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.

PGM-MVS		96.81 27	96.53 30	97.65 29	99.35 13	93.53 43	97.65 64	98.98 1	92.22 86	97.14 21	98.44 14	91.17 41	99.85 9	94.35 66	99.46 23	99.57 11

MVS_111021_HR		96.68 34	96.58 29	96.99 57	98.46 51	92.31 71	96.20 203	98.90 2	94.30 35	95.86 60	97.74 64	92.33 21	99.38 88	96.04 30	99.42 28	99.28 46

ACMMP		96.27 44	95.93 44	97.28 45	99.24 19	92.62 65	98.25 25	98.81 3	92.99 67	94.56 84	98.39 20	88.96 63	99.85 9	94.57 65	97.63 94	99.36 39
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
MVS_111021_LR		96.24 45	96.19 42	96.39 79	98.23 72	91.35 100	96.24 201	98.79 4	93.99 39	95.80 63	97.65 70	89.92 58	99.24 95	95.87 33	99.20 49	98.58 92

FC-MVSNet-test		93.94 98	93.57 90	95.04 138	95.48 179	91.45 98	98.12 30	98.71 5	93.37 53	90.23 167	96.70 110	87.66 80	97.85 231	91.49 119	90.39 211	95.83 194

UniMVSNet (Re)		93.31 117	92.55 123	95.61 112	95.39 182	93.34 50	97.39 89	98.71 5	93.14 63	90.10 176	94.83 199	87.71 79	98.03 204	91.67 117	83.99 273	95.46 210

FIs		94.09 92	93.70 86	95.27 127	95.70 173	92.03 81	98.10 31	98.68 7	93.36 55	90.39 164	96.70 110	87.63 82	97.94 221	92.25 97	90.50 210	95.84 193

WR-MVS_H		92.00 164	91.35 159	93.95 182	95.09 203	89.47 155	98.04 35	98.68 7	91.46 110	88.34 223	94.68 205	85.86 103	97.56 253	85.77 215	84.24 271	94.82 253

VPA-MVSNet		93.24 119	92.48 128	95.51 117	95.70 173	92.39 70	97.86 45	98.66 9	92.30 85	92.09 134	95.37 181	80.49 201	98.40 162	93.95 71	85.86 246	95.75 201

UniMVSNet_NR-MVSNet		93.37 115	92.67 118	95.47 122	95.34 185	92.83 59	97.17 111	98.58 10	92.98 72	90.13 172	95.80 155	88.37 73	97.85 231	91.71 113	83.93 274	95.73 203

CSCG		96.05 49	95.91 45	96.46 77	99.24 19	90.47 128	98.30 21	98.57 11	89.01 173	93.97 95	97.57 79	92.62 16	99.76 21	94.66 64	99.27 43	99.15 53

MSLP-MVS++		96.94 23	97.06 8	96.59 67	98.72 35	91.86 86	97.67 61	98.49 12	94.66 27	97.24 16	98.41 19	92.31 24	98.94 122	96.61 14	99.46 23	98.96 69

HyFIR lowres test		93.66 106	92.92 109	95.87 101	98.24 69	89.88 141	94.58 257	98.49 12	85.06 259	93.78 96	95.78 159	82.86 153	98.67 143	91.77 111	95.71 137	99.07 61

CHOSEN 1792x2688		94.15 88	93.51 94	96.06 94	98.27 66	89.38 163	95.18 250	98.48 14	85.60 252	93.76 97	97.11 97	83.15 132	99.61 45	91.33 122	98.72 70	99.19 49

PHI-MVS		96.77 29	96.46 33	97.71 26	98.40 55	94.07 27	98.21 28	98.45 15	89.86 148	97.11 24	98.01 46	92.52 19	99.69 33	96.03 31	99.53 14	99.36 39

PVSNet_BlendedMVS		94.06 93	93.92 81	94.47 160	98.27 66	89.46 157	96.73 150	98.36 16	90.17 143	94.36 87	95.24 187	88.02 74	99.58 53	93.44 84	90.72 206	94.36 270

PVSNet_Blended		94.87 77	94.56 71	95.81 103	98.27 66	89.46 157	95.47 238	98.36 16	88.84 180	94.36 87	96.09 144	88.02 74	99.58 53	93.44 84	98.18 81	98.40 110

3Dnovator	91.36 5	95.19 67	94.44 78	97.44 38	96.56 136	93.36 49	98.65 6	98.36 16	94.12 37	89.25 211	98.06 43	82.20 171	99.77 20	93.41 86	99.32 39	99.18 50

HFP-MVS		97.14 13	96.92 14	97.83 14	99.42 3	94.12 25	98.52 10	98.32 19	93.21 58	97.18 18	98.29 34	92.08 26	99.83 13	95.63 39	99.59 7	99.54 17

#test#		97.02 19	96.75 24	97.83 14	99.42 3	94.12 25	98.15 29	98.32 19	92.57 81	97.18 18	98.29 34	92.08 26	99.83 13	95.12 49	99.59 7	99.54 17

ACMMPR		97.07 16	96.84 17	97.79 18	99.44 2	93.88 31	98.52 10	98.31 21	93.21 58	97.15 20	98.33 28	91.35 39	99.86 6	95.63 39	99.59 7	99.62 5

APDe-MVS		97.82 1	97.73 1	98.08 7	99.15 23	94.82 10	98.81 2	98.30 22	94.76 24	98.30 4	98.90 1	93.77 6	99.68 35	97.93 1	99.69 1	99.75 1

CP-MVS		97.02 19	96.81 20	97.64 31	99.33 14	93.54 42	98.80 3	98.28 23	92.99 67	96.45 42	98.30 33	91.90 31	99.85 9	95.61 41	99.68 2	99.54 17

SteuartSystems-ACMMP		97.62 3	97.53 2	97.87 12	98.39 57	94.25 20	98.43 16	98.27 24	95.34 9	98.11 5	98.56 7	94.53 1	99.71 27	96.57 16	99.62 5	99.65 3
Skip Steuart: Steuart Systems R&D Blog.
ESAPD								98.25 25

PVSNet_Blended_VisFu		95.27 63	94.91 63	96.38 80	98.20 73	90.86 118	97.27 99	98.25 25	90.21 142	94.18 91	97.27 89	87.48 85	99.73 23	93.53 80	97.77 92	98.55 93

region2R		97.07 16	96.84 17	97.77 21	99.46 1	93.79 35	98.52 10	98.24 27	93.19 61	97.14 21	98.34 25	91.59 37	99.87 5	95.46 44	99.59 7	99.64 4

PS-CasMVS		91.55 181	90.84 180	93.69 201	94.96 208	88.28 187	97.84 48	98.24 27	91.46 110	88.04 230	95.80 155	79.67 214	97.48 258	87.02 196	84.54 269	95.31 222

DU-MVS		92.90 131	92.04 134	95.49 119	94.95 209	92.83 59	97.16 112	98.24 27	93.02 66	90.13 172	95.71 163	83.47 127	97.85 231	91.71 113	83.93 274	95.78 197

XVS		97.18 10	96.96 12	97.81 16	99.38 8	94.03 29	98.59 7	98.20 30	94.85 17	96.59 35	98.29 34	91.70 34	99.80 18	95.66 37	99.40 30	99.62 5

X-MVStestdata		91.71 168	89.67 221	97.81 16	99.38 8	94.03 29	98.59 7	98.20 30	94.85 17	96.59 35	32.69 338	91.70 34	99.80 18	95.66 37	99.40 30	99.62 5

ACMMP_Plus		97.20 9	96.86 16	98.23 3	99.09 24	95.16 6	97.60 71	98.19 32	92.82 76	97.93 8	98.74 3	91.60 36	99.86 6	96.26 20	99.52 15	99.67 2

CP-MVSNet		91.89 166	91.24 165	93.82 188	95.05 204	88.57 181	97.82 49	98.19 32	91.70 104	88.21 228	95.76 160	81.96 175	97.52 256	87.86 173	84.65 267	95.37 219

PEN-MVS		91.20 196	90.44 191	93.48 212	94.49 227	87.91 215	97.76 52	98.18 34	91.29 115	87.78 233	95.74 162	80.35 204	97.33 269	85.46 220	82.96 285	95.19 231

DELS-MVS		96.61 35	96.38 36	97.30 43	97.79 94	93.19 51	95.96 215	98.18 34	95.23 11	95.87 59	97.65 70	91.45 38	99.70 32	95.87 33	99.44 27	99.00 67
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
tfpnnormal		89.70 236	88.40 240	93.60 205	95.15 199	90.10 131	97.56 75	98.16 36	87.28 224	86.16 258	94.63 208	77.57 247	98.05 199	74.48 299	84.59 268	92.65 292

VNet		95.89 54	95.45 51	97.21 51	98.07 79	92.94 58	97.50 79	98.15 37	93.87 41	97.52 10	97.61 76	85.29 108	99.53 68	95.81 36	95.27 141	99.16 51

DeepPCF-MVS	93.97 1	96.61 35	97.09 7	95.15 134	98.09 78	86.63 241	96.00 214	98.15 37	95.43 7	97.95 7	98.56 7	93.40 8	99.36 89	96.77 12	99.48 22	99.45 28

SD-MVS		97.41 6	97.53 2	97.06 55	98.57 49	94.46 14	97.92 42	98.14 39	94.82 21	99.01 1	98.55 9	94.18 3	97.41 264	96.94 5	99.64 3	99.32 41

UA-Net		95.95 53	95.53 50	97.20 52	97.67 98	92.98 57	97.65 64	98.13 40	94.81 22	96.61 33	98.35 22	88.87 64	99.51 72	90.36 131	97.35 104	99.11 58

QAPM		93.45 113	92.27 131	96.98 58	96.77 128	92.62 65	98.39 18	98.12 41	84.50 267	88.27 227	97.77 62	82.39 167	99.81 17	85.40 221	98.81 67	98.51 98

Vis-MVSNet		95.23 64	94.81 64	96.51 72	97.18 112	91.58 94	98.26 24	98.12 41	94.38 33	94.90 79	98.15 39	82.28 168	98.92 123	91.45 121	98.58 74	99.01 66
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 133	91.68 146	96.40 78	95.34 185	92.73 62	98.27 23	98.12 41	84.86 262	85.78 260	97.75 63	78.89 228	99.74 22	87.50 186	98.65 71	96.73 168

TranMVSNet+NR-MVSNet		92.50 144	91.63 151	95.14 135	94.76 218	92.07 79	97.53 77	98.11 44	92.90 75	89.56 199	96.12 141	83.16 131	97.60 252	89.30 145	83.20 284	95.75 201

CPTT-MVS		95.57 58	95.19 59	96.70 61	99.27 17	91.48 95	98.33 20	98.11 44	87.79 211	95.17 77	98.03 44	87.09 90	99.61 45	93.51 81	99.42 28	99.02 62

Regformer-2		97.16 12	96.99 10	97.67 28	98.32 63	93.84 33	96.83 138	98.10 46	95.24 10	97.49 11	98.25 37	92.57 17	99.61 45	96.80 9	99.29 41	99.56 13

APD-MVS		96.95 22	96.60 27	98.01 8	99.03 27	94.93 9	97.72 58	98.10 46	91.50 108	98.01 6	98.32 30	92.33 21	99.58 53	94.85 58	99.51 17	99.53 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 25	96.60 27	97.64 31	99.40 5	93.44 45	98.50 13	98.09 48	93.27 57	95.95 58	98.33 28	91.04 43	99.88 3	95.20 46	99.57 11	99.60 8

MPTG		97.07 16	96.77 23	97.97 10	99.37 10	94.42 16	97.15 113	98.08 49	95.07 14	96.11 49	98.59 5	90.88 47	99.90 1	96.18 27	99.50 19	99.58 9

MTGPA								98.08 49

MTAPA		97.08 15	96.78 22	97.97 10	99.37 10	94.42 16	97.24 101	98.08 49	95.07 14	96.11 49	98.59 5	90.88 47	99.90 1	96.18 27	99.50 19	99.58 9

CNVR-MVS		97.68 2	97.44 5	98.37 2	98.90 30	95.86 2	97.27 99	98.08 49	95.81 3	97.87 9	98.31 31	94.26 2	99.68 35	97.02 4	99.49 21	99.57 11

DP-MVS Recon		95.68 56	95.12 61	97.37 40	99.19 22	94.19 22	97.03 118	98.08 49	88.35 197	95.09 78	97.65 70	89.97 57	99.48 75	92.08 104	98.59 73	98.44 107

MCST-MVS		97.18 10	96.84 17	98.20 4	99.30 16	95.35 3	97.12 115	98.07 54	93.54 51	96.08 51	97.69 66	93.86 5	99.71 27	96.50 17	99.39 32	99.55 15

NR-MVSNet		92.34 150	91.27 164	95.53 116	94.95 209	93.05 54	97.39 89	98.07 54	92.65 80	84.46 268	95.71 163	85.00 112	97.77 240	89.71 137	83.52 281	95.78 197

MP-MVS-pluss		96.70 31	96.27 38	97.98 9	99.23 21	94.71 11	96.96 125	98.06 56	90.67 130	95.55 72	98.78 2	91.07 42	99.86 6	96.58 15	99.55 12	99.38 37
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 27	96.71 25	97.12 54	99.01 28	92.31 71	97.98 40	98.06 56	93.11 64	97.44 13	98.55 9	90.93 45	99.55 63	96.06 29	99.25 44	99.51 21

MP-MVS		96.77 29	96.45 34	97.72 24	99.39 7	93.80 34	98.41 17	98.06 56	93.37 53	95.54 73	98.34 25	90.59 50	99.88 3	94.83 59	99.54 13	99.49 24

HPM-MVS_fast		96.51 37	96.27 38	97.22 50	99.32 15	92.74 61	98.74 4	98.06 56	90.57 139	96.77 28	98.35 22	90.21 54	99.53 68	94.80 61	99.63 4	99.38 37

HPM-MVS		96.69 32	96.45 34	97.40 39	99.36 12	93.11 53	98.87 1	98.06 56	91.17 119	96.40 43	97.99 48	90.99 44	99.58 53	95.61 41	99.61 6	99.49 24

sss		94.51 82	93.80 84	96.64 62	97.07 116	91.97 84	96.32 192	98.06 56	88.94 177	94.50 85	96.78 105	84.60 117	99.27 93	91.90 107	96.02 129	98.68 90

DeepC-MVS	93.07 3	96.06 48	95.66 49	97.29 44	97.96 85	93.17 52	97.30 98	98.06 56	93.92 40	93.38 103	98.66 4	86.83 92	99.73 23	95.60 43	99.22 47	98.96 69
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 8	97.03 9	98.11 6	98.77 33	95.06 8	97.34 93	98.04 63	95.96 2	97.09 25	97.88 52	93.18 9	99.71 27	95.84 35	99.17 51	99.56 13

DeepC-MVS_fast	93.89 2	96.93 24	96.64 26	97.78 19	98.64 44	94.30 18	97.41 85	98.04 63	94.81 22	96.59 35	98.37 21	91.24 40	99.64 44	95.16 47	99.52 15	99.42 32
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
abl_6		96.40 40	96.21 40	96.98 58	98.89 31	92.20 76	97.89 43	98.03 65	93.34 56	97.22 17	98.42 16	87.93 77	99.72 26	95.10 50	99.07 59	99.02 62

TEST9					98.70 36	94.19 22	96.41 180	98.02 66	88.17 204	96.03 52	97.56 81	92.74 12	99.59 50

train_agg		96.30 43	95.83 46	97.72 24	98.70 36	94.19 22	96.41 180	98.02 66	88.58 189	96.03 52	97.56 81	92.73 13	99.59 50	95.04 51	99.37 37	99.39 34

test_8					98.67 38	94.06 28	96.37 187	98.01 68	88.58 189	95.98 57	97.55 83	92.73 13	99.58 53

Regformer-4		96.97 21	96.87 15	97.25 47	98.34 60	92.66 64	96.96 125	98.01 68	95.12 13	97.14 21	98.42 16	91.82 32	99.61 45	96.90 6	99.13 54	99.50 22

agg_prior3		96.16 47	95.67 48	97.62 34	98.67 38	93.88 31	96.41 180	98.00 70	87.93 208	95.81 62	97.47 85	92.33 21	99.59 50	95.04 51	99.37 37	99.39 34

agg_prior1		96.22 46	95.77 47	97.56 35	98.67 38	93.79 35	96.28 196	98.00 70	88.76 186	95.68 66	97.55 83	92.70 15	99.57 61	95.01 53	99.32 39	99.32 41

agg_prior					98.67 38	93.79 35		98.00 70		95.68 66			99.57 61

test_prior3		96.46 39	96.20 41	97.23 48	98.67 38	92.99 55	96.35 188	98.00 70	92.80 77	96.03 52	97.59 77	92.01 28	99.41 83	95.01 53	99.38 33	99.29 43

test_prior				97.23 48	98.67 38	92.99 55		98.00 70					99.41 83			99.29 43

Regformer-1		97.10 14	96.96 12	97.54 36	98.32 63	93.48 44	96.83 138	97.99 75	95.20 12	97.46 12	98.25 37	92.48 20	99.58 53	96.79 11	99.29 41	99.55 15

WR-MVS		92.34 150	91.53 154	94.77 152	95.13 201	90.83 119	96.40 184	97.98 76	91.88 101	89.29 208	95.54 173	82.50 162	97.80 236	89.79 136	85.27 253	95.69 204

HPM-MVS++		97.34 7	96.97 11	98.47 1	99.08 25	96.16 1	97.55 76	97.97 77	95.59 4	96.61 33	97.89 50	92.57 17	99.84 12	95.95 32	99.51 17	99.40 33

CANet		96.39 41	96.02 43	97.50 37	97.62 101	93.38 47	97.02 120	97.96 78	95.42 8	94.86 80	97.81 59	87.38 87	99.82 16	96.88 7	99.20 49	99.29 43

114514_t		93.95 97	93.06 106	96.63 64	99.07 26	91.61 91	97.46 84	97.96 78	77.99 310	93.00 115	97.57 79	86.14 101	99.33 90	89.22 148	99.15 52	98.94 72

MVS_0304		96.05 49	95.45 51	97.85 13	97.75 96	94.50 13	96.87 135	97.95 80	95.46 6	95.60 70	98.01 46	80.96 189	99.83 13	97.23 2	99.25 44	99.23 47

原ACMM1				96.38 80	98.59 46	91.09 111		97.89 81	87.41 220	95.22 76	97.68 67	90.25 52	99.54 65	87.95 172	99.12 57	98.49 102

CDPH-MVS		95.97 52	95.38 54	97.77 21	98.93 29	94.44 15	96.35 188	97.88 82	86.98 232	96.65 32	97.89 50	91.99 30	99.47 76	92.26 95	99.46 23	99.39 34

test11								97.88 82

无先验							95.79 223	97.87 84	83.87 274				99.65 39	87.68 179		98.89 78

3Dnovator+	91.43 4	95.40 59	94.48 76	98.16 5	96.90 122	95.34 4	98.48 14	97.87 84	94.65 28	88.53 221	98.02 45	83.69 125	99.71 27	93.18 89	98.96 64	99.44 30

VPNet		92.23 157	91.31 162	94.99 140	95.56 176	90.96 114	97.22 106	97.86 86	92.96 73	90.96 156	96.62 122	75.06 261	98.20 174	91.90 107	83.65 280	95.80 196

HSP-MVS		97.53 4	97.49 4	97.63 33	99.40 5	93.77 38	98.53 9	97.85 87	95.55 5	98.56 3	97.81 59	93.90 4	99.65 39	96.62 13	99.21 48	99.48 26

TSAR-MVS + MP.		97.42 5	97.33 6	97.69 27	99.25 18	94.24 21	98.07 34	97.85 87	93.72 45	98.57 2	98.35 22	93.69 7	99.40 85	97.06 3	99.46 23	99.44 30

AdaColmap		94.34 84	93.68 88	96.31 84	98.59 46	91.68 90	96.59 171	97.81 89	89.87 147	92.15 132	97.06 99	83.62 126	99.54 65	89.34 144	98.07 84	97.70 138

Regformer-3		96.85 26	96.80 21	97.01 56	98.34 60	92.02 82	96.96 125	97.76 90	95.01 16	97.08 26	98.42 16	91.71 33	99.54 65	96.80 9	99.13 54	99.48 26

新几何1				97.32 42	98.60 45	93.59 41		97.75 91	81.58 292	95.75 65	97.85 56	90.04 56	99.67 37	86.50 202	99.13 54	98.69 89

旧先验1					98.38 58	93.38 47		97.75 91			98.09 41	92.30 25			99.01 62	99.16 51

EI-MVSNet-Vis-set		96.51 37	96.47 32	96.63 64	98.24 69	91.20 105	96.89 134	97.73 93	94.74 25	96.49 39	98.49 11	90.88 47	99.58 53	96.44 18	98.32 78	99.13 55

1121		94.71 80	93.83 83	97.34 41	98.57 49	93.64 40	96.04 210	97.73 93	81.56 294	95.68 66	97.85 56	90.23 53	99.65 39	87.68 179	99.12 57	98.73 85

PAPM_NR		95.01 69	94.59 70	96.26 89	98.89 31	90.68 123	97.24 101	97.73 93	91.80 102	92.93 120	96.62 122	89.13 62	99.14 104	89.21 149	97.78 91	98.97 68

CHOSEN 280x420		93.12 122	92.72 117	94.34 166	96.71 130	87.27 224	90.29 312	97.72 96	86.61 242	91.34 146	95.29 184	84.29 121	98.41 161	93.25 88	98.94 65	97.35 151

EI-MVSNet-UG-set		96.34 42	96.30 37	96.47 75	98.20 73	90.93 116	96.86 136	97.72 96	94.67 26	96.16 48	98.46 12	90.43 51	99.58 53	96.23 21	97.96 87	98.90 76

LS3D		93.57 110	92.61 121	96.47 75	97.59 104	91.61 91	97.67 61	97.72 96	85.17 257	90.29 166	98.34 25	84.60 117	99.73 23	83.85 247	98.27 79	98.06 124

PAPR		94.18 87	93.42 100	96.48 74	97.64 100	91.42 99	95.55 233	97.71 99	88.99 174	92.34 128	95.82 154	89.19 60	99.11 106	86.14 207	97.38 102	98.90 76

pcd1.5k->3k		38.37 316	40.51 317	31.96 329	94.29 235	0.00 347	0.00 338	97.69 100	0.00 342	0.00 343	0.00 344	81.45 183	0.00 345	0.00 342	91.11 200	95.89 189

UGNet		94.04 95	93.28 103	96.31 84	96.85 123	91.19 106	97.88 44	97.68 101	94.40 31	93.00 115	96.18 138	73.39 275	99.61 45	91.72 112	98.46 75	98.13 119
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
testdata				95.46 123	98.18 76	88.90 177		97.66 102	82.73 283	97.03 27	98.07 42	90.06 55	98.85 130	89.67 138	98.98 63	98.64 91

test12				97.65 29	98.46 51	94.26 19		97.66 102		95.52 74		90.89 46	99.46 77		99.25 44	99.22 48

DTE-MVSNet		90.56 218	89.75 219	93.01 229	93.95 258	87.25 225	97.64 68	97.65 104	90.74 127	87.12 247	95.68 166	79.97 210	97.00 280	83.33 251	81.66 292	94.78 258

TAPA-MVS	90.10 7	92.30 153	91.22 167	95.56 114	98.33 62	89.60 148	96.79 145	97.65 104	81.83 289	91.52 141	97.23 92	87.94 76	98.91 124	71.31 310	98.37 77	98.17 118
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
cdsmvs_eth3d_5k		23.24 318	30.99 318	0.00 333	0.00 346	0.00 347	0.00 338	97.63 106	0.00 342	0.00 343	96.88 103	84.38 120	0.00 345	0.00 342	0.00 343	0.00 341

canonicalmvs		96.02 51	95.45 51	97.75 23	97.59 104	95.15 7	98.28 22	97.60 107	94.52 29	96.27 45	96.12 141	87.65 81	99.18 99	96.20 26	94.82 147	98.91 75

test222					98.24 69	92.21 74	95.33 242	97.60 107	79.22 305	95.25 75	97.84 58	88.80 66			99.15 52	98.72 86

cascas		91.20 196	90.08 204	94.58 158	94.97 207	89.16 173	93.65 278	97.59 109	79.90 302	89.40 203	92.92 264	75.36 259	98.36 165	92.14 100	94.75 149	96.23 176

MVSFormer		95.37 60	95.16 60	95.99 98	96.34 148	91.21 103	98.22 26	97.57 110	91.42 112	96.22 46	97.32 87	86.20 99	97.92 225	94.07 68	99.05 60	98.85 80

test_djsdf		93.07 124	92.76 112	94.00 177	93.49 273	88.70 179	98.22 26	97.57 110	91.42 112	90.08 178	95.55 172	82.85 154	97.92 225	94.07 68	91.58 192	95.40 216

OMC-MVS		95.09 68	94.70 68	96.25 90	98.46 51	91.28 101	96.43 178	97.57 110	92.04 97	94.77 82	97.96 49	87.01 91	99.09 114	91.31 123	96.77 116	98.36 114

PS-MVSNAJss		93.74 104	93.51 94	94.44 161	93.91 260	89.28 169	97.75 53	97.56 113	92.50 82	89.94 180	96.54 125	88.65 68	98.18 177	93.83 77	90.90 203	95.86 190

jajsoiax		92.42 147	91.89 140	94.03 176	93.33 279	88.50 183	97.73 56	97.53 114	92.00 99	88.85 215	96.50 127	75.62 258	98.11 183	93.88 75	91.56 193	95.48 207

mvs_tets		92.31 152	91.76 142	93.94 185	93.41 275	88.29 186	97.63 69	97.53 114	92.04 97	88.76 216	96.45 129	74.62 265	98.09 186	93.91 73	91.48 194	95.45 211

HQP_MVS		93.78 103	93.43 98	94.82 147	96.21 152	89.99 135	97.74 54	97.51 116	94.85 17	91.34 146	96.64 115	81.32 185	98.60 148	93.02 90	92.23 179	95.86 190

plane_prior5								97.51 116					98.60 148	93.02 90	92.23 179	95.86 190

PS-MVSNAJ		95.37 60	95.33 56	95.49 119	97.35 108	90.66 124	95.31 244	97.48 118	93.85 42	96.51 38	95.70 165	88.65 68	99.65 39	94.80 61	98.27 79	96.17 179

API-MVS		94.84 78	94.49 75	95.90 100	97.90 90	92.00 83	97.80 50	97.48 118	89.19 163	94.81 81	96.71 108	88.84 65	99.17 100	88.91 157	98.76 69	96.53 171

MG-MVS		95.61 57	95.38 54	96.31 84	98.42 54	90.53 126	96.04 210	97.48 118	93.47 52	95.67 69	98.10 40	89.17 61	99.25 94	91.27 124	98.77 68	99.13 55

MAR-MVS		94.22 86	93.46 96	96.51 72	98.00 80	92.19 77	97.67 61	97.47 121	88.13 206	93.00 115	95.84 152	84.86 115	99.51 72	87.99 171	98.17 82	97.83 133
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
CLD-MVS		92.98 127	92.53 125	94.32 167	96.12 161	89.20 171	95.28 245	97.47 121	92.66 79	89.90 181	95.62 168	80.58 199	98.40 162	92.73 93	92.40 177	95.38 218
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
nrg030		94.05 94	93.31 102	96.27 88	95.22 195	94.59 12	98.34 19	97.46 123	92.93 74	91.21 154	96.64 115	87.23 89	98.22 173	94.99 56	85.80 247	95.98 188

XVG-OURS		93.72 105	93.35 101	94.80 150	97.07 116	88.61 180	94.79 254	97.46 123	91.97 100	93.99 93	97.86 55	81.74 180	98.88 129	92.64 94	92.67 175	96.92 163

LPG-MVS_test		92.94 129	92.56 122	94.10 172	96.16 157	88.26 188	97.65 64	97.46 123	91.29 115	90.12 174	97.16 94	79.05 222	98.73 140	92.25 97	91.89 187	95.31 222

LGP-MVS_train				94.10 172	96.16 157	88.26 188		97.46 123	91.29 115	90.12 174	97.16 94	79.05 222	98.73 140	92.25 97	91.89 187	95.31 222

MVS		91.71 168	90.44 191	95.51 117	95.20 197	91.59 93	96.04 210	97.45 127	73.44 322	87.36 243	95.60 169	85.42 107	99.10 111	85.97 212	97.46 97	95.83 194

XVG-OURS-SEG-HR		93.86 100	93.55 91	94.81 149	97.06 118	88.53 182	95.28 245	97.45 127	91.68 105	94.08 92	97.68 67	82.41 166	98.90 125	93.84 76	92.47 176	96.98 155

ab-mvs		93.57 110	92.55 123	96.64 62	97.28 109	91.96 85	95.40 240	97.45 127	89.81 152	93.22 108	96.28 135	79.62 215	99.46 77	90.74 128	93.11 170	98.50 100

xiu_mvs_v2_base		95.32 62	95.29 57	95.40 125	97.22 110	90.50 127	95.44 239	97.44 130	93.70 47	96.46 41	96.18 138	88.59 71	99.53 68	94.79 63	97.81 90	96.17 179

1314		92.81 136	92.03 135	95.14 135	95.33 188	89.52 154	96.04 210	97.44 130	87.72 214	86.25 257	95.33 183	83.84 123	98.79 134	89.26 146	97.05 110	97.11 153

XXY-MVS		92.16 159	91.23 166	94.95 144	94.75 219	90.94 115	97.47 83	97.43 132	89.14 170	88.90 213	96.43 130	79.71 213	98.24 172	89.56 141	87.68 234	95.67 205

anonymousdsp		92.16 159	91.55 153	93.97 180	92.58 296	89.55 151	97.51 78	97.42 133	89.42 158	88.40 222	94.84 198	80.66 198	97.88 230	91.87 109	91.28 198	94.48 266

Effi-MVS+		94.93 74	94.45 77	96.36 82	96.61 131	91.47 96	96.41 180	97.41 134	91.02 124	94.50 85	95.92 148	87.53 84	98.78 135	93.89 74	96.81 115	98.84 82

HQP3-MVS								97.39 135							92.10 184

HQP-MVS		93.19 121	92.74 116	94.54 159	95.86 166	89.33 164	96.65 163	97.39 135	93.55 48	90.14 168	95.87 150	80.95 190	98.50 157	92.13 101	92.10 184	95.78 197

PLC	91.00 6	94.11 91	93.43 98	96.13 93	98.58 48	91.15 110	96.69 160	97.39 135	87.29 223	91.37 144	96.71 108	88.39 72	99.52 71	87.33 190	97.13 109	97.73 136
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 209	89.86 213	93.45 215	93.54 270	87.60 221	97.70 60	97.37 138	88.85 179	87.65 237	94.08 237	81.08 187	98.10 184	84.68 230	83.79 279	94.66 262

UnsupCasMVSNet_eth		85.99 278	84.45 279	90.62 285	89.97 309	82.40 280	93.62 279	97.37 138	89.86 148	78.59 310	92.37 273	65.25 308	95.35 308	82.27 263	70.75 322	94.10 275

ACMM	89.79 8	92.96 128	92.50 127	94.35 165	96.30 150	88.71 178	97.58 74	97.36 140	91.40 114	90.53 160	96.65 114	79.77 212	98.75 139	91.24 125	91.64 190	95.59 206
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 69	94.76 65	95.75 106	96.58 133	91.71 87	96.25 198	97.35 141	92.99 67	96.70 29	96.63 119	82.67 157	99.44 80	96.22 22	97.46 97	96.11 184

xiu_mvs_v1_base		95.01 69	94.76 65	95.75 106	96.58 133	91.71 87	96.25 198	97.35 141	92.99 67	96.70 29	96.63 119	82.67 157	99.44 80	96.22 22	97.46 97	96.11 184

xiu_mvs_v1_base_debi		95.01 69	94.76 65	95.75 106	96.58 133	91.71 87	96.25 198	97.35 141	92.99 67	96.70 29	96.63 119	82.67 157	99.44 80	96.22 22	97.46 97	96.11 184

WTY-MVS		94.71 80	94.02 80	96.79 60	97.71 97	92.05 80	96.59 171	97.35 141	90.61 136	94.64 83	96.93 101	86.41 96	99.39 86	91.20 126	94.71 151	98.94 72

F-COLMAP		93.58 109	92.98 107	95.37 126	98.40 55	88.98 175	97.18 110	97.29 145	87.75 213	90.49 161	97.10 98	85.21 109	99.50 74	86.70 199	96.72 119	97.63 139

XVG-ACMP-BASELINE		90.93 205	90.21 202	93.09 227	94.31 234	85.89 246	95.33 242	97.26 146	91.06 123	89.38 204	95.44 180	68.61 294	98.60 148	89.46 143	91.05 201	94.79 257

PCF-MVS	89.48 11	91.56 180	89.95 210	96.36 82	96.60 132	92.52 68	92.51 296	97.26 146	79.41 303	88.90 213	96.56 124	84.04 122	99.55 63	77.01 295	97.30 105	97.01 154
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 139	92.14 132	94.05 175	96.40 146	88.20 194	97.36 92	97.25 148	91.52 107	88.30 225	96.64 115	78.46 232	98.72 142	91.86 110	91.48 194	95.23 229
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 118	92.76 112	94.82 147	94.63 223	90.77 122	96.65 163	97.18 149	93.72 45	91.68 139	97.26 90	79.33 219	98.63 145	92.13 101	92.28 178	95.07 235

PatchMatch-RL		92.90 131	92.02 136	95.56 114	98.19 75	90.80 120	95.27 247	97.18 149	87.96 207	91.86 138	95.68 166	80.44 202	98.99 120	84.01 243	97.54 96	96.89 164

alignmvs		95.87 55	95.23 58	97.78 19	97.56 106	95.19 5	97.86 45	97.17 151	94.39 32	96.47 40	96.40 131	85.89 102	99.20 96	96.21 25	95.11 143	98.95 71

v748		90.34 222	89.54 224	92.75 237	93.25 280	85.71 249	97.61 70	97.17 151	88.54 192	87.20 246	93.54 252	81.02 188	98.01 208	85.73 217	81.80 289	94.52 265

MVS_Test		94.89 76	94.62 69	95.68 110	96.83 126	89.55 151	96.70 158	97.17 151	91.17 119	95.60 70	96.11 143	87.87 78	98.76 138	93.01 92	97.17 108	98.72 86

V4		90.71 214	90.00 208	92.82 232	93.21 284	87.03 231	97.59 73	97.16 154	88.21 200	87.69 235	93.92 242	80.93 192	98.06 196	87.39 187	83.90 277	93.39 284

v52		90.70 215	90.00 208	92.82 232	93.24 281	87.03 231	97.60 71	97.14 155	88.21 200	87.69 235	93.94 240	80.91 193	98.07 191	87.39 187	83.87 278	93.36 286

diffmvs		93.43 114	92.75 114	95.48 121	96.47 143	89.61 147	96.09 207	97.14 155	85.97 249	93.09 113	95.35 182	84.87 114	98.55 153	89.51 142	96.26 128	98.28 116

Fast-Effi-MVS+		93.46 112	92.75 114	95.59 113	96.77 128	90.03 132	96.81 142	97.13 157	88.19 202	91.30 149	94.27 231	86.21 98	98.63 145	87.66 181	96.46 126	98.12 120

EI-MVSNet		93.03 126	92.88 110	93.48 212	95.77 171	86.98 233	96.44 176	97.12 158	90.66 132	91.30 149	97.64 73	86.56 94	98.05 199	89.91 133	90.55 208	95.41 212

MVSTER		93.20 120	92.81 111	94.37 164	96.56 136	89.59 149	97.06 117	97.12 158	91.24 118	91.30 149	95.96 146	82.02 174	98.05 199	93.48 83	90.55 208	95.47 209

testing_2		87.33 268	85.03 275	94.22 168	87.77 318	89.32 166	94.97 252	97.11 160	89.22 162	71.64 320	88.73 306	55.16 325	97.94 221	91.95 105	88.73 227	95.41 212

Test4		89.48 238	87.50 248	95.44 124	90.76 306	89.72 145	95.78 225	97.09 161	90.28 141	77.67 311	91.74 285	55.42 324	98.08 187	91.92 106	96.83 114	98.52 96

LTVRE_ROB	88.41 13	90.99 203	89.92 211	94.19 169	96.18 155	89.55 151	96.31 193	97.09 161	87.88 210	85.67 261	95.91 149	78.79 229	98.57 151	81.50 270	89.98 214	94.44 268
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
v10		91.04 202	90.23 200	93.49 211	94.12 245	88.16 197	97.32 96	97.08 163	88.26 199	88.29 226	94.22 234	82.17 172	97.97 215	86.45 203	84.12 272	94.33 271

v144192		91.06 201	90.28 196	93.39 216	93.66 268	87.23 227	96.83 138	97.07 164	87.43 219	89.69 194	94.28 229	81.48 182	98.00 211	87.18 194	84.92 265	94.93 245

v1192		91.07 200	90.23 200	93.58 208	93.70 266	87.82 216	96.73 150	97.07 164	87.77 212	89.58 197	94.32 225	80.90 196	97.97 215	86.52 201	85.48 248	94.95 241

v8		91.29 194	90.53 190	93.57 209	94.15 241	88.12 201	97.34 93	97.06 166	88.99 174	88.32 224	94.26 233	83.08 138	98.01 208	87.62 183	83.92 276	94.57 264

v7		91.47 185	90.73 184	93.68 202	94.13 243	88.16 197	97.09 116	97.05 167	88.38 195	89.80 187	94.52 210	82.21 170	98.01 208	88.00 170	85.42 250	94.87 247

mvs_anonymous		93.82 101	93.74 85	94.06 174	96.44 145	85.41 253	95.81 222	97.05 167	89.85 150	90.09 177	96.36 133	87.44 86	97.75 241	93.97 70	96.69 120	99.02 62

IterMVS-LS		92.29 154	91.94 139	93.34 219	96.25 151	86.97 234	96.57 174	97.05 167	90.67 130	89.50 202	94.80 201	86.59 93	97.64 249	89.91 133	86.11 245	95.40 216
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 207	90.03 207	93.29 221	93.55 269	86.96 235	96.74 149	97.04 170	87.36 221	89.52 201	94.34 223	80.23 207	97.97 215	86.27 204	85.21 254	94.94 243

CDS-MVSNet		94.14 90	93.54 92	95.93 99	96.18 155	91.46 97	96.33 191	97.04 170	88.97 176	93.56 98	96.51 126	87.55 83	97.89 229	89.80 135	95.95 131	98.44 107
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 190	90.60 188	93.68 202	93.89 261	88.23 191	96.84 137	97.03 172	88.37 196	89.69 194	94.39 220	82.04 173	97.98 212	87.80 175	85.37 251	94.84 249

v1240		90.70 215	89.85 214	93.23 223	93.51 272	86.80 236	96.61 168	97.02 173	87.16 226	89.58 197	94.31 226	79.55 216	97.98 212	85.52 219	85.44 249	94.90 246

EPP-MVSNet		95.22 65	95.04 62	95.76 105	97.49 107	89.56 150	98.67 5	97.00 174	90.69 129	94.24 90	97.62 75	89.79 59	98.81 133	93.39 87	96.49 124	98.92 74

v1neww		91.70 171	91.01 170	93.75 194	94.19 237	88.14 199	97.20 107	96.98 175	89.18 165	89.87 184	94.44 217	83.10 136	98.06 196	89.06 153	85.09 257	95.06 238

v7new		91.70 171	91.01 170	93.75 194	94.19 237	88.14 199	97.20 107	96.98 175	89.18 165	89.87 184	94.44 217	83.10 136	98.06 196	89.06 153	85.09 257	95.06 238

v6		91.69 173	91.00 172	93.75 194	94.14 242	88.12 201	97.20 107	96.98 175	89.19 163	89.90 181	94.42 219	83.04 142	98.07 191	89.07 152	85.10 256	95.07 235

V42		91.58 179	90.87 176	93.73 197	94.05 254	88.50 183	97.32 96	96.97 178	88.80 185	89.71 192	94.33 224	82.54 161	98.05 199	89.01 155	85.07 259	94.64 263

v1141		91.61 175	90.89 173	93.78 191	94.01 255	88.24 190	96.96 125	96.96 179	89.17 167	89.75 190	94.29 227	82.99 146	98.03 204	88.85 159	85.00 262	95.07 235

divwei89l23v2f112		91.61 175	90.89 173	93.78 191	94.01 255	88.22 192	96.96 125	96.96 179	89.17 167	89.75 190	94.28 229	83.02 144	98.03 204	88.86 158	84.98 264	95.08 233

v1		91.61 175	90.89 173	93.78 191	94.01 255	88.21 193	96.96 125	96.96 179	89.17 167	89.78 189	94.29 227	82.97 148	98.05 199	88.85 159	84.99 263	95.08 233

FMVSNet2		91.31 193	90.08 204	94.99 140	96.51 139	92.21 74	97.41 85	96.95 182	88.82 182	88.62 218	94.75 203	73.87 269	97.42 263	85.20 224	88.55 229	95.35 220

ACMH	87.59 16	90.53 219	89.42 226	93.87 187	96.21 152	87.92 213	97.24 101	96.94 183	88.45 193	83.91 276	96.27 136	71.92 277	98.62 147	84.43 235	89.43 219	95.05 240
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 191	90.27 197	94.59 154	96.51 139	91.18 107	97.50 79	96.93 184	88.82 182	89.35 205	94.51 211	73.87 269	97.29 271	86.12 208	88.82 223	95.31 222

test1		91.35 191	90.27 197	94.59 154	96.51 139	91.18 107	97.50 79	96.93 184	88.82 182	89.35 205	94.51 211	73.87 269	97.29 271	86.12 208	88.82 223	95.31 222

FMVSNet3		91.78 167	90.69 186	95.03 139	96.53 138	92.27 73	97.02 120	96.93 184	89.79 153	89.35 205	94.65 207	77.01 249	97.47 259	86.12 208	88.82 223	95.35 220

FMVSNet1		89.88 233	88.31 241	94.59 154	95.41 181	91.18 107	97.50 79	96.93 184	86.62 241	87.41 241	94.51 211	65.94 306	97.29 271	83.04 254	87.43 237	95.31 222

TAMVS		94.01 96	93.46 96	95.64 111	96.16 157	90.45 129	96.71 155	96.89 188	89.27 161	93.46 102	96.92 102	87.29 88	97.94 221	88.70 163	95.74 135	98.53 95

v2v482		91.59 178	90.85 178	93.80 189	93.87 262	88.17 196	96.94 131	96.88 189	89.54 154	89.53 200	94.90 196	81.70 181	98.02 207	89.25 147	85.04 261	95.20 230

CNLPA		94.28 85	93.53 93	96.52 69	98.38 58	92.55 67	96.59 171	96.88 189	90.13 144	91.91 136	97.24 91	85.21 109	99.09 114	87.64 182	97.83 89	97.92 127

PAPM		91.52 183	90.30 195	95.20 128	95.30 189	89.83 142	93.38 282	96.85 191	86.26 245	88.59 220	95.80 155	84.88 113	98.15 179	75.67 298	95.93 132	97.63 139

pm-mvs1		90.72 213	89.65 223	93.96 181	94.29 235	89.63 146	97.79 51	96.82 192	89.07 171	86.12 259	95.48 179	78.61 230	97.78 238	86.97 197	81.67 291	94.46 267

CMPMVS	62.92 21	85.62 281	84.92 276	87.74 299	89.14 313	73.12 317	94.17 267	96.80 193	73.98 320	73.65 316	94.93 194	66.36 303	97.61 251	83.95 245	91.28 198	92.48 298
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 223	89.77 217	91.78 266	94.33 233	84.72 262	95.55 233	96.73 194	86.17 247	86.36 256	95.28 186	71.28 282	97.80 236	84.09 240	98.14 83	92.81 291

Effi-MVS+-dtu		93.08 123	93.21 104	92.68 240	96.02 163	83.25 275	97.14 114	96.72 195	93.85 42	91.20 155	93.44 258	83.08 138	98.30 170	91.69 115	95.73 136	96.50 173

mvs-test1		93.63 107	93.69 87	93.46 214	96.02 163	84.61 263	97.24 101	96.72 195	93.85 42	92.30 129	95.76 160	83.08 138	98.89 127	91.69 115	96.54 123	96.87 165

TSAR-MVS + GP.		96.69 32	96.49 31	97.27 46	98.31 65	93.39 46	96.79 145	96.72 195	94.17 36	97.44 13	97.66 69	92.76 11	99.33 90	96.86 8	97.76 93	99.08 60

1112_ss		93.37 115	92.42 129	96.21 91	97.05 119	90.99 112	96.31 193	96.72 195	86.87 238	89.83 186	96.69 112	86.51 95	99.14 104	88.12 168	93.67 164	98.50 100

PVSNet	86.66 18	92.24 156	91.74 145	93.73 197	97.77 95	83.69 272	92.88 291	96.72 195	87.91 209	93.00 115	94.86 197	78.51 231	99.05 118	86.53 200	97.45 101	98.47 105

v148		90.99 203	90.38 193	92.81 235	93.83 263	85.80 247	96.78 147	96.68 200	89.45 157	88.75 217	93.93 241	82.96 150	97.82 235	87.83 174	83.25 282	94.80 255

ACMH+	87.92 14	90.20 226	89.18 230	93.25 222	96.48 142	86.45 242	96.99 123	96.68 200	88.83 181	84.79 267	96.22 137	70.16 290	98.53 154	84.42 236	88.04 231	94.77 259

CANet_DTU		94.37 83	93.65 89	96.55 68	96.46 144	92.13 78	96.21 202	96.67 202	94.38 33	93.53 100	97.03 100	79.34 218	99.71 27	90.76 127	98.45 76	97.82 134

HY-MVS	89.66 9	93.87 99	92.95 108	96.63 64	97.10 115	92.49 69	95.64 230	96.64 203	89.05 172	93.00 115	95.79 158	85.77 105	99.45 79	89.16 151	94.35 152	97.96 125

Test_1112_low_res		92.84 135	91.84 141	95.85 102	97.04 120	89.97 138	95.53 235	96.64 203	85.38 253	89.65 196	95.18 188	85.86 103	99.10 111	87.70 177	93.58 169	98.49 102

Fast-Effi-MVS+-dtu		92.29 154	91.99 137	93.21 225	95.27 190	85.52 252	97.03 118	96.63 205	92.09 91	89.11 212	95.14 190	80.33 205	98.08 187	87.54 185	94.74 150	96.03 187

UnsupCasMVSNet_bld		82.13 293	79.46 295	90.14 291	88.00 316	82.47 278	90.89 310	96.62 206	78.94 306	75.61 313	84.40 322	56.63 321	96.31 286	77.30 294	66.77 328	91.63 312

jason		94.84 78	94.39 79	96.18 92	95.52 177	90.93 116	96.09 207	96.52 207	89.28 160	96.01 56	97.32 87	84.70 116	98.77 137	95.15 48	98.91 66	98.85 80
jason: jason.
EG-PatchMatch MVS		87.02 271	85.44 272	91.76 268	92.67 294	85.00 257	96.08 209	96.45 208	83.41 279	79.52 307	93.49 255	57.10 320	97.72 243	79.34 286	90.87 204	92.56 294

pmmvs6		87.81 265	86.19 267	92.69 239	91.32 303	86.30 243	97.34 93	96.41 209	80.59 301	84.05 275	94.37 222	67.37 301	97.67 246	84.75 228	79.51 299	94.09 276

PMMVS		92.86 133	92.34 130	94.42 163	94.92 211	86.73 237	94.53 259	96.38 210	84.78 264	94.27 89	95.12 192	83.13 134	98.40 162	91.47 120	96.49 124	98.12 120

RPSCF		90.75 211	90.86 177	90.42 288	96.84 124	76.29 311	95.61 232	96.34 211	83.89 272	91.38 143	97.87 53	76.45 251	98.78 135	87.16 195	92.23 179	96.20 177

MSDG		91.42 187	90.24 199	94.96 143	97.15 114	88.91 176	93.69 276	96.32 212	85.72 251	86.93 252	96.47 128	80.24 206	98.98 121	80.57 277	95.05 144	96.98 155

OurMVSNet-221017-0		90.51 220	90.19 203	91.44 273	93.41 275	81.25 287	96.98 124	96.28 213	91.68 105	86.55 255	96.30 134	74.20 268	97.98 212	88.96 156	87.40 239	95.09 232

MVP-Stereo		90.74 212	90.08 204	92.71 238	93.19 286	88.20 194	95.86 219	96.27 214	86.07 248	84.86 266	94.76 202	77.84 245	97.75 241	83.88 246	98.01 85	92.17 309
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 73	94.56 71	96.29 87	96.34 148	91.21 103	95.83 221	96.27 214	88.93 178	96.22 46	96.88 103	86.20 99	98.85 130	95.27 45	99.05 60	98.82 83

BH-untuned		92.94 129	92.62 120	93.92 186	97.22 110	86.16 245	96.40 184	96.25 216	90.06 145	89.79 188	96.17 140	83.19 130	98.35 166	87.19 193	97.27 106	97.24 152

test_normal		92.01 162	90.75 183	95.80 104	93.24 281	89.97 138	95.93 217	96.24 217	90.62 134	81.63 286	93.45 257	74.98 262	98.89 127	93.61 79	97.04 111	98.55 93

IS-MVSNet		94.90 75	94.52 74	96.05 95	97.67 98	90.56 125	98.44 15	96.22 218	93.21 58	93.99 93	97.74 64	85.55 106	98.45 160	89.98 132	97.86 88	99.14 54

GA-MVS		91.38 189	90.31 194	94.59 154	94.65 222	87.62 220	94.34 262	96.19 219	90.73 128	90.35 165	93.83 243	71.84 278	97.96 219	87.22 192	93.61 167	98.21 117

DI_MVS_plusplus_test		92.01 162	90.77 181	95.73 109	93.34 277	89.78 144	96.14 205	96.18 220	90.58 138	81.80 285	93.50 254	74.95 263	98.90 125	93.51 81	96.94 112	98.51 98

semantic-postprocess				91.82 263	95.52 177	84.20 266		96.15 221	90.61 136	87.39 242	94.27 231	75.63 257	96.44 284	87.34 189	86.88 242	94.82 253

IterMVS		90.15 228	89.67 221	91.61 270	95.48 179	83.72 269	94.33 263	96.12 222	89.99 146	87.31 245	94.15 235	75.78 256	96.27 287	86.97 197	86.89 241	94.83 251
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 137	91.51 157	96.52 69	98.77 33	90.99 112	97.38 91	96.08 223	82.38 285	89.29 208	97.87 53	83.77 124	99.69 33	81.37 274	96.69 120	98.89 78

pmmvs4		90.93 205	89.85 214	94.17 170	93.34 277	90.79 121	94.60 256	96.02 224	84.62 265	87.45 239	95.15 189	81.88 178	97.45 260	87.70 177	87.87 233	94.27 274

v18		88.71 248	87.52 247	92.27 245	94.16 240	88.11 203	96.82 141	95.96 225	87.03 228	80.76 292	89.81 293	83.15 132	96.22 288	84.69 229	75.31 310	92.49 296

v17		88.67 250	87.47 250	92.26 247	94.13 243	88.09 205	96.81 142	95.95 226	87.02 229	80.72 293	89.75 295	83.11 135	96.20 289	84.61 232	75.15 312	92.49 296

v16		88.69 249	87.50 248	92.26 247	94.19 237	88.11 203	96.81 142	95.95 226	87.01 230	80.71 294	89.80 294	83.08 138	96.20 289	84.61 232	75.34 309	92.48 298

ITE_SJBPF				92.43 244	95.34 185	85.37 254		95.92 228	91.47 109	87.75 234	96.39 132	71.00 284	97.96 219	82.36 262	89.86 217	93.97 277

V14		88.52 253	87.30 253	92.17 252	94.12 245	87.99 208	96.72 153	95.91 229	86.98 232	80.50 298	89.63 296	83.03 143	96.12 293	84.23 238	74.60 315	92.40 303

v15		88.53 252	87.31 252	92.20 250	94.09 249	88.05 206	96.72 153	95.90 230	87.01 230	80.53 297	89.60 299	83.02 144	96.13 291	84.29 237	74.64 313	92.41 302

v13		88.45 258	87.22 258	92.16 254	94.08 251	87.95 212	96.71 155	95.90 230	86.86 239	80.27 304	89.55 301	82.92 151	96.12 293	84.02 242	74.63 314	92.40 303

v12		88.46 257	87.23 257	92.17 252	94.10 248	87.99 208	96.71 155	95.90 230	86.91 235	80.34 302	89.58 300	82.92 151	96.11 295	84.09 240	74.50 318	92.42 301

V9		88.49 256	87.26 254	92.18 251	94.12 245	87.97 211	96.73 150	95.90 230	86.95 234	80.40 300	89.61 297	82.98 147	96.13 291	84.14 239	74.55 316	92.44 300

USDC		88.94 243	87.83 245	92.27 245	94.66 221	84.96 258	93.86 273	95.90 230	87.34 222	83.40 278	95.56 171	67.43 300	98.19 176	82.64 260	89.67 218	93.66 280

COLMAP_ROB	87.81 15	90.40 221	89.28 228	93.79 190	97.95 86	87.13 230	96.92 132	95.89 235	82.83 282	86.88 254	97.18 93	73.77 272	99.29 92	78.44 289	93.62 166	94.95 241
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 101	93.08 105	96.02 96	97.88 91	89.96 140	97.72 58	95.85 236	92.43 83	95.86 60	98.44 14	68.42 296	99.39 86	96.31 19	94.85 145	98.71 88

v11		88.41 259	87.19 261	92.08 257	94.08 251	87.77 217	96.75 148	95.85 236	86.74 240	80.50 298	89.50 302	82.49 163	96.08 296	83.55 248	75.20 311	92.38 305

VDDNet		93.05 125	92.07 133	96.02 96	96.84 124	90.39 130	98.08 33	95.85 236	86.22 246	95.79 64	98.46 12	67.59 299	99.19 97	94.92 57	94.85 145	98.47 105

Vis-MVSNet (Re-imp)		94.15 88	93.88 82	94.95 144	97.61 102	87.92 213	98.10 31	95.80 239	92.22 86	93.02 114	97.45 86	84.53 119	97.91 228	88.24 166	97.97 86	99.02 62

tpm cat1		88.36 260	87.21 259	91.81 264	95.13 201	80.55 293	92.58 295	95.70 240	74.97 318	87.45 239	91.96 281	78.01 244	98.17 178	80.39 279	88.74 226	96.72 169

BH-w/o		92.14 161	91.75 143	93.31 220	96.99 121	85.73 248	95.67 227	95.69 241	88.73 187	89.26 210	94.82 200	82.97 148	98.07 191	85.26 223	96.32 127	96.13 183

CR-MVSNet		90.82 208	89.77 217	93.95 182	94.45 229	87.19 228	90.23 313	95.68 242	86.89 237	92.40 124	92.36 276	80.91 193	97.05 275	81.09 276	93.95 162	97.60 144

Patchmtry		88.64 251	87.25 255	92.78 236	94.09 249	86.64 238	89.82 316	95.68 242	80.81 299	87.63 238	92.36 276	80.91 193	97.03 277	78.86 287	85.12 255	94.67 261

BH-RMVSNet		92.72 138	91.97 138	94.97 142	97.16 113	87.99 208	96.15 204	95.60 244	90.62 134	91.87 137	97.15 96	78.41 233	98.57 151	83.16 252	97.60 95	98.36 114

PVSNet_0	82.17 19	85.46 282	83.64 283	90.92 279	95.27 190	79.49 302	90.55 311	95.60 244	83.76 275	83.00 279	89.95 290	71.09 283	97.97 215	82.75 258	60.79 329	95.31 222

Patchmatch-test1		91.54 182	90.85 178	93.59 206	95.59 175	84.95 259	94.72 255	95.58 246	90.82 125	92.25 130	93.58 251	75.80 255	97.41 264	83.35 249	95.98 130	98.40 110

AllTest		90.23 225	88.98 232	93.98 178	97.94 87	86.64 238	96.51 175	95.54 247	85.38 253	85.49 263	96.77 106	70.28 288	99.15 102	80.02 280	92.87 171	96.15 181

TestCases				93.98 178	97.94 87	86.64 238		95.54 247	85.38 253	85.49 263	96.77 106	70.28 288	99.15 102	80.02 280	92.87 171	96.15 181

tpmvs		89.83 235	89.15 231	91.89 261	94.92 211	80.30 296	93.11 288	95.46 249	86.28 244	88.08 229	92.65 267	80.44 202	98.52 155	81.47 271	89.92 216	96.84 166

PatchFormer-LS_test		91.68 174	91.18 169	93.19 226	95.24 194	83.63 273	95.53 235	95.44 250	89.82 151	91.37 144	92.58 270	80.85 197	98.52 155	89.65 140	90.16 213	97.42 150

pmmvs5		89.86 234	88.87 234	92.82 232	92.86 290	86.23 244	96.26 197	95.39 251	84.24 268	87.12 247	94.51 211	74.27 267	97.36 268	87.61 184	87.57 235	94.86 248

PatchmatchNet		91.91 165	91.35 159	93.59 206	95.38 183	84.11 267	93.15 287	95.39 251	89.54 154	92.10 133	93.68 247	82.82 155	98.13 180	84.81 227	95.32 140	98.52 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 186	91.32 161	91.79 265	95.15 199	79.20 305	93.42 281	95.37 253	88.55 191	93.49 101	93.67 248	82.49 163	98.27 171	90.41 130	89.34 220	97.90 128

Anonymous20231206		87.09 270	86.14 268	89.93 293	91.22 304	80.35 294	96.11 206	95.35 254	83.57 277	84.16 272	93.02 263	73.54 274	95.61 303	72.16 307	86.14 244	93.84 279

MIMVSNet1		84.93 284	83.05 284	90.56 286	89.56 312	84.84 261	95.40 240	95.35 254	83.91 271	80.38 301	92.21 280	57.23 319	93.34 317	70.69 313	82.75 288	93.50 281

TDRefinement		86.53 273	84.76 278	91.85 262	82.23 328	84.25 264	96.38 186	95.35 254	84.97 261	84.09 274	94.94 193	65.76 307	98.34 168	84.60 234	74.52 317	92.97 287

TR-MVS		91.48 184	90.59 189	94.16 171	96.40 146	87.33 222	95.67 227	95.34 257	87.68 215	91.46 142	95.52 174	76.77 250	98.35 166	82.85 256	93.61 167	96.79 167

EPNet_dtu		91.71 168	91.28 163	92.99 230	93.76 265	83.71 270	96.69 160	95.28 258	93.15 62	87.02 251	95.95 147	83.37 129	97.38 267	79.46 284	96.84 113	97.88 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 269	85.79 270	91.78 266	94.80 217	87.28 223	95.49 237	95.28 258	84.09 270	83.85 277	91.82 282	62.95 311	94.17 313	78.48 288	85.34 252	93.91 278

MDTV_nov1_ep13			90.76 182		95.22 195	80.33 295	93.03 290	95.28 258	88.14 205	92.84 121	93.83 243	81.34 184	98.08 187	82.86 255	94.34 153

LF4IMVS		87.94 263	87.25 255	89.98 292	92.38 298	80.05 300	94.38 261	95.25 261	87.59 217	84.34 269	94.74 204	64.31 309	97.66 248	84.83 226	87.45 236	92.23 307

TransMVSNet (Re)		88.94 243	87.56 246	93.08 228	94.35 232	88.45 185	97.73 56	95.23 262	87.47 218	84.26 271	95.29 184	79.86 211	97.33 269	79.44 285	74.44 319	93.45 283

test20.03		86.14 277	85.40 273	88.35 295	90.12 307	80.06 299	95.90 218	95.20 263	88.59 188	81.29 288	93.62 250	71.43 281	92.65 319	71.26 311	81.17 294	92.34 306

new-patchmatchnet		83.18 288	81.87 289	87.11 301	86.88 320	75.99 312	93.70 275	95.18 264	85.02 260	77.30 312	88.40 309	65.99 305	93.88 315	74.19 303	70.18 323	91.47 315

MDA-MVSNet_test_wron		85.87 279	84.23 281	90.80 283	92.38 298	82.57 277	93.17 285	95.15 265	82.15 286	67.65 322	92.33 279	78.20 235	95.51 306	77.33 292	79.74 297	94.31 273

YYNet1		85.87 279	84.23 281	90.78 284	92.38 298	82.46 279	93.17 285	95.14 266	82.12 287	67.69 321	92.36 276	78.16 238	95.50 307	77.31 293	79.73 298	94.39 269

Baseline_NR-MVSNet		91.20 196	90.62 187	92.95 231	93.83 263	88.03 207	97.01 122	95.12 267	88.42 194	89.70 193	95.13 191	83.47 127	97.44 261	89.66 139	83.24 283	93.37 285

thres200		92.23 157	91.39 158	94.75 153	97.61 102	89.03 174	96.60 170	95.09 268	92.08 96	93.28 105	94.00 238	78.39 234	99.04 119	81.26 275	94.18 154	96.19 178

tpmp4_e23		89.58 237	88.59 237	92.54 242	95.16 198	81.53 285	94.11 269	95.09 268	81.66 290	88.60 219	93.44 258	75.11 260	98.33 169	82.45 261	91.72 189	97.75 135

ADS-MVSNet		89.89 232	88.68 236	93.53 210	95.86 166	84.89 260	90.93 308	95.07 270	83.23 280	91.28 152	91.81 283	79.01 226	97.85 231	79.52 282	91.39 196	97.84 131

pmmvs-eth3d		86.22 276	84.45 279	91.53 271	88.34 315	87.25 225	94.47 260	95.01 271	83.47 278	79.51 308	89.61 297	69.75 291	95.71 302	83.13 253	76.73 305	91.64 311

MDA-MVSNet-bldmvs		85.00 283	82.95 285	91.17 276	93.13 288	83.33 274	94.56 258	95.00 272	84.57 266	65.13 326	92.65 267	70.45 287	95.85 299	73.57 304	77.49 302	94.33 271

RPMNet		88.52 253	86.72 265	93.95 182	94.45 229	87.19 228	90.23 313	94.99 273	77.87 312	92.40 124	87.55 317	80.17 208	97.05 275	68.84 314	93.95 162	97.60 144

ambc				86.56 304	83.60 325	70.00 323	85.69 326	94.97 274		80.60 296	88.45 308	37.42 333	96.84 282	82.69 259	75.44 308	92.86 288

testgi		87.97 262	87.21 259	90.24 290	92.86 290	80.76 289	96.67 162	94.97 274	91.74 103	85.52 262	95.83 153	62.66 312	94.47 312	76.25 296	88.36 230	95.48 207

dp		88.90 245	88.26 243	90.81 281	94.58 226	76.62 310	92.85 292	94.93 276	85.12 258	90.07 179	93.07 262	75.81 254	98.12 182	80.53 278	87.42 238	97.71 137

test_0402		86.46 274	84.79 277	91.45 272	95.02 206	85.55 251	96.29 195	94.89 277	80.90 296	82.21 280	93.97 239	68.21 297	97.29 271	62.98 320	88.68 228	91.51 313

tfpn200view9		92.38 149	91.52 155	94.95 144	97.85 92	89.29 167	97.41 85	94.88 278	92.19 88	93.27 106	94.46 215	78.17 236	99.08 116	81.40 272	94.08 155	96.48 174

CVMVSNet		91.23 195	91.75 143	89.67 294	95.77 171	74.69 313	96.44 176	94.88 278	85.81 250	92.18 131	97.64 73	79.07 221	95.58 305	88.06 169	95.86 134	98.74 84

thres400		92.42 147	91.52 155	95.12 137	97.85 92	89.29 167	97.41 85	94.88 278	92.19 88	93.27 106	94.46 215	78.17 236	99.08 116	81.40 272	94.08 155	96.98 155

EPNet		95.20 66	94.56 71	97.14 53	92.80 292	92.68 63	97.85 47	94.87 281	96.64 1	92.46 123	97.80 61	86.23 97	99.65 39	93.72 78	98.62 72	99.10 59
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SixPastTwentyTwo		89.15 242	88.54 239	90.98 277	93.49 273	80.28 297	96.70 158	94.70 282	90.78 126	84.15 273	95.57 170	71.78 279	97.71 244	84.63 231	85.07 259	94.94 243

thres600view7		92.49 146	91.60 152	95.18 129	97.91 89	89.47 155	97.65 64	94.66 283	92.18 90	93.33 104	94.91 195	78.06 243	99.10 111	81.61 265	94.06 157	96.98 155

PatchT		88.87 246	87.42 251	93.22 224	94.08 251	85.10 256	89.51 317	94.64 284	81.92 288	92.36 127	88.15 312	80.05 209	97.01 279	72.43 306	93.65 165	97.54 147

view600		92.55 140	91.68 146	95.18 129	97.98 81	89.44 159	98.00 36	94.57 285	92.09 91	93.17 109	95.52 174	78.14 239	99.11 106	81.61 265	94.04 158	96.98 155

view800		92.55 140	91.68 146	95.18 129	97.98 81	89.44 159	98.00 36	94.57 285	92.09 91	93.17 109	95.52 174	78.14 239	99.11 106	81.61 265	94.04 158	96.98 155

conf0.05thres1000		92.55 140	91.68 146	95.18 129	97.98 81	89.44 159	98.00 36	94.57 285	92.09 91	93.17 109	95.52 174	78.14 239	99.11 106	81.61 265	94.04 158	96.98 155

tfpn		92.55 140	91.68 146	95.18 129	97.98 81	89.44 159	98.00 36	94.57 285	92.09 91	93.17 109	95.52 174	78.14 239	99.11 106	81.61 265	94.04 158	96.98 155

Gipuma		67.86 306	65.41 307	75.18 319	92.66 295	73.45 316	66.50 336	94.52 289	53.33 331	57.80 330	66.07 333	30.81 335	89.20 329	48.15 334	78.88 300	62.90 333
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CostFormer		91.18 199	90.70 185	92.62 241	94.84 215	81.76 284	94.09 270	94.43 290	84.15 269	92.72 122	93.77 245	79.43 217	98.20 174	90.70 129	92.18 182	97.90 128

tpm2		89.96 230	89.21 229	92.23 249	94.91 213	81.25 287	93.78 274	94.42 291	80.62 300	91.56 140	93.44 258	76.44 252	97.94 221	85.60 218	92.08 186	97.49 148

JIA-IIPM		88.26 261	87.04 262	91.91 260	93.52 271	81.42 286	89.38 318	94.38 292	80.84 298	90.93 157	80.74 324	79.22 220	97.92 225	82.76 257	91.62 191	96.38 175

Patchmatch-test		89.42 240	87.99 244	93.70 200	95.27 190	85.11 255	88.98 319	94.37 293	81.11 295	87.10 249	93.69 246	82.28 168	97.50 257	74.37 301	94.76 148	98.48 104

LCM-MVSNet		72.55 301	69.39 304	82.03 309	70.81 338	65.42 329	90.12 315	94.36 294	55.02 330	65.88 325	81.72 323	24.16 342	89.96 327	74.32 302	68.10 326	90.71 317

ADS-MVSNet2		89.45 239	88.59 237	92.03 258	95.86 166	82.26 281	90.93 308	94.32 295	83.23 280	91.28 152	91.81 283	79.01 226	95.99 297	79.52 282	91.39 196	97.84 131

DWT-MVSNet_test		90.76 209	89.89 212	93.38 217	95.04 205	83.70 271	95.85 220	94.30 296	88.19 202	90.46 162	92.80 265	73.61 273	98.50 157	88.16 167	90.58 207	97.95 126

testus		82.63 291	82.15 287	84.07 307	87.31 319	67.67 325	93.18 283	94.29 297	82.47 284	82.14 282	90.69 288	53.01 326	91.94 322	66.30 317	89.96 215	92.62 293

LP		84.13 286	81.85 291	90.97 278	93.20 285	82.12 282	87.68 323	94.27 298	76.80 313	81.93 283	88.52 307	72.97 276	95.95 298	59.53 325	81.73 290	94.84 249

EU-MVSNet		88.72 247	88.90 233	88.20 297	93.15 287	74.21 314	96.63 167	94.22 299	85.18 256	87.32 244	95.97 145	76.16 253	94.98 310	85.27 222	86.17 243	95.41 212

test1235678		79.82 296	78.53 297	83.69 308	82.55 327	67.55 326	92.50 297	94.13 300	79.28 304	72.10 319	86.45 320	57.27 318	90.68 326	61.60 323	80.90 295	92.82 289

MIMVSNet		88.50 255	86.76 263	93.72 199	94.84 215	87.77 217	91.39 303	94.05 301	86.41 243	87.99 231	92.59 269	63.27 310	95.82 301	77.44 291	92.84 173	97.57 146

OpenMVS_ROB	81.14 20	84.42 285	82.28 286	90.83 280	90.06 308	84.05 268	95.73 226	94.04 302	73.89 321	80.17 306	91.53 287	59.15 317	97.64 249	66.92 316	89.05 222	90.80 316

TinyColmap		86.82 272	85.35 274	91.21 275	94.91 213	82.99 276	93.94 272	94.02 303	83.58 276	81.56 287	94.68 205	62.34 313	98.13 180	75.78 297	87.35 240	92.52 295

IB-MVS	87.33 17	89.91 231	88.28 242	94.79 151	95.26 193	87.70 219	95.12 251	93.95 304	89.35 159	87.03 250	92.49 271	70.74 286	99.19 97	89.18 150	81.37 293	97.49 148
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
Anonymous20231211		78.22 299	75.30 300	86.99 303	86.14 321	74.16 315	95.62 231	93.88 305	66.43 325	74.44 315	87.86 314	41.39 332	95.11 309	62.49 321	69.46 325	91.71 310

1111		78.29 298	77.55 298	80.50 311	83.89 323	59.98 333	91.89 300	93.71 306	75.06 316	73.60 317	87.67 315	55.66 322	92.60 320	58.54 327	77.92 301	88.93 320

.test1245		65.38 307	69.22 305	53.86 327	83.89 323	59.98 333	91.89 300	93.71 306	75.06 316	73.60 317	87.67 315	55.66 322	92.60 320	58.54 327	2.96 340	9.00 338

LCM-MVSNet-Re		92.50 144	92.52 126	92.44 243	96.82 127	81.89 283	96.92 132	93.71 306	92.41 84	84.30 270	94.60 209	85.08 111	97.03 277	91.51 118	97.36 103	98.40 110

test2356		82.77 290	82.14 288	84.65 306	85.77 322	70.36 320	91.22 306	93.69 309	81.58 292	81.82 284	89.00 305	60.63 316	90.77 325	64.74 318	90.80 205	92.82 289

tpm		90.25 224	89.74 220	91.76 268	93.92 259	79.73 301	93.98 271	93.54 310	88.28 198	91.99 135	93.25 261	77.51 248	97.44 261	87.30 191	87.94 232	98.12 120

LFMVS		93.60 108	92.63 119	96.52 69	98.13 77	91.27 102	97.94 41	93.39 311	90.57 139	96.29 44	98.31 31	69.00 292	99.16 101	94.18 67	95.87 133	99.12 57

Patchmatch-RL test		87.38 267	86.24 266	90.81 281	88.74 314	78.40 308	88.12 322	93.17 312	87.11 227	82.17 281	89.29 303	81.95 176	95.60 304	88.64 164	77.02 303	98.41 109

test-LLR		91.42 187	91.19 168	92.12 255	94.59 224	80.66 290	94.29 264	92.98 313	91.11 121	90.76 158	92.37 273	79.02 224	98.07 191	88.81 161	96.74 117	97.63 139

test-mter		90.19 227	89.54 224	92.12 255	94.59 224	80.66 290	94.29 264	92.98 313	87.68 215	90.76 158	92.37 273	67.67 298	98.07 191	88.81 161	96.74 117	97.63 139

test12356		74.97 300	74.13 301	77.49 316	78.81 329	56.23 337	88.53 321	92.75 315	75.14 315	67.50 323	85.07 321	44.88 330	89.96 327	58.71 326	75.75 307	86.26 321

test0.0.03 1		89.37 241	88.70 235	91.41 274	92.47 297	85.63 250	95.22 249	92.70 316	91.11 121	86.91 253	93.65 249	79.02 224	93.19 318	78.00 290	89.18 221	95.41 212

new_pmnet		82.89 289	81.12 294	88.18 298	89.63 311	80.18 298	91.77 302	92.57 317	76.79 314	75.56 314	88.23 311	61.22 315	94.48 311	71.43 309	82.92 286	89.87 318

testmv		72.22 302	70.02 302	78.82 314	73.06 336	61.75 331	91.24 305	92.31 318	74.45 319	61.06 328	80.51 325	34.21 334	88.63 330	55.31 330	68.07 327	86.06 322

K. test v3		87.64 266	86.75 264	90.32 289	93.02 289	79.48 303	96.61 168	92.08 319	90.66 132	80.25 305	94.09 236	67.21 302	96.65 283	85.96 213	80.83 296	94.83 251

TESTMET0.1,1		90.06 229	89.42 226	91.97 259	94.41 231	80.62 292	94.29 264	91.97 320	87.28 224	90.44 163	92.47 272	68.79 293	97.67 246	88.50 165	96.60 122	97.61 143

PM-MVS		83.48 287	81.86 290	88.31 296	87.83 317	77.59 309	93.43 280	91.75 321	86.91 235	80.63 295	89.91 291	44.42 331	95.84 300	85.17 225	76.73 305	91.50 314

FPMVS		71.27 303	69.85 303	75.50 318	74.64 331	59.03 335	91.30 304	91.50 322	58.80 329	57.92 329	88.28 310	29.98 338	85.53 333	53.43 331	82.84 287	81.95 325

door								91.13 323

door-mid								91.06 324

pmmvs3		79.97 295	77.50 299	87.39 300	82.80 326	79.38 304	92.70 294	90.75 325	70.69 324	78.66 309	87.47 318	51.34 328	93.40 316	73.39 305	69.65 324	89.38 319

no-one		68.12 305	63.78 308	81.13 310	74.01 333	70.22 322	87.61 324	90.71 326	72.63 323	53.13 331	71.89 330	30.29 336	91.45 323	61.53 324	32.21 334	81.72 326

DSMNet-mixed		86.34 275	86.12 269	87.00 302	89.88 310	70.43 319	94.93 253	90.08 327	77.97 311	85.42 265	92.78 266	74.44 266	93.96 314	74.43 300	95.14 142	96.62 170

testpf		80.97 294	81.40 292	79.65 313	91.53 302	72.43 318	73.47 334	89.55 328	78.63 307	80.81 290	89.06 304	61.36 314	91.36 324	83.34 250	84.89 266	75.15 329

MVS-HIRNet		82.47 292	81.21 293	86.26 305	95.38 183	69.21 324	88.96 320	89.49 329	66.28 326	80.79 291	74.08 329	68.48 295	97.39 266	71.93 308	95.47 138	92.18 308

EPMVS		90.70 215	89.81 216	93.37 218	94.73 220	84.21 265	93.67 277	88.02 330	89.50 156	92.38 126	93.49 255	77.82 246	97.78 238	86.03 211	92.68 174	98.11 123

ANet_high		63.94 308	59.58 309	77.02 317	61.24 341	66.06 327	85.66 327	87.93 331	78.53 309	42.94 333	71.04 331	25.42 341	80.71 335	52.60 332	30.83 336	84.28 324

PMMVS2		70.19 304	66.92 306	80.01 312	76.35 330	65.67 328	86.22 325	87.58 332	64.83 328	62.38 327	80.29 326	26.78 340	88.49 331	63.79 319	54.07 330	85.88 323

lessismore_v0				90.45 287	91.96 301	79.09 306		87.19 333		80.32 303	94.39 220	66.31 304	97.55 254	84.00 244	76.84 304	94.70 260

PMVS	53.92 22	58.58 310	55.40 311	68.12 323	51.00 342	48.64 339	78.86 332	87.10 334	46.77 334	35.84 338	74.28 328	8.76 344	86.34 332	42.07 335	73.91 320	69.38 331
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuykxyi23d		56.92 311	51.11 315	74.38 321	62.30 340	61.47 332	80.09 331	84.87 335	49.62 333	30.80 339	57.20 337	7.03 345	82.94 334	55.69 329	32.36 333	78.72 328

gg-mvs-nofinetune		87.82 264	85.61 271	94.44 161	94.46 228	89.27 170	91.21 307	84.61 336	80.88 297	89.89 183	74.98 327	71.50 280	97.53 255	85.75 216	97.21 107	96.51 172

GG-mvs-BLEND				93.62 204	93.69 267	89.20 171	92.39 299	83.33 337		87.98 232	89.84 292	71.00 284	96.87 281	82.08 264	95.40 139	94.80 255

PNet_i23d		59.01 309	55.87 310	68.44 322	73.98 334	51.37 338	81.36 330	82.41 338	52.37 332	42.49 335	70.39 332	11.39 343	79.99 337	49.77 333	38.71 332	73.97 330

MTMP								82.03 339

DeepMVS_CX				74.68 320	90.84 305	64.34 330		81.61 340	65.34 327	67.47 324	88.01 313	48.60 329	80.13 336	62.33 322	73.68 321	79.58 327

E-PMN		53.28 312	52.56 313	55.43 325	74.43 332	47.13 340	83.63 329	76.30 341	42.23 335	42.59 334	62.22 335	28.57 339	74.40 338	31.53 337	31.51 335	44.78 334

EMVS		52.08 314	51.31 314	54.39 326	72.62 337	45.39 342	83.84 328	75.51 342	41.13 336	40.77 336	59.65 336	30.08 337	73.60 339	28.31 338	29.90 337	44.18 335

MVE	50.73 23	53.25 313	48.81 316	66.58 324	65.34 339	57.50 336	72.49 335	70.94 343	40.15 337	39.28 337	63.51 334	6.89 347	73.48 340	38.29 336	42.38 331	68.76 332
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 315	53.82 312	46.29 328	33.73 343	45.30 343	78.32 333	67.24 344	18.02 338	50.93 332	87.05 319	52.99 327	53.11 341	70.76 312	25.29 338	40.46 336

N_pmnet		78.73 297	78.71 296	78.79 315	92.80 292	46.50 341	94.14 268	43.71 345	78.61 308	80.83 289	91.66 286	74.94 264	96.36 285	67.24 315	84.45 270	93.50 281

wuyk23d		25.11 317	24.57 319	26.74 330	73.98 334	39.89 344	57.88 337	9.80 346	12.27 339	10.39 340	6.97 343	7.03 345	36.44 342	25.43 339	17.39 339	3.89 340

testmvs		13.36 319	16.33 320	4.48 332	5.04 344	2.26 346	93.18 283	3.28 347	2.70 340	8.24 341	21.66 339	2.29 349	2.19 343	7.58 340	2.96 340	9.00 338

test123		13.04 320	15.66 321	5.18 331	4.51 345	3.45 345	92.50 297	1.81 348	2.50 341	7.58 342	20.15 340	3.67 348	2.18 344	7.13 341	1.07 342	9.90 337

pcd_1.5k_mvsjas		7.39 322	9.85 323	0.00 333	0.00 346	0.00 347	0.00 338	0.00 349	0.00 342	0.00 343	0.00 344	88.65 68	0.00 345	0.00 342	0.00 343	0.00 341

sosnet-low-res		0.00 323	0.00 324	0.00 333	0.00 346	0.00 347	0.00 338	0.00 349	0.00 342	0.00 343	0.00 344	0.00 350	0.00 345	0.00 342	0.00 343	0.00 341

sosnet		0.00 323	0.00 324	0.00 333	0.00 346	0.00 347	0.00 338	0.00 349	0.00 342	0.00 343	0.00 344	0.00 350	0.00 345	0.00 342	0.00 343	0.00 341

uncertanet		0.00 323	0.00 324	0.00 333	0.00 346	0.00 347	0.00 338	0.00 349	0.00 342	0.00 343	0.00 344	0.00 350	0.00 345	0.00 342	0.00 343	0.00 341

Regformer		0.00 323	0.00 324	0.00 333	0.00 346	0.00 347	0.00 338	0.00 349	0.00 342	0.00 343	0.00 344	0.00 350	0.00 345	0.00 342	0.00 343	0.00 341

n2								0.00 349

nn								0.00 349

ab-mvs-re		8.06 321	10.74 322	0.00 333	0.00 346	0.00 347	0.00 338	0.00 349	0.00 342	0.00 343	96.69 112	0.00 350	0.00 345	0.00 342	0.00 343	0.00 341

uanet		0.00 323	0.00 324	0.00 333	0.00 346	0.00 347	0.00 338	0.00 349	0.00 342	0.00 343	0.00 344	0.00 350	0.00 345	0.00 342	0.00 343	0.00 341

sam_mvs1												82.76 156

sam_mvs												81.94 177

test_post1							92.81 293				16.58 342	80.53 200	97.68 245	86.20 206

test_post											17.58 341	81.76 179	98.08 187

patchmatchnet-post											90.45 289	82.65 160	98.10 184

gm-plane-assit					93.22 283	78.89 307			84.82 263		93.52 253		98.64 144	87.72 176

test9_res														94.81 60	99.38 33	99.45 28

agg_prior2														93.94 72	99.38 33	99.50 22

test_prior4						93.66 39	96.42 179

test_prior2							96.35 188		92.80 77	96.03 52	97.59 77	92.01 28		95.01 53	99.38 33

旧先验2							95.94 216		81.66 290	97.34 15			98.82 132	92.26 95

新几何2							95.79 223

原ACMM2							95.67 227

testdata2													99.67 37	85.96 213

segment_acmp												92.89 10

testdata1							95.26 248		93.10 65

plane_prior7					96.21 152	89.98 137

plane_prior6					96.10 162	90.00 133						81.32 185

plane_prior4											96.64 115

plane_prior3						90.00 133			94.46 30	91.34 146

plane_prior2							97.74 54		94.85 17

plane_prior1					96.14 160

plane_prior						89.99 135	97.24 101		94.06 38						92.16 183

HQP5-MVS						89.33 164

HQP-NCC					95.86 166		96.65 163		93.55 48	90.14 168

ACMP_Plane					95.86 166		96.65 163		93.55 48	90.14 168

BP-MVS														92.13 101

HQP4-MVS										90.14 168			98.50 157			95.78 197

HQP2-MVS												80.95 190

NP-MVS					95.99 165	89.81 143					95.87 150

MDTV_nov1_ep13_2view						70.35 321	93.10 289		83.88 273	93.55 99		82.47 165		86.25 205		98.38 113

ACMMP++_ref															90.30 212

ACMMP++															91.02 202

Test By Simon												88.73 67

High-resolution multi-view benchmark