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.

DP-MVS Recon		91.72 75	90.85 84	94.34 34	99.50 1	85.00 64	98.51 35	95.96 143	80.57 239	88.08 136	97.63 78	76.84 116	99.89 7	85.67 154	94.88 116	98.13 74

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 23	97.10 31	95.17 3	92.11 78	98.46 26	87.33 24	99.97 2	97.21 28	99.31 4	99.63 7

MG-MVS		94.25 27	93.72 33	95.85 11	99.38 3	89.35 11	97.98 59	98.09 9	89.99 51	92.34 74	96.97 108	81.30 58	98.99 107	88.54 129	98.88 20	99.20 22

AdaColmap		88.81 137	87.61 148	92.39 108	99.33 4	79.95 171	96.70 159	95.58 163	77.51 292	83.05 188	96.69 121	61.90 261	99.72 43	84.29 164	93.47 137	97.50 123

CNVR-MVS		96.30 1	96.54 1	95.55 15	99.31 5	87.69 22	99.06 16	97.12 29	94.66 5	96.79 16	98.78 9	86.42 29	99.95 3	97.59 23	99.18 7	99.00 27

NCCC		95.63 6	95.94 8	94.69 28	99.21 6	85.15 59	99.16 6	96.96 38	94.11 9	95.59 32	98.64 17	85.07 33	99.91 4	95.61 45	99.10 9	99.00 27

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 11				98.54 20	92.06 3	99.84 12	99.11 2	99.37 1	99.74 1

ZD-MVS					99.09 8	83.22 97		96.60 82	82.88 200	93.61 61	98.06 50	82.93 50	99.14 97	95.51 48	98.49 37

DVP-MVS++		96.05 4	96.41 3	94.96 22	99.05 9	85.34 49	98.13 49	96.77 56	88.38 73	97.70 8	98.77 10	92.06 3	99.84 12	97.47 24	99.37 1	99.70 3

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 47					99.81 21	98.08 14	98.81 24	99.43 11

No_MVS				97.14 3	99.05 9	92.19 4		96.83 47					99.81 21	98.08 14	98.81 24	99.43 11

DVP-MVS		95.58 8	95.91 9	94.57 30	99.05 9	85.18 54	99.06 16	96.46 97	88.75 64	96.69 17	98.76 12	87.69 22	99.76 31	97.90 17	98.85 21	98.77 34
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
test0726					99.05 9	85.18 54	99.11 14	96.78 50	88.75 64	97.65 11	98.91 2	87.69 22

test_0728_SECOND				95.14 18	99.04 14	86.14 35	99.06 16	96.77 56					99.84 12	97.90 17	98.85 21	99.45 10

SED-MVS		95.88 5	96.22 4	94.87 23	99.03 15	85.03 62	99.12 11	96.78 50	88.72 66	97.79 6	98.91 2	88.48 17	99.82 18	98.15 11	98.97 17	99.74 1

IU-MVS					99.03 15	85.34 49		96.86 46	92.05 27	98.74 1				98.15 11	98.97 17	99.42 13

test_241102_ONE					99.03 15	85.03 62		96.78 50	88.72 66	97.79 6	98.90 5	88.48 17	99.82 18

test_one_0601					98.91 18	84.56 72		96.70 66	88.06 79	96.57 22	98.77 10	88.04 20

test_part2					98.90 19	85.14 60				96.07 28

PAPR		92.74 51	92.17 65	94.45 32	98.89 20	84.87 67	97.20 113	96.20 124	87.73 88	88.40 131	98.12 43	78.71 87	99.76 31	87.99 136	96.28 97	98.74 35

DeepC-MVS_fast	89.06 2	94.48 23	94.30 28	95.02 20	98.86 21	85.68 44	98.06 55	96.64 76	93.64 12	91.74 84	98.54 20	80.17 69	99.90 5	92.28 84	98.75 28	99.49 8
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		94.56 22	94.75 19	93.96 46	98.84 22	83.40 93	98.04 57	96.41 103	85.79 125	95.00 42	98.28 34	84.32 41	99.18 94	97.35 26	98.77 27	99.28 19
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		95.32 10	95.55 11	94.64 29	98.79 23	84.87 67	97.77 72	96.74 61	86.11 117	96.54 23	98.89 6	88.39 19	99.74 38	97.67 22	99.05 12	99.31 18
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APD-MVS		93.61 36	93.59 37	93.69 56	98.76 24	83.26 96	97.21 111	96.09 132	82.41 211	94.65 48	98.21 36	81.96 56	98.81 119	94.65 56	98.36 45	99.01 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
HFP-MVS		92.89 48	92.86 50	92.98 83	98.71 25	81.12 139	97.58 86	96.70 66	85.20 138	91.75 83	97.97 57	78.47 89	99.71 45	90.95 95	98.41 41	98.12 75

region2R		92.72 54	92.70 52	92.79 91	98.68 26	80.53 159	97.53 90	96.51 91	85.22 136	91.94 81	97.98 55	77.26 108	99.67 53	90.83 99	98.37 44	98.18 69

test_prior				93.09 79	98.68 26	81.91 119		96.40 105					99.06 104			98.29 64

ACMMPR		92.69 56	92.67 53	92.75 92	98.66 28	80.57 155	97.58 86	96.69 68	85.20 138	91.57 85	97.92 58	77.01 113	99.67 53	90.95 95	98.41 41	98.00 84

API-MVS		90.18 110	88.97 122	93.80 50	98.66 28	82.95 101	97.50 94	95.63 162	75.16 312	86.31 151	97.69 70	72.49 188	99.90 5	81.26 195	96.07 102	98.56 47

CDPH-MVS		93.12 42	92.91 48	93.74 52	98.65 30	83.88 81	97.67 81	96.26 118	83.00 197	93.22 65	98.24 35	81.31 57	99.21 88	89.12 124	98.74 29	98.14 73

TEST9					98.64 31	83.71 85	97.82 68	96.65 73	84.29 165	95.16 35	98.09 45	84.39 37	99.36 81

train_agg		94.28 25	94.45 24	93.74 52	98.64 31	83.71 85	97.82 68	96.65 73	84.50 156	95.16 35	98.09 45	84.33 38	99.36 81	95.91 41	98.96 19	98.16 71

test_8					98.63 33	83.64 88	97.81 70	96.63 78	84.50 156	95.10 39	98.11 44	84.33 38	99.23 86

HPM-MVS++		95.32 10	95.48 13	94.85 24	98.62 34	86.04 36	97.81 70	96.93 41	92.45 20	95.69 31	98.50 24	85.38 31	99.85 10	94.75 54	99.18 7	98.65 43

agg_prior					98.59 35	83.13 98		96.56 87		94.19 53			99.16 96

CSCG		92.02 69	91.65 74	93.12 77	98.53 36	80.59 154	97.47 95	97.18 26	77.06 300	84.64 169	97.98 55	83.98 43	99.52 69	90.72 101	97.33 76	99.23 21

XVS		92.69 56	92.71 51	92.63 99	98.52 37	80.29 162	97.37 105	96.44 99	87.04 105	91.38 87	97.83 66	77.24 110	99.59 60	90.46 105	98.07 52	98.02 79

X-MVStestdata		86.26 186	84.14 205	92.63 99	98.52 37	80.29 162	97.37 105	96.44 99	87.04 105	91.38 87	20.73 400	77.24 110	99.59 60	90.46 105	98.07 52	98.02 79

FOURS1					98.51 39	78.01 228	98.13 49	96.21 123	83.04 195	94.39 51

CP-MVS		92.54 61	92.60 55	92.34 109	98.50 40	79.90 173	98.40 38	96.40 105	84.75 147	90.48 104	98.09 45	77.40 107	99.21 88	91.15 94	98.23 50	97.92 90

PAPM_NR		91.46 81	90.82 85	93.37 70	98.50 40	81.81 125	95.03 244	96.13 129	84.65 152	86.10 154	97.65 76	79.24 78	99.75 36	83.20 183	96.88 86	98.56 47

MAR-MVS		90.63 101	90.22 99	91.86 134	98.47 42	78.20 224	97.18 115	96.61 79	83.87 177	88.18 135	98.18 38	68.71 217	99.75 36	83.66 177	97.15 80	97.63 113
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
patch_mono-2		95.14 12	96.08 7	92.33 111	98.44 43	77.84 236	98.43 36	97.21 23	92.58 19	97.68 10	97.65 76	86.88 26	99.83 16	98.25 9	97.60 67	99.33 17

mPP-MVS		91.88 71	91.82 70	92.07 125	98.38 44	78.63 208	97.29 108	96.09 132	85.12 140	88.45 130	97.66 72	75.53 142	99.68 51	89.83 115	98.02 55	97.88 91

SR-MVS		92.16 66	92.27 61	91.83 137	98.37 45	78.41 214	96.67 160	95.76 154	82.19 215	91.97 79	98.07 49	76.44 124	98.64 123	93.71 66	97.27 78	98.45 54

test12				94.25 37	98.34 46	85.55 46		96.35 112		92.36 73		80.84 59	99.22 87		98.31 47	97.98 86

CPTT-MVS		89.72 118	89.87 111	89.29 206	98.33 47	73.30 298	97.70 78	95.35 180	75.68 308	87.40 140	97.44 88	70.43 210	98.25 143	89.56 120	96.90 84	96.33 172

MSP-MVS		95.62 7	96.54 1	92.86 88	98.31 48	80.10 170	97.42 102	96.78 50	92.20 22	97.11 14	98.29 33	93.46 1	99.10 101	96.01 38	99.30 5	99.38 14
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
MSLP-MVS++		94.28 25	94.39 26	93.97 45	98.30 49	84.06 80	98.64 31	96.93 41	90.71 40	93.08 67	98.70 15	79.98 71	99.21 88	94.12 62	99.07 11	98.63 44

PGM-MVS		91.93 70	91.80 71	92.32 113	98.27 50	79.74 179	95.28 228	97.27 21	83.83 178	90.89 99	97.78 68	76.12 131	99.56 66	88.82 127	97.93 60	97.66 110

ZNCC-MVS		92.75 50	92.60 55	93.23 74	98.24 51	81.82 124	97.63 82	96.50 93	85.00 144	91.05 95	97.74 69	78.38 90	99.80 25	90.48 104	98.34 46	98.07 77

save fliter					98.24 51	83.34 94	98.61 33	96.57 85	91.32 32

114514_t		88.79 139	87.57 149	92.45 104	98.21 53	81.74 127	96.99 133	95.45 172	75.16 312	82.48 191	95.69 139	68.59 218	98.50 130	80.33 201	95.18 114	97.10 143

GST-MVS		92.43 63	92.22 64	93.04 81	98.17 54	81.64 131	97.40 104	96.38 108	84.71 150	90.90 98	97.40 90	77.55 105	99.76 31	89.75 117	97.74 63	97.72 105

DP-MVS		81.47 265	78.28 282	91.04 160	98.14 55	78.48 210	95.09 243	86.97 361	61.14 372	71.12 314	92.78 209	59.59 272	99.38 78	53.11 363	86.61 196	95.27 197

MP-MVS		92.61 59	92.67 53	92.42 107	98.13 56	79.73 180	97.33 107	96.20 124	85.63 127	90.53 102	97.66 72	78.14 95	99.70 48	92.12 86	98.30 48	97.85 95
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
9.14			94.26 29		98.10 57		98.14 46	96.52 90	84.74 148	94.83 46	98.80 7	82.80 52	99.37 80	95.95 40	98.42 40

PHI-MVS		93.59 37	93.63 36	93.48 67	98.05 58	81.76 126	98.64 31	97.13 27	82.60 207	94.09 55	98.49 25	80.35 64	99.85 10	94.74 55	98.62 32	98.83 32

SMA-MVS		94.70 20	94.68 20	94.76 26	98.02 59	85.94 39	97.47 95	96.77 56	85.32 133	97.92 3	98.70 15	83.09 49	99.84 12	95.79 42	99.08 10	98.49 51
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
PLC	83.97 7	88.00 159	87.38 155	89.83 198	98.02 59	76.46 262	97.16 119	94.43 229	79.26 271	81.98 202	96.28 126	69.36 215	99.27 84	77.71 227	92.25 153	93.77 225
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MTAPA		92.45 62	92.31 60	92.86 88	97.90 61	80.85 148	92.88 295	96.33 113	87.92 83	90.20 107	98.18 38	76.71 121	99.76 31	92.57 83	98.09 51	97.96 89

APD-MVS_3200maxsize		91.23 88	91.35 78	90.89 166	97.89 62	76.35 265	96.30 183	95.52 167	79.82 258	91.03 96	97.88 63	74.70 161	98.54 128	92.11 87	96.89 85	97.77 102

HPM-MVS		91.62 78	91.53 76	91.89 133	97.88 63	79.22 192	96.99 133	95.73 157	82.07 217	89.50 118	97.19 99	75.59 140	98.93 114	90.91 97	97.94 58	97.54 117
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SD-MVS		94.84 17	95.02 18	94.29 36	97.87 64	84.61 70	97.76 74	96.19 126	89.59 56	96.66 19	98.17 41	84.33 38	99.60 59	96.09 37	98.50 36	98.66 42
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
dcpmvs_2		93.10 43	93.46 41	92.02 129	97.77 65	79.73 180	94.82 248	93.86 261	86.91 107	91.33 90	96.76 117	85.20 32	98.06 148	96.90 32	97.60 67	98.27 66

原ACMM1				91.22 156	97.77 65	78.10 226		96.61 79	81.05 229	91.28 92	97.42 89	77.92 99	98.98 108	79.85 209	98.51 34	96.59 163

SR-MVS-dyc-post		91.29 86	91.45 77	90.80 168	97.76 67	76.03 270	96.20 190	95.44 173	80.56 240	90.72 100	97.84 64	75.76 137	98.61 124	91.99 88	96.79 89	97.75 103

RE-MVS-def			91.18 82		97.76 67	76.03 270	96.20 190	95.44 173	80.56 240	90.72 100	97.84 64	73.36 181		91.99 88	96.79 89	97.75 103

TSAR-MVS + MP.		94.79 19	95.17 17	93.64 57	97.66 69	84.10 79	95.85 208	96.42 102	91.26 33	97.49 12	96.80 116	86.50 28	98.49 131	95.54 47	99.03 13	98.33 59
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS_fast		90.38 108	90.17 102	91.03 161	97.61 70	77.35 248	97.15 121	95.48 169	79.51 264	88.79 125	96.90 109	71.64 199	98.81 119	87.01 147	97.44 72	96.94 148

EI-MVSNet-Vis-set		91.84 72	91.77 72	92.04 128	97.60 71	81.17 138	96.61 161	96.87 44	88.20 77	89.19 119	97.55 84	78.69 88	99.14 97	90.29 111	90.94 163	95.80 182

CNLPA		86.96 173	85.37 182	91.72 140	97.59 72	79.34 190	97.21 111	91.05 329	74.22 318	78.90 234	96.75 119	67.21 226	98.95 111	74.68 260	90.77 164	96.88 153

ACMMP		90.39 106	89.97 106	91.64 142	97.58 73	78.21 223	96.78 152	96.72 64	84.73 149	84.72 167	97.23 97	71.22 202	99.63 57	88.37 134	92.41 151	97.08 144
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
SF-MVS		94.17 28	94.05 32	94.55 31	97.56 74	85.95 37	97.73 76	96.43 101	84.02 170	95.07 41	98.74 14	82.93 50	99.38 78	95.42 49	98.51 34	98.32 60

CANet		94.89 15	94.64 21	95.63 13	97.55 75	88.12 16	99.06 16	96.39 107	94.07 10	95.34 34	97.80 67	76.83 118	99.87 8	97.08 30	97.64 66	98.89 30

PVSNet_BlendedMVS		90.05 112	89.96 107	90.33 182	97.47 76	83.86 82	98.02 58	96.73 62	87.98 81	89.53 116	89.61 256	76.42 125	99.57 64	94.29 59	79.59 253	87.57 320

PVSNet_Blended		93.13 41	92.98 47	93.57 61	97.47 76	83.86 82	99.32 1	96.73 62	91.02 38	89.53 116	96.21 127	76.42 125	99.57 64	94.29 59	95.81 109	97.29 135

新几何1				93.12 77	97.44 78	81.60 133		96.71 65	74.54 317	91.22 93	97.57 80	79.13 80	99.51 71	77.40 234	98.46 38	98.26 67

LS3D		82.22 255	79.94 270	89.06 209	97.43 79	74.06 294	93.20 290	92.05 312	61.90 366	73.33 297	95.21 153	59.35 275	99.21 88	54.54 359	92.48 150	93.90 223

test_yl		91.46 81	90.53 91	94.24 38	97.41 80	85.18 54	98.08 52	97.72 12	80.94 230	89.85 108	96.14 128	75.61 138	98.81 119	90.42 109	88.56 180	98.74 35

DCV-MVSNet		91.46 81	90.53 91	94.24 38	97.41 80	85.18 54	98.08 52	97.72 12	80.94 230	89.85 108	96.14 128	75.61 138	98.81 119	90.42 109	88.56 180	98.74 35

EI-MVSNet-UG-set		91.35 85	91.22 79	91.73 139	97.39 82	80.68 152	96.47 170	96.83 47	87.92 83	88.30 134	97.36 91	77.84 100	99.13 99	89.43 122	89.45 170	95.37 193

旧先验1					97.39 82	79.58 184		96.54 88			98.08 48	84.00 42			97.42 74	97.62 114

TSAR-MVS + GP.		94.35 24	94.50 22	93.89 47	97.38 84	83.04 100	98.10 51	95.29 183	91.57 30	93.81 57	97.45 85	86.64 27	99.43 76	96.28 36	94.01 128	99.20 22

MVS_111021_HR		93.41 39	93.39 42	93.47 69	97.34 85	82.83 102	97.56 88	98.27 6	89.16 61	89.71 111	97.14 100	79.77 73	99.56 66	93.65 67	97.94 58	98.02 79

MP-MVS-pluss		92.58 60	92.35 59	93.29 71	97.30 86	82.53 106	96.44 173	96.04 137	84.68 151	89.12 121	98.37 29	77.48 106	99.74 38	93.31 73	98.38 43	97.59 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
EPNet		94.06 31	94.15 30	93.76 51	97.27 87	84.35 74	98.29 41	97.64 15	94.57 6	95.36 33	96.88 111	79.96 72	99.12 100	91.30 92	96.11 101	97.82 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		93.46 38	93.23 44	94.17 41	97.16 88	84.28 77	96.82 149	96.65 73	86.24 115	94.27 52	97.99 52	77.94 97	99.83 16	93.39 69	98.57 33	98.39 57

LFMVS		89.27 127	87.64 145	94.16 43	97.16 88	85.52 47	97.18 115	94.66 213	79.17 272	89.63 114	96.57 122	55.35 311	98.22 144	89.52 121	89.54 169	98.74 35

DeepPCF-MVS	89.82 1	94.61 21	96.17 5	89.91 195	97.09 90	70.21 328	98.99 22	96.69 68	95.57 2	95.08 40	99.23 1	86.40 30	99.87 8	97.84 20	98.66 31	99.65 6

VNet		92.11 68	91.22 79	94.79 25	96.91 91	86.98 27	97.91 63	97.96 10	86.38 114	93.65 59	95.74 136	70.16 213	98.95 111	93.39 69	88.87 176	98.43 55

TAPA-MVS	81.61 12	85.02 206	83.67 209	89.06 209	96.79 92	73.27 301	95.92 202	94.79 206	74.81 315	80.47 218	96.83 113	71.07 204	98.19 146	49.82 372	92.57 147	95.71 185
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Anonymous202405211		84.41 217	81.93 239	91.85 136	96.78 93	78.41 214	97.44 98	91.34 324	70.29 345	84.06 172	94.26 179	41.09 363	98.96 109	79.46 211	82.65 233	98.17 70

CS-MVS-test		92.98 45	93.67 35	90.90 165	96.52 94	76.87 255	98.68 28	94.73 208	90.36 48	94.84 45	97.89 62	77.94 97	97.15 200	94.28 61	97.80 62	98.70 41

DELS-MVS		94.98 13	94.49 23	96.44 6	96.42 95	90.59 7	99.21 4	97.02 33	94.40 8	91.46 86	97.08 104	83.32 47	99.69 49	92.83 79	98.70 30	99.04 25
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
thres200		88.92 133	87.65 144	92.73 94	96.30 96	85.62 45	97.85 66	98.86 1	84.38 160	84.82 165	93.99 187	75.12 156	98.01 149	70.86 290	86.67 195	94.56 213

CS-MVS		92.73 52	93.48 40	90.48 177	96.27 97	75.93 275	98.55 34	94.93 195	89.32 58	94.54 50	97.67 71	78.91 83	97.02 204	93.80 64	97.32 77	98.49 51

DPM-MVS		96.21 2	95.53 12	98.26 1	96.26 98	95.09 1	99.15 7	96.98 35	93.39 14	96.45 24	98.79 8	90.17 10	99.99 1	89.33 123	99.25 6	99.70 3

tfpn200view9		88.48 146	87.15 159	92.47 103	96.21 99	85.30 52	97.44 98	98.85 2	83.37 187	83.99 174	93.82 190	75.36 149	97.93 151	69.04 298	86.24 202	94.17 215

thres400		88.42 149	87.15 159	92.23 117	96.21 99	85.30 52	97.44 98	98.85 2	83.37 187	83.99 174	93.82 190	75.36 149	97.93 151	69.04 298	86.24 202	93.45 231

test222					96.15 101	78.41 214	95.87 206	96.46 97	71.97 337	89.66 113	97.45 85	76.33 128			98.24 49	98.30 63

HY-MVS	84.06 6	91.63 77	90.37 97	95.39 17	96.12 102	88.25 15	90.22 322	97.58 16	88.33 75	90.50 103	91.96 219	79.26 77	99.06 104	90.29 111	89.07 173	98.88 31

thres100view900		88.30 152	86.95 165	92.33 111	96.10 103	84.90 66	97.14 122	98.85 2	82.69 205	83.41 182	93.66 194	75.43 146	97.93 151	69.04 298	86.24 202	94.17 215

thres600view7		88.06 157	86.70 169	92.15 123	96.10 103	85.17 58	97.14 122	98.85 2	82.70 204	83.41 182	93.66 194	75.43 146	97.82 158	67.13 307	85.88 206	93.45 231

WTY-MVS		92.65 58	91.68 73	95.56 14	96.00 105	88.90 13	98.23 43	97.65 14	88.57 69	89.82 110	97.22 98	79.29 76	99.06 104	89.57 119	88.73 178	98.73 39

MVSTER		89.25 128	88.92 125	90.24 184	95.98 106	84.66 69	96.79 151	95.36 178	87.19 103	80.33 221	90.61 242	90.02 12	95.97 248	85.38 157	78.64 262	90.09 261

testdata				90.13 187	95.92 107	74.17 292		96.49 96	73.49 326	94.82 47	97.99 52	78.80 86	97.93 151	83.53 180	97.52 69	98.29 64

PatchMatch-RL		85.00 207	83.66 210	89.02 211	95.86 108	74.55 289	92.49 299	93.60 277	79.30 269	79.29 233	91.47 225	58.53 282	98.45 135	70.22 294	92.17 155	94.07 220

iter_conf05		90.14 111	89.79 112	91.17 157	95.85 109	86.93 28	97.68 80	88.67 355	89.93 52	81.73 208	92.80 206	90.37 8	96.03 243	90.44 107	80.65 246	90.56 249

testing222		91.09 91	90.49 93	92.87 87	95.82 110	85.04 61	96.51 168	97.28 20	86.05 120	89.13 120	95.34 149	80.16 70	96.62 226	85.82 152	88.31 183	96.96 147

canonicalmvs		92.27 65	91.22 79	95.41 16	95.80 111	88.31 14	97.09 129	94.64 216	88.49 71	92.99 69	97.31 92	72.68 186	98.57 127	93.38 71	88.58 179	99.36 16

Anonymous20240529		83.15 238	80.60 259	90.80 168	95.74 112	78.27 218	96.81 150	94.92 196	60.10 376	81.89 204	92.54 210	45.82 347	98.82 118	79.25 214	78.32 269	95.31 195

MVS_111021_LR		91.60 79	91.64 75	91.47 148	95.74 112	78.79 205	96.15 192	96.77 56	88.49 71	88.64 128	97.07 105	72.33 190	99.19 93	93.13 77	96.48 96	96.43 167

PS-MVSNAJ		94.17 28	93.52 39	96.10 9	95.65 114	92.35 2	98.21 44	95.79 153	92.42 21	96.24 26	98.18 38	71.04 205	99.17 95	96.77 33	97.39 75	96.79 155

iter_conf_final		89.51 121	89.21 118	90.39 179	95.60 115	84.44 73	97.22 109	89.09 348	89.11 62	82.07 201	92.80 206	87.03 25	96.03 243	89.10 125	80.89 242	90.70 247

Anonymous20231211		79.72 283	77.19 291	87.33 251	95.59 116	77.16 253	95.18 237	94.18 244	59.31 379	72.57 305	86.20 308	47.89 341	95.66 268	74.53 264	69.24 319	89.18 279

alignmvs		92.97 46	92.26 62	95.12 19	95.54 117	87.77 20	98.67 29	96.38 108	88.04 80	93.01 68	97.45 85	79.20 79	98.60 125	93.25 74	88.76 177	98.99 29

PVSNet	82.34 9	89.02 130	87.79 142	92.71 95	95.49 118	81.50 134	97.70 78	97.29 19	87.76 87	85.47 158	95.12 160	56.90 300	98.90 115	80.33 201	94.02 127	97.71 107

tpmvs		83.04 241	80.77 254	89.84 197	95.43 119	77.96 230	85.59 356	95.32 182	75.31 311	76.27 266	83.70 337	73.89 173	97.41 182	59.53 339	81.93 240	94.14 217

SteuartSystems-ACMMP		94.13 30	94.44 25	93.20 75	95.41 120	81.35 136	99.02 20	96.59 83	89.50 57	94.18 54	98.36 30	83.68 46	99.45 75	94.77 53	98.45 39	98.81 33
Skip Steuart: Steuart Systems R&D Blog.
EPMVS		87.47 169	85.90 175	92.18 120	95.41 120	82.26 113	87.00 346	96.28 116	85.88 124	84.23 171	85.57 315	75.07 157	96.26 236	71.14 288	92.50 149	98.03 78

BH-RMVSNet		86.84 176	85.28 183	91.49 147	95.35 122	80.26 165	96.95 140	92.21 310	82.86 201	81.77 207	95.46 147	59.34 276	97.64 164	69.79 296	93.81 132	96.57 164

OMC-MVS		88.80 138	88.16 136	90.72 171	95.30 123	77.92 233	94.81 249	94.51 223	86.80 110	84.97 163	96.85 112	67.53 222	98.60 125	85.08 158	87.62 188	95.63 186

test_fmvsm_n_1920		94.81 18	95.60 10	92.45 104	95.29 124	80.96 145	99.29 2	97.21 23	94.50 7	97.29 13	98.44 27	82.15 54	99.78 28	98.56 7	97.68 65	96.61 162

MVS_Test		90.29 109	89.18 119	93.62 59	95.23 125	84.93 65	94.41 255	94.66 213	84.31 161	90.37 106	91.02 234	75.13 155	97.82 158	83.11 185	94.42 123	98.12 75

F-COLMAP		84.50 216	83.44 217	87.67 240	95.22 126	72.22 307	95.95 200	93.78 268	75.74 307	76.30 265	95.18 156	59.50 274	98.45 135	72.67 276	86.59 197	92.35 239

baseline1		88.85 136	87.49 151	92.93 86	95.21 127	86.85 29	95.47 222	94.61 218	87.29 98	83.11 187	94.99 165	80.70 62	96.89 212	82.28 189	73.72 287	95.05 200

CHOSEN 1792x2688		91.07 93	90.21 100	93.64 57	95.18 128	83.53 90	96.26 185	96.13 129	88.92 63	84.90 164	93.10 203	72.86 184	99.62 58	88.86 126	95.67 110	97.79 101

UGNet		87.73 164	86.55 170	91.27 153	95.16 129	79.11 196	96.35 180	96.23 121	88.14 78	87.83 138	90.48 243	50.65 328	99.09 102	80.13 206	94.03 126	95.60 187
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
VDD-MVS		88.28 153	87.02 164	92.06 126	95.09 130	80.18 168	97.55 89	94.45 228	83.09 193	89.10 122	95.92 134	47.97 339	98.49 131	93.08 78	86.91 194	97.52 122

PVSNet_Blended_VisFu		91.24 87	90.77 86	92.66 96	95.09 130	82.40 110	97.77 72	95.87 150	88.26 76	86.39 150	93.94 188	76.77 119	99.27 84	88.80 128	94.00 129	96.31 173

h-mvs33		89.30 126	88.95 124	90.36 181	95.07 132	76.04 269	96.96 139	97.11 30	90.39 46	92.22 76	95.10 161	74.70 161	98.86 116	93.14 75	65.89 345	96.16 175

xiu_mvs_v2_base		93.92 33	93.26 43	95.91 10	95.07 132	92.02 6	98.19 45	95.68 159	92.06 25	96.01 30	98.14 42	70.83 208	98.96 109	96.74 35	96.57 94	96.76 158

cl22		85.11 205	84.17 203	87.92 235	95.06 134	78.82 202	95.51 220	94.22 241	79.74 260	76.77 255	87.92 278	75.96 133	95.68 267	79.93 208	72.42 294	89.27 277

BH-w/o		88.24 154	87.47 153	90.54 176	95.03 135	78.54 209	97.41 103	93.82 263	84.08 168	78.23 241	94.51 175	69.34 216	97.21 194	80.21 205	94.58 121	95.87 181

CHOSEN 280x420		91.71 76	91.85 69	91.29 152	94.94 136	82.69 103	87.89 339	96.17 127	85.94 122	87.27 143	94.31 177	90.27 9	95.65 270	94.04 63	95.86 107	95.53 189

GG-mvs-BLEND				93.49 66	94.94 136	86.26 33	81.62 369	97.00 34		88.32 133	94.30 178	91.23 5	96.21 239	88.49 131	97.43 73	98.00 84

HyFIR lowres test		89.36 124	88.60 128	91.63 144	94.91 138	80.76 151	95.60 218	95.53 165	82.56 208	84.03 173	91.24 231	78.03 96	96.81 218	87.07 146	88.41 182	97.32 132

MVS_0304		95.36 9	95.20 16	95.85 11	94.89 139	89.22 12	98.83 25	97.88 11	94.68 4	95.14 38	97.99 52	80.80 60	99.81 21	98.60 6	97.95 57	98.50 50

miper_enhance_ethall		85.95 191	85.20 184	88.19 231	94.85 140	79.76 176	96.00 197	94.06 251	82.98 198	77.74 245	88.76 264	79.42 74	95.46 280	80.58 199	72.42 294	89.36 275

mvs_anonymous		88.68 140	87.62 147	91.86 134	94.80 141	81.69 130	93.53 280	94.92 196	82.03 218	78.87 236	90.43 245	75.77 136	95.34 284	85.04 159	93.16 142	98.55 49

CANet_DTU		90.98 94	90.04 104	93.83 49	94.76 142	86.23 34	96.32 182	93.12 298	93.11 16	93.71 58	96.82 115	63.08 251	99.48 73	84.29 164	95.12 115	95.77 183

PMMVS		89.46 123	89.92 109	88.06 232	94.64 143	69.57 334	96.22 187	94.95 194	87.27 99	91.37 89	96.54 123	65.88 233	97.39 184	88.54 129	93.89 130	97.23 136

TR-MVS		86.30 185	84.93 192	90.42 178	94.63 144	77.58 243	96.57 163	93.82 263	80.30 248	82.42 193	95.16 157	58.74 280	97.55 171	74.88 258	87.82 187	96.13 177

EPNet_dtu		87.65 166	87.89 139	86.93 261	94.57 145	71.37 322	96.72 155	96.50 93	88.56 70	87.12 146	95.02 163	75.91 135	94.01 323	66.62 310	90.00 166	95.42 192
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n		93.69 35	94.13 31	92.34 109	94.56 146	82.01 114	99.07 15	97.13 27	92.09 23	96.25 25	98.53 22	76.47 123	99.80 25	98.39 8	94.71 119	95.22 198

FMVSNet3		84.71 210	82.71 228	90.70 172	94.55 147	87.71 21	95.92 202	94.67 212	81.73 222	75.82 275	88.08 276	66.99 227	94.47 315	71.23 285	75.38 280	89.91 265

ETV-MVS		92.72 54	92.87 49	92.28 115	94.54 148	81.89 120	97.98 59	95.21 186	89.77 55	93.11 66	96.83 113	77.23 112	97.50 177	95.74 43	95.38 113	97.44 126

EIA-MVS		91.73 73	92.05 68	90.78 170	94.52 149	76.40 264	98.06 55	95.34 181	89.19 60	88.90 124	97.28 96	77.56 104	97.73 161	90.77 100	96.86 88	98.20 68

BH-untuned		86.95 174	85.94 174	89.99 190	94.52 149	77.46 245	96.78 152	93.37 288	81.80 220	76.62 258	93.81 192	66.64 230	97.02 204	76.06 247	93.88 131	95.48 191

DeepC-MVS	86.58 3	91.53 80	91.06 83	92.94 85	94.52 149	81.89 120	95.95 200	95.98 141	90.76 39	83.76 180	96.76 117	73.24 182	99.71 45	91.67 91	96.96 83	97.22 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
gg-mvs-nofinetune		85.48 200	82.90 224	93.24 73	94.51 152	85.82 41	79.22 373	96.97 37	61.19 371	87.33 142	53.01 389	90.58 6	96.07 242	86.07 151	97.23 79	97.81 100

fmvsm_l_conf0.5_n_a		94.91 14	95.30 14	93.72 55	94.50 153	84.30 76	99.14 9	96.00 139	91.94 28	97.91 5	98.60 18	84.78 35	99.77 29	98.84 4	96.03 104	97.08 144

3Dnovator+	82.88 8	89.63 120	87.85 140	94.99 21	94.49 154	86.76 31	97.84 67	95.74 156	86.10 118	75.47 280	96.02 131	65.00 241	99.51 71	82.91 187	97.07 82	98.72 40

fmvsm_l_conf0.5_n		94.89 15	95.24 15	93.86 48	94.42 155	84.61 70	99.13 10	96.15 128	92.06 25	97.92 3	98.52 23	84.52 36	99.74 38	98.76 5	95.67 110	97.22 137

ET-MVSNet_ETH3D		90.01 113	89.03 120	92.95 84	94.38 156	86.77 30	98.14 46	96.31 115	89.30 59	63.33 351	96.72 120	90.09 11	93.63 330	90.70 102	82.29 237	98.46 53

tpmrst		88.36 150	87.38 155	91.31 150	94.36 157	79.92 172	87.32 343	95.26 185	85.32 133	88.34 132	86.13 309	80.60 63	96.70 222	83.78 171	85.34 213	97.30 134

FE-MVS		86.06 189	84.15 204	91.78 138	94.33 158	79.81 174	84.58 361	96.61 79	76.69 302	85.00 162	87.38 284	70.71 209	98.37 139	70.39 293	91.70 159	97.17 141

MVS		90.60 102	88.64 127	96.50 5	94.25 159	90.53 8	93.33 284	97.21 23	77.59 291	78.88 235	97.31 92	71.52 200	99.69 49	89.60 118	98.03 54	99.27 20

dp		84.30 219	82.31 233	90.28 183	94.24 160	77.97 229	86.57 349	95.53 165	79.94 257	80.75 215	85.16 323	71.49 201	96.39 232	63.73 325	83.36 223	96.48 166

FA-MVS(test-final)		87.71 165	86.23 172	92.17 121	94.19 161	80.55 156	87.16 345	96.07 135	82.12 216	85.98 155	88.35 271	72.04 195	98.49 131	80.26 203	89.87 167	97.48 125

sss		90.87 98	89.96 107	93.60 60	94.15 162	83.84 84	97.14 122	98.13 7	85.93 123	89.68 112	96.09 130	71.67 197	99.30 83	87.69 139	89.16 172	97.66 110

SDMVSNet		87.02 172	85.61 177	91.24 154	94.14 163	83.30 95	93.88 272	95.98 141	84.30 163	79.63 229	92.01 215	58.23 284	97.68 162	90.28 113	82.02 238	92.75 234

sd_testset		84.62 212	83.11 221	89.17 207	94.14 163	77.78 238	91.54 313	94.38 232	84.30 163	79.63 229	92.01 215	52.28 323	96.98 206	77.67 228	82.02 238	92.75 234

PatchmatchNet		86.83 177	85.12 188	91.95 131	94.12 165	82.27 112	86.55 350	95.64 161	84.59 154	82.98 189	84.99 327	77.26 108	95.96 251	68.61 301	91.34 161	97.64 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13			83.69 208		94.09 166	81.01 142	86.78 348	96.09 132	83.81 179	84.75 166	84.32 332	74.44 167	96.54 227	63.88 324	85.07 214

UA-Net		88.92 133	88.48 131	90.24 184	94.06 167	77.18 252	93.04 292	94.66 213	87.39 96	91.09 94	93.89 189	74.92 158	98.18 147	75.83 250	91.43 160	95.35 194

Fast-Effi-MVS+		87.93 161	86.94 166	90.92 164	94.04 168	79.16 194	98.26 42	93.72 272	81.29 226	83.94 177	92.90 204	69.83 214	96.68 223	76.70 240	91.74 158	96.93 149

QAPM		86.88 175	84.51 196	93.98 44	94.04 168	85.89 40	97.19 114	96.05 136	73.62 323	75.12 283	95.62 142	62.02 258	99.74 38	70.88 289	96.06 103	96.30 174

thisisatest0515		90.95 96	90.26 98	93.01 82	94.03 170	84.27 78	97.91 63	96.67 70	83.18 190	86.87 148	95.51 146	88.66 16	97.85 157	80.46 200	89.01 174	96.92 151

Vis-MVSNet (Re-imp)		88.88 135	88.87 126	88.91 213	93.89 171	74.43 290	96.93 142	94.19 243	84.39 159	83.22 185	95.67 140	78.24 92	94.70 308	78.88 218	94.40 124	97.61 115

ADS-MVSNet2		79.57 285	77.53 288	85.71 281	93.78 172	72.13 309	79.48 371	86.11 367	73.09 329	80.14 223	79.99 356	62.15 256	90.14 364	59.49 340	83.52 220	94.85 205

ADS-MVSNet		81.26 268	78.36 281	89.96 193	93.78 172	79.78 175	79.48 371	93.60 277	73.09 329	80.14 223	79.99 356	62.15 256	95.24 290	59.49 340	83.52 220	94.85 205

EPP-MVSNet		89.76 117	89.72 113	89.87 196	93.78 172	76.02 272	97.22 109	96.51 91	79.35 266	85.11 160	95.01 164	84.82 34	97.10 202	87.46 142	88.21 185	96.50 165

3Dnovator	82.32 10	89.33 125	87.64 145	94.42 33	93.73 175	85.70 43	97.73 76	96.75 60	86.73 113	76.21 268	95.93 132	62.17 255	99.68 51	81.67 193	97.81 61	97.88 91

Effi-MVS+		90.70 100	89.90 110	93.09 79	93.61 176	83.48 91	95.20 234	92.79 303	83.22 189	91.82 82	95.70 138	71.82 196	97.48 179	91.25 93	93.67 134	98.32 60

IS-MVSNet		88.67 141	88.16 136	90.20 186	93.61 176	76.86 256	96.77 154	93.07 299	84.02 170	83.62 181	95.60 143	74.69 164	96.24 238	78.43 222	93.66 135	97.49 124

AUN-MVS		86.25 187	85.57 178	88.26 227	93.57 178	73.38 296	95.45 223	95.88 148	83.94 174	85.47 158	94.21 181	73.70 178	96.67 224	83.54 179	64.41 349	94.73 211

test2506		90.96 95	90.39 95	92.65 97	93.54 179	82.46 109	96.37 178	97.35 18	86.78 111	87.55 139	95.25 150	77.83 101	97.50 177	84.07 166	94.80 117	97.98 86

ECVR-MVS		88.35 151	87.25 157	91.65 141	93.54 179	79.40 187	96.56 165	90.78 334	86.78 111	85.57 157	95.25 150	57.25 298	97.56 169	84.73 162	94.80 117	97.98 86

hse-mvs2		88.22 155	88.21 134	88.25 228	93.54 179	73.41 295	95.41 225	95.89 147	90.39 46	92.22 76	94.22 180	74.70 161	96.66 225	93.14 75	64.37 350	94.69 212

LCM-MVSNet-Re		83.75 228	83.54 214	84.39 307	93.54 179	64.14 355	92.51 298	84.03 374	83.90 176	66.14 340	86.59 298	67.36 224	92.68 337	84.89 161	92.87 144	96.35 169

EC-MVSNet		91.73 73	92.11 66	90.58 174	93.54 179	77.77 239	98.07 54	94.40 231	87.44 94	92.99 69	97.11 103	74.59 165	96.87 214	93.75 65	97.08 81	97.11 142

tpm cat1		83.63 230	81.38 247	90.39 179	93.53 184	78.19 225	85.56 357	95.09 189	70.78 343	78.51 238	83.28 340	74.80 160	97.03 203	66.77 308	84.05 218	95.95 178

thisisatest0530		89.65 119	89.02 121	91.53 146	93.46 185	80.78 150	96.52 166	96.67 70	81.69 223	83.79 179	94.90 167	88.85 15	97.68 162	77.80 223	87.49 191	96.14 176

MSDG		80.62 277	77.77 287	89.14 208	93.43 186	77.24 249	91.89 306	90.18 338	69.86 348	68.02 328	91.94 221	52.21 324	98.84 117	59.32 342	83.12 224	91.35 241

fmvsm_s_conf0.5_n_a		93.34 40	93.71 34	92.22 118	93.38 187	81.71 129	98.86 24	96.98 35	91.64 29	96.85 15	98.55 19	75.58 141	99.77 29	97.88 19	93.68 133	95.18 199

ab-mvs		87.08 171	84.94 191	93.48 67	93.34 188	83.67 87	88.82 330	95.70 158	81.18 227	84.55 170	90.14 251	62.72 252	98.94 113	85.49 156	82.54 234	97.85 95

1314		88.94 132	87.20 158	94.17 41	93.21 189	85.73 42	93.33 284	96.64 76	82.89 199	75.98 271	96.36 124	66.83 229	99.39 77	83.52 181	96.02 105	97.39 130

1112_ss		88.60 144	87.47 153	92.00 130	93.21 189	80.97 144	96.47 170	92.46 306	83.64 184	80.86 214	97.30 94	80.24 67	97.62 165	77.60 229	85.49 210	97.40 129

GeoE		86.36 183	85.20 184	89.83 198	93.17 191	76.13 267	97.53 90	92.11 311	79.58 263	80.99 212	94.01 186	66.60 231	96.17 241	73.48 272	89.30 171	97.20 140

test1111		88.11 156	87.04 163	91.35 149	93.15 192	78.79 205	96.57 163	90.78 334	86.88 109	85.04 161	95.20 154	57.23 299	97.39 184	83.88 169	94.59 120	97.87 93

Test_1112_low_res		88.03 158	86.73 167	91.94 132	93.15 192	80.88 147	96.44 173	92.41 308	83.59 186	80.74 216	91.16 232	80.18 68	97.59 167	77.48 232	85.40 211	97.36 131

CostFormer		89.08 129	88.39 132	91.15 158	93.13 194	79.15 195	88.61 333	96.11 131	83.14 191	89.58 115	86.93 293	83.83 45	96.87 214	88.22 135	85.92 205	97.42 127

IB-MVS	85.34 4	88.67 141	87.14 161	93.26 72	93.12 195	84.32 75	98.76 26	97.27 21	87.19 103	79.36 232	90.45 244	83.92 44	98.53 129	84.41 163	69.79 313	96.93 149
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
diffmvs		91.17 89	90.74 87	92.44 106	93.11 196	82.50 108	96.25 186	93.62 276	87.79 86	90.40 105	95.93 132	73.44 180	97.42 181	93.62 68	92.55 148	97.41 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tttt0517		88.57 145	88.19 135	89.71 202	93.00 197	75.99 273	95.67 213	96.67 70	80.78 234	81.82 205	94.40 176	88.97 14	97.58 168	76.05 248	86.31 199	95.57 188

MVSFormer		91.36 84	90.57 90	93.73 54	93.00 197	88.08 17	94.80 250	94.48 224	80.74 235	94.90 43	97.13 101	78.84 84	95.10 298	83.77 172	97.46 70	98.02 79

lupinMVS		93.87 34	93.58 38	94.75 27	93.00 197	88.08 17	99.15 7	95.50 168	91.03 37	94.90 43	97.66 72	78.84 84	97.56 169	94.64 57	97.46 70	98.62 45

casdiffmvs_mvg		91.13 90	90.45 94	93.17 76	92.99 200	83.58 89	97.46 97	94.56 221	87.69 89	87.19 145	94.98 166	74.50 166	97.60 166	91.88 90	92.79 145	98.34 58
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_fmvs1		87.79 163	88.52 130	85.62 285	92.98 201	64.31 353	97.88 65	92.42 307	87.95 82	92.24 75	95.82 135	47.94 340	98.44 137	95.31 50	94.09 125	94.09 219

tpm2		87.35 170	86.26 171	90.62 173	92.93 202	78.67 207	88.06 338	95.99 140	79.33 267	87.40 140	86.43 304	80.28 66	96.40 231	80.23 204	85.73 209	96.79 155

baseline		90.76 99	90.10 103	92.74 93	92.90 203	82.56 105	94.60 252	94.56 221	87.69 89	89.06 123	95.67 140	73.76 175	97.51 176	90.43 108	92.23 154	98.16 71

test_fmvsmconf_n		93.99 32	94.36 27	92.86 88	92.82 204	81.12 139	99.26 3	96.37 111	93.47 13	95.16 35	98.21 36	79.00 81	99.64 55	98.21 10	96.73 92	97.83 97

casdiffmvs		90.95 96	90.39 95	92.63 99	92.82 204	82.53 106	96.83 147	94.47 226	87.69 89	88.47 129	95.56 145	74.04 172	97.54 173	90.90 98	92.74 146	97.83 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet		88.67 141	87.82 141	91.24 154	92.68 206	78.82 202	96.95 140	93.85 262	87.55 92	87.07 147	95.13 159	63.43 249	97.21 194	77.58 230	96.15 100	97.70 108
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GBi-Net		82.42 251	80.43 262	88.39 223	92.66 207	81.95 115	94.30 261	93.38 285	79.06 275	75.82 275	85.66 311	56.38 306	93.84 325	71.23 285	75.38 280	89.38 272

test1		82.42 251	80.43 262	88.39 223	92.66 207	81.95 115	94.30 261	93.38 285	79.06 275	75.82 275	85.66 311	56.38 306	93.84 325	71.23 285	75.38 280	89.38 272

FMVSNet2		82.79 245	80.44 261	89.83 198	92.66 207	85.43 48	95.42 224	94.35 233	79.06 275	74.46 287	87.28 285	56.38 306	94.31 318	69.72 297	74.68 284	89.76 267

miper_ehance_all_eth		84.57 214	83.60 213	87.50 248	92.64 210	78.25 219	95.40 226	93.47 281	79.28 270	76.41 262	87.64 281	76.53 122	95.24 290	78.58 220	72.42 294	89.01 288

cascas		86.50 181	84.48 198	92.55 102	92.64 210	85.95 37	97.04 132	95.07 191	75.32 310	80.50 217	91.02 234	54.33 318	97.98 150	86.79 149	87.62 188	93.71 226

TESTMET0.1,1		89.83 116	89.34 117	91.31 150	92.54 212	80.19 167	97.11 125	96.57 85	86.15 116	86.85 149	91.83 223	79.32 75	96.95 208	81.30 194	92.35 152	96.77 157

COLMAP_ROB	73.24 19	75.74 314	73.00 321	83.94 309	92.38 213	69.08 336	91.85 307	86.93 362	61.48 369	65.32 343	90.27 247	42.27 358	96.93 211	50.91 368	75.63 279	85.80 348
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_vis1_n_1920		89.95 114	90.59 89	88.03 234	92.36 214	68.98 337	99.12 11	94.34 234	93.86 11	93.64 60	97.01 107	51.54 325	99.59 60	96.76 34	96.71 93	95.53 189

xiu_mvs_v1_base_debu		90.54 103	89.54 114	93.55 62	92.31 215	87.58 23	96.99 133	94.87 199	87.23 100	93.27 62	97.56 81	57.43 294	98.32 140	92.72 80	93.46 138	94.74 208

xiu_mvs_v1_base		90.54 103	89.54 114	93.55 62	92.31 215	87.58 23	96.99 133	94.87 199	87.23 100	93.27 62	97.56 81	57.43 294	98.32 140	92.72 80	93.46 138	94.74 208

xiu_mvs_v1_base_debi		90.54 103	89.54 114	93.55 62	92.31 215	87.58 23	96.99 133	94.87 199	87.23 100	93.27 62	97.56 81	57.43 294	98.32 140	92.72 80	93.46 138	94.74 208

SCA		85.63 196	83.64 211	91.60 145	92.30 218	81.86 122	92.88 295	95.56 164	84.85 145	82.52 190	85.12 325	58.04 287	95.39 281	73.89 268	87.58 190	97.54 117

gm-plane-assit					92.27 219	79.64 183			84.47 158		95.15 158		97.93 151	85.81 153

test-LLR		88.48 146	87.98 138	89.98 191	92.26 220	77.23 250	97.11 125	95.96 143	83.76 181	86.30 152	91.38 227	72.30 191	96.78 220	80.82 197	91.92 156	95.94 179

test-mter		88.95 131	88.60 128	89.98 191	92.26 220	77.23 250	97.11 125	95.96 143	85.32 133	86.30 152	91.38 227	76.37 127	96.78 220	80.82 197	91.92 156	95.94 179

PAPM		92.87 49	92.40 58	94.30 35	92.25 222	87.85 19	96.40 177	96.38 108	91.07 36	88.72 127	96.90 109	82.11 55	97.37 186	90.05 114	97.70 64	97.67 109

cl____		83.27 235	82.12 235	86.74 262	92.20 223	75.95 274	95.11 240	93.27 291	78.44 284	74.82 285	87.02 292	74.19 169	95.19 292	74.67 261	69.32 317	89.09 283

DIV-MVS_self_test		83.27 235	82.12 235	86.74 262	92.19 224	75.92 276	95.11 240	93.26 292	78.44 284	74.81 286	87.08 291	74.19 169	95.19 292	74.66 262	69.30 318	89.11 282

AllTest		75.92 312	73.06 320	84.47 303	92.18 225	67.29 342	91.07 316	84.43 372	67.63 352	63.48 348	90.18 248	38.20 368	97.16 197	57.04 350	73.37 289	88.97 291

TestCases				84.47 303	92.18 225	67.29 342		84.43 372	67.63 352	63.48 348	90.18 248	38.20 368	97.16 197	57.04 350	73.37 289	88.97 291

CLD-MVS		87.97 160	87.48 152	89.44 204	92.16 227	80.54 158	98.14 46	94.92 196	91.41 31	79.43 231	95.40 148	62.34 254	97.27 192	90.60 103	82.90 229	90.50 251
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Syy-MVS		77.97 298	78.05 284	77.74 348	92.13 228	56.85 375	93.97 269	94.23 239	82.43 209	73.39 293	93.57 196	57.95 290	87.86 370	32.40 388	82.34 235	88.51 298

myMVS_eth3d		81.93 259	82.18 234	81.18 332	92.13 228	67.18 344	93.97 269	94.23 239	82.43 209	73.39 293	93.57 196	76.98 114	87.86 370	50.53 370	82.34 235	88.51 298

c3_l		83.80 227	82.65 229	87.25 255	92.10 230	77.74 241	95.25 231	93.04 300	78.58 281	76.01 270	87.21 289	75.25 154	95.11 297	77.54 231	68.89 321	88.91 294

HQP-NCC					92.08 231		97.63 82		90.52 43	82.30 194

ACMP_Plane					92.08 231		97.63 82		90.52 43	82.30 194

HQP-MVS		87.91 162	87.55 150	88.98 212	92.08 231	78.48 210	97.63 82	94.80 204	90.52 43	82.30 194	94.56 173	65.40 237	97.32 187	87.67 140	83.01 226	91.13 242

PCF-MVS	84.09 5	86.77 179	85.00 190	92.08 124	92.06 234	83.07 99	92.14 303	94.47 226	79.63 262	76.90 254	94.78 169	71.15 203	99.20 92	72.87 274	91.05 162	93.98 221
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
NP-MVS					92.04 235	78.22 220					94.56 173

plane_prior6					91.98 236	77.92 233						64.77 243

Effi-MVS+-dtu		84.61 213	84.90 193	83.72 314	91.96 237	63.14 361	94.95 245	93.34 289	85.57 128	79.79 227	87.12 290	61.99 259	95.61 274	83.55 178	85.83 207	92.41 238

plane_prior1					91.95 238

CDS-MVSNet		89.50 122	88.96 123	91.14 159	91.94 239	80.93 146	97.09 129	95.81 152	84.26 166	84.72 167	94.20 182	80.31 65	95.64 271	83.37 182	88.96 175	96.85 154
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP_MVS		87.50 168	87.09 162	88.74 217	91.86 240	77.96 230	97.18 115	94.69 209	89.89 53	81.33 209	94.15 183	64.77 243	97.30 189	87.08 144	82.82 230	90.96 244

plane_prior7					91.86 240	77.55 244

eth_miper_zixun_eth		83.12 239	82.01 237	86.47 267	91.85 242	74.80 285	94.33 259	93.18 295	79.11 273	75.74 278	87.25 288	72.71 185	95.32 286	76.78 239	67.13 339	89.27 277

VDDNet		86.44 182	84.51 196	92.22 118	91.56 243	81.83 123	97.10 128	94.64 216	69.50 349	87.84 137	95.19 155	48.01 338	97.92 156	89.82 116	86.92 193	96.89 152

EI-MVSNet		85.80 193	85.20 184	87.59 244	91.55 244	77.41 246	95.13 238	95.36 178	80.43 245	80.33 221	94.71 170	73.72 176	95.97 248	76.96 238	78.64 262	89.39 270

CVMVSNet		84.83 209	85.57 178	82.63 324	91.55 244	60.38 369	95.13 238	95.03 192	80.60 238	82.10 200	94.71 170	66.40 232	90.19 363	74.30 265	90.32 165	97.31 133

ACMP	81.66 11	84.00 223	83.22 220	86.33 268	91.53 246	72.95 305	95.91 204	93.79 267	83.70 183	73.79 290	92.22 213	54.31 319	96.89 212	83.98 167	79.74 251	89.16 280
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
IterMVS-LS		83.93 224	82.80 227	87.31 253	91.46 247	77.39 247	95.66 214	93.43 283	80.44 243	75.51 279	87.26 287	73.72 176	95.16 294	76.99 236	70.72 304	89.39 270
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		84.10 221	82.90 224	87.70 239	91.41 248	73.28 299	90.59 320	93.19 293	85.02 142	77.96 244	93.68 193	57.92 292	96.18 240	75.50 253	80.87 243	93.63 227

WB-MVSnew		84.08 222	83.51 215	85.80 278	91.34 249	76.69 260	95.62 217	96.27 117	81.77 221	81.81 206	92.81 205	58.23 284	94.70 308	66.66 309	87.06 192	85.99 344

Patchmatch-test		78.25 294	74.72 308	88.83 215	91.20 250	74.10 293	73.91 386	88.70 354	59.89 377	66.82 335	85.12 325	78.38 90	94.54 313	48.84 375	79.58 254	97.86 94

miper_lstm_enhance		81.66 264	80.66 258	84.67 299	91.19 251	71.97 314	91.94 305	93.19 293	77.86 288	72.27 307	85.26 319	73.46 179	93.42 333	73.71 271	67.05 340	88.61 296

ACMM	80.70 13	83.72 229	82.85 226	86.31 271	91.19 251	72.12 310	95.88 205	94.29 237	80.44 243	77.02 252	91.96 219	55.24 312	97.14 201	79.30 213	80.38 247	89.67 268
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testing3		80.74 275	81.17 250	79.44 341	91.15 253	63.48 359	97.16 119	95.76 154	80.83 232	71.36 311	93.15 202	78.22 93	87.30 375	43.19 382	79.67 252	87.55 323

TAMVS		88.48 146	87.79 142	90.56 175	91.09 254	79.18 193	96.45 172	95.88 148	83.64 184	83.12 186	93.33 198	75.94 134	95.74 266	82.40 188	88.27 184	96.75 159

ACMH+	76.62 16	77.47 303	74.94 305	85.05 293	91.07 255	71.58 320	93.26 288	90.01 339	71.80 338	64.76 345	88.55 267	41.62 360	96.48 229	62.35 331	71.00 301	87.09 329

OpenMVS	79.58 14	86.09 188	83.62 212	93.50 65	90.95 256	86.71 32	97.44 98	95.83 151	75.35 309	72.64 304	95.72 137	57.42 297	99.64 55	71.41 283	95.85 108	94.13 218

LPG-MVS_test		84.20 220	83.49 216	86.33 268	90.88 257	73.06 302	95.28 228	94.13 246	82.20 213	76.31 263	93.20 199	54.83 316	96.95 208	83.72 174	80.83 244	88.98 289

LGP-MVS_train				86.33 268	90.88 257	73.06 302		94.13 246	82.20 213	76.31 263	93.20 199	54.83 316	96.95 208	83.72 174	80.83 244	88.98 289

test_fmvsmvis_n_1920		92.12 67	92.10 67	92.17 121	90.87 259	81.04 141	98.34 40	93.90 258	92.71 18	87.24 144	97.90 61	74.83 159	99.72 43	96.96 31	96.20 98	95.76 184

KD-MVS_2432*1600		77.63 301	74.92 306	85.77 279	90.86 260	79.44 185	88.08 336	93.92 256	76.26 304	67.05 333	82.78 342	72.15 193	91.92 346	61.53 332	41.62 389	85.94 345

miper_refine_blended		77.63 301	74.92 306	85.77 279	90.86 260	79.44 185	88.08 336	93.92 256	76.26 304	67.05 333	82.78 342	72.15 193	91.92 346	61.53 332	41.62 389	85.94 345

baseline2		90.39 106	90.21 100	90.93 163	90.86 260	80.99 143	95.20 234	97.41 17	86.03 121	80.07 226	94.61 172	90.58 6	97.47 180	87.29 143	89.86 168	94.35 214

PVSNet_0	77.72 15	81.70 262	78.95 279	89.94 194	90.77 263	76.72 259	95.96 199	96.95 39	85.01 143	70.24 321	88.53 269	52.32 322	98.20 145	86.68 150	44.08 386	94.89 203

ACMH	75.40 17	77.99 296	74.96 304	87.10 258	90.67 264	76.41 263	93.19 291	91.64 319	72.47 335	63.44 350	87.61 282	43.34 353	97.16 197	58.34 344	73.94 286	87.72 315
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS-HIRNet		71.36 335	67.00 340	84.46 305	90.58 265	69.74 332	79.15 374	87.74 360	46.09 386	61.96 359	50.50 390	45.14 348	95.64 271	53.74 361	88.11 186	88.00 312

fmvsm_s_conf0.1_n		92.93 47	93.16 46	92.24 116	90.52 266	81.92 118	98.42 37	96.24 120	91.17 34	96.02 29	98.35 31	75.34 152	99.74 38	97.84 20	94.58 121	95.05 200

jason		92.73 52	92.23 63	94.21 40	90.50 267	87.30 26	98.65 30	95.09 189	90.61 42	92.76 71	97.13 101	75.28 153	97.30 189	93.32 72	96.75 91	98.02 79
jason: jason.
LTVRE_ROB	73.68 18	77.99 296	75.74 301	84.74 296	90.45 268	72.02 312	86.41 351	91.12 326	72.57 334	66.63 337	87.27 286	54.95 315	96.98 206	56.29 354	75.98 275	85.21 351
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
XVG-OURS		85.18 203	84.38 200	87.59 244	90.42 269	71.73 318	91.06 317	94.07 250	82.00 219	83.29 184	95.08 162	56.42 305	97.55 171	83.70 176	83.42 222	93.49 230

VPA-MVSNet		85.32 201	83.83 207	89.77 201	90.25 270	82.63 104	96.36 179	97.07 32	83.03 196	81.21 211	89.02 261	61.58 262	96.31 235	85.02 160	70.95 302	90.36 252

XVG-OURS-SEG-HR		85.74 195	85.16 187	87.49 249	90.22 271	71.45 321	91.29 314	94.09 249	81.37 225	83.90 178	95.22 152	60.30 269	97.53 175	85.58 155	84.42 217	93.50 229

tpm		85.55 198	84.47 199	88.80 216	90.19 272	75.39 280	88.79 331	94.69 209	84.83 146	83.96 176	85.21 321	78.22 93	94.68 310	76.32 246	78.02 271	96.34 170

CR-MVSNet		83.53 231	81.36 248	90.06 188	90.16 273	79.75 177	79.02 375	91.12 326	84.24 167	82.27 198	80.35 354	75.45 144	93.67 329	63.37 328	86.25 200	96.75 159

RPMNet		79.85 281	75.92 300	91.64 142	90.16 273	79.75 177	79.02 375	95.44 173	58.43 381	82.27 198	72.55 378	73.03 183	98.41 138	46.10 379	86.25 200	96.75 159

test_cas_vis1_n_1920		89.90 115	90.02 105	89.54 203	90.14 275	74.63 287	98.71 27	94.43 229	93.04 17	92.40 72	96.35 125	53.41 321	99.08 103	95.59 46	96.16 99	94.90 202

FIs		86.73 180	86.10 173	88.61 219	90.05 276	80.21 166	96.14 193	96.95 39	85.56 130	78.37 240	92.30 212	76.73 120	95.28 288	79.51 210	79.27 256	90.35 253

FMVSNet5		76.46 310	74.16 314	83.35 319	90.05 276	76.17 266	89.58 325	89.85 340	71.39 341	65.29 344	80.42 353	50.61 329	87.70 373	61.05 337	69.24 319	86.18 340

IterMVS		80.67 276	79.16 276	85.20 291	89.79 278	76.08 268	92.97 294	91.86 314	80.28 249	71.20 313	85.14 324	57.93 291	91.34 353	72.52 277	70.74 303	88.18 309
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mvsany_test1		87.58 167	88.22 133	85.67 283	89.78 279	67.18 344	95.25 231	87.93 357	83.96 173	88.79 125	97.06 106	72.52 187	94.53 314	92.21 85	86.45 198	95.30 196

UniMVSNet (Re)		85.31 202	84.23 202	88.55 220	89.75 280	80.55 156	96.72 155	96.89 43	85.42 131	78.40 239	88.93 262	75.38 148	95.52 278	78.58 220	68.02 330	89.57 269

Patchmtry		77.36 304	74.59 309	85.67 283	89.75 280	75.75 278	77.85 378	91.12 326	60.28 374	71.23 312	80.35 354	75.45 144	93.56 331	57.94 345	67.34 338	87.68 317

JIA-IIPM		79.00 291	77.20 290	84.40 306	89.74 282	64.06 356	75.30 383	95.44 173	62.15 365	81.90 203	59.08 387	78.92 82	95.59 275	66.51 313	85.78 208	93.54 228

MS-PatchMatch		83.05 240	81.82 241	86.72 266	89.64 283	79.10 197	94.88 247	94.59 220	79.70 261	70.67 317	89.65 255	50.43 330	96.82 217	70.82 292	95.99 106	84.25 357

IterMVS-SCA-FT		80.51 278	79.10 277	84.73 297	89.63 284	74.66 286	92.98 293	91.81 316	80.05 254	71.06 315	85.18 322	58.04 287	91.40 352	72.48 278	70.70 305	88.12 310

Fast-Effi-MVS+-dtu		83.33 234	82.60 230	85.50 287	89.55 285	69.38 335	96.09 196	91.38 321	82.30 212	75.96 272	91.41 226	56.71 301	95.58 276	75.13 257	84.90 215	91.54 240

PatchT		79.75 282	76.85 294	88.42 221	89.55 285	75.49 279	77.37 379	94.61 218	63.07 362	82.46 192	73.32 375	75.52 143	93.41 334	51.36 366	84.43 216	96.36 168

GA-MVS		85.79 194	84.04 206	91.02 162	89.47 287	80.27 164	96.90 144	94.84 202	85.57 128	80.88 213	89.08 259	56.56 304	96.47 230	77.72 226	85.35 212	96.34 170

UniMVSNet_NR-MVSNet		85.49 199	84.59 194	88.21 230	89.44 288	79.36 188	96.71 157	96.41 103	85.22 136	78.11 242	90.98 236	76.97 115	95.14 295	79.14 215	68.30 327	90.12 258

FC-MVSNet-test		85.96 190	85.39 181	87.66 241	89.38 289	78.02 227	95.65 215	96.87 44	85.12 140	77.34 247	91.94 221	76.28 129	94.74 307	77.09 235	78.82 260	90.21 256

WR-MVS		84.32 218	82.96 222	88.41 222	89.38 289	80.32 161	96.59 162	96.25 119	83.97 172	76.63 257	90.36 246	67.53 222	94.86 305	75.82 251	70.09 311	90.06 263

VPNet		84.69 211	82.92 223	90.01 189	89.01 291	83.45 92	96.71 157	95.46 171	85.71 126	79.65 228	92.18 214	56.66 303	96.01 247	83.05 186	67.84 333	90.56 249

nrg030		86.79 178	85.43 180	90.87 167	88.76 292	85.34 49	97.06 131	94.33 235	84.31 161	80.45 219	91.98 218	72.36 189	96.36 233	88.48 132	71.13 300	90.93 246

DU-MVS		84.57 214	83.33 218	88.28 226	88.76 292	79.36 188	96.43 175	95.41 177	85.42 131	78.11 242	90.82 238	67.61 219	95.14 295	79.14 215	68.30 327	90.33 254

NR-MVSNet		83.35 233	81.52 246	88.84 214	88.76 292	81.31 137	94.45 254	95.16 187	84.65 152	67.81 329	90.82 238	70.36 211	94.87 304	74.75 259	66.89 342	90.33 254

test_0402		72.68 328	69.54 335	82.09 328	88.67 295	71.81 317	92.72 297	86.77 364	61.52 368	62.21 357	83.91 335	43.22 354	93.76 328	34.60 387	72.23 297	80.72 375

RPSCF		77.73 300	76.63 295	81.06 333	88.66 296	55.76 380	87.77 340	87.88 358	64.82 361	74.14 289	92.79 208	49.22 335	96.81 218	67.47 305	76.88 273	90.62 248

FMVSNet1		79.50 286	76.54 296	88.39 223	88.47 297	81.95 115	94.30 261	93.38 285	73.14 328	72.04 309	85.66 311	43.86 350	93.84 325	65.48 317	72.53 293	89.38 272

test_fmvsmconf0.1_n		93.08 44	93.22 45	92.65 97	88.45 298	80.81 149	99.00 21	95.11 188	93.21 15	94.00 56	97.91 60	76.84 116	99.59 60	97.91 16	96.55 95	97.54 117

OPM-MVS		85.84 192	85.10 189	88.06 232	88.34 299	77.83 237	95.72 211	94.20 242	87.89 85	80.45 219	94.05 185	58.57 281	97.26 193	83.88 169	82.76 232	89.09 283
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tfpnnormal		78.14 295	75.42 302	86.31 271	88.33 300	79.24 191	94.41 255	96.22 122	73.51 324	69.81 323	85.52 317	55.43 310	95.75 263	47.65 377	67.86 332	83.95 360

TinyColmap		72.41 329	68.99 338	82.68 323	88.11 301	69.59 333	88.41 334	85.20 369	65.55 358	57.91 371	84.82 329	30.80 382	95.94 252	51.38 365	68.70 322	82.49 368

fmvsm_s_conf0.1_n_a		92.38 64	92.49 57	92.06 126	88.08 302	81.62 132	97.97 61	96.01 138	90.62 41	96.58 21	98.33 32	74.09 171	99.71 45	97.23 27	93.46 138	94.86 204

WR-MVS_H		81.02 271	80.09 265	83.79 311	88.08 302	71.26 323	94.46 253	96.54 88	80.08 253	72.81 303	86.82 294	70.36 211	92.65 338	64.18 322	67.50 336	87.46 325

mvsmamba		85.17 204	84.54 195	87.05 259	87.94 304	75.11 283	96.22 187	87.79 359	86.91 107	78.55 237	91.77 224	64.93 242	95.91 254	86.94 148	79.80 248	90.12 258

CP-MVSNet		81.01 272	80.08 266	83.79 311	87.91 305	70.51 325	94.29 264	95.65 160	80.83 232	72.54 306	88.84 263	63.71 247	92.32 341	68.58 302	68.36 326	88.55 297

D2MVS		82.67 247	81.55 244	86.04 276	87.77 306	76.47 261	95.21 233	96.58 84	82.66 206	70.26 320	85.46 318	60.39 268	95.80 260	76.40 244	79.18 257	85.83 347

TranMVSNet+NR-MVSNet		83.24 237	81.71 242	87.83 236	87.71 307	78.81 204	96.13 195	94.82 203	84.52 155	76.18 269	90.78 240	64.07 246	94.60 311	74.60 263	66.59 344	90.09 261

USDC		78.65 292	76.25 297	85.85 277	87.58 308	74.60 288	89.58 325	90.58 337	84.05 169	63.13 352	88.23 273	40.69 366	96.86 216	66.57 312	75.81 278	86.09 342

PS-CasMVS		80.27 279	79.18 275	83.52 317	87.56 309	69.88 330	94.08 267	95.29 183	80.27 250	72.08 308	88.51 270	59.22 278	92.23 343	67.49 304	68.15 329	88.45 303

test_fmvs1_n		86.34 184	86.72 168	85.17 292	87.54 310	63.64 358	96.91 143	92.37 309	87.49 93	91.33 90	95.58 144	40.81 365	98.46 134	95.00 52	93.49 136	93.41 233

RRT_MVS		83.88 225	83.27 219	85.71 281	87.53 311	72.12 310	95.35 227	94.33 235	83.81 179	75.86 274	91.28 230	60.55 267	95.09 300	83.93 168	76.76 274	89.90 266

MIMVSNet		79.18 290	75.99 299	88.72 218	87.37 312	80.66 153	79.96 370	91.82 315	77.38 294	74.33 288	81.87 346	41.78 359	90.74 359	66.36 315	83.10 225	94.76 207

XXY-MVS		83.84 226	82.00 238	89.35 205	87.13 313	81.38 135	95.72 211	94.26 238	80.15 252	75.92 273	90.63 241	61.96 260	96.52 228	78.98 217	73.28 292	90.14 257

ITE_SJBPF				82.38 325	87.00 314	65.59 350		89.55 342	79.99 256	69.37 325	91.30 229	41.60 361	95.33 285	62.86 330	74.63 285	86.24 339

test0.0.03 1		82.79 245	82.48 231	83.74 313	86.81 315	72.22 307	96.52 166	95.03 192	83.76 181	73.00 300	93.20 199	72.30 191	88.88 366	64.15 323	77.52 272	90.12 258

v8		81.88 260	80.06 268	87.32 252	86.63 316	79.04 200	94.41 255	93.65 275	78.77 279	73.19 299	85.57 315	66.87 228	95.81 259	73.84 270	67.61 335	87.11 328

tt0805		81.20 270	79.06 278	87.61 242	86.50 317	72.97 304	93.66 275	95.48 169	74.11 319	76.23 267	91.99 217	41.36 362	97.40 183	77.44 233	74.78 283	92.45 237

v10		81.43 266	79.53 274	87.11 257	86.38 318	78.87 201	94.31 260	93.43 283	77.88 287	73.24 298	85.26 319	65.44 236	95.75 263	72.14 279	67.71 334	86.72 332

PEN-MVS		79.47 287	78.26 283	83.08 320	86.36 319	68.58 338	93.85 273	94.77 207	79.76 259	71.37 310	88.55 267	59.79 270	92.46 339	64.50 321	65.40 346	88.19 308

UniMVSNet_ETH3D		80.86 274	78.75 280	87.22 256	86.31 320	72.02 312	91.95 304	93.76 271	73.51 324	75.06 284	90.16 250	43.04 356	95.66 268	76.37 245	78.55 266	93.98 221

v1144		82.90 244	81.27 249	87.78 238	86.29 321	79.07 199	96.14 193	93.93 254	80.05 254	77.38 246	86.80 295	65.50 235	95.93 253	75.21 256	70.13 308	88.33 306

V42		83.04 241	81.53 245	87.57 246	86.27 322	79.09 198	95.87 206	94.11 248	80.35 247	77.22 250	86.79 296	65.32 239	96.02 246	77.74 225	70.14 307	87.61 319

v2v482		83.46 232	81.86 240	88.25 228	86.19 323	79.65 182	96.34 181	94.02 252	81.56 224	77.32 248	88.23 273	65.62 234	96.03 243	77.77 224	69.72 315	89.09 283

v148		82.41 253	80.89 252	86.99 260	86.18 324	76.81 257	96.27 184	93.82 263	80.49 242	75.28 282	86.11 310	67.32 225	95.75 263	75.48 254	67.03 341	88.42 304

pmmvs4		82.54 249	80.79 253	87.79 237	86.11 325	80.49 160	93.55 279	93.18 295	77.29 295	73.35 296	89.40 258	65.26 240	95.05 302	75.32 255	73.61 288	87.83 314

MVP-Stereo		82.65 248	81.67 243	85.59 286	86.10 326	78.29 217	93.33 284	92.82 302	77.75 289	69.17 327	87.98 277	59.28 277	95.76 262	71.77 280	96.88 86	82.73 365
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v1192		82.31 254	80.55 260	87.60 243	85.94 327	78.47 213	95.85 208	93.80 266	79.33 267	76.97 253	86.51 299	63.33 250	95.87 256	73.11 273	70.13 308	88.46 302

TransMVSNet (Re)		76.94 307	74.38 311	84.62 301	85.92 328	75.25 281	95.28 228	89.18 347	73.88 322	67.22 330	86.46 301	59.64 271	94.10 321	59.24 343	52.57 375	84.50 355

PS-MVSNAJss		84.91 208	84.30 201	86.74 262	85.89 329	74.40 291	94.95 245	94.16 245	83.93 175	76.45 261	90.11 252	71.04 205	95.77 261	83.16 184	79.02 259	90.06 263

v144192		82.43 250	80.73 256	87.54 247	85.81 330	78.22 220	95.98 198	93.78 268	79.09 274	77.11 251	86.49 300	64.66 245	95.91 254	74.20 266	69.42 316	88.49 300

bld_raw_dy_0_64		82.13 256	80.76 255	86.24 273	85.78 331	75.03 284	94.40 258	82.62 379	83.12 192	76.46 260	90.96 237	53.83 320	94.55 312	81.04 196	78.60 265	89.14 281

v1921920		82.02 258	80.23 264	87.41 250	85.62 332	77.92 233	95.79 210	93.69 273	78.86 278	76.67 256	86.44 302	62.50 253	95.83 258	72.69 275	69.77 314	88.47 301

v1240		81.70 262	79.83 272	87.30 254	85.50 333	77.70 242	95.48 221	93.44 282	78.46 283	76.53 259	86.44 302	60.85 266	95.84 257	71.59 282	70.17 306	88.35 305

pm-mvs1		80.05 280	78.02 285	86.15 274	85.42 334	75.81 277	95.11 240	92.69 305	77.13 297	70.36 319	87.43 283	58.44 283	95.27 289	71.36 284	64.25 351	87.36 326

our_test_3		77.90 299	75.37 303	85.48 288	85.39 335	76.74 258	93.63 276	91.67 317	73.39 327	65.72 342	84.65 330	58.20 286	93.13 336	57.82 346	67.87 331	86.57 335

ppachtmachnet_test		77.19 305	74.22 313	86.13 275	85.39 335	78.22 220	93.98 268	91.36 323	71.74 339	67.11 332	84.87 328	56.67 302	93.37 335	52.21 364	64.59 348	86.80 331

MDA-MVSNet-bldmvs		71.45 334	67.94 339	81.98 329	85.33 337	68.50 339	92.35 302	88.76 352	70.40 344	42.99 385	81.96 345	46.57 345	91.31 354	48.75 376	54.39 369	86.11 341

Baseline_NR-MVSNet		81.22 269	80.07 267	84.68 298	85.32 338	75.12 282	96.48 169	88.80 351	76.24 306	77.28 249	86.40 305	67.61 219	94.39 317	75.73 252	66.73 343	84.54 354

DTE-MVSNet		78.37 293	77.06 292	82.32 327	85.22 339	67.17 347	93.40 281	93.66 274	78.71 280	70.53 318	88.29 272	59.06 279	92.23 343	61.38 335	63.28 355	87.56 321

pmmvs5		81.34 267	79.54 273	86.73 265	85.02 340	76.91 254	96.22 187	91.65 318	77.65 290	73.55 291	88.61 266	55.70 309	94.43 316	74.12 267	73.35 291	88.86 295

XVG-ACMP-BASELINE		79.38 288	77.90 286	83.81 310	84.98 341	67.14 348	89.03 329	93.18 295	80.26 251	72.87 302	88.15 275	38.55 367	96.26 236	76.05 248	78.05 270	88.02 311

test_vis1_n		85.60 197	85.70 176	85.33 289	84.79 342	64.98 351	96.83 147	91.61 320	87.36 97	91.00 97	94.84 168	36.14 371	97.18 196	95.66 44	93.03 143	93.82 224

MDA-MVSNet_test_wron		73.54 323	70.43 331	82.86 321	84.55 343	71.85 315	91.74 309	91.32 325	67.63 352	46.73 382	81.09 351	55.11 313	90.42 362	55.91 356	59.76 361	86.31 338

SixPastTwentyTwo		76.04 311	74.32 312	81.22 331	84.54 344	61.43 367	91.16 315	89.30 346	77.89 286	64.04 347	86.31 306	48.23 336	94.29 319	63.54 327	63.84 353	87.93 313

YYNet1		73.53 324	70.43 331	82.85 322	84.52 345	71.73 318	91.69 310	91.37 322	67.63 352	46.79 381	81.21 350	55.04 314	90.43 361	55.93 355	59.70 362	86.38 337

N_pmnet		61.30 347	60.20 350	64.60 367	84.32 346	17.00 408	91.67 311	10.98 406	61.77 367	58.45 370	78.55 360	49.89 333	91.83 349	42.27 383	63.94 352	84.97 352

mvs_tets		81.74 261	80.71 257	84.84 295	84.22 347	70.29 327	93.91 271	93.78 268	82.77 203	73.37 295	89.46 257	47.36 344	95.31 287	81.99 191	79.55 255	88.92 293

jajsoiax		82.12 257	81.15 251	85.03 294	84.19 348	70.70 324	94.22 265	93.95 253	83.07 194	73.48 292	89.75 254	49.66 334	95.37 283	82.24 190	79.76 249	89.02 287

EU-MVSNet		76.92 308	76.95 293	76.83 351	84.10 349	54.73 382	91.77 308	92.71 304	72.74 332	69.57 324	88.69 265	58.03 289	87.43 374	64.91 320	70.00 312	88.33 306

test_djsdf		83.00 243	82.45 232	84.64 300	84.07 350	69.78 331	94.80 250	94.48 224	80.74 235	75.41 281	87.70 280	61.32 265	95.10 298	83.77 172	79.76 249	89.04 286

v7n		79.32 289	77.34 289	85.28 290	84.05 351	72.89 306	93.38 282	93.87 260	75.02 314	70.68 316	84.37 331	59.58 273	95.62 273	67.60 303	67.50 336	87.32 327

test_vis1_rt		73.96 320	72.40 323	78.64 345	83.91 352	61.16 368	95.63 216	68.18 395	76.32 303	60.09 366	74.77 369	29.01 384	97.54 173	87.74 138	75.94 276	77.22 379

dmvs_testset		72.00 333	73.36 319	67.91 362	83.83 353	31.90 402	85.30 358	77.12 387	82.80 202	63.05 354	92.46 211	61.54 263	82.55 385	42.22 384	71.89 298	89.29 276

OurMVSNet-221017-0		77.18 306	76.06 298	80.55 336	83.78 354	60.00 371	90.35 321	91.05 329	77.01 301	66.62 338	87.92 278	47.73 342	94.03 322	71.63 281	68.44 325	87.62 318

EG-PatchMatch MVS		74.92 317	72.02 324	83.62 315	83.76 355	73.28 299	93.62 277	92.04 313	68.57 351	58.88 368	83.80 336	31.87 380	95.57 277	56.97 352	78.67 261	82.00 371

K. test v3		73.62 321	71.59 326	79.69 339	82.98 356	59.85 372	90.85 319	88.83 350	77.13 297	58.90 367	82.11 344	43.62 351	91.72 350	65.83 316	54.10 370	87.50 324

test_fmvs2		79.59 284	79.90 271	78.67 344	82.86 357	55.82 379	95.20 234	89.55 342	81.09 228	80.12 225	89.80 253	34.31 376	93.51 332	87.82 137	78.36 268	86.69 333

test_fmvsmconf0.01_n		91.08 92	90.68 88	92.29 114	82.43 358	80.12 169	97.94 62	93.93 254	92.07 24	91.97 79	97.60 79	67.56 221	99.53 68	97.09 29	95.56 112	97.21 139

EGC-MVSNET		52.46 355	47.56 358	67.15 363	81.98 359	60.11 370	82.54 368	72.44 391	0.11 403	0.70 404	74.59 370	25.11 385	83.26 382	29.04 390	61.51 359	58.09 388

anonymousdsp		80.98 273	79.97 269	84.01 308	81.73 360	70.44 326	92.49 299	93.58 279	77.10 299	72.98 301	86.31 306	57.58 293	94.90 303	79.32 212	78.63 264	86.69 333

Anonymous20231206		75.29 316	73.64 317	80.22 337	80.75 361	63.38 360	93.36 283	90.71 336	73.09 329	67.12 331	83.70 337	50.33 331	90.85 358	53.63 362	70.10 310	86.44 336

Gipuma		45.11 360	42.05 362	54.30 377	80.69 362	51.30 384	35.80 395	83.81 375	28.13 391	27.94 395	34.53 395	11.41 398	76.70 391	21.45 394	54.65 367	34.90 395
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
lessismore_v0				79.98 338	80.59 363	58.34 374		80.87 381		58.49 369	83.46 339	43.10 355	93.89 324	63.11 329	48.68 379	87.72 315

OpenMVS_ROB	68.52 20	73.02 327	69.57 334	83.37 318	80.54 364	71.82 316	93.60 278	88.22 356	62.37 364	61.98 358	83.15 341	35.31 375	95.47 279	45.08 380	75.88 277	82.82 363

testgi		74.88 318	73.40 318	79.32 342	80.13 365	61.75 364	93.21 289	86.64 365	79.49 265	66.56 339	91.06 233	35.51 374	88.67 367	56.79 353	71.25 299	87.56 321

CMPMVS	54.94 21	75.71 315	74.56 310	79.17 343	79.69 366	55.98 377	89.59 324	93.30 290	60.28 374	53.85 378	89.07 260	47.68 343	96.33 234	76.55 241	81.02 241	85.22 350
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LF4IMVS		72.36 330	70.82 328	76.95 350	79.18 367	56.33 376	86.12 353	86.11 367	69.30 350	63.06 353	86.66 297	33.03 378	92.25 342	65.33 318	68.64 323	82.28 369

pmmvs6		74.65 319	71.67 325	83.60 316	79.13 368	69.94 329	93.31 287	90.88 333	61.05 373	65.83 341	84.15 334	43.43 352	94.83 306	66.62 310	60.63 360	86.02 343

DeepMVS_CX				64.06 368	78.53 369	43.26 393		68.11 397	69.94 347	38.55 387	76.14 367	18.53 389	79.34 386	43.72 381	41.62 389	69.57 383

CL-MVSNet_self_test		75.81 313	74.14 315	80.83 335	78.33 370	67.79 341	94.22 265	93.52 280	77.28 296	69.82 322	81.54 348	61.47 264	89.22 365	57.59 348	53.51 371	85.48 349

test20.03		72.36 330	71.15 327	75.98 355	77.79 371	59.16 373	92.40 301	89.35 345	74.09 320	61.50 360	84.32 332	48.09 337	85.54 380	50.63 369	62.15 358	83.24 361

UnsupCasMVSNet_eth		73.25 325	70.57 330	81.30 330	77.53 372	66.33 349	87.24 344	93.89 259	80.38 246	57.90 372	81.59 347	42.91 357	90.56 360	65.18 319	48.51 380	87.01 330

DSMNet-mixed		73.13 326	72.45 322	75.19 357	77.51 373	46.82 387	85.09 359	82.01 380	67.61 356	69.27 326	81.33 349	50.89 327	86.28 377	54.54 359	83.80 219	92.46 236

Patchmatch-RL test		76.65 309	74.01 316	84.55 302	77.37 374	64.23 354	78.49 377	82.84 378	78.48 282	64.63 346	73.40 374	76.05 132	91.70 351	76.99 236	57.84 364	97.72 105

Anonymous20240521		72.06 332	69.91 333	78.50 346	77.11 375	61.67 366	91.62 312	90.97 331	65.52 359	62.37 356	79.05 359	36.32 370	90.96 357	57.75 347	68.52 324	82.87 362

test_method		56.77 349	54.53 353	63.49 369	76.49 376	40.70 395	75.68 382	74.24 389	19.47 397	48.73 380	71.89 380	19.31 388	65.80 397	57.46 349	47.51 383	83.97 359

MIMVSNet1		69.44 338	66.65 342	77.84 347	76.48 377	62.84 362	87.42 342	88.97 349	66.96 357	57.75 373	79.72 358	32.77 379	85.83 379	46.32 378	63.42 354	84.85 353

pmmvs-eth3d		73.59 322	70.66 329	82.38 325	76.40 378	73.38 296	89.39 328	89.43 344	72.69 333	60.34 365	77.79 362	46.43 346	91.26 355	66.42 314	57.06 365	82.51 366

new_pmnet		66.18 344	63.18 347	75.18 358	76.27 379	61.74 365	83.79 364	84.66 371	56.64 383	51.57 379	71.85 381	31.29 381	87.93 369	49.98 371	62.55 356	75.86 380

KD-MVS_self_test		70.97 336	69.31 336	75.95 356	76.24 380	55.39 381	87.45 341	90.94 332	70.20 346	62.96 355	77.48 363	44.01 349	88.09 368	61.25 336	53.26 372	84.37 356

UnsupCasMVSNet_bld		68.60 342	64.50 346	80.92 334	74.63 381	67.80 340	83.97 363	92.94 301	65.12 360	54.63 377	68.23 383	35.97 372	92.17 345	60.13 338	44.83 384	82.78 364

PM-MVS		69.32 339	66.93 341	76.49 352	73.60 382	55.84 378	85.91 354	79.32 385	74.72 316	61.09 362	78.18 361	21.76 387	91.10 356	70.86 290	56.90 366	82.51 366

new-patchmatchnet		68.85 341	65.93 343	77.61 349	73.57 383	63.94 357	90.11 323	88.73 353	71.62 340	55.08 376	73.60 373	40.84 364	87.22 376	51.35 367	48.49 381	81.67 374

WB-MVS		57.26 348	56.22 351	60.39 373	69.29 384	35.91 400	86.39 352	70.06 393	59.84 378	46.46 383	72.71 376	51.18 326	78.11 387	15.19 397	34.89 392	67.14 386

test_fmvs3		69.56 337	69.19 337	70.67 360	69.01 385	47.05 386	90.87 318	86.81 363	71.31 342	66.79 336	77.15 364	16.40 391	83.17 383	81.84 192	62.51 357	81.79 373

SSC-MVS		56.01 351	54.96 352	59.17 374	68.42 386	34.13 401	84.98 360	69.23 394	58.08 382	45.36 384	71.67 382	50.30 332	77.46 388	14.28 398	32.33 393	65.91 387

ambc				76.02 354	68.11 387	51.43 383	64.97 391	89.59 341		60.49 364	74.49 371	17.17 390	92.46 339	61.50 334	52.85 374	84.17 358

APD_test1		56.56 350	53.58 354	65.50 364	67.93 388	46.51 389	77.24 381	72.95 390	38.09 388	42.75 386	75.17 368	13.38 394	82.78 384	40.19 385	54.53 368	67.23 385

pmmvs3		65.75 345	62.18 348	76.45 353	67.12 389	64.54 352	88.68 332	85.05 370	54.77 385	57.54 374	73.79 372	29.40 383	86.21 378	55.49 358	47.77 382	78.62 377

TDRefinement		69.20 340	65.78 344	79.48 340	66.04 390	62.21 363	88.21 335	86.12 366	62.92 363	61.03 363	85.61 314	33.23 377	94.16 320	55.82 357	53.02 373	82.08 370

mvsany_test3		67.19 343	65.34 345	72.72 359	63.08 391	48.57 385	83.12 366	78.09 386	72.07 336	61.21 361	77.11 365	22.94 386	87.78 372	78.59 219	51.88 376	81.80 372

test_f		64.01 346	62.13 349	69.65 361	63.00 392	45.30 392	83.66 365	80.68 382	61.30 370	55.70 375	72.62 377	14.23 393	84.64 381	69.84 295	58.11 363	79.00 376

test_vis3_rt		54.10 353	51.04 356	63.27 370	58.16 393	46.08 391	84.17 362	49.32 405	56.48 384	36.56 389	49.48 392	8.03 401	91.91 348	67.29 306	49.87 377	51.82 391

FPMVS		55.09 352	52.93 355	61.57 371	55.98 394	40.51 396	83.11 367	83.41 377	37.61 389	34.95 390	71.95 379	14.40 392	76.95 389	29.81 389	65.16 347	67.25 384

PMMVS2		50.90 356	46.31 359	64.67 366	55.53 395	46.67 388	77.30 380	71.02 392	40.89 387	34.16 391	59.32 386	9.83 399	76.14 392	40.09 386	28.63 394	71.21 381

wuyk23d		14.10 367	13.89 370	14.72 383	55.23 396	22.91 407	33.83 396	3.56 407	4.94 400	4.11 401	2.28 403	2.06 406	19.66 402	10.23 401	8.74 400	1.59 400

E-PMN		32.70 364	32.39 366	33.65 381	53.35 397	25.70 405	74.07 385	53.33 403	21.08 395	17.17 399	33.63 397	11.85 397	54.84 399	12.98 399	14.04 396	20.42 396

testf1		45.70 358	42.41 360	55.58 375	53.29 398	40.02 397	68.96 389	62.67 399	27.45 392	29.85 392	61.58 384	5.98 402	73.83 394	28.49 392	43.46 387	52.90 389

APD_test2		45.70 358	42.41 360	55.58 375	53.29 398	40.02 397	68.96 389	62.67 399	27.45 392	29.85 392	61.58 384	5.98 402	73.83 394	28.49 392	43.46 387	52.90 389

EMVS		31.70 365	31.45 367	32.48 382	50.72 400	23.95 406	74.78 384	52.30 404	20.36 396	16.08 400	31.48 398	12.80 395	53.60 400	11.39 400	13.10 399	19.88 397

LCM-MVSNet		52.52 354	48.24 357	65.35 365	47.63 401	41.45 394	72.55 387	83.62 376	31.75 390	37.66 388	57.92 388	9.19 400	76.76 390	49.26 373	44.60 385	77.84 378

MVE	35.65 22	33.85 363	29.49 368	46.92 379	41.86 402	36.28 399	50.45 394	56.52 402	18.75 398	18.28 397	37.84 394	2.41 405	58.41 398	18.71 395	20.62 395	46.06 393
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		46.22 357	41.28 364	61.04 372	39.91 403	46.25 390	70.59 388	76.18 388	58.87 380	23.09 396	48.00 393	12.58 396	66.54 396	28.65 391	13.62 397	70.35 382

PMVS	34.80 23	39.19 362	35.53 365	50.18 378	29.72 404	30.30 403	59.60 393	66.20 398	26.06 394	17.91 398	49.53 391	3.12 404	74.09 393	18.19 396	49.40 378	46.14 392
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		41.54 361	41.93 363	40.38 380	20.10 405	26.84 404	61.93 392	59.09 401	14.81 399	28.51 394	80.58 352	35.53 373	48.33 401	63.70 326	13.11 398	45.96 394

testmvs		9.92 368	12.94 371	0.84 385	0.65 406	0.29 410	93.78 274	0.39 408	0.42 401	2.85 402	15.84 401	0.17 408	0.30 404	2.18 402	0.21 401	1.91 399

test123		9.07 369	11.73 372	1.11 384	0.50 407	0.77 409	89.44 327	0.20 409	0.34 402	2.15 403	10.72 402	0.34 407	0.32 403	1.79 403	0.08 402	2.23 398

test_blank		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

eth-test2					0.00 408

eth-test					0.00 408

uanet_test		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

DCPMVS		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

cdsmvs_eth3d_5k		21.43 366	28.57 369	0.00 386	0.00 408	0.00 411	0.00 397	95.93 146	0.00 404	0.00 405	97.66 72	63.57 248	0.00 405	0.00 404	0.00 403	0.00 401

pcd_1.5k_mvsjas		5.92 371	7.89 374	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	71.04 205	0.00 405	0.00 404	0.00 403	0.00 401

sosnet-low-res		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

sosnet		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

uncertanet		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

Regformer		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

ab-mvs-re		8.11 370	10.81 373	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	97.30 94	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

uanet		0.00 372	0.00 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.00 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

MM				96.15 8		89.50 9	99.18 5	98.10 8	95.68 1	96.64 20	97.92 58	80.72 61	99.80 25	99.16 1	97.96 56	99.15 24

WAC-MVS						67.18 344								49.00 374

PC_three_1452									91.12 35	98.33 2	98.42 28	92.51 2	99.81 21	98.96 3	99.37 1	99.70 3

test_241102_TWO								96.78 50	88.72 66	97.70 8	98.91 2	87.86 21	99.82 18	98.15 11	99.00 15	99.47 9

test_0728_THIRD									88.38 73	96.69 17	98.76 12	89.64 13	99.76 31	97.47 24	98.84 23	99.38 14

GSMVS																97.54 117

sam_mvs1												77.59 103				97.54 117

sam_mvs												75.35 151

MTGPA								96.33 113

test_post1							85.88 355				30.24 399	73.77 174	95.07 301	73.89 268

test_post											33.80 396	76.17 130	95.97 248

patchmatchnet-post											77.09 366	77.78 102	95.39 281

MTMP							97.53 90	68.16 396

test9_res														96.00 39	99.03 13	98.31 62

agg_prior2														94.30 58	99.00 15	98.57 46

test_prior4						82.34 111	97.75 75

test_prior2							98.37 39		86.08 119	94.57 49	98.02 51	83.14 48		95.05 51	98.79 26

旧先验2							96.97 138		74.06 321	96.10 27			97.76 160	88.38 133

新几何2							96.42 176

无先验							96.87 145	96.78 50	77.39 293				99.52 69	79.95 207		98.43 55

原ACMM2							96.84 146

testdata2													99.48 73	76.45 243

segment_acmp												82.69 53

testdata1							95.57 219		87.44 94

plane_prior5								94.69 209					97.30 189	87.08 144	82.82 230	90.96 244

plane_prior4											94.15 183

plane_prior3						77.75 240			90.17 50	81.33 209

plane_prior2							97.18 115		89.89 53

plane_prior						77.96 230	97.52 93		90.36 48						82.96 228

n2								0.00 410

nn								0.00 410

door-mid								79.75 384

test11								96.50 93

door								80.13 383

HQP5-MVS						78.48 210

BP-MVS														87.67 140

HQP4-MVS										82.30 194			97.32 187			91.13 242

HQP3-MVS								94.80 204							83.01 226

HQP2-MVS												65.40 237

MDTV_nov1_ep13_2view						81.74 127	86.80 347		80.65 237	85.65 156		74.26 168		76.52 242		96.98 146

ACMMP++_ref															78.45 267

ACMMP++															79.05 258

Test By Simon												71.65 198

High-resolution multi-view benchmark