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.

MSP-MVS		90.38 4	91.87 1	85.88 80	92.83 71	64.03 181	93.06 105	94.33 48	82.19 28	93.65 3	96.15 33	85.89 1	97.19 82	91.02 31	97.75 1	96.43 26
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
DPM-MVS		90.70 2	90.52 7	91.24 1	89.68 144	76.68 2	97.29 1	95.35 12	82.87 20	91.58 10	97.22 3	79.93 5	99.10 9	83.12 90	97.64 2	97.94 1

OPU-MVS				89.97 3	97.52 3	73.15 12	96.89 5				97.00 9	83.82 2	99.15 2	95.72 3	97.63 3	97.62 2

DVP-MVS++		90.53 3	91.09 4	88.87 14	97.31 4	69.91 37	93.96 68	94.37 46	72.48 173	92.07 6	96.85 14	83.82 2	99.15 2	91.53 27	97.42 4	97.55 4

PC_three_1452									80.91 45	94.07 2	96.83 16	83.57 4	99.12 5	95.70 5	97.42 4	97.55 4

HPM-MVS++		89.37 13	89.95 12	87.64 30	95.10 30	68.23 77	95.24 33	94.49 38	82.43 25	88.90 30	96.35 25	71.89 33	98.63 26	88.76 45	96.40 6	96.06 36

SMA-MVS		88.14 16	88.29 20	87.67 29	93.21 63	68.72 64	93.85 75	94.03 55	74.18 136	91.74 9	96.67 19	65.61 63	98.42 33	89.24 41	96.08 7	95.88 43
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
DELS-MVS		90.05 6	90.09 10	89.94 4	93.14 66	73.88 7	97.01 4	94.40 44	88.32 3	85.71 50	94.91 66	74.11 19	98.91 17	87.26 57	95.94 8	97.03 10
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
MCST-MVS		91.08 1	91.46 2	89.94 4	97.66 2	73.37 8	97.13 2	95.58 10	89.33 1	85.77 49	96.26 28	72.84 26	99.38 1	92.64 17	95.93 9	97.08 9

CNVR-MVS		90.32 5	90.89 6	88.61 19	96.76 8	70.65 26	96.47 13	94.83 25	84.83 11	89.07 29	96.80 17	70.86 34	99.06 15	92.64 17	95.71 10	96.12 35

PHI-MVS		86.83 34	86.85 37	86.78 55	93.47 57	65.55 144	95.39 30	95.10 18	71.77 199	85.69 51	96.52 21	62.07 108	98.77 22	86.06 68	95.60 11	96.03 38

DeepPCF-MVS	81.17 1	89.72 9	91.38 3	84.72 121	93.00 69	58.16 293	96.72 8	94.41 42	86.50 8	90.25 19	97.83 1	75.46 14	98.67 25	92.78 16	95.49 12	97.32 6

SED-MVS		89.94 8	90.36 9	88.70 16	96.45 12	69.38 47	96.89 5	94.44 40	71.65 202	92.11 4	97.21 4	76.79 9	99.11 6	92.34 19	95.36 13	97.62 2

IU-MVS					96.46 11	69.91 37		95.18 16	80.75 46	95.28 1				92.34 19	95.36 13	96.47 25

test_241102_TWO								94.41 42	71.65 202	92.07 6	97.21 4	74.58 17	99.11 6	92.34 19	95.36 13	96.59 16

MM				88.92 13		71.10 22	97.02 3	96.04 6	88.70 2	91.57 11	96.19 31	70.12 36	98.91 17	96.83 1	95.06 16	96.76 12

test_0728_THIRD									72.48 173	90.55 17	96.93 10	76.24 11	99.08 11	91.53 27	94.99 17	96.43 26

test9_res														89.41 37	94.96 18	95.29 63

ACMMP_NAP		86.05 45	85.80 50	86.80 54	91.58 106	67.53 95	91.79 160	93.49 76	74.93 127	84.61 61	95.30 51	59.42 137	97.92 41	86.13 66	94.92 19	94.94 79

DPE-MVS		88.77 15	89.21 15	87.45 37	96.26 20	67.56 93	94.17 55	94.15 53	68.77 252	90.74 15	97.27 2	76.09 12	98.49 29	90.58 35	94.91 20	96.30 29
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		89.41 12	89.73 13	88.45 22	96.40 15	69.99 33	96.64 9	94.52 36	71.92 189	90.55 17	96.93 10	73.77 21	99.08 11	91.91 25	94.90 21	96.29 30
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				88.70 16	96.45 12	70.43 29	96.64 9	94.37 46					99.15 2	91.91 25	94.90 21	96.51 21

train_agg		87.21 29	87.42 28	86.60 59	94.18 41	67.28 100	94.16 56	93.51 73	71.87 194	85.52 52	95.33 49	68.19 41	97.27 80	89.09 42	94.90 21	95.25 69

DeepC-MVS_fast	79.48 2	87.95 20	88.00 21	87.79 28	95.86 27	68.32 72	95.74 21	94.11 54	83.82 15	83.49 71	96.19 31	64.53 77	98.44 31	83.42 89	94.88 24	96.61 15
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSC_two_6792asdad				89.60 8	97.31 4	73.22 10		95.05 21					99.07 13	92.01 22	94.77 25	96.51 21

No_MVS				89.60 8	97.31 4	73.22 10		95.05 21					99.07 13	92.01 22	94.77 25	96.51 21

TSAR-MVS + MP.		88.11 18	88.64 16	86.54 63	91.73 102	68.04 81	90.36 215	93.55 72	82.89 19	91.29 13	92.89 117	72.27 30	96.03 133	87.99 48	94.77 25	95.54 52
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_prior2							95.10 38		75.40 121	85.25 58	95.61 43	67.94 44		87.47 54	94.77 25

agg_prior2														86.41 64	94.75 29	95.33 59

MVS_0304		90.01 7	90.50 8	88.53 20	90.14 135	70.94 23	96.47 13	95.72 9	87.33 4	89.60 26	96.26 28	68.44 38	98.74 24	95.82 2	94.72 30	95.90 42

MVS		84.66 66	82.86 92	90.06 2	90.93 120	74.56 6	87.91 266	95.54 11	68.55 254	72.35 188	94.71 71	59.78 133	98.90 19	81.29 106	94.69 31	96.74 13

SF-MVS		87.03 31	87.09 31	86.84 51	92.70 77	67.45 98	93.64 87	93.76 62	70.78 226	86.25 43	96.44 24	66.98 50	97.79 47	88.68 46	94.56 32	95.28 65

NCCC		89.07 14	89.46 14	87.91 25	96.60 10	69.05 56	96.38 15	94.64 33	84.42 12	86.74 41	96.20 30	66.56 55	98.76 23	89.03 44	94.56 32	95.92 41

3Dnovator	73.91 6	82.69 105	80.82 120	88.31 23	89.57 146	71.26 18	92.60 126	94.39 45	78.84 75	67.89 245	92.48 127	48.42 250	98.52 28	68.80 204	94.40 34	95.15 71

CDPH-MVS		85.71 51	85.46 53	86.46 65	94.75 34	67.19 102	93.89 73	92.83 101	70.90 222	83.09 74	95.28 52	63.62 89	97.36 71	80.63 109	94.18 35	94.84 83

MG-MVS		87.11 30	86.27 39	89.62 7	97.79 1	76.27 4	94.96 43	94.49 38	78.74 78	83.87 70	92.94 115	64.34 78	96.94 101	75.19 145	94.09 36	95.66 47

9.14			87.63 24		93.86 47		94.41 52	94.18 51	72.76 168	86.21 44	96.51 22	66.64 53	97.88 44	90.08 36	94.04 37

原ACMM1				84.42 134	93.21 63	64.27 177		93.40 81	65.39 278	79.51 106	92.50 124	58.11 150	96.69 110	65.27 241	93.96 38	92.32 165

MSLP-MVS++		86.27 41	85.91 48	87.35 39	92.01 93	68.97 59	95.04 40	92.70 104	79.04 72	81.50 85	96.50 23	58.98 143	96.78 108	83.49 88	93.93 39	96.29 30

CANet		89.61 11	89.99 11	88.46 21	94.39 39	69.71 43	96.53 12	93.78 59	86.89 6	89.68 25	95.78 38	65.94 59	99.10 9	92.99 14	93.91 40	96.58 18

MP-MVS-pluss		85.24 58	85.13 57	85.56 92	91.42 111	65.59 142	91.54 170	92.51 114	74.56 130	80.62 95	95.64 42	59.15 141	97.00 92	86.94 61	93.80 41	94.07 113
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MVP-Stereo		77.12 199	76.23 192	79.79 253	81.72 289	66.34 125	89.29 242	90.88 182	70.56 230	62.01 299	82.88 259	49.34 241	94.13 208	65.55 238	93.80 41	78.88 354
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
GG-mvs-BLEND				86.53 64	91.91 98	69.67 45	75.02 354	94.75 28		78.67 120	90.85 154	77.91 7	94.56 192	72.25 169	93.74 43	95.36 58

ZNCC-MVS		85.33 57	85.08 58	86.06 75	93.09 68	65.65 140	93.89 73	93.41 80	73.75 147	79.94 101	94.68 72	60.61 124	98.03 38	82.63 93	93.72 44	94.52 96

CSCG		86.87 32	86.26 40	88.72 15	95.05 31	70.79 25	93.83 80	95.33 13	68.48 256	77.63 128	94.35 84	73.04 24	98.45 30	84.92 77	93.71 45	96.92 11

test12				87.09 45	94.60 36	68.86 60		92.91 98		82.67 79		65.44 64	97.55 62		93.69 46	94.84 83

PAPM		85.89 48	85.46 53	87.18 42	88.20 186	72.42 13	92.41 133	92.77 102	82.11 29	80.34 97	93.07 112	68.27 40	95.02 170	78.39 128	93.59 47	94.09 111

SteuartSystems-ACMMP		86.82 35	86.90 35	86.58 61	90.42 129	66.38 123	96.09 17	93.87 57	77.73 90	84.01 69	95.66 41	63.39 93	97.94 40	87.40 55	93.55 48	95.42 53
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		87.54 25	87.84 22	86.65 58	96.07 23	66.30 126	94.84 45	93.78 59	69.35 243	88.39 31	96.34 26	67.74 46	97.66 54	90.62 34	93.44 49	96.01 39
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CS-MVS-test		86.14 44	87.01 32	83.52 159	92.63 80	59.36 281	95.49 27	91.92 134	80.09 51	85.46 54	95.53 45	61.82 113	95.77 141	86.77 63	93.37 50	95.41 54

PS-MVSNAJ		88.14 16	87.61 25	89.71 6	92.06 90	76.72 1	95.75 20	93.26 83	83.86 14	89.55 27	96.06 34	53.55 204	97.89 43	91.10 29	93.31 51	94.54 94

MAR-MVS		84.18 76	83.43 78	86.44 66	96.25 21	65.93 135	94.28 53	94.27 50	74.41 131	79.16 111	95.61 43	53.99 199	98.88 21	69.62 194	93.26 52	94.50 98
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
gg-mvs-nofinetune		77.18 198	74.31 218	85.80 85	91.42 111	68.36 71	71.78 357	94.72 29	49.61 358	77.12 135	45.92 381	77.41 8	93.98 220	67.62 214	93.16 53	95.05 74

ZD-MVS					96.63 9	65.50 146		93.50 75	70.74 227	85.26 57	95.19 59	64.92 71	97.29 76	87.51 53	93.01 54

APD-MVS		85.93 47	85.99 46	85.76 87	95.98 26	65.21 151	93.59 90	92.58 112	66.54 270	86.17 45	95.88 37	63.83 84	97.00 92	86.39 65	92.94 55	95.06 73
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
新几何1				84.73 120	92.32 84	64.28 176		91.46 159	59.56 325	79.77 103	92.90 116	56.95 164	96.57 114	63.40 251	92.91 56	93.34 135

DeepC-MVS	77.85 3	85.52 55	85.24 55	86.37 69	88.80 168	66.64 117	92.15 140	93.68 67	81.07 43	76.91 138	93.64 102	62.59 103	98.44 31	85.50 70	92.84 57	94.03 115
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
xiu_mvs_v2_base		87.92 21	87.38 29	89.55 11	91.41 113	76.43 3	95.74 21	93.12 91	83.53 17	89.55 27	95.95 36	53.45 208	97.68 50	91.07 30	92.62 58	94.54 94

MP-MVS		85.02 60	84.97 60	85.17 105	92.60 81	64.27 177	93.24 100	92.27 119	73.13 158	79.63 105	94.43 78	61.90 109	97.17 83	85.00 75	92.56 59	94.06 114
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		83.91 81	83.38 82	85.50 93	91.89 99	65.16 153	81.75 315	92.23 120	75.32 122	80.53 96	95.21 58	56.06 176	97.16 84	84.86 78	92.55 60	94.18 105

GST-MVS		84.63 67	84.29 67	85.66 90	92.82 73	65.27 149	93.04 107	93.13 90	73.20 156	78.89 113	94.18 91	59.41 138	97.85 45	81.45 102	92.48 61	93.86 123

HFP-MVS		84.73 65	84.40 66	85.72 88	93.75 51	65.01 157	93.50 94	93.19 87	72.19 183	79.22 110	94.93 64	59.04 142	97.67 51	81.55 100	92.21 62	94.49 99

ACMMPR		84.37 69	84.06 68	85.28 100	93.56 54	64.37 173	93.50 94	93.15 89	72.19 183	78.85 118	94.86 67	56.69 168	97.45 65	81.55 100	92.20 63	94.02 116

MS-PatchMatch		77.90 190	76.50 188	82.12 197	85.99 229	69.95 36	91.75 165	92.70 104	73.97 141	62.58 296	84.44 244	41.11 293	95.78 139	63.76 250	92.17 64	80.62 340

region2R		84.36 70	84.03 69	85.36 98	93.54 55	64.31 175	93.43 97	92.95 97	72.16 186	78.86 117	94.84 68	56.97 163	97.53 63	81.38 104	92.11 65	94.24 103

CS-MVS		85.80 49	86.65 38	83.27 167	92.00 94	58.92 286	95.31 31	91.86 139	79.97 52	84.82 60	95.40 47	62.26 106	95.51 159	86.11 67	92.08 66	95.37 57

patch_mono-2		89.71 10	90.99 5	85.85 83	96.04 24	63.70 191	95.04 40	95.19 15	86.74 7	91.53 12	95.15 60	73.86 20	97.58 59	93.38 12	92.00 67	96.28 32

dcpmvs_2		87.37 27	87.55 26	86.85 50	95.04 32	68.20 78	90.36 215	90.66 188	79.37 62	81.20 87	93.67 101	74.73 15	96.55 116	90.88 32	92.00 67	95.82 44

旧先验1					91.94 95	60.74 258		91.50 157			94.36 80	65.23 66			91.84 69	94.55 92

MVSFormer		83.75 86	82.88 91	86.37 69	89.24 158	71.18 19	89.07 248	90.69 185	65.80 275	87.13 37	94.34 85	64.99 68	92.67 257	72.83 161	91.80 70	95.27 66

lupinMVS		87.74 23	87.77 23	87.63 34	89.24 158	71.18 19	96.57 11	92.90 99	82.70 23	87.13 37	95.27 54	64.99 68	95.80 138	89.34 39	91.80 70	95.93 40

EPNet		87.84 22	88.38 18	86.23 73	93.30 60	66.05 130	95.26 32	94.84 24	87.09 5	88.06 32	94.53 75	66.79 52	97.34 73	83.89 86	91.68 72	95.29 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
3Dnovator+	73.60 7	82.10 114	80.60 126	86.60 59	90.89 122	66.80 114	95.20 34	93.44 78	74.05 138	67.42 251	92.49 126	49.46 240	97.65 55	70.80 182	91.68 72	95.33 59

XVS		83.87 82	83.47 76	85.05 106	93.22 61	63.78 185	92.92 112	92.66 107	73.99 139	78.18 122	94.31 87	55.25 182	97.41 68	79.16 119	91.58 74	93.95 118

X-MVStestdata		76.86 202	74.13 222	85.05 106	93.22 61	63.78 185	92.92 112	92.66 107	73.99 139	78.18 122	10.19 396	55.25 182	97.41 68	79.16 119	91.58 74	93.95 118

SD-MVS		87.49 26	87.49 27	87.50 36	93.60 53	68.82 62	93.90 72	92.63 110	76.86 102	87.90 33	95.76 39	66.17 56	97.63 56	89.06 43	91.48 76	96.05 37
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
EC-MVSNet		84.53 68	85.04 59	83.01 171	89.34 151	61.37 245	94.42 51	91.09 174	77.91 87	83.24 72	94.20 90	58.37 146	95.40 160	85.35 71	91.41 77	92.27 170

PGM-MVS		83.25 94	82.70 95	84.92 110	92.81 75	64.07 180	90.44 211	92.20 124	71.28 214	77.23 134	94.43 78	55.17 186	97.31 75	79.33 118	91.38 78	93.37 134

PVSNet_Blended		86.73 36	86.86 36	86.31 72	93.76 49	67.53 95	96.33 16	93.61 69	82.34 27	81.00 92	93.08 111	63.19 97	97.29 76	87.08 59	91.38 78	94.13 109

HPM-MVS		83.25 94	82.95 89	84.17 144	92.25 86	62.88 216	90.91 196	91.86 139	70.30 232	77.12 135	93.96 96	56.75 166	96.28 121	82.04 97	91.34 80	93.34 135
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EIA-MVS		84.84 63	84.88 61	84.69 123	91.30 114	62.36 224	93.85 75	92.04 129	79.45 59	79.33 109	94.28 88	62.42 104	96.35 119	80.05 112	91.25 81	95.38 56

MVS_111021_HR		86.19 43	85.80 50	87.37 38	93.17 65	69.79 40	93.99 67	93.76 62	79.08 70	78.88 116	93.99 95	62.25 107	98.15 36	85.93 69	91.15 82	94.15 108

test222					89.77 142	61.60 241	89.55 236	89.42 236	56.83 338	77.28 133	92.43 128	52.76 212			91.14 83	93.09 143

jason		86.40 38	86.17 42	87.11 44	86.16 227	70.54 28	95.71 24	92.19 125	82.00 30	84.58 62	94.34 85	61.86 110	95.53 158	87.76 50	90.89 84	95.27 66
jason: jason.
mPP-MVS		82.96 100	82.44 100	84.52 131	92.83 71	62.92 214	92.76 116	91.85 141	71.52 210	75.61 150	94.24 89	53.48 207	96.99 95	78.97 122	90.73 85	93.64 129

CP-MVS		83.71 87	83.40 81	84.65 125	93.14 66	63.84 183	94.59 49	92.28 118	71.03 220	77.41 131	94.92 65	55.21 185	96.19 123	81.32 105	90.70 86	93.91 120

OpenMVS	70.45 11	78.54 178	75.92 196	86.41 68	85.93 233	71.68 16	92.74 117	92.51 114	66.49 271	64.56 275	91.96 136	43.88 283	98.10 37	54.61 293	90.65 87	89.44 216

PAPM_NR		82.97 99	81.84 107	86.37 69	94.10 44	66.76 115	87.66 271	92.84 100	69.96 236	74.07 166	93.57 104	63.10 99	97.50 64	70.66 185	90.58 88	94.85 80

testdata				81.34 214	89.02 162	57.72 298		89.84 220	58.65 329	85.32 56	94.09 92	57.03 159	93.28 236	69.34 197	90.56 89	93.03 146

Vis-MVSNet		80.92 133	79.98 135	83.74 152	88.48 173	61.80 235	93.44 96	88.26 284	73.96 142	77.73 126	91.76 139	49.94 236	94.76 178	65.84 233	90.37 90	94.65 90
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		84.98 62	83.45 77	89.57 10	89.94 139	75.14 5	92.07 146	92.32 117	81.87 31	75.68 147	88.27 192	60.18 127	98.60 27	80.46 111	90.27 91	94.96 77

test_fmvsm_n_1920		87.69 24	88.50 17	85.27 101	87.05 213	63.55 198	93.69 85	91.08 176	84.18 13	90.17 21	97.04 8	67.58 47	97.99 39	95.72 3	90.03 92	94.26 102

ETV-MVS		86.01 46	86.11 43	85.70 89	90.21 134	67.02 109	93.43 97	91.92 134	81.21 42	84.13 68	94.07 94	60.93 121	95.63 149	89.28 40	89.81 93	94.46 100

QAPM		79.95 151	77.39 177	87.64 30	89.63 145	71.41 17	93.30 99	93.70 66	65.34 280	67.39 253	91.75 140	47.83 257	98.96 16	57.71 284	89.81 93	92.54 159

CANet_DTU		84.09 78	83.52 72	85.81 84	90.30 132	66.82 112	91.87 156	89.01 256	85.27 9	86.09 46	93.74 99	47.71 259	96.98 96	77.90 131	89.78 95	93.65 128

API-MVS		82.28 109	80.53 127	87.54 35	96.13 22	70.59 27	93.63 88	91.04 180	65.72 277	75.45 152	92.83 120	56.11 175	98.89 20	64.10 247	89.75 96	93.15 141

test2506		83.29 92	82.92 90	84.37 137	88.39 178	63.18 207	92.01 149	91.35 162	77.66 92	78.49 121	91.42 145	64.58 76	95.09 169	73.19 157	89.23 97	94.85 80

ECVR-MVS		81.29 125	80.38 130	84.01 148	88.39 178	61.96 233	92.56 131	86.79 301	77.66 92	76.63 139	91.42 145	46.34 268	95.24 167	74.36 154	89.23 97	94.85 80

MVS_Test		84.16 77	83.20 84	87.05 47	91.56 107	69.82 39	89.99 229	92.05 128	77.77 89	82.84 75	86.57 219	63.93 83	96.09 127	74.91 150	89.18 99	95.25 69

PAPR		85.15 59	84.47 64	87.18 42	96.02 25	68.29 73	91.85 158	93.00 96	76.59 109	79.03 112	95.00 61	61.59 114	97.61 58	78.16 129	89.00 100	95.63 48

TSAR-MVS + GP.		87.96 19	88.37 19	86.70 57	93.51 56	65.32 148	95.15 36	93.84 58	78.17 83	85.93 48	94.80 69	75.80 13	98.21 34	89.38 38	88.78 101	96.59 16

SR-MVS		82.81 101	82.58 97	83.50 162	93.35 58	61.16 248	92.23 138	91.28 166	64.48 284	81.27 86	95.28 52	53.71 203	95.86 137	82.87 91	88.77 102	93.49 132

test1111		80.84 134	80.02 132	83.33 165	87.87 194	60.76 256	92.62 125	86.86 300	77.86 88	75.73 146	91.39 147	46.35 267	94.70 184	72.79 163	88.68 103	94.52 96

HPM-MVS_fast		80.25 144	79.55 143	82.33 187	91.55 108	59.95 271	91.32 184	89.16 247	65.23 281	74.71 159	93.07 112	47.81 258	95.74 142	74.87 152	88.23 104	91.31 188

PVSNet_Blended_VisFu		83.97 80	83.50 74	85.39 97	90.02 137	66.59 120	93.77 82	91.73 145	77.43 98	77.08 137	89.81 174	63.77 86	96.97 98	79.67 114	88.21 105	92.60 157

Vis-MVSNet (Re-imp)		79.24 161	79.57 140	78.24 276	88.46 174	52.29 332	90.41 213	89.12 250	74.24 135	69.13 222	91.91 137	65.77 61	90.09 308	59.00 280	88.09 106	92.33 164

APD-MVS_3200maxsize		81.64 121	81.32 112	82.59 181	92.36 83	58.74 288	91.39 177	91.01 181	63.35 293	79.72 104	94.62 74	51.82 218	96.14 125	79.71 113	87.93 107	92.89 152

Effi-MVS+		83.82 83	82.76 93	86.99 49	89.56 147	69.40 46	91.35 182	86.12 308	72.59 170	83.22 73	92.81 121	59.60 135	96.01 135	81.76 99	87.80 108	95.56 51

casdiffmvs_mvg		85.66 53	85.18 56	87.09 45	88.22 185	69.35 50	93.74 84	91.89 137	81.47 35	80.10 99	91.45 144	64.80 73	96.35 119	87.23 58	87.69 109	95.58 50
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
1314		80.70 135	78.95 152	85.94 79	87.77 199	67.56 93	87.91 266	92.55 113	72.17 185	67.44 250	93.09 110	50.27 233	97.04 90	71.68 177	87.64 110	93.23 139

test_fmvsmconf_n		86.58 37	87.17 30	84.82 114	85.28 242	62.55 221	94.26 54	89.78 221	83.81 16	87.78 34	96.33 27	65.33 65	96.98 96	94.40 9	87.55 111	94.95 78

PMMVS		81.98 116	82.04 104	81.78 204	89.76 143	56.17 313	91.13 192	90.69 185	77.96 85	80.09 100	93.57 104	46.33 269	94.99 172	81.41 103	87.46 112	94.17 106

casdiffmvs		85.37 56	84.87 62	86.84 51	88.25 183	69.07 55	93.04 107	91.76 144	81.27 41	80.84 94	92.07 135	64.23 79	96.06 131	84.98 76	87.43 113	95.39 55
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_fmvsmconf0.1_n		85.71 51	86.08 45	84.62 128	80.83 295	62.33 225	93.84 78	88.81 264	83.50 18	87.00 40	96.01 35	63.36 94	96.93 103	94.04 10	87.29 114	94.61 91

UGNet		79.87 152	78.68 154	83.45 164	89.96 138	61.51 242	92.13 141	90.79 183	76.83 104	78.85 118	86.33 223	38.16 308	96.17 124	67.93 211	87.17 115	92.67 155
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
MVS_111021_LR		82.02 115	81.52 110	83.51 161	88.42 176	62.88 216	89.77 233	88.93 260	76.78 105	75.55 151	93.10 109	50.31 232	95.38 162	83.82 87	87.02 116	92.26 171

test_fmvsmvis_n_1920		83.80 84	83.48 75	84.77 118	82.51 281	63.72 189	91.37 180	83.99 328	81.42 39	77.68 127	95.74 40	58.37 146	97.58 59	93.38 12	86.87 117	93.00 148

xiu_mvs_v1_base_debu		82.16 111	81.12 114	85.26 102	86.42 221	68.72 64	92.59 128	90.44 195	73.12 159	84.20 65	94.36 80	38.04 310	95.73 143	84.12 83	86.81 118	91.33 184

xiu_mvs_v1_base		82.16 111	81.12 114	85.26 102	86.42 221	68.72 64	92.59 128	90.44 195	73.12 159	84.20 65	94.36 80	38.04 310	95.73 143	84.12 83	86.81 118	91.33 184

xiu_mvs_v1_base_debi		82.16 111	81.12 114	85.26 102	86.42 221	68.72 64	92.59 128	90.44 195	73.12 159	84.20 65	94.36 80	38.04 310	95.73 143	84.12 83	86.81 118	91.33 184

SR-MVS-dyc-post		81.06 130	80.70 122	82.15 195	92.02 91	58.56 290	90.90 197	90.45 192	62.76 300	78.89 113	94.46 76	51.26 226	95.61 151	78.77 125	86.77 121	92.28 167

RE-MVS-def			80.48 128		92.02 91	58.56 290	90.90 197	90.45 192	62.76 300	78.89 113	94.46 76	49.30 242		78.77 125	86.77 121	92.28 167

baseline		85.01 61	84.44 65	86.71 56	88.33 180	68.73 63	90.24 220	91.82 143	81.05 44	81.18 88	92.50 124	63.69 87	96.08 130	84.45 81	86.71 123	95.32 61

TESTMET0.1,1		82.41 107	81.98 106	83.72 155	88.08 187	63.74 187	92.70 120	93.77 61	79.30 63	77.61 129	87.57 207	58.19 149	94.08 211	73.91 156	86.68 124	93.33 137

IS-MVSNet		80.14 146	79.41 145	82.33 187	87.91 192	60.08 270	91.97 153	88.27 282	72.90 166	71.44 199	91.73 141	61.44 115	93.66 230	62.47 261	86.53 125	93.24 138

CPTT-MVS		79.59 155	79.16 150	80.89 229	91.54 109	59.80 273	92.10 143	88.54 276	60.42 318	72.96 174	93.28 108	48.27 251	92.80 251	78.89 124	86.50 126	90.06 203

BH-w/o		80.49 139	79.30 148	84.05 147	90.83 124	64.36 174	93.60 89	89.42 236	74.35 133	69.09 223	90.15 169	55.23 184	95.61 151	64.61 244	86.43 127	92.17 173

PVSNet	73.49 8	80.05 148	78.63 155	84.31 139	90.92 121	64.97 158	92.47 132	91.05 179	79.18 66	72.43 186	90.51 159	37.05 322	94.06 213	68.06 208	86.00 128	93.90 122

test_fmvsmconf0.01_n		83.70 88	83.52 72	84.25 142	75.26 347	61.72 239	92.17 139	87.24 297	82.36 26	84.91 59	95.41 46	55.60 180	96.83 107	92.85 15	85.87 129	94.21 104

mvs_anonymous		81.36 124	79.99 134	85.46 94	90.39 131	68.40 70	86.88 282	90.61 190	74.41 131	70.31 211	84.67 240	63.79 85	92.32 272	73.13 158	85.70 130	95.67 46

DP-MVS Recon		82.73 102	81.65 109	85.98 77	97.31 4	67.06 106	95.15 36	91.99 131	69.08 249	76.50 142	93.89 97	54.48 194	98.20 35	70.76 183	85.66 131	92.69 154

BH-RMVSNet		79.46 159	77.65 169	84.89 111	91.68 104	65.66 139	93.55 91	88.09 286	72.93 163	73.37 171	91.12 151	46.20 271	96.12 126	56.28 288	85.61 132	92.91 150

diffmvs		84.28 72	83.83 70	85.61 91	87.40 205	68.02 82	90.88 199	89.24 242	80.54 47	81.64 84	92.52 123	59.83 132	94.52 195	87.32 56	85.11 133	94.29 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Fast-Effi-MVS+		81.14 127	80.01 133	84.51 132	90.24 133	65.86 136	94.12 60	89.15 248	73.81 146	75.37 153	88.26 193	57.26 156	94.53 194	66.97 221	84.92 134	93.15 141

LFMVS		84.34 71	82.73 94	89.18 12	94.76 33	73.25 9	94.99 42	91.89 137	71.90 191	82.16 81	93.49 106	47.98 255	97.05 87	82.55 94	84.82 135	97.25 7

BH-untuned		78.68 174	77.08 180	83.48 163	89.84 140	63.74 187	92.70 120	88.59 274	71.57 208	66.83 260	88.65 184	51.75 220	95.39 161	59.03 279	84.77 136	91.32 187

test-LLR		80.10 147	79.56 141	81.72 206	86.93 216	61.17 246	92.70 120	91.54 154	71.51 211	75.62 148	86.94 215	53.83 200	92.38 268	72.21 170	84.76 137	91.60 178

test-mter		79.96 150	79.38 147	81.72 206	86.93 216	61.17 246	92.70 120	91.54 154	73.85 144	75.62 148	86.94 215	49.84 238	92.38 268	72.21 170	84.76 137	91.60 178

canonicalmvs		86.85 33	86.25 41	88.66 18	91.80 101	71.92 14	93.54 92	91.71 147	80.26 50	87.55 35	95.25 56	63.59 91	96.93 103	88.18 47	84.34 139	97.11 8

alignmvs		87.28 28	86.97 33	88.24 24	91.30 114	71.14 21	95.61 25	93.56 71	79.30 63	87.07 39	95.25 56	68.43 39	96.93 103	87.87 49	84.33 140	96.65 14

VNet		86.20 42	85.65 52	87.84 27	93.92 46	69.99 33	95.73 23	95.94 7	78.43 80	86.00 47	93.07 112	58.22 148	97.00 92	85.22 72	84.33 140	96.52 20

UA-Net		80.02 149	79.65 139	81.11 220	89.33 153	57.72 298	86.33 285	89.00 259	77.44 97	81.01 91	89.15 180	59.33 139	95.90 136	61.01 268	84.28 142	89.73 210

LCM-MVSNet-Re		72.93 253	71.84 252	76.18 299	88.49 172	48.02 352	80.07 333	70.17 369	73.96 142	52.25 342	80.09 303	49.98 235	88.24 321	67.35 215	84.23 143	92.28 167

ACMMP		81.49 122	80.67 123	83.93 149	91.71 103	62.90 215	92.13 141	92.22 123	71.79 198	71.68 196	93.49 106	50.32 231	96.96 99	78.47 127	84.22 144	91.93 176
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
114514_t		79.17 162	77.67 168	83.68 156	95.32 29	65.53 145	92.85 114	91.60 153	63.49 291	67.92 242	90.63 157	46.65 264	95.72 147	67.01 220	83.54 145	89.79 208

test_vis1_n_1920		81.66 120	82.01 105	80.64 231	82.24 284	55.09 321	94.76 46	86.87 299	81.67 34	84.40 64	94.63 73	38.17 307	94.67 185	91.98 24	83.34 146	92.16 174

EPMVS		78.49 179	75.98 195	86.02 76	91.21 116	69.68 44	80.23 330	91.20 167	75.25 123	72.48 184	78.11 317	54.65 190	93.69 229	57.66 285	83.04 147	94.69 86

AdaColmap		78.94 167	77.00 183	84.76 119	96.34 17	65.86 136	92.66 124	87.97 290	62.18 305	70.56 205	92.37 130	43.53 284	97.35 72	64.50 245	82.86 148	91.05 193

CDS-MVSNet		81.43 123	80.74 121	83.52 159	86.26 225	64.45 167	92.09 144	90.65 189	75.83 116	73.95 168	89.81 174	63.97 82	92.91 247	71.27 178	82.82 149	93.20 140
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CHOSEN 280x420		77.35 196	76.95 184	78.55 271	87.07 212	62.68 220	69.71 363	82.95 335	68.80 251	71.48 198	87.27 212	66.03 58	84.00 350	76.47 138	82.81 150	88.95 217

PCF-MVS	73.15 9	79.29 160	77.63 170	84.29 140	86.06 228	65.96 134	87.03 278	91.10 173	69.86 238	69.79 219	90.64 155	57.54 155	96.59 112	64.37 246	82.29 151	90.32 200
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n		86.39 39	86.91 34	84.82 114	87.36 207	63.54 199	94.74 47	90.02 215	82.52 24	90.14 22	96.92 12	62.93 101	97.84 46	95.28 6	82.26 152	93.07 145

WTY-MVS		86.32 40	85.81 49	87.85 26	92.82 73	69.37 49	95.20 34	95.25 14	82.71 22	81.91 82	94.73 70	67.93 45	97.63 56	79.55 115	82.25 153	96.54 19

HY-MVS	76.49 5	84.28 72	83.36 83	87.02 48	92.22 87	67.74 88	84.65 292	94.50 37	79.15 67	82.23 80	87.93 201	66.88 51	96.94 101	80.53 110	82.20 154	96.39 28

VDD-MVS		83.06 97	81.81 108	86.81 53	90.86 123	67.70 89	95.40 29	91.50 157	75.46 119	81.78 83	92.34 131	40.09 296	97.13 85	86.85 62	82.04 155	95.60 49

fmvsm_s_conf0.1_n		85.61 54	85.93 47	84.68 124	82.95 279	63.48 201	94.03 66	89.46 233	81.69 33	89.86 23	96.74 18	61.85 111	97.75 49	94.74 7	82.01 156	92.81 153

TAMVS		80.37 141	79.45 144	83.13 170	85.14 245	63.37 202	91.23 187	90.76 184	74.81 129	72.65 179	88.49 185	60.63 123	92.95 242	69.41 196	81.95 157	93.08 144

test_yl		84.28 72	83.16 85	87.64 30	94.52 37	69.24 51	95.78 18	95.09 19	69.19 246	81.09 89	92.88 118	57.00 161	97.44 66	81.11 107	81.76 158	96.23 33

DCV-MVSNet		84.28 72	83.16 85	87.64 30	94.52 37	69.24 51	95.78 18	95.09 19	69.19 246	81.09 89	92.88 118	57.00 161	97.44 66	81.11 107	81.76 158	96.23 33

FA-MVS(test-final)		79.12 163	77.23 179	84.81 117	90.54 127	63.98 182	81.35 321	91.71 147	71.09 219	74.85 157	82.94 258	52.85 211	97.05 87	67.97 209	81.73 160	93.41 133

thisisatest0515		83.41 90	82.49 99	86.16 74	89.46 150	68.26 75	93.54 92	94.70 30	74.31 134	75.75 145	90.92 152	72.62 28	96.52 117	69.64 192	81.50 161	93.71 126

baseline2		83.68 89	83.42 80	84.48 133	87.37 206	66.00 132	90.06 224	95.93 8	79.71 57	69.08 224	90.39 162	77.92 6	96.28 121	78.91 123	81.38 162	91.16 191

PatchmatchNet		77.46 194	74.63 211	85.96 78	89.55 148	70.35 30	79.97 335	89.55 231	72.23 182	70.94 201	76.91 328	57.03 159	92.79 252	54.27 295	81.17 163	94.74 85
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VDDNet		80.50 138	78.26 160	87.21 41	86.19 226	69.79 40	94.48 50	91.31 163	60.42 318	79.34 108	90.91 153	38.48 305	96.56 115	82.16 95	81.05 164	95.27 66

EPNet_dtu		78.80 171	79.26 149	77.43 284	88.06 188	49.71 345	91.96 154	91.95 133	77.67 91	76.56 141	91.28 149	58.51 145	90.20 306	56.37 287	80.95 165	92.39 162
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		82.71 104	82.38 101	83.73 154	89.25 155	59.58 276	92.24 137	94.89 23	77.96 85	79.86 102	92.38 129	56.70 167	97.05 87	77.26 134	80.86 166	94.55 92

FE-MVS		75.97 219	73.02 235	84.82 114	89.78 141	65.56 143	77.44 346	91.07 177	64.55 283	72.66 178	79.85 305	46.05 273	96.69 110	54.97 292	80.82 167	92.21 172

GeoE		78.90 168	77.43 173	83.29 166	88.95 164	62.02 231	92.31 134	86.23 306	70.24 233	71.34 200	89.27 178	54.43 195	94.04 216	63.31 253	80.81 168	93.81 125

fmvsm_s_conf0.5_n_a		85.75 50	86.09 44	84.72 121	85.73 236	63.58 196	93.79 81	89.32 239	81.42 39	90.21 20	96.91 13	62.41 105	97.67 51	94.48 8	80.56 169	92.90 151

TR-MVS		78.77 173	77.37 178	82.95 172	90.49 128	60.88 252	93.67 86	90.07 211	70.08 235	74.51 160	91.37 148	45.69 274	95.70 148	60.12 274	80.32 170	92.29 166

fmvsm_s_conf0.1_n_a		84.76 64	84.84 63	84.53 130	80.23 305	63.50 200	92.79 115	88.73 268	80.46 48	89.84 24	96.65 20	60.96 120	97.57 61	93.80 11	80.14 171	92.53 160

TAPA-MVS	70.22 12	74.94 234	73.53 230	79.17 264	90.40 130	52.07 333	89.19 246	89.61 230	62.69 302	70.07 213	92.67 122	48.89 249	94.32 199	38.26 358	79.97 172	91.12 192
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_cas_vis1_n_1920		80.45 140	80.61 125	79.97 248	78.25 331	57.01 309	94.04 65	88.33 279	79.06 71	82.81 76	93.70 100	38.65 302	91.63 286	90.82 33	79.81 173	91.27 190

cascas		78.18 183	75.77 198	85.41 96	87.14 211	69.11 53	92.96 110	91.15 171	66.71 269	70.47 206	86.07 226	37.49 316	96.48 118	70.15 188	79.80 174	90.65 196

HyFIR lowres test		81.03 131	79.56 141	85.43 95	87.81 197	68.11 80	90.18 221	90.01 216	70.65 228	72.95 175	86.06 227	63.61 90	94.50 196	75.01 148	79.75 175	93.67 127

LS3D		69.17 284	66.40 288	77.50 282	91.92 97	56.12 314	85.12 289	80.37 345	46.96 364	56.50 328	87.51 208	37.25 317	93.71 228	32.52 374	79.40 176	82.68 321

EI-MVSNet-Vis-set		83.77 85	83.67 71	84.06 146	92.79 76	63.56 197	91.76 163	94.81 26	79.65 58	77.87 125	94.09 92	63.35 95	97.90 42	79.35 117	79.36 177	90.74 195

CVMVSNet		74.04 242	74.27 219	73.33 318	85.33 240	43.94 368	89.53 238	88.39 277	54.33 346	70.37 209	90.13 170	49.17 245	84.05 348	61.83 265	79.36 177	91.99 175

EPP-MVSNet		81.79 118	81.52 110	82.61 180	88.77 169	60.21 268	93.02 109	93.66 68	68.52 255	72.90 176	90.39 162	72.19 31	94.96 173	74.93 149	79.29 179	92.67 155

CLD-MVS		82.73 102	82.35 102	83.86 150	87.90 193	67.65 91	95.45 28	92.18 126	85.06 10	72.58 181	92.27 132	52.46 215	95.78 139	84.18 82	79.06 180	88.16 233
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP3-MVS								91.70 149							78.90 181

HQP-MVS		81.14 127	80.64 124	82.64 179	87.54 201	63.66 194	94.06 61	91.70 149	79.80 54	74.18 162	90.30 164	51.63 222	95.61 151	77.63 132	78.90 181	88.63 223

plane_prior						62.42 222	93.85 75		79.38 61						78.80 183

thres200		79.66 154	78.33 158	83.66 158	92.54 82	65.82 138	93.06 105	96.31 3	74.90 128	73.30 172	88.66 183	59.67 134	95.61 151	47.84 321	78.67 184	89.56 213

ET-MVSNet_ETH3D		84.01 79	83.15 87	86.58 61	90.78 125	70.89 24	94.74 47	94.62 34	81.44 38	58.19 318	93.64 102	73.64 23	92.35 271	82.66 92	78.66 185	96.50 24

HQP_MVS		80.34 142	79.75 138	82.12 197	86.94 214	62.42 222	93.13 103	91.31 163	78.81 76	72.53 182	89.14 181	50.66 229	95.55 156	76.74 135	78.53 186	88.39 230

plane_prior5								91.31 163					95.55 156	76.74 135	78.53 186	88.39 230

EI-MVSNet-UG-set		83.14 96	82.96 88	83.67 157	92.28 85	63.19 206	91.38 179	94.68 31	79.22 65	76.60 140	93.75 98	62.64 102	97.76 48	78.07 130	78.01 188	90.05 204

OMC-MVS		78.67 176	77.91 167	80.95 227	85.76 235	57.40 305	88.49 257	88.67 271	73.85 144	72.43 186	92.10 134	49.29 243	94.55 193	72.73 164	77.89 189	90.91 194

1112_ss		80.56 137	79.83 137	82.77 175	88.65 170	60.78 254	92.29 135	88.36 278	72.58 171	72.46 185	94.95 62	65.09 67	93.42 235	66.38 227	77.71 190	94.10 110

OPM-MVS		79.00 165	78.09 162	81.73 205	83.52 271	63.83 184	91.64 169	90.30 202	76.36 112	71.97 191	89.93 173	46.30 270	95.17 168	75.10 146	77.70 191	86.19 266
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		72.06 263	69.98 266	78.28 274	89.51 149	55.70 317	83.49 299	83.39 333	61.24 313	63.72 284	82.76 260	34.77 330	93.03 240	53.37 300	77.59 192	86.12 270

thres100view900		78.37 180	77.01 182	82.46 182	91.89 99	63.21 205	91.19 191	96.33 1	72.28 181	70.45 208	87.89 202	60.31 125	95.32 163	45.16 332	77.58 193	88.83 218

tfpn200view9		78.79 172	77.43 173	82.88 173	92.21 88	64.49 164	92.05 147	96.28 4	73.48 153	71.75 194	88.26 193	60.07 130	95.32 163	45.16 332	77.58 193	88.83 218

thres400		78.68 174	77.43 173	82.43 183	92.21 88	64.49 164	92.05 147	96.28 4	73.48 153	71.75 194	88.26 193	60.07 130	95.32 163	45.16 332	77.58 193	87.48 239

CostFormer		82.33 108	81.15 113	85.86 82	89.01 163	68.46 69	82.39 312	93.01 94	75.59 117	80.25 98	81.57 277	72.03 32	94.96 173	79.06 121	77.48 196	94.16 107

tpm2		79.80 153	77.95 166	85.34 99	88.28 181	68.26 75	81.56 318	91.42 160	70.11 234	77.59 130	80.50 295	67.40 48	94.26 205	67.34 216	77.35 197	93.51 131

Test_1112_low_res		79.56 156	78.60 156	82.43 183	88.24 184	60.39 265	92.09 144	87.99 288	72.10 187	71.84 192	87.42 209	64.62 75	93.04 239	65.80 234	77.30 198	93.85 124

tpmrst		80.57 136	79.14 151	84.84 113	90.10 136	68.28 74	81.70 316	89.72 228	77.63 94	75.96 144	79.54 309	64.94 70	92.71 254	75.43 143	77.28 199	93.55 130

Anonymous202405211		77.96 187	75.33 205	85.87 81	93.73 52	64.52 163	94.85 44	85.36 314	62.52 303	76.11 143	90.18 167	29.43 351	97.29 76	68.51 206	77.24 200	95.81 45

GA-MVS		78.33 182	76.23 192	84.65 125	83.65 269	66.30 126	91.44 171	90.14 209	76.01 114	70.32 210	84.02 248	42.50 288	94.72 181	70.98 180	77.00 201	92.94 149

thisisatest0530		81.15 126	80.07 131	84.39 136	88.26 182	65.63 141	91.40 175	94.62 34	71.27 215	70.93 202	89.18 179	72.47 29	96.04 132	65.62 236	76.89 202	91.49 180

thres600view7		78.00 185	76.66 187	82.03 202	91.93 96	63.69 192	91.30 185	96.33 1	72.43 176	70.46 207	87.89 202	60.31 125	94.92 176	42.64 344	76.64 203	87.48 239

PLC	68.80 14	75.23 230	73.68 229	79.86 251	92.93 70	58.68 289	90.64 208	88.30 280	60.90 315	64.43 279	90.53 158	42.38 289	94.57 190	56.52 286	76.54 204	86.33 261
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
iter_conf_final		81.74 119	80.93 119	84.18 143	92.66 79	69.10 54	92.94 111	82.80 337	79.01 73	74.85 157	88.40 188	61.83 112	94.61 186	79.36 116	76.52 205	88.83 218

MIMVSNet		71.64 265	68.44 279	81.23 216	81.97 288	64.44 168	73.05 356	88.80 265	69.67 240	64.59 273	74.79 340	32.79 337	87.82 325	53.99 296	76.35 206	91.42 182

test_fmvs1		74.07 241	73.69 228	75.22 303	78.91 323	47.34 357	89.06 250	74.69 358	63.68 290	79.41 107	91.59 143	24.36 360	87.77 327	85.22 72	76.26 207	90.55 199

MVS-HIRNet		60.25 330	55.55 337	74.35 311	84.37 259	56.57 312	71.64 358	74.11 359	34.44 379	45.54 365	42.24 386	31.11 347	89.81 309	40.36 352	76.10 208	76.67 363

CNLPA		74.31 239	72.30 247	80.32 235	91.49 110	61.66 240	90.85 200	80.72 343	56.67 339	63.85 283	90.64 155	46.75 263	90.84 296	53.79 297	75.99 209	88.47 229

ab-mvs		80.18 145	78.31 159	85.80 85	88.44 175	65.49 147	83.00 309	92.67 106	71.82 197	77.36 132	85.01 235	54.50 191	96.59 112	76.35 139	75.63 210	95.32 61

test_fmvs1_n		72.69 260	71.92 251	74.99 306	71.15 360	47.08 359	87.34 276	75.67 353	63.48 292	78.08 124	91.17 150	20.16 371	87.87 324	84.65 79	75.57 211	90.01 205

iter_conf05		83.27 93	82.70 95	84.98 109	93.32 59	71.84 15	94.16 56	81.76 339	82.74 21	73.83 169	88.40 188	72.77 27	94.61 186	82.10 96	75.21 212	88.48 227

FIs		79.47 158	79.41 145	79.67 255	85.95 230	59.40 278	91.68 167	93.94 56	78.06 84	68.96 228	88.28 191	66.61 54	91.77 283	66.20 230	74.99 213	87.82 235

SDMVSNet		80.26 143	78.88 153	84.40 135	89.25 155	67.63 92	85.35 288	93.02 93	76.77 106	70.84 203	87.12 213	47.95 256	96.09 127	85.04 74	74.55 214	89.48 214

sd_testset		77.08 200	75.37 203	82.20 193	89.25 155	62.11 230	82.06 313	89.09 252	76.77 106	70.84 203	87.12 213	41.43 292	95.01 171	67.23 218	74.55 214	89.48 214

CMPMVS	48.56 21	66.77 304	64.41 305	73.84 315	70.65 363	50.31 342	77.79 345	85.73 312	45.54 368	44.76 367	82.14 268	35.40 328	90.14 307	63.18 255	74.54 216	81.07 335
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dmvs_re		76.93 201	75.36 204	81.61 208	87.78 198	60.71 259	80.00 334	87.99 288	79.42 60	69.02 226	89.47 177	46.77 262	94.32 199	63.38 252	74.45 217	89.81 207

test_vis1_n		71.63 266	70.73 262	74.31 313	69.63 366	47.29 358	86.91 280	72.11 364	63.21 296	75.18 154	90.17 168	20.40 369	85.76 339	84.59 80	74.42 218	89.87 206

XVG-OURS		74.25 240	72.46 246	79.63 256	78.45 329	57.59 302	80.33 328	87.39 293	63.86 288	68.76 232	89.62 176	40.50 295	91.72 284	69.00 201	74.25 219	89.58 211

tpm cat1		75.30 229	72.21 248	84.58 129	88.52 171	67.77 87	78.16 344	88.02 287	61.88 310	68.45 237	76.37 332	60.65 122	94.03 218	53.77 298	74.11 220	91.93 176

XVG-OURS-SEG-HR		74.70 236	73.08 234	79.57 258	78.25 331	57.33 306	80.49 326	87.32 294	63.22 295	68.76 232	90.12 172	44.89 280	91.59 287	70.55 186	74.09 221	89.79 208

FC-MVSNet-test		77.99 186	78.08 163	77.70 279	84.89 250	55.51 318	90.27 218	93.75 65	76.87 101	66.80 261	87.59 206	65.71 62	90.23 305	62.89 258	73.94 222	87.37 242

PVSNet_BlendedMVS		83.38 91	83.43 78	83.22 168	93.76 49	67.53 95	94.06 61	93.61 69	79.13 68	81.00 92	85.14 234	63.19 97	97.29 76	87.08 59	73.91 223	84.83 294

tttt0517		79.50 157	78.53 157	82.41 186	87.22 209	61.43 244	89.75 234	94.76 27	69.29 244	67.91 243	88.06 200	72.92 25	95.63 149	62.91 257	73.90 224	90.16 202

MDTV_nov1_ep13			72.61 243		89.06 161	68.48 68	80.33 328	90.11 210	71.84 196	71.81 193	75.92 336	53.01 210	93.92 223	48.04 318	73.38 225

SCA		75.82 222	72.76 239	85.01 108	86.63 218	70.08 32	81.06 323	89.19 245	71.60 207	70.01 214	77.09 326	45.53 275	90.25 301	60.43 271	73.27 226	94.68 87

CR-MVSNet		73.79 246	70.82 261	82.70 177	83.15 274	67.96 83	70.25 360	84.00 326	73.67 151	69.97 216	72.41 346	57.82 152	89.48 312	52.99 301	73.13 227	90.64 197

RPMNet		70.42 274	65.68 293	84.63 127	83.15 274	67.96 83	70.25 360	90.45 192	46.83 366	69.97 216	65.10 365	56.48 172	95.30 166	35.79 363	73.13 227	90.64 197

Fast-Effi-MVS+-dtu		75.04 232	73.37 232	80.07 243	80.86 294	59.52 277	91.20 190	85.38 313	71.90 191	65.20 268	84.84 238	41.46 291	92.97 241	66.50 226	72.96 229	87.73 236

mvsmamba		76.85 204	75.71 200	80.25 239	83.07 276	59.16 283	91.44 171	80.64 344	76.84 103	67.95 241	86.33 223	46.17 272	94.24 206	76.06 140	72.92 230	87.36 243

LPG-MVS_test		75.82 222	74.58 213	79.56 259	84.31 260	59.37 279	90.44 211	89.73 226	69.49 241	64.86 270	88.42 186	38.65 302	94.30 201	72.56 166	72.76 231	85.01 292

LGP-MVS_train				79.56 259	84.31 260	59.37 279		89.73 226	69.49 241	64.86 270	88.42 186	38.65 302	94.30 201	72.56 166	72.76 231	85.01 292

EG-PatchMatch MVS		68.55 290	65.41 296	77.96 278	78.69 326	62.93 212	89.86 231	89.17 246	60.55 317	50.27 350	77.73 320	22.60 365	94.06 213	47.18 324	72.65 233	76.88 362

EI-MVSNet		78.97 166	78.22 161	81.25 215	85.33 240	62.73 219	89.53 238	93.21 84	72.39 178	72.14 189	90.13 170	60.99 118	94.72 181	67.73 213	72.49 234	86.29 262

MVSTER		82.47 106	82.05 103	83.74 152	92.68 78	69.01 57	91.90 155	93.21 84	79.83 53	72.14 189	85.71 231	74.72 16	94.72 181	75.72 141	72.49 234	87.50 238

Anonymous20240529		76.84 205	74.15 221	84.88 112	91.02 118	64.95 159	93.84 78	91.09 174	53.57 347	73.00 173	87.42 209	35.91 326	97.32 74	69.14 200	72.41 236	92.36 163

D2MVS		73.80 245	72.02 250	79.15 266	79.15 318	62.97 210	88.58 256	90.07 211	72.94 162	59.22 312	78.30 314	42.31 290	92.70 256	65.59 237	72.00 237	81.79 329

PS-MVSNAJss		77.26 197	76.31 191	80.13 242	80.64 299	59.16 283	90.63 210	91.06 178	72.80 167	68.58 235	84.57 242	53.55 204	93.96 221	72.97 159	71.96 238	87.27 247

Effi-MVS+-dtu		76.14 212	75.28 206	78.72 270	83.22 273	55.17 320	89.87 230	87.78 291	75.42 120	67.98 240	81.43 279	45.08 279	92.52 264	75.08 147	71.63 239	88.48 227

ACMMP++_ref															71.63 239

ACMM	69.62 13	74.34 238	72.73 241	79.17 264	84.25 262	57.87 296	90.36 215	89.93 217	63.17 297	65.64 265	86.04 228	37.79 314	94.10 209	65.89 232	71.52 241	85.55 283
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	71.68 10	75.58 227	74.23 220	79.62 257	84.97 249	59.64 274	90.80 202	89.07 254	70.39 231	62.95 292	87.30 211	38.28 306	93.87 225	72.89 160	71.45 242	85.36 287
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
dp		75.01 233	72.09 249	83.76 151	89.28 154	66.22 129	79.96 336	89.75 223	71.16 216	67.80 247	77.19 325	51.81 219	92.54 263	50.39 306	71.44 243	92.51 161

tpm		78.58 177	77.03 181	83.22 168	85.94 232	64.56 162	83.21 306	91.14 172	78.31 81	73.67 170	79.68 307	64.01 81	92.09 277	66.07 231	71.26 244	93.03 146

DP-MVS		69.90 279	66.48 286	80.14 241	95.36 28	62.93 212	89.56 235	76.11 351	50.27 357	57.69 324	85.23 233	39.68 297	95.73 143	33.35 368	71.05 245	81.78 330

UniMVSNet_ETH3D		72.74 257	70.53 264	79.36 261	78.62 328	56.64 311	85.01 290	89.20 244	63.77 289	64.84 272	84.44 244	34.05 333	91.86 281	63.94 248	70.89 246	89.57 212

bld_raw_dy_0_64		71.59 267	69.71 272	77.22 289	77.82 337	58.12 294	87.71 270	73.66 360	68.01 258	61.90 301	84.29 246	33.68 334	88.43 319	69.91 191	70.43 247	85.11 291

jajsoiax		73.05 251	71.51 256	77.67 280	77.46 338	54.83 322	88.81 252	90.04 214	69.13 248	62.85 294	83.51 253	31.16 346	92.75 253	70.83 181	69.80 248	85.43 286

ACMMP++															69.72 249

mvs_tets		72.71 258	71.11 257	77.52 281	77.41 339	54.52 324	88.45 258	89.76 222	68.76 253	62.70 295	83.26 256	29.49 350	92.71 254	70.51 187	69.62 250	85.34 288

tpmvs		72.88 255	69.76 271	82.22 192	90.98 119	67.05 107	78.22 343	88.30 280	63.10 298	64.35 280	74.98 339	55.09 187	94.27 203	43.25 338	69.57 251	85.34 288

GBi-Net		75.65 224	73.83 226	81.10 221	88.85 165	65.11 154	90.01 226	90.32 198	70.84 223	67.04 256	80.25 300	48.03 252	91.54 289	59.80 276	69.34 252	86.64 255

test1		75.65 224	73.83 226	81.10 221	88.85 165	65.11 154	90.01 226	90.32 198	70.84 223	67.04 256	80.25 300	48.03 252	91.54 289	59.80 276	69.34 252	86.64 255

FMVSNet3		77.73 191	76.04 194	82.80 174	91.20 117	68.99 58	91.87 156	91.99 131	73.35 155	67.04 256	83.19 257	56.62 169	92.14 274	59.80 276	69.34 252	87.28 246

Syy-MVS		69.65 281	69.52 273	70.03 337	87.87 194	43.21 370	88.07 262	89.01 256	72.91 164	63.11 289	88.10 197	45.28 278	85.54 340	22.07 383	69.23 255	81.32 332

myMVS_eth3d		72.58 262	72.74 240	72.10 330	87.87 194	49.45 347	88.07 262	89.01 256	72.91 164	63.11 289	88.10 197	63.63 88	85.54 340	32.73 372	69.23 255	81.32 332

MSDG		69.54 282	65.73 292	80.96 226	85.11 247	63.71 190	84.19 294	83.28 334	56.95 336	54.50 333	84.03 247	31.50 343	96.03 133	42.87 342	69.13 257	83.14 313

JIA-IIPM		66.06 307	62.45 316	76.88 294	81.42 292	54.45 325	57.49 382	88.67 271	49.36 359	63.86 282	46.86 380	56.06 176	90.25 301	49.53 311	68.83 258	85.95 274

OpenMVS_ROB	61.12 18	66.39 305	62.92 313	76.80 295	76.51 342	57.77 297	89.22 244	83.41 332	55.48 343	53.86 337	77.84 319	26.28 359	93.95 222	34.90 365	68.76 259	78.68 356

FMVSNet2		76.07 213	74.01 224	82.26 191	88.85 165	67.66 90	91.33 183	91.61 152	70.84 223	65.98 263	82.25 266	48.03 252	92.00 279	58.46 281	68.73 260	87.10 249

test_djsdf		73.76 247	72.56 244	77.39 285	77.00 341	53.93 326	89.07 248	90.69 185	65.80 275	63.92 281	82.03 269	43.14 287	92.67 257	72.83 161	68.53 261	85.57 282

F-COLMAP		70.66 271	68.44 279	77.32 286	86.37 224	55.91 315	88.00 264	86.32 303	56.94 337	57.28 326	88.07 199	33.58 335	92.49 265	51.02 304	68.37 262	83.55 303

XVG-ACMP-BASELINE		68.04 295	65.53 295	75.56 301	74.06 352	52.37 331	78.43 340	85.88 310	62.03 307	58.91 316	81.21 287	20.38 370	91.15 295	60.69 270	68.18 263	83.16 312

LTVRE_ROB	59.60 19	66.27 306	63.54 309	74.45 310	84.00 265	51.55 335	67.08 370	83.53 330	58.78 328	54.94 332	80.31 298	34.54 331	93.23 237	40.64 351	68.03 264	78.58 357
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
XXY-MVS		77.94 188	76.44 189	82.43 183	82.60 280	64.44 168	92.01 149	91.83 142	73.59 152	70.00 215	85.82 229	54.43 195	94.76 178	69.63 193	68.02 265	88.10 234

ADS-MVSNet2		66.90 303	63.44 310	77.26 288	88.06 188	60.70 260	68.01 367	75.56 355	57.57 331	64.48 276	69.87 356	38.68 300	84.10 347	40.87 349	67.89 266	86.97 250

ADS-MVSNet		68.54 291	64.38 306	81.03 225	88.06 188	66.90 111	68.01 367	84.02 325	57.57 331	64.48 276	69.87 356	38.68 300	89.21 314	40.87 349	67.89 266	86.97 250

test0.0.03 1		72.76 256	72.71 242	72.88 322	80.25 304	47.99 353	91.22 188	89.45 234	71.51 211	62.51 297	87.66 205	53.83 200	85.06 344	50.16 308	67.84 268	85.58 281

anonymousdsp		71.14 270	69.37 274	76.45 296	72.95 355	54.71 323	84.19 294	88.88 261	61.92 309	62.15 298	79.77 306	38.14 309	91.44 294	68.90 203	67.45 269	83.21 311

tt0805		73.07 250	70.73 262	80.07 243	78.37 330	57.05 308	87.78 268	92.18 126	61.23 314	67.04 256	86.49 220	31.35 345	94.58 188	65.06 242	67.12 270	88.57 225

VPA-MVSNet		79.03 164	78.00 164	82.11 200	85.95 230	64.48 166	93.22 102	94.66 32	75.05 126	74.04 167	84.95 236	52.17 217	93.52 232	74.90 151	67.04 271	88.32 232

nrg030		80.93 132	79.86 136	84.13 145	83.69 268	68.83 61	93.23 101	91.20 167	75.55 118	75.06 155	88.22 196	63.04 100	94.74 180	81.88 98	66.88 272	88.82 221

FMVSNet1		72.71 258	69.91 269	81.10 221	83.60 270	65.11 154	90.01 226	90.32 198	63.92 287	63.56 285	80.25 300	36.35 325	91.54 289	54.46 294	66.75 273	86.64 255

PatchT		69.11 285	65.37 297	80.32 235	82.07 287	63.68 193	67.96 369	87.62 292	50.86 355	69.37 220	65.18 364	57.09 158	88.53 318	41.59 347	66.60 274	88.74 222

IB-MVS	77.80 4	82.18 110	80.46 129	87.35 39	89.14 160	70.28 31	95.59 26	95.17 17	78.85 74	70.19 212	85.82 229	70.66 35	97.67 51	72.19 172	66.52 275	94.09 111
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
RRT_MVS		74.44 237	72.97 237	78.84 269	82.36 283	57.66 300	89.83 232	88.79 267	70.61 229	64.58 274	84.89 237	39.24 298	92.65 260	70.11 189	66.34 276	86.21 265

test_fmvs2		65.78 310	64.84 298	68.60 343	66.54 371	41.71 372	83.27 303	69.81 370	54.38 345	67.91 243	84.54 243	15.35 376	81.22 367	75.65 142	66.16 277	82.88 314

pmmvs5		73.35 248	71.52 255	78.86 268	78.64 327	60.61 263	91.08 193	86.90 298	67.69 260	63.32 287	83.64 251	44.33 282	90.53 298	62.04 263	66.02 278	85.46 285

dmvs_testset		65.55 311	66.45 287	62.86 353	79.87 308	22.35 396	76.55 348	71.74 366	77.42 99	55.85 329	87.77 204	51.39 224	80.69 368	31.51 378	65.92 279	85.55 283

pmmvs4		73.92 244	71.81 253	80.25 239	79.17 317	65.24 150	87.43 274	87.26 296	67.64 263	63.46 286	83.91 250	48.96 248	91.53 292	62.94 256	65.49 280	83.96 299

cl22		77.94 188	76.78 185	81.42 212	87.57 200	64.93 160	90.67 206	88.86 263	72.45 175	67.63 249	82.68 262	64.07 80	92.91 247	71.79 173	65.30 281	86.44 260

miper_ehance_all_eth		77.60 192	76.44 189	81.09 224	85.70 237	64.41 171	90.65 207	88.64 273	72.31 179	67.37 254	82.52 263	64.77 74	92.64 261	70.67 184	65.30 281	86.24 264

miper_enhance_ethall		78.86 169	77.97 165	81.54 210	88.00 191	65.17 152	91.41 173	89.15 248	75.19 124	68.79 231	83.98 249	67.17 49	92.82 249	72.73 164	65.30 281	86.62 259

v1144		76.73 208	74.88 208	82.27 189	80.23 305	66.60 119	91.68 167	90.21 208	73.69 149	69.06 225	81.89 270	52.73 213	94.40 198	69.21 199	65.23 284	85.80 277

DSMNet-mixed		56.78 336	54.44 339	63.79 352	63.21 375	29.44 391	64.43 373	64.10 378	42.12 376	51.32 346	71.60 351	31.76 342	75.04 373	36.23 360	65.20 285	86.87 253

v1192		75.98 218	73.92 225	82.15 195	79.73 309	66.24 128	91.22 188	89.75 223	72.67 169	68.49 236	81.42 280	49.86 237	94.27 203	67.08 219	65.02 286	85.95 274

v2v482		77.42 195	75.65 201	82.73 176	80.38 301	67.13 105	91.85 158	90.23 206	75.09 125	69.37 220	83.39 255	53.79 202	94.44 197	71.77 174	65.00 287	86.63 258

V42		76.46 210	74.55 214	82.19 194	79.14 319	67.82 86	90.26 219	89.42 236	73.75 147	68.63 234	81.89 270	51.31 225	94.09 210	71.69 176	64.84 288	84.66 295

ACMH	63.93 17	68.62 289	64.81 299	80.03 245	85.22 243	63.25 204	87.72 269	84.66 320	60.83 316	51.57 345	79.43 310	27.29 356	94.96 173	41.76 345	64.84 288	81.88 328
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		81.84 117	81.03 118	84.28 141	91.60 105	66.62 118	91.08 193	91.66 151	81.87 31	74.86 156	91.67 142	69.98 37	94.92 176	71.76 175	64.75 290	91.29 189

v1240		75.21 231	72.98 236	81.88 203	79.20 316	66.00 132	90.75 204	89.11 251	71.63 206	67.41 252	81.22 285	47.36 260	93.87 225	65.46 239	64.72 291	85.77 278

IterMVS-LS		76.49 209	75.18 207	80.43 234	84.49 256	62.74 218	90.64 208	88.80 265	72.40 177	65.16 269	81.72 273	60.98 119	92.27 273	67.74 212	64.65 292	86.29 262
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		75.63 226	73.49 231	82.06 201	79.38 314	66.35 124	91.07 195	89.48 232	71.98 188	67.99 239	81.22 285	49.16 246	93.90 224	66.56 223	64.56 293	85.92 276

v144192		76.05 216	74.03 223	82.12 197	79.50 313	66.55 121	91.39 177	89.71 229	72.30 180	68.17 238	81.33 282	51.75 220	94.03 218	67.94 210	64.19 294	85.77 278

Anonymous20231211		73.08 249	70.39 265	81.13 219	90.62 126	63.33 203	91.40 175	90.06 213	51.84 352	64.46 278	80.67 293	36.49 324	94.07 212	63.83 249	64.17 295	85.98 273

testing3		70.38 275	70.83 259	69.03 341	85.82 234	43.93 369	90.72 205	90.56 191	68.06 257	60.24 306	86.82 217	64.83 72	84.12 346	26.33 379	64.10 296	79.04 353

Patchmatch-test		65.86 308	60.94 322	80.62 232	83.75 267	58.83 287	58.91 381	75.26 357	44.50 371	50.95 349	77.09 326	58.81 144	87.90 323	35.13 364	64.03 297	95.12 72

USDC		67.43 302	64.51 303	76.19 298	77.94 335	55.29 319	78.38 341	85.00 317	73.17 157	48.36 357	80.37 297	21.23 367	92.48 266	52.15 302	64.02 298	80.81 338

VPNet		78.82 170	77.53 172	82.70 177	84.52 255	66.44 122	93.93 70	92.23 120	80.46 48	72.60 180	88.38 190	49.18 244	93.13 238	72.47 168	63.97 299	88.55 226

Anonymous20231206		67.53 300	65.78 291	72.79 323	74.95 348	47.59 355	88.23 260	87.32 294	61.75 312	58.07 320	77.29 323	37.79 314	87.29 333	42.91 340	63.71 300	83.48 306

WR-MVS		76.76 207	75.74 199	79.82 252	84.60 253	62.27 228	92.60 126	92.51 114	76.06 113	67.87 246	85.34 232	56.76 165	90.24 304	62.20 262	63.69 301	86.94 252

h-mvs33		83.01 98	82.56 98	84.35 138	89.34 151	62.02 231	92.72 118	93.76 62	81.45 36	82.73 77	92.25 133	60.11 128	97.13 85	87.69 51	62.96 302	93.91 120

c3_l		76.83 206	75.47 202	80.93 228	85.02 248	64.18 179	90.39 214	88.11 285	71.66 201	66.65 262	81.64 275	63.58 92	92.56 262	69.31 198	62.86 303	86.04 271

test_vis1_rt		59.09 334	57.31 333	64.43 351	68.44 369	46.02 363	83.05 308	48.63 391	51.96 351	49.57 353	63.86 367	16.30 374	80.20 369	71.21 179	62.79 304	67.07 376

mvsany_test1		68.77 288	68.56 277	69.39 339	73.57 353	45.88 364	80.93 324	60.88 382	59.65 324	71.56 197	90.26 166	43.22 286	75.05 372	74.26 155	62.70 305	87.25 248

UniMVSNet_NR-MVSNet		78.15 184	77.55 171	79.98 246	84.46 257	60.26 266	92.25 136	93.20 86	77.50 96	68.88 229	86.61 218	66.10 57	92.13 275	66.38 227	62.55 306	87.54 237

DU-MVS		76.86 202	75.84 197	79.91 249	82.96 277	60.26 266	91.26 186	91.54 154	76.46 111	68.88 229	86.35 221	56.16 173	92.13 275	66.38 227	62.55 306	87.35 244

UniMVSNet (Re)		77.58 193	76.78 185	79.98 246	84.11 263	60.80 253	91.76 163	93.17 88	76.56 110	69.93 218	84.78 239	63.32 96	92.36 270	64.89 243	62.51 308	86.78 254

v8		75.35 228	73.26 233	81.61 208	80.67 298	66.82 112	89.54 237	89.27 241	71.65 202	63.30 288	80.30 299	54.99 188	94.06 213	67.33 217	62.33 309	83.94 300

cl____		76.07 213	74.67 209	80.28 237	85.15 244	61.76 237	90.12 222	88.73 268	71.16 216	65.43 266	81.57 277	61.15 116	92.95 242	66.54 224	62.17 310	86.13 269

v10		74.77 235	72.54 245	81.46 211	80.33 303	66.71 116	89.15 247	89.08 253	70.94 221	63.08 291	79.86 304	52.52 214	94.04 216	65.70 235	62.17 310	83.64 302

DIV-MVS_self_test		76.07 213	74.67 209	80.28 237	85.14 245	61.75 238	90.12 222	88.73 268	71.16 216	65.42 267	81.60 276	61.15 116	92.94 246	66.54 224	62.16 312	86.14 267

IterMVS-SCA-FT		71.55 268	69.97 267	76.32 297	81.48 290	60.67 261	87.64 272	85.99 309	66.17 273	59.50 310	78.88 311	45.53 275	83.65 352	62.58 260	61.93 313	84.63 297

IterMVS		72.65 261	70.83 259	78.09 277	82.17 285	62.96 211	87.64 272	86.28 304	71.56 209	60.44 305	78.85 312	45.42 277	86.66 335	63.30 254	61.83 314	84.65 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet5		68.04 295	65.66 294	75.18 305	84.43 258	57.89 295	83.54 298	86.26 305	61.83 311	53.64 338	73.30 343	37.15 320	85.08 343	48.99 313	61.77 315	82.56 323

v7n		71.31 269	68.65 276	79.28 262	76.40 343	60.77 255	86.71 283	89.45 234	64.17 286	58.77 317	78.24 315	44.59 281	93.54 231	57.76 283	61.75 316	83.52 305

v148		76.19 211	74.47 216	81.36 213	80.05 307	64.44 168	91.75 165	90.23 206	73.68 150	67.13 255	80.84 290	55.92 178	93.86 227	68.95 202	61.73 317	85.76 280

tfpnnormal		70.10 276	67.36 284	78.32 273	83.45 272	60.97 251	88.85 251	92.77 102	64.85 282	60.83 304	78.53 313	43.52 285	93.48 233	31.73 375	61.70 318	80.52 341

ACMH+	65.35 16	67.65 298	64.55 302	76.96 293	84.59 254	57.10 307	88.08 261	80.79 342	58.59 330	53.00 339	81.09 289	26.63 358	92.95 242	46.51 326	61.69 319	80.82 337

ITE_SJBPF				70.43 336	74.44 350	47.06 360		77.32 349	60.16 321	54.04 336	83.53 252	23.30 364	84.01 349	43.07 339	61.58 320	80.21 346

NR-MVSNet		76.05 216	74.59 212	80.44 233	82.96 277	62.18 229	90.83 201	91.73 145	77.12 100	60.96 303	86.35 221	59.28 140	91.80 282	60.74 269	61.34 321	87.35 244

test_0402		64.54 315	61.09 321	74.92 307	84.10 264	60.75 257	87.95 265	79.71 347	52.03 350	52.41 341	77.20 324	32.21 341	91.64 285	23.14 381	61.03 322	72.36 370

Baseline_NR-MVSNet		73.99 243	72.83 238	77.48 283	80.78 296	59.29 282	91.79 160	84.55 321	68.85 250	68.99 227	80.70 291	56.16 173	92.04 278	62.67 259	60.98 323	81.11 334

TranMVSNet+NR-MVSNet		75.86 221	74.52 215	79.89 250	82.44 282	60.64 262	91.37 180	91.37 161	76.63 108	67.65 248	86.21 225	52.37 216	91.55 288	61.84 264	60.81 324	87.48 239

testgi		64.48 316	62.87 314	69.31 340	71.24 358	40.62 375	85.49 287	79.92 346	65.36 279	54.18 335	83.49 254	23.74 363	84.55 345	41.60 346	60.79 325	82.77 316

eth_miper_zixun_eth		75.96 220	74.40 217	80.66 230	84.66 252	63.02 209	89.28 243	88.27 282	71.88 193	65.73 264	81.65 274	59.45 136	92.81 250	68.13 207	60.53 326	86.14 267

COLMAP_ROB	57.96 20	62.98 323	59.65 325	72.98 321	81.44 291	53.00 330	83.75 297	75.53 356	48.34 362	48.81 356	81.40 281	24.14 361	90.30 300	32.95 370	60.52 327	75.65 365
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AUN-MVS		78.37 180	77.43 173	81.17 217	86.60 219	57.45 304	89.46 240	91.16 169	74.11 137	74.40 161	90.49 160	55.52 181	94.57 190	74.73 153	60.43 328	91.48 181

hse-mvs2		81.12 129	81.11 117	81.16 218	86.52 220	57.48 303	89.40 241	91.16 169	81.45 36	82.73 77	90.49 160	60.11 128	94.58 188	87.69 51	60.41 329	91.41 183

RPSCF		64.24 317	61.98 319	71.01 335	76.10 345	45.00 365	75.83 352	75.94 352	46.94 365	58.96 315	84.59 241	31.40 344	82.00 364	47.76 322	60.33 330	86.04 271

miper_lstm_enhance		73.05 251	71.73 254	77.03 290	83.80 266	58.32 292	81.76 314	88.88 261	69.80 239	61.01 302	78.23 316	57.19 157	87.51 331	65.34 240	59.53 331	85.27 290

CP-MVSNet		70.50 273	69.91 269	72.26 327	80.71 297	51.00 339	87.23 277	90.30 202	67.84 259	59.64 309	82.69 261	50.23 234	82.30 362	51.28 303	59.28 332	83.46 307

PS-CasMVS		69.86 280	69.13 275	72.07 331	80.35 302	50.57 341	87.02 279	89.75 223	67.27 265	59.19 313	82.28 265	46.58 265	82.24 363	50.69 305	59.02 333	83.39 309

pm-mvs1		72.89 254	71.09 258	78.26 275	79.10 320	57.62 301	90.80 202	89.30 240	67.66 261	62.91 293	81.78 272	49.11 247	92.95 242	60.29 273	58.89 334	84.22 298

Anonymous20240521		62.09 324	59.08 327	71.10 334	67.19 370	48.72 351	83.91 296	85.23 315	50.38 356	47.84 358	71.22 355	20.74 368	85.51 342	46.47 327	58.75 335	79.06 352

WR-MVS_H		70.59 272	69.94 268	72.53 324	81.03 293	51.43 336	87.35 275	92.03 130	67.38 264	60.23 307	80.70 291	55.84 179	83.45 354	46.33 328	58.58 336	82.72 318

PEN-MVS		69.46 283	68.56 277	72.17 329	79.27 315	49.71 345	86.90 281	89.24 242	67.24 268	59.08 314	82.51 264	47.23 261	83.54 353	48.42 316	57.12 337	83.25 310

EU-MVSNet		64.01 318	63.01 312	67.02 349	74.40 351	38.86 380	83.27 303	86.19 307	45.11 369	54.27 334	81.15 288	36.91 323	80.01 370	48.79 315	57.02 338	82.19 327

AllTest		61.66 325	58.06 329	72.46 325	79.57 310	51.42 337	80.17 331	68.61 372	51.25 353	45.88 361	81.23 283	19.86 372	86.58 336	38.98 355	57.01 339	79.39 349

TestCases				72.46 325	79.57 310	51.42 337		68.61 372	51.25 353	45.88 361	81.23 283	19.86 372	86.58 336	38.98 355	57.01 339	79.39 349

Patchmtry		67.53 300	63.93 307	78.34 272	82.12 286	64.38 172	68.72 364	84.00 326	48.23 363	59.24 311	72.41 346	57.82 152	89.27 313	46.10 329	56.68 341	81.36 331

our_test_3		68.29 293	64.69 301	79.11 267	78.92 321	64.85 161	88.40 259	85.06 316	60.32 320	52.68 340	76.12 334	40.81 294	89.80 311	44.25 337	55.65 342	82.67 322

FPMVS		45.64 345	43.10 349	53.23 363	51.42 387	36.46 381	64.97 372	71.91 365	29.13 383	27.53 383	61.55 372	9.83 385	65.01 387	16.00 389	55.58 343	58.22 379

DTE-MVSNet		68.46 292	67.33 285	71.87 333	77.94 335	49.00 350	86.16 286	88.58 275	66.36 272	58.19 318	82.21 267	46.36 266	83.87 351	44.97 335	55.17 344	82.73 317

MIMVSNet1		60.16 331	57.33 332	68.67 342	69.71 365	44.13 367	78.92 338	84.21 322	55.05 344	44.63 368	71.85 350	23.91 362	81.54 366	32.63 373	55.03 345	80.35 342

pmmvs6		67.57 299	64.76 300	76.00 300	72.82 357	53.37 328	88.71 253	86.78 302	53.19 348	57.58 325	78.03 318	35.33 329	92.41 267	55.56 290	54.88 346	82.21 326

TinyColmap		60.32 329	56.42 336	72.00 332	78.78 324	53.18 329	78.36 342	75.64 354	52.30 349	41.59 374	75.82 337	14.76 379	88.35 320	35.84 361	54.71 347	74.46 366

test20.03		63.83 319	62.65 315	67.38 348	70.58 364	39.94 376	86.57 284	84.17 323	63.29 294	51.86 343	77.30 322	37.09 321	82.47 360	38.87 357	54.13 348	79.73 347

OurMVSNet-221017-0		64.68 314	62.17 318	72.21 328	76.08 346	47.35 356	80.67 325	81.02 341	56.19 340	51.60 344	79.66 308	27.05 357	88.56 317	53.60 299	53.63 349	80.71 339

test_fmvs3		56.82 335	54.86 338	62.69 354	53.59 384	35.47 382	75.87 351	65.64 377	43.91 372	55.10 331	71.43 354	6.91 390	74.40 375	68.64 205	52.63 350	78.20 359

Patchmatch-RL test		68.17 294	64.49 304	79.19 263	71.22 359	53.93 326	70.07 362	71.54 368	69.22 245	56.79 327	62.89 368	56.58 170	88.61 315	69.53 195	52.61 351	95.03 76

ppachtmachnet_test		67.72 297	63.70 308	79.77 254	78.92 321	66.04 131	88.68 254	82.90 336	60.11 322	55.45 330	75.96 335	39.19 299	90.55 297	39.53 353	52.55 352	82.71 319

LF4IMVS		54.01 339	52.12 340	59.69 355	62.41 377	39.91 378	68.59 365	68.28 374	42.96 375	44.55 369	75.18 338	14.09 381	68.39 381	41.36 348	51.68 353	70.78 371

N_pmnet		50.55 340	49.11 343	54.88 361	77.17 340	4.02 404	84.36 293	2.00 402	48.59 360	45.86 363	68.82 358	32.22 340	82.80 359	31.58 376	51.38 354	77.81 360

pmmvs-eth3d		65.53 312	62.32 317	75.19 304	69.39 367	59.59 275	82.80 310	83.43 331	62.52 303	51.30 347	72.49 344	32.86 336	87.16 334	55.32 291	50.73 355	78.83 355

CL-MVSNet_self_test		69.92 278	68.09 282	75.41 302	73.25 354	55.90 316	90.05 225	89.90 218	69.96 236	61.96 300	76.54 329	51.05 227	87.64 328	49.51 312	50.59 356	82.70 320

PM-MVS		59.40 332	56.59 334	67.84 344	63.63 374	41.86 371	76.76 347	63.22 379	59.01 327	51.07 348	72.27 349	11.72 382	83.25 356	61.34 266	50.28 357	78.39 358

MDA-MVSNet_test_wron		63.78 320	60.16 323	74.64 308	78.15 333	60.41 264	83.49 299	84.03 324	56.17 342	39.17 376	71.59 352	37.22 318	83.24 357	42.87 342	48.73 358	80.26 344

YYNet1		63.76 321	60.14 324	74.62 309	78.06 334	60.19 269	83.46 301	83.99 328	56.18 341	39.25 375	71.56 353	37.18 319	83.34 355	42.90 341	48.70 359	80.32 343

KD-MVS_self_test		60.87 328	58.60 328	67.68 346	66.13 372	39.93 377	75.63 353	84.70 319	57.32 334	49.57 353	68.45 359	29.55 349	82.87 358	48.09 317	47.94 360	80.25 345

SixPastTwentyTwo		64.92 313	61.78 320	74.34 312	78.74 325	49.76 344	83.42 302	79.51 348	62.86 299	50.27 350	77.35 321	30.92 348	90.49 299	45.89 330	47.06 361	82.78 315

new_pmnet		49.31 341	46.44 344	57.93 356	62.84 376	40.74 374	68.47 366	62.96 380	36.48 378	35.09 378	57.81 375	14.97 378	72.18 377	32.86 371	46.44 362	60.88 378

EGC-MVSNET		42.35 347	38.09 350	55.11 360	74.57 349	46.62 361	71.63 359	55.77 383	0.04 397	0.24 398	62.70 369	14.24 380	74.91 374	17.59 386	46.06 363	43.80 383

TransMVSNet (Re)		70.07 277	67.66 283	77.31 287	80.62 300	59.13 285	91.78 162	84.94 318	65.97 274	60.08 308	80.44 296	50.78 228	91.87 280	48.84 314	45.46 364	80.94 336

ambc				69.61 338	61.38 379	41.35 373	49.07 387	85.86 311		50.18 352	66.40 362	10.16 384	88.14 322	45.73 331	44.20 365	79.32 351

TDRefinement		55.28 338	51.58 341	66.39 350	59.53 381	46.15 362	76.23 350	72.80 362	44.60 370	42.49 372	76.28 333	15.29 377	82.39 361	33.20 369	43.75 366	70.62 372

Gipuma		34.91 354	31.44 357	45.30 370	70.99 361	39.64 379	19.85 392	72.56 363	20.10 388	16.16 392	21.47 393	5.08 393	71.16 378	13.07 390	43.70 367	25.08 390
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		46.58 343	43.45 347	55.96 358	45.18 391	32.05 386	61.18 376	49.49 390	33.39 380	42.05 373	62.48 370	7.00 389	65.56 385	47.08 325	43.21 368	70.27 373

MDA-MVSNet-bldmvs		61.54 327	57.70 331	73.05 320	79.53 312	57.00 310	83.08 307	81.23 340	57.57 331	34.91 379	72.45 345	32.79 337	86.26 338	35.81 362	41.95 369	75.89 364

new-patchmatchnet		59.30 333	56.48 335	67.79 345	65.86 373	44.19 366	82.47 311	81.77 338	59.94 323	43.65 371	66.20 363	27.67 355	81.68 365	39.34 354	41.40 370	77.50 361

UnsupCasMVSNet_eth		65.79 309	63.10 311	73.88 314	70.71 362	50.29 343	81.09 322	89.88 219	72.58 171	49.25 355	74.77 341	32.57 339	87.43 332	55.96 289	41.04 371	83.90 301

test_vis3_rt		40.46 350	37.79 351	48.47 368	44.49 392	33.35 385	66.56 371	32.84 399	32.39 381	29.65 381	39.13 389	3.91 397	68.65 380	50.17 307	40.99 372	43.40 384

pmmvs3		55.51 337	51.50 342	67.53 347	57.90 382	50.93 340	80.37 327	73.66 360	40.63 377	44.15 370	64.75 366	16.30 374	78.97 371	44.77 336	40.98 373	72.69 368

APD_test1		40.50 349	37.31 352	50.09 366	51.88 385	35.27 383	59.45 380	52.59 387	21.64 386	26.12 384	57.80 376	4.56 394	66.56 383	22.64 382	39.09 374	48.43 382

UnsupCasMVSNet_bld		61.60 326	57.71 330	73.29 319	68.73 368	51.64 334	78.61 339	89.05 255	57.20 335	46.11 360	61.96 371	28.70 353	88.60 316	50.08 309	38.90 375	79.63 348

PMVS	26.43 22	31.84 357	28.16 360	42.89 371	25.87 400	27.58 392	50.92 386	49.78 389	21.37 387	14.17 393	40.81 388	2.01 400	66.62 382	9.61 393	38.88 376	34.49 389
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
K. test v3		63.09 322	59.61 326	73.53 317	76.26 344	49.38 349	83.27 303	77.15 350	64.35 285	47.77 359	72.32 348	28.73 352	87.79 326	49.93 310	36.69 377	83.41 308

KD-MVS_2432*1600		69.03 286	66.37 289	77.01 291	85.56 238	61.06 249	81.44 319	90.25 204	67.27 265	58.00 321	76.53 330	54.49 192	87.63 329	48.04 318	35.77 378	82.34 324

miper_refine_blended		69.03 286	66.37 289	77.01 291	85.56 238	61.06 249	81.44 319	90.25 204	67.27 265	58.00 321	76.53 330	54.49 192	87.63 329	48.04 318	35.77 378	82.34 324

mvsany_test3		48.86 342	46.35 345	56.41 357	46.00 390	31.67 387	62.26 375	47.25 392	43.71 373	45.54 365	68.15 360	10.84 383	64.44 389	57.95 282	35.44 380	73.13 367

LCM-MVSNet		40.54 348	35.79 353	54.76 362	36.92 397	30.81 388	51.41 385	69.02 371	22.07 385	24.63 385	45.37 382	4.56 394	65.81 384	33.67 367	34.50 381	67.67 374

test_method		38.59 352	35.16 355	48.89 367	54.33 383	21.35 397	45.32 388	53.71 386	7.41 394	28.74 382	51.62 378	8.70 387	52.87 392	33.73 366	32.89 382	72.47 369

lessismore_v0				73.72 316	72.93 356	47.83 354		61.72 381		45.86 363	73.76 342	28.63 354	89.81 309	47.75 323	31.37 383	83.53 304

testf1		32.77 355	29.47 358	42.67 372	41.89 394	30.81 388	52.07 383	43.45 393	15.45 389	18.52 389	44.82 383	2.12 398	58.38 390	16.05 387	30.87 384	38.83 385

APD_test2		32.77 355	29.47 358	42.67 372	41.89 394	30.81 388	52.07 383	43.45 393	15.45 389	18.52 389	44.82 383	2.12 398	58.38 390	16.05 387	30.87 384	38.83 385

PVSNet_0	68.08 15	71.81 264	68.32 281	82.27 189	84.68 251	62.31 227	88.68 254	90.31 201	75.84 115	57.93 323	80.65 294	37.85 313	94.19 207	69.94 190	29.05 386	90.31 201

WB-MVS		46.23 344	44.94 346	50.11 365	62.13 378	21.23 398	76.48 349	55.49 384	45.89 367	35.78 377	61.44 373	35.54 327	72.83 376	9.96 392	21.75 387	56.27 380

SSC-MVS		44.51 346	43.35 348	47.99 369	61.01 380	18.90 400	74.12 355	54.36 385	43.42 374	34.10 380	60.02 374	34.42 332	70.39 379	9.14 394	19.57 388	54.68 381

DeepMVS_CX				34.71 375	51.45 386	24.73 395		28.48 401	31.46 382	17.49 391	52.75 377	5.80 392	42.60 396	18.18 385	19.42 389	36.81 388

PMMVS2		37.93 353	33.61 356	50.92 364	46.31 389	24.76 394	60.55 379	50.05 388	28.94 384	20.93 386	47.59 379	4.41 396	65.13 386	25.14 380	18.55 390	62.87 377

MVE	24.84 23	24.35 359	19.77 365	38.09 374	34.56 399	26.92 393	26.57 390	38.87 397	11.73 393	11.37 394	27.44 390	1.37 401	50.42 393	11.41 391	14.60 391	36.93 387
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		24.61 358	24.00 362	26.45 376	43.74 393	18.44 401	60.86 377	39.66 395	15.11 391	9.53 395	22.10 392	6.52 391	46.94 394	8.31 395	10.14 392	13.98 392

EMVS		23.76 360	23.20 364	25.46 377	41.52 396	16.90 402	60.56 378	38.79 398	14.62 392	8.99 396	20.24 395	7.35 388	45.82 395	7.25 396	9.46 393	13.64 393

tmp_tt		22.26 361	23.75 363	17.80 378	5.23 401	12.06 403	35.26 389	39.48 396	2.82 396	18.94 387	44.20 385	22.23 366	24.64 397	36.30 359	9.31 394	16.69 391

ANet_high		40.27 351	35.20 354	55.47 359	34.74 398	34.47 384	63.84 374	71.56 367	48.42 361	18.80 388	41.08 387	9.52 386	64.45 388	20.18 384	8.66 395	67.49 375

wuyk23d		11.30 363	10.95 366	12.33 379	48.05 388	19.89 399	25.89 391	1.92 403	3.58 395	3.12 397	1.37 397	0.64 402	15.77 398	6.23 397	7.77 396	1.35 394

testmvs		7.23 365	9.62 368	0.06 381	0.04 402	0.02 406	84.98 291	0.02 404	0.03 398	0.18 399	1.21 398	0.01 404	0.02 399	0.14 398	0.01 397	0.13 396

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

cdsmvs_eth3d_5k		19.86 362	26.47 361	0.00 382	0.00 404	0.00 407	0.00 393	93.45 77	0.00 400	0.00 401	95.27 54	49.56 239	0.00 401	0.00 400	0.00 398	0.00 397

pcd_1.5k_mvsjas		4.46 367	5.95 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	53.55 204	0.00 401	0.00 400	0.00 398	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

test123		6.92 366	9.21 369	0.08 380	0.03 403	0.05 405	81.65 317	0.01 405	0.02 399	0.14 400	0.85 399	0.03 403	0.02 399	0.12 399	0.00 398	0.16 395

ab-mvs-re		7.91 364	10.55 367	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	94.95 62	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 398	0.00 397

WAC-MVS						49.45 347								31.56 377

FOURS1					93.95 45	61.77 236	93.96 68	91.92 134	62.14 306	86.57 42

test_one_0601					96.32 18	69.74 42		94.18 51	71.42 213	90.67 16	96.85 14	74.45 18

eth-test2					0.00 404

eth-test					0.00 404

test_241102_ONE					96.45 12	69.38 47		94.44 40	71.65 202	92.11 4	97.05 7	76.79 9	99.11 6

save fliter					93.84 48	67.89 85	95.05 39	92.66 107	78.19 82

test0726					96.40 15	69.99 33	96.76 7	94.33 48	71.92 189	91.89 8	97.11 6	73.77 21

GSMVS																94.68 87

test_part2					96.29 19	68.16 79				90.78 14

sam_mvs1												57.85 151				94.68 87

sam_mvs												54.91 189

MTGPA								92.23 120

test_post1							78.95 337				20.70 394	53.05 209	91.50 293	60.43 271

test_post											23.01 391	56.49 171	92.67 257

patchmatchnet-post											67.62 361	57.62 154	90.25 301

MTMP							93.77 82	32.52 400

gm-plane-assit					88.42 176	67.04 108			78.62 79		91.83 138		97.37 70	76.57 137

TEST9					94.18 41	67.28 100	94.16 56	93.51 73	71.75 200	85.52 52	95.33 49	68.01 43	97.27 80

test_8					94.19 40	67.19 102	94.15 59	93.42 79	71.87 194	85.38 55	95.35 48	68.19 41	96.95 100

agg_prior					94.16 43	66.97 110		93.31 82		84.49 63			96.75 109

test_prior4						67.18 104	93.92 71

test_prior				86.42 67	94.71 35	67.35 99		93.10 92					96.84 106			95.05 74

旧先验2							92.00 152		59.37 326	87.54 36			93.47 234	75.39 144

新几何2							91.41 173

无先验							92.71 119	92.61 111	62.03 307				97.01 91	66.63 222		93.97 117

原ACMM2							92.01 149

testdata2													96.09 127	61.26 267

segment_acmp												65.94 59

testdata1							89.21 245		77.55 95

plane_prior7					86.94 214	61.51 242

plane_prior6					87.23 208	62.32 226						50.66 229

plane_prior4											89.14 181

plane_prior3						61.95 234			79.09 69	72.53 182

plane_prior2							93.13 103		78.81 76

plane_prior1					87.15 210

n2								0.00 406

nn								0.00 406

door-mid								66.01 376

test11								93.01 94

door								66.57 375

HQP5-MVS						63.66 194

HQP-NCC					87.54 201		94.06 61		79.80 54	74.18 162

ACMP_Plane					87.54 201		94.06 61		79.80 54	74.18 162

BP-MVS														77.63 132

HQP4-MVS										74.18 162			95.61 151			88.63 223

HQP2-MVS												51.63 222

NP-MVS					87.41 204	63.04 208					90.30 164

MDTV_nov1_ep13_2view						59.90 272	80.13 332		67.65 262	72.79 177		54.33 197		59.83 275		92.58 158

Test By Simon												54.21 198

High-resolution multi-view benchmark