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 57	95.06 1	94.23 3	78.38 33	92.78 4	95.74 6	82.45 3	97.49 4	89.42 9	96.68 2	94.95 10

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 115	91.30 15

CP-MVS		87.11 30	86.92 32	87.68 34	94.20 34	73.86 7	93.98 3	92.82 59	76.62 71	83.68 88	94.46 25	67.93 97	95.95 54	84.20 56	94.39 53	93.23 92

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 91	91.06 16	96.03 1	76.84 14	97.03 17	89.09 11	95.65 27	94.47 34
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 69	72.96 25	93.73 5	93.67 20	80.19 12	88.10 25	94.80 17	73.76 33	97.11 15	87.51 31	95.82 21	94.90 13
Skip Steuart: Steuart Systems R&D Blog.
test0726					95.27 5	71.25 57	93.60 6	94.11 6	77.33 48	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 63	93.57 7	94.06 10	77.24 50	93.10 1	95.72 8	82.99 1	97.44 6	89.07 14	96.63 4	94.88 14

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 44	82.45 3	96.87 20	83.77 59	96.48 8	94.88 14

DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 57	93.49 9	92.73 60	77.33 48	92.12 9	95.78 4	80.98 9	97.40 8	89.08 12	96.41 12	93.33 89
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 56	93.49 9	94.23 3					97.49 4	89.08 12	96.41 12	94.21 47

3Dnovator+	77.84 4	85.48 56	84.47 74	88.51 7	91.08 82	73.49 16	93.18 11	93.78 18	80.79 8	76.66 198	93.37 62	60.40 195	96.75 26	77.20 122	93.73 65	95.29 5

HFP-MVS		87.58 22	87.47 24	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 65	84.91 61	94.44 28	70.78 63	96.61 32	84.53 50	94.89 41	93.66 70

ACMMPR		87.44 23	87.23 27	88.08 14	94.64 13	73.59 12	93.04 12	93.20 34	76.78 65	84.66 68	94.52 21	68.81 90	96.65 30	84.53 50	94.90 40	94.00 55

ZNCC-MVS		87.94 19	87.85 20	88.20 12	94.39 24	73.33 19	93.03 14	93.81 17	76.81 63	85.24 55	94.32 31	71.76 51	96.93 19	85.53 39	95.79 22	94.32 43

region2R		87.42 25	87.20 28	88.09 13	94.63 14	73.55 13	93.03 14	93.12 37	76.73 68	84.45 74	94.52 21	69.09 82	96.70 27	84.37 52	94.83 44	94.03 54

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 16	94.11 6	80.27 10	91.35 14	94.16 37	78.35 13	96.77 24	89.59 8	94.22 60	94.67 25
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 35	86.95 31	85.90 64	90.76 93	67.57 141	92.83 17	93.30 32	79.67 17	84.57 72	92.27 86	71.47 56	95.02 90	84.24 55	93.46 66	95.13 6

XVS		87.18 29	86.91 33	88.00 17	94.42 20	73.33 19	92.78 18	92.99 46	79.14 21	83.67 89	94.17 36	67.45 102	96.60 33	83.06 64	94.50 50	94.07 52

X-MVStestdata		80.37 150	77.83 186	88.00 17	94.42 20	73.33 19	92.78 18	92.99 46	79.14 21	83.67 89	12.47 408	67.45 102	96.60 33	83.06 64	94.50 50	94.07 52

mPP-MVS		86.67 37	86.32 39	87.72 30	94.41 22	73.55 13	92.74 20	92.22 83	76.87 62	82.81 102	94.25 34	66.44 112	96.24 41	82.88 69	94.28 58	93.38 86

ACMMP		85.89 49	85.39 57	87.38 39	93.59 45	72.63 33	92.74 20	93.18 36	76.78 65	80.73 126	93.82 53	64.33 132	96.29 39	82.67 75	90.69 98	93.23 92
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 22	92.65 65	77.57 41	83.84 86	94.40 30	72.24 45	96.28 40	85.65 38	95.30 35	93.62 77
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 92	73.65 10	92.66 23	91.17 122	86.57 1	87.39 37	94.97 16	71.70 53	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 61	71.95 50	92.40 24	94.74 2	75.71 89	89.16 19	95.10 14	75.65 21	96.19 43	87.07 34	96.01 17	94.79 21

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 109	92.29 7	95.97 2	74.28 29	97.24 12	88.58 21	96.91 1	94.87 16
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 25	87.26 25	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 61	84.68 65	93.99 48	70.67 65	96.82 22	84.18 57	95.01 37	93.90 60

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 27	92.85 55	80.26 11	87.78 30	94.27 32	75.89 19	96.81 23	87.45 32	96.44 9	93.05 101

SR-MVS		86.73 34	86.67 35	86.91 46	94.11 37	72.11 47	92.37 28	92.56 70	74.50 114	86.84 44	94.65 20	67.31 104	95.77 56	84.80 46	92.85 70	92.84 108

CS-MVS-test		86.29 42	86.48 37	85.71 68	91.02 84	67.21 153	92.36 29	93.78 18	78.97 28	83.51 92	91.20 114	70.65 66	95.15 81	81.96 78	94.89 41	94.77 22

EC-MVSNet		86.01 43	86.38 38	84.91 92	89.31 135	66.27 170	92.32 30	93.63 21	79.37 20	84.17 80	91.88 93	69.04 86	95.43 68	83.93 58	93.77 64	93.01 104

EPP-MVSNet		83.40 89	83.02 89	84.57 100	90.13 103	64.47 209	92.32 30	90.73 134	74.45 117	79.35 140	91.10 117	69.05 85	95.12 82	72.78 166	87.22 144	94.13 49

PHI-MVS		86.43 39	86.17 43	87.24 41	90.88 88	70.96 65	92.27 32	94.07 9	72.45 155	85.22 56	91.90 92	69.47 77	96.42 37	83.28 63	95.94 19	94.35 41

MVS_0304		88.08 14	88.08 17	88.08 14	89.67 117	72.04 48	92.26 33	89.26 179	84.19 2	85.01 57	95.18 13	69.93 72	97.20 14	91.63 2	95.60 29	94.99 9

HPM-MVS		87.11 30	86.98 30	87.50 38	93.88 39	72.16 45	92.19 34	93.33 31	76.07 84	83.81 87	93.95 51	69.77 75	96.01 49	85.15 40	94.66 46	94.32 43
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MTMP							92.18 35	32.83 413

HPM-MVS_fast		85.35 60	84.95 66	86.57 53	93.69 42	70.58 75	92.15 36	91.62 109	73.89 128	82.67 104	94.09 40	62.60 151	95.54 63	80.93 88	92.93 69	93.57 79

CPTT-MVS		83.73 79	83.33 85	84.92 91	93.28 49	70.86 69	92.09 37	90.38 143	68.75 237	79.57 137	92.83 76	60.60 191	93.04 181	80.92 89	91.56 88	90.86 171

APD-MVS_3200maxsize		85.97 45	85.88 48	86.22 57	92.69 63	69.53 89	91.93 38	92.99 46	73.54 137	85.94 47	94.51 24	65.80 122	95.61 60	83.04 66	92.51 74	93.53 83

SR-MVS-dyc-post		85.77 50	85.61 53	86.23 56	93.06 55	70.63 73	91.88 39	92.27 79	73.53 138	85.69 51	94.45 26	65.00 130	95.56 61	82.75 70	91.87 83	92.50 119

RE-MVS-def			85.48 55		93.06 55	70.63 73	91.88 39	92.27 79	73.53 138	85.69 51	94.45 26	63.87 136		82.75 70	91.87 83	92.50 119

APD-MVS		87.44 23	87.52 23	87.19 42	94.24 32	72.39 39	91.86 41	92.83 56	73.01 151	88.58 21	94.52 21	73.36 34	96.49 36	84.26 53	95.01 37	92.70 110
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		88.06 15	88.50 14	86.71 51	92.60 66	72.71 29	91.81 42	93.19 35	77.87 36	90.32 17	94.00 46	74.83 23	93.78 138	87.63 30	94.27 59	93.65 74
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
DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 43	94.10 8	75.90 87	92.29 7	95.66 10	81.67 6	97.38 10	87.44 33	96.34 15	93.95 57
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
QAPM		80.88 132	79.50 148	85.03 85	88.01 188	68.97 104	91.59 43	92.00 92	66.63 265	75.15 241	92.16 88	57.70 209	95.45 66	63.52 245	88.76 126	90.66 179

IS-MVSNet		83.15 93	82.81 93	84.18 120	89.94 112	63.30 234	91.59 43	88.46 209	79.04 25	79.49 138	92.16 88	65.10 127	94.28 114	67.71 212	91.86 85	94.95 10

9.14			88.26 15		92.84 60		91.52 46	94.75 1	73.93 127	88.57 22	94.67 19	75.57 22	95.79 55	86.77 35	95.76 23

TSAR-MVS + MP.		88.02 18	88.11 16	87.72 30	93.68 43	72.13 46	91.41 47	92.35 77	74.62 113	88.90 20	93.85 52	75.75 20	96.00 50	87.80 28	94.63 47	95.04 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
mvsmamba		81.69 117	80.74 123	84.56 101	87.45 208	66.72 161	91.26 48	85.89 256	74.66 111	78.23 162	90.56 132	54.33 234	94.91 92	80.73 93	83.54 201	92.04 139

DeepC-MVS_fast	79.65 3	86.91 33	86.62 36	87.76 27	93.52 46	72.37 41	91.26 48	93.04 38	76.62 71	84.22 78	93.36 63	71.44 57	96.76 25	80.82 90	95.33 34	94.16 48
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 82	83.14 86	85.14 81	90.08 105	68.71 113	91.25 50	92.44 72	79.12 23	78.92 146	91.00 124	60.42 193	95.38 72	78.71 105	86.32 157	91.33 155

plane_prior2							91.25 50		79.12 23

NCCC		88.06 15	88.01 19	88.24 11	94.41 22	73.62 11	91.22 52	92.83 56	81.50 5	85.79 50	93.47 60	73.02 40	97.00 18	84.90 42	94.94 39	94.10 50

API-MVS		81.99 111	81.23 114	84.26 118	90.94 86	70.18 82	91.10 53	89.32 175	71.51 172	78.66 151	88.28 189	65.26 125	95.10 87	64.74 239	91.23 92	87.51 280

EPNet		83.72 80	82.92 92	86.14 59	84.22 270	69.48 91	91.05 54	85.27 262	81.30 6	76.83 193	91.65 98	66.09 117	95.56 61	76.00 135	93.85 62	93.38 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		88.05 17	88.08 17	87.94 19	93.70 41	73.05 22	90.86 55	93.59 23	76.27 81	88.14 24	95.09 15	71.06 60	96.67 29	87.67 29	96.37 14	94.09 51

CSCG		86.41 41	86.19 42	87.07 45	92.91 58	72.48 37	90.81 56	93.56 24	73.95 125	83.16 95	91.07 119	75.94 18	95.19 79	79.94 99	94.38 56	93.55 81

MSLP-MVS++		85.43 58	85.76 51	84.45 106	91.93 72	70.24 76	90.71 57	92.86 54	77.46 47	84.22 78	92.81 78	67.16 106	92.94 183	80.36 95	94.35 57	90.16 199

3Dnovator	76.31 5	83.38 90	82.31 100	86.59 52	87.94 189	72.94 28	90.64 58	92.14 88	77.21 52	75.47 223	92.83 76	58.56 202	94.72 103	73.24 162	92.71 72	92.13 135

OpenMVS	72.83 10	79.77 159	78.33 174	84.09 125	85.17 250	69.91 84	90.57 59	90.97 127	66.70 259	72.17 279	91.91 91	54.70 231	93.96 125	61.81 266	90.95 95	88.41 265

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 60	93.00 43	80.90 7	88.06 26	94.06 42	76.43 16	96.84 21	88.48 24	95.99 18	94.34 42

MVSFormer		82.85 99	82.05 104	85.24 79	87.35 209	70.21 77	90.50 61	90.38 143	68.55 240	81.32 117	89.47 157	61.68 166	93.46 155	78.98 102	90.26 104	92.05 137

test_djsdf		80.30 151	79.32 152	83.27 156	83.98 276	65.37 191	90.50 61	90.38 143	68.55 240	76.19 210	88.70 175	56.44 220	93.46 155	78.98 102	80.14 244	90.97 168

save fliter					93.80 40	72.35 42	90.47 63	91.17 122	74.31 118

nrg030		83.88 76	83.53 80	84.96 88	86.77 225	69.28 99	90.46 64	92.67 62	74.79 108	82.95 96	91.33 110	72.70 43	93.09 177	80.79 92	79.28 254	92.50 119

sasdasda		85.91 47	85.87 49	86.04 60	89.84 114	69.44 95	90.45 65	93.00 43	76.70 69	88.01 28	91.23 111	73.28 36	93.91 132	81.50 81	88.80 124	94.77 22

canonicalmvs		85.91 47	85.87 49	86.04 60	89.84 114	69.44 95	90.45 65	93.00 43	76.70 69	88.01 28	91.23 111	73.28 36	93.91 132	81.50 81	88.80 124	94.77 22

plane_prior						68.71 113	90.38 67		77.62 39						86.16 161

DeepC-MVS	79.81 2	87.08 32	86.88 34	87.69 33	91.16 80	72.32 43	90.31 68	93.94 14	77.12 55	82.82 101	94.23 35	72.13 47	97.09 16	84.83 45	95.37 32	93.65 74
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 87	82.80 94	85.43 75	90.25 101	68.74 111	90.30 69	90.13 154	76.33 80	80.87 125	92.89 74	61.00 183	94.20 119	72.45 171	90.97 94	93.35 88
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PGM-MVS		86.68 36	86.27 40	87.90 22	94.22 33	73.38 18	90.22 70	93.04 38	75.53 93	83.86 85	94.42 29	67.87 99	96.64 31	82.70 74	94.57 49	93.66 70

LPG-MVS_test		82.08 107	81.27 113	84.50 103	89.23 139	68.76 109	90.22 70	91.94 96	75.37 96	76.64 199	91.51 103	54.29 235	94.91 92	78.44 108	83.78 190	89.83 220

Anonymous20231211		78.97 182	77.69 194	82.81 179	90.54 96	64.29 213	90.11 72	91.51 113	65.01 283	76.16 214	88.13 198	50.56 277	93.03 182	69.68 195	77.56 271	91.11 161

ACMM	73.20 8	80.78 140	79.84 141	83.58 146	89.31 135	68.37 122	89.99 73	91.60 110	70.28 199	77.25 183	89.66 150	53.37 245	93.53 151	74.24 151	82.85 210	88.85 252
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	74.13 6	81.51 124	80.57 126	84.36 109	89.42 127	68.69 116	89.97 74	91.50 116	74.46 116	75.04 245	90.41 135	53.82 240	94.54 106	77.56 118	82.91 209	89.86 219
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LFMVS		81.82 114	81.23 114	83.57 147	91.89 73	63.43 232	89.84 75	81.85 312	77.04 58	83.21 93	93.10 67	52.26 253	93.43 157	71.98 172	89.95 111	93.85 62

MCST-MVS		87.37 27	87.25 26	87.73 28	94.53 17	72.46 38	89.82 76	93.82 16	73.07 149	84.86 64	92.89 74	76.22 17	96.33 38	84.89 44	95.13 36	94.40 39

MAR-MVS		81.84 113	80.70 124	85.27 78	91.32 79	71.53 54	89.82 76	90.92 128	69.77 212	78.50 155	86.21 248	62.36 157	94.52 108	65.36 233	92.05 81	89.77 223
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 21	87.72 21	87.54 36	93.64 44	72.04 48	89.80 78	93.50 25	75.17 102	86.34 46	95.29 12	70.86 62	96.00 50	88.78 19	96.04 16	94.58 29
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
UA-Net		85.08 64	84.96 65	85.45 74	92.07 70	68.07 130	89.78 79	90.86 132	82.48 3	84.60 71	93.20 66	69.35 79	95.22 78	71.39 177	90.88 96	93.07 100

alignmvs		85.48 56	85.32 60	85.96 63	89.51 123	69.47 92	89.74 80	92.47 71	76.17 82	87.73 34	91.46 106	70.32 68	93.78 138	81.51 80	88.95 121	94.63 28

VDDNet		81.52 122	80.67 125	84.05 132	90.44 98	64.13 216	89.73 81	85.91 255	71.11 180	83.18 94	93.48 58	50.54 278	93.49 152	73.40 159	88.25 134	94.54 32

CANet		86.45 38	86.10 45	87.51 37	90.09 104	70.94 67	89.70 82	92.59 69	81.78 4	81.32 117	91.43 107	70.34 67	97.23 13	84.26 53	93.36 67	94.37 40

test_fmvsmconf0.1_n		85.61 54	85.65 52	85.50 73	82.99 301	69.39 97	89.65 83	90.29 150	73.31 143	87.77 31	94.15 38	71.72 52	93.23 164	90.31 4	90.67 99	93.89 61

114514_t		80.68 141	79.51 147	84.20 119	94.09 38	67.27 150	89.64 84	91.11 125	58.75 347	74.08 257	90.72 129	58.10 205	95.04 89	69.70 194	89.42 117	90.30 195

iter_conf05_11		84.86 70	84.52 72	85.87 65	90.86 89	67.18 154	89.63 85	92.15 87	71.48 173	84.64 69	90.81 128	68.82 89	96.00 50	78.50 107	93.84 63	94.43 35

test_fmvsmconf_n		85.92 46	86.04 47	85.57 72	85.03 256	69.51 90	89.62 86	90.58 137	73.42 140	87.75 32	94.02 44	72.85 41	93.24 163	90.37 3	90.75 97	93.96 56

DeepPCF-MVS	80.84 1	88.10 13	88.56 13	86.73 50	92.24 68	69.03 100	89.57 87	93.39 30	77.53 45	89.79 18	94.12 39	78.98 12	96.58 35	85.66 37	95.72 24	94.58 29

test_fmvsmconf0.01_n		84.73 71	84.52 72	85.34 76	80.25 341	69.03 100	89.47 88	89.65 167	73.24 147	86.98 42	94.27 32	66.62 108	93.23 164	90.26 5	89.95 111	93.78 67

fmvsm_s_conf0.5_n		83.80 78	83.71 79	84.07 127	86.69 227	67.31 148	89.46 89	83.07 295	71.09 181	86.96 43	93.70 55	69.02 87	91.47 236	88.79 18	84.62 178	93.44 85

MGCFI-Net		85.06 65	85.51 54	83.70 143	89.42 127	63.01 240	89.43 90	92.62 68	76.43 73	87.53 35	91.34 109	72.82 42	93.42 158	81.28 85	88.74 127	94.66 27

fmvsm_s_conf0.5_n_a		83.63 83	83.41 82	84.28 115	86.14 234	68.12 128	89.43 90	82.87 300	70.27 200	87.27 39	93.80 54	69.09 82	91.58 227	88.21 26	83.65 197	93.14 98

UGNet		80.83 134	79.59 146	84.54 102	88.04 186	68.09 129	89.42 92	88.16 211	76.95 59	76.22 209	89.46 159	49.30 293	93.94 128	68.48 207	90.31 102	91.60 145
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		78.73 186	77.83 186	81.43 208	85.17 250	60.30 276	89.41 93	90.90 129	71.21 178	77.17 189	88.73 174	46.38 312	93.21 166	72.57 169	78.96 256	90.79 172

fmvsm_s_conf0.1_n		83.56 85	83.38 83	84.10 122	84.86 258	67.28 149	89.40 94	83.01 296	70.67 189	87.08 40	93.96 50	68.38 93	91.45 237	88.56 22	84.50 179	93.56 80

AdaColmap		80.58 145	79.42 149	84.06 129	93.09 54	68.91 105	89.36 95	88.97 194	69.27 221	75.70 219	89.69 149	57.20 216	95.77 56	63.06 250	88.41 133	87.50 281

fmvsm_s_conf0.1_n_a		83.32 91	82.99 90	84.28 115	83.79 279	68.07 130	89.34 96	82.85 301	69.80 210	87.36 38	94.06 42	68.34 94	91.56 229	87.95 27	83.46 203	93.21 95

PS-MVSNAJss		82.07 108	81.31 112	84.34 111	86.51 230	67.27 150	89.27 97	91.51 113	71.75 165	79.37 139	90.22 140	63.15 145	94.27 115	77.69 116	82.36 217	91.49 151

jajsoiax		79.29 173	77.96 181	83.27 156	84.68 261	66.57 164	89.25 98	90.16 153	69.20 226	75.46 225	89.49 156	45.75 323	93.13 175	76.84 126	80.80 234	90.11 203

mvs_tets		79.13 177	77.77 190	83.22 160	84.70 260	66.37 168	89.17 99	90.19 152	69.38 219	75.40 228	89.46 159	44.17 332	93.15 173	76.78 128	80.70 236	90.14 200

HQP-NCC					89.33 132		89.17 99		76.41 74	77.23 185

ACMP_Plane					89.33 132		89.17 99		76.41 74	77.23 185

HQP-MVS		82.61 102	82.02 105	84.37 108	89.33 132	66.98 157	89.17 99	92.19 85	76.41 74	77.23 185	90.23 139	60.17 196	95.11 84	77.47 119	85.99 165	91.03 165

LS3D		76.95 228	74.82 244	83.37 153	90.45 97	67.36 147	89.15 103	86.94 240	61.87 322	69.52 307	90.61 131	51.71 266	94.53 107	46.38 365	86.71 152	88.21 267

OPM-MVS		83.50 86	82.95 91	85.14 81	88.79 156	70.95 66	89.13 104	91.52 112	77.55 44	80.96 124	91.75 95	60.71 186	94.50 109	79.67 100	86.51 155	89.97 215
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TSAR-MVS + GP.		85.71 52	85.33 59	86.84 47	91.34 78	72.50 36	89.07 105	87.28 233	76.41 74	85.80 49	90.22 140	74.15 31	95.37 75	81.82 79	91.88 82	92.65 114

test_prior4						72.60 34	89.01 106

GeoE		81.71 116	81.01 120	83.80 142	89.51 123	64.45 210	88.97 107	88.73 204	71.27 177	78.63 152	89.76 148	66.32 114	93.20 169	69.89 192	86.02 164	93.74 68

Anonymous20240529		80.19 154	78.89 162	84.10 122	90.60 94	64.75 203	88.95 108	90.90 129	65.97 273	80.59 127	91.17 116	49.97 283	93.73 144	69.16 200	82.70 214	93.81 65

VDD-MVS		83.01 98	82.36 99	84.96 88	91.02 84	66.40 167	88.91 109	88.11 212	77.57 41	84.39 76	93.29 64	52.19 254	93.91 132	77.05 124	88.70 128	94.57 31

Effi-MVS+		83.62 84	83.08 87	85.24 79	88.38 173	67.45 143	88.89 110	89.15 185	75.50 94	82.27 105	88.28 189	69.61 76	94.45 111	77.81 115	87.84 136	93.84 64

ACMH+	68.96 14	76.01 245	74.01 253	82.03 196	88.60 164	65.31 192	88.86 111	87.55 227	70.25 201	67.75 321	87.47 211	41.27 348	93.19 171	58.37 295	75.94 294	87.60 277

test_prior2							88.85 112		75.41 95	84.91 61	93.54 56	74.28 29		83.31 62	95.86 20

DP-MVS Recon		83.11 96	82.09 103	86.15 58	94.44 19	70.92 68	88.79 113	92.20 84	70.53 194	79.17 142	91.03 122	64.12 134	96.03 46	68.39 209	90.14 106	91.50 150

Effi-MVS+-dtu		80.03 156	78.57 167	84.42 107	85.13 254	68.74 111	88.77 114	88.10 213	74.99 104	74.97 246	83.49 304	57.27 215	93.36 159	73.53 156	80.88 232	91.18 159

TEST9					93.26 50	72.96 25	88.75 115	91.89 99	68.44 243	85.00 59	93.10 67	74.36 28	95.41 70

train_agg		86.43 39	86.20 41	87.13 44	93.26 50	72.96 25	88.75 115	91.89 99	68.69 238	85.00 59	93.10 67	74.43 26	95.41 70	84.97 41	95.71 25	93.02 103

ETV-MVS		84.90 69	84.67 69	85.59 71	89.39 130	68.66 117	88.74 117	92.64 66	79.97 15	84.10 81	85.71 257	69.32 80	95.38 72	80.82 90	91.37 90	92.72 109

PVSNet_Blended_VisFu		82.62 101	81.83 109	84.96 88	90.80 91	69.76 87	88.74 117	91.70 108	69.39 218	78.96 144	88.46 184	65.47 124	94.87 98	74.42 148	88.57 129	90.24 197

casdiffmvs_mvg		85.99 44	86.09 46	85.70 69	87.65 202	67.22 152	88.69 119	93.04 38	79.64 18	85.33 54	92.54 83	73.30 35	94.50 109	83.49 60	91.14 93	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 52	72.57 35	88.68 120	91.84 103	68.69 238	84.87 63	93.10 67	74.43 26	95.16 80

test_fmvsm_n_1920		85.29 61	85.34 58	85.13 83	86.12 235	69.93 83	88.65 121	90.78 133	69.97 206	88.27 23	93.98 49	71.39 58	91.54 231	88.49 23	90.45 101	93.91 58

ACMH	67.68 16	75.89 246	73.93 255	81.77 201	88.71 161	66.61 163	88.62 122	89.01 191	69.81 209	66.78 333	86.70 233	41.95 347	91.51 234	55.64 316	78.14 265	87.17 288
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CDPH-MVS		85.76 51	85.29 62	87.17 43	93.49 47	71.08 61	88.58 123	92.42 75	68.32 245	84.61 70	93.48 58	72.32 44	96.15 45	79.00 101	95.43 31	94.28 45

DP-MVS		76.78 231	74.57 246	83.42 150	93.29 48	69.46 94	88.55 124	83.70 282	63.98 298	70.20 295	88.89 171	54.01 239	94.80 100	46.66 362	81.88 223	86.01 313

fmvsm_l_conf0.5_n		84.47 72	84.54 70	84.27 117	85.42 246	68.81 106	88.49 125	87.26 234	68.08 247	88.03 27	93.49 57	72.04 48	91.77 221	88.90 17	89.14 120	92.24 130

MVSMamba_pp		84.98 66	84.70 68	85.80 66	89.43 126	67.63 139	88.44 126	92.64 66	72.17 161	84.54 73	90.39 136	68.88 88	95.28 76	81.45 83	94.39 53	94.49 33

WR-MVS_H		78.51 192	78.49 168	78.56 269	88.02 187	56.38 323	88.43 127	92.67 62	77.14 54	73.89 258	87.55 208	66.25 115	89.24 280	58.92 289	73.55 327	90.06 209

F-COLMAP		76.38 240	74.33 251	82.50 189	89.28 137	66.95 160	88.41 128	89.03 189	64.05 296	66.83 332	88.61 179	46.78 310	92.89 184	57.48 302	78.55 258	87.67 275

GBi-Net		78.40 193	77.40 199	81.40 210	87.60 203	63.01 240	88.39 129	89.28 176	71.63 167	75.34 230	87.28 213	54.80 227	91.11 245	62.72 252	79.57 248	90.09 205

test1		78.40 193	77.40 199	81.40 210	87.60 203	63.01 240	88.39 129	89.28 176	71.63 167	75.34 230	87.28 213	54.80 227	91.11 245	62.72 252	79.57 248	90.09 205

FMVSNet1		77.44 219	76.12 226	81.40 210	86.81 224	63.01 240	88.39 129	89.28 176	70.49 195	74.39 254	87.28 213	49.06 297	91.11 245	60.91 273	78.52 259	90.09 205

tttt0517		79.40 170	77.91 183	83.90 141	88.10 183	63.84 220	88.37 132	84.05 278	71.45 174	76.78 195	89.12 166	49.93 286	94.89 96	70.18 188	83.18 207	92.96 106

fmvsm_l_conf0.5_n_a		84.13 74	84.16 76	84.06 129	85.38 247	68.40 121	88.34 133	86.85 242	67.48 254	87.48 36	93.40 61	70.89 61	91.61 225	88.38 25	89.22 119	92.16 134

v7n		78.97 182	77.58 197	83.14 163	83.45 286	65.51 186	88.32 134	91.21 120	73.69 132	72.41 276	86.32 247	57.93 206	93.81 137	69.18 199	75.65 297	90.11 203

COLMAP_ROB	66.92 17	73.01 278	70.41 293	80.81 227	87.13 219	65.63 184	88.30 135	84.19 277	62.96 308	63.80 358	87.69 203	38.04 364	92.56 192	46.66 362	74.91 314	84.24 337
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FIs		82.07 108	82.42 96	81.04 221	88.80 155	58.34 291	88.26 136	93.49 26	76.93 60	78.47 157	91.04 120	69.92 73	92.34 202	69.87 193	84.97 173	92.44 123

EIA-MVS		83.31 92	82.80 94	84.82 94	89.59 119	65.59 185	88.21 137	92.68 61	74.66 111	78.96 144	86.42 244	69.06 84	95.26 77	75.54 141	90.09 107	93.62 77

PLC	70.83 11	78.05 204	76.37 224	83.08 166	91.88 74	67.80 135	88.19 138	89.46 171	64.33 291	69.87 304	88.38 186	53.66 241	93.58 146	58.86 290	82.73 212	87.86 272
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MG-MVS		83.41 88	83.45 81	83.28 155	92.74 62	62.28 251	88.17 139	89.50 170	75.22 98	81.49 116	92.74 82	66.75 107	95.11 84	72.85 165	91.58 87	92.45 122

TAPA-MVS	73.13 9	79.15 176	77.94 182	82.79 182	89.59 119	62.99 244	88.16 140	91.51 113	65.77 274	77.14 190	91.09 118	60.91 184	93.21 166	50.26 344	87.05 146	92.17 133
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvsmvis_n_1920		84.02 75	83.87 77	84.49 105	84.12 272	69.37 98	88.15 141	87.96 217	70.01 204	83.95 84	93.23 65	68.80 91	91.51 234	88.61 20	89.96 110	92.57 115

h-mvs33		83.15 93	82.19 101	86.02 62	90.56 95	70.85 70	88.15 141	89.16 184	76.02 85	84.67 66	91.39 108	61.54 169	95.50 64	82.71 72	75.48 301	91.72 144

PS-CasMVS		78.01 206	78.09 179	77.77 283	87.71 199	54.39 347	88.02 143	91.22 119	77.50 46	73.26 264	88.64 178	60.73 185	88.41 295	61.88 264	73.88 324	90.53 185

OMC-MVS		82.69 100	81.97 107	84.85 93	88.75 158	67.42 144	87.98 144	90.87 131	74.92 105	79.72 135	91.65 98	62.19 161	93.96 125	75.26 143	86.42 156	93.16 97

v8		79.97 158	79.02 160	82.80 180	84.09 273	64.50 208	87.96 145	90.29 150	74.13 124	75.24 238	86.81 226	62.88 150	93.89 135	74.39 149	75.40 306	90.00 211

FC-MVSNet-test		81.52 122	82.02 105	80.03 242	88.42 172	55.97 329	87.95 146	93.42 29	77.10 56	77.38 180	90.98 126	69.96 71	91.79 220	68.46 208	84.50 179	92.33 124

CP-MVSNet		78.22 197	78.34 173	77.84 281	87.83 193	54.54 345	87.94 147	91.17 122	77.65 38	73.48 262	88.49 183	62.24 160	88.43 294	62.19 260	74.07 320	90.55 184

PAPM_NR		83.02 97	82.41 97	84.82 94	92.47 67	66.37 168	87.93 148	91.80 104	73.82 129	77.32 182	90.66 130	67.90 98	94.90 95	70.37 186	89.48 116	93.19 96

PEN-MVS		77.73 212	77.69 194	77.84 281	87.07 220	53.91 350	87.91 149	91.18 121	77.56 43	73.14 266	88.82 173	61.23 178	89.17 281	59.95 279	72.37 335	90.43 189

ECVR-MVS		79.61 161	79.26 154	80.67 230	90.08 105	54.69 343	87.89 150	77.44 351	74.88 106	80.27 129	92.79 79	48.96 299	92.45 195	68.55 206	92.50 75	94.86 17

v10		79.74 160	78.67 164	82.97 173	84.06 274	64.95 198	87.88 151	90.62 136	73.11 148	75.11 242	86.56 240	61.46 172	94.05 124	73.68 154	75.55 299	89.90 217

test2506		77.30 223	76.49 220	79.74 248	90.08 105	52.02 359	87.86 152	63.10 394	74.88 106	80.16 132	92.79 79	38.29 363	92.35 201	68.74 205	92.50 75	94.86 17

casdiffmvs		85.11 63	85.14 63	85.01 86	87.20 217	65.77 182	87.75 153	92.83 56	77.84 37	84.36 77	92.38 85	72.15 46	93.93 131	81.27 86	90.48 100	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		80.84 133	80.31 132	82.42 190	87.85 192	62.33 249	87.74 154	91.33 118	80.55 9	77.99 170	89.86 145	65.23 126	92.62 189	67.05 221	75.24 311	92.30 126

EI-MVSNet-Vis-set		84.19 73	83.81 78	85.31 77	88.18 178	67.85 134	87.66 155	89.73 165	80.05 14	82.95 96	89.59 154	70.74 64	94.82 99	80.66 94	84.72 176	93.28 91

UniMVSNet (Re)		81.60 121	81.11 117	83.09 165	88.38 173	64.41 211	87.60 156	93.02 42	78.42 32	78.56 154	88.16 193	69.78 74	93.26 162	69.58 196	76.49 283	91.60 145

CNLPA		78.08 202	76.79 213	81.97 198	90.40 99	71.07 62	87.59 157	84.55 270	66.03 272	72.38 277	89.64 151	57.56 211	86.04 314	59.61 282	83.35 204	88.79 255

DTE-MVSNet		76.99 226	76.80 212	77.54 288	86.24 232	53.06 358	87.52 158	90.66 135	77.08 57	72.50 274	88.67 177	60.48 192	89.52 275	57.33 305	70.74 346	90.05 210

无先验							87.48 159	88.98 192	60.00 334				94.12 122	67.28 217		88.97 247

FMVSNet2		78.20 199	77.21 203	81.20 216	87.60 203	62.89 245	87.47 160	89.02 190	71.63 167	75.29 236	87.28 213	54.80 227	91.10 248	62.38 257	79.38 252	89.61 227

EI-MVSNet-UG-set		83.81 77	83.38 83	85.09 84	87.87 191	67.53 142	87.44 161	89.66 166	79.74 16	82.23 106	89.41 163	70.24 69	94.74 102	79.95 98	83.92 189	92.99 105

thisisatest0530		79.40 170	77.76 191	84.31 113	87.69 201	65.10 196	87.36 162	84.26 276	70.04 203	77.42 179	88.26 191	49.94 284	94.79 101	70.20 187	84.70 177	93.03 102

CANet_DTU		80.61 142	79.87 140	82.83 177	85.60 243	63.17 239	87.36 162	88.65 205	76.37 78	75.88 216	88.44 185	53.51 243	93.07 178	73.30 160	89.74 114	92.25 128

test1111		79.43 168	79.18 157	80.15 240	89.99 110	53.31 356	87.33 164	77.05 354	75.04 103	80.23 131	92.77 81	48.97 298	92.33 203	68.87 203	92.40 77	94.81 20

baseline		84.93 67	84.98 64	84.80 96	87.30 215	65.39 190	87.30 165	92.88 53	77.62 39	84.04 83	92.26 87	71.81 50	93.96 125	81.31 84	90.30 103	95.03 8

UniMVSNet_ETH3D		79.10 178	78.24 176	81.70 202	86.85 222	60.24 277	87.28 166	88.79 198	74.25 120	76.84 192	90.53 134	49.48 289	91.56 229	67.98 210	82.15 218	93.29 90

anonymousdsp		78.60 190	77.15 204	82.98 172	80.51 339	67.08 155	87.24 167	89.53 169	65.66 276	75.16 240	87.19 219	52.52 248	92.25 205	77.17 123	79.34 253	89.61 227

iter_conf05		85.49 55	85.43 56	85.67 70	91.09 81	66.55 165	87.18 168	92.08 89	72.89 154	82.90 98	91.71 96	71.85 49	96.03 46	84.77 47	94.39 53	94.42 36

UniMVSNet_NR-MVSNet		81.88 112	81.54 111	82.92 174	88.46 169	63.46 230	87.13 169	92.37 76	80.19 12	78.38 158	89.14 165	71.66 55	93.05 179	70.05 189	76.46 284	92.25 128

DPM-MVS		84.93 67	84.29 75	86.84 47	90.20 102	73.04 23	87.12 170	93.04 38	69.80 210	82.85 100	91.22 113	73.06 39	96.02 48	76.72 129	94.63 47	91.46 154

v1144		80.03 156	79.03 159	83.01 170	83.78 280	64.51 206	87.11 171	90.57 139	71.96 164	78.08 168	86.20 249	61.41 173	93.94 128	74.93 144	77.23 272	90.60 182

v2v482		80.23 152	79.29 153	83.05 168	83.62 282	64.14 215	87.04 172	89.97 158	73.61 134	78.18 165	87.22 217	61.10 181	93.82 136	76.11 132	76.78 281	91.18 159

DU-MVS		81.12 129	80.52 128	82.90 175	87.80 194	63.46 230	87.02 173	91.87 101	79.01 26	78.38 158	89.07 167	65.02 128	93.05 179	70.05 189	76.46 284	92.20 131

v144192		79.47 166	78.37 172	82.78 183	83.35 287	63.96 218	86.96 174	90.36 146	69.99 205	77.50 177	85.67 260	60.66 188	93.77 140	74.27 150	76.58 282	90.62 180

Fast-Effi-MVS+-dtu		78.02 205	76.49 220	82.62 187	83.16 295	66.96 159	86.94 175	87.45 231	72.45 155	71.49 286	84.17 291	54.79 230	91.58 227	67.61 213	80.31 241	89.30 235

v1192		79.59 163	78.43 171	83.07 167	83.55 284	64.52 205	86.93 176	90.58 137	70.83 185	77.78 173	85.90 253	59.15 199	93.94 128	73.96 153	77.19 274	90.76 174

EPNet_dtu		75.46 252	74.86 243	77.23 292	82.57 310	54.60 344	86.89 177	83.09 294	71.64 166	66.25 342	85.86 255	55.99 221	88.04 299	54.92 318	86.55 154	89.05 242
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM2							86.86 178

VPA-MVSNet		80.60 143	80.55 127	80.76 228	88.07 185	60.80 268	86.86 178	91.58 111	75.67 92	80.24 130	89.45 161	63.34 139	90.25 262	70.51 185	79.22 255	91.23 158

v1921920		79.22 174	78.03 180	82.80 180	83.30 289	63.94 219	86.80 180	90.33 147	69.91 208	77.48 178	85.53 263	58.44 203	93.75 142	73.60 155	76.85 279	90.71 178

IterMVS-LS		80.06 155	79.38 150	82.11 194	85.89 238	63.20 237	86.79 181	89.34 174	74.19 121	75.45 226	86.72 229	66.62 108	92.39 198	72.58 168	76.86 278	90.75 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TransMVSNet (Re)		75.39 255	74.56 247	77.86 280	85.50 245	57.10 311	86.78 182	86.09 254	72.17 161	71.53 285	87.34 212	63.01 149	89.31 279	56.84 310	61.83 372	87.17 288

Baseline_NR-MVSNet		78.15 201	78.33 174	77.61 286	85.79 239	56.21 327	86.78 182	85.76 258	73.60 135	77.93 171	87.57 206	65.02 128	88.99 284	67.14 220	75.33 308	87.63 276

PAPR		81.66 120	80.89 122	83.99 137	90.27 100	64.00 217	86.76 184	91.77 107	68.84 236	77.13 191	89.50 155	67.63 100	94.88 97	67.55 214	88.52 131	93.09 99

Vis-MVSNet (Re-imp)		78.36 195	78.45 169	78.07 279	88.64 163	51.78 365	86.70 185	79.63 336	74.14 123	75.11 242	90.83 127	61.29 177	89.75 271	58.10 298	91.60 86	92.69 112

pmmvs6		74.69 259	73.39 261	78.61 267	81.38 328	57.48 306	86.64 186	87.95 218	64.99 284	70.18 296	86.61 236	50.43 279	89.52 275	62.12 262	70.18 348	88.83 253

v1240		78.99 181	77.78 189	82.64 186	83.21 291	63.54 227	86.62 187	90.30 149	69.74 215	77.33 181	85.68 259	57.04 217	93.76 141	73.13 163	76.92 276	90.62 180

MTAPA		87.23 28	87.00 29	87.90 22	94.18 35	74.25 5	86.58 188	92.02 90	79.45 19	85.88 48	94.80 17	68.07 95	96.21 42	86.69 36	95.34 33	93.23 92

旧先验2							86.56 189		58.10 351	87.04 41			88.98 285	74.07 152

FMVSNet3		77.88 209	76.85 211	80.97 224	86.84 223	62.36 248	86.52 190	88.77 199	71.13 179	75.34 230	86.66 235	54.07 238	91.10 248	62.72 252	79.57 248	89.45 231

dcpmvs_2		85.63 53	86.15 44	84.06 129	91.71 75	64.94 199	86.47 191	91.87 101	73.63 133	86.60 45	93.02 72	76.57 15	91.87 219	83.36 61	92.15 78	95.35 3

pm-mvs1		77.25 224	76.68 218	78.93 263	84.22 270	58.62 289	86.41 192	88.36 210	71.37 175	73.31 263	88.01 199	61.22 179	89.15 282	64.24 243	73.01 332	89.03 243

EI-MVSNet		80.52 146	79.98 137	82.12 193	84.28 268	63.19 238	86.41 192	88.95 195	74.18 122	78.69 149	87.54 209	66.62 108	92.43 196	72.57 169	80.57 238	90.74 177

CVMVSNet		72.99 279	72.58 269	74.25 319	84.28 268	50.85 371	86.41 192	83.45 288	44.56 386	73.23 265	87.54 209	49.38 291	85.70 316	65.90 229	78.44 261	86.19 308

NR-MVSNet		80.23 152	79.38 150	82.78 183	87.80 194	63.34 233	86.31 195	91.09 126	79.01 26	72.17 279	89.07 167	67.20 105	92.81 188	66.08 228	75.65 297	92.20 131

v148		78.72 187	77.80 188	81.47 207	82.73 306	61.96 255	86.30 196	88.08 214	73.26 145	76.18 211	85.47 265	62.46 155	92.36 200	71.92 173	73.82 325	90.09 205

新几何2							86.29 197

test_yl		81.17 127	80.47 129	83.24 158	89.13 143	63.62 223	86.21 198	89.95 159	72.43 158	81.78 113	89.61 152	57.50 212	93.58 146	70.75 181	86.90 148	92.52 117

DCV-MVSNet		81.17 127	80.47 129	83.24 158	89.13 143	63.62 223	86.21 198	89.95 159	72.43 158	81.78 113	89.61 152	57.50 212	93.58 146	70.75 181	86.90 148	92.52 117

PVSNet_BlendedMVS		80.60 143	80.02 136	82.36 192	88.85 150	65.40 188	86.16 200	92.00 92	69.34 220	78.11 166	86.09 252	66.02 119	94.27 115	71.52 174	82.06 220	87.39 282

MVS_Test		83.15 93	83.06 88	83.41 152	86.86 221	63.21 236	86.11 201	92.00 92	74.31 118	82.87 99	89.44 162	70.03 70	93.21 166	77.39 121	88.50 132	93.81 65

BH-untuned		79.47 166	78.60 166	82.05 195	89.19 141	65.91 177	86.07 202	88.52 208	72.18 160	75.42 227	87.69 203	61.15 180	93.54 150	60.38 276	86.83 150	86.70 301

MVS_111021_HR		85.14 62	84.75 67	86.32 55	91.65 76	72.70 30	85.98 203	90.33 147	76.11 83	82.08 107	91.61 101	71.36 59	94.17 121	81.02 87	92.58 73	92.08 136

jason		81.39 125	80.29 133	84.70 98	86.63 229	69.90 85	85.95 204	86.77 243	63.24 303	81.07 123	89.47 157	61.08 182	92.15 208	78.33 111	90.07 109	92.05 137
jason: jason.
test_0402		72.79 281	70.44 292	79.84 246	88.13 181	65.99 175	85.93 205	84.29 274	65.57 277	67.40 327	85.49 264	46.92 309	92.61 190	35.88 388	74.38 319	80.94 367

OurMVSNet-221017-0		74.26 262	72.42 271	79.80 247	83.76 281	59.59 284	85.92 206	86.64 244	66.39 267	66.96 330	87.58 205	39.46 356	91.60 226	65.76 231	69.27 351	88.22 266

hse-mvs2		81.72 115	80.94 121	84.07 127	88.72 160	67.68 138	85.87 207	87.26 234	76.02 85	84.67 66	88.22 192	61.54 169	93.48 153	82.71 72	73.44 329	91.06 163

EG-PatchMatch MVS		74.04 265	71.82 275	80.71 229	84.92 257	67.42 144	85.86 208	88.08 214	66.04 271	64.22 354	83.85 295	35.10 372	92.56 192	57.44 303	80.83 233	82.16 361

AUN-MVS		79.21 175	77.60 196	84.05 132	88.71 161	67.61 140	85.84 209	87.26 234	69.08 229	77.23 185	88.14 197	53.20 247	93.47 154	75.50 142	73.45 328	91.06 163

thres100view900		76.50 235	75.55 233	79.33 256	89.52 122	56.99 312	85.83 210	83.23 291	73.94 126	76.32 207	87.12 221	51.89 263	91.95 214	48.33 353	83.75 193	89.07 237

CLD-MVS		82.31 104	81.65 110	84.29 114	88.47 168	67.73 137	85.81 211	92.35 77	75.78 88	78.33 160	86.58 239	64.01 135	94.35 112	76.05 134	87.48 141	90.79 172
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
SixPastTwentyTwo		73.37 272	71.26 284	79.70 249	85.08 255	57.89 299	85.57 212	83.56 285	71.03 183	65.66 344	85.88 254	42.10 345	92.57 191	59.11 287	63.34 370	88.65 260

xiu_mvs_v1_base_debu		80.80 137	79.72 143	84.03 134	87.35 209	70.19 79	85.56 213	88.77 199	69.06 230	81.83 109	88.16 193	50.91 272	92.85 185	78.29 112	87.56 138	89.06 239

xiu_mvs_v1_base		80.80 137	79.72 143	84.03 134	87.35 209	70.19 79	85.56 213	88.77 199	69.06 230	81.83 109	88.16 193	50.91 272	92.85 185	78.29 112	87.56 138	89.06 239

xiu_mvs_v1_base_debi		80.80 137	79.72 143	84.03 134	87.35 209	70.19 79	85.56 213	88.77 199	69.06 230	81.83 109	88.16 193	50.91 272	92.85 185	78.29 112	87.56 138	89.06 239

V42		79.38 172	78.24 176	82.83 177	81.10 333	65.50 187	85.55 216	89.82 161	71.57 171	78.21 163	86.12 251	60.66 188	93.18 172	75.64 138	75.46 303	89.81 222

lupinMVS		81.39 125	80.27 134	84.76 97	87.35 209	70.21 77	85.55 216	86.41 247	62.85 310	81.32 117	88.61 179	61.68 166	92.24 206	78.41 110	90.26 104	91.83 141

Fast-Effi-MVS+		80.81 135	79.92 138	83.47 148	88.85 150	64.51 206	85.53 218	89.39 173	70.79 186	78.49 156	85.06 275	67.54 101	93.58 146	67.03 222	86.58 153	92.32 125

thres600view7		76.50 235	75.44 234	79.68 250	89.40 129	57.16 309	85.53 218	83.23 291	73.79 130	76.26 208	87.09 222	51.89 263	91.89 217	48.05 358	83.72 196	90.00 211

DELS-MVS		85.41 59	85.30 61	85.77 67	88.49 167	67.93 133	85.52 220	93.44 27	78.70 29	83.63 91	89.03 169	74.57 24	95.71 59	80.26 97	94.04 61	93.66 70
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
tfpn200view9		76.42 238	75.37 238	79.55 255	89.13 143	57.65 303	85.17 221	83.60 283	73.41 141	76.45 203	86.39 245	52.12 255	91.95 214	48.33 353	83.75 193	89.07 237

thres400		76.50 235	75.37 238	79.86 245	89.13 143	57.65 303	85.17 221	83.60 283	73.41 141	76.45 203	86.39 245	52.12 255	91.95 214	48.33 353	83.75 193	90.00 211

MVS_111021_LR		82.61 102	82.11 102	84.11 121	88.82 153	71.58 53	85.15 223	86.16 252	74.69 110	80.47 128	91.04 120	62.29 158	90.55 259	80.33 96	90.08 108	90.20 198

baseline1		76.98 227	76.75 216	77.66 284	88.13 181	55.66 333	85.12 224	81.89 310	73.04 150	76.79 194	88.90 170	62.43 156	87.78 302	63.30 249	71.18 344	89.55 229

WR-MVS		79.49 165	79.22 156	80.27 238	88.79 156	58.35 290	85.06 225	88.61 207	78.56 30	77.65 175	88.34 187	63.81 138	90.66 258	64.98 237	77.22 273	91.80 143

ET-MVSNet_ETH3D		78.63 189	76.63 219	84.64 99	86.73 226	69.47 92	85.01 226	84.61 269	69.54 216	66.51 340	86.59 237	50.16 281	91.75 222	76.26 131	84.24 186	92.69 112

OpenMVS_ROB	64.09 19	70.56 301	68.19 307	77.65 285	80.26 340	59.41 286	85.01 226	82.96 299	58.76 346	65.43 346	82.33 320	37.63 366	91.23 244	45.34 372	76.03 293	82.32 358

BH-RMVSNet		79.61 161	78.44 170	83.14 163	89.38 131	65.93 176	84.95 228	87.15 237	73.56 136	78.19 164	89.79 147	56.67 219	93.36 159	59.53 283	86.74 151	90.13 201

BH-w/o		78.21 198	77.33 202	80.84 226	88.81 154	65.13 195	84.87 229	87.85 222	69.75 213	74.52 253	84.74 280	61.34 175	93.11 176	58.24 297	85.84 167	84.27 336

TDRefinement		67.49 324	64.34 334	76.92 294	73.47 382	61.07 264	84.86 230	82.98 298	59.77 336	58.30 376	85.13 273	26.06 386	87.89 300	47.92 359	60.59 377	81.81 363

Anonymous202405211		78.25 196	77.01 206	81.99 197	91.03 83	60.67 270	84.77 231	83.90 280	70.65 193	80.00 133	91.20 114	41.08 350	91.43 238	65.21 234	85.26 171	93.85 62

TAMVS		78.89 184	77.51 198	83.03 169	87.80 194	67.79 136	84.72 232	85.05 265	67.63 250	76.75 196	87.70 202	62.25 159	90.82 254	58.53 294	87.13 145	90.49 187

1314		76.53 234	75.30 240	80.21 239	83.93 277	62.32 250	84.66 233	88.81 197	60.23 332	70.16 298	84.07 293	55.30 224	90.73 257	67.37 216	83.21 206	87.59 279

MVS		78.19 200	76.99 208	81.78 200	85.66 241	66.99 156	84.66 233	90.47 141	55.08 367	72.02 281	85.27 268	63.83 137	94.11 123	66.10 227	89.80 113	84.24 337

tfpnnormal		74.39 260	73.16 264	78.08 278	86.10 237	58.05 294	84.65 235	87.53 228	70.32 198	71.22 288	85.63 261	54.97 225	89.86 268	43.03 376	75.02 313	86.32 305

TR-MVS		77.44 219	76.18 225	81.20 216	88.24 177	63.24 235	84.61 236	86.40 248	67.55 252	77.81 172	86.48 243	54.10 237	93.15 173	57.75 301	82.72 213	87.20 287

AllTest		70.96 295	68.09 310	79.58 253	85.15 252	63.62 223	84.58 237	79.83 333	62.31 317	60.32 369	86.73 227	32.02 376	88.96 287	50.28 342	71.57 342	86.15 309

FA-MVS(test-final)		80.96 131	79.91 139	84.10 122	88.30 176	65.01 197	84.55 238	90.01 157	73.25 146	79.61 136	87.57 206	58.35 204	94.72 103	71.29 178	86.25 159	92.56 116

EU-MVSNet		68.53 319	67.61 320	71.31 344	78.51 360	47.01 382	84.47 239	84.27 275	42.27 389	66.44 341	84.79 279	40.44 353	83.76 332	58.76 292	68.54 356	83.17 349

VNet		82.21 105	82.41 97	81.62 203	90.82 90	60.93 265	84.47 239	89.78 162	76.36 79	84.07 82	91.88 93	64.71 131	90.26 261	70.68 183	88.89 122	93.66 70

xiu_mvs_v2_base		81.69 117	81.05 118	83.60 145	89.15 142	68.03 132	84.46 241	90.02 156	70.67 189	81.30 120	86.53 242	63.17 144	94.19 120	75.60 140	88.54 130	88.57 262

VPNet		78.69 188	78.66 165	78.76 265	88.31 175	55.72 332	84.45 242	86.63 245	76.79 64	78.26 161	90.55 133	59.30 198	89.70 273	66.63 223	77.05 275	90.88 170

PVSNet_Blended		80.98 130	80.34 131	82.90 175	88.85 150	65.40 188	84.43 243	92.00 92	67.62 251	78.11 166	85.05 276	66.02 119	94.27 115	71.52 174	89.50 115	89.01 244

MVP-Stereo		76.12 242	74.46 250	81.13 219	85.37 248	69.79 86	84.42 244	87.95 218	65.03 282	67.46 325	85.33 267	53.28 246	91.73 224	58.01 299	83.27 205	81.85 362
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CDS-MVSNet		79.07 179	77.70 193	83.17 162	87.60 203	68.23 126	84.40 245	86.20 251	67.49 253	76.36 206	86.54 241	61.54 169	90.79 255	61.86 265	87.33 142	90.49 187
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
K. test v3		71.19 292	68.51 304	79.21 259	83.04 298	57.78 302	84.35 246	76.91 355	72.90 153	62.99 361	82.86 314	39.27 357	91.09 250	61.65 267	52.66 388	88.75 257

PS-MVSNAJ		81.69 117	81.02 119	83.70 143	89.51 123	68.21 127	84.28 247	90.09 155	70.79 186	81.26 121	85.62 262	63.15 145	94.29 113	75.62 139	88.87 123	88.59 261

patch_mono-2		83.65 81	84.54 70	80.99 222	90.06 109	65.83 179	84.21 248	88.74 203	71.60 170	85.01 57	92.44 84	74.51 25	83.50 335	82.15 77	92.15 78	93.64 76

test222					91.50 77	68.26 125	84.16 249	83.20 293	54.63 368	79.74 134	91.63 100	58.97 200			91.42 89	86.77 299

testdata1							84.14 250		75.71 89

c3_l		78.75 185	77.91 183	81.26 214	82.89 303	61.56 260	84.09 251	89.13 187	69.97 206	75.56 221	84.29 287	66.36 113	92.09 210	73.47 158	75.48 301	90.12 202

MVSTER		79.01 180	77.88 185	82.38 191	83.07 296	64.80 202	84.08 252	88.95 195	69.01 233	78.69 149	87.17 220	54.70 231	92.43 196	74.69 145	80.57 238	89.89 218

ab-mvs		79.51 164	78.97 161	81.14 218	88.46 169	60.91 266	83.84 253	89.24 181	70.36 196	79.03 143	88.87 172	63.23 143	90.21 263	65.12 235	82.57 215	92.28 127

PAPM		77.68 216	76.40 223	81.51 206	87.29 216	61.85 256	83.78 254	89.59 168	64.74 285	71.23 287	88.70 175	62.59 152	93.66 145	52.66 329	87.03 147	89.01 244

diffmvs		82.10 106	81.88 108	82.76 185	83.00 299	63.78 222	83.68 255	89.76 163	72.94 152	82.02 108	89.85 146	65.96 121	90.79 255	82.38 76	87.30 143	93.71 69
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		78.59 191	77.76 191	81.08 220	82.66 308	61.56 260	83.65 256	89.15 185	68.87 235	75.55 222	83.79 298	66.49 111	92.03 211	73.25 161	76.39 286	89.64 226

1112_ss		77.40 221	76.43 222	80.32 237	89.11 147	60.41 275	83.65 256	87.72 225	62.13 320	73.05 267	86.72 229	62.58 153	89.97 267	62.11 263	80.80 234	90.59 183

PCF-MVS	73.52 7	80.38 148	78.84 163	85.01 86	87.71 199	68.99 103	83.65 256	91.46 117	63.00 307	77.77 174	90.28 137	66.10 116	95.09 88	61.40 269	88.22 135	90.94 169
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
XVG-ACMP-BASELINE		76.11 243	74.27 252	81.62 203	83.20 292	64.67 204	83.60 259	89.75 164	69.75 213	71.85 282	87.09 222	32.78 375	92.11 209	69.99 191	80.43 240	88.09 268

cl22		78.07 203	77.01 206	81.23 215	82.37 315	61.83 257	83.55 260	87.98 216	68.96 234	75.06 244	83.87 294	61.40 174	91.88 218	73.53 156	76.39 286	89.98 214

XVG-OURS-SEG-HR		80.81 135	79.76 142	83.96 139	85.60 243	68.78 108	83.54 261	90.50 140	70.66 192	76.71 197	91.66 97	60.69 187	91.26 242	76.94 125	81.58 225	91.83 141

IB-MVS	68.01 15	75.85 247	73.36 262	83.31 154	84.76 259	66.03 172	83.38 262	85.06 264	70.21 202	69.40 308	81.05 331	45.76 322	94.66 105	65.10 236	75.49 300	89.25 236
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	77.95 207	77.15 204	80.36 235	87.57 207	60.21 278	83.37 263	87.78 224	66.11 269	75.37 229	87.06 224	63.27 141	90.48 260	61.38 270	82.43 216	90.40 191

test_vis1_n_1920		75.52 251	75.78 227	74.75 315	79.84 347	57.44 307	83.26 264	85.52 260	62.83 311	79.34 141	86.17 250	45.10 327	79.71 354	78.75 104	81.21 229	87.10 294

Anonymous20240521		68.80 315	67.22 324	73.55 324	74.33 375	54.11 348	83.18 265	85.61 259	58.15 350	61.68 364	80.94 334	30.71 381	81.27 348	57.00 308	73.34 331	85.28 323

eth_miper_zixun_eth		77.92 208	76.69 217	81.61 205	83.00 299	61.98 254	83.15 266	89.20 183	69.52 217	74.86 248	84.35 286	61.76 165	92.56 192	71.50 176	72.89 333	90.28 196

FE-MVS		77.78 211	75.68 229	84.08 126	88.09 184	66.00 174	83.13 267	87.79 223	68.42 244	78.01 169	85.23 270	45.50 325	95.12 82	59.11 287	85.83 168	91.11 161

cl____		77.72 213	76.76 214	80.58 231	82.49 312	60.48 273	83.09 268	87.87 220	69.22 224	74.38 255	85.22 271	62.10 162	91.53 232	71.09 179	75.41 305	89.73 225

DIV-MVS_self_test		77.72 213	76.76 214	80.58 231	82.48 313	60.48 273	83.09 268	87.86 221	69.22 224	74.38 255	85.24 269	62.10 162	91.53 232	71.09 179	75.40 306	89.74 224

thres200		75.55 250	74.47 249	78.82 264	87.78 197	57.85 300	83.07 270	83.51 286	72.44 157	75.84 217	84.42 282	52.08 258	91.75 222	47.41 360	83.64 198	86.86 297

testing3		68.56 318	67.67 319	71.22 345	87.33 214	42.87 393	83.06 271	71.54 375	70.36 196	69.08 312	84.38 284	30.33 382	85.69 317	37.50 387	75.45 304	85.09 329

XVG-OURS		80.41 147	79.23 155	83.97 138	85.64 242	69.02 102	83.03 272	90.39 142	71.09 181	77.63 176	91.49 105	54.62 233	91.35 240	75.71 137	83.47 202	91.54 148

miper_enhance_ethall		77.87 210	76.86 210	80.92 225	81.65 322	61.38 262	82.68 273	88.98 192	65.52 278	75.47 223	82.30 321	65.76 123	92.00 213	72.95 164	76.39 286	89.39 232

mvs_anonymous		79.42 169	79.11 158	80.34 236	84.45 267	57.97 297	82.59 274	87.62 226	67.40 255	76.17 213	88.56 182	68.47 92	89.59 274	70.65 184	86.05 163	93.47 84

baseline2		75.70 248	73.83 258	81.30 213	83.26 290	61.79 258	82.57 275	80.65 322	66.81 256	66.88 331	83.42 305	57.86 208	92.19 207	63.47 246	79.57 248	89.91 216

cascas		76.72 232	74.64 245	82.99 171	85.78 240	65.88 178	82.33 276	89.21 182	60.85 328	72.74 270	81.02 332	47.28 306	93.75 142	67.48 215	85.02 172	89.34 234

WB-MVSnew		71.96 289	71.65 277	72.89 330	84.67 264	51.88 363	82.29 277	77.57 348	62.31 317	73.67 260	83.00 310	53.49 244	81.10 349	45.75 369	82.13 219	85.70 318

RPSCF		73.23 276	71.46 279	78.54 270	82.50 311	59.85 280	82.18 278	82.84 302	58.96 344	71.15 289	89.41 163	45.48 326	84.77 327	58.82 291	71.83 340	91.02 167

thisisatest0515		77.33 222	75.38 237	83.18 161	85.27 249	63.80 221	82.11 279	83.27 290	65.06 281	75.91 215	83.84 296	49.54 288	94.27 115	67.24 218	86.19 160	91.48 152

bld_raw_dy_0_64		82.00 110	81.23 114	84.34 111	88.75 158	66.52 166	81.95 280	91.90 98	63.91 300	75.26 237	90.15 142	69.37 78	95.74 58	77.66 117	92.08 80	90.76 174

pmmvs-eth3d		70.50 302	67.83 315	78.52 272	77.37 364	66.18 171	81.82 281	81.51 314	58.90 345	63.90 357	80.42 339	42.69 340	86.28 312	58.56 293	65.30 366	83.11 351

MS-PatchMatch		73.83 268	72.67 267	77.30 291	83.87 278	66.02 173	81.82 281	84.66 268	61.37 326	68.61 316	82.82 315	47.29 305	88.21 296	59.27 284	84.32 185	77.68 376

pmmvs5		71.55 290	70.20 296	75.61 304	77.83 361	56.39 322	81.74 283	80.89 318	57.76 353	67.46 325	84.49 281	49.26 294	85.32 323	57.08 307	75.29 309	85.11 328

Test_1112_low_res		76.40 239	75.44 234	79.27 257	89.28 137	58.09 293	81.69 284	87.07 238	59.53 339	72.48 275	86.67 234	61.30 176	89.33 278	60.81 275	80.15 243	90.41 190

IterMVS		74.29 261	72.94 266	78.35 274	81.53 325	63.49 229	81.58 285	82.49 304	68.06 248	69.99 301	83.69 301	51.66 267	85.54 319	65.85 230	71.64 341	86.01 313
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		75.43 253	73.87 257	80.11 241	82.69 307	64.85 201	81.57 286	83.47 287	69.16 227	70.49 292	84.15 292	51.95 261	88.15 297	69.23 198	72.14 338	87.34 284

test_vis1_n		69.85 309	69.21 300	71.77 338	72.66 388	55.27 339	81.48 287	76.21 359	52.03 375	75.30 235	83.20 308	28.97 383	76.22 374	74.60 146	78.41 263	83.81 343

pmmvs4		74.03 267	71.91 274	80.39 234	81.96 318	68.32 123	81.45 288	82.14 307	59.32 340	69.87 304	85.13 273	52.40 251	88.13 298	60.21 278	74.74 316	84.73 333

GA-MVS		76.87 229	75.17 241	81.97 198	82.75 305	62.58 246	81.44 289	86.35 250	72.16 163	74.74 249	82.89 313	46.20 317	92.02 212	68.85 204	81.09 230	91.30 157

UWE-MVS		72.13 287	71.49 278	74.03 321	86.66 228	47.70 379	81.40 290	76.89 356	63.60 302	75.59 220	84.22 290	39.94 355	85.62 318	48.98 350	86.13 162	88.77 256

test_fmvs1_n		70.86 297	70.24 295	72.73 332	72.51 389	55.28 338	81.27 291	79.71 335	51.49 378	78.73 148	84.87 277	27.54 385	77.02 366	76.06 133	79.97 246	85.88 316

testing91		76.54 233	75.66 231	79.18 260	88.43 171	55.89 330	81.08 292	83.00 297	73.76 131	75.34 230	84.29 287	46.20 317	90.07 265	64.33 241	84.50 179	91.58 147

testing222		74.04 265	72.66 268	78.19 276	87.89 190	55.36 336	81.06 293	79.20 340	71.30 176	74.65 251	83.57 303	39.11 359	88.67 291	51.43 336	85.75 169	90.53 185

test_fmvs1		70.93 296	70.52 290	72.16 336	73.71 378	55.05 340	80.82 294	78.77 342	51.21 379	78.58 153	84.41 283	31.20 380	76.94 367	75.88 136	80.12 245	84.47 335

CostFormer		75.24 256	73.90 256	79.27 257	82.65 309	58.27 292	80.80 295	82.73 303	61.57 323	75.33 234	83.13 309	55.52 222	91.07 251	64.98 237	78.34 264	88.45 263

testing99		76.09 244	75.12 242	79.00 261	88.16 179	55.50 335	80.79 296	81.40 316	73.30 144	75.17 239	84.27 289	44.48 330	90.02 266	64.28 242	84.22 187	91.48 152

MIMVSNet1		68.58 317	66.78 327	73.98 322	80.07 344	51.82 364	80.77 297	84.37 271	64.40 289	59.75 372	82.16 324	36.47 368	83.63 334	42.73 377	70.33 347	86.48 304

CL-MVSNet_self_test		72.37 284	71.46 279	75.09 310	79.49 354	53.53 352	80.76 298	85.01 266	69.12 228	70.51 291	82.05 325	57.92 207	84.13 330	52.27 331	66.00 364	87.60 277

testing11		75.14 257	74.01 253	78.53 271	88.16 179	56.38 323	80.74 299	80.42 327	70.67 189	72.69 273	83.72 300	43.61 335	89.86 268	62.29 259	83.76 192	89.36 233

MSDG		73.36 274	70.99 286	80.49 233	84.51 266	65.80 180	80.71 300	86.13 253	65.70 275	65.46 345	83.74 299	44.60 328	90.91 253	51.13 337	76.89 277	84.74 332

tpm2		73.26 275	71.46 279	78.63 266	83.34 288	56.71 317	80.65 301	80.40 328	56.63 361	73.55 261	82.02 326	51.80 265	91.24 243	56.35 314	78.42 262	87.95 269

XXY-MVS		75.41 254	75.56 232	74.96 311	83.59 283	57.82 301	80.59 302	83.87 281	66.54 266	74.93 247	88.31 188	63.24 142	80.09 353	62.16 261	76.85 279	86.97 295

test_cas_vis1_n_1920		73.76 269	73.74 259	73.81 323	75.90 368	59.77 281	80.51 303	82.40 305	58.30 349	81.62 115	85.69 258	44.35 331	76.41 372	76.29 130	78.61 257	85.23 324

EGC-MVSNET		52.07 361	47.05 365	67.14 362	83.51 285	60.71 269	80.50 304	67.75 385	0.07 411	0.43 412	75.85 373	24.26 390	81.54 346	28.82 394	62.25 371	59.16 394

SDMVSNet		80.38 148	80.18 135	80.99 222	89.03 148	64.94 199	80.45 305	89.40 172	75.19 100	76.61 201	89.98 143	60.61 190	87.69 303	76.83 127	83.55 199	90.33 193

HyFIR lowres test		77.53 218	75.40 236	83.94 140	89.59 119	66.62 162	80.36 306	88.64 206	56.29 363	76.45 203	85.17 272	57.64 210	93.28 161	61.34 271	83.10 208	91.91 140

D2MVS		74.82 258	73.21 263	79.64 252	79.81 348	62.56 247	80.34 307	87.35 232	64.37 290	68.86 313	82.66 317	46.37 313	90.10 264	67.91 211	81.24 228	86.25 306

TinyColmap		67.30 327	64.81 332	74.76 314	81.92 320	56.68 318	80.29 308	81.49 315	60.33 330	56.27 383	83.22 306	24.77 389	87.66 304	45.52 370	69.47 350	79.95 371

LCM-MVSNet-Re		77.05 225	76.94 209	77.36 289	87.20 217	51.60 366	80.06 309	80.46 326	75.20 99	67.69 322	86.72 229	62.48 154	88.98 285	63.44 247	89.25 118	91.51 149

test_fmvs2		68.35 321	67.48 322	70.98 347	69.50 392	51.95 361	80.05 310	76.38 358	49.33 381	74.65 251	84.38 284	23.30 393	75.40 381	74.51 147	75.17 312	85.60 319

FMVSNet5		69.50 310	67.96 311	74.15 320	82.97 302	55.35 337	80.01 311	82.12 308	62.56 315	63.02 359	81.53 328	36.92 367	81.92 344	48.42 352	74.06 321	85.17 327

SCA		74.22 263	72.33 272	79.91 244	84.05 275	62.17 252	79.96 312	79.29 339	66.30 268	72.38 277	80.13 341	51.95 261	88.60 292	59.25 285	77.67 270	88.96 248

tpmrst		72.39 282	72.13 273	73.18 329	80.54 338	49.91 375	79.91 313	79.08 341	63.11 305	71.69 284	79.95 343	55.32 223	82.77 340	65.66 232	73.89 323	86.87 296

PatchmatchNet		73.12 277	71.33 282	78.49 273	83.18 293	60.85 267	79.63 314	78.57 343	64.13 292	71.73 283	79.81 346	51.20 270	85.97 315	57.40 304	76.36 291	88.66 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PatchMatch-RL		72.38 283	70.90 287	76.80 296	88.60 164	67.38 146	79.53 315	76.17 360	62.75 313	69.36 309	82.00 327	45.51 324	84.89 326	53.62 324	80.58 237	78.12 375

CMPMVS	51.72 21	70.19 305	68.16 308	76.28 298	73.15 385	57.55 305	79.47 316	83.92 279	48.02 382	56.48 382	84.81 278	43.13 337	86.42 311	62.67 255	81.81 224	84.89 330
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ETVMVS		72.25 286	71.05 285	75.84 301	87.77 198	51.91 362	79.39 317	74.98 363	69.26 222	73.71 259	82.95 311	40.82 352	86.14 313	46.17 366	84.43 184	89.47 230

GG-mvs-BLEND				75.38 308	81.59 324	55.80 331	79.32 318	69.63 380		67.19 328	73.67 378	43.24 336	88.90 289	50.41 339	84.50 179	81.45 364

LTVRE_ROB	69.57 13	76.25 241	74.54 248	81.41 209	88.60 164	64.38 212	79.24 319	89.12 188	70.76 188	69.79 306	87.86 200	49.09 296	93.20 169	56.21 315	80.16 242	86.65 302
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		72.37 284	71.71 276	74.35 318	82.19 316	52.00 360	79.22 320	77.29 352	64.56 287	72.95 269	83.68 302	51.35 268	83.26 338	58.33 296	75.80 295	87.81 273

ppachtmachnet_test		70.04 306	67.34 323	78.14 277	79.80 349	61.13 263	79.19 321	80.59 323	59.16 342	65.27 347	79.29 349	46.75 311	87.29 305	49.33 348	66.72 359	86.00 315

USDC		70.33 303	68.37 305	76.21 299	80.60 337	56.23 326	79.19 321	86.49 246	60.89 327	61.29 365	85.47 265	31.78 378	89.47 277	53.37 326	76.21 292	82.94 355

sd_testset		77.70 215	77.40 199	78.60 268	89.03 148	60.02 279	79.00 323	85.83 257	75.19 100	76.61 201	89.98 143	54.81 226	85.46 321	62.63 256	83.55 199	90.33 193

PM-MVS		66.41 333	64.14 335	73.20 328	73.92 377	56.45 320	78.97 324	64.96 392	63.88 301	64.72 351	80.24 340	19.84 396	83.44 336	66.24 224	64.52 368	79.71 372

tpmvs		71.09 294	69.29 299	76.49 297	82.04 317	56.04 328	78.92 325	81.37 317	64.05 296	67.18 329	78.28 358	49.74 287	89.77 270	49.67 347	72.37 335	83.67 345

test_post1							78.90 326				5.43 410	48.81 301	85.44 322	59.25 285

mamv4		76.81 230	78.23 178	72.54 334	86.12 235	65.75 183	78.76 327	82.07 309	64.12 293	72.97 268	91.02 123	67.97 96	68.08 396	83.04 66	78.02 266	83.80 344

CHOSEN 1792x2688		77.63 217	75.69 228	83.44 149	89.98 111	68.58 119	78.70 328	87.50 229	56.38 362	75.80 218	86.84 225	58.67 201	91.40 239	61.58 268	85.75 169	90.34 192

Syy-MVS		68.05 322	67.85 313	68.67 358	84.68 261	40.97 399	78.62 329	73.08 372	66.65 263	66.74 334	79.46 347	52.11 257	82.30 342	32.89 391	76.38 289	82.75 356

myMVS_eth3d		67.02 328	66.29 329	69.21 353	84.68 261	42.58 394	78.62 329	73.08 372	66.65 263	66.74 334	79.46 347	31.53 379	82.30 342	39.43 384	76.38 289	82.75 356

test-LLR		72.94 280	72.43 270	74.48 316	81.35 329	58.04 295	78.38 331	77.46 349	66.66 260	69.95 302	79.00 352	48.06 302	79.24 355	66.13 225	84.83 174	86.15 309

TESTMET0.1,1		69.89 308	69.00 302	72.55 333	79.27 357	56.85 313	78.38 331	74.71 367	57.64 354	68.09 319	77.19 365	37.75 365	76.70 368	63.92 244	84.09 188	84.10 340

test-mter		71.41 291	70.39 294	74.48 316	81.35 329	58.04 295	78.38 331	77.46 349	60.32 331	69.95 302	79.00 352	36.08 370	79.24 355	66.13 225	84.83 174	86.15 309

Anonymous20231206		68.60 316	67.80 316	71.02 346	80.23 342	50.75 372	78.30 334	80.47 325	56.79 360	66.11 343	82.63 318	46.35 314	78.95 357	43.62 375	75.70 296	83.36 348

tpm cat1		70.57 300	68.31 306	77.35 290	82.41 314	57.95 298	78.08 335	80.22 331	52.04 374	68.54 317	77.66 363	52.00 260	87.84 301	51.77 332	72.07 339	86.25 306

our_test_3		69.14 312	67.00 325	75.57 305	79.80 349	58.80 287	77.96 336	77.81 346	59.55 338	62.90 362	78.25 359	47.43 304	83.97 331	51.71 333	67.58 358	83.93 342

KD-MVS_self_test		68.81 314	67.59 321	72.46 335	74.29 376	45.45 384	77.93 337	87.00 239	63.12 304	63.99 356	78.99 354	42.32 342	84.77 327	56.55 313	64.09 369	87.16 290

WTY-MVS		75.65 249	75.68 229	75.57 305	86.40 231	56.82 314	77.92 338	82.40 305	65.10 280	76.18 211	87.72 201	63.13 148	80.90 350	60.31 277	81.96 221	89.00 246

test20.03		67.45 325	66.95 326	68.94 354	75.48 372	44.84 389	77.50 339	77.67 347	66.66 260	63.01 360	83.80 297	47.02 308	78.40 359	42.53 378	68.86 355	83.58 346

EPMVS		69.02 313	68.16 308	71.59 339	79.61 352	49.80 377	77.40 340	66.93 386	62.82 312	70.01 299	79.05 350	45.79 321	77.86 363	56.58 312	75.26 310	87.13 291

test_fmvs3		63.36 344	61.82 347	67.98 360	62.51 400	46.96 383	77.37 341	74.03 369	45.24 385	67.50 324	78.79 355	12.16 404	72.98 389	72.77 167	66.02 363	83.99 341

gg-mvs-nofinetune		69.95 307	67.96 311	75.94 300	83.07 296	54.51 346	77.23 342	70.29 378	63.11 305	70.32 294	62.33 389	43.62 334	88.69 290	53.88 323	87.76 137	84.62 334

MDTV_nov1_ep13			69.97 297		83.18 293	53.48 353	77.10 343	80.18 332	60.45 329	69.33 310	80.44 338	48.89 300	86.90 307	51.60 334	78.51 260

LF4IMVS		64.02 342	62.19 346	69.50 352	70.90 390	53.29 357	76.13 344	77.18 353	52.65 373	58.59 374	80.98 333	23.55 392	76.52 370	53.06 328	66.66 360	78.68 374

sss		73.60 270	73.64 260	73.51 325	82.80 304	55.01 341	76.12 345	81.69 313	62.47 316	74.68 250	85.85 256	57.32 214	78.11 361	60.86 274	80.93 231	87.39 282

testgi		66.67 331	66.53 328	67.08 363	75.62 371	41.69 398	75.93 346	76.50 357	66.11 269	65.20 350	86.59 237	35.72 371	74.71 383	43.71 374	73.38 330	84.84 331

CR-MVSNet		73.37 272	71.27 283	79.67 251	81.32 331	65.19 193	75.92 347	80.30 329	59.92 335	72.73 271	81.19 329	52.50 249	86.69 308	59.84 280	77.71 268	87.11 292

RPMNet		73.51 271	70.49 291	82.58 188	81.32 331	65.19 193	75.92 347	92.27 79	57.60 355	72.73 271	76.45 368	52.30 252	95.43 68	48.14 357	77.71 268	87.11 292

MIMVSNet		70.69 299	69.30 298	74.88 312	84.52 265	56.35 325	75.87 349	79.42 337	64.59 286	67.76 320	82.41 319	41.10 349	81.54 346	46.64 364	81.34 226	86.75 300

test0.0.03 1		68.00 323	67.69 318	68.90 355	77.55 362	47.43 380	75.70 350	72.95 374	66.66 260	66.56 336	82.29 322	48.06 302	75.87 376	44.97 373	74.51 318	83.41 347

dmvs_re		71.14 293	70.58 289	72.80 331	81.96 318	59.68 282	75.60 351	79.34 338	68.55 240	69.27 311	80.72 337	49.42 290	76.54 369	52.56 330	77.79 267	82.19 360

dmvs_testset		62.63 345	64.11 336	58.19 373	78.55 359	24.76 411	75.28 352	65.94 389	67.91 249	60.34 368	76.01 370	53.56 242	73.94 387	31.79 392	67.65 357	75.88 380

PMMVS		69.34 311	68.67 303	71.35 343	75.67 370	62.03 253	75.17 353	73.46 370	50.00 380	68.68 314	79.05 350	52.07 259	78.13 360	61.16 272	82.77 211	73.90 382

UnsupCasMVSNet_eth		67.33 326	65.99 330	71.37 341	73.48 381	51.47 368	75.16 354	85.19 263	65.20 279	60.78 367	80.93 336	42.35 341	77.20 365	57.12 306	53.69 387	85.44 321

MDTV_nov1_ep13_2view						37.79 401	75.16 354		55.10 366	66.53 337		49.34 292		53.98 322		87.94 270

pmmvs3		57.79 351	54.26 356	68.37 359	64.02 399	56.72 316	75.12 356	65.17 390	40.20 391	52.93 387	69.86 386	20.36 395	75.48 379	45.45 371	55.25 386	72.90 384

dp		66.80 329	65.43 331	70.90 348	79.74 351	48.82 378	75.12 356	74.77 365	59.61 337	64.08 355	77.23 364	42.89 338	80.72 351	48.86 351	66.58 361	83.16 350

Patchmtry		70.74 298	69.16 301	75.49 307	80.72 335	54.07 349	74.94 358	80.30 329	58.34 348	70.01 299	81.19 329	52.50 249	86.54 309	53.37 326	71.09 345	85.87 317

PVSNet	64.34 18	72.08 288	70.87 288	75.69 303	86.21 233	56.44 321	74.37 359	80.73 321	62.06 321	70.17 297	82.23 323	42.86 339	83.31 337	54.77 319	84.45 183	87.32 285

WB-MVS		54.94 353	54.72 355	55.60 379	73.50 380	20.90 413	74.27 360	61.19 396	59.16 342	50.61 389	74.15 376	47.19 307	75.78 377	17.31 404	35.07 398	70.12 386

MDA-MVSNet-bldmvs		66.68 330	63.66 339	75.75 302	79.28 356	60.56 272	73.92 361	78.35 344	64.43 288	50.13 390	79.87 345	44.02 333	83.67 333	46.10 367	56.86 380	83.03 353

SSC-MVS		53.88 356	53.59 357	54.75 381	72.87 386	19.59 414	73.84 362	60.53 398	57.58 356	49.18 392	73.45 379	46.34 315	75.47 380	16.20 407	32.28 400	69.20 387

UnsupCasMVSNet_bld		63.70 343	61.53 349	70.21 350	73.69 379	51.39 369	72.82 363	81.89 310	55.63 365	57.81 378	71.80 382	38.67 360	78.61 358	49.26 349	52.21 389	80.63 368

PatchT		68.46 320	67.85 313	70.29 349	80.70 336	43.93 391	72.47 364	74.88 364	60.15 333	70.55 290	76.57 367	49.94 284	81.59 345	50.58 338	74.83 315	85.34 322

miper_lstm_enhance		74.11 264	73.11 265	77.13 293	80.11 343	59.62 283	72.23 365	86.92 241	66.76 258	70.40 293	82.92 312	56.93 218	82.92 339	69.06 201	72.63 334	88.87 251

MVS-HIRNet		59.14 350	57.67 353	63.57 367	81.65 322	43.50 392	71.73 366	65.06 391	39.59 393	51.43 388	57.73 395	38.34 362	82.58 341	39.53 382	73.95 322	64.62 391

APD_test1		53.31 358	49.93 363	63.42 368	65.68 396	50.13 374	71.59 367	66.90 387	34.43 398	40.58 397	71.56 383	8.65 409	76.27 373	34.64 390	55.36 385	63.86 392

Patchmatch-RL test		70.24 304	67.78 317	77.61 286	77.43 363	59.57 285	71.16 368	70.33 377	62.94 309	68.65 315	72.77 380	50.62 276	85.49 320	69.58 196	66.58 361	87.77 274

test123		6.12 380	8.11 383	0.14 394	0.06 418	0.09 419	71.05 369	0.03 419	0.04 413	0.25 414	1.30 413	0.05 417	0.03 414	0.21 413	0.01 412	0.29 409

ANet_high		50.57 363	46.10 367	63.99 366	48.67 411	39.13 400	70.99 370	80.85 319	61.39 325	31.18 400	57.70 396	17.02 399	73.65 388	31.22 393	15.89 408	79.18 373

KD-MVS_2432*1600		66.22 335	63.89 337	73.21 326	75.47 373	53.42 354	70.76 371	84.35 272	64.10 294	66.52 338	78.52 356	34.55 373	84.98 324	50.40 340	50.33 391	81.23 365

miper_refine_blended		66.22 335	63.89 337	73.21 326	75.47 373	53.42 354	70.76 371	84.35 272	64.10 294	66.52 338	78.52 356	34.55 373	84.98 324	50.40 340	50.33 391	81.23 365

test_vis1_rt		60.28 349	58.42 352	65.84 364	67.25 395	55.60 334	70.44 373	60.94 397	44.33 387	59.00 373	66.64 387	24.91 388	68.67 394	62.80 251	69.48 349	73.25 383

testmvs		6.04 381	8.02 384	0.10 395	0.08 417	0.03 420	69.74 374	0.04 418	0.05 412	0.31 413	1.68 412	0.02 418	0.04 413	0.24 412	0.02 411	0.25 410

N_pmnet		52.79 359	53.26 358	51.40 383	78.99 358	7.68 417	69.52 375	3.89 416	51.63 377	57.01 380	74.98 375	40.83 351	65.96 398	37.78 386	64.67 367	80.56 370

FPMVS		53.68 357	51.64 359	59.81 372	65.08 397	51.03 370	69.48 376	69.58 381	41.46 390	40.67 396	72.32 381	16.46 400	70.00 393	24.24 400	65.42 365	58.40 396

DSMNet-mixed		57.77 352	56.90 354	60.38 371	67.70 394	35.61 402	69.18 377	53.97 403	32.30 401	57.49 379	79.88 344	40.39 354	68.57 395	38.78 385	72.37 335	76.97 377

new-patchmatchnet		61.73 347	61.73 348	61.70 369	72.74 387	24.50 412	69.16 378	78.03 345	61.40 324	56.72 381	75.53 374	38.42 361	76.48 371	45.95 368	57.67 379	84.13 339

YYNet1		65.03 338	62.91 343	71.38 340	75.85 369	56.60 319	69.12 379	74.66 368	57.28 358	54.12 385	77.87 361	45.85 320	74.48 384	49.95 345	61.52 374	83.05 352

MDA-MVSNet_test_wron		65.03 338	62.92 342	71.37 341	75.93 367	56.73 315	69.09 380	74.73 366	57.28 358	54.03 386	77.89 360	45.88 319	74.39 385	49.89 346	61.55 373	82.99 354

PVSNet_0	57.27 20	61.67 348	59.27 351	68.85 356	79.61 352	57.44 307	68.01 381	73.44 371	55.93 364	58.54 375	70.41 385	44.58 329	77.55 364	47.01 361	35.91 397	71.55 385

dongtai		45.42 367	45.38 368	45.55 385	73.36 383	26.85 409	67.72 382	34.19 411	54.15 369	49.65 391	56.41 398	25.43 387	62.94 401	19.45 402	28.09 402	46.86 401

ADS-MVSNet2		66.20 337	63.33 340	74.82 313	79.92 345	58.75 288	67.55 383	75.19 362	53.37 371	65.25 348	75.86 371	42.32 342	80.53 352	41.57 379	68.91 353	85.18 325

ADS-MVSNet		64.36 341	62.88 344	68.78 357	79.92 345	47.17 381	67.55 383	71.18 376	53.37 371	65.25 348	75.86 371	42.32 342	73.99 386	41.57 379	68.91 353	85.18 325

mvsany_test1		62.30 346	61.26 350	65.41 365	69.52 391	54.86 342	66.86 385	49.78 405	46.65 383	68.50 318	83.21 307	49.15 295	66.28 397	56.93 309	60.77 375	75.11 381

LCM-MVSNet		54.25 354	49.68 364	67.97 361	53.73 408	45.28 387	66.85 386	80.78 320	35.96 397	39.45 398	62.23 391	8.70 408	78.06 362	48.24 356	51.20 390	80.57 369

test_vis3_rt		49.26 364	47.02 366	56.00 376	54.30 405	45.27 388	66.76 387	48.08 406	36.83 395	44.38 394	53.20 399	7.17 411	64.07 399	56.77 311	55.66 383	58.65 395

testf1		45.72 365	41.96 369	57.00 374	56.90 402	45.32 385	66.14 388	59.26 399	26.19 402	30.89 401	60.96 393	4.14 412	70.64 391	26.39 398	46.73 395	55.04 397

APD_test2		45.72 365	41.96 369	57.00 374	56.90 402	45.32 385	66.14 388	59.26 399	26.19 402	30.89 401	60.96 393	4.14 412	70.64 391	26.39 398	46.73 395	55.04 397

kuosan		39.70 371	40.40 372	37.58 388	64.52 398	26.98 407	65.62 390	33.02 412	46.12 384	42.79 395	48.99 401	24.10 391	46.56 409	12.16 410	26.30 403	39.20 402

JIA-IIPM		66.32 334	62.82 345	76.82 295	77.09 365	61.72 259	65.34 391	75.38 361	58.04 352	64.51 352	62.32 390	42.05 346	86.51 310	51.45 335	69.22 352	82.21 359

PMVS	37.38 22	44.16 369	40.28 373	55.82 378	40.82 413	42.54 396	65.12 392	63.99 393	34.43 398	24.48 404	57.12 397	3.92 414	76.17 375	17.10 405	55.52 384	48.75 399
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		50.91 362	50.29 362	52.78 382	68.58 393	34.94 404	63.71 393	56.63 402	39.73 392	44.95 393	65.47 388	21.93 394	58.48 402	34.98 389	56.62 381	64.92 390

mvsany_test3		53.99 355	51.45 360	61.61 370	55.51 404	44.74 390	63.52 394	45.41 409	43.69 388	58.11 377	76.45 368	17.99 397	63.76 400	54.77 319	47.59 393	76.34 379

Patchmatch-test		64.82 340	63.24 341	69.57 351	79.42 355	49.82 376	63.49 395	69.05 383	51.98 376	59.95 371	80.13 341	50.91 272	70.98 390	40.66 381	73.57 326	87.90 271

ambc				75.24 309	73.16 384	50.51 373	63.05 396	87.47 230		64.28 353	77.81 362	17.80 398	89.73 272	57.88 300	60.64 376	85.49 320

test_f		52.09 360	50.82 361	55.90 377	53.82 407	42.31 397	59.42 397	58.31 401	36.45 396	56.12 384	70.96 384	12.18 403	57.79 403	53.51 325	56.57 382	67.60 388

CHOSEN 280x420		66.51 332	64.71 333	71.90 337	81.45 326	63.52 228	57.98 398	68.95 384	53.57 370	62.59 363	76.70 366	46.22 316	75.29 382	55.25 317	79.68 247	76.88 378

E-PMN		31.77 372	30.64 375	35.15 389	52.87 409	27.67 406	57.09 399	47.86 407	24.64 404	16.40 409	33.05 405	11.23 405	54.90 405	14.46 408	18.15 406	22.87 405

EMVS		30.81 374	29.65 376	34.27 390	50.96 410	25.95 410	56.58 400	46.80 408	24.01 405	15.53 410	30.68 406	12.47 402	54.43 406	12.81 409	17.05 407	22.43 406

PMMVS2		40.82 370	38.86 374	46.69 384	53.84 406	16.45 415	48.61 401	49.92 404	37.49 394	31.67 399	60.97 392	8.14 410	56.42 404	28.42 395	30.72 401	67.19 389

wuyk23d		16.82 378	15.94 381	19.46 392	58.74 401	31.45 405	39.22 402	3.74 417	6.84 408	6.04 411	2.70 411	1.27 416	24.29 411	10.54 411	14.40 410	2.63 408

tmp_tt		18.61 377	21.40 380	10.23 393	4.82 416	10.11 416	34.70 403	30.74 414	1.48 410	23.91 406	26.07 407	28.42 384	13.41 412	27.12 396	15.35 409	7.17 407

Gipuma		45.18 368	41.86 371	55.16 380	77.03 366	51.52 367	32.50 404	80.52 324	32.46 400	27.12 403	35.02 404	9.52 407	75.50 378	22.31 401	60.21 378	38.45 403
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	26.22 23	30.37 375	25.89 379	43.81 386	44.55 412	35.46 403	28.87 405	39.07 410	18.20 406	18.58 408	40.18 403	2.68 415	47.37 408	17.07 406	23.78 405	48.60 400
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		31.52 373	29.28 377	38.23 387	27.03 415	6.50 418	20.94 406	62.21 395	4.05 409	22.35 407	52.50 400	13.33 401	47.58 407	27.04 397	34.04 399	60.62 393

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		19.96 376	26.61 378	0.00 396	0.00 419	0.00 421	0.00 407	89.26 179	0.00 414	0.00 415	88.61 179	61.62 168	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		5.26 382	7.02 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	63.15 145	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		7.23 379	9.64 382	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	86.72 229	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						42.58 394								39.46 383

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 46					97.53 2	89.67 6	96.44 9	94.41 37

PC_three_1452									68.21 246	92.02 12	94.00 46	82.09 5	95.98 53	84.58 49	96.68 2	94.95 10

No_MVS				89.16 1	94.34 27	75.53 2		92.99 46					97.53 2	89.67 6	96.44 9	94.41 37

test_one_0601					95.07 7	71.46 55		94.14 5	78.27 35	92.05 11	95.74 6	80.83 11

eth-test2					0.00 419

eth-test					0.00 419

ZD-MVS					94.38 25	72.22 44		92.67 62	70.98 184	87.75 32	94.07 41	74.01 32	96.70 27	84.66 48	94.84 43

IU-MVS					95.30 2	71.25 57		92.95 52	66.81 256	92.39 6				88.94 16	96.63 4	94.85 19

test_241102_TWO								94.06 10	77.24 50	92.78 4	95.72 8	81.26 8	97.44 6	89.07 14	96.58 6	94.26 46

test_241102_ONE					95.30 2	70.98 63		94.06 10	77.17 53	93.10 1	95.39 11	82.99 1	97.27 11

test_0728_THIRD									78.38 33	92.12 9	95.78 4	81.46 7	97.40 8	89.42 9	96.57 7	94.67 25

GSMVS																88.96 248

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 269				88.96 248

sam_mvs												50.01 282

MTGPA								92.02 90

test_post											5.46 409	50.36 280	84.24 329

patchmatchnet-post											74.00 377	51.12 271	88.60 292

gm-plane-assit					81.40 327	53.83 351			62.72 314		80.94 334		92.39 198	63.40 248

test9_res														84.90 42	95.70 26	92.87 107

agg_prior2														82.91 68	95.45 30	92.70 110

agg_prior					92.85 59	71.94 51		91.78 106		84.41 75			94.93 91

TestCases				79.58 253	85.15 252	63.62 223		79.83 333	62.31 317	60.32 369	86.73 227	32.02 376	88.96 287	50.28 342	71.57 342	86.15 309

test_prior				86.33 54	92.61 65	69.59 88		92.97 51					95.48 65			93.91 58

新几何1				83.42 150	93.13 52	70.71 71		85.48 261	57.43 357	81.80 112	91.98 90	63.28 140	92.27 204	64.60 240	92.99 68	87.27 286

旧先验1					91.96 71	65.79 181		86.37 249			93.08 71	69.31 81			92.74 71	88.74 258

原ACMM1				84.35 110	93.01 57	68.79 107		92.44 72	63.96 299	81.09 122	91.57 102	66.06 118	95.45 66	67.19 219	94.82 45	88.81 254

testdata2													91.01 252	62.37 258

segment_acmp												73.08 38

testdata				79.97 243	90.90 87	64.21 214		84.71 267	59.27 341	85.40 53	92.91 73	62.02 164	89.08 283	68.95 202	91.37 90	86.63 303

test12				86.80 49	92.63 64	70.70 72		91.79 105		82.71 103		71.67 54	96.16 44		94.50 50	93.54 82

plane_prior7					90.08 105	68.51 120

plane_prior6					89.84 114	68.70 115						60.42 193

plane_prior5								92.44 72					95.38 72	78.71 105	86.32 157	91.33 155

plane_prior4											91.00 124

plane_prior3						68.60 118			78.44 31	78.92 146

plane_prior1					89.90 113

n2								0.00 420

nn								0.00 420

door-mid								69.98 379

lessismore_v0				78.97 262	81.01 334	57.15 310		65.99 388		61.16 366	82.82 315	39.12 358	91.34 241	59.67 281	46.92 394	88.43 264

LGP-MVS_train				84.50 103	89.23 139	68.76 109		91.94 96	75.37 96	76.64 199	91.51 103	54.29 235	94.91 92	78.44 108	83.78 190	89.83 220

test11								92.23 82

door								69.44 382

HQP5-MVS						66.98 157

BP-MVS														77.47 119

HQP4-MVS										77.24 184			95.11 84			91.03 165

HQP3-MVS								92.19 85							85.99 165

HQP2-MVS												60.17 196

NP-MVS					89.62 118	68.32 123					90.24 138

ACMMP++_ref															81.95 222

ACMMP++															81.25 227

Test By Simon												64.33 132

ITE_SJBPF				78.22 275	81.77 321	60.57 271		83.30 289	69.25 223	67.54 323	87.20 218	36.33 369	87.28 306	54.34 321	74.62 317	86.80 298

DeepMVS_CX				27.40 391	40.17 414	26.90 408		24.59 415	17.44 407	23.95 405	48.61 402	9.77 406	26.48 410	18.06 403	24.47 404	28.83 404

High-resolution multi-view benchmark