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.

thres200		88.92 101	87.65 106	92.73 81	96.30 80	85.62 34	97.85 35	98.86 1	84.38 117	84.82 117	93.99 144	75.12 131	98.01 115	70.86 226	86.67 152	94.56 175

tfpn111		88.08 121	86.70 129	92.20 101	96.10 85	84.90 47	97.14 84	98.85 2	82.69 152	83.41 134	93.66 150	75.43 121	97.82 126	67.13 251	85.88 162	93.89 183

conf200view11		88.27 119	86.95 125	92.24 98	96.10 85	84.90 47	97.14 84	98.85 2	82.69 152	83.41 134	93.66 150	75.43 121	97.93 117	69.04 236	86.24 157	93.89 183

thres100view900		88.30 117	86.95 125	92.33 96	96.10 85	84.90 47	97.14 84	98.85 2	82.69 152	83.41 134	93.66 150	75.43 121	97.93 117	69.04 236	86.24 157	94.17 176

tfpn200view9		88.48 112	87.15 120	92.47 90	96.21 81	85.30 39	97.44 62	98.85 2	83.37 140	83.99 127	93.82 147	75.36 126	97.93 117	69.04 236	86.24 157	94.17 176

view600		87.45 133	85.98 136	91.88 112	95.90 92	84.52 53	96.68 121	98.85 2	81.85 164	82.30 147	93.39 154	75.44 117	97.66 130	64.02 270	85.36 169	93.45 192

view800		87.45 133	85.98 136	91.88 112	95.90 92	84.52 53	96.68 121	98.85 2	81.85 164	82.30 147	93.39 154	75.44 117	97.66 130	64.02 270	85.36 169	93.45 192

conf0.05thres1000		87.45 133	85.98 136	91.88 112	95.90 92	84.52 53	96.68 121	98.85 2	81.85 164	82.30 147	93.39 154	75.44 117	97.66 130	64.02 270	85.36 169	93.45 192

tfpn		87.45 133	85.98 136	91.88 112	95.90 92	84.52 53	96.68 121	98.85 2	81.85 164	82.30 147	93.39 154	75.44 117	97.66 130	64.02 270	85.36 169	93.45 192

thres600view7		88.06 122	86.70 129	92.15 103	96.10 85	85.17 41	97.14 84	98.85 2	82.70 151	83.41 134	93.66 150	75.43 121	97.82 126	67.13 251	85.88 162	93.45 192

thres400		88.42 115	87.15 120	92.23 99	96.21 81	85.30 39	97.44 62	98.85 2	83.37 140	83.99 127	93.82 147	75.36 126	97.93 117	69.04 236	86.24 157	93.45 192

MVS_111021_HR		93.41 32	93.39 29	93.47 58	97.34 69	82.83 86	97.56 56	98.27 12	89.16 36	89.71 73	97.14 75	79.77 61	99.56 41	93.65 32	97.94 46	98.02 60

sss		90.87 71	89.96 74	93.60 47	94.15 142	83.84 66	97.14 84	98.13 13	85.93 78	89.68 74	96.09 97	71.67 153	99.30 57	87.69 92	89.16 133	97.66 86

MG-MVS		94.25 17	93.72 24	95.85 7	99.38 3	89.35 6	97.98 32	98.09 14	89.99 29	92.34 46	96.97 81	81.30 47	98.99 85	88.54 82	98.88 14	99.20 8

VNet		92.11 53	91.22 60	94.79 17	96.91 75	86.98 22	97.91 33	97.96 15	86.38 71	93.65 34	95.74 101	70.16 169	98.95 89	93.39 35	88.87 136	98.43 35

WTY-MVS		92.65 47	91.68 55	95.56 9	96.00 89	88.90 8	98.23 22	97.65 16	88.57 40	89.82 72	97.22 73	79.29 63	99.06 81	89.57 74	88.73 138	98.73 25

EPNet		94.06 22	94.15 21	93.76 38	97.27 71	84.35 57	98.29 20	97.64 17	94.57 4	95.36 12	96.88 84	79.96 60	99.12 78	91.30 56	96.11 76	97.82 77
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	84.06 6	91.63 60	90.37 68	95.39 12	96.12 84	88.25 10	90.22 279	97.58 18	88.33 46	90.50 67	91.96 170	79.26 65	99.06 81	90.29 67	89.07 134	98.88 18

PVSNet	82.34 9	89.02 98	87.79 104	92.71 82	95.49 104	81.50 114	97.70 48	97.29 19	87.76 56	85.47 112	95.12 126	56.90 269	98.90 93	80.33 144	94.02 95	97.71 83

PGM-MVS		91.93 55	91.80 53	92.32 97	98.27 41	79.74 153	95.28 185	97.27 20	83.83 132	90.89 65	97.78 48	76.12 107	99.56 41	88.82 80	97.93 48	97.66 86

IB-MVS	85.34 4	88.67 108	87.14 122	93.26 61	93.12 164	84.32 58	98.76 10	97.27 20	87.19 65	79.36 187	90.45 192	83.92 28	98.53 101	84.41 113	69.79 268	96.93 120
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
MVS		90.60 75	88.64 93	96.50 1	94.25 140	90.53 4	93.33 234	97.21 22	77.59 233	78.88 190	97.31 68	71.52 156	99.69 27	89.60 73	98.03 44	99.27 6

CSCG		92.02 54	91.65 56	93.12 66	98.53 28	80.59 131	97.47 61	97.18 23	77.06 242	84.64 122	97.98 38	83.98 27	99.52 43	90.72 63	97.33 60	99.23 7

PHI-MVS		93.59 30	93.63 25	93.48 55	98.05 47	81.76 107	98.64 13	97.13 24	82.60 155	94.09 31	98.49 9	80.35 52	99.85 10	94.74 24	98.62 23	98.83 19

CNVR-MVS		96.30 1	96.54 1	95.55 10	99.31 5	87.69 17	99.06 5	97.12 25	94.66 3	96.79 3	98.78 4	86.42 12	99.95 2	97.59 4	99.18 3	99.00 14

conf0.01		85.70 167	84.35 163	89.77 174	94.53 128	79.70 155	95.17 189	97.11 26	75.97 245	79.44 180	95.31 111	81.90 40	95.73 225	56.78 299	82.91 193	93.89 183

conf0.002		85.70 167	84.35 163	89.77 174	94.53 128	79.70 155	95.17 189	97.11 26	75.97 245	79.44 180	95.31 111	81.90 40	95.73 225	56.78 299	82.91 193	93.89 183

thresconf0.02		85.80 160	84.35 163	90.17 155	94.53 128	79.70 155	95.17 189	97.11 26	75.97 245	79.44 180	95.31 111	81.90 40	95.73 225	56.78 299	82.91 193	95.09 163

tfpn_n400		85.80 160	84.35 163	90.17 155	94.53 128	79.70 155	95.17 189	97.11 26	75.97 245	79.44 180	95.31 111	81.90 40	95.73 225	56.78 299	82.91 193	95.09 163

tfpnconf		85.80 160	84.35 163	90.17 155	94.53 128	79.70 155	95.17 189	97.11 26	75.97 245	79.44 180	95.31 111	81.90 40	95.73 225	56.78 299	82.91 193	95.09 163

tfpnview11		85.80 160	84.35 163	90.17 155	94.53 128	79.70 155	95.17 189	97.11 26	75.97 245	79.44 180	95.31 111	81.90 40	95.73 225	56.78 299	82.91 193	95.09 163

MCST-MVS		96.17 2	96.12 4	96.32 3	99.42 2	89.36 5	98.94 9	97.10 32	95.17 2	92.11 47	98.46 10	87.33 8	99.97 1	97.21 6	99.31 1	99.63 2

tfpn1000		86.43 152	85.10 150	90.41 148	95.56 102	80.51 136	95.90 168	97.09 33	75.91 251	80.02 177	94.82 131	84.78 17	95.47 242	57.36 294	84.46 178	95.26 162

tfpn_ndepth		87.25 138	86.00 135	91.01 137	95.86 96	81.46 115	96.53 128	97.09 33	77.35 237	81.36 161	95.07 128	84.74 18	95.86 214	60.88 285	85.14 175	95.72 152

VPA-MVSNet		85.32 172	83.83 173	89.77 174	90.25 216	82.63 89	96.36 143	97.07 35	83.03 146	81.21 164	89.02 208	61.58 236	96.31 189	85.02 110	70.95 253	90.36 211

Regformer-1		94.00 24	94.04 22	93.87 35	98.41 34	84.29 59	97.43 65	97.04 36	89.50 33	92.75 43	98.13 23	82.60 36	99.26 60	93.55 33	96.99 64	98.06 57

DELS-MVS		94.98 7	94.49 13	96.44 2	96.42 79	90.59 3	99.21 2	97.02 37	94.40 5	91.46 54	97.08 78	83.32 32	99.69 27	92.83 43	98.70 21	99.04 12
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
GG-mvs-BLEND				93.49 54	94.94 119	86.26 25	81.62 322	97.00 38		88.32 92	94.30 139	91.23 2	96.21 194	88.49 84	97.43 56	98.00 65

Regformer-2		93.92 25	94.01 23	93.67 43	98.41 34	83.75 67	97.43 65	97.00 38	89.43 35	92.69 44	98.13 23	82.48 37	99.22 63	93.51 34	96.99 64	98.04 58

Regformer-3		93.19 33	93.19 32	93.19 64	98.10 45	83.01 83	97.08 95	96.98 40	88.98 37	91.35 59	97.89 43	80.80 49	99.23 61	92.30 49	95.20 86	97.32 105

gg-mvs-nofinetune		85.48 171	82.90 187	93.24 62	94.51 136	85.82 30	79.22 326	96.97 41	61.19 323	87.33 100	53.01 340	90.58 3	96.07 198	86.07 102	97.23 61	97.81 78

NCCC		95.63 3	95.94 5	94.69 20	99.21 6	85.15 42	99.16 3	96.96 42	94.11 6	95.59 11	98.64 6	85.07 15	99.91 3	95.61 18	99.10 5	99.00 14

FIs		86.73 148	86.10 134	88.61 191	90.05 221	80.21 143	96.14 156	96.95 43	85.56 87	78.37 194	92.30 166	76.73 98	95.28 250	79.51 152	79.27 216	90.35 212

PVSNet_0	77.72 15	81.70 226	78.95 236	89.94 168	90.77 210	76.72 238	95.96 162	96.95 43	85.01 100	70.24 266	88.53 215	52.32 290	98.20 112	86.68 101	44.08 340	94.89 168

HPM-MVS++		95.32 5	95.48 7	94.85 16	98.62 24	86.04 27	97.81 39	96.93 45	92.45 11	95.69 10	98.50 8	85.38 14	99.85 10	94.75 23	99.18 3	98.65 28

MSLP-MVS++		94.28 15	94.39 16	93.97 32	98.30 40	84.06 62	98.64 13	96.93 45	90.71 22	93.08 39	98.70 5	79.98 59	99.21 65	94.12 30	99.07 6	98.63 29

Regformer-4		93.06 36	93.12 33	92.89 74	98.10 45	82.20 96	97.08 95	96.92 47	88.87 39	91.23 61	97.89 43	80.57 51	99.19 70	92.21 51	95.20 86	97.29 110

UniMVSNet (Re)		85.31 173	84.23 170	88.55 192	89.75 224	80.55 133	96.72 116	96.89 48	85.42 88	78.40 193	88.93 209	75.38 125	95.52 239	78.58 159	68.02 283	89.57 227

FC-MVSNet-test		85.96 156	85.39 144	87.66 215	89.38 233	78.02 214	95.65 178	96.87 49	85.12 96	77.34 206	91.94 172	76.28 105	94.74 264	77.09 177	78.82 219	90.21 215

EI-MVSNet-Vis-set		91.84 57	91.77 54	92.04 107	97.60 57	81.17 119	96.61 125	96.87 49	88.20 48	89.19 82	97.55 60	78.69 74	99.14 76	90.29 67	90.94 126	95.80 149

EI-MVSNet-UG-set		91.35 66	91.22 60	91.73 119	97.39 65	80.68 129	96.47 131	96.83 51	87.92 52	88.30 93	97.36 67	77.84 84	99.13 77	89.43 77	89.45 132	95.37 159

无先验							96.87 109	96.78 52	77.39 235				99.52 43	79.95 149		98.43 35

test_part1								96.77 53				89.33 6			98.95 12	99.18 10

ESAPD		95.32 5	95.52 6	94.70 19	98.90 7	85.14 43	98.15 25	96.77 53	84.95 101	96.07 7	98.83 2	89.33 6	99.80 13	97.78 2	98.95 12	99.18 10

MVS_111021_LR		91.60 62	91.64 57	91.47 124	95.74 99	78.79 192	96.15 155	96.77 53	88.49 43	88.64 88	97.07 79	72.33 149	99.19 70	93.13 41	96.48 73	96.43 136

3Dnovator	82.32 10	89.33 94	87.64 107	94.42 22	93.73 153	85.70 32	97.73 47	96.75 56	86.73 70	76.21 223	95.93 99	62.17 228	99.68 29	81.67 139	97.81 49	97.88 72

PVSNet_BlendedMVS		90.05 85	89.96 74	90.33 150	97.47 61	83.86 64	98.02 31	96.73 57	87.98 51	89.53 78	89.61 203	76.42 101	99.57 39	94.29 28	79.59 212	87.57 273

PVSNet_Blended		93.13 34	92.98 36	93.57 48	97.47 61	83.86 64	99.32 1	96.73 57	91.02 20	89.53 78	96.21 96	76.42 101	99.57 39	94.29 28	95.81 83	97.29 110

ACMMP		90.39 80	89.97 73	91.64 121	97.58 59	78.21 210	96.78 113	96.72 59	84.73 107	84.72 120	97.23 72	71.22 158	99.63 34	88.37 87	92.41 112	97.08 116
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
新几何1				93.12 66	97.44 63	81.60 113		96.71 60	74.54 274	91.22 62	97.57 56	79.13 68	99.51 46	77.40 173	98.46 27	98.26 46

HFP-MVS		92.89 39	92.86 38	92.98 71	98.71 13	81.12 120	97.58 54	96.70 61	85.20 94	91.75 50	97.97 40	78.47 75	99.71 23	90.95 59	98.41 30	98.12 54

#test#		92.99 37	92.99 35	92.98 71	98.71 13	81.12 120	97.77 42	96.70 61	85.75 81	91.75 50	97.97 40	78.47 75	99.71 23	91.36 55	98.41 30	98.12 54

ACMMPR		92.69 45	92.67 42	92.75 80	98.66 18	80.57 132	97.58 54	96.69 63	85.20 94	91.57 53	97.92 42	77.01 93	99.67 31	90.95 59	98.41 30	98.00 65

DeepPCF-MVS	89.82 1	94.61 11	96.17 3	89.91 169	97.09 74	70.21 290	98.99 8	96.69 63	95.57 1	95.08 17	99.23 1	86.40 13	99.87 8	97.84 1	98.66 22	99.65 1

1121		90.66 73	89.82 79	93.16 65	97.39 65	81.71 111	93.33 234	96.66 65	74.45 275	91.38 55	97.55 60	79.27 64	99.52 43	79.95 149	98.43 29	98.26 46

ACMMP_Plus		93.46 31	93.23 31	94.17 28	97.16 72	84.28 60	96.82 111	96.65 66	86.24 72	94.27 27	97.99 36	77.94 82	99.83 12	93.39 35	98.57 24	98.39 37

TEST9					98.64 21	83.71 68	97.82 37	96.65 66	84.29 121	95.16 14	98.09 28	84.39 21	99.36 55

train_agg		94.28 15	94.45 14	93.74 39	98.64 21	83.71 68	97.82 37	96.65 66	84.50 113	95.16 14	98.09 28	84.33 22	99.36 55	95.91 15	98.96 10	98.16 49

agg_prior3		94.10 20	94.29 20	93.53 52	98.62 24	83.03 82	97.80 41	96.64 69	84.28 122	95.01 18	98.03 32	83.40 31	99.41 52	95.91 15	98.96 10	98.16 49

1314		88.94 100	87.20 118	94.17 28	93.21 160	85.73 31	93.33 234	96.64 69	82.89 148	75.98 225	96.36 94	66.83 192	99.39 53	83.52 128	96.02 79	97.39 103

DeepC-MVS_fast	89.06 2	94.48 13	94.30 19	95.02 14	98.86 10	85.68 33	98.06 29	96.64 69	93.64 8	91.74 52	98.54 7	80.17 57	99.90 4	92.28 50	98.75 18	99.49 3
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_8					98.63 23	83.64 71	97.81 39	96.63 72	84.50 113	95.10 16	98.11 27	84.33 22	99.23 61

原ACMM1				91.22 131	97.77 54	78.10 213		96.61 73	81.05 175	91.28 60	97.42 66	77.92 83	98.98 86	79.85 151	98.51 25	96.59 132

MAR-MVS		90.63 74	90.22 69	91.86 116	98.47 33	78.20 211	97.18 78	96.61 73	83.87 131	88.18 94	98.18 17	68.71 174	99.75 18	83.66 124	97.15 62	97.63 89
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
SteuartSystems-ACMMP		94.13 19	94.44 15	93.20 63	95.41 107	81.35 117	99.02 7	96.59 75	89.50 33	94.18 30	98.36 12	83.68 30	99.45 50	94.77 22	98.45 28	98.81 20
Skip Steuart: Steuart Systems R&D Blog.
TESTMET0.1,1		89.83 86	89.34 86	91.31 125	92.54 173	80.19 144	97.11 89	96.57 76	86.15 73	86.85 105	91.83 174	79.32 62	96.95 167	81.30 140	92.35 113	96.77 127

agg_prior1		94.10 20	94.31 18	93.48 55	98.59 26	83.13 78	97.77 42	96.56 77	84.38 117	94.19 28	98.13 23	84.66 19	99.16 74	95.74 17	98.74 19	98.15 51

agg_prior					98.59 26	83.13 78		96.56 77		94.19 28			99.16 74

DWT-MVSNet_test		90.52 79	89.80 80	92.70 83	95.73 100	82.20 96	93.69 225	96.55 79	88.34 45	87.04 104	95.34 110	86.53 10	97.55 139	76.32 185	88.66 139	98.34 38

旧先验1					97.39 65	79.58 164		96.54 80			98.08 31	84.00 26			97.42 57	97.62 90

WR-MVS_H		81.02 233	80.09 224	83.79 276	88.08 246	71.26 284	94.46 208	96.54 80	80.08 200	72.81 250	86.82 240	70.36 167	92.65 289	64.18 268	67.50 288	87.46 277

region2R		92.72 44	92.70 41	92.79 78	98.68 15	80.53 135	97.53 58	96.51 82	85.22 92	91.94 48	97.98 38	77.26 89	99.67 31	90.83 62	98.37 34	98.18 48

EPP-MVSNet		89.76 88	89.72 81	89.87 170	93.78 149	76.02 244	97.22 73	96.51 82	79.35 213	85.11 114	95.01 130	84.82 16	97.10 162	87.46 95	88.21 143	96.50 134

test11								96.50 84

EPNet_dtu		87.65 130	87.89 101	86.93 229	94.57 126	71.37 281	96.72 116	96.50 84	88.56 41	87.12 102	95.02 129	75.91 110	94.01 278	66.62 255	90.00 130	95.42 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testdata				90.13 159	95.92 91	74.17 257		96.49 86	73.49 282	94.82 22	97.99 36	78.80 72	97.93 117	83.53 127	97.52 52	98.29 43

HSP-MVS		95.55 4	96.51 2	92.66 84	98.31 39	80.10 146	97.42 67	96.46 87	92.20 13	97.11 2	98.29 13	93.46 1	99.10 79	96.01 13	99.30 2	98.77 22

test222					96.15 83	78.41 204	95.87 170	96.46 87	71.97 291	89.66 75	97.45 62	76.33 104			98.24 38	98.30 42

XVS		92.69 45	92.71 39	92.63 87	98.52 29	80.29 139	97.37 69	96.44 89	87.04 67	91.38 55	97.83 46	77.24 91	99.59 37	90.46 65	98.07 42	98.02 60

X-MVStestdata		86.26 154	84.14 171	92.63 87	98.52 29	80.29 139	97.37 69	96.44 89	87.04 67	91.38 55	20.73 353	77.24 91	99.59 37	90.46 65	98.07 42	98.02 60

TSAR-MVS + MP.		94.79 10	95.17 8	93.64 44	97.66 55	84.10 61	95.85 172	96.42 91	91.26 17	97.49 1	96.80 88	86.50 11	98.49 103	95.54 19	99.03 7	98.33 39

APDe-MVS		94.56 12	94.75 10	93.96 33	98.84 11	83.40 75	98.04 30	96.41 92	85.79 80	95.00 19	98.28 14	84.32 25	99.18 72	97.35 5	98.77 17	99.28 5

UniMVSNet_NR-MVSNet		85.49 170	84.59 157	88.21 201	89.44 232	79.36 165	96.71 118	96.41 92	85.22 92	78.11 196	90.98 185	76.97 94	95.14 254	79.14 155	68.30 280	90.12 218

test_prior3		94.03 23	94.34 17	93.09 68	98.68 15	81.91 101	98.37 18	96.40 94	86.08 75	94.57 25	98.02 33	83.14 33	99.06 81	95.05 20	98.79 15	98.29 43

test_prior				93.09 68	98.68 15	81.91 101		96.40 94					99.06 81			98.29 43

CP-MVS		92.54 50	92.60 44	92.34 95	98.50 31	79.90 149	98.40 17	96.40 94	84.75 106	90.48 68	98.09 28	77.40 88	99.21 65	91.15 58	98.23 39	97.92 71

CANet		94.89 8	94.64 11	95.63 8	97.55 60	88.12 11	99.06 5	96.39 97	94.07 7	95.34 13	97.80 47	76.83 96	99.87 8	97.08 7	97.64 51	98.89 17

alignmvs		92.97 38	92.26 48	95.12 13	95.54 103	87.77 15	98.67 11	96.38 98	88.04 50	93.01 40	97.45 62	79.20 67	98.60 97	93.25 40	88.76 137	98.99 16

PAPM		92.87 40	92.40 45	94.30 24	92.25 182	87.85 14	96.40 142	96.38 98	91.07 18	88.72 87	96.90 82	82.11 38	97.37 147	90.05 69	97.70 50	97.67 85

test12				94.25 26	98.34 37	85.55 35		96.35 100		92.36 45		80.84 48	99.22 63		98.31 36	97.98 67

PatchFormer-LS_test		90.14 84	89.30 87	92.65 86	95.43 105	82.46 91	93.46 230	96.35 100	88.56 41	84.82 117	95.22 117	84.63 20	97.55 139	78.40 161	86.81 151	97.94 70

MPTG		92.74 41	92.71 39	92.86 75	97.90 49	80.85 126	96.47 131	96.33 102	87.92 52	90.20 70	98.18 17	76.71 99	99.76 15	92.57 47	98.09 40	97.96 68

MTGPA								96.33 102

MTAPA		92.45 51	92.31 47	92.86 75	97.90 49	80.85 126	92.88 247	96.33 102	87.92 52	90.20 70	98.18 17	76.71 99	99.76 15	92.57 47	98.09 40	97.96 68

EPMVS		87.47 132	85.90 141	92.18 102	95.41 107	82.26 95	87.00 305	96.28 105	85.88 79	84.23 125	85.57 262	75.07 132	96.26 191	71.14 224	92.50 110	98.03 59

CDPH-MVS		93.12 35	92.91 37	93.74 39	98.65 20	83.88 63	97.67 50	96.26 106	83.00 147	93.22 38	98.24 15	81.31 46	99.21 65	89.12 78	98.74 19	98.14 52

WR-MVS		84.32 185	82.96 185	88.41 194	89.38 233	80.32 138	96.59 126	96.25 107	83.97 128	76.63 215	90.36 194	67.53 178	94.86 262	75.82 190	70.09 263	90.06 222

UGNet		87.73 129	86.55 131	91.27 128	95.16 114	79.11 176	96.35 144	96.23 108	88.14 49	87.83 97	90.48 191	50.65 293	99.09 80	80.13 148	94.03 94	95.60 155
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
tfpnnormal		78.14 255	75.42 261	86.31 236	88.33 244	79.24 169	94.41 210	96.22 109	73.51 281	69.81 267	85.52 264	55.43 280	95.75 221	47.65 327	67.86 284	83.95 308

MP-MVS		92.61 48	92.67 42	92.42 92	98.13 44	79.73 154	97.33 71	96.20 110	85.63 83	90.53 66	97.66 50	78.14 80	99.70 26	92.12 52	98.30 37	97.85 75

PAPR		92.74 41	92.17 50	94.45 21	98.89 9	84.87 50	97.20 76	96.20 110	87.73 57	88.40 90	98.12 26	78.71 73	99.76 15	87.99 90	96.28 74	98.74 23

SD-MVS		94.84 9	95.02 9	94.29 25	97.87 53	84.61 52	97.76 45	96.19 112	89.59 32	96.66 4	98.17 21	84.33 22	99.60 36	96.09 12	98.50 26	98.66 27

CHOSEN 280x420		91.71 59	91.85 51	91.29 127	94.94 119	82.69 88	87.89 297	96.17 113	85.94 77	87.27 101	94.31 138	90.27 4	95.65 231	94.04 31	95.86 81	95.53 156

CHOSEN 1792x2688		91.07 69	90.21 70	93.64 44	95.18 113	83.53 72	96.26 152	96.13 114	88.92 38	84.90 116	93.10 162	72.86 145	99.62 35	88.86 79	95.67 84	97.79 79

PAPM_NR		91.46 64	90.82 65	93.37 59	98.50 31	81.81 106	95.03 199	96.13 114	84.65 109	86.10 110	97.65 54	79.24 66	99.75 18	83.20 130	96.88 69	98.56 32

CostFormer		89.08 97	88.39 97	91.15 132	93.13 163	79.15 175	88.61 292	96.11 116	83.14 143	89.58 77	86.93 235	83.83 29	96.87 172	88.22 88	85.92 161	97.42 101

mPP-MVS		91.88 56	91.82 52	92.07 105	98.38 36	78.63 195	97.29 72	96.09 117	85.12 96	88.45 89	97.66 50	75.53 113	99.68 29	89.83 71	98.02 45	97.88 72

APD-MVS		93.61 29	93.59 26	93.69 42	98.76 12	83.26 76	97.21 74	96.09 117	82.41 157	94.65 24	98.21 16	81.96 39	98.81 95	94.65 25	98.36 35	99.01 13
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MDTV_nov1_ep13			83.69 174		94.09 144	81.01 122	86.78 307	96.09 117	83.81 133	84.75 119	84.32 275	74.44 137	96.54 181	63.88 274	85.07 176

QAPM		86.88 142	84.51 158	93.98 31	94.04 146	85.89 29	97.19 77	96.05 120	73.62 280	75.12 235	95.62 106	62.02 231	99.74 20	70.88 225	96.06 78	96.30 143

MP-MVS-pluss		92.58 49	92.35 46	93.29 60	97.30 70	82.53 90	96.44 136	96.04 121	84.68 108	89.12 83	98.37 11	77.48 87	99.74 20	93.31 39	98.38 33	97.59 92
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
tpm2		87.35 137	86.26 133	90.62 144	92.93 167	78.67 193	88.06 296	95.99 122	79.33 214	87.40 98	86.43 251	80.28 54	96.40 185	80.23 146	85.73 166	96.79 125

DeepC-MVS	86.58 3	91.53 63	91.06 63	92.94 73	94.52 134	81.89 103	95.95 163	95.98 123	90.76 21	83.76 132	96.76 89	73.24 143	99.71 23	91.67 54	96.96 66	97.22 114
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test-LLR		88.48 112	87.98 100	89.98 165	92.26 180	77.23 232	97.11 89	95.96 124	83.76 134	86.30 108	91.38 177	72.30 150	96.78 177	80.82 142	91.92 119	95.94 146

test-mter		88.95 99	88.60 94	89.98 165	92.26 180	77.23 232	97.11 89	95.96 124	85.32 90	86.30 108	91.38 177	76.37 103	96.78 177	80.82 142	91.92 119	95.94 146

DP-MVS Recon		91.72 58	90.85 64	94.34 23	99.50 1	85.00 45	98.51 16	95.96 124	80.57 187	88.08 95	97.63 55	76.84 95	99.89 6	85.67 104	94.88 90	98.13 53

cdsmvs_eth3d_5k		21.43 329	28.57 330	0.00 345	0.00 359	0.00 360	0.00 351	95.93 127	0.00 355	0.00 356	97.66 50	63.57 219	0.00 358	0.00 355	0.00 356	0.00 356

tpmp4_e23		86.46 150	84.95 153	90.98 138	93.74 152	78.60 197	88.13 295	95.90 128	79.65 209	85.42 113	85.67 257	80.08 58	97.06 163	71.71 216	84.26 181	97.28 112

TAMVS		88.48 112	87.79 104	90.56 145	91.09 205	79.18 173	96.45 134	95.88 129	83.64 137	83.12 140	93.33 158	75.94 109	95.74 224	82.40 135	88.27 142	96.75 129

PVSNet_Blended_VisFu		91.24 67	90.77 66	92.66 84	95.09 115	82.40 92	97.77 42	95.87 130	88.26 47	86.39 106	93.94 145	76.77 97	99.27 58	88.80 81	94.00 97	96.31 142

OpenMVS	79.58 14	86.09 155	83.62 177	93.50 53	90.95 207	86.71 24	97.44 62	95.83 131	75.35 258	72.64 251	95.72 102	57.42 267	99.64 33	71.41 219	95.85 82	94.13 179

CDS-MVSNet		89.50 91	88.96 90	91.14 133	91.94 195	80.93 124	97.09 93	95.81 132	84.26 123	84.72 120	94.20 140	80.31 53	95.64 232	83.37 129	88.96 135	96.85 124
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PS-MVSNAJ		94.17 18	93.52 28	96.10 4	95.65 101	92.35 1	98.21 23	95.79 133	92.42 12	96.24 5	98.18 17	71.04 161	99.17 73	96.77 9	97.39 58	96.79 125

3Dnovator+	82.88 8	89.63 90	87.85 102	94.99 15	94.49 137	86.76 23	97.84 36	95.74 134	86.10 74	75.47 232	96.02 98	65.00 213	99.51 46	82.91 134	97.07 63	98.72 26

HPM-MVS		91.62 61	91.53 58	91.89 111	97.88 52	79.22 172	96.99 99	95.73 135	82.07 161	89.50 80	97.19 74	75.59 112	98.93 92	90.91 61	97.94 46	97.54 93

ab-mvs		87.08 139	84.94 154	93.48 55	93.34 159	83.67 70	88.82 289	95.70 136	81.18 173	84.55 123	90.14 198	62.72 225	98.94 91	85.49 106	82.54 203	97.85 75

xiu_mvs_v2_base		93.92 25	93.26 30	95.91 6	95.07 117	92.02 2	98.19 24	95.68 137	92.06 14	96.01 9	98.14 22	70.83 164	98.96 87	96.74 10	96.57 72	96.76 128

CP-MVSNet		81.01 234	80.08 225	83.79 276	87.91 248	70.51 287	94.29 217	95.65 138	80.83 179	72.54 252	88.84 210	63.71 218	92.32 292	68.58 245	68.36 279	88.55 251

PatchmatchNet		86.83 144	85.12 149	91.95 109	94.12 143	82.27 94	86.55 309	95.64 139	84.59 111	82.98 142	84.99 272	77.26 89	95.96 209	68.61 244	91.34 124	97.64 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
API-MVS		90.18 83	88.97 89	93.80 37	98.66 18	82.95 85	97.50 60	95.63 140	75.16 262	86.31 107	97.69 49	72.49 147	99.90 4	81.26 141	96.07 77	98.56 32

AdaColmap		88.81 104	87.61 110	92.39 94	99.33 4	79.95 147	96.70 120	95.58 141	77.51 234	83.05 141	96.69 91	61.90 235	99.72 22	84.29 114	93.47 103	97.50 97

Patchmatch-test1		84.89 178	82.76 190	91.27 128	92.30 178	81.86 104	92.88 247	95.56 142	84.85 104	82.52 143	85.19 267	58.04 258	94.21 274	65.93 261	87.58 148	97.74 81

dp		84.30 186	82.31 195	90.28 151	94.24 141	77.97 215	86.57 308	95.53 143	79.94 204	80.75 167	85.16 269	71.49 157	96.39 186	63.73 275	83.36 187	96.48 135

HyFIR lowres test		89.36 93	88.60 94	91.63 122	94.91 121	80.76 128	95.60 179	95.53 143	82.56 156	84.03 126	91.24 180	78.03 81	96.81 175	87.07 98	88.41 141	97.32 105

APD-MVS_3200maxsize		91.23 68	91.35 59	90.89 140	97.89 51	76.35 241	96.30 150	95.52 145	79.82 206	91.03 64	97.88 45	74.70 135	98.54 100	92.11 53	96.89 68	97.77 80

lupinMVS		93.87 27	93.58 27	94.75 18	93.00 165	88.08 12	99.15 4	95.50 146	91.03 19	94.90 20	97.66 50	78.84 70	97.56 137	94.64 26	97.46 53	98.62 30

HPM-MVS_fast		90.38 81	90.17 71	91.03 135	97.61 56	77.35 230	97.15 83	95.48 147	79.51 211	88.79 86	96.90 82	71.64 155	98.81 95	87.01 99	97.44 55	96.94 119

test_normal		85.83 159	83.51 180	92.78 79	86.33 272	83.01 83	95.56 182	95.46 148	85.11 98	65.73 284	86.63 244	56.62 273	97.86 125	87.87 91	92.29 115	97.47 100

VPNet		84.69 181	82.92 186	90.01 163	89.01 235	83.45 74	96.71 118	95.46 148	85.71 82	79.65 179	92.18 168	56.66 272	96.01 204	83.05 133	67.84 285	90.56 209

DI_MVS_plusplus_test		85.92 157	83.61 178	92.86 75	86.43 267	83.20 77	95.57 180	95.46 148	85.10 99	65.99 282	86.84 239	56.70 271	97.89 124	88.10 89	92.33 114	97.48 99

114514_t		88.79 106	87.57 111	92.45 91	98.21 42	81.74 108	96.99 99	95.45 151	75.16 262	82.48 144	95.69 104	68.59 175	98.50 102	80.33 144	95.18 88	97.10 115

JIA-IIPM		79.00 248	77.20 245	84.40 268	89.74 226	64.06 312	75.30 334	95.44 152	62.15 318	81.90 159	59.08 338	78.92 69	95.59 236	66.51 258	85.78 165	93.54 189

DU-MVS		84.57 183	83.33 183	88.28 199	88.76 237	79.36 165	96.43 140	95.41 153	85.42 88	78.11 196	90.82 186	67.61 176	95.14 254	79.14 155	68.30 280	90.33 213

EI-MVSNet		85.80 160	85.20 147	87.59 217	91.55 199	77.41 228	95.13 195	95.36 154	80.43 191	80.33 173	94.71 133	73.72 141	95.97 205	76.96 180	78.64 221	89.39 229

MVSTER		89.25 96	88.92 91	90.24 152	95.98 90	84.66 51	96.79 112	95.36 154	87.19 65	80.33 173	90.61 190	90.02 5	95.97 205	85.38 107	78.64 221	90.09 220

CPTT-MVS		89.72 89	89.87 78	89.29 179	98.33 38	73.30 261	97.70 48	95.35 156	75.68 254	87.40 98	97.44 65	70.43 166	98.25 110	89.56 75	96.90 67	96.33 141

tpmvs		83.04 206	80.77 216	89.84 171	95.43 105	77.96 216	85.59 314	95.32 157	75.31 260	76.27 222	83.70 284	73.89 139	97.41 145	59.53 287	81.93 204	94.14 178

MVS_0304		93.82 28	93.11 34	95.95 5	96.79 76	89.15 7	98.56 15	95.30 158	93.61 9	94.82 22	98.02 33	66.60 196	99.88 7	96.94 8	97.39 58	98.81 20

PS-CasMVS		80.27 238	79.18 233	83.52 282	87.56 251	69.88 292	94.08 219	95.29 159	80.27 196	72.08 253	88.51 216	59.22 249	92.23 294	67.49 249	68.15 282	88.45 255

TSAR-MVS + GP.		94.35 14	94.50 12	93.89 34	97.38 68	83.04 81	98.10 28	95.29 159	91.57 15	93.81 32	97.45 62	86.64 9	99.43 51	96.28 11	94.01 96	99.20 8

tpmrst		88.36 116	87.38 116	91.31 125	94.36 138	79.92 148	87.32 301	95.26 161	85.32 90	88.34 91	86.13 255	80.60 50	96.70 179	83.78 118	85.34 174	97.30 108

NR-MVSNet		83.35 202	81.52 208	88.84 186	88.76 237	81.31 118	94.45 209	95.16 162	84.65 109	67.81 274	90.82 186	70.36 167	94.87 261	74.75 198	66.89 292	90.33 213

jason		92.73 43	92.23 49	94.21 27	90.50 213	87.30 21	98.65 12	95.09 163	90.61 23	92.76 42	97.13 76	75.28 129	97.30 150	93.32 38	96.75 71	98.02 60
jason: jason.
tpm cat1		83.63 193	81.38 210	90.39 149	93.53 157	78.19 212	85.56 315	95.09 163	70.78 297	78.51 192	83.28 288	74.80 134	97.03 164	66.77 254	84.05 182	95.95 145

cascas		86.50 149	84.48 160	92.55 89	92.64 172	85.95 28	97.04 98	95.07 165	75.32 259	80.50 169	91.02 183	54.33 288	97.98 116	86.79 100	87.62 146	93.71 188

abl_6		89.80 87	89.71 82	90.07 160	96.53 78	75.52 247	94.48 207	95.04 166	81.12 174	89.22 81	97.00 80	68.83 173	98.96 87	89.86 70	95.27 85	95.73 151

CVMVSNet		84.83 179	85.57 142	82.63 289	91.55 199	60.38 321	95.13 195	95.03 167	80.60 186	82.10 157	94.71 133	66.40 198	90.19 319	74.30 201	90.32 129	97.31 107

test0.0.03 1		82.79 211	82.48 193	83.74 278	86.81 255	72.22 268	96.52 129	95.03 167	83.76 134	73.00 247	93.20 159	72.30 150	88.88 322	64.15 269	77.52 228	90.12 218

PMMVS		89.46 92	89.92 76	88.06 202	94.64 124	69.57 296	96.22 153	94.95 169	87.27 61	91.37 58	96.54 93	65.88 201	97.39 146	88.54 82	93.89 98	97.23 113

mvs_anonymous		88.68 107	87.62 109	91.86 116	94.80 122	81.69 112	93.53 229	94.92 170	82.03 162	78.87 191	90.43 193	75.77 111	95.34 247	85.04 109	93.16 107	98.55 34

CLD-MVS		87.97 125	87.48 113	89.44 177	92.16 185	80.54 134	98.14 27	94.92 170	91.41 16	79.43 186	95.40 109	62.34 227	97.27 153	90.60 64	82.90 199	90.50 210
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
xiu_mvs_v1_base_debu		90.54 76	89.54 83	93.55 49	92.31 175	87.58 18	96.99 99	94.87 172	87.23 62	93.27 35	97.56 57	57.43 264	98.32 107	92.72 44	93.46 104	94.74 172

xiu_mvs_v1_base		90.54 76	89.54 83	93.55 49	92.31 175	87.58 18	96.99 99	94.87 172	87.23 62	93.27 35	97.56 57	57.43 264	98.32 107	92.72 44	93.46 104	94.74 172

xiu_mvs_v1_base_debi		90.54 76	89.54 83	93.55 49	92.31 175	87.58 18	96.99 99	94.87 172	87.23 62	93.27 35	97.56 57	57.43 264	98.32 107	92.72 44	93.46 104	94.74 172

GA-MVS		85.79 165	84.04 172	91.02 136	89.47 231	80.27 141	96.90 108	94.84 175	85.57 84	80.88 165	89.08 206	56.56 274	96.47 184	77.72 168	85.35 173	96.34 139

TranMVSNet+NR-MVSNet		83.24 204	81.71 205	87.83 210	87.71 249	78.81 191	96.13 158	94.82 176	84.52 112	76.18 224	90.78 188	64.07 217	94.60 267	74.60 200	66.59 296	90.09 220

HQP3-MVS								94.80 177							83.01 190

HQP-MVS		87.91 128	87.55 112	88.98 184	92.08 186	78.48 200	97.63 51	94.80 177	90.52 24	82.30 147	94.56 135	65.40 209	97.32 148	87.67 93	83.01 190	91.13 203

TAPA-MVS	81.61 12	85.02 175	83.67 175	89.06 181	96.79 76	73.27 263	95.92 165	94.79 179	74.81 269	80.47 170	96.83 86	71.07 160	98.19 113	49.82 323	92.57 109	95.71 153
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PEN-MVS		79.47 243	78.26 239	83.08 285	86.36 271	68.58 299	93.85 222	94.77 180	79.76 207	71.37 255	88.55 213	59.79 240	92.46 290	64.50 267	65.40 297	88.19 261

pcd1.5k->3k		34.11 325	35.46 325	30.05 341	86.70 256	0.00 360	0.00 351	94.74 181	0.00 355	0.00 356	0.00 357	58.13 256	0.00 358	0.00 355	79.56 214	90.14 216

HQP_MVS		87.50 131	87.09 123	88.74 189	91.86 196	77.96 216	97.18 78	94.69 182	89.89 30	81.33 162	94.15 141	64.77 214	97.30 150	87.08 96	82.82 200	90.96 205

plane_prior5								94.69 182					97.30 150	87.08 96	82.82 200	90.96 205

tpm		85.55 169	84.47 161	88.80 188	90.19 218	75.39 249	88.79 290	94.69 182	84.83 105	83.96 129	85.21 266	78.22 79	94.68 266	76.32 185	78.02 226	96.34 139

FMVSNet3		84.71 180	82.71 191	90.70 143	94.55 127	87.71 16	95.92 165	94.67 185	81.73 169	75.82 228	88.08 221	66.99 190	94.47 269	71.23 221	75.38 234	89.91 224

UA-Net		88.92 101	88.48 96	90.24 152	94.06 145	77.18 234	93.04 244	94.66 186	87.39 60	91.09 63	93.89 146	74.92 133	98.18 114	75.83 189	91.43 123	95.35 160

LFMVS		89.27 95	87.64 107	94.16 30	97.16 72	85.52 36	97.18 78	94.66 186	79.17 218	89.63 76	96.57 92	55.35 281	98.22 111	89.52 76	89.54 131	98.74 23

MVS_Test		90.29 82	89.18 88	93.62 46	95.23 111	84.93 46	94.41 210	94.66 186	84.31 119	90.37 69	91.02 183	75.13 130	97.82 126	83.11 132	94.42 92	98.12 54

canonicalmvs		92.27 52	91.22 60	95.41 11	95.80 98	88.31 9	97.09 93	94.64 189	88.49 43	92.99 41	97.31 68	72.68 146	98.57 99	93.38 37	88.58 140	99.36 4

VDDNet		86.44 151	84.51 158	92.22 100	91.56 198	81.83 105	97.10 92	94.64 189	69.50 301	87.84 96	95.19 120	48.01 303	97.92 123	89.82 72	86.92 149	96.89 122

PatchT		79.75 240	76.85 250	88.42 193	89.55 229	75.49 248	77.37 332	94.61 191	63.07 313	82.46 145	73.32 327	75.52 114	93.41 287	51.36 317	84.43 179	96.36 137

MS-PatchMatch		83.05 205	81.82 201	86.72 232	89.64 227	79.10 177	94.88 202	94.59 192	79.70 208	70.67 261	89.65 202	50.43 295	96.82 174	70.82 228	95.99 80	84.25 304

OMC-MVS		88.80 105	88.16 98	90.72 142	95.30 110	77.92 219	94.81 203	94.51 193	86.80 69	84.97 115	96.85 85	67.53 178	98.60 97	85.08 108	87.62 146	95.63 154

MVSFormer		91.36 65	90.57 67	93.73 41	93.00 165	88.08 12	94.80 204	94.48 194	80.74 183	94.90 20	97.13 76	78.84 70	95.10 256	83.77 119	97.46 53	98.02 60

test_djsdf		83.00 208	82.45 194	84.64 260	84.07 303	69.78 293	94.80 204	94.48 194	80.74 183	75.41 233	87.70 224	61.32 237	95.10 256	83.77 119	79.76 209	89.04 237

PCF-MVS	84.09 5	86.77 147	85.00 152	92.08 104	92.06 189	83.07 80	92.14 263	94.47 196	79.63 210	76.90 213	94.78 132	71.15 159	99.20 69	72.87 207	91.05 125	93.98 181
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VDD-MVS		88.28 118	87.02 124	92.06 106	95.09 115	80.18 145	97.55 57	94.45 197	83.09 144	89.10 84	95.92 100	47.97 304	98.49 103	93.08 42	86.91 150	97.52 96

PLC	83.97 7	88.00 124	87.38 116	89.83 172	98.02 48	76.46 239	97.16 82	94.43 198	79.26 217	81.98 158	96.28 95	69.36 171	99.27 58	77.71 169	92.25 116	93.77 187
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
FMVSNet2		82.79 211	80.44 220	89.83 172	92.66 169	85.43 37	95.42 184	94.35 199	79.06 220	74.46 236	87.28 227	56.38 276	94.31 272	69.72 234	74.68 238	89.76 225

nrg030		86.79 146	85.43 143	90.87 141	88.76 237	85.34 38	97.06 97	94.33 200	84.31 119	80.45 171	91.98 169	72.36 148	96.36 187	88.48 85	71.13 251	90.93 207

ACMM	80.70 13	83.72 192	82.85 188	86.31 236	91.19 204	72.12 271	95.88 169	94.29 201	80.44 189	77.02 211	91.96 170	55.24 282	97.14 161	79.30 154	80.38 208	89.67 226
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		83.84 190	82.00 196	89.35 178	87.13 253	81.38 116	95.72 175	94.26 202	80.15 199	75.92 227	90.63 189	61.96 234	96.52 182	78.98 157	73.28 245	90.14 216

testing_2		76.96 271	73.18 281	88.30 198	75.87 330	79.64 162	89.92 281	94.21 203	80.16 198	51.23 329	75.94 320	33.94 332	95.81 217	82.28 136	75.12 237	89.46 228

OPM-MVS		85.84 158	85.10 150	88.06 202	88.34 243	77.83 222	95.72 175	94.20 204	87.89 55	80.45 171	94.05 143	58.57 252	97.26 154	83.88 117	82.76 202	89.09 235

Test4		82.30 220	79.15 235	91.78 118	81.84 309	81.74 108	94.04 220	94.20 204	84.86 103	59.75 315	83.88 279	37.14 327	96.28 190	84.60 112	92.00 118	97.30 108

Vis-MVSNet (Re-imp)		88.88 103	88.87 92	88.91 185	93.89 148	74.43 255	96.93 107	94.19 206	84.39 116	83.22 139	95.67 105	78.24 78	94.70 265	78.88 158	94.40 93	97.61 91

v1neww		83.45 196	81.95 197	87.95 207	86.66 257	79.04 180	96.32 146	94.17 207	80.76 180	77.56 199	87.25 230	67.02 188	96.08 196	77.73 165	70.07 264	88.74 249

v7new		83.45 196	81.95 197	87.95 207	86.66 257	79.04 180	96.32 146	94.17 207	80.76 180	77.56 199	87.25 230	67.02 188	96.08 196	77.73 165	70.07 264	88.74 249

v6		83.45 196	81.94 199	87.95 207	86.62 261	79.03 183	96.32 146	94.17 207	80.76 180	77.57 198	87.23 232	67.03 187	96.09 195	77.73 165	70.06 266	88.75 247

PS-MVSNAJss		84.91 177	84.30 169	86.74 230	85.89 286	74.40 256	94.95 200	94.16 210	83.93 129	76.45 218	90.11 199	71.04 161	95.77 219	83.16 131	79.02 218	90.06 222

v1		83.37 199	81.82 201	88.01 204	86.58 265	79.24 169	96.45 134	94.13 211	80.88 176	77.48 203	86.88 236	67.15 183	96.04 199	77.15 174	69.67 272	88.76 245

LPG-MVS_test		84.20 187	83.49 181	86.33 233	90.88 208	73.06 264	95.28 185	94.13 211	82.20 159	76.31 219	93.20 159	54.83 286	96.95 167	83.72 121	80.83 206	88.98 239

LGP-MVS_train				86.33 233	90.88 208	73.06 264		94.13 211	82.20 159	76.31 219	93.20 159	54.83 286	96.95 167	83.72 121	80.83 206	88.98 239

v1141		83.36 200	81.81 203	88.01 204	86.61 263	79.26 168	96.44 136	94.12 214	80.88 176	77.48 203	86.87 237	67.08 185	96.03 200	77.14 175	69.69 271	88.75 247

divwei89l23v2f112		83.36 200	81.81 203	88.01 204	86.60 264	79.23 171	96.44 136	94.12 214	80.88 176	77.49 201	86.87 237	67.08 185	96.03 200	77.14 175	69.67 272	88.76 245

V42		83.04 206	81.53 207	87.57 219	86.27 276	79.09 178	95.87 170	94.11 216	80.35 193	77.22 209	86.79 242	65.32 211	96.02 203	77.74 164	70.14 259	87.61 272

XVG-OURS-SEG-HR		85.74 166	85.16 148	87.49 221	90.22 217	71.45 280	91.29 273	94.09 217	81.37 171	83.90 131	95.22 117	60.30 239	97.53 143	85.58 105	84.42 180	93.50 190

XVG-OURS		85.18 174	84.38 162	87.59 217	90.42 215	71.73 277	91.06 276	94.07 218	82.00 163	83.29 138	95.08 127	56.42 275	97.55 139	83.70 123	83.42 186	93.49 191

diffmvs		87.96 126	86.47 132	92.42 92	94.26 139	82.70 87	92.79 251	94.03 219	77.94 228	88.99 85	89.98 200	70.72 165	97.56 137	77.75 163	91.80 121	96.98 117

v2v482		83.46 195	81.86 200	88.25 200	86.19 278	79.65 161	96.34 145	94.02 220	81.56 170	77.32 207	88.23 218	65.62 204	96.03 200	77.77 162	69.72 270	89.09 235

v7		82.99 209	81.41 209	87.73 213	86.41 268	78.86 188	96.10 159	93.98 221	79.88 205	77.49 201	87.11 234	65.44 207	95.97 205	75.69 192	70.59 257	88.36 257

jajsoiax		82.12 222	81.15 213	85.03 248	84.19 301	70.70 286	94.22 218	93.95 222	83.07 145	73.48 241	89.75 201	49.66 298	95.37 246	82.24 137	79.76 209	89.02 238

v1144		82.90 210	81.27 212	87.78 212	86.29 274	79.07 179	96.14 156	93.93 223	80.05 201	77.38 205	86.80 241	65.50 205	95.93 211	75.21 195	70.13 260	88.33 259

RPMNet		79.32 245	75.75 257	90.06 161	90.16 219	79.75 151	79.02 328	93.92 224	58.43 330	82.27 155	72.55 328	73.03 144	93.67 284	46.10 329	86.25 155	96.75 129

UnsupCasMVSNet_eth		73.25 289	70.57 291	81.30 296	77.53 323	66.33 306	87.24 302	93.89 225	80.38 192	57.90 322	81.59 294	42.91 317	90.56 316	65.18 265	48.51 334	87.01 282

v7n		79.32 245	77.34 244	85.28 245	84.05 304	72.89 267	93.38 232	93.87 226	75.02 265	70.68 260	84.37 274	59.58 243	95.62 234	67.60 248	67.50 288	87.32 279

Vis-MVSNet		88.67 108	87.82 103	91.24 130	92.68 168	78.82 189	96.95 105	93.85 227	87.55 58	87.07 103	95.13 125	63.43 222	97.21 155	77.58 171	96.15 75	97.70 84
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v148		82.41 218	80.89 214	86.99 228	86.18 279	76.81 237	96.27 151	93.82 228	80.49 188	75.28 234	86.11 256	67.32 181	95.75 221	75.48 193	67.03 291	88.42 256

BH-w/o		88.24 120	87.47 114	90.54 146	95.03 118	78.54 198	97.41 68	93.82 228	84.08 125	78.23 195	94.51 137	69.34 172	97.21 155	80.21 147	94.58 91	95.87 148

TR-MVS		86.30 153	84.93 155	90.42 147	94.63 125	77.58 225	96.57 127	93.82 228	80.30 194	82.42 146	95.16 122	58.74 251	97.55 139	74.88 197	87.82 145	96.13 144

v1192		82.31 219	80.55 219	87.60 216	85.94 284	78.47 203	95.85 172	93.80 231	79.33 214	76.97 212	86.51 246	63.33 223	95.87 213	73.11 206	70.13 260	88.46 254

ACMP	81.66 11	84.00 188	83.22 184	86.33 233	91.53 201	72.95 266	95.91 167	93.79 232	83.70 136	73.79 239	92.22 167	54.31 289	96.89 171	83.98 116	79.74 211	89.16 234
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v144192		82.43 215	80.73 217	87.54 220	85.81 287	78.22 208	95.98 161	93.78 233	79.09 219	77.11 210	86.49 247	64.66 216	95.91 212	74.20 202	69.42 274	88.49 252

mvs_tets		81.74 225	80.71 218	84.84 252	84.22 300	70.29 289	93.91 221	93.78 233	82.77 150	73.37 242	89.46 204	47.36 307	95.31 249	81.99 138	79.55 215	88.92 243

F-COLMAP		84.50 184	83.44 182	87.67 214	95.22 112	72.22 268	95.95 163	93.78 233	75.74 252	76.30 221	95.18 121	59.50 244	98.45 105	72.67 209	86.59 154	92.35 200

Fast-Effi-MVS+		87.93 127	86.94 127	90.92 139	94.04 146	79.16 174	98.26 21	93.72 236	81.29 172	83.94 130	92.90 163	69.83 170	96.68 180	76.70 181	91.74 122	96.93 120

v1921920		82.02 223	80.23 223	87.41 222	85.62 288	77.92 219	95.79 174	93.69 237	78.86 223	76.67 214	86.44 249	62.50 226	95.83 216	72.69 208	69.77 269	88.47 253

DTE-MVSNet		78.37 253	77.06 246	82.32 293	85.22 293	67.17 304	93.40 231	93.66 238	78.71 225	70.53 262	88.29 217	59.06 250	92.23 294	61.38 283	63.28 304	87.56 274

v8		81.88 224	80.06 227	87.32 223	86.63 260	79.04 180	94.41 210	93.65 239	78.77 224	73.19 246	85.57 262	66.87 191	95.81 217	73.84 205	67.61 287	87.11 280

v748		78.69 251	76.79 251	84.39 269	83.40 307	70.78 285	93.25 240	93.62 240	74.96 266	69.40 269	83.74 281	59.40 245	95.39 244	68.74 242	64.59 299	86.99 283

ADS-MVSNet		81.26 231	78.36 237	89.96 167	93.78 149	79.78 150	79.48 324	93.60 241	73.09 284	80.14 175	79.99 302	62.15 229	95.24 252	59.49 288	83.52 184	94.85 169

PatchMatch-RL		85.00 176	83.66 176	89.02 183	95.86 96	74.55 254	92.49 255	93.60 241	79.30 216	79.29 188	91.47 175	58.53 253	98.45 105	70.22 229	92.17 117	94.07 180

anonymousdsp		80.98 235	79.97 228	84.01 271	81.73 310	70.44 288	92.49 255	93.58 243	77.10 241	72.98 248	86.31 253	57.58 263	94.90 260	79.32 153	78.63 223	86.69 285

v1240		81.70 226	79.83 230	87.30 225	85.50 289	77.70 224	95.48 183	93.44 244	78.46 227	76.53 217	86.44 249	60.85 238	95.84 215	71.59 218	70.17 258	88.35 258

V4		78.70 249	76.95 247	83.95 272	81.66 312	71.34 282	91.94 265	93.44 244	74.69 272	70.35 265	83.73 282	58.07 257	95.50 240	71.84 213	66.86 293	85.02 298

v52		78.70 249	76.95 247	83.95 272	81.71 311	71.34 282	91.93 266	93.43 246	74.69 272	70.36 263	83.71 283	58.04 258	95.50 240	71.84 213	66.82 294	85.00 299

v10		81.43 229	79.53 232	87.11 226	86.38 269	78.87 187	94.31 213	93.43 246	77.88 230	73.24 245	85.26 265	65.44 207	95.75 221	72.14 212	67.71 286	86.72 284

IterMVS-LS		83.93 189	82.80 189	87.31 224	91.46 202	77.39 229	95.66 177	93.43 246	80.44 189	75.51 231	87.26 229	73.72 141	95.16 253	76.99 178	70.72 255	89.39 229
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		82.42 216	80.43 221	88.39 195	92.66 169	81.95 98	94.30 214	93.38 249	79.06 220	75.82 228	85.66 258	56.38 276	93.84 280	71.23 221	75.38 234	89.38 231

test1		82.42 216	80.43 221	88.39 195	92.66 169	81.95 98	94.30 214	93.38 249	79.06 220	75.82 228	85.66 258	56.38 276	93.84 280	71.23 221	75.38 234	89.38 231

FMVSNet1		79.50 242	76.54 253	88.39 195	88.47 242	81.95 98	94.30 214	93.38 249	73.14 283	72.04 254	85.66 258	43.86 311	93.84 280	65.48 263	72.53 248	89.38 231

BH-untuned		86.95 141	85.94 140	89.99 164	94.52 134	77.46 227	96.78 113	93.37 252	81.80 168	76.62 216	93.81 149	66.64 195	97.02 165	76.06 187	93.88 99	95.48 157

Effi-MVS+-dtu		84.61 182	84.90 156	83.72 279	91.96 192	63.14 315	94.95 200	93.34 253	85.57 84	79.79 178	87.12 233	61.99 232	95.61 235	83.55 125	85.83 164	92.41 199

mvs-test1		86.83 144	87.17 119	85.81 240	91.96 192	65.24 308	97.90 34	93.34 253	85.57 84	84.51 124	95.14 124	61.99 232	97.19 157	83.55 125	90.55 128	95.00 167

CMPMVS	54.94 21	75.71 279	74.56 273	79.17 306	79.69 318	55.98 328	89.59 282	93.30 255	60.28 326	53.85 327	89.07 207	47.68 306	96.33 188	76.55 182	81.02 205	85.22 296
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs4		82.54 214	80.79 215	87.79 211	86.11 281	80.49 137	93.55 228	93.18 256	77.29 238	73.35 243	89.40 205	65.26 212	95.05 259	75.32 194	73.61 241	87.83 267

XVG-ACMP-BASELINE		79.38 244	77.90 241	83.81 275	84.98 295	67.14 305	89.03 288	93.18 256	80.26 197	72.87 249	88.15 220	38.55 324	96.26 191	76.05 188	78.05 225	88.02 264

testpf		70.88 298	70.47 292	72.08 320	88.92 236	59.57 324	48.62 348	93.15 258	63.05 314	63.07 296	79.51 305	58.33 255	86.63 329	66.93 253	72.69 247	70.05 340

CANet_DTU		90.98 70	90.04 72	93.83 36	94.76 123	86.23 26	96.32 146	93.12 259	93.11 10	93.71 33	96.82 87	63.08 224	99.48 48	84.29 114	95.12 89	95.77 150

IS-MVSNet		88.67 108	88.16 98	90.20 154	93.61 154	76.86 236	96.77 115	93.07 260	84.02 127	83.62 133	95.60 107	74.69 136	96.24 193	78.43 160	93.66 102	97.49 98

UnsupCasMVSNet_bld		68.60 304	64.50 305	80.92 299	74.63 331	67.80 301	83.97 317	92.94 261	65.12 311	54.63 326	68.23 335	35.97 328	92.17 296	60.13 286	44.83 338	82.78 321

MVP-Stereo		82.65 213	81.67 206	85.59 243	86.10 282	78.29 206	93.33 234	92.82 262	77.75 231	69.17 272	87.98 222	59.28 248	95.76 220	71.77 215	96.88 69	82.73 322
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Effi-MVS+		90.70 72	89.90 77	93.09 68	93.61 154	83.48 73	95.20 188	92.79 263	83.22 142	91.82 49	95.70 103	71.82 152	97.48 144	91.25 57	93.67 101	98.32 40

EU-MVSNet		76.92 273	76.95 247	76.83 310	84.10 302	54.73 331	91.77 269	92.71 264	72.74 287	69.57 268	88.69 211	58.03 260	87.43 327	64.91 266	70.00 267	88.33 259

pm-mvs1		80.05 239	78.02 240	86.15 238	85.42 290	75.81 245	95.11 197	92.69 265	77.13 239	70.36 263	87.43 226	58.44 254	95.27 251	71.36 220	64.25 300	87.36 278

1112_ss		88.60 111	87.47 114	92.00 108	93.21 160	80.97 123	96.47 131	92.46 266	83.64 137	80.86 166	97.30 70	80.24 55	97.62 135	77.60 170	85.49 167	97.40 102

Test_1112_low_res		88.03 123	86.73 128	91.94 110	93.15 162	80.88 125	96.44 136	92.41 267	83.59 139	80.74 168	91.16 181	80.18 56	97.59 136	77.48 172	85.40 168	97.36 104

BH-RMVSNet		86.84 143	85.28 146	91.49 123	95.35 109	80.26 142	96.95 105	92.21 268	82.86 149	81.77 160	95.46 108	59.34 247	97.64 134	69.79 233	93.81 100	96.57 133

test2356		74.41 284	74.53 274	74.07 317	76.13 329	54.45 332	94.74 206	92.08 269	71.96 292	65.51 285	83.05 290	56.96 268	83.71 337	52.74 315	77.58 227	84.06 306

LS3D		82.22 221	79.94 229	89.06 181	97.43 64	74.06 259	93.20 242	92.05 270	61.90 319	73.33 244	95.21 119	59.35 246	99.21 65	54.54 310	92.48 111	93.90 182

EG-PatchMatch MVS		74.92 281	72.02 285	83.62 280	83.76 306	73.28 262	93.62 226	92.04 271	68.57 303	58.88 317	83.80 280	31.87 336	95.57 238	56.97 297	78.67 220	82.00 328

IterMVS		80.67 236	79.16 234	85.20 246	89.79 223	76.08 243	92.97 246	91.86 272	80.28 195	71.20 257	85.14 270	57.93 262	91.34 310	72.52 210	70.74 254	88.18 262
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MIMVSNet		79.18 247	75.99 256	88.72 190	87.37 252	80.66 130	79.96 323	91.82 273	77.38 236	74.33 237	81.87 293	41.78 319	90.74 315	66.36 260	83.10 189	94.76 171

semantic-postprocess				84.73 256	89.63 228	74.66 252		91.81 274	80.05 201	71.06 259	85.18 268	57.98 261	91.40 309	72.48 211	70.70 256	88.12 263

pmmvs5		81.34 230	79.54 231	86.73 231	85.02 294	76.91 235	96.22 153	91.65 275	77.65 232	73.55 240	88.61 212	55.70 279	94.43 270	74.12 203	73.35 244	88.86 244

ACMH	75.40 17	77.99 256	74.96 265	87.10 227	90.67 211	76.41 240	93.19 243	91.64 276	72.47 290	63.44 293	87.61 225	43.34 314	97.16 158	58.34 292	73.94 240	87.72 268
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+-dtu		83.33 203	82.60 192	85.50 244	89.55 229	69.38 297	96.09 160	91.38 277	82.30 158	75.96 226	91.41 176	56.71 270	95.58 237	75.13 196	84.90 177	91.54 201

YYNet1		73.53 288	70.43 293	82.85 287	84.52 298	71.73 277	91.69 271	91.37 278	67.63 304	46.79 334	81.21 296	55.04 284	90.43 317	55.93 306	59.70 311	86.38 287

MDA-MVSNet_test_wron		73.54 287	70.43 293	82.86 286	84.55 296	71.85 273	91.74 270	91.32 279	67.63 304	46.73 335	81.09 297	55.11 283	90.42 318	55.91 307	59.76 310	86.31 288

CR-MVSNet		83.53 194	81.36 211	90.06 161	90.16 219	79.75 151	79.02 328	91.12 280	84.24 124	82.27 155	80.35 300	75.45 115	93.67 284	63.37 278	86.25 155	96.75 129

Patchmtry		77.36 265	74.59 272	85.67 242	89.75 224	75.75 246	77.85 331	91.12 280	60.28 326	71.23 256	80.35 300	75.45 115	93.56 286	57.94 293	67.34 290	87.68 270

LTVRE_ROB	73.68 18	77.99 256	75.74 258	84.74 255	90.45 214	72.02 272	86.41 310	91.12 280	72.57 289	66.63 278	87.27 228	54.95 285	96.98 166	56.29 305	75.98 230	85.21 297
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
OurMVSNet-221017-0		77.18 269	76.06 255	80.55 300	83.78 305	60.00 322	90.35 278	91.05 283	77.01 243	66.62 279	87.92 223	47.73 305	94.03 277	71.63 217	68.44 278	87.62 271

CNLPA		86.96 140	85.37 145	91.72 120	97.59 58	79.34 167	97.21 74	91.05 283	74.22 276	78.90 189	96.75 90	67.21 182	98.95 89	74.68 199	90.77 127	96.88 123

v18		77.96 258	75.61 259	84.98 249	86.66 257	79.01 184	93.02 245	90.94 285	75.69 253	63.19 294	77.62 309	67.11 184	92.07 297	70.05 230	56.24 316	83.87 309

v16		77.84 259	75.47 260	84.93 251	86.62 261	78.93 186	92.84 249	90.89 286	75.50 256	63.03 298	77.54 310	66.82 193	92.04 298	69.82 231	56.22 317	83.82 311

pmmvs6		74.65 283	71.67 286	83.60 281	79.13 320	69.94 291	93.31 238	90.88 287	61.05 325	65.83 283	84.15 277	43.43 313	94.83 263	66.62 255	60.63 308	86.02 293

v17		77.79 260	75.41 262	84.94 250	86.53 266	78.94 185	92.83 250	90.88 287	75.51 255	62.97 299	77.50 311	66.69 194	92.03 299	69.80 232	56.01 318	83.83 310

v15		77.52 262	75.09 263	84.82 253	86.37 270	78.82 189	92.58 253	90.78 289	75.47 257	62.53 301	77.17 312	66.58 197	91.92 300	69.18 235	55.16 320	83.73 312

V14		77.43 264	74.99 264	84.75 254	86.32 273	78.67 193	92.44 257	90.77 290	75.28 261	62.42 302	77.13 313	66.40 198	91.88 301	69.01 240	55.14 321	83.70 313

V9		77.32 266	74.87 267	84.69 257	86.26 277	78.52 199	92.33 260	90.72 291	75.11 264	62.21 304	77.08 315	66.19 200	91.87 302	68.84 241	55.06 323	83.69 314

Anonymous20231206		75.29 280	73.64 279	80.22 301	80.75 313	63.38 314	93.36 233	90.71 292	73.09 284	67.12 276	83.70 284	50.33 296	90.85 314	53.63 313	70.10 262	86.44 286

v12		77.20 268	74.73 268	84.63 261	86.15 280	78.41 204	92.17 262	90.71 292	74.92 267	62.05 306	77.00 316	65.83 202	91.83 303	68.69 243	55.01 324	83.64 315

v13		77.11 270	74.63 271	84.55 263	86.08 283	78.27 207	92.06 264	90.68 294	74.73 270	61.86 309	76.93 317	65.73 203	91.81 306	68.55 246	55.07 322	83.59 316

v11		77.21 267	74.72 269	84.68 258	86.29 274	78.62 196	92.30 261	90.63 295	74.86 268	62.32 303	76.73 318	65.49 206	91.83 303	68.17 247	55.72 319	83.59 316

USDC		78.65 252	76.25 254	85.85 239	87.58 250	74.60 253	89.58 283	90.58 296	84.05 126	63.13 295	88.23 218	40.69 323	96.86 173	66.57 257	75.81 232	86.09 292

MSDG		80.62 237	77.77 242	89.14 180	93.43 158	77.24 231	91.89 267	90.18 297	69.86 300	68.02 273	91.94 172	52.21 291	98.84 94	59.32 290	83.12 188	91.35 202

ACMH+	76.62 16	77.47 263	74.94 266	85.05 247	91.07 206	71.58 279	93.26 239	90.01 298	71.80 293	64.76 288	88.55 213	41.62 320	96.48 183	62.35 281	71.00 252	87.09 281

FMVSNet5		76.46 275	74.16 277	83.35 284	90.05 221	76.17 242	89.58 283	89.85 299	71.39 296	65.29 287	80.42 299	50.61 294	87.70 326	61.05 284	69.24 275	86.18 290

ambc				76.02 313	68.11 338	51.43 335	64.97 343	89.59 300		60.49 313	74.49 321	17.17 346	92.46 290	61.50 282	52.85 329	84.17 305

ITE_SJBPF				82.38 291	87.00 254	65.59 307		89.55 301	79.99 203	69.37 270	91.30 179	41.60 321	95.33 248	62.86 280	74.63 239	86.24 289

pmmvs-eth3d		73.59 286	70.66 290	82.38 291	76.40 327	73.38 260	89.39 287	89.43 302	72.69 288	60.34 314	77.79 308	46.43 309	91.26 312	66.42 259	57.06 313	82.51 323

test20.03		72.36 294	71.15 288	75.98 314	77.79 322	59.16 325	92.40 258	89.35 303	74.09 277	61.50 310	84.32 275	48.09 302	85.54 335	50.63 321	62.15 306	83.24 318

SixPastTwentyTwo		76.04 276	74.32 276	81.22 297	84.54 297	61.43 320	91.16 274	89.30 304	77.89 229	64.04 290	86.31 253	48.23 301	94.29 273	63.54 277	63.84 302	87.93 266

TransMVSNet (Re)		76.94 272	74.38 275	84.62 262	85.92 285	75.25 250	95.28 185	89.18 305	73.88 279	67.22 275	86.46 248	59.64 241	94.10 276	59.24 291	52.57 330	84.50 303

MIMVSNet1		69.44 300	66.65 302	77.84 307	76.48 326	62.84 316	87.42 300	88.97 306	66.96 309	57.75 323	79.72 304	32.77 335	85.83 332	46.32 328	63.42 303	84.85 301

K. test v3		73.62 285	71.59 287	79.69 303	82.98 308	59.85 323	90.85 277	88.83 307	77.13 239	58.90 316	82.11 291	43.62 312	91.72 307	65.83 262	54.10 327	87.50 276

Baseline_NR-MVSNet		81.22 232	80.07 226	84.68 258	85.32 292	75.12 251	96.48 130	88.80 308	76.24 244	77.28 208	86.40 252	67.61 176	94.39 271	75.73 191	66.73 295	84.54 302

MDA-MVSNet-bldmvs		71.45 296	67.94 299	81.98 295	85.33 291	68.50 300	92.35 259	88.76 309	70.40 298	42.99 336	81.96 292	46.57 308	91.31 311	48.75 326	54.39 326	86.11 291

new-patchmatchnet		68.85 303	65.93 303	77.61 308	73.57 334	63.94 313	90.11 280	88.73 310	71.62 294	55.08 325	73.60 323	40.84 322	87.22 328	51.35 318	48.49 335	81.67 329

Patchmatch-test		78.25 254	74.72 269	88.83 187	91.20 203	74.10 258	73.91 338	88.70 311	59.89 328	66.82 277	85.12 271	78.38 77	94.54 268	48.84 325	79.58 213	97.86 74

OpenMVS_ROB	68.52 20	73.02 291	69.57 295	83.37 283	80.54 316	71.82 274	93.60 227	88.22 312	62.37 317	61.98 307	83.15 289	35.31 331	95.47 242	45.08 330	75.88 231	82.82 320

test1235678		64.50 309	62.19 309	71.42 321	66.82 340	48.00 338	89.44 285	87.90 313	62.82 316	49.12 333	71.31 333	30.14 339	82.19 339	41.88 333	60.32 309	84.06 306

RPSCF		77.73 261	76.63 252	81.06 298	88.66 241	55.76 330	87.77 298	87.88 314	64.82 312	74.14 238	92.79 164	49.22 300	96.81 175	67.47 250	76.88 229	90.62 208

MVS-HIRNet		71.36 297	67.00 300	84.46 267	90.58 212	69.74 294	79.15 327	87.74 315	46.09 339	61.96 308	50.50 341	45.14 310	95.64 232	53.74 312	88.11 144	88.00 265

testus		70.06 299	69.09 297	72.98 319	74.54 332	51.28 337	93.78 223	87.34 316	71.49 295	62.69 300	83.46 286	24.44 341	84.77 336	51.22 319	72.85 246	82.90 319

1111		65.60 308	64.33 306	69.41 322	68.26 336	45.11 342	87.06 303	87.32 317	54.99 334	51.20 330	73.45 324	63.57 219	85.70 333	36.53 337	56.59 315	77.42 334

.test1245		54.61 314	58.07 312	44.24 337	68.26 336	45.11 342	87.06 303	87.32 317	54.99 334	51.20 330	73.45 324	63.57 219	85.70 333	36.53 337	0.21 353	1.91 353

DP-MVS		81.47 228	78.28 238	91.04 134	98.14 43	78.48 200	95.09 198	86.97 319	61.14 324	71.12 258	92.78 165	59.59 242	99.38 54	53.11 314	86.61 153	95.27 161

COLMAP_ROB	73.24 19	75.74 278	73.00 283	83.94 274	92.38 174	69.08 298	91.85 268	86.93 320	61.48 322	65.32 286	90.27 195	42.27 318	96.93 170	50.91 320	75.63 233	85.80 294
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_0402		72.68 292	69.54 296	82.09 294	88.67 240	71.81 275	92.72 252	86.77 321	61.52 321	62.21 304	83.91 278	43.22 315	93.76 283	34.60 340	72.23 249	80.72 330

testgi		74.88 282	73.40 280	79.32 305	80.13 317	61.75 318	93.21 241	86.64 322	79.49 212	66.56 280	91.06 182	35.51 330	88.67 323	56.79 298	71.25 250	87.56 274

TDRefinement		69.20 302	65.78 304	79.48 304	66.04 341	62.21 317	88.21 294	86.12 323	62.92 315	61.03 312	85.61 261	33.23 333	94.16 275	55.82 308	53.02 328	82.08 327

ADS-MVSNet2		79.57 241	77.53 243	85.71 241	93.78 149	72.13 270	79.48 324	86.11 324	73.09 284	80.14 175	79.99 302	62.15 229	90.14 320	59.49 288	83.52 184	94.85 169

LF4IMVS		72.36 294	70.82 289	76.95 309	79.18 319	56.33 327	86.12 311	86.11 324	69.30 302	63.06 297	86.66 243	33.03 334	92.25 293	65.33 264	68.64 277	82.28 326

LP		68.54 305	63.92 307	82.39 290	87.93 247	71.79 276	72.37 341	86.01 326	55.89 333	58.33 320	71.46 332	49.58 299	90.10 321	32.25 342	61.48 307	85.27 295

TinyColmap		72.41 293	68.99 298	82.68 288	88.11 245	69.59 295	88.41 293	85.20 327	65.55 310	57.91 321	84.82 273	30.80 338	95.94 210	51.38 316	68.70 276	82.49 325

pmmvs3		65.75 307	62.18 310	76.45 312	67.12 339	64.54 309	88.68 291	85.05 328	54.77 337	57.54 324	73.79 322	29.40 340	86.21 331	55.49 309	47.77 336	78.62 332

new_pmnet		66.18 306	63.18 308	75.18 316	76.27 328	61.74 319	83.79 318	84.66 329	56.64 332	51.57 328	71.85 330	31.29 337	87.93 325	49.98 322	62.55 305	75.86 335

AllTest		75.92 277	73.06 282	84.47 265	92.18 183	67.29 302	91.07 275	84.43 330	67.63 304	63.48 291	90.18 196	38.20 325	97.16 158	57.04 295	73.37 242	88.97 241

TestCases				84.47 265	92.18 183	67.29 302		84.43 330	67.63 304	63.48 291	90.18 196	38.20 325	97.16 158	57.04 295	73.37 242	88.97 241

test12356		58.24 312	56.06 314	64.77 325	60.65 342	39.42 348	82.78 321	84.34 332	57.47 331	42.65 337	69.10 334	19.21 344	81.18 340	38.97 336	49.40 331	73.69 336

LCM-MVSNet-Re		83.75 191	83.54 179	84.39 269	93.54 156	64.14 311	92.51 254	84.03 333	83.90 130	66.14 281	86.59 245	67.36 180	92.68 288	84.89 111	92.87 108	96.35 138

testmv		54.58 315	51.53 316	63.74 329	53.58 347	40.82 346	83.26 319	83.92 334	54.07 338	36.35 340	61.26 336	14.80 348	77.07 342	33.00 341	43.53 341	73.33 337

Gipuma		45.11 320	42.05 320	54.30 333	80.69 314	51.30 336	35.80 349	83.81 335	28.13 345	27.94 345	34.53 347	11.41 353	76.70 345	21.45 347	54.65 325	34.90 349
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		52.52 316	48.24 317	65.35 324	47.63 351	41.45 345	72.55 340	83.62 336	31.75 343	37.66 339	57.92 339	9.19 355	76.76 344	49.26 324	44.60 339	77.84 333

FPMVS		55.09 313	52.93 315	61.57 330	55.98 343	40.51 347	83.11 320	83.41 337	37.61 342	34.95 341	71.95 329	14.40 349	76.95 343	29.81 344	65.16 298	67.25 342

Patchmatch-RL test		76.65 274	74.01 278	84.55 263	77.37 325	64.23 310	78.49 330	82.84 338	78.48 226	64.63 289	73.40 326	76.05 108	91.70 308	76.99 178	57.84 312	97.72 82

DSMNet-mixed		73.13 290	72.45 284	75.19 315	77.51 324	46.82 339	85.09 316	82.01 339	67.61 308	69.27 271	81.33 295	50.89 292	86.28 330	54.54 310	83.80 183	92.46 198

Anonymous20231211		61.03 311	56.76 313	73.82 318	71.24 335	53.47 333	87.60 299	81.65 340	44.19 340	51.08 332	71.82 331	20.79 343	88.46 324	35.45 339	47.07 337	79.52 331

lessismore_v0				79.98 302	80.59 315	58.34 326		80.87 341		58.49 318	83.46 286	43.10 316	93.89 279	63.11 279	48.68 333	87.72 268

no-one		51.12 317	45.81 319	67.03 323	53.16 349	52.22 334	75.21 335	80.40 342	54.89 336	28.26 344	48.50 343	15.54 347	82.81 338	39.29 335	17.06 346	66.07 343

door								80.13 343

door-mid								79.75 344

PM-MVS		69.32 301	66.93 301	76.49 311	73.60 333	55.84 329	85.91 312	79.32 345	74.72 271	61.09 311	78.18 307	21.76 342	91.10 313	70.86 226	56.90 314	82.51 323

ANet_high		46.22 319	41.28 322	61.04 331	39.91 354	46.25 341	70.59 342	76.18 346	58.87 329	23.09 346	48.00 344	12.58 351	66.54 349	28.65 345	13.62 349	70.35 339

PMMVS2		50.90 318	46.31 318	64.67 326	55.53 344	46.67 340	77.30 333	71.02 347	40.89 341	34.16 342	59.32 337	9.83 354	76.14 346	40.09 334	28.63 343	71.21 338

wuykxyi23d		37.75 324	31.85 327	55.46 332	40.00 353	38.01 349	59.81 345	69.47 348	25.46 347	12.42 352	30.55 351	2.06 359	67.08 348	31.81 343	15.03 347	61.29 344

MTMP								68.16 349

DeepMVS_CX				64.06 328	78.53 321	43.26 344		68.11 350	69.94 299	38.55 338	76.14 319	18.53 345	79.34 341	43.72 331	41.62 342	69.57 341

PMVS	34.80 23	39.19 323	35.53 324	50.18 335	29.72 355	30.30 352	59.60 346	66.20 351	26.06 346	17.91 349	49.53 342	3.12 357	74.09 347	18.19 349	49.40 331	46.14 346
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PNet_i23d		41.20 322	38.13 323	50.41 334	55.23 345	36.24 351	73.80 339	65.45 352	29.75 344	21.36 347	47.05 345	3.43 356	63.23 350	28.17 346	18.92 345	51.76 345

tmp_tt		41.54 321	41.93 321	40.38 338	20.10 356	26.84 353	61.93 344	59.09 353	14.81 351	28.51 343	80.58 298	35.53 329	48.33 354	63.70 276	13.11 350	45.96 348

MVE	35.65 22	33.85 326	29.49 329	46.92 336	41.86 352	36.28 350	50.45 347	56.52 354	18.75 350	18.28 348	37.84 346	2.41 358	58.41 351	18.71 348	20.62 344	46.06 347
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 327	32.39 326	33.65 339	53.35 348	25.70 354	74.07 337	53.33 355	21.08 348	17.17 350	33.63 349	11.85 352	54.84 352	12.98 350	14.04 348	20.42 350

EMVS		31.70 328	31.45 328	32.48 340	50.72 350	23.95 355	74.78 336	52.30 356	20.36 349	16.08 351	31.48 350	12.80 350	53.60 353	11.39 351	13.10 351	19.88 351

N_pmnet		61.30 310	60.20 311	64.60 327	84.32 299	17.00 357	91.67 272	10.98 357	61.77 320	58.45 319	78.55 306	49.89 297	91.83 303	42.27 332	63.94 301	84.97 300

wuyk23d		14.10 330	13.89 331	14.72 342	55.23 345	22.91 356	33.83 350	3.56 358	4.94 352	4.11 353	2.28 356	2.06 359	19.66 355	10.23 352	8.74 352	1.59 355

testmvs		9.92 331	12.94 332	0.84 344	0.65 357	0.29 359	93.78 223	0.39 359	0.42 353	2.85 354	15.84 354	0.17 362	0.30 357	2.18 353	0.21 353	1.91 353

test123		9.07 332	11.73 333	1.11 343	0.50 358	0.77 358	89.44 285	0.20 360	0.34 354	2.15 355	10.72 355	0.34 361	0.32 356	1.79 354	0.08 355	2.23 352

pcd_1.5k_mvsjas		5.92 334	7.89 335	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	71.04 161	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		8.11 333	10.81 334	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	97.30 70	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																97.54 93

test_part3							98.15 25		84.95 101		98.83 2		99.80 13	97.78 2

test_part2					98.90 7	85.14 43				96.07 7

sam_mvs1												77.59 86				97.54 93

sam_mvs												75.35 128

test_post1							85.88 313				30.24 352	73.77 140	95.07 258	73.89 204

test_post											33.80 348	76.17 106	95.97 205

patchmatchnet-post											77.09 314	77.78 85	95.39 244

gm-plane-assit					92.27 179	79.64 162			84.47 115		95.15 123		97.93 117	85.81 103

test9_res														96.00 14	99.03 7	98.31 41

agg_prior2														94.30 27	99.00 9	98.57 31

test_prior4						82.34 93	97.75 46

test_prior2							98.37 18		86.08 75	94.57 25	98.02 33	83.14 33		95.05 20	98.79 15

旧先验2							96.97 104		74.06 278	96.10 6			97.76 129	88.38 86

新几何2							96.42 141

原ACMM2							96.84 110

testdata2													99.48 48	76.45 184

segment_acmp												82.69 35

testdata1							95.57 180		87.44 59

plane_prior7					91.86 196	77.55 226

plane_prior6					91.98 191	77.92 219						64.77 214

plane_prior4											94.15 141

plane_prior3						77.75 223			90.17 28	81.33 162

plane_prior2							97.18 78		89.89 30

plane_prior1					91.95 194

plane_prior						77.96 216	97.52 59		90.36 27						82.96 192

HQP5-MVS						78.48 200

HQP-NCC					92.08 186		97.63 51		90.52 24	82.30 147

ACMP_Plane					92.08 186		97.63 51		90.52 24	82.30 147

BP-MVS														87.67 93

HQP4-MVS										82.30 147			97.32 148			91.13 203

HQP2-MVS												65.40 209

NP-MVS					92.04 190	78.22 208					94.56 135

MDTV_nov1_ep13_2view						81.74 108	86.80 306		80.65 185	85.65 111		74.26 138		76.52 183		96.98 117

ACMMP++_ref															78.45 224

ACMMP++															79.05 217

Test By Simon												71.65 154

High-resolution multi-view benchmark