202	83.27 173	84.68 291	66.57 177	89.25 105	90.16 164	69.20 255	75.46 248	89.49 175	45.75 348	93.13 184	76.84 147	80.80 259	90.11 227

fmvsm_s_conf0.5_n_8		86.56 43	87.17 34	84.73 108	87.76 210	65.62 197	89.20 106	92.21 90	79.94 16	89.74 21	94.86 21	68.63 97	94.20 126	90.83 4	91.39 95	94.38 43

fmvsm_s_conf0.5_n_5		85.22 73	85.55 65	84.25 130	86.26 249	67.40 159	89.18 107	89.31 192	72.50 179	88.31 30	93.86 62	69.66 82	91.96 230	89.81 10	91.05 100	93.38 97

mvs_tets		79.13 198	77.77 212	83.22 177	84.70 290	66.37 179	89.17 108	90.19 163	69.38 248	75.40 251	89.46 178	44.17 360	93.15 182	76.78 149	80.70 261	90.14 224

HQP-NCC					89.33 138		89.17 108		76.41 83	77.23 206

ACMP_Plane					89.33 138		89.17 108		76.41 83	77.23 206

HQP-MVS		82.61 118	82.02 122	84.37 118	89.33 138	66.98 171	89.17 108	92.19 92	76.41 83	77.23 206	90.23 156	60.17 208	95.11 89	77.47 137	85.99 186	91.03 186

LS3D		76.95 250	74.82 268	83.37 170	90.45 102	67.36 161	89.15 112	86.94 261	61.87 354	69.52 339	90.61 148	51.71 286	94.53 114	46.38 399	86.71 173	88.21 296

GDP-MVS		83.52 99	82.64 110	86.16 64	88.14 187	68.45 127	89.13 113	92.69 66	72.82 178	83.71 102	91.86 110	55.69 239	95.35 81	80.03 112	89.74 125	94.69 27

OPM-MVS		83.50 100	82.95 105	85.14 90	88.79 162	70.95 70	89.13 113	91.52 120	77.55 50	80.96 141	91.75 112	60.71 197	94.50 116	79.67 117	86.51 176	89.97 239
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
fmvsm_s_conf0.5_n_3		86.36 48	87.46 28	83.09 182	87.08 233	65.21 206	89.09 115	90.21 162	79.67 18	89.98 18	95.02 19	73.17 38	91.71 242	91.30 2	91.60 90	92.34 145

TSAR-MVS + GP.		85.71 61	85.33 70	86.84 51	91.34 83	72.50 36	89.07 116	87.28 252	76.41 83	85.80 63	90.22 157	74.15 31	95.37 80	81.82 94	91.88 85	92.65 133

test_prior4						72.60 34	89.01 117

GeoE		81.71 132	81.01 136	83.80 158	89.51 129	64.45 228	88.97 118	88.73 221	71.27 204	78.63 174	89.76 166	66.32 123	93.20 178	69.89 217	86.02 185	93.74 78

Anonymous20240529		80.19 175	78.89 183	84.10 134	90.60 99	64.75 221	88.95 119	90.90 138	65.97 303	80.59 146	91.17 134	49.97 305	93.73 153	69.16 225	82.70 238	93.81 73

VDD-MVS		83.01 114	82.36 115	84.96 98	91.02 90	66.40 178	88.91 120	88.11 229	77.57 47	84.39 88	93.29 77	52.19 273	93.91 141	77.05 143	88.70 143	94.57 35

Effi-MVS+		83.62 97	83.08 101	85.24 88	88.38 178	67.45 156	88.89 121	89.15 201	75.50 103	82.27 119	88.28 209	69.61 83	94.45 118	77.81 133	87.84 154	93.84 71

fmvsm_s_conf0.5_n_6		85.55 64	86.20 49	83.60 161	87.32 226	65.13 209	88.86 122	91.63 116	75.41 105	88.23 33	93.45 73	68.56 98	92.47 210	89.52 15	92.78 74	93.20 109

ACMH+	68.96 14	76.01 268	74.01 278	82.03 216	88.60 169	65.31 205	88.86 122	87.55 246	70.25 229	67.75 353	87.47 233	41.27 378	93.19 180	58.37 323	75.94 322	87.60 307

test_prior2							88.85 124		75.41 105	84.91 74	93.54 68	74.28 29		83.31 77	95.86 20

ElysianMVS		81.53 137	80.16 152	85.62 77	85.51 268	68.25 133	88.84 125	92.19 92	71.31 201	80.50 147	89.83 163	46.89 332	94.82 103	76.85 145	89.57 127	93.80 75

StellarMVS		81.53 137	80.16 152	85.62 77	85.51 268	68.25 133	88.84 125	92.19 92	71.31 201	80.50 147	89.83 163	46.89 332	94.82 103	76.85 145	89.57 127	93.80 75

DP-MVS Recon		83.11 112	82.09 120	86.15 65	94.44 19	70.92 72	88.79 127	92.20 91	70.53 221	79.17 164	91.03 140	64.12 144	96.03 51	68.39 234	90.14 116	91.50 171

fmvsm_s_conf0.5_n_4		85.39 69	85.75 62	84.30 123	86.70 242	65.83 190	88.77 128	89.78 174	75.46 104	88.35 29	93.73 66	69.19 88	93.06 188	91.30 2	88.44 148	94.02 60

Effi-MVS+-dtu		80.03 177	78.57 188	84.42 117	85.13 281	68.74 116	88.77 128	88.10 230	74.99 117	74.97 270	83.49 335	57.27 227	93.36 168	73.53 180	80.88 257	91.18 180

TEST9					93.26 52	72.96 25	88.75 130	91.89 105	68.44 272	85.00 72	93.10 80	74.36 28	95.41 75

train_agg		86.43 45	86.20 49	87.13 44	93.26 52	72.96 25	88.75 130	91.89 105	68.69 267	85.00 72	93.10 80	74.43 26	95.41 75	84.97 55	95.71 25	93.02 120

ETV-MVS		84.90 80	84.67 80	85.59 79	89.39 136	68.66 122	88.74 132	92.64 73	79.97 15	84.10 94	85.71 279	69.32 86	95.38 77	80.82 104	91.37 96	92.72 128

PVSNet_Blended_VisFu		82.62 117	81.83 126	84.96 98	90.80 96	69.76 92	88.74 132	91.70 114	69.39 247	78.96 166	88.46 204	65.47 133	94.87 102	74.42 172	88.57 144	90.24 221

casdiffmvs_mvg		85.99 52	86.09 55	85.70 76	87.65 214	67.22 167	88.69 134	93.04 42	79.64 20	85.33 68	92.54 96	73.30 35	94.50 116	83.49 75	91.14 99	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_8					93.13 55	72.57 35	88.68 135	91.84 109	68.69 267	84.87 76	93.10 80	74.43 26	95.16 85

test_fmvsm_n_1920		85.29 72	85.34 69	85.13 93	86.12 254	69.93 87	88.65 136	90.78 142	69.97 235	88.27 31	93.98 58	71.39 61	91.54 250	88.49 31	90.45 111	93.91 65

ACMH	67.68 16	75.89 269	73.93 280	81.77 221	88.71 166	66.61 176	88.62 137	89.01 207	69.81 238	66.78 367	86.70 255	41.95 376	91.51 253	55.64 346	78.14 290	87.17 319
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CDPH-MVS		85.76 60	85.29 73	87.17 43	93.49 47	71.08 65	88.58 138	92.42 81	68.32 274	84.61 83	93.48 70	72.32 46	96.15 49	79.00 119	95.43 30	94.28 49

DP-MVS		76.78 253	74.57 270	83.42 167	93.29 48	69.46 99	88.55 139	83.70 307	63.98 330	70.20 327	88.89 191	54.01 257	94.80 106	46.66 396	81.88 247	86.01 345

fmvsm_l_conf0.5_n		84.47 82	84.54 81	84.27 127	85.42 271	68.81 111	88.49 140	87.26 254	68.08 276	88.03 37	93.49 69	72.04 51	91.77 238	88.90 25	89.14 135	92.24 152

WR-MVS_H		78.51 214	78.49 189	78.56 293	88.02 194	56.38 351	88.43 141	92.67 68	77.14 62	73.89 285	87.55 230	66.25 124	89.24 302	58.92 316	73.55 355	90.06 233

F-COLMAP		76.38 263	74.33 276	82.50 209	89.28 143	66.95 174	88.41 142	89.03 205	64.05 328	66.83 366	88.61 199	46.78 334	92.89 194	57.48 330	78.55 283	87.67 305

GBi-Net		78.40 215	77.40 221	81.40 230	87.60 215	63.01 260	88.39 143	89.28 193	71.63 193	75.34 254	87.28 235	54.80 245	91.11 265	62.72 277	79.57 273	90.09 229

test1		78.40 215	77.40 221	81.40 230	87.60 215	63.01 260	88.39 143	89.28 193	71.63 193	75.34 254	87.28 235	54.80 245	91.11 265	62.72 277	79.57 273	90.09 229

FMVSNet1		77.44 241	76.12 248	81.40 230	86.81 239	63.01 260	88.39 143	89.28 193	70.49 222	74.39 280	87.28 235	49.06 319	91.11 265	60.91 298	78.52 284	90.09 229

tttt0517		79.40 191	77.91 204	83.90 154	88.10 190	63.84 240	88.37 146	84.05 303	71.45 199	76.78 217	89.12 185	49.93 308	94.89 100	70.18 213	83.18 231	92.96 124

fmvsm_l_conf0.5_n_a		84.13 85	84.16 86	84.06 142	85.38 272	68.40 128	88.34 147	86.85 264	67.48 283	87.48 48	93.40 74	70.89 67	91.61 243	88.38 33	89.22 133	92.16 156

v7n		78.97 203	77.58 219	83.14 180	83.45 318	65.51 199	88.32 148	91.21 129	73.69 154	72.41 305	86.32 269	57.93 218	93.81 146	69.18 224	75.65 325	90.11 227

COLMAP_ROB	66.92 17	73.01 308	70.41 323	80.81 248	87.13 232	65.63 196	88.30 149	84.19 302	62.96 339	63.80 393	87.69 225	38.04 396	92.56 205	46.66 396	74.91 342	84.24 372
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FIs		82.07 125	82.42 112	81.04 242	88.80 161	58.34 318	88.26 150	93.49 27	76.93 69	78.47 179	91.04 138	69.92 79	92.34 218	69.87 218	84.97 195	92.44 143

EIA-MVS		83.31 107	82.80 108	84.82 104	89.59 125	65.59 198	88.21 151	92.68 67	74.66 129	78.96 166	86.42 266	69.06 91	95.26 82	75.54 162	90.09 117	93.62 88

PLC	70.83 11	78.05 226	76.37 246	83.08 184	91.88 78	67.80 146	88.19 152	89.46 187	64.33 323	69.87 336	88.38 206	53.66 259	93.58 155	58.86 317	82.73 236	87.86 302
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MG-MVS		83.41 102	83.45 95	83.28 172	92.74 66	62.28 273	88.17 153	89.50 186	75.22 110	81.49 132	92.74 95	66.75 115	95.11 89	72.85 189	91.58 92	92.45 142

TAPA-MVS	73.13 9	79.15 197	77.94 203	82.79 201	89.59 125	62.99 264	88.16 154	91.51 121	65.77 304	77.14 212	91.09 136	60.91 195	93.21 175	50.26 378	87.05 166	92.17 155
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvsmvis_n_1920		84.02 87	83.87 89	84.49 115	84.12 302	69.37 103	88.15 155	87.96 235	70.01 233	83.95 98	93.23 78	68.80 96	91.51 253	88.61 28	89.96 120	92.57 134

h-mvs33		83.15 109	82.19 117	86.02 71	90.56 100	70.85 74	88.15 155	89.16 200	76.02 94	84.67 79	91.39 126	61.54 180	95.50 68	82.71 87	75.48 329	91.72 165

KinetiMVS		83.31 107	82.61 111	85.39 84	87.08 233	67.56 154	88.06 157	91.65 115	77.80 42	82.21 121	91.79 111	57.27 227	94.07 132	77.77 134	89.89 123	94.56 36

PS-CasMVS		78.01 228	78.09 200	77.77 310	87.71 211	54.39 376	88.02 158	91.22 128	77.50 52	73.26 293	88.64 198	60.73 196	88.41 319	61.88 289	73.88 352	90.53 208

OMC-MVS		82.69 116	81.97 124	84.85 103	88.75 164	67.42 157	87.98 159	90.87 140	74.92 121	79.72 157	91.65 115	62.19 171	93.96 134	75.26 166	86.42 177	93.16 111

v8		79.97 179	79.02 181	82.80 198	84.09 303	64.50 226	87.96 160	90.29 160	74.13 144	75.24 261	86.81 248	62.88 160	93.89 144	74.39 173	75.40 334	90.00 235

FC-MVSNet-test		81.52 139	82.02 122	80.03 265	88.42 177	55.97 357	87.95 161	93.42 30	77.10 65	77.38 201	90.98 144	69.96 78	91.79 237	68.46 233	84.50 201	92.33 146

CP-MVSNet		78.22 219	78.34 194	77.84 308	87.83 204	54.54 374	87.94 162	91.17 131	77.65 44	73.48 291	88.49 203	62.24 170	88.43 318	62.19 285	74.07 348	90.55 207

PAPM_NR		83.02 113	82.41 113	84.82 104	92.47 71	66.37 179	87.93 163	91.80 110	73.82 150	77.32 203	90.66 147	67.90 106	94.90 99	70.37 211	89.48 130	93.19 110

PEN-MVS		77.73 234	77.69 216	77.84 308	87.07 235	53.91 379	87.91 164	91.18 130	77.56 49	73.14 295	88.82 193	61.23 189	89.17 304	59.95 305	72.37 363	90.43 212

ECVR-MVS		79.61 182	79.26 175	80.67 251	90.08 111	54.69 372	87.89 165	77.44 384	74.88 122	80.27 150	92.79 92	48.96 321	92.45 211	68.55 231	92.50 79	94.86 18

v10		79.74 181	78.67 185	82.97 191	84.06 304	64.95 215	87.88 166	90.62 145	73.11 171	75.11 265	86.56 262	61.46 183	94.05 133	73.68 178	75.55 327	89.90 241

test2506		77.30 245	76.49 242	79.74 271	90.08 111	52.02 389	87.86 167	63.10 431	74.88 122	80.16 153	92.79 92	38.29 395	92.35 217	68.74 230	92.50 79	94.86 18

casdiffmvs		85.11 75	85.14 74	85.01 96	87.20 229	65.77 194	87.75 168	92.83 61	77.84 41	84.36 90	92.38 98	72.15 49	93.93 140	81.27 100	90.48 110	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TranMVSNet+NR-MVSNet		80.84 151	80.31 148	82.42 210	87.85 202	62.33 271	87.74 169	91.33 126	80.55 9	77.99 191	89.86 161	65.23 135	92.62 200	67.05 246	75.24 339	92.30 148

EI-MVSNet-Vis-set		84.19 84	83.81 90	85.31 86	88.18 184	67.85 144	87.66 170	89.73 178	80.05 14	82.95 111	89.59 173	70.74 70	94.82 103	80.66 108	84.72 198	93.28 103

UniMVSNet (Re)		81.60 136	81.11 133	83.09 182	88.38 178	64.41 229	87.60 171	93.02 46	78.42 35	78.56 176	88.16 213	69.78 80	93.26 171	69.58 221	76.49 311	91.60 166

CNLPA		78.08 224	76.79 235	81.97 218	90.40 104	71.07 66	87.59 172	84.55 295	66.03 302	72.38 306	89.64 170	57.56 223	86.04 344	59.61 309	83.35 228	88.79 279

DTE-MVSNet		76.99 248	76.80 234	77.54 316	86.24 250	53.06 388	87.52 173	90.66 144	77.08 66	72.50 303	88.67 197	60.48 204	89.52 296	57.33 333	70.74 375	90.05 234

无先验							87.48 174	88.98 208	60.00 367				94.12 130	67.28 242		88.97 271

mvsmamba		80.60 163	79.38 170	84.27 127	89.74 123	67.24 166	87.47 175	86.95 260	70.02 232	75.38 252	88.93 189	51.24 290	92.56 205	75.47 164	89.22 133	93.00 122

FMVSNet2		78.20 221	77.21 225	81.20 237	87.60 215	62.89 266	87.47 175	89.02 206	71.63 193	75.29 260	87.28 235	54.80 245	91.10 268	62.38 282	79.38 277	89.61 251

RRT-MVS		82.60 120	82.10 119	84.10 134	87.98 197	62.94 265	87.45 177	91.27 127	77.42 54	79.85 155	90.28 153	56.62 235	94.70 111	79.87 115	88.15 152	94.67 28

EI-MVSNet-UG-set		83.81 89	83.38 97	85.09 94	87.87 201	67.53 155	87.44 178	89.66 179	79.74 17	82.23 120	89.41 182	70.24 76	94.74 108	79.95 113	83.92 213	92.99 123

thisisatest0530		79.40 191	77.76 213	84.31 122	87.69 213	65.10 212	87.36 179	84.26 301	70.04 231	77.42 200	88.26 211	49.94 306	94.79 107	70.20 212	84.70 199	93.03 119

CANet_DTU		80.61 162	79.87 159	82.83 195	85.60 266	63.17 259	87.36 179	88.65 222	76.37 87	75.88 239	88.44 205	53.51 261	93.07 187	73.30 184	89.74 125	92.25 150

test1111		79.43 189	79.18 178	80.15 263	89.99 116	53.31 385	87.33 181	77.05 388	75.04 116	80.23 152	92.77 94	48.97 320	92.33 219	68.87 228	92.40 81	94.81 21

baseline		84.93 78	84.98 75	84.80 106	87.30 227	65.39 203	87.30 182	92.88 58	77.62 45	84.04 96	92.26 100	71.81 53	93.96 134	81.31 98	90.30 113	95.03 10

UniMVSNet_ETH3D		79.10 199	78.24 197	81.70 222	86.85 237	60.24 301	87.28 183	88.79 215	74.25 140	76.84 214	90.53 151	49.48 311	91.56 248	67.98 235	82.15 242	93.29 102

anonymousdsp		78.60 211	77.15 226	82.98 190	80.51 372	67.08 169	87.24 184	89.53 185	65.66 306	75.16 263	87.19 241	52.52 267	92.25 221	77.17 141	79.34 278	89.61 251

UniMVSNet_NR-MVSNet		81.88 128	81.54 128	82.92 192	88.46 174	63.46 250	87.13 185	92.37 82	80.19 12	78.38 180	89.14 184	71.66 58	93.05 189	70.05 214	76.46 312	92.25 150

DPM-MVS		84.93 78	84.29 85	86.84 51	90.20 108	73.04 23	87.12 186	93.04 42	69.80 239	82.85 114	91.22 131	73.06 40	96.02 53	76.72 150	94.63 49	91.46 175

v1144		80.03 177	79.03 180	83.01 188	83.78 311	64.51 224	87.11 187	90.57 148	71.96 190	78.08 189	86.20 271	61.41 184	93.94 137	74.93 168	77.23 299	90.60 205

v2v482		80.23 173	79.29 174	83.05 186	83.62 314	64.14 233	87.04 188	89.97 169	73.61 156	78.18 186	87.22 239	61.10 192	93.82 145	76.11 153	76.78 308	91.18 180

fmvsm_s_conf0.1_n_2		83.80 90	83.79 91	83.83 155	85.62 265	64.94 216	87.03 189	86.62 268	74.32 136	87.97 40	94.33 37	60.67 199	92.60 202	89.72 11	87.79 155	93.96 62

DU-MVS		81.12 147	80.52 144	82.90 193	87.80 205	63.46 250	87.02 190	91.87 107	79.01 29	78.38 180	89.07 186	65.02 137	93.05 189	70.05 214	76.46 312	92.20 153

LuminaMVS		80.68 160	79.62 165	83.83 155	85.07 283	68.01 142	86.99 191	88.83 213	70.36 223	81.38 133	87.99 220	50.11 303	92.51 209	79.02 118	86.89 170	90.97 189

fmvsm_s_conf0.5_n_2		84.04 86	84.11 87	83.81 157	86.17 252	65.00 214	86.96 192	87.28 252	74.35 135	88.25 32	94.23 43	61.82 175	92.60 202	89.85 9	88.09 153	93.84 71

v144192		79.47 187	78.37 193	82.78 202	83.35 319	63.96 236	86.96 192	90.36 156	69.99 234	77.50 198	85.67 282	60.66 200	93.77 149	74.27 174	76.58 309	90.62 203

Fast-Effi-MVS+-dtu		78.02 227	76.49 242	82.62 206	83.16 327	66.96 173	86.94 194	87.45 250	72.45 180	71.49 317	84.17 319	54.79 248	91.58 245	67.61 238	80.31 266	89.30 259

v1192		79.59 184	78.43 192	83.07 185	83.55 316	64.52 223	86.93 195	90.58 146	70.83 212	77.78 194	85.90 275	59.15 211	93.94 137	73.96 177	77.19 301	90.76 197

EPNet_dtu		75.46 275	74.86 267	77.23 320	82.57 342	54.60 373	86.89 196	83.09 320	71.64 192	66.25 376	85.86 277	55.99 237	88.04 323	54.92 350	86.55 175	89.05 266
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM2							86.86 197

VPA-MVSNet		80.60 163	80.55 143	80.76 249	88.07 192	60.80 292	86.86 197	91.58 119	75.67 101	80.24 151	89.45 180	63.34 149	90.25 283	70.51 210	79.22 280	91.23 179

v1921920		79.22 195	78.03 201	82.80 198	83.30 321	63.94 238	86.80 199	90.33 157	69.91 237	77.48 199	85.53 286	58.44 215	93.75 151	73.60 179	76.85 306	90.71 201

IterMVS-LS		80.06 176	79.38 170	82.11 214	85.89 258	63.20 257	86.79 200	89.34 190	74.19 141	75.45 249	86.72 251	66.62 117	92.39 214	72.58 192	76.86 305	90.75 198
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TransMVSNet (Re)		75.39 279	74.56 271	77.86 307	85.50 270	57.10 339	86.78 201	86.09 278	72.17 186	71.53 316	87.34 234	63.01 159	89.31 300	56.84 339	61.83 404	87.17 319

Baseline_NR-MVSNet		78.15 223	78.33 195	77.61 313	85.79 260	56.21 355	86.78 201	85.76 282	73.60 157	77.93 192	87.57 228	65.02 137	88.99 307	67.14 245	75.33 336	87.63 306

PAPR		81.66 135	80.89 138	83.99 150	90.27 106	64.00 235	86.76 203	91.77 113	68.84 265	77.13 213	89.50 174	67.63 108	94.88 101	67.55 239	88.52 146	93.09 114

Vis-MVSNet (Re-imp)		78.36 217	78.45 190	78.07 304	88.64 168	51.78 395	86.70 204	79.63 366	74.14 143	75.11 265	90.83 145	61.29 188	89.75 292	58.10 326	91.60 90	92.69 131

guyue		81.13 146	80.64 141	82.60 207	86.52 246	63.92 239	86.69 205	87.73 243	73.97 145	80.83 144	89.69 167	56.70 233	91.33 261	78.26 132	85.40 192	92.54 136

pmmvs6		74.69 284	73.39 287	78.61 290	81.38 361	57.48 334	86.64 206	87.95 236	64.99 316	70.18 328	86.61 258	50.43 300	89.52 296	62.12 287	70.18 378	88.83 277

v1240		78.99 202	77.78 211	82.64 205	83.21 323	63.54 247	86.62 207	90.30 159	69.74 244	77.33 202	85.68 281	57.04 230	93.76 150	73.13 187	76.92 303	90.62 203

MTAPA		87.23 32	87.00 35	87.90 22	94.18 35	74.25 5	86.58 208	92.02 97	79.45 21	85.88 62	94.80 22	68.07 103	96.21 46	86.69 45	95.34 32	93.23 104

旧先验2							86.56 209		58.10 386	87.04 54			88.98 308	74.07 176

FMVSNet3		77.88 231	76.85 233	80.97 245	86.84 238	62.36 270	86.52 210	88.77 216	71.13 206	75.34 254	86.66 257	54.07 255	91.10 268	62.72 277	79.57 273	89.45 255

dcpmvs_2		85.63 62	86.15 53	84.06 142	91.71 79	64.94 216	86.47 211	91.87 107	73.63 155	86.60 59	93.02 85	76.57 15	91.87 236	83.36 76	92.15 82	95.35 3

AstraMVS		80.81 153	80.14 154	82.80 198	86.05 257	63.96 236	86.46 212	85.90 280	73.71 153	80.85 143	90.56 149	54.06 256	91.57 247	79.72 116	83.97 212	92.86 126

pm-mvs1		77.25 246	76.68 240	78.93 286	84.22 300	58.62 315	86.41 213	88.36 227	71.37 200	73.31 292	88.01 219	61.22 190	89.15 305	64.24 268	73.01 360	89.03 267

EI-MVSNet		80.52 167	79.98 156	82.12 213	84.28 298	63.19 258	86.41 213	88.95 211	74.18 142	78.69 171	87.54 231	66.62 117	92.43 212	72.57 193	80.57 263	90.74 199

CVMVSNet		72.99 309	72.58 298	74.25 351	84.28 298	50.85 403	86.41 213	83.45 313	44.56 422	73.23 294	87.54 231	49.38 313	85.70 347	65.90 254	78.44 286	86.19 340

MonoMVSNet		76.49 260	75.80 249	78.58 292	81.55 357	58.45 316	86.36 216	86.22 274	74.87 124	74.73 274	83.73 328	51.79 285	88.73 313	70.78 205	72.15 366	88.55 289

NR-MVSNet		80.23 173	79.38 170	82.78 202	87.80 205	63.34 253	86.31 217	91.09 135	79.01 29	72.17 309	89.07 186	67.20 113	92.81 198	66.08 253	75.65 325	92.20 153

v148		78.72 208	77.80 210	81.47 227	82.73 338	61.96 277	86.30 218	88.08 231	73.26 168	76.18 234	85.47 288	62.46 165	92.36 216	71.92 197	73.82 353	90.09 229

新几何2							86.29 219

test_yl		81.17 144	80.47 145	83.24 175	89.13 149	63.62 243	86.21 220	89.95 170	72.43 183	81.78 129	89.61 171	57.50 224	93.58 155	70.75 206	86.90 168	92.52 137

DCV-MVSNet		81.17 144	80.47 145	83.24 175	89.13 149	63.62 243	86.21 220	89.95 170	72.43 183	81.78 129	89.61 171	57.50 224	93.58 155	70.75 206	86.90 168	92.52 137

PVSNet_BlendedMVS		80.60 163	80.02 155	82.36 212	88.85 156	65.40 201	86.16 222	92.00 99	69.34 249	78.11 187	86.09 274	66.02 128	94.27 122	71.52 198	82.06 244	87.39 312

MVS_Test		83.15 109	83.06 102	83.41 169	86.86 236	63.21 256	86.11 223	92.00 99	74.31 137	82.87 113	89.44 181	70.03 77	93.21 175	77.39 139	88.50 147	93.81 73

BH-untuned		79.47 187	78.60 187	82.05 215	89.19 147	65.91 188	86.07 224	88.52 225	72.18 185	75.42 250	87.69 225	61.15 191	93.54 159	60.38 302	86.83 171	86.70 333

MVS_111021_HR		85.14 74	84.75 79	86.32 60	91.65 80	72.70 30	85.98 225	90.33 157	76.11 92	82.08 123	91.61 119	71.36 62	94.17 129	81.02 101	92.58 77	92.08 158

jason		81.39 142	80.29 149	84.70 109	86.63 245	69.90 89	85.95 226	86.77 265	63.24 334	81.07 140	89.47 176	61.08 193	92.15 224	78.33 128	90.07 119	92.05 159
jason: jason.
test_0402		72.79 311	70.44 322	79.84 269	88.13 188	65.99 186	85.93 227	84.29 299	65.57 307	67.40 360	85.49 287	46.92 331	92.61 201	35.88 424	74.38 347	80.94 403

OurMVSNet-221017-0		74.26 287	72.42 300	79.80 270	83.76 312	59.59 308	85.92 228	86.64 266	66.39 297	66.96 364	87.58 227	39.46 386	91.60 244	65.76 256	69.27 381	88.22 295

hse-mvs2		81.72 131	80.94 137	84.07 140	88.72 165	67.68 149	85.87 229	87.26 254	76.02 94	84.67 79	88.22 212	61.54 180	93.48 162	82.71 87	73.44 357	91.06 184

EG-PatchMatch MVS		74.04 291	71.82 305	80.71 250	84.92 285	67.42 157	85.86 230	88.08 231	66.04 301	64.22 388	83.85 323	35.10 406	92.56 205	57.44 331	80.83 258	82.16 397

AUN-MVS		79.21 196	77.60 218	84.05 145	88.71 166	67.61 151	85.84 231	87.26 254	69.08 258	77.23 206	88.14 217	53.20 265	93.47 163	75.50 163	73.45 356	91.06 184

thres100view900		76.50 257	75.55 256	79.33 279	89.52 128	56.99 340	85.83 232	83.23 316	73.94 147	76.32 230	87.12 243	51.89 282	91.95 231	48.33 387	83.75 217	89.07 261

CLD-MVS		82.31 121	81.65 127	84.29 124	88.47 173	67.73 148	85.81 233	92.35 83	75.78 97	78.33 182	86.58 261	64.01 145	94.35 119	76.05 155	87.48 160	90.79 195
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
VortexMVS		78.57 213	77.89 206	80.59 252	85.89 258	62.76 267	85.61 234	89.62 182	72.06 188	74.99 269	85.38 290	55.94 238	90.77 277	74.99 167	76.58 309	88.23 294

SixPastTwentyTwo		73.37 300	71.26 314	79.70 272	85.08 282	57.89 326	85.57 235	83.56 310	71.03 210	65.66 378	85.88 276	42.10 374	92.57 204	59.11 314	63.34 400	88.65 285

xiu_mvs_v1_base_debu		80.80 156	79.72 162	84.03 147	87.35 220	70.19 83	85.56 236	88.77 216	69.06 259	81.83 125	88.16 213	50.91 293	92.85 195	78.29 129	87.56 157	89.06 263

xiu_mvs_v1_base		80.80 156	79.72 162	84.03 147	87.35 220	70.19 83	85.56 236	88.77 216	69.06 259	81.83 125	88.16 213	50.91 293	92.85 195	78.29 129	87.56 157	89.06 263

xiu_mvs_v1_base_debi		80.80 156	79.72 162	84.03 147	87.35 220	70.19 83	85.56 236	88.77 216	69.06 259	81.83 125	88.16 213	50.91 293	92.85 195	78.29 129	87.56 157	89.06 263

V42		79.38 193	78.24 197	82.83 195	81.10 366	65.50 200	85.55 239	89.82 173	71.57 197	78.21 184	86.12 273	60.66 200	93.18 181	75.64 159	75.46 331	89.81 246

lupinMVS		81.39 142	80.27 150	84.76 107	87.35 220	70.21 81	85.55 239	86.41 270	62.85 341	81.32 134	88.61 199	61.68 177	92.24 222	78.41 127	90.26 114	91.83 162

Fast-Effi-MVS+		80.81 153	79.92 157	83.47 165	88.85 156	64.51 224	85.53 241	89.39 189	70.79 213	78.49 178	85.06 299	67.54 109	93.58 155	67.03 247	86.58 174	92.32 147

thres600view7		76.50 257	75.44 257	79.68 273	89.40 135	57.16 337	85.53 241	83.23 316	73.79 151	76.26 231	87.09 244	51.89 282	91.89 234	48.05 392	83.72 220	90.00 235

DELS-MVS		85.41 68	85.30 72	85.77 74	88.49 172	67.93 143	85.52 243	93.44 28	78.70 32	83.63 106	89.03 188	74.57 24	95.71 62	80.26 111	94.04 62	93.66 81
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
fmvsm_s_conf0.5_n_7		83.34 105	84.03 88	81.28 234	85.73 262	65.13 209	85.40 244	89.90 172	74.96 120	82.13 122	93.89 61	66.65 116	87.92 324	86.56 46	91.05 100	90.80 194

tfpn200view9		76.42 261	75.37 261	79.55 278	89.13 149	57.65 331	85.17 245	83.60 308	73.41 164	76.45 226	86.39 267	52.12 274	91.95 231	48.33 387	83.75 217	89.07 261

thres400		76.50 257	75.37 261	79.86 268	89.13 149	57.65 331	85.17 245	83.60 308	73.41 164	76.45 226	86.39 267	52.12 274	91.95 231	48.33 387	83.75 217	90.00 235

MVS_111021_LR		82.61 118	82.11 118	84.11 133	88.82 159	71.58 56	85.15 247	86.16 276	74.69 127	80.47 149	91.04 138	62.29 168	90.55 280	80.33 110	90.08 118	90.20 222

baseline1		76.98 249	76.75 238	77.66 311	88.13 188	55.66 362	85.12 248	81.89 336	73.04 173	76.79 216	88.90 190	62.43 166	87.78 327	63.30 274	71.18 373	89.55 253

mmtdpeth		74.16 289	73.01 293	77.60 315	83.72 313	61.13 285	85.10 249	85.10 288	72.06 188	77.21 210	80.33 375	43.84 362	85.75 346	77.14 142	52.61 423	85.91 348

WR-MVS		79.49 186	79.22 177	80.27 260	88.79 162	58.35 317	85.06 250	88.61 224	78.56 33	77.65 196	88.34 207	63.81 148	90.66 279	64.98 262	77.22 300	91.80 164

ET-MVSNet_ETH3D		78.63 210	76.63 241	84.64 110	86.73 241	69.47 97	85.01 251	84.61 294	69.54 245	66.51 374	86.59 259	50.16 302	91.75 239	76.26 152	84.24 209	92.69 131

OpenMVS_ROB	64.09 19	70.56 332	68.19 338	77.65 312	80.26 373	59.41 311	85.01 251	82.96 325	58.76 380	65.43 380	82.33 354	37.63 398	91.23 264	45.34 406	76.03 321	82.32 394

BH-RMVSNet		79.61 182	78.44 191	83.14 180	89.38 137	65.93 187	84.95 253	87.15 257	73.56 158	78.19 185	89.79 165	56.67 234	93.36 168	59.53 310	86.74 172	90.13 225

BH-w/o		78.21 220	77.33 224	80.84 247	88.81 160	65.13 209	84.87 254	87.85 240	69.75 242	74.52 278	84.74 306	61.34 186	93.11 185	58.24 325	85.84 188	84.27 371

TDRefinement		67.49 358	64.34 369	76.92 322	73.47 417	61.07 288	84.86 255	82.98 324	59.77 369	58.30 412	85.13 297	26.06 421	87.89 325	47.92 393	60.59 409	81.81 399

Anonymous202405211		78.25 218	77.01 228	81.99 217	91.03 89	60.67 294	84.77 256	83.90 305	70.65 220	80.00 154	91.20 132	41.08 380	91.43 257	65.21 259	85.26 193	93.85 69

TAMVS		78.89 205	77.51 220	83.03 187	87.80 205	67.79 147	84.72 257	85.05 290	67.63 279	76.75 218	87.70 224	62.25 169	90.82 274	58.53 321	87.13 165	90.49 210

sc_t1		72.19 317	69.51 328	80.23 261	84.81 287	61.09 287	84.68 258	80.22 360	60.70 361	71.27 318	83.58 333	36.59 401	89.24 302	60.41 301	63.31 401	90.37 215

1314		76.53 256	75.30 263	80.21 262	83.93 307	62.32 272	84.66 259	88.81 214	60.23 365	70.16 330	84.07 321	55.30 242	90.73 278	67.37 241	83.21 230	87.59 309

MVS		78.19 222	76.99 230	81.78 220	85.66 263	66.99 170	84.66 259	90.47 150	55.08 402	72.02 311	85.27 292	63.83 147	94.11 131	66.10 252	89.80 124	84.24 372

tfpnnormal		74.39 285	73.16 291	78.08 303	86.10 256	58.05 321	84.65 261	87.53 247	70.32 226	71.22 320	85.63 283	54.97 243	89.86 289	43.03 410	75.02 341	86.32 337

TR-MVS		77.44 241	76.18 247	81.20 237	88.24 182	63.24 255	84.61 262	86.40 271	67.55 281	77.81 193	86.48 265	54.10 254	93.15 182	57.75 329	82.72 237	87.20 318

AllTest		70.96 326	68.09 341	79.58 276	85.15 279	63.62 243	84.58 263	79.83 363	62.31 348	60.32 405	86.73 249	32.02 411	88.96 310	50.28 376	71.57 371	86.15 341

FA-MVS(test-final)		80.96 149	79.91 158	84.10 134	88.30 181	65.01 213	84.55 264	90.01 168	73.25 169	79.61 158	87.57 228	58.35 216	94.72 109	71.29 202	86.25 180	92.56 135

EU-MVSNet		68.53 353	67.61 352	71.31 378	78.51 394	47.01 416	84.47 265	84.27 300	42.27 425	66.44 375	84.79 305	40.44 383	83.76 364	58.76 319	68.54 386	83.17 384

VNet		82.21 122	82.41 113	81.62 223	90.82 95	60.93 289	84.47 265	89.78 174	76.36 88	84.07 95	91.88 108	64.71 140	90.26 282	70.68 208	88.89 137	93.66 81

xiu_mvs_v2_base		81.69 133	81.05 134	83.60 161	89.15 148	68.03 141	84.46 267	90.02 167	70.67 216	81.30 137	86.53 264	63.17 154	94.19 128	75.60 161	88.54 145	88.57 288

VPNet		78.69 209	78.66 186	78.76 288	88.31 180	55.72 361	84.45 268	86.63 267	76.79 73	78.26 183	90.55 150	59.30 210	89.70 294	66.63 248	77.05 302	90.88 192

PVSNet_Blended		80.98 148	80.34 147	82.90 193	88.85 156	65.40 201	84.43 269	92.00 99	67.62 280	78.11 187	85.05 300	66.02 128	94.27 122	71.52 198	89.50 129	89.01 268

MVP-Stereo		76.12 265	74.46 274	81.13 240	85.37 273	69.79 90	84.42 270	87.95 236	65.03 314	67.46 357	85.33 291	53.28 264	91.73 241	58.01 327	83.27 229	81.85 398
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CDS-MVSNet		79.07 200	77.70 215	83.17 179	87.60 215	68.23 135	84.40 271	86.20 275	67.49 282	76.36 229	86.54 263	61.54 180	90.79 275	61.86 290	87.33 162	90.49 210
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
K. test v3		71.19 323	68.51 335	79.21 282	83.04 330	57.78 330	84.35 272	76.91 389	72.90 176	62.99 396	82.86 347	39.27 387	91.09 270	61.65 292	52.66 422	88.75 281

PS-MVSNAJ		81.69 133	81.02 135	83.70 159	89.51 129	68.21 136	84.28 273	90.09 166	70.79 213	81.26 138	85.62 284	63.15 155	94.29 120	75.62 160	88.87 138	88.59 287

patch_mono-2		83.65 94	84.54 81	80.99 243	90.06 115	65.83 190	84.21 274	88.74 220	71.60 196	85.01 71	92.44 97	74.51 25	83.50 368	82.15 92	92.15 82	93.64 87

test222					91.50 81	68.26 132	84.16 275	83.20 319	54.63 403	79.74 156	91.63 117	58.97 212			91.42 94	86.77 331

testdata1							84.14 276		75.71 98

c3_l		78.75 206	77.91 204	81.26 235	82.89 335	61.56 282	84.09 277	89.13 203	69.97 235	75.56 244	84.29 314	66.36 122	92.09 226	73.47 182	75.48 329	90.12 226

MVSTER		79.01 201	77.88 207	82.38 211	83.07 328	64.80 220	84.08 278	88.95 211	69.01 262	78.69 171	87.17 242	54.70 249	92.43 212	74.69 169	80.57 263	89.89 242

ab-mvs		79.51 185	78.97 182	81.14 239	88.46 174	60.91 290	83.84 279	89.24 197	70.36 223	79.03 165	88.87 192	63.23 153	90.21 284	65.12 260	82.57 239	92.28 149

reproduce_monomvs		75.40 278	74.38 275	78.46 298	83.92 308	57.80 329	83.78 280	86.94 261	73.47 162	72.25 308	84.47 308	38.74 391	89.27 301	75.32 165	70.53 376	88.31 293

PAPM		77.68 238	76.40 245	81.51 226	87.29 228	61.85 278	83.78 280	89.59 183	64.74 317	71.23 319	88.70 195	62.59 162	93.66 154	52.66 362	87.03 167	89.01 268

diffmvs		82.10 123	81.88 125	82.76 204	83.00 331	63.78 242	83.68 282	89.76 176	72.94 175	82.02 124	89.85 162	65.96 130	90.79 275	82.38 91	87.30 163	93.71 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
miper_ehance_all_eth		78.59 212	77.76 213	81.08 241	82.66 340	61.56 282	83.65 283	89.15 201	68.87 264	75.55 245	83.79 326	66.49 120	92.03 227	73.25 185	76.39 314	89.64 250

1112_ss		77.40 243	76.43 244	80.32 259	89.11 153	60.41 299	83.65 283	87.72 244	62.13 351	73.05 296	86.72 251	62.58 163	89.97 288	62.11 288	80.80 259	90.59 206

PCF-MVS	73.52 7	80.38 169	78.84 184	85.01 96	87.71 211	68.99 108	83.65 283	91.46 125	63.00 338	77.77 195	90.28 153	66.10 125	95.09 93	61.40 294	88.22 151	90.94 191
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
XVG-ACMP-BASELINE		76.11 266	74.27 277	81.62 223	83.20 324	64.67 222	83.60 286	89.75 177	69.75 242	71.85 312	87.09 244	32.78 410	92.11 225	69.99 216	80.43 265	88.09 298

tt0320		70.49 334	68.03 342	77.89 306	84.78 288	59.12 312	83.55 287	80.44 355	58.13 385	67.43 359	80.41 374	39.26 388	87.54 330	55.12 348	63.18 402	86.99 326

cl22		78.07 225	77.01 228	81.23 236	82.37 347	61.83 279	83.55 287	87.98 234	68.96 263	75.06 267	83.87 322	61.40 185	91.88 235	73.53 180	76.39 314	89.98 238

XVG-OURS-SEG-HR		80.81 153	79.76 161	83.96 152	85.60 266	68.78 113	83.54 289	90.50 149	70.66 219	76.71 219	91.66 114	60.69 198	91.26 262	76.94 144	81.58 249	91.83 162

IB-MVS	68.01 15	75.85 270	73.36 289	83.31 171	84.76 289	66.03 183	83.38 290	85.06 289	70.21 230	69.40 340	81.05 365	45.76 347	94.66 112	65.10 261	75.49 328	89.25 260
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
HY-MVS	69.67 12	77.95 229	77.15 226	80.36 257	87.57 219	60.21 302	83.37 291	87.78 242	66.11 299	75.37 253	87.06 246	63.27 151	90.48 281	61.38 295	82.43 240	90.40 214

tt0320-xc		70.11 338	67.45 355	78.07 304	85.33 274	59.51 310	83.28 292	78.96 373	58.77 379	67.10 363	80.28 376	36.73 400	87.42 331	56.83 340	59.77 411	87.29 316

test_vis1_n_1920		75.52 274	75.78 250	74.75 347	79.84 380	57.44 335	83.26 293	85.52 284	62.83 342	79.34 163	86.17 272	45.10 353	79.71 388	78.75 122	81.21 253	87.10 325

Anonymous20240521		68.80 349	67.22 358	73.55 357	74.33 409	54.11 377	83.18 294	85.61 283	58.15 384	61.68 400	80.94 368	30.71 416	81.27 382	57.00 337	73.34 359	85.28 357

eth_miper_zixun_eth		77.92 230	76.69 239	81.61 225	83.00 331	61.98 276	83.15 295	89.20 199	69.52 246	74.86 272	84.35 313	61.76 176	92.56 205	71.50 200	72.89 361	90.28 220

FE-MVS		77.78 233	75.68 252	84.08 139	88.09 191	66.00 185	83.13 296	87.79 241	68.42 273	78.01 190	85.23 294	45.50 351	95.12 87	59.11 314	85.83 189	91.11 182

cl____		77.72 235	76.76 236	80.58 253	82.49 344	60.48 297	83.09 297	87.87 238	69.22 253	74.38 281	85.22 295	62.10 172	91.53 251	71.09 203	75.41 333	89.73 249

DIV-MVS_self_test		77.72 235	76.76 236	80.58 253	82.48 345	60.48 297	83.09 297	87.86 239	69.22 253	74.38 281	85.24 293	62.10 172	91.53 251	71.09 203	75.40 334	89.74 248

thres200		75.55 273	74.47 273	78.82 287	87.78 208	57.85 327	83.07 299	83.51 311	72.44 182	75.84 240	84.42 309	52.08 277	91.75 239	47.41 394	83.64 222	86.86 329

testing3		68.56 352	67.67 351	71.22 379	87.33 225	42.87 429	83.06 300	71.54 409	70.36 223	69.08 344	84.38 311	30.33 417	85.69 348	37.50 422	75.45 332	85.09 363

XVG-OURS		80.41 168	79.23 176	83.97 151	85.64 264	69.02 107	83.03 301	90.39 152	71.09 208	77.63 197	91.49 123	54.62 251	91.35 259	75.71 158	83.47 226	91.54 169

miper_enhance_ethall		77.87 232	76.86 232	80.92 246	81.65 354	61.38 284	82.68 302	88.98 208	65.52 308	75.47 246	82.30 355	65.76 132	92.00 229	72.95 188	76.39 314	89.39 256

mvs_anonymous		79.42 190	79.11 179	80.34 258	84.45 297	57.97 324	82.59 303	87.62 245	67.40 284	76.17 236	88.56 202	68.47 99	89.59 295	70.65 209	86.05 184	93.47 95

baseline2		75.70 271	73.83 283	81.30 233	83.26 322	61.79 280	82.57 304	80.65 350	66.81 286	66.88 365	83.42 336	57.86 220	92.19 223	63.47 271	79.57 273	89.91 240

cascas		76.72 254	74.64 269	82.99 189	85.78 261	65.88 189	82.33 305	89.21 198	60.85 360	72.74 299	81.02 366	47.28 328	93.75 151	67.48 240	85.02 194	89.34 258

WB-MVSnew		71.96 320	71.65 307	72.89 364	84.67 294	51.88 393	82.29 306	77.57 381	62.31 348	73.67 289	83.00 343	53.49 262	81.10 383	45.75 403	82.13 243	85.70 351

RPSCF		73.23 305	71.46 309	78.54 294	82.50 343	59.85 304	82.18 307	82.84 328	58.96 377	71.15 321	89.41 182	45.48 352	84.77 359	58.82 318	71.83 369	91.02 188

thisisatest0515		77.33 244	75.38 260	83.18 178	85.27 276	63.80 241	82.11 308	83.27 315	65.06 313	75.91 238	83.84 324	49.54 310	94.27 122	67.24 243	86.19 181	91.48 173

pmmvs-eth3d		70.50 333	67.83 347	78.52 296	77.37 398	66.18 182	81.82 309	81.51 341	58.90 378	63.90 392	80.42 373	42.69 369	86.28 342	58.56 320	65.30 396	83.11 386

MS-PatchMatch		73.83 294	72.67 296	77.30 319	83.87 309	66.02 184	81.82 309	84.66 293	61.37 358	68.61 348	82.82 348	47.29 327	88.21 320	59.27 311	84.32 208	77.68 413

pmmvs5		71.55 321	70.20 326	75.61 332	77.83 395	56.39 350	81.74 311	80.89 346	57.76 388	67.46 357	84.49 307	49.26 316	85.32 354	57.08 335	75.29 337	85.11 362

Test_1112_low_res		76.40 262	75.44 257	79.27 280	89.28 143	58.09 320	81.69 312	87.07 258	59.53 372	72.48 304	86.67 256	61.30 187	89.33 299	60.81 300	80.15 268	90.41 213

IterMVS		74.29 286	72.94 294	78.35 299	81.53 358	63.49 249	81.58 313	82.49 330	68.06 277	69.99 333	83.69 330	51.66 287	85.54 350	65.85 255	71.64 370	86.01 345
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		75.43 276	73.87 282	80.11 264	82.69 339	64.85 219	81.57 314	83.47 312	69.16 256	70.49 324	84.15 320	51.95 280	88.15 321	69.23 223	72.14 367	87.34 314

test_vis1_n		69.85 342	69.21 331	71.77 372	72.66 423	55.27 368	81.48 315	76.21 393	52.03 410	75.30 259	83.20 340	28.97 418	76.22 408	74.60 170	78.41 288	83.81 378

pmmvs4		74.03 293	71.91 304	80.39 256	81.96 350	68.32 130	81.45 316	82.14 333	59.32 373	69.87 336	85.13 297	52.40 270	88.13 322	60.21 304	74.74 344	84.73 368

GA-MVS		76.87 251	75.17 265	81.97 218	82.75 337	62.58 268	81.44 317	86.35 273	72.16 187	74.74 273	82.89 346	46.20 342	92.02 228	68.85 229	81.09 254	91.30 178

UWE-MVS		72.13 318	71.49 308	74.03 353	86.66 244	47.70 412	81.40 318	76.89 390	63.60 333	75.59 243	84.22 318	39.94 385	85.62 349	48.98 384	86.13 183	88.77 280

test_fmvs1_n		70.86 328	70.24 325	72.73 366	72.51 424	55.28 367	81.27 319	79.71 365	51.49 413	78.73 170	84.87 302	27.54 420	77.02 400	76.06 154	79.97 271	85.88 349

testing91		76.54 255	75.66 254	79.18 283	88.43 176	55.89 358	81.08 320	83.00 323	73.76 152	75.34 254	84.29 314	46.20 342	90.07 286	64.33 266	84.50 201	91.58 168

testing222		74.04 291	72.66 297	78.19 301	87.89 200	55.36 365	81.06 321	79.20 371	71.30 203	74.65 276	83.57 334	39.11 390	88.67 315	51.43 370	85.75 190	90.53 208

test_fmvs1		70.93 327	70.52 320	72.16 370	73.71 413	55.05 369	80.82 322	78.77 374	51.21 414	78.58 175	84.41 310	31.20 415	76.94 401	75.88 157	80.12 270	84.47 370

CostFormer		75.24 280	73.90 281	79.27 280	82.65 341	58.27 319	80.80 323	82.73 329	61.57 355	75.33 258	83.13 341	55.52 240	91.07 271	64.98 262	78.34 289	88.45 290

testing99		76.09 267	75.12 266	79.00 284	88.16 185	55.50 364	80.79 324	81.40 343	73.30 167	75.17 262	84.27 317	44.48 357	90.02 287	64.28 267	84.22 210	91.48 173

MIMVSNet1		68.58 351	66.78 361	73.98 354	80.07 377	51.82 394	80.77 325	84.37 296	64.40 321	59.75 408	82.16 358	36.47 402	83.63 366	42.73 411	70.33 377	86.48 336

CL-MVSNet_self_test		72.37 314	71.46 309	75.09 341	79.49 387	53.53 381	80.76 326	85.01 291	69.12 257	70.51 323	82.05 359	57.92 219	84.13 362	52.27 364	66.00 394	87.60 307

testing11		75.14 281	74.01 278	78.53 295	88.16 185	56.38 351	80.74 327	80.42 356	70.67 216	72.69 302	83.72 329	43.61 364	89.86 289	62.29 284	83.76 216	89.36 257

MSDG		73.36 302	70.99 316	80.49 255	84.51 296	65.80 192	80.71 328	86.13 277	65.70 305	65.46 379	83.74 327	44.60 355	90.91 273	51.13 371	76.89 304	84.74 367

tpm2		73.26 304	71.46 309	78.63 289	83.34 320	56.71 345	80.65 329	80.40 357	56.63 396	73.55 290	82.02 360	51.80 284	91.24 263	56.35 344	78.42 287	87.95 299

XXY-MVS		75.41 277	75.56 255	74.96 342	83.59 315	57.82 328	80.59 330	83.87 306	66.54 296	74.93 271	88.31 208	63.24 152	80.09 387	62.16 286	76.85 306	86.97 327

test_cas_vis1_n_1920		73.76 295	73.74 284	73.81 356	75.90 402	59.77 305	80.51 331	82.40 331	58.30 383	81.62 131	85.69 280	44.35 359	76.41 406	76.29 151	78.61 282	85.23 358

EGC-MVSNET		52.07 398	47.05 402	67.14 398	83.51 317	60.71 293	80.50 332	67.75 420	0.07 448	0.43 449	75.85 410	24.26 426	81.54 380	28.82 431	62.25 403	59.16 431

SDMVSNet		80.38 169	80.18 151	80.99 243	89.03 154	64.94 216	80.45 333	89.40 188	75.19 113	76.61 223	89.98 159	60.61 202	87.69 328	76.83 148	83.55 223	90.33 217

HyFIR lowres test		77.53 240	75.40 259	83.94 153	89.59 125	66.62 175	80.36 334	88.64 223	56.29 398	76.45 226	85.17 296	57.64 222	93.28 170	61.34 296	83.10 232	91.91 161

D2MVS		74.82 283	73.21 290	79.64 275	79.81 381	62.56 269	80.34 335	87.35 251	64.37 322	68.86 345	82.66 350	46.37 338	90.10 285	67.91 236	81.24 252	86.25 338

testing3-2		75.12 282	75.19 264	74.91 343	90.40 104	45.09 424	80.29 336	78.42 376	78.37 38	76.54 225	87.75 222	44.36 358	87.28 333	57.04 336	83.49 225	92.37 144

TinyColmap		67.30 361	64.81 367	74.76 346	81.92 352	56.68 346	80.29 336	81.49 342	60.33 363	56.27 419	83.22 338	24.77 425	87.66 329	45.52 404	69.47 380	79.95 408

LCM-MVSNet-Re		77.05 247	76.94 231	77.36 317	87.20 229	51.60 396	80.06 338	80.46 354	75.20 112	67.69 354	86.72 251	62.48 164	88.98 308	63.44 272	89.25 132	91.51 170

test_fmvs2		68.35 355	67.48 354	70.98 381	69.50 427	51.95 391	80.05 339	76.38 392	49.33 416	74.65 276	84.38 311	23.30 429	75.40 417	74.51 171	75.17 340	85.60 352

FMVSNet5		69.50 343	67.96 343	74.15 352	82.97 334	55.35 366	80.01 340	82.12 334	62.56 346	63.02 394	81.53 362	36.92 399	81.92 378	48.42 386	74.06 349	85.17 361

SCA		74.22 288	72.33 301	79.91 267	84.05 305	62.17 274	79.96 341	79.29 370	66.30 298	72.38 306	80.13 378	51.95 280	88.60 316	59.25 312	77.67 297	88.96 272

tpmrst		72.39 312	72.13 303	73.18 363	80.54 371	49.91 407	79.91 342	79.08 372	63.11 336	71.69 314	79.95 380	55.32 241	82.77 373	65.66 257	73.89 351	86.87 328

PatchmatchNet		73.12 306	71.33 312	78.49 297	83.18 325	60.85 291	79.63 343	78.57 375	64.13 324	71.73 313	79.81 383	51.20 291	85.97 345	57.40 332	76.36 319	88.66 284
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PatchMatch-RL		72.38 313	70.90 317	76.80 324	88.60 169	67.38 160	79.53 344	76.17 394	62.75 344	69.36 341	82.00 361	45.51 350	84.89 358	53.62 357	80.58 262	78.12 412

CMPMVS	51.72 21	70.19 337	68.16 339	76.28 326	73.15 420	57.55 333	79.47 345	83.92 304	48.02 418	56.48 418	84.81 304	43.13 366	86.42 341	62.67 280	81.81 248	84.89 365
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ETVMVS		72.25 316	71.05 315	75.84 329	87.77 209	51.91 392	79.39 346	74.98 397	69.26 251	73.71 287	82.95 344	40.82 382	86.14 343	46.17 400	84.43 206	89.47 254

GG-mvs-BLEND				75.38 338	81.59 356	55.80 360	79.32 347	69.63 414		67.19 361	73.67 415	43.24 365	88.90 312	50.41 373	84.50 201	81.45 400

LTVRE_ROB	69.57 13	76.25 264	74.54 272	81.41 229	88.60 169	64.38 230	79.24 348	89.12 204	70.76 215	69.79 338	87.86 221	49.09 318	93.20 178	56.21 345	80.16 267	86.65 334
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
tpm		72.37 314	71.71 306	74.35 350	82.19 348	52.00 390	79.22 349	77.29 386	64.56 319	72.95 298	83.68 331	51.35 288	83.26 371	58.33 324	75.80 323	87.81 303

mvs5depth		69.45 344	67.45 355	75.46 337	73.93 411	55.83 359	79.19 350	83.23 316	66.89 285	71.63 315	83.32 337	33.69 409	85.09 355	59.81 307	55.34 419	85.46 354

ppachtmachnet_test		70.04 339	67.34 357	78.14 302	79.80 382	61.13 285	79.19 350	80.59 351	59.16 375	65.27 381	79.29 386	46.75 335	87.29 332	49.33 382	66.72 389	86.00 347

USDC		70.33 335	68.37 336	76.21 327	80.60 370	56.23 354	79.19 350	86.49 269	60.89 359	61.29 401	85.47 288	31.78 413	89.47 298	53.37 359	76.21 320	82.94 390

sd_testset		77.70 237	77.40 221	78.60 291	89.03 154	60.02 303	79.00 353	85.83 281	75.19 113	76.61 223	89.98 159	54.81 244	85.46 352	62.63 281	83.55 223	90.33 217

PM-MVS		66.41 367	64.14 370	73.20 362	73.92 412	56.45 348	78.97 354	64.96 428	63.88 332	64.72 385	80.24 377	19.84 433	83.44 369	66.24 249	64.52 398	79.71 409

tpmvs		71.09 325	69.29 330	76.49 325	82.04 349	56.04 356	78.92 355	81.37 344	64.05 328	67.18 362	78.28 395	49.74 309	89.77 291	49.67 381	72.37 363	83.67 380

test_post1							78.90 356				5.43 447	48.81 323	85.44 353	59.25 312

mamv4		76.81 252	78.23 199	72.54 368	86.12 254	65.75 195	78.76 357	82.07 335	64.12 325	72.97 297	91.02 141	67.97 104	68.08 433	83.04 81	78.02 291	83.80 379

CHOSEN 1792x2688		77.63 239	75.69 251	83.44 166	89.98 117	68.58 124	78.70 358	87.50 248	56.38 397	75.80 241	86.84 247	58.67 213	91.40 258	61.58 293	85.75 190	90.34 216

Syy-MVS		68.05 356	67.85 345	68.67 392	84.68 291	40.97 435	78.62 359	73.08 406	66.65 293	66.74 368	79.46 384	52.11 276	82.30 375	32.89 427	76.38 317	82.75 391

myMVS_eth3d		67.02 362	66.29 363	69.21 387	84.68 291	42.58 430	78.62 359	73.08 406	66.65 293	66.74 368	79.46 384	31.53 414	82.30 375	39.43 419	76.38 317	82.75 391

WBMVS		73.43 299	72.81 295	75.28 339	87.91 199	50.99 402	78.59 361	81.31 345	65.51 310	74.47 279	84.83 303	46.39 336	86.68 337	58.41 322	77.86 292	88.17 297

test-LLR		72.94 310	72.43 299	74.48 348	81.35 362	58.04 322	78.38 362	77.46 382	66.66 290	69.95 334	79.00 389	48.06 324	79.24 389	66.13 250	84.83 196	86.15 341

TESTMET0.1,1		69.89 341	69.00 333	72.55 367	79.27 390	56.85 341	78.38 362	74.71 401	57.64 389	68.09 351	77.19 402	37.75 397	76.70 402	63.92 269	84.09 211	84.10 375

test-mter		71.41 322	70.39 324	74.48 348	81.35 362	58.04 322	78.38 362	77.46 382	60.32 364	69.95 334	79.00 389	36.08 404	79.24 389	66.13 250	84.83 196	86.15 341

UBG		73.08 307	72.27 302	75.51 335	88.02 194	51.29 400	78.35 365	77.38 385	65.52 308	73.87 286	82.36 353	45.55 349	86.48 340	55.02 349	84.39 207	88.75 281

Anonymous20231206		68.60 350	67.80 348	71.02 380	80.23 375	50.75 404	78.30 366	80.47 353	56.79 395	66.11 377	82.63 351	46.35 339	78.95 391	43.62 409	75.70 324	83.36 383

tpm cat1		70.57 331	68.31 337	77.35 318	82.41 346	57.95 325	78.08 367	80.22 360	52.04 409	68.54 349	77.66 400	52.00 279	87.84 326	51.77 365	72.07 368	86.25 338

myMVS_eth3d28		73.62 296	73.53 286	73.90 355	88.20 183	47.41 414	78.06 368	79.37 368	74.29 139	73.98 284	84.29 314	44.67 354	83.54 367	51.47 368	87.39 161	90.74 199

our_test_3		69.14 346	67.00 359	75.57 333	79.80 382	58.80 313	77.96 369	77.81 379	59.55 371	62.90 397	78.25 396	47.43 326	83.97 363	51.71 366	67.58 388	83.93 377

KD-MVS_self_test		68.81 348	67.59 353	72.46 369	74.29 410	45.45 419	77.93 370	87.00 259	63.12 335	63.99 391	78.99 391	42.32 371	84.77 359	56.55 343	64.09 399	87.16 321

WTY-MVS		75.65 272	75.68 252	75.57 333	86.40 248	56.82 342	77.92 371	82.40 331	65.10 312	76.18 234	87.72 223	63.13 158	80.90 384	60.31 303	81.96 245	89.00 270

UWE-MVS-28		65.32 372	64.93 366	66.49 400	78.70 392	38.55 437	77.86 372	64.39 429	62.00 353	64.13 389	83.60 332	41.44 377	76.00 410	31.39 429	80.89 256	84.92 364

test20.03		67.45 359	66.95 360	68.94 388	75.48 406	44.84 425	77.50 373	77.67 380	66.66 290	63.01 395	83.80 325	47.02 330	78.40 393	42.53 413	68.86 385	83.58 381

EPMVS		69.02 347	68.16 339	71.59 373	79.61 385	49.80 409	77.40 374	66.93 422	62.82 343	70.01 331	79.05 387	45.79 346	77.86 397	56.58 342	75.26 338	87.13 322

test_fmvs3		63.36 379	61.82 382	67.98 396	62.51 436	46.96 417	77.37 375	74.03 403	45.24 421	67.50 356	78.79 392	12.16 441	72.98 425	72.77 191	66.02 393	83.99 376

gg-mvs-nofinetune		69.95 340	67.96 343	75.94 328	83.07 328	54.51 375	77.23 376	70.29 412	63.11 336	70.32 326	62.33 426	43.62 363	88.69 314	53.88 356	87.76 156	84.62 369

MDTV_nov1_ep13			69.97 327		83.18 325	53.48 382	77.10 377	80.18 362	60.45 362	69.33 342	80.44 372	48.89 322	86.90 335	51.60 367	78.51 285

LF4IMVS		64.02 377	62.19 381	69.50 386	70.90 425	53.29 386	76.13 378	77.18 387	52.65 408	58.59 410	80.98 367	23.55 428	76.52 404	53.06 361	66.66 390	78.68 411

sss		73.60 297	73.64 285	73.51 358	82.80 336	55.01 370	76.12 379	81.69 339	62.47 347	74.68 275	85.85 278	57.32 226	78.11 395	60.86 299	80.93 255	87.39 312

testgi		66.67 365	66.53 362	67.08 399	75.62 405	41.69 434	75.93 380	76.50 391	66.11 299	65.20 384	86.59 259	35.72 405	74.71 419	43.71 408	73.38 358	84.84 366

CR-MVSNet		73.37 300	71.27 313	79.67 274	81.32 364	65.19 207	75.92 381	80.30 358	59.92 368	72.73 300	81.19 363	52.50 268	86.69 336	59.84 306	77.71 294	87.11 323

RPMNet		73.51 298	70.49 321	82.58 208	81.32 364	65.19 207	75.92 381	92.27 85	57.60 390	72.73 300	76.45 405	52.30 271	95.43 72	48.14 391	77.71 294	87.11 323

MIMVSNet		70.69 330	69.30 329	74.88 344	84.52 295	56.35 353	75.87 383	79.42 367	64.59 318	67.76 352	82.41 352	41.10 379	81.54 380	46.64 398	81.34 250	86.75 332

test0.0.03 1		68.00 357	67.69 350	68.90 389	77.55 396	47.43 413	75.70 384	72.95 408	66.66 290	66.56 370	82.29 356	48.06 324	75.87 412	44.97 407	74.51 346	83.41 382

dmvs_re		71.14 324	70.58 319	72.80 365	81.96 350	59.68 306	75.60 385	79.34 369	68.55 269	69.27 343	80.72 371	49.42 312	76.54 403	52.56 363	77.79 293	82.19 396

dmvs_testset		62.63 380	64.11 371	58.19 410	78.55 393	24.76 448	75.28 386	65.94 425	67.91 278	60.34 404	76.01 407	53.56 260	73.94 423	31.79 428	67.65 387	75.88 417

PMMVS		69.34 345	68.67 334	71.35 377	75.67 404	62.03 275	75.17 387	73.46 404	50.00 415	68.68 346	79.05 387	52.07 278	78.13 394	61.16 297	82.77 235	73.90 419

UnsupCasMVSNet_eth		67.33 360	65.99 364	71.37 375	73.48 416	51.47 398	75.16 388	85.19 287	65.20 311	60.78 403	80.93 370	42.35 370	77.20 399	57.12 334	53.69 421	85.44 355

MDTV_nov1_ep13_2view						37.79 438	75.16 388		55.10 401	66.53 371		49.34 314		53.98 355		87.94 300

pmmvs3		57.79 387	54.26 392	68.37 393	64.02 435	56.72 344	75.12 390	65.17 426	40.20 427	52.93 423	69.86 423	20.36 432	75.48 415	45.45 405	55.25 420	72.90 421

dp		66.80 363	65.43 365	70.90 382	79.74 384	48.82 411	75.12 390	74.77 399	59.61 370	64.08 390	77.23 401	42.89 367	80.72 385	48.86 385	66.58 391	83.16 385

Patchmtry		70.74 329	69.16 332	75.49 336	80.72 368	54.07 378	74.94 392	80.30 358	58.34 382	70.01 331	81.19 363	52.50 268	86.54 338	53.37 359	71.09 374	85.87 350

ttmdpeth		59.91 385	57.10 389	68.34 394	67.13 431	46.65 418	74.64 393	67.41 421	48.30 417	62.52 399	85.04 301	20.40 431	75.93 411	42.55 412	45.90 432	82.44 393

SSC-MVS3.2		73.35 303	73.39 287	73.23 359	85.30 275	49.01 410	74.58 394	81.57 340	75.21 111	73.68 288	85.58 285	52.53 266	82.05 377	54.33 354	77.69 296	88.63 286

PVSNet	64.34 18	72.08 319	70.87 318	75.69 331	86.21 251	56.44 349	74.37 395	80.73 349	62.06 352	70.17 329	82.23 357	42.86 368	83.31 370	54.77 351	84.45 205	87.32 315

WB-MVS		54.94 390	54.72 391	55.60 416	73.50 415	20.90 450	74.27 396	61.19 433	59.16 375	50.61 425	74.15 413	47.19 329	75.78 413	17.31 441	35.07 435	70.12 423

MDA-MVSNet-bldmvs		66.68 364	63.66 374	75.75 330	79.28 389	60.56 296	73.92 397	78.35 377	64.43 320	50.13 427	79.87 382	44.02 361	83.67 365	46.10 401	56.86 413	83.03 388

SSC-MVS		53.88 393	53.59 393	54.75 418	72.87 421	19.59 451	73.84 398	60.53 435	57.58 391	49.18 429	73.45 416	46.34 340	75.47 416	16.20 444	32.28 437	69.20 424

UnsupCasMVSNet_bld		63.70 378	61.53 384	70.21 384	73.69 414	51.39 399	72.82 399	81.89 336	55.63 400	57.81 414	71.80 419	38.67 392	78.61 392	49.26 383	52.21 424	80.63 405

PatchT		68.46 354	67.85 345	70.29 383	80.70 369	43.93 427	72.47 400	74.88 398	60.15 366	70.55 322	76.57 404	49.94 306	81.59 379	50.58 372	74.83 343	85.34 356

miper_lstm_enhance		74.11 290	73.11 292	77.13 321	80.11 376	59.62 307	72.23 401	86.92 263	66.76 288	70.40 325	82.92 345	56.93 231	82.92 372	69.06 226	72.63 362	88.87 275

MVS-HIRNet		59.14 386	57.67 388	63.57 404	81.65 354	43.50 428	71.73 402	65.06 427	39.59 429	51.43 424	57.73 432	38.34 394	82.58 374	39.53 417	73.95 350	64.62 428

MVStest1		56.63 389	52.76 395	68.25 395	61.67 437	53.25 387	71.67 403	68.90 419	38.59 430	50.59 426	83.05 342	25.08 423	70.66 427	36.76 423	38.56 433	80.83 404

APD_test1		53.31 395	49.93 400	63.42 405	65.68 432	50.13 406	71.59 404	66.90 423	34.43 435	40.58 434	71.56 420	8.65 446	76.27 407	34.64 426	55.36 418	63.86 429

Patchmatch-RL test		70.24 336	67.78 349	77.61 313	77.43 397	59.57 309	71.16 405	70.33 411	62.94 340	68.65 347	72.77 417	50.62 297	85.49 351	69.58 221	66.58 391	87.77 304

test123		6.12 417	8.11 420	0.14 431	0.06 455	0.09 456	71.05 406	0.03 456	0.04 450	0.25 451	1.30 450	0.05 454	0.03 451	0.21 450	0.01 449	0.29 446

ANet_high		50.57 400	46.10 404	63.99 403	48.67 448	39.13 436	70.99 407	80.85 347	61.39 357	31.18 437	57.70 433	17.02 436	73.65 424	31.22 430	15.89 445	79.18 410

KD-MVS_2432*1600		66.22 369	63.89 372	73.21 360	75.47 407	53.42 383	70.76 408	84.35 297	64.10 326	66.52 372	78.52 393	34.55 407	84.98 356	50.40 374	50.33 426	81.23 401

miper_refine_blended		66.22 369	63.89 372	73.21 360	75.47 407	53.42 383	70.76 408	84.35 297	64.10 326	66.52 372	78.52 393	34.55 407	84.98 356	50.40 374	50.33 426	81.23 401

test_vis1_rt		60.28 384	58.42 387	65.84 401	67.25 430	55.60 363	70.44 410	60.94 434	44.33 423	59.00 409	66.64 424	24.91 424	68.67 431	62.80 276	69.48 379	73.25 420

testmvs		6.04 418	8.02 421	0.10 432	0.08 454	0.03 457	69.74 411	0.04 455	0.05 449	0.31 450	1.68 449	0.02 455	0.04 450	0.24 449	0.02 448	0.25 447

N_pmnet		52.79 396	53.26 394	51.40 420	78.99 391	7.68 454	69.52 412	3.89 453	51.63 412	57.01 416	74.98 412	40.83 381	65.96 435	37.78 421	64.67 397	80.56 407

FPMVS		53.68 394	51.64 396	59.81 409	65.08 433	51.03 401	69.48 413	69.58 415	41.46 426	40.67 433	72.32 418	16.46 437	70.00 430	24.24 437	65.42 395	58.40 433

DSMNet-mixed		57.77 388	56.90 390	60.38 408	67.70 429	35.61 439	69.18 414	53.97 440	32.30 438	57.49 415	79.88 381	40.39 384	68.57 432	38.78 420	72.37 363	76.97 414

new-patchmatchnet		61.73 382	61.73 383	61.70 406	72.74 422	24.50 449	69.16 415	78.03 378	61.40 356	56.72 417	75.53 411	38.42 393	76.48 405	45.95 402	57.67 412	84.13 374

YYNet1		65.03 373	62.91 378	71.38 374	75.85 403	56.60 347	69.12 416	74.66 402	57.28 393	54.12 421	77.87 398	45.85 345	74.48 420	49.95 379	61.52 406	83.05 387

MDA-MVSNet_test_wron		65.03 373	62.92 377	71.37 375	75.93 401	56.73 343	69.09 417	74.73 400	57.28 393	54.03 422	77.89 397	45.88 344	74.39 421	49.89 380	61.55 405	82.99 389

PVSNet_0	57.27 20	61.67 383	59.27 386	68.85 390	79.61 385	57.44 335	68.01 418	73.44 405	55.93 399	58.54 411	70.41 422	44.58 356	77.55 398	47.01 395	35.91 434	71.55 422

dongtai		45.42 404	45.38 405	45.55 422	73.36 418	26.85 446	67.72 419	34.19 448	54.15 404	49.65 428	56.41 435	25.43 422	62.94 438	19.45 439	28.09 439	46.86 438

ADS-MVSNet2		66.20 371	63.33 375	74.82 345	79.92 378	58.75 314	67.55 420	75.19 396	53.37 406	65.25 382	75.86 408	42.32 371	80.53 386	41.57 414	68.91 383	85.18 359

ADS-MVSNet		64.36 376	62.88 379	68.78 391	79.92 378	47.17 415	67.55 420	71.18 410	53.37 406	65.25 382	75.86 408	42.32 371	73.99 422	41.57 414	68.91 383	85.18 359

mvsany_test1		62.30 381	61.26 385	65.41 402	69.52 426	54.86 371	66.86 422	49.78 442	46.65 419	68.50 350	83.21 339	49.15 317	66.28 434	56.93 338	60.77 407	75.11 418

LCM-MVSNet		54.25 391	49.68 401	67.97 397	53.73 445	45.28 422	66.85 423	80.78 348	35.96 434	39.45 435	62.23 428	8.70 445	78.06 396	48.24 390	51.20 425	80.57 406

test_vis3_rt		49.26 401	47.02 403	56.00 413	54.30 442	45.27 423	66.76 424	48.08 443	36.83 432	44.38 431	53.20 436	7.17 448	64.07 436	56.77 341	55.66 416	58.65 432

testf1		45.72 402	41.96 406	57.00 411	56.90 439	45.32 420	66.14 425	59.26 436	26.19 439	30.89 438	60.96 430	4.14 449	70.64 428	26.39 435	46.73 430	55.04 434

APD_test2		45.72 402	41.96 406	57.00 411	56.90 439	45.32 420	66.14 425	59.26 436	26.19 439	30.89 438	60.96 430	4.14 449	70.64 428	26.39 435	46.73 430	55.04 434

kuosan		39.70 408	40.40 409	37.58 425	64.52 434	26.98 444	65.62 427	33.02 449	46.12 420	42.79 432	48.99 438	24.10 427	46.56 446	12.16 447	26.30 440	39.20 439

JIA-IIPM		66.32 368	62.82 380	76.82 323	77.09 399	61.72 281	65.34 428	75.38 395	58.04 387	64.51 386	62.32 427	42.05 375	86.51 339	51.45 369	69.22 382	82.21 395

PMVS	37.38 22	44.16 406	40.28 410	55.82 415	40.82 450	42.54 432	65.12 429	63.99 430	34.43 435	24.48 441	57.12 434	3.92 451	76.17 409	17.10 442	55.52 417	48.75 436
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		50.91 399	50.29 399	52.78 419	68.58 428	34.94 441	63.71 430	56.63 439	39.73 428	44.95 430	65.47 425	21.93 430	58.48 439	34.98 425	56.62 414	64.92 427

mvsany_test3		53.99 392	51.45 397	61.61 407	55.51 441	44.74 426	63.52 431	45.41 446	43.69 424	58.11 413	76.45 405	17.99 434	63.76 437	54.77 351	47.59 428	76.34 416

Patchmatch-test		64.82 375	63.24 376	69.57 385	79.42 388	49.82 408	63.49 432	69.05 417	51.98 411	59.95 407	80.13 378	50.91 293	70.98 426	40.66 416	73.57 354	87.90 301

ambc				75.24 340	73.16 419	50.51 405	63.05 433	87.47 249		64.28 387	77.81 399	17.80 435	89.73 293	57.88 328	60.64 408	85.49 353

test_f		52.09 397	50.82 398	55.90 414	53.82 444	42.31 433	59.42 434	58.31 438	36.45 433	56.12 420	70.96 421	12.18 440	57.79 440	53.51 358	56.57 415	67.60 425

CHOSEN 280x420		66.51 366	64.71 368	71.90 371	81.45 359	63.52 248	57.98 435	68.95 418	53.57 405	62.59 398	76.70 403	46.22 341	75.29 418	55.25 347	79.68 272	76.88 415

E-PMN		31.77 409	30.64 412	35.15 426	52.87 446	27.67 443	57.09 436	47.86 444	24.64 441	16.40 446	33.05 442	11.23 442	54.90 442	14.46 445	18.15 443	22.87 442

EMVS		30.81 411	29.65 413	34.27 427	50.96 447	25.95 447	56.58 437	46.80 445	24.01 442	15.53 447	30.68 443	12.47 439	54.43 443	12.81 446	17.05 444	22.43 443

PMMVS2		40.82 407	38.86 411	46.69 421	53.84 443	16.45 452	48.61 438	49.92 441	37.49 431	31.67 436	60.97 429	8.14 447	56.42 441	28.42 432	30.72 438	67.19 426

wuyk23d		16.82 415	15.94 418	19.46 429	58.74 438	31.45 442	39.22 439	3.74 454	6.84 445	6.04 448	2.70 448	1.27 453	24.29 448	10.54 448	14.40 447	2.63 445

tmp_tt		18.61 414	21.40 417	10.23 430	4.82 453	10.11 453	34.70 440	30.74 451	1.48 447	23.91 443	26.07 444	28.42 419	13.41 449	27.12 433	15.35 446	7.17 444

Gipuma		45.18 405	41.86 408	55.16 417	77.03 400	51.52 397	32.50 441	80.52 352	32.46 437	27.12 440	35.02 441	9.52 444	75.50 414	22.31 438	60.21 410	38.45 440
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	26.22 23	30.37 412	25.89 416	43.81 423	44.55 449	35.46 440	28.87 442	39.07 447	18.20 443	18.58 445	40.18 440	2.68 452	47.37 445	17.07 443	23.78 442	48.60 437
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		31.52 410	29.28 414	38.23 424	27.03 452	6.50 455	20.94 443	62.21 432	4.05 446	22.35 444	52.50 437	13.33 438	47.58 444	27.04 434	34.04 436	60.62 430

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		19.96 413	26.61 415	0.00 433	0.00 456	0.00 458	0.00 444	89.26 196	0.00 451	0.00 452	88.61 199	61.62 179	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		5.26 419	7.02 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	63.15 155	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		7.23 416	9.64 419	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	86.72 251	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						42.58 430								39.46 418

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 12	96.44 9	94.41 40

PC_three_1452									68.21 275	92.02 12	94.00 55	82.09 5	95.98 57	84.58 63	96.68 2	94.95 11

No_MVS				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 12	96.44 9	94.41 40

test_one_0601					95.07 7	71.46 58		94.14 6	78.27 39	92.05 11	95.74 6	80.83 11

eth-test2					0.00 456

eth-test					0.00 456

ZD-MVS					94.38 25	72.22 45		92.67 68	70.98 211	87.75 43	94.07 50	74.01 32	96.70 27	84.66 62	94.84 44

IU-MVS					95.30 2	71.25 60		92.95 56	66.81 286	92.39 6				88.94 24	96.63 4	94.85 20

test_241102_TWO								94.06 11	77.24 58	92.78 4	95.72 8	81.26 8	97.44 7	89.07 21	96.58 6	94.26 50

test_241102_ONE					95.30 2	70.98 67		94.06 11	77.17 61	93.10 1	95.39 15	82.99 1	97.27 12

test_0728_THIRD									78.38 36	92.12 9	95.78 4	81.46 7	97.40 9	89.42 16	96.57 7	94.67 28

GSMVS																88.96 272

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 289				88.96 272

sam_mvs												50.01 304

MTGPA								92.02 97

test_post											5.46 446	50.36 301	84.24 361

patchmatchnet-post											74.00 414	51.12 292	88.60 316

gm-plane-assit					81.40 360	53.83 380			62.72 345		80.94 368		92.39 214	63.40 273

test9_res														84.90 56	95.70 26	92.87 125

agg_prior2														82.91 83	95.45 29	92.70 129

agg_prior					92.85 63	71.94 51		91.78 112		84.41 87			94.93 96

TestCases				79.58 276	85.15 279	63.62 243		79.83 363	62.31 348	60.32 405	86.73 249	32.02 411	88.96 310	50.28 376	71.57 371	86.15 341

test_prior				86.33 59	92.61 69	69.59 93		92.97 55					95.48 69			93.91 65

新几何1				83.42 167	93.13 55	70.71 75		85.48 285	57.43 392	81.80 128	91.98 105	63.28 150	92.27 220	64.60 265	92.99 71	87.27 317

旧先验1					91.96 75	65.79 193		86.37 272			93.08 84	69.31 87			92.74 75	88.74 283

原ACMM1				84.35 120	93.01 61	68.79 112		92.44 78	63.96 331	81.09 139	91.57 120	66.06 127	95.45 70	67.19 244	94.82 46	88.81 278

testdata2													91.01 272	62.37 283

segment_acmp												73.08 39

testdata				79.97 266	90.90 93	64.21 232		84.71 292	59.27 374	85.40 67	92.91 86	62.02 174	89.08 306	68.95 227	91.37 96	86.63 335

test12				86.80 53	92.63 68	70.70 76		91.79 111		82.71 117		71.67 57	96.16 48		94.50 52	93.54 93

plane_prior7					90.08 111	68.51 126

plane_prior6					89.84 120	68.70 120						60.42 205

plane_prior5								92.44 78					95.38 77	78.71 123	86.32 178	91.33 176

plane_prior4											91.00 142

plane_prior3						68.60 123			78.44 34	78.92 168

plane_prior1					89.90 119

n2								0.00 457

nn								0.00 457

door-mid								69.98 413

lessismore_v0				78.97 285	81.01 367	57.15 338		65.99 424		61.16 402	82.82 348	39.12 389	91.34 260	59.67 308	46.92 429	88.43 291

LGP-MVS_train				84.50 113	89.23 145	68.76 114		91.94 103	75.37 107	76.64 221	91.51 121	54.29 252	94.91 97	78.44 125	83.78 214	89.83 244

test11								92.23 88

door								69.44 416

HQP5-MVS						66.98 171

BP-MVS														77.47 137

HQP4-MVS										77.24 205			95.11 89			91.03 186

HQP3-MVS								92.19 92							85.99 186

HQP2-MVS												60.17 208

NP-MVS					89.62 124	68.32 130					90.24 155

ACMMP++_ref															81.95 246

ACMMP++															81.25 251

Test By Simon												64.33 142

ITE_SJBPF				78.22 300	81.77 353	60.57 295		83.30 314	69.25 252	67.54 355	87.20 240	36.33 403	87.28 333	54.34 353	74.62 345	86.80 330

DeepMVS_CX				27.40 428	40.17 451	26.90 445		24.59 452	17.44 444	23.95 442	48.61 439	9.77 443	26.48 447	18.06 440	24.47 441	28.83 441

High-resolution multi-view benchmark