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 28	96.53 31	97.65 30	99.35 13	93.53 45	97.65 69	98.98 1	92.22 88	97.14 23	98.44 16	91.17 43	99.85 11	94.35 68	99.46 25	99.57 13

MVS_111021_HR		96.68 35	96.58 30	96.99 58	98.46 53	92.31 73	96.20 216	98.90 2	94.30 35	95.86 62	97.74 66	92.33 23	99.38 90	96.04 30	99.42 30	99.28 48

ACMMP		96.27 45	95.93 45	97.28 46	99.24 21	92.62 67	98.25 25	98.81 3	92.99 69	94.56 86	98.39 22	88.96 65	99.85 11	94.57 67	97.63 96	99.36 41
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 46	96.19 43	96.39 80	98.23 74	91.35 102	96.24 214	98.79 4	93.99 39	95.80 65	97.65 72	89.92 60	99.24 97	95.87 33	99.20 51	98.58 94

FC-MVSNet-test		93.94 99	93.57 91	95.04 141	95.48 192	91.45 100	98.12 30	98.71 5	93.37 55	90.23 180	96.70 112	87.66 82	97.85 244	91.49 121	90.39 224	95.83 208

UniMVSNet (Re)		93.31 118	92.55 124	95.61 113	95.39 195	93.34 52	97.39 102	98.71 5	93.14 65	90.10 189	94.83 205	87.71 81	98.03 217	91.67 119	83.99 286	95.46 224

FIs		94.09 93	93.70 87	95.27 128	95.70 186	92.03 83	98.10 31	98.68 7	93.36 57	90.39 177	96.70 112	87.63 84	97.94 234	92.25 99	90.50 223	95.84 207

WR-MVS_H		92.00 168	91.35 163	93.95 194	95.09 216	89.47 165	98.04 35	98.68 7	91.46 115	88.34 236	94.68 211	85.86 105	97.56 266	85.77 217	84.24 284	94.82 268

VPA-MVSNet		93.24 120	92.48 129	95.51 118	95.70 186	92.39 72	97.86 46	98.66 9	92.30 87	92.09 139	95.37 183	80.49 203	98.40 174	93.95 73	85.86 259	95.75 215

UniMVSNet_NR-MVSNet		93.37 116	92.67 119	95.47 123	95.34 198	92.83 61	97.17 124	98.58 10	92.98 74	90.13 185	95.80 157	88.37 75	97.85 244	91.71 115	83.93 287	95.73 217

CSCG		96.05 50	95.91 46	96.46 78	99.24 21	90.47 130	98.30 21	98.57 11	89.01 178	93.97 97	97.57 81	92.62 18	99.76 23	94.66 66	99.27 45	99.15 55

MSLP-MVS++		96.94 24	97.06 9	96.59 68	98.72 37	91.86 88	97.67 66	98.49 12	94.66 27	97.24 18	98.41 21	92.31 26	98.94 127	96.61 14	99.46 25	98.96 71

HyFIR lowres test		93.66 107	92.92 110	95.87 102	98.24 71	89.88 144	94.58 270	98.49 12	85.06 272	93.78 98	95.78 161	82.86 155	98.67 148	91.77 113	95.71 139	99.07 63

CHOSEN 1792x2688		94.15 89	93.51 95	96.06 95	98.27 68	89.38 173	95.18 263	98.48 14	85.60 265	93.76 99	97.11 99	83.15 134	99.61 47	91.33 124	98.72 72	99.19 51

PHI-MVS		96.77 30	96.46 34	97.71 27	98.40 57	94.07 29	98.21 28	98.45 15	89.86 153	97.11 26	98.01 48	92.52 21	99.69 35	96.03 31	99.53 16	99.36 41

PVSNet_BlendedMVS		94.06 94	93.92 82	94.47 172	98.27 68	89.46 167	96.73 163	98.36 16	90.17 148	94.36 89	95.24 189	88.02 76	99.58 55	93.44 86	90.72 219	94.36 285

PVSNet_Blended		94.87 78	94.56 72	95.81 104	98.27 68	89.46 167	95.47 251	98.36 16	88.84 187	94.36 89	96.09 146	88.02 76	99.58 55	93.44 86	98.18 83	98.40 114

3Dnovator	91.36 5	95.19 68	94.44 79	97.44 39	96.56 149	93.36 51	98.65 6	98.36 16	94.12 37	89.25 224	98.06 45	82.20 173	99.77 22	93.41 88	99.32 41	99.18 52

HFP-MVS		97.14 14	96.92 15	97.83 15	99.42 3	94.12 27	98.52 10	98.32 19	93.21 60	97.18 20	98.29 36	92.08 28	99.83 15	95.63 39	99.59 9	99.54 19

#test#		97.02 20	96.75 25	97.83 15	99.42 3	94.12 27	98.15 29	98.32 19	92.57 83	97.18 20	98.29 36	92.08 28	99.83 15	95.12 51	99.59 9	99.54 19

ACMMPR		97.07 17	96.84 18	97.79 19	99.44 2	93.88 33	98.52 10	98.31 21	93.21 60	97.15 22	98.33 30	91.35 41	99.86 8	95.63 39	99.59 9	99.62 7

APDe-MVS		97.82 1	97.73 1	98.08 8	99.15 25	94.82 12	98.81 2	98.30 22	94.76 24	98.30 4	98.90 1	93.77 8	99.68 37	97.93 1	99.69 1	99.75 1

CP-MVS		97.02 20	96.81 21	97.64 32	99.33 14	93.54 44	98.80 3	98.28 23	92.99 69	96.45 44	98.30 35	91.90 33	99.85 11	95.61 41	99.68 2	99.54 19

SteuartSystems-ACMMP		97.62 3	97.53 2	97.87 13	98.39 59	94.25 22	98.43 16	98.27 24	95.34 9	98.11 5	98.56 7	94.53 3	99.71 29	96.57 16	99.62 7	99.65 3
Skip Steuart: Steuart Systems R&D Blog.
test_part1								98.26 25				95.31 1			99.63 4	99.63 5

ESAPD		97.57 4	97.29 7	98.41 2	99.28 17	95.74 3	97.50 90	98.26 25	93.81 45	98.10 6	98.53 11	95.31 1	99.87 5	95.19 47	99.63 4	99.63 5

PVSNet_Blended_VisFu		95.27 64	94.91 64	96.38 81	98.20 75	90.86 120	97.27 112	98.25 27	90.21 147	94.18 93	97.27 91	87.48 87	99.73 25	93.53 82	97.77 94	98.55 95

region2R		97.07 17	96.84 18	97.77 22	99.46 1	93.79 37	98.52 10	98.24 28	93.19 63	97.14 23	98.34 27	91.59 39	99.87 5	95.46 44	99.59 9	99.64 4

PS-CasMVS		91.55 193	90.84 186	93.69 213	94.96 221	88.28 200	97.84 49	98.24 28	91.46 115	88.04 243	95.80 157	79.67 216	97.48 271	87.02 198	84.54 282	95.31 237

DU-MVS		92.90 132	92.04 135	95.49 120	94.95 222	92.83 61	97.16 125	98.24 28	93.02 68	90.13 185	95.71 165	83.47 129	97.85 244	91.71 115	83.93 287	95.78 211

XVS		97.18 11	96.96 13	97.81 17	99.38 8	94.03 31	98.59 7	98.20 31	94.85 17	96.59 37	98.29 36	91.70 36	99.80 20	95.66 37	99.40 32	99.62 7

X-MVStestdata		91.71 176	89.67 233	97.81 17	99.38 8	94.03 31	98.59 7	98.20 31	94.85 17	96.59 37	32.69 351	91.70 36	99.80 20	95.66 37	99.40 32	99.62 7

ACMMP_Plus		97.20 10	96.86 17	98.23 4	99.09 26	95.16 8	97.60 82	98.19 33	92.82 78	97.93 10	98.74 3	91.60 38	99.86 8	96.26 20	99.52 17	99.67 2

CP-MVSNet		91.89 171	91.24 169	93.82 200	95.05 217	88.57 194	97.82 50	98.19 33	91.70 109	88.21 241	95.76 162	81.96 177	97.52 269	87.86 175	84.65 280	95.37 234

PEN-MVS		91.20 208	90.44 203	93.48 224	94.49 240	87.91 228	97.76 53	98.18 35	91.29 120	87.78 246	95.74 164	80.35 206	97.33 282	85.46 222	82.96 298	95.19 246

DELS-MVS		96.61 36	96.38 37	97.30 44	97.79 99	93.19 53	95.96 228	98.18 35	95.23 11	95.87 61	97.65 72	91.45 40	99.70 34	95.87 33	99.44 29	99.00 69
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		89.70 248	88.40 252	93.60 217	95.15 212	90.10 133	97.56 86	98.16 37	87.28 237	86.16 271	94.63 214	77.57 260	98.05 212	74.48 312	84.59 281	92.65 307

VNet		95.89 55	95.45 52	97.21 52	98.07 81	92.94 60	97.50 90	98.15 38	93.87 41	97.52 12	97.61 78	85.29 110	99.53 70	95.81 36	95.27 143	99.16 53

DeepPCF-MVS	93.97 1	96.61 36	97.09 8	95.15 135	98.09 80	86.63 254	96.00 227	98.15 38	95.43 7	97.95 9	98.56 7	93.40 10	99.36 91	96.77 12	99.48 24	99.45 30

SD-MVS		97.41 7	97.53 2	97.06 56	98.57 51	94.46 16	97.92 42	98.14 40	94.82 21	99.01 1	98.55 9	94.18 5	97.41 277	96.94 5	99.64 3	99.32 43

UA-Net		95.95 54	95.53 51	97.20 53	97.67 105	92.98 59	97.65 69	98.13 41	94.81 22	96.61 35	98.35 24	88.87 66	99.51 74	90.36 133	97.35 106	99.11 60

QAPM		93.45 114	92.27 132	96.98 59	96.77 141	92.62 67	98.39 18	98.12 42	84.50 280	88.27 240	97.77 64	82.39 169	99.81 19	85.40 223	98.81 69	98.51 100

Vis-MVSNet		95.23 65	94.81 65	96.51 73	97.18 125	91.58 96	98.26 24	98.12 42	94.38 33	94.90 81	98.15 41	82.28 170	98.92 128	91.45 123	98.58 76	99.01 68
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 134	91.68 147	96.40 79	95.34 198	92.73 64	98.27 23	98.12 42	84.86 275	85.78 273	97.75 65	78.89 238	99.74 24	87.50 188	98.65 73	96.73 172

TranMVSNet+NR-MVSNet		92.50 145	91.63 152	95.14 136	94.76 231	92.07 81	97.53 88	98.11 45	92.90 77	89.56 212	96.12 143	83.16 133	97.60 265	89.30 147	83.20 297	95.75 215

CPTT-MVS		95.57 59	95.19 60	96.70 62	99.27 19	91.48 97	98.33 20	98.11 45	87.79 224	95.17 79	98.03 46	87.09 92	99.61 47	93.51 83	99.42 30	99.02 64

Regformer-2		97.16 13	96.99 11	97.67 29	98.32 65	93.84 35	96.83 151	98.10 47	95.24 10	97.49 13	98.25 39	92.57 19	99.61 47	96.80 9	99.29 43	99.56 15

APD-MVS		96.95 23	96.60 28	98.01 9	99.03 29	94.93 11	97.72 60	98.10 47	91.50 113	98.01 8	98.32 32	92.33 23	99.58 55	94.85 60	99.51 19	99.53 22
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 26	96.60 28	97.64 32	99.40 5	93.44 47	98.50 13	98.09 49	93.27 59	95.95 60	98.33 30	91.04 45	99.88 3	95.20 46	99.57 13	99.60 10

MPTG		97.07 17	96.77 24	97.97 11	99.37 10	94.42 18	97.15 126	98.08 50	95.07 14	96.11 51	98.59 5	90.88 49	99.90 1	96.18 27	99.50 21	99.58 11

MTGPA								98.08 50

MTAPA		97.08 16	96.78 23	97.97 11	99.37 10	94.42 18	97.24 114	98.08 50	95.07 14	96.11 51	98.59 5	90.88 49	99.90 1	96.18 27	99.50 21	99.58 11

CNVR-MVS		97.68 2	97.44 5	98.37 3	98.90 32	95.86 2	97.27 112	98.08 50	95.81 3	97.87 11	98.31 33	94.26 4	99.68 37	97.02 4	99.49 23	99.57 13

DP-MVS Recon		95.68 57	95.12 62	97.37 41	99.19 24	94.19 24	97.03 131	98.08 50	88.35 210	95.09 80	97.65 72	89.97 59	99.48 77	92.08 106	98.59 75	98.44 111

MCST-MVS		97.18 11	96.84 18	98.20 5	99.30 16	95.35 5	97.12 128	98.07 55	93.54 53	96.08 53	97.69 68	93.86 7	99.71 29	96.50 17	99.39 34	99.55 17

NR-MVSNet		92.34 154	91.27 168	95.53 117	94.95 222	93.05 56	97.39 102	98.07 55	92.65 82	84.46 281	95.71 165	85.00 114	97.77 253	89.71 139	83.52 294	95.78 211

MP-MVS-pluss		96.70 32	96.27 39	97.98 10	99.23 23	94.71 13	96.96 138	98.06 57	90.67 135	95.55 74	98.78 2	91.07 44	99.86 8	96.58 15	99.55 14	99.38 39
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 28	96.71 26	97.12 55	99.01 30	92.31 73	97.98 40	98.06 57	93.11 66	97.44 15	98.55 9	90.93 47	99.55 65	96.06 29	99.25 46	99.51 23

MP-MVS		96.77 30	96.45 35	97.72 25	99.39 7	93.80 36	98.41 17	98.06 57	93.37 55	95.54 75	98.34 27	90.59 52	99.88 3	94.83 61	99.54 15	99.49 26

HPM-MVS_fast		96.51 38	96.27 39	97.22 51	99.32 15	92.74 63	98.74 4	98.06 57	90.57 144	96.77 30	98.35 24	90.21 56	99.53 70	94.80 63	99.63 4	99.38 39

HPM-MVS		96.69 33	96.45 35	97.40 40	99.36 12	93.11 55	98.87 1	98.06 57	91.17 124	96.40 45	97.99 50	90.99 46	99.58 55	95.61 41	99.61 8	99.49 26

sss		94.51 83	93.80 85	96.64 63	97.07 129	91.97 86	96.32 205	98.06 57	88.94 183	94.50 87	96.78 107	84.60 119	99.27 95	91.90 109	96.02 131	98.68 92

DeepC-MVS	93.07 3	96.06 49	95.66 50	97.29 45	97.96 87	93.17 54	97.30 111	98.06 57	93.92 40	93.38 105	98.66 4	86.83 94	99.73 25	95.60 43	99.22 49	98.96 71
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 9	97.03 10	98.11 7	98.77 35	95.06 10	97.34 106	98.04 64	95.96 2	97.09 27	97.88 54	93.18 11	99.71 29	95.84 35	99.17 53	99.56 15

DeepC-MVS_fast	93.89 2	96.93 25	96.64 27	97.78 20	98.64 46	94.30 20	97.41 98	98.04 64	94.81 22	96.59 37	98.37 23	91.24 42	99.64 46	95.16 49	99.52 17	99.42 34
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 41	96.21 41	96.98 59	98.89 33	92.20 78	97.89 44	98.03 66	93.34 58	97.22 19	98.42 18	87.93 79	99.72 28	95.10 52	99.07 61	99.02 64

TEST9					98.70 38	94.19 24	96.41 193	98.02 67	88.17 217	96.03 54	97.56 83	92.74 14	99.59 52

train_agg		96.30 44	95.83 47	97.72 25	98.70 38	94.19 24	96.41 193	98.02 67	88.58 196	96.03 54	97.56 83	92.73 15	99.59 52	95.04 53	99.37 39	99.39 36

test_8					98.67 40	94.06 30	96.37 200	98.01 69	88.58 196	95.98 59	97.55 85	92.73 15	99.58 55

Regformer-4		96.97 22	96.87 16	97.25 48	98.34 62	92.66 66	96.96 138	98.01 69	95.12 13	97.14 23	98.42 18	91.82 34	99.61 47	96.90 6	99.13 56	99.50 24

agg_prior3		96.16 48	95.67 49	97.62 35	98.67 40	93.88 33	96.41 193	98.00 71	87.93 221	95.81 64	97.47 87	92.33 23	99.59 52	95.04 53	99.37 39	99.39 36

agg_prior1		96.22 47	95.77 48	97.56 36	98.67 40	93.79 37	96.28 209	98.00 71	88.76 193	95.68 68	97.55 85	92.70 17	99.57 63	95.01 55	99.32 41	99.32 43

agg_prior					98.67 40	93.79 37		98.00 71		95.68 68			99.57 63

test_prior3		96.46 40	96.20 42	97.23 49	98.67 40	92.99 57	96.35 201	98.00 71	92.80 79	96.03 54	97.59 79	92.01 30	99.41 85	95.01 55	99.38 35	99.29 45

test_prior				97.23 49	98.67 40	92.99 57		98.00 71					99.41 85			99.29 45

Regformer-1		97.10 15	96.96 13	97.54 37	98.32 65	93.48 46	96.83 151	97.99 76	95.20 12	97.46 14	98.25 39	92.48 22	99.58 55	96.79 11	99.29 43	99.55 17

WR-MVS		92.34 154	91.53 158	94.77 159	95.13 214	90.83 121	96.40 197	97.98 77	91.88 106	89.29 221	95.54 175	82.50 164	97.80 249	89.79 138	85.27 266	95.69 218

HPM-MVS++		97.34 8	96.97 12	98.47 1	99.08 27	96.16 1	97.55 87	97.97 78	95.59 4	96.61 35	97.89 52	92.57 19	99.84 14	95.95 32	99.51 19	99.40 35

CANet		96.39 42	96.02 44	97.50 38	97.62 108	93.38 49	97.02 133	97.96 79	95.42 8	94.86 82	97.81 61	87.38 89	99.82 18	96.88 7	99.20 51	99.29 45

114514_t		93.95 98	93.06 107	96.63 65	99.07 28	91.61 93	97.46 97	97.96 79	77.99 323	93.00 120	97.57 81	86.14 103	99.33 92	89.22 150	99.15 54	98.94 74

MVS_0304		96.05 50	95.45 52	97.85 14	97.75 102	94.50 15	96.87 148	97.95 81	95.46 6	95.60 72	98.01 48	80.96 191	99.83 15	97.23 2	99.25 46	99.23 49

原ACMM1				96.38 81	98.59 48	91.09 113		97.89 82	87.41 233	95.22 78	97.68 69	90.25 54	99.54 67	87.95 174	99.12 59	98.49 104

CDPH-MVS		95.97 53	95.38 55	97.77 22	98.93 31	94.44 17	96.35 201	97.88 83	86.98 245	96.65 34	97.89 52	91.99 32	99.47 78	92.26 97	99.46 25	99.39 36

test11								97.88 83

无先验							95.79 236	97.87 85	83.87 287				99.65 41	87.68 181		98.89 80

3Dnovator+	91.43 4	95.40 60	94.48 77	98.16 6	96.90 135	95.34 6	98.48 14	97.87 85	94.65 28	88.53 234	98.02 47	83.69 127	99.71 29	93.18 91	98.96 66	99.44 32

VPNet		92.23 161	91.31 166	94.99 143	95.56 189	90.96 116	97.22 119	97.86 87	92.96 75	90.96 169	96.62 124	75.06 274	98.20 187	91.90 109	83.65 293	95.80 210

HSP-MVS		97.53 5	97.49 4	97.63 34	99.40 5	93.77 40	98.53 9	97.85 88	95.55 5	98.56 3	97.81 61	93.90 6	99.65 41	96.62 13	99.21 50	99.48 28

TSAR-MVS + MP.		97.42 6	97.33 6	97.69 28	99.25 20	94.24 23	98.07 34	97.85 88	93.72 47	98.57 2	98.35 24	93.69 9	99.40 87	97.06 3	99.46 25	99.44 32

AdaColmap		94.34 85	93.68 89	96.31 85	98.59 48	91.68 92	96.59 184	97.81 90	89.87 152	92.15 137	97.06 101	83.62 128	99.54 67	89.34 146	98.07 86	97.70 142

Regformer-3		96.85 27	96.80 22	97.01 57	98.34 62	92.02 84	96.96 138	97.76 91	95.01 16	97.08 28	98.42 18	91.71 35	99.54 67	96.80 9	99.13 56	99.48 28

新几何1				97.32 43	98.60 47	93.59 43		97.75 92	81.58 305	95.75 67	97.85 58	90.04 58	99.67 39	86.50 204	99.13 56	98.69 91

旧先验1					98.38 60	93.38 49		97.75 92			98.09 43	92.30 27			99.01 64	99.16 53

EI-MVSNet-Vis-set		96.51 38	96.47 33	96.63 65	98.24 71	91.20 107	96.89 147	97.73 94	94.74 25	96.49 41	98.49 13	90.88 49	99.58 55	96.44 18	98.32 80	99.13 57

1121		94.71 81	93.83 84	97.34 42	98.57 51	93.64 42	96.04 223	97.73 94	81.56 307	95.68 68	97.85 58	90.23 55	99.65 41	87.68 181	99.12 59	98.73 87

PAPM_NR		95.01 70	94.59 71	96.26 90	98.89 33	90.68 125	97.24 114	97.73 94	91.80 107	92.93 125	96.62 124	89.13 64	99.14 106	89.21 151	97.78 93	98.97 70

CHOSEN 280x420		93.12 123	92.72 118	94.34 178	96.71 143	87.27 237	90.29 325	97.72 97	86.61 255	91.34 153	95.29 186	84.29 123	98.41 173	93.25 90	98.94 67	97.35 155

EI-MVSNet-UG-set		96.34 43	96.30 38	96.47 76	98.20 75	90.93 118	96.86 149	97.72 97	94.67 26	96.16 50	98.46 14	90.43 53	99.58 55	96.23 21	97.96 89	98.90 78

LS3D		93.57 111	92.61 122	96.47 76	97.59 111	91.61 93	97.67 66	97.72 97	85.17 270	90.29 179	98.34 27	84.60 119	99.73 25	83.85 249	98.27 81	98.06 128

PAPR		94.18 88	93.42 101	96.48 75	97.64 107	91.42 101	95.55 246	97.71 100	88.99 179	92.34 133	95.82 156	89.19 62	99.11 108	86.14 209	97.38 104	98.90 78

pcd1.5k->3k		38.37 328	40.51 329	31.96 341	94.29 248	0.00 360	0.00 351	97.69 101	0.00 355	0.00 356	0.00 357	81.45 185	0.00 358	0.00 355	91.11 213	95.89 203

UGNet		94.04 96	93.28 104	96.31 85	96.85 136	91.19 108	97.88 45	97.68 102	94.40 31	93.00 120	96.18 140	73.39 288	99.61 47	91.72 114	98.46 77	98.13 123
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				95.46 124	98.18 78	88.90 190		97.66 103	82.73 296	97.03 29	98.07 44	90.06 57	98.85 135	89.67 140	98.98 65	98.64 93

test12				97.65 30	98.46 53	94.26 21		97.66 103		95.52 76		90.89 48	99.46 79		99.25 46	99.22 50

DTE-MVSNet		90.56 230	89.75 231	93.01 241	93.95 271	87.25 238	97.64 73	97.65 105	90.74 132	87.12 260	95.68 168	79.97 212	97.00 293	83.33 253	81.66 305	94.78 273

TAPA-MVS	90.10 7	92.30 157	91.22 171	95.56 115	98.33 64	89.60 158	96.79 158	97.65 105	81.83 302	91.52 148	97.23 94	87.94 78	98.91 129	71.31 323	98.37 79	98.17 122
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
cdsmvs_eth3d_5k		23.24 330	30.99 330	0.00 345	0.00 359	0.00 360	0.00 351	97.63 107	0.00 355	0.00 356	96.88 105	84.38 122	0.00 358	0.00 355	0.00 356	0.00 356

canonicalmvs		96.02 52	95.45 52	97.75 24	97.59 111	95.15 9	98.28 22	97.60 108	94.52 29	96.27 47	96.12 143	87.65 83	99.18 101	96.20 26	94.82 149	98.91 77

test222					98.24 71	92.21 76	95.33 255	97.60 108	79.22 318	95.25 77	97.84 60	88.80 68			99.15 54	98.72 88

cascas		91.20 208	90.08 216	94.58 170	94.97 220	89.16 186	93.65 291	97.59 110	79.90 315	89.40 216	92.92 277	75.36 272	98.36 177	92.14 102	94.75 151	96.23 186

MVSFormer		95.37 61	95.16 61	95.99 99	96.34 161	91.21 105	98.22 26	97.57 111	91.42 117	96.22 48	97.32 89	86.20 101	97.92 238	94.07 70	99.05 62	98.85 82

test_djsdf		93.07 125	92.76 113	94.00 189	93.49 286	88.70 192	98.22 26	97.57 111	91.42 117	90.08 191	95.55 174	82.85 156	97.92 238	94.07 70	91.58 205	95.40 231

OMC-MVS		95.09 69	94.70 69	96.25 91	98.46 53	91.28 103	96.43 191	97.57 111	92.04 102	94.77 84	97.96 51	87.01 93	99.09 117	91.31 125	96.77 118	98.36 118

PS-MVSNAJss		93.74 105	93.51 95	94.44 173	93.91 273	89.28 182	97.75 54	97.56 114	92.50 84	89.94 193	96.54 127	88.65 70	98.18 190	93.83 79	90.90 216	95.86 204

jajsoiax		92.42 151	91.89 141	94.03 188	93.33 292	88.50 196	97.73 58	97.53 115	92.00 104	88.85 228	96.50 129	75.62 271	98.11 196	93.88 77	91.56 206	95.48 221

mvs_tets		92.31 156	91.76 143	93.94 197	93.41 288	88.29 199	97.63 80	97.53 115	92.04 102	88.76 229	96.45 131	74.62 278	98.09 199	93.91 75	91.48 207	95.45 225

HQP_MVS		93.78 104	93.43 99	94.82 153	96.21 165	89.99 137	97.74 56	97.51 117	94.85 17	91.34 153	96.64 117	81.32 187	98.60 153	93.02 92	92.23 192	95.86 204

plane_prior5								97.51 117					98.60 153	93.02 92	92.23 192	95.86 204

PS-MVSNAJ		95.37 61	95.33 57	95.49 120	97.35 121	90.66 126	95.31 257	97.48 119	93.85 42	96.51 40	95.70 167	88.65 70	99.65 41	94.80 63	98.27 81	96.17 189

API-MVS		94.84 79	94.49 76	95.90 101	97.90 95	92.00 85	97.80 51	97.48 119	89.19 168	94.81 83	96.71 110	88.84 67	99.17 102	88.91 159	98.76 71	96.53 179

MG-MVS		95.61 58	95.38 55	96.31 85	98.42 56	90.53 128	96.04 223	97.48 119	93.47 54	95.67 71	98.10 42	89.17 63	99.25 96	91.27 126	98.77 70	99.13 57

MAR-MVS		94.22 87	93.46 97	96.51 73	98.00 82	92.19 79	97.67 66	97.47 122	88.13 219	93.00 120	95.84 154	84.86 117	99.51 74	87.99 173	98.17 84	97.83 137
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		92.98 128	92.53 126	94.32 179	96.12 174	89.20 184	95.28 258	97.47 122	92.66 81	89.90 194	95.62 170	80.58 201	98.40 174	92.73 95	92.40 190	95.38 233
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 95	93.31 103	96.27 89	95.22 208	94.59 14	98.34 19	97.46 124	92.93 76	91.21 167	96.64 117	87.23 91	98.22 186	94.99 58	85.80 260	95.98 202

XVG-OURS		93.72 106	93.35 102	94.80 156	97.07 129	88.61 193	94.79 267	97.46 124	91.97 105	93.99 95	97.86 57	81.74 182	98.88 134	92.64 96	92.67 188	96.92 167

LPG-MVS_test		92.94 130	92.56 123	94.10 184	96.16 170	88.26 201	97.65 69	97.46 124	91.29 120	90.12 187	97.16 96	79.05 224	98.73 145	92.25 99	91.89 200	95.31 237

LGP-MVS_train				94.10 184	96.16 170	88.26 201		97.46 124	91.29 120	90.12 187	97.16 96	79.05 224	98.73 145	92.25 99	91.89 200	95.31 237

MVS		91.71 176	90.44 203	95.51 118	95.20 210	91.59 95	96.04 223	97.45 128	73.44 335	87.36 256	95.60 171	85.42 109	99.10 114	85.97 214	97.46 99	95.83 208

XVG-OURS-SEG-HR		93.86 101	93.55 92	94.81 155	97.06 131	88.53 195	95.28 258	97.45 128	91.68 110	94.08 94	97.68 69	82.41 168	98.90 130	93.84 78	92.47 189	96.98 159

ab-mvs		93.57 111	92.55 124	96.64 63	97.28 122	91.96 87	95.40 253	97.45 128	89.81 157	93.22 113	96.28 137	79.62 217	99.46 79	90.74 130	93.11 183	98.50 102

xiu_mvs_v2_base		95.32 63	95.29 58	95.40 126	97.22 123	90.50 129	95.44 252	97.44 131	93.70 49	96.46 43	96.18 140	88.59 73	99.53 70	94.79 65	97.81 92	96.17 189

1314		92.81 137	92.03 136	95.14 136	95.33 201	89.52 164	96.04 223	97.44 131	87.72 227	86.25 270	95.33 185	83.84 125	98.79 139	89.26 148	97.05 112	97.11 157

XXY-MVS		92.16 163	91.23 170	94.95 148	94.75 232	90.94 117	97.47 96	97.43 133	89.14 175	88.90 226	96.43 132	79.71 215	98.24 185	89.56 143	87.68 247	95.67 219

anonymousdsp		92.16 163	91.55 157	93.97 192	92.58 309	89.55 161	97.51 89	97.42 134	89.42 163	88.40 235	94.84 203	80.66 200	97.88 243	91.87 111	91.28 211	94.48 281

Effi-MVS+		94.93 75	94.45 78	96.36 83	96.61 144	91.47 98	96.41 193	97.41 135	91.02 129	94.50 87	95.92 150	87.53 86	98.78 140	93.89 76	96.81 117	98.84 84

HQP3-MVS								97.39 136							92.10 197

HQP-MVS		93.19 122	92.74 117	94.54 171	95.86 179	89.33 177	96.65 176	97.39 136	93.55 50	90.14 181	95.87 152	80.95 192	98.50 162	92.13 103	92.10 197	95.78 211

PLC	91.00 6	94.11 92	93.43 99	96.13 94	98.58 50	91.15 112	96.69 173	97.39 136	87.29 236	91.37 151	96.71 110	88.39 74	99.52 73	87.33 192	97.13 111	97.73 140
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 221	89.86 225	93.45 227	93.54 283	87.60 234	97.70 65	97.37 139	88.85 186	87.65 250	94.08 249	81.08 189	98.10 197	84.68 232	83.79 292	94.66 277

UnsupCasMVSNet_eth		85.99 290	84.45 291	90.62 297	89.97 322	82.40 293	93.62 292	97.37 139	89.86 153	78.59 323	92.37 286	65.25 321	95.35 321	82.27 267	70.75 335	94.10 290

ACMM	89.79 8	92.96 129	92.50 128	94.35 177	96.30 163	88.71 191	97.58 85	97.36 141	91.40 119	90.53 173	96.65 116	79.77 214	98.75 144	91.24 127	91.64 203	95.59 220
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 70	94.76 66	95.75 107	96.58 146	91.71 89	96.25 211	97.35 142	92.99 69	96.70 31	96.63 121	82.67 159	99.44 82	96.22 22	97.46 99	96.11 194

xiu_mvs_v1_base		95.01 70	94.76 66	95.75 107	96.58 146	91.71 89	96.25 211	97.35 142	92.99 69	96.70 31	96.63 121	82.67 159	99.44 82	96.22 22	97.46 99	96.11 194

xiu_mvs_v1_base_debi		95.01 70	94.76 66	95.75 107	96.58 146	91.71 89	96.25 211	97.35 142	92.99 69	96.70 31	96.63 121	82.67 159	99.44 82	96.22 22	97.46 99	96.11 194

WTY-MVS		94.71 81	94.02 81	96.79 61	97.71 104	92.05 82	96.59 184	97.35 142	90.61 141	94.64 85	96.93 103	86.41 98	99.39 88	91.20 128	94.71 153	98.94 74

F-COLMAP		93.58 110	92.98 108	95.37 127	98.40 57	88.98 188	97.18 123	97.29 146	87.75 226	90.49 174	97.10 100	85.21 111	99.50 76	86.70 201	96.72 121	97.63 143

XVG-ACMP-BASELINE		90.93 217	90.21 214	93.09 239	94.31 247	85.89 259	95.33 255	97.26 147	91.06 128	89.38 217	95.44 182	68.61 307	98.60 153	89.46 145	91.05 214	94.79 272

PCF-MVS	89.48 11	91.56 192	89.95 222	96.36 83	96.60 145	92.52 70	92.51 309	97.26 147	79.41 316	88.90 226	96.56 126	84.04 124	99.55 65	77.01 308	97.30 107	97.01 158
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 140	92.14 133	94.05 187	96.40 159	88.20 207	97.36 105	97.25 149	91.52 112	88.30 238	96.64 117	78.46 242	98.72 147	91.86 112	91.48 207	95.23 244
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 119	92.76 113	94.82 153	94.63 236	90.77 124	96.65 176	97.18 150	93.72 47	91.68 146	97.26 92	79.33 221	98.63 150	92.13 103	92.28 191	95.07 250

PatchMatch-RL		92.90 132	92.02 137	95.56 115	98.19 77	90.80 122	95.27 260	97.18 150	87.96 220	91.86 143	95.68 168	80.44 204	98.99 125	84.01 245	97.54 98	96.89 168

alignmvs		95.87 56	95.23 59	97.78 20	97.56 113	95.19 7	97.86 46	97.17 152	94.39 32	96.47 42	96.40 133	85.89 104	99.20 98	96.21 25	95.11 145	98.95 73

v748		90.34 234	89.54 236	92.75 249	93.25 293	85.71 262	97.61 81	97.17 152	88.54 199	87.20 259	93.54 265	81.02 190	98.01 221	85.73 219	81.80 302	94.52 280

MVS_Test		94.89 77	94.62 70	95.68 111	96.83 139	89.55 161	96.70 171	97.17 152	91.17 124	95.60 72	96.11 145	87.87 80	98.76 143	93.01 94	97.17 110	98.72 88

V4		90.71 226	90.00 220	92.82 244	93.21 297	87.03 244	97.59 84	97.16 155	88.21 213	87.69 248	93.92 254	80.93 194	98.06 209	87.39 189	83.90 290	93.39 299

v52		90.70 227	90.00 220	92.82 244	93.24 294	87.03 244	97.60 82	97.14 156	88.21 213	87.69 248	93.94 252	80.91 195	98.07 204	87.39 189	83.87 291	93.36 301

diffmvs		93.43 115	92.75 115	95.48 122	96.47 156	89.61 157	96.09 220	97.14 156	85.97 262	93.09 118	95.35 184	84.87 116	98.55 158	89.51 144	96.26 130	98.28 120

Fast-Effi-MVS+		93.46 113	92.75 115	95.59 114	96.77 141	90.03 134	96.81 155	97.13 158	88.19 215	91.30 156	94.27 243	86.21 100	98.63 150	87.66 183	96.46 128	98.12 124

EI-MVSNet		93.03 127	92.88 111	93.48 224	95.77 184	86.98 246	96.44 189	97.12 159	90.66 137	91.30 156	97.64 75	86.56 96	98.05 212	89.91 135	90.55 221	95.41 227

MVSTER		93.20 121	92.81 112	94.37 176	96.56 149	89.59 159	97.06 130	97.12 159	91.24 123	91.30 156	95.96 148	82.02 176	98.05 212	93.48 85	90.55 221	95.47 223

testing_2		87.33 280	85.03 287	94.22 180	87.77 331	89.32 179	94.97 265	97.11 161	89.22 167	71.64 333	88.73 319	55.16 338	97.94 234	91.95 107	88.73 240	95.41 227

Test4		89.48 250	87.50 260	95.44 125	90.76 319	89.72 148	95.78 238	97.09 162	90.28 146	77.67 324	91.74 298	55.42 337	98.08 200	91.92 108	96.83 116	98.52 98

LTVRE_ROB	88.41 13	90.99 215	89.92 223	94.19 181	96.18 168	89.55 161	96.31 206	97.09 162	87.88 223	85.67 274	95.91 151	78.79 239	98.57 156	81.50 274	89.98 227	94.44 283
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		91.04 214	90.23 212	93.49 223	94.12 258	88.16 210	97.32 109	97.08 164	88.26 212	88.29 239	94.22 246	82.17 174	97.97 228	86.45 205	84.12 285	94.33 286

v144192		91.06 213	90.28 208	93.39 228	93.66 281	87.23 240	96.83 151	97.07 165	87.43 232	89.69 207	94.28 241	81.48 184	98.00 224	87.18 196	84.92 278	94.93 260

v1192		91.07 212	90.23 212	93.58 220	93.70 279	87.82 229	96.73 163	97.07 165	87.77 225	89.58 210	94.32 231	80.90 198	97.97 228	86.52 203	85.48 261	94.95 256

v8		91.29 206	90.53 202	93.57 221	94.15 254	88.12 214	97.34 106	97.06 167	88.99 179	88.32 237	94.26 245	83.08 140	98.01 221	87.62 185	83.92 289	94.57 279

v7		91.47 197	90.73 190	93.68 214	94.13 256	88.16 210	97.09 129	97.05 168	88.38 208	89.80 200	94.52 216	82.21 172	98.01 221	88.00 172	85.42 263	94.87 262

mvs_anonymous		93.82 102	93.74 86	94.06 186	96.44 158	85.41 266	95.81 235	97.05 168	89.85 155	90.09 190	96.36 135	87.44 88	97.75 254	93.97 72	96.69 122	99.02 64

IterMVS-LS		92.29 158	91.94 140	93.34 231	96.25 164	86.97 247	96.57 187	97.05 168	90.67 135	89.50 215	94.80 207	86.59 95	97.64 262	89.91 135	86.11 258	95.40 231
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 219	90.03 219	93.29 233	93.55 282	86.96 248	96.74 162	97.04 171	87.36 234	89.52 214	94.34 229	80.23 209	97.97 228	86.27 206	85.21 267	94.94 258

CDS-MVSNet		94.14 91	93.54 93	95.93 100	96.18 168	91.46 99	96.33 204	97.04 171	88.97 182	93.56 100	96.51 128	87.55 85	97.89 242	89.80 137	95.95 133	98.44 111
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 202	90.60 200	93.68 214	93.89 274	88.23 204	96.84 150	97.03 173	88.37 209	89.69 207	94.39 226	82.04 175	97.98 225	87.80 177	85.37 264	94.84 264

v1240		90.70 227	89.85 226	93.23 235	93.51 285	86.80 249	96.61 181	97.02 174	87.16 239	89.58 210	94.31 232	79.55 218	97.98 225	85.52 221	85.44 262	94.90 261

EPP-MVSNet		95.22 66	95.04 63	95.76 106	97.49 120	89.56 160	98.67 5	97.00 175	90.69 134	94.24 92	97.62 77	89.79 61	98.81 138	93.39 89	96.49 126	98.92 76

v1neww		91.70 179	91.01 175	93.75 206	94.19 250	88.14 212	97.20 120	96.98 176	89.18 170	89.87 197	94.44 223	83.10 138	98.06 209	89.06 155	85.09 270	95.06 253

v7new		91.70 179	91.01 175	93.75 206	94.19 250	88.14 212	97.20 120	96.98 176	89.18 170	89.87 197	94.44 223	83.10 138	98.06 209	89.06 155	85.09 270	95.06 253

v6		91.69 181	91.00 177	93.75 206	94.14 255	88.12 214	97.20 120	96.98 176	89.19 168	89.90 194	94.42 225	83.04 144	98.07 204	89.07 154	85.10 269	95.07 250

V42		91.58 191	90.87 182	93.73 209	94.05 267	88.50 196	97.32 109	96.97 179	88.80 192	89.71 205	94.33 230	82.54 163	98.05 212	89.01 157	85.07 272	94.64 278

v1141		91.61 187	90.89 179	93.78 203	94.01 268	88.24 203	96.96 138	96.96 180	89.17 172	89.75 203	94.29 239	82.99 148	98.03 217	88.85 161	85.00 275	95.07 250

divwei89l23v2f112		91.61 187	90.89 179	93.78 203	94.01 268	88.22 205	96.96 138	96.96 180	89.17 172	89.75 203	94.28 241	83.02 146	98.03 217	88.86 160	84.98 277	95.08 248

v1		91.61 187	90.89 179	93.78 203	94.01 268	88.21 206	96.96 138	96.96 180	89.17 172	89.78 202	94.29 239	82.97 150	98.05 212	88.85 161	84.99 276	95.08 248

FMVSNet2		91.31 205	90.08 216	94.99 143	96.51 152	92.21 76	97.41 98	96.95 183	88.82 189	88.62 231	94.75 209	73.87 282	97.42 276	85.20 226	88.55 242	95.35 235

ACMH	87.59 16	90.53 231	89.42 238	93.87 199	96.21 165	87.92 226	97.24 114	96.94 184	88.45 200	83.91 289	96.27 138	71.92 290	98.62 152	84.43 237	89.43 232	95.05 255
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 203	90.27 209	94.59 166	96.51 152	91.18 109	97.50 90	96.93 185	88.82 189	89.35 218	94.51 217	73.87 282	97.29 284	86.12 210	88.82 236	95.31 237

test1		91.35 203	90.27 209	94.59 166	96.51 152	91.18 109	97.50 90	96.93 185	88.82 189	89.35 218	94.51 217	73.87 282	97.29 284	86.12 210	88.82 236	95.31 237

FMVSNet3		91.78 173	90.69 192	95.03 142	96.53 151	92.27 75	97.02 133	96.93 185	89.79 158	89.35 218	94.65 213	77.01 262	97.47 272	86.12 210	88.82 236	95.35 235

FMVSNet1		89.88 245	88.31 253	94.59 166	95.41 194	91.18 109	97.50 90	96.93 185	86.62 254	87.41 254	94.51 217	65.94 319	97.29 284	83.04 256	87.43 250	95.31 237

TAMVS		94.01 97	93.46 97	95.64 112	96.16 170	90.45 131	96.71 168	96.89 189	89.27 166	93.46 104	96.92 104	87.29 90	97.94 234	88.70 165	95.74 137	98.53 97

v2v482		91.59 190	90.85 184	93.80 201	93.87 275	88.17 209	96.94 144	96.88 190	89.54 159	89.53 213	94.90 198	81.70 183	98.02 220	89.25 149	85.04 274	95.20 245

CNLPA		94.28 86	93.53 94	96.52 70	98.38 60	92.55 69	96.59 184	96.88 190	90.13 149	91.91 141	97.24 93	85.21 111	99.09 117	87.64 184	97.83 91	97.92 131

PAPM		91.52 195	90.30 207	95.20 129	95.30 202	89.83 145	93.38 295	96.85 192	86.26 258	88.59 233	95.80 157	84.88 115	98.15 192	75.67 311	95.93 134	97.63 143

pm-mvs1		90.72 225	89.65 235	93.96 193	94.29 248	89.63 156	97.79 52	96.82 193	89.07 176	86.12 272	95.48 181	78.61 240	97.78 251	86.97 199	81.67 304	94.46 282

CMPMVS	62.92 21	85.62 293	84.92 288	87.74 311	89.14 326	73.12 330	94.17 280	96.80 194	73.98 333	73.65 329	94.93 196	66.36 316	97.61 264	83.95 247	91.28 211	92.48 313
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 235	89.77 229	91.78 278	94.33 246	84.72 275	95.55 246	96.73 195	86.17 260	86.36 269	95.28 188	71.28 295	97.80 249	84.09 242	98.14 85	92.81 306

Effi-MVS+-dtu		93.08 124	93.21 105	92.68 252	96.02 176	83.25 288	97.14 127	96.72 196	93.85 42	91.20 168	93.44 271	83.08 140	98.30 183	91.69 117	95.73 138	96.50 181

mvs-test1		93.63 108	93.69 88	93.46 226	96.02 176	84.61 276	97.24 114	96.72 196	93.85 42	92.30 134	95.76 162	83.08 140	98.89 132	91.69 117	96.54 125	96.87 169

TSAR-MVS + GP.		96.69 33	96.49 32	97.27 47	98.31 67	93.39 48	96.79 158	96.72 196	94.17 36	97.44 15	97.66 71	92.76 13	99.33 92	96.86 8	97.76 95	99.08 62

1112_ss		93.37 116	92.42 130	96.21 92	97.05 132	90.99 114	96.31 206	96.72 196	86.87 251	89.83 199	96.69 114	86.51 97	99.14 106	88.12 170	93.67 171	98.50 102

PVSNet	86.66 18	92.24 160	91.74 146	93.73 209	97.77 101	83.69 285	92.88 304	96.72 196	87.91 222	93.00 120	94.86 202	78.51 241	99.05 123	86.53 202	97.45 103	98.47 107

v148		90.99 215	90.38 205	92.81 247	93.83 276	85.80 260	96.78 160	96.68 201	89.45 162	88.75 230	93.93 253	82.96 152	97.82 248	87.83 176	83.25 295	94.80 270

ACMH+	87.92 14	90.20 238	89.18 242	93.25 234	96.48 155	86.45 255	96.99 136	96.68 201	88.83 188	84.79 280	96.22 139	70.16 303	98.53 159	84.42 238	88.04 244	94.77 274

CANet_DTU		94.37 84	93.65 90	96.55 69	96.46 157	92.13 80	96.21 215	96.67 203	94.38 33	93.53 102	97.03 102	79.34 220	99.71 29	90.76 129	98.45 78	97.82 138

HY-MVS	89.66 9	93.87 100	92.95 109	96.63 65	97.10 128	92.49 71	95.64 243	96.64 204	89.05 177	93.00 120	95.79 160	85.77 107	99.45 81	89.16 153	94.35 154	97.96 129

Test_1112_low_res		92.84 136	91.84 142	95.85 103	97.04 133	89.97 140	95.53 248	96.64 204	85.38 266	89.65 209	95.18 190	85.86 105	99.10 114	87.70 179	93.58 176	98.49 104

Fast-Effi-MVS+-dtu		92.29 158	91.99 138	93.21 237	95.27 203	85.52 265	97.03 131	96.63 206	92.09 96	89.11 225	95.14 192	80.33 207	98.08 200	87.54 187	94.74 152	96.03 201

UnsupCasMVSNet_bld		82.13 305	79.46 307	90.14 303	88.00 329	82.47 291	90.89 323	96.62 207	78.94 319	75.61 326	84.40 335	56.63 334	96.31 299	77.30 307	66.77 341	91.63 327

jason		94.84 79	94.39 80	96.18 93	95.52 190	90.93 118	96.09 220	96.52 208	89.28 165	96.01 58	97.32 89	84.70 118	98.77 142	95.15 50	98.91 68	98.85 82
jason: jason.
EG-PatchMatch MVS		87.02 283	85.44 284	91.76 280	92.67 307	85.00 270	96.08 222	96.45 209	83.41 292	79.52 320	93.49 268	57.10 333	97.72 256	79.34 299	90.87 217	92.56 309

pmmvs6		87.81 277	86.19 279	92.69 251	91.32 316	86.30 256	97.34 106	96.41 210	80.59 314	84.05 288	94.37 228	67.37 314	97.67 259	84.75 230	79.51 312	94.09 291

PMMVS		92.86 134	92.34 131	94.42 175	94.92 224	86.73 250	94.53 272	96.38 211	84.78 277	94.27 91	95.12 194	83.13 136	98.40 174	91.47 122	96.49 126	98.12 124

RPSCF		90.75 223	90.86 183	90.42 300	96.84 137	76.29 324	95.61 245	96.34 212	83.89 285	91.38 150	97.87 55	76.45 264	98.78 140	87.16 197	92.23 192	96.20 187

MSDG		91.42 199	90.24 211	94.96 147	97.15 127	88.91 189	93.69 289	96.32 213	85.72 264	86.93 265	96.47 130	80.24 208	98.98 126	80.57 290	95.05 146	96.98 159

OurMVSNet-221017-0		90.51 232	90.19 215	91.44 285	93.41 288	81.25 300	96.98 137	96.28 214	91.68 110	86.55 268	96.30 136	74.20 281	97.98 225	88.96 158	87.40 252	95.09 247

MVP-Stereo		90.74 224	90.08 216	92.71 250	93.19 299	88.20 207	95.86 232	96.27 215	86.07 261	84.86 279	94.76 208	77.84 258	97.75 254	83.88 248	98.01 87	92.17 324
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 74	94.56 72	96.29 88	96.34 161	91.21 105	95.83 234	96.27 215	88.93 184	96.22 48	96.88 105	86.20 101	98.85 135	95.27 45	99.05 62	98.82 85

BH-untuned		92.94 130	92.62 121	93.92 198	97.22 123	86.16 258	96.40 197	96.25 217	90.06 150	89.79 201	96.17 142	83.19 132	98.35 178	87.19 195	97.27 108	97.24 156

test_normal		92.01 166	90.75 189	95.80 105	93.24 294	89.97 140	95.93 230	96.24 218	90.62 139	81.63 299	93.45 270	74.98 275	98.89 132	93.61 81	97.04 113	98.55 95

IS-MVSNet		94.90 76	94.52 75	96.05 96	97.67 105	90.56 127	98.44 15	96.22 219	93.21 60	93.99 95	97.74 66	85.55 108	98.45 166	89.98 134	97.86 90	99.14 56

GA-MVS		91.38 201	90.31 206	94.59 166	94.65 235	87.62 233	94.34 275	96.19 220	90.73 133	90.35 178	93.83 255	71.84 291	97.96 232	87.22 194	93.61 174	98.21 121

DI_MVS_plusplus_test		92.01 166	90.77 187	95.73 110	93.34 290	89.78 147	96.14 218	96.18 221	90.58 143	81.80 298	93.50 267	74.95 276	98.90 130	93.51 83	96.94 114	98.51 100

semantic-postprocess				91.82 275	95.52 190	84.20 279		96.15 222	90.61 141	87.39 255	94.27 243	75.63 270	96.44 297	87.34 191	86.88 255	94.82 268

IterMVS		90.15 240	89.67 233	91.61 282	95.48 192	83.72 282	94.33 276	96.12 223	89.99 151	87.31 258	94.15 247	75.78 269	96.27 300	86.97 199	86.89 254	94.83 266
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 138	91.51 161	96.52 70	98.77 35	90.99 114	97.38 104	96.08 224	82.38 298	89.29 221	97.87 55	83.77 126	99.69 35	81.37 280	96.69 122	98.89 80

pmmvs4		90.93 217	89.85 226	94.17 182	93.34 290	90.79 123	94.60 269	96.02 225	84.62 278	87.45 252	95.15 191	81.88 180	97.45 273	87.70 179	87.87 246	94.27 289

v18		88.71 260	87.52 259	92.27 257	94.16 253	88.11 216	96.82 154	95.96 226	87.03 241	80.76 305	89.81 306	83.15 134	96.22 301	84.69 231	75.31 323	92.49 311

v17		88.67 262	87.47 262	92.26 259	94.13 256	88.09 218	96.81 155	95.95 227	87.02 242	80.72 306	89.75 308	83.11 137	96.20 302	84.61 234	75.15 325	92.49 311

v16		88.69 261	87.50 260	92.26 259	94.19 250	88.11 216	96.81 155	95.95 227	87.01 243	80.71 307	89.80 307	83.08 140	96.20 302	84.61 234	75.34 322	92.48 313

ITE_SJBPF				92.43 256	95.34 198	85.37 267		95.92 229	91.47 114	87.75 247	96.39 134	71.00 297	97.96 232	82.36 266	89.86 230	93.97 292

V14		88.52 265	87.30 265	92.17 264	94.12 258	87.99 221	96.72 166	95.91 230	86.98 245	80.50 311	89.63 309	83.03 145	96.12 306	84.23 240	74.60 328	92.40 318

v15		88.53 264	87.31 264	92.20 262	94.09 262	88.05 219	96.72 166	95.90 231	87.01 243	80.53 310	89.60 312	83.02 146	96.13 304	84.29 239	74.64 326	92.41 317

v13		88.45 270	87.22 270	92.16 266	94.08 264	87.95 225	96.71 168	95.90 231	86.86 252	80.27 317	89.55 314	82.92 153	96.12 306	84.02 244	74.63 327	92.40 318

v12		88.46 269	87.23 269	92.17 264	94.10 261	87.99 221	96.71 168	95.90 231	86.91 248	80.34 315	89.58 313	82.92 153	96.11 308	84.09 242	74.50 331	92.42 316

V9		88.49 268	87.26 266	92.18 263	94.12 258	87.97 224	96.73 163	95.90 231	86.95 247	80.40 313	89.61 310	82.98 149	96.13 304	84.14 241	74.55 329	92.44 315

USDC		88.94 255	87.83 257	92.27 257	94.66 234	84.96 271	93.86 286	95.90 231	87.34 235	83.40 291	95.56 173	67.43 313	98.19 189	82.64 263	89.67 231	93.66 295

COLMAP_ROB	87.81 15	90.40 233	89.28 240	93.79 202	97.95 88	87.13 243	96.92 145	95.89 236	82.83 295	86.88 267	97.18 95	73.77 285	99.29 94	78.44 302	93.62 173	94.95 256
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 102	93.08 106	96.02 97	97.88 96	89.96 142	97.72 60	95.85 237	92.43 85	95.86 62	98.44 16	68.42 309	99.39 88	96.31 19	94.85 147	98.71 90

v11		88.41 271	87.19 273	92.08 269	94.08 264	87.77 230	96.75 161	95.85 237	86.74 253	80.50 311	89.50 315	82.49 165	96.08 309	83.55 250	75.20 324	92.38 320

VDDNet		93.05 126	92.07 134	96.02 97	96.84 137	90.39 132	98.08 33	95.85 237	86.22 259	95.79 66	98.46 14	67.59 312	99.19 99	94.92 59	94.85 147	98.47 107

Vis-MVSNet (Re-imp)		94.15 89	93.88 83	94.95 148	97.61 109	87.92 226	98.10 31	95.80 240	92.22 88	93.02 119	97.45 88	84.53 121	97.91 241	88.24 168	97.97 88	99.02 64

tpm cat1		88.36 272	87.21 271	91.81 276	95.13 214	80.55 306	92.58 308	95.70 241	74.97 331	87.45 252	91.96 294	78.01 257	98.17 191	80.39 292	88.74 239	96.72 173

BH-w/o		92.14 165	91.75 144	93.31 232	96.99 134	85.73 261	95.67 240	95.69 242	88.73 194	89.26 223	94.82 206	82.97 150	98.07 204	85.26 225	96.32 129	96.13 193

CR-MVSNet		90.82 220	89.77 229	93.95 194	94.45 242	87.19 241	90.23 326	95.68 243	86.89 250	92.40 129	92.36 289	80.91 195	97.05 288	81.09 289	93.95 167	97.60 148

Patchmtry		88.64 263	87.25 267	92.78 248	94.09 262	86.64 251	89.82 329	95.68 243	80.81 312	87.63 251	92.36 289	80.91 195	97.03 290	78.86 300	85.12 268	94.67 276

BH-RMVSNet		92.72 139	91.97 139	94.97 146	97.16 126	87.99 221	96.15 217	95.60 245	90.62 139	91.87 142	97.15 98	78.41 243	98.57 156	83.16 254	97.60 97	98.36 118

PVSNet_0	82.17 19	85.46 294	83.64 295	90.92 291	95.27 203	79.49 315	90.55 324	95.60 245	83.76 288	83.00 292	89.95 303	71.09 296	97.97 228	82.75 261	60.79 342	95.31 237

Patchmatch-test1		91.54 194	90.85 184	93.59 218	95.59 188	84.95 272	94.72 268	95.58 247	90.82 130	92.25 135	93.58 264	75.80 268	97.41 277	83.35 251	95.98 132	98.40 114

AllTest		90.23 237	88.98 244	93.98 190	97.94 89	86.64 251	96.51 188	95.54 248	85.38 266	85.49 276	96.77 108	70.28 301	99.15 104	80.02 293	92.87 184	96.15 191

TestCases				93.98 190	97.94 89	86.64 251		95.54 248	85.38 266	85.49 276	96.77 108	70.28 301	99.15 104	80.02 293	92.87 184	96.15 191

tpmvs		89.83 247	89.15 243	91.89 273	94.92 224	80.30 309	93.11 301	95.46 250	86.28 257	88.08 242	92.65 280	80.44 204	98.52 160	81.47 275	89.92 229	96.84 170

PatchFormer-LS_test		91.68 186	91.18 173	93.19 238	95.24 207	83.63 286	95.53 248	95.44 251	89.82 156	91.37 151	92.58 283	80.85 199	98.52 160	89.65 142	90.16 226	97.42 154

pmmvs5		89.86 246	88.87 246	92.82 244	92.86 303	86.23 257	96.26 210	95.39 252	84.24 281	87.12 260	94.51 217	74.27 280	97.36 281	87.61 186	87.57 248	94.86 263

PatchmatchNet		91.91 170	91.35 163	93.59 218	95.38 196	84.11 280	93.15 300	95.39 252	89.54 159	92.10 138	93.68 260	82.82 157	98.13 193	84.81 229	95.32 142	98.52 98
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 198	91.32 165	91.79 277	95.15 212	79.20 318	93.42 294	95.37 254	88.55 198	93.49 103	93.67 261	82.49 165	98.27 184	90.41 132	89.34 233	97.90 132

Anonymous20231206		87.09 282	86.14 280	89.93 305	91.22 317	80.35 307	96.11 219	95.35 255	83.57 290	84.16 285	93.02 276	73.54 287	95.61 316	72.16 320	86.14 257	93.84 294

MIMVSNet1		84.93 296	83.05 296	90.56 298	89.56 325	84.84 274	95.40 253	95.35 255	83.91 284	80.38 314	92.21 293	57.23 332	93.34 330	70.69 326	82.75 301	93.50 296

TDRefinement		86.53 285	84.76 290	91.85 274	82.23 341	84.25 277	96.38 199	95.35 255	84.97 274	84.09 287	94.94 195	65.76 320	98.34 180	84.60 236	74.52 330	92.97 302

TR-MVS		91.48 196	90.59 201	94.16 183	96.40 159	87.33 235	95.67 240	95.34 258	87.68 228	91.46 149	95.52 176	76.77 263	98.35 178	82.85 259	93.61 174	96.79 171

EPNet_dtu		91.71 176	91.28 167	92.99 242	93.76 278	83.71 283	96.69 173	95.28 259	93.15 64	87.02 264	95.95 149	83.37 131	97.38 280	79.46 297	96.84 115	97.88 134
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 281	85.79 282	91.78 278	94.80 230	87.28 236	95.49 250	95.28 259	84.09 283	83.85 290	91.82 295	62.95 324	94.17 326	78.48 301	85.34 265	93.91 293

MDTV_nov1_ep13			90.76 188		95.22 208	80.33 308	93.03 303	95.28 259	88.14 218	92.84 126	93.83 255	81.34 186	98.08 200	82.86 258	94.34 155

LF4IMVS		87.94 275	87.25 267	89.98 304	92.38 311	80.05 313	94.38 274	95.25 262	87.59 230	84.34 282	94.74 210	64.31 322	97.66 261	84.83 228	87.45 249	92.23 322

TransMVSNet (Re)		88.94 255	87.56 258	93.08 240	94.35 245	88.45 198	97.73 58	95.23 263	87.47 231	84.26 284	95.29 186	79.86 213	97.33 282	79.44 298	74.44 332	93.45 298

test20.03		86.14 289	85.40 285	88.35 307	90.12 320	80.06 312	95.90 231	95.20 264	88.59 195	81.29 301	93.62 263	71.43 294	92.65 332	71.26 324	81.17 307	92.34 321

new-patchmatchnet		83.18 300	81.87 301	87.11 313	86.88 333	75.99 325	93.70 288	95.18 265	85.02 273	77.30 325	88.40 322	65.99 318	93.88 328	74.19 316	70.18 336	91.47 330

MDA-MVSNet_test_wron		85.87 291	84.23 293	90.80 295	92.38 311	82.57 290	93.17 298	95.15 266	82.15 299	67.65 335	92.33 292	78.20 245	95.51 319	77.33 305	79.74 310	94.31 288

YYNet1		85.87 291	84.23 293	90.78 296	92.38 311	82.46 292	93.17 298	95.14 267	82.12 300	67.69 334	92.36 289	78.16 248	95.50 320	77.31 306	79.73 311	94.39 284

Baseline_NR-MVSNet		91.20 208	90.62 199	92.95 243	93.83 276	88.03 220	97.01 135	95.12 268	88.42 207	89.70 206	95.13 193	83.47 129	97.44 274	89.66 141	83.24 296	93.37 300

thres200		92.23 161	91.39 162	94.75 160	97.61 109	89.03 187	96.60 183	95.09 269	92.08 101	93.28 110	94.00 250	78.39 244	99.04 124	81.26 288	94.18 156	96.19 188

tpmp4_e23		89.58 249	88.59 249	92.54 254	95.16 211	81.53 298	94.11 282	95.09 269	81.66 303	88.60 232	93.44 271	75.11 273	98.33 181	82.45 264	91.72 202	97.75 139

ADS-MVSNet		89.89 244	88.68 248	93.53 222	95.86 179	84.89 273	90.93 321	95.07 271	83.23 293	91.28 159	91.81 296	79.01 228	97.85 244	79.52 295	91.39 209	97.84 135

pmmvs-eth3d		86.22 288	84.45 291	91.53 283	88.34 328	87.25 238	94.47 273	95.01 272	83.47 291	79.51 321	89.61 310	69.75 304	95.71 315	83.13 255	76.73 318	91.64 326

MDA-MVSNet-bldmvs		85.00 295	82.95 297	91.17 288	93.13 301	83.33 287	94.56 271	95.00 273	84.57 279	65.13 339	92.65 280	70.45 300	95.85 312	73.57 317	77.49 315	94.33 286

RPMNet		88.52 265	86.72 277	93.95 194	94.45 242	87.19 241	90.23 326	94.99 274	77.87 325	92.40 129	87.55 330	80.17 210	97.05 288	68.84 327	93.95 167	97.60 148

ambc				86.56 316	83.60 338	70.00 336	85.69 339	94.97 275		80.60 309	88.45 321	37.42 346	96.84 295	82.69 262	75.44 321	92.86 303

testgi		87.97 274	87.21 271	90.24 302	92.86 303	80.76 302	96.67 175	94.97 275	91.74 108	85.52 275	95.83 155	62.66 325	94.47 325	76.25 309	88.36 243	95.48 221

dp		88.90 257	88.26 255	90.81 293	94.58 239	76.62 323	92.85 305	94.93 277	85.12 271	90.07 192	93.07 275	75.81 267	98.12 195	80.53 291	87.42 251	97.71 141

test_0402		86.46 286	84.79 289	91.45 284	95.02 219	85.55 264	96.29 208	94.89 278	80.90 309	82.21 293	93.97 251	68.21 310	97.29 284	62.98 333	88.68 241	91.51 328

tfpn200view9		92.38 153	91.52 159	94.95 148	97.85 97	89.29 180	97.41 98	94.88 279	92.19 93	93.27 111	94.46 221	78.17 246	99.08 119	81.40 276	94.08 157	96.48 182

CVMVSNet		91.23 207	91.75 144	89.67 306	95.77 184	74.69 326	96.44 189	94.88 279	85.81 263	92.18 136	97.64 75	79.07 223	95.58 318	88.06 171	95.86 136	98.74 86

thres400		92.42 151	91.52 159	95.12 138	97.85 97	89.29 180	97.41 98	94.88 279	92.19 93	93.27 111	94.46 221	78.17 246	99.08 119	81.40 276	94.08 157	96.98 159

EPNet		95.20 67	94.56 72	97.14 54	92.80 305	92.68 65	97.85 48	94.87 282	96.64 1	92.46 128	97.80 63	86.23 99	99.65 41	93.72 80	98.62 74	99.10 61
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SixPastTwentyTwo		89.15 254	88.54 251	90.98 289	93.49 286	80.28 310	96.70 171	94.70 283	90.78 131	84.15 286	95.57 172	71.78 292	97.71 257	84.63 233	85.07 272	94.94 258

tfpn111		92.45 148	91.58 154	95.06 139	97.92 91	89.37 174	97.71 62	94.66 284	92.20 90	93.31 107	94.90 198	78.06 253	99.11 108	81.37 280	94.06 161	96.70 174

conf200view11		92.45 148	91.58 154	95.05 140	97.92 91	89.37 174	97.71 62	94.66 284	92.20 90	93.31 107	94.90 198	78.06 253	99.08 119	81.40 276	94.08 157	96.70 174

thres100view900		92.43 150	91.58 154	94.98 145	97.92 91	89.37 174	97.71 62	94.66 284	92.20 90	93.31 107	94.90 198	78.06 253	99.08 119	81.40 276	94.08 157	96.48 182

thres600view7		92.49 147	91.60 153	95.18 130	97.91 94	89.47 165	97.65 69	94.66 284	92.18 95	93.33 106	94.91 197	78.06 253	99.10 114	81.61 269	94.06 161	96.98 159

PatchT		88.87 258	87.42 263	93.22 236	94.08 264	85.10 269	89.51 330	94.64 288	81.92 301	92.36 132	88.15 325	80.05 211	97.01 292	72.43 319	93.65 172	97.54 151

view600		92.55 141	91.68 147	95.18 130	97.98 83	89.44 169	98.00 36	94.57 289	92.09 96	93.17 114	95.52 176	78.14 249	99.11 108	81.61 269	94.04 163	96.98 159

view800		92.55 141	91.68 147	95.18 130	97.98 83	89.44 169	98.00 36	94.57 289	92.09 96	93.17 114	95.52 176	78.14 249	99.11 108	81.61 269	94.04 163	96.98 159

conf0.05thres1000		92.55 141	91.68 147	95.18 130	97.98 83	89.44 169	98.00 36	94.57 289	92.09 96	93.17 114	95.52 176	78.14 249	99.11 108	81.61 269	94.04 163	96.98 159

tfpn		92.55 141	91.68 147	95.18 130	97.98 83	89.44 169	98.00 36	94.57 289	92.09 96	93.17 114	95.52 176	78.14 249	99.11 108	81.61 269	94.04 163	96.98 159

Gipuma		67.86 318	65.41 319	75.18 331	92.66 308	73.45 329	66.50 349	94.52 293	53.33 344	57.80 343	66.07 346	30.81 348	89.20 342	48.15 347	78.88 313	62.90 348
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CostFormer		91.18 211	90.70 191	92.62 253	94.84 228	81.76 297	94.09 283	94.43 294	84.15 282	92.72 127	93.77 258	79.43 219	98.20 187	90.70 131	92.18 195	97.90 132

tpm2		89.96 242	89.21 241	92.23 261	94.91 226	81.25 300	93.78 287	94.42 295	80.62 313	91.56 147	93.44 271	76.44 265	97.94 234	85.60 220	92.08 199	97.49 152

JIA-IIPM		88.26 273	87.04 274	91.91 272	93.52 284	81.42 299	89.38 331	94.38 296	80.84 311	90.93 170	80.74 337	79.22 222	97.92 238	82.76 260	91.62 204	96.38 185

Patchmatch-test		89.42 252	87.99 256	93.70 212	95.27 203	85.11 268	88.98 332	94.37 297	81.11 308	87.10 262	93.69 259	82.28 170	97.50 270	74.37 314	94.76 150	98.48 106

LCM-MVSNet		72.55 313	69.39 316	82.03 321	70.81 351	65.42 342	90.12 328	94.36 298	55.02 343	65.88 338	81.72 336	24.16 355	89.96 340	74.32 315	68.10 339	90.71 332

ADS-MVSNet2		89.45 251	88.59 249	92.03 270	95.86 179	82.26 294	90.93 321	94.32 299	83.23 293	91.28 159	91.81 296	79.01 228	95.99 310	79.52 295	91.39 209	97.84 135

DWT-MVSNet_test		90.76 221	89.89 224	93.38 229	95.04 218	83.70 284	95.85 233	94.30 300	88.19 215	90.46 175	92.80 278	73.61 286	98.50 162	88.16 169	90.58 220	97.95 130

testus		82.63 303	82.15 299	84.07 319	87.31 332	67.67 338	93.18 296	94.29 301	82.47 297	82.14 295	90.69 301	53.01 339	91.94 335	66.30 330	89.96 228	92.62 308

LP		84.13 298	81.85 303	90.97 290	93.20 298	82.12 295	87.68 336	94.27 302	76.80 326	81.93 296	88.52 320	72.97 289	95.95 311	59.53 338	81.73 303	94.84 264

EU-MVSNet		88.72 259	88.90 245	88.20 309	93.15 300	74.21 327	96.63 180	94.22 303	85.18 269	87.32 257	95.97 147	76.16 266	94.98 323	85.27 224	86.17 256	95.41 227

test1235678		79.82 308	78.53 309	83.69 320	82.55 340	67.55 339	92.50 310	94.13 304	79.28 317	72.10 332	86.45 333	57.27 331	90.68 339	61.60 336	80.90 308	92.82 304

MIMVSNet		88.50 267	86.76 275	93.72 211	94.84 228	87.77 230	91.39 316	94.05 305	86.41 256	87.99 244	92.59 282	63.27 323	95.82 314	77.44 304	92.84 186	97.57 150

OpenMVS_ROB	81.14 20	84.42 297	82.28 298	90.83 292	90.06 321	84.05 281	95.73 239	94.04 306	73.89 334	80.17 319	91.53 300	59.15 330	97.64 262	66.92 329	89.05 235	90.80 331

TinyColmap		86.82 284	85.35 286	91.21 287	94.91 226	82.99 289	93.94 285	94.02 307	83.58 289	81.56 300	94.68 211	62.34 326	98.13 193	75.78 310	87.35 253	92.52 310

IB-MVS	87.33 17	89.91 243	88.28 254	94.79 158	95.26 206	87.70 232	95.12 264	93.95 308	89.35 164	87.03 263	92.49 284	70.74 299	99.19 99	89.18 152	81.37 306	97.49 152
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		78.22 311	75.30 312	86.99 315	86.14 334	74.16 328	95.62 244	93.88 309	66.43 338	74.44 328	87.86 327	41.39 345	95.11 322	62.49 334	69.46 338	91.71 325

1111		78.29 310	77.55 310	80.50 323	83.89 336	59.98 346	91.89 313	93.71 310	75.06 329	73.60 330	87.67 328	55.66 335	92.60 333	58.54 340	77.92 314	88.93 335

.test1245		65.38 319	69.22 317	53.86 339	83.89 336	59.98 346	91.89 313	93.71 310	75.06 329	73.60 330	87.67 328	55.66 335	92.60 333	58.54 340	2.96 353	9.00 353

LCM-MVSNet-Re		92.50 145	92.52 127	92.44 255	96.82 140	81.89 296	96.92 145	93.71 310	92.41 86	84.30 283	94.60 215	85.08 113	97.03 290	91.51 120	97.36 105	98.40 114

test2356		82.77 302	82.14 300	84.65 318	85.77 335	70.36 333	91.22 319	93.69 313	81.58 305	81.82 297	89.00 318	60.63 329	90.77 338	64.74 331	90.80 218	92.82 304

tpm		90.25 236	89.74 232	91.76 280	93.92 272	79.73 314	93.98 284	93.54 314	88.28 211	91.99 140	93.25 274	77.51 261	97.44 274	87.30 193	87.94 245	98.12 124

LFMVS		93.60 109	92.63 120	96.52 70	98.13 79	91.27 104	97.94 41	93.39 315	90.57 144	96.29 46	98.31 33	69.00 305	99.16 103	94.18 69	95.87 135	99.12 59

Patchmatch-RL test		87.38 279	86.24 278	90.81 293	88.74 327	78.40 321	88.12 335	93.17 316	87.11 240	82.17 294	89.29 316	81.95 178	95.60 317	88.64 166	77.02 316	98.41 113

conf0.01		91.74 174	90.67 193	94.94 151	97.55 114	89.68 149	97.64 73	93.14 317	88.43 201	91.24 161	94.30 233	78.91 231	98.45 166	81.28 282	93.57 177	96.70 174

conf0.002		91.74 174	90.67 193	94.94 151	97.55 114	89.68 149	97.64 73	93.14 317	88.43 201	91.24 161	94.30 233	78.91 231	98.45 166	81.28 282	93.57 177	96.70 174

thresconf0.02		91.69 181	90.67 193	94.75 160	97.55 114	89.68 149	97.64 73	93.14 317	88.43 201	91.24 161	94.30 233	78.91 231	98.45 166	81.28 282	93.57 177	96.11 194

tfpn_n400		91.69 181	90.67 193	94.75 160	97.55 114	89.68 149	97.64 73	93.14 317	88.43 201	91.24 161	94.30 233	78.91 231	98.45 166	81.28 282	93.57 177	96.11 194

tfpnconf		91.69 181	90.67 193	94.75 160	97.55 114	89.68 149	97.64 73	93.14 317	88.43 201	91.24 161	94.30 233	78.91 231	98.45 166	81.28 282	93.57 177	96.11 194

tfpnview11		91.69 181	90.67 193	94.75 160	97.55 114	89.68 149	97.64 73	93.14 317	88.43 201	91.24 161	94.30 233	78.91 231	98.45 166	81.28 282	93.57 177	96.11 194

test-LLR		91.42 199	91.19 172	92.12 267	94.59 237	80.66 303	94.29 277	92.98 323	91.11 126	90.76 171	92.37 286	79.02 226	98.07 204	88.81 163	96.74 119	97.63 143

test-mter		90.19 239	89.54 236	92.12 267	94.59 237	80.66 303	94.29 277	92.98 323	87.68 228	90.76 171	92.37 286	67.67 311	98.07 204	88.81 163	96.74 119	97.63 143

tfpn_ndepth		91.88 172	90.96 178	94.62 165	97.73 103	89.93 143	97.75 54	92.92 325	88.93 184	91.73 144	93.80 257	78.91 231	98.49 165	83.02 257	93.86 170	95.45 225

tfpn1000		91.99 169	91.05 174	94.80 156	97.78 100	89.66 155	97.91 43	92.90 326	88.99 179	91.73 144	94.84 203	78.99 230	98.33 181	82.41 265	93.91 169	96.40 184

test12356		74.97 312	74.13 313	77.49 328	78.81 342	56.23 350	88.53 334	92.75 327	75.14 328	67.50 336	85.07 334	44.88 343	89.96 340	58.71 339	75.75 320	86.26 336

test0.0.03 1		89.37 253	88.70 247	91.41 286	92.47 310	85.63 263	95.22 262	92.70 328	91.11 126	86.91 266	93.65 262	79.02 226	93.19 331	78.00 303	89.18 234	95.41 227

new_pmnet		82.89 301	81.12 306	88.18 310	89.63 324	80.18 311	91.77 315	92.57 329	76.79 327	75.56 327	88.23 324	61.22 328	94.48 324	71.43 322	82.92 299	89.87 333

testmv		72.22 314	70.02 314	78.82 326	73.06 349	61.75 344	91.24 318	92.31 330	74.45 332	61.06 341	80.51 338	34.21 347	88.63 343	55.31 343	68.07 340	86.06 337

K. test v3		87.64 278	86.75 276	90.32 301	93.02 302	79.48 316	96.61 181	92.08 331	90.66 137	80.25 318	94.09 248	67.21 315	96.65 296	85.96 215	80.83 309	94.83 266

TESTMET0.1,1		90.06 241	89.42 238	91.97 271	94.41 244	80.62 305	94.29 277	91.97 332	87.28 237	90.44 176	92.47 285	68.79 306	97.67 259	88.50 167	96.60 124	97.61 147

PM-MVS		83.48 299	81.86 302	88.31 308	87.83 330	77.59 322	93.43 293	91.75 333	86.91 248	80.63 308	89.91 304	44.42 344	95.84 313	85.17 227	76.73 318	91.50 329

FPMVS		71.27 315	69.85 315	75.50 330	74.64 344	59.03 348	91.30 317	91.50 334	58.80 342	57.92 342	88.28 323	29.98 351	85.53 346	53.43 344	82.84 300	81.95 340

door								91.13 335

door-mid								91.06 336

pmmvs3		79.97 307	77.50 311	87.39 312	82.80 339	79.38 317	92.70 307	90.75 337	70.69 337	78.66 322	87.47 331	51.34 341	93.40 329	73.39 318	69.65 337	89.38 334

no-one		68.12 317	63.78 320	81.13 322	74.01 346	70.22 335	87.61 337	90.71 338	72.63 336	53.13 344	71.89 343	30.29 349	91.45 336	61.53 337	32.21 347	81.72 341

DSMNet-mixed		86.34 287	86.12 281	87.00 314	89.88 323	70.43 332	94.93 266	90.08 339	77.97 324	85.42 278	92.78 279	74.44 279	93.96 327	74.43 313	95.14 144	96.62 178

testpf		80.97 306	81.40 304	79.65 325	91.53 315	72.43 331	73.47 347	89.55 340	78.63 320	80.81 303	89.06 317	61.36 327	91.36 337	83.34 252	84.89 279	75.15 344

MVS-HIRNet		82.47 304	81.21 305	86.26 317	95.38 196	69.21 337	88.96 333	89.49 341	66.28 339	80.79 304	74.08 342	68.48 308	97.39 279	71.93 321	95.47 140	92.18 323

EPMVS		90.70 227	89.81 228	93.37 230	94.73 233	84.21 278	93.67 290	88.02 342	89.50 161	92.38 131	93.49 268	77.82 259	97.78 251	86.03 213	92.68 187	98.11 127

ANet_high		63.94 320	59.58 321	77.02 329	61.24 354	66.06 340	85.66 340	87.93 343	78.53 322	42.94 346	71.04 344	25.42 354	80.71 348	52.60 345	30.83 349	84.28 339

PMMVS2		70.19 316	66.92 318	80.01 324	76.35 343	65.67 341	86.22 338	87.58 344	64.83 341	62.38 340	80.29 339	26.78 353	88.49 344	63.79 332	54.07 343	85.88 338

lessismore_v0				90.45 299	91.96 314	79.09 319		87.19 345		80.32 316	94.39 226	66.31 317	97.55 267	84.00 246	76.84 317	94.70 275

PMVS	53.92 22	58.58 322	55.40 323	68.12 335	51.00 355	48.64 352	78.86 345	87.10 346	46.77 347	35.84 351	74.28 341	8.76 357	86.34 345	42.07 348	73.91 333	69.38 346
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuykxyi23d		56.92 323	51.11 327	74.38 333	62.30 353	61.47 345	80.09 344	84.87 347	49.62 346	30.80 352	57.20 350	7.03 358	82.94 347	55.69 342	32.36 346	78.72 343

gg-mvs-nofinetune		87.82 276	85.61 283	94.44 173	94.46 241	89.27 183	91.21 320	84.61 348	80.88 310	89.89 196	74.98 340	71.50 293	97.53 268	85.75 218	97.21 109	96.51 180

GG-mvs-BLEND				93.62 216	93.69 280	89.20 184	92.39 312	83.33 349		87.98 245	89.84 305	71.00 297	96.87 294	82.08 268	95.40 141	94.80 270

PNet_i23d		59.01 321	55.87 322	68.44 334	73.98 347	51.37 351	81.36 343	82.41 350	52.37 345	42.49 348	70.39 345	11.39 356	79.99 350	49.77 346	38.71 345	73.97 345

MTMP								82.03 351

DeepMVS_CX				74.68 332	90.84 318	64.34 343		81.61 352	65.34 340	67.47 337	88.01 326	48.60 342	80.13 349	62.33 335	73.68 334	79.58 342

E-PMN		53.28 324	52.56 325	55.43 337	74.43 345	47.13 353	83.63 342	76.30 353	42.23 348	42.59 347	62.22 348	28.57 352	74.40 351	31.53 350	31.51 348	44.78 349

EMVS		52.08 326	51.31 326	54.39 338	72.62 350	45.39 355	83.84 341	75.51 354	41.13 349	40.77 349	59.65 349	30.08 350	73.60 352	28.31 351	29.90 350	44.18 350

MVE	50.73 23	53.25 325	48.81 328	66.58 336	65.34 352	57.50 349	72.49 348	70.94 355	40.15 350	39.28 350	63.51 347	6.89 360	73.48 353	38.29 349	42.38 344	68.76 347
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 327	53.82 324	46.29 340	33.73 356	45.30 356	78.32 346	67.24 356	18.02 351	50.93 345	87.05 332	52.99 340	53.11 354	70.76 325	25.29 351	40.46 351

N_pmnet		78.73 309	78.71 308	78.79 327	92.80 305	46.50 354	94.14 281	43.71 357	78.61 321	80.83 302	91.66 299	74.94 277	96.36 298	67.24 328	84.45 283	93.50 296

wuyk23d		25.11 329	24.57 331	26.74 342	73.98 347	39.89 357	57.88 350	9.80 358	12.27 352	10.39 353	6.97 356	7.03 358	36.44 355	25.43 352	17.39 352	3.89 355

testmvs		13.36 331	16.33 332	4.48 344	5.04 357	2.26 359	93.18 296	3.28 359	2.70 353	8.24 354	21.66 352	2.29 362	2.19 356	7.58 353	2.96 353	9.00 353

test123		13.04 332	15.66 333	5.18 343	4.51 358	3.45 358	92.50 310	1.81 360	2.50 354	7.58 355	20.15 353	3.67 361	2.18 357	7.13 354	1.07 355	9.90 352

pcd_1.5k_mvsjas		7.39 334	9.85 335	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	88.65 70	0.00 358	0.00 355	0.00 356	0.00 356

sosnet-low-res		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

sosnet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

uncertanet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

Regformer		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

n2								0.00 361

nn								0.00 361

ab-mvs-re		8.06 333	10.74 334	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	96.69 114	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

uanet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

GSMVS																98.45 109

test_part3							97.50 90		93.81 45		98.53 11		99.87 5	95.19 47

test_part2					99.28 17	95.74 3				98.10 6

sam_mvs1												82.76 158				98.45 109

sam_mvs												81.94 179

test_post1							92.81 306				16.58 355	80.53 202	97.68 258	86.20 208

test_post											17.58 354	81.76 181	98.08 200

patchmatchnet-post											90.45 302	82.65 162	98.10 197

gm-plane-assit					93.22 296	78.89 320			84.82 276		93.52 266		98.64 149	87.72 178

test9_res														94.81 62	99.38 35	99.45 30

agg_prior2														93.94 74	99.38 35	99.50 24

test_prior4						93.66 41	96.42 192

test_prior2							96.35 201		92.80 79	96.03 54	97.59 79	92.01 30		95.01 55	99.38 35

旧先验2							95.94 229		81.66 303	97.34 17			98.82 137	92.26 97

新几何2							95.79 236

原ACMM2							95.67 240

testdata2													99.67 39	85.96 215

segment_acmp												92.89 12

testdata1							95.26 261		93.10 67

plane_prior7					96.21 165	89.98 139

plane_prior6					96.10 175	90.00 135						81.32 187

plane_prior4											96.64 117

plane_prior3						90.00 135			94.46 30	91.34 153

plane_prior2							97.74 56		94.85 17

plane_prior1					96.14 173

plane_prior						89.99 137	97.24 114		94.06 38						92.16 196

HQP5-MVS						89.33 177

HQP-NCC					95.86 179		96.65 176		93.55 50	90.14 181

ACMP_Plane					95.86 179		96.65 176		93.55 50	90.14 181

BP-MVS														92.13 103

HQP4-MVS										90.14 181			98.50 162			95.78 211

HQP2-MVS												80.95 192

NP-MVS					95.99 178	89.81 146					95.87 152

MDTV_nov1_ep13_2view						70.35 334	93.10 302		83.88 286	93.55 101		82.47 167		86.25 207		98.38 117

ACMMP++_ref															90.30 225

ACMMP++															91.02 215

Test By Simon												88.73 69

High-resolution multi-view benchmark