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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

CS-MVS		98.56 45	99.32 30	97.68 49	98.28 64	99.89 2	98.71 63	94.53 66	99.41 24	95.43 52	99.05 37	98.66 66	99.19 41	99.21 30	99.07 27	99.93 1	99.94 1

EC-MVSNet		98.22 53	99.44 18	96.79 76	95.62 131	99.56 52	99.01 52	92.22 121	99.17 59	94.51 78	99.41 15	99.62 53	99.49 19	99.16 35	99.26 15	99.91 2	99.94 1

SPE-MVS-test		98.58 44	99.42 22	97.60 53	98.52 59	99.91 1	98.60 66	94.60 63	99.37 28	94.62 74	99.40 16	99.16 62	99.39 27	99.36 21	98.85 50	99.90 3	99.92 3

EPP-MVSNet		97.75 64	98.71 61	96.63 84	95.68 127	99.56 52	97.51 128	93.10 117	99.22 51	94.99 69	97.18 102	97.30 85	98.65 96	98.83 60	98.93 42	99.84 12	99.92 3

LTVRE_ROB	93.20 16	92.84 201	94.92 185	90.43 222	92.83 186	98.63 156	97.08 152	87.87 202	97.91 177	68.42 253	93.54 178	79.46 246	96.62 162	97.55 159	97.40 147	99.74 54	99.92 3
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
MGCFI-Net		97.26 83	97.79 101	96.64 83	96.17 105	99.43 83	98.14 94	91.52 138	99.23 49	95.16 65	98.48 62	90.87 154	99.07 55	97.59 157	99.02 36	99.76 41	99.91 6

sasdasda		97.31 78	97.81 98	96.72 77	96.20 103	99.45 71	98.21 88	91.60 133	99.22 51	95.39 53	98.48 62	90.95 152	99.16 47	97.66 151	99.05 31	99.76 41	99.90 7

DVP-MVS++		99.41 5	99.64 1	99.14 8	99.69 8	99.75 9	99.64 10	98.33 6	99.67 5	98.10 15	99.66 6	99.99 1	99.33 31	99.62 5	98.86 47	99.74 54	99.90 7

MGCNet		98.81 34	99.44 18	98.08 40	98.83 52	99.75 9	99.58 19	95.53 48	99.76 1	96.48 40	99.70 4	98.64 67	98.21 111	99.00 47	99.33 10	99.82 16	99.90 7

canonicalmvs		97.31 78	97.81 98	96.72 77	96.20 103	99.45 71	98.21 88	91.60 133	99.22 51	95.39 53	98.48 62	90.95 152	99.16 47	97.66 151	99.05 31	99.76 41	99.90 7

PVSNet_Blended_VisFu		97.41 75	98.49 67	96.15 108	97.49 73	99.76 6	96.02 179	93.75 83	99.26 46	93.38 104	93.73 176	99.35 58	96.47 167	98.96 48	98.46 69	99.77 39	99.90 7

CSCG		98.90 31	98.93 54	98.85 25	99.75 3	99.72 13	99.49 24	96.58 44	99.38 26	98.05 18	98.97 39	97.87 78	99.49 19	97.78 144	98.92 43	99.78 34	99.90 7

PS-CasMVS		92.72 206	93.36 217	91.98 191	91.62 214	97.52 214	94.13 225	88.98 184	95.94 226	81.51 207	87.35 232	79.95 243	95.91 181	96.37 194	96.49 168	99.70 100	99.89 13

CP-MVSNet		93.25 194	94.00 205	92.38 182	91.65 212	97.56 212	94.38 221	89.20 179	96.05 223	83.16 196	89.51 215	81.97 231	96.16 175	96.43 192	96.56 166	99.71 90	99.89 13

WR-MVS_H		93.54 188	94.67 192	92.22 183	91.95 201	97.91 192	94.58 218	88.75 188	96.64 212	83.88 188	90.66 209	85.13 201	94.40 218	96.54 190	95.91 188	99.73 67	99.89 13

FC-MVSNet-train		97.04 93	97.91 94	96.03 116	96.00 108	98.41 173	96.53 168	93.42 88	99.04 89	93.02 110	98.03 79	94.32 122	97.47 140	97.93 135	97.77 128	99.75 47	99.88 16

IterMVS-LS		96.12 138	97.48 113	94.53 138	95.19 158	97.56 212	97.15 147	89.19 180	99.08 81	88.23 157	94.97 162	94.73 116	97.84 129	97.86 141	98.26 92	99.60 152	99.88 16
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DCV-MVSNet		97.56 70	98.36 70	96.62 85	96.44 94	98.36 177	98.37 79	91.73 130	99.11 76	94.80 71	98.36 70	96.28 96	98.60 100	98.12 111	98.44 71	99.76 41	99.87 18

v7n		91.61 225	92.95 220	90.04 224	90.56 228	97.69 200	93.74 226	85.59 220	95.89 227	76.95 227	86.60 237	78.60 249	93.76 229	97.01 179	94.99 208	99.65 131	99.87 18

CHOSEN 1792x2688		96.41 129	96.99 142	95.74 124	98.01 68	99.72 13	97.70 115	90.78 153	99.13 75	90.03 151	87.35 232	95.36 107	98.33 109	98.59 83	98.91 45	99.59 158	99.87 18

CANet		98.46 46	99.16 39	97.64 51	98.48 60	99.64 28	99.35 34	94.71 59	99.53 14	95.17 64	97.63 91	99.59 55	98.38 108	98.88 58	98.99 38	99.74 54	99.86 21

baseline		97.45 74	98.70 62	95.99 119	95.89 111	99.36 101	98.29 84	91.37 141	99.21 54	92.99 111	98.40 68	96.87 90	97.96 122	98.60 81	98.60 63	99.42 193	99.86 21

HyFIR lowres test		95.99 141	96.56 155	95.32 130	97.99 69	99.65 23	96.54 166	88.86 186	98.44 144	89.77 154	84.14 242	97.05 88	99.03 58	98.55 85	98.19 99	99.73 67	99.86 21

GeoE		95.98 143	97.24 128	94.51 139	95.02 161	99.38 94	98.02 102	87.86 203	98.37 153	87.86 162	92.99 191	93.54 131	98.56 101	98.61 78	97.92 116	99.73 67	99.85 24

tfpnnormal		93.85 186	94.12 201	93.54 164	93.22 185	98.24 181	95.45 189	91.96 127	94.61 232	83.91 187	90.74 207	81.75 233	97.04 148	97.49 161	96.16 179	99.68 112	99.84 25

Effi-MVS+		95.81 144	97.31 126	94.06 150	95.09 159	99.35 104	97.24 141	88.22 197	98.54 139	85.38 180	98.52 60	88.68 174	98.70 89	98.32 98	97.93 115	99.74 54	99.84 25

SD-MVS		99.25 13	99.50 13	98.96 21	98.79 54	99.55 54	99.33 35	98.29 12	99.75 2	97.96 20	99.15 26	99.95 17	99.61 6	99.17 33	99.06 29	99.81 23	99.84 25
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
EPNet		98.05 56	98.86 56	97.10 65	99.02 49	99.43 83	98.47 72	94.73 58	99.05 87	95.62 48	98.93 42	97.62 82	95.48 201	98.59 83	98.55 64	99.29 203	99.84 25
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SteuartSystems-ACMMP		99.20 16	99.51 12	98.83 27	99.66 17	99.66 22	99.71 5	98.12 29	99.14 70	96.62 35	99.16 25	99.98 2	99.12 50	99.63 3	99.19 22	99.78 34	99.83 29
Skip Steuart: Steuart Systems R&D Blog.
TSAR-MVS + MP.		99.27 11	99.57 5	98.92 23	98.78 55	99.53 56	99.72 4	98.11 30	99.73 3	97.43 27	99.15 26	99.96 12	99.59 9	99.73 1	99.07 27	99.88 4	99.82 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
anonymousdsp		93.12 197	95.86 177	89.93 227	91.09 225	98.25 180	95.12 193	85.08 222	97.44 191	73.30 242	90.89 202	90.78 156	95.25 209	97.91 136	95.96 187	99.71 90	99.82 30

TSAR-MVS + ACMM		98.77 35	99.45 15	97.98 44	99.37 38	99.46 67	99.44 30	98.13 28	99.65 6	92.30 126	98.91 44	99.95 17	99.05 56	99.42 18	98.95 41	99.58 162	99.82 30

PEN-MVS		92.72 206	93.20 219	92.15 186	91.29 222	97.31 222	94.67 215	89.81 166	96.19 219	81.83 205	88.58 223	79.06 247	95.61 197	95.21 218	96.27 174	99.72 79	99.82 30

WR-MVS		93.43 192	94.48 195	92.21 184	91.52 217	97.69 200	94.66 216	89.98 163	96.86 206	83.43 193	90.12 211	85.03 202	93.94 226	96.02 208	95.82 190	99.71 90	99.82 30

UniMVSNet_ETH3D		93.15 196	92.33 229	94.11 148	93.91 173	98.61 159	94.81 209	90.98 148	97.06 201	87.51 165	82.27 246	76.33 252	97.87 128	94.79 225	97.47 143	99.56 169	99.81 35

DeepC-MVS	97.63 4	98.33 50	98.57 63	98.04 42	98.62 58	99.65 23	99.45 28	98.15 25	99.51 17	92.80 116	95.74 148	96.44 93	99.46 22	99.37 20	99.50 2	99.78 34	99.81 35
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EIA-MVS		97.70 66	98.78 59	96.44 92	95.72 120	99.65 23	98.14 94	93.72 84	98.30 158	92.31 125	98.63 57	97.90 77	98.97 61	98.92 53	98.30 85	99.78 34	99.80 37

v8		92.87 200	93.87 210	91.72 199	92.05 199	97.50 215	94.79 210	88.20 198	96.85 207	80.11 215	90.01 212	82.86 227	95.48 201	95.15 220	94.90 211	99.66 126	99.80 37

v10		92.79 204	94.06 203	91.31 205	91.78 207	97.29 224	94.87 203	86.10 218	96.97 204	79.82 217	88.16 226	84.56 205	95.63 195	96.33 197	95.31 199	99.65 131	99.80 37

UniMVSNet_NR-MVSNet		94.59 171	95.47 181	93.55 163	91.85 205	97.89 193	95.03 195	92.00 125	97.33 194	86.12 171	93.19 184	87.29 180	96.60 163	96.12 204	96.70 159	99.72 79	99.80 37

DU-MVS		93.98 181	94.44 196	93.44 166	91.66 210	97.77 195	95.03 195	91.57 135	97.17 198	86.12 171	93.13 187	81.13 235	96.60 163	95.10 221	97.01 154	99.67 121	99.80 37

casdiffmvs_mvg		97.27 81	97.97 92	96.46 91	95.83 115	99.51 62	98.42 75	93.32 97	98.34 156	92.38 124	95.64 151	95.35 108	98.91 64	98.73 70	98.45 70	99.86 9	99.80 37
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UGNet		97.66 67	99.07 45	96.01 118	97.19 82	99.65 23	97.09 151	93.39 89	99.35 34	94.40 83	98.79 49	99.59 55	94.24 221	98.04 125	98.29 90	99.73 67	99.80 37
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
IS_MVSNet		97.86 60	98.86 56	96.68 79	96.02 106	99.72 13	98.35 82	93.37 93	98.75 129	94.01 87	96.88 114	98.40 72	98.48 106	99.09 38	99.42 5	99.83 15	99.80 37

E6new		96.66 118	97.04 138	96.21 102	95.52 146	99.46 67	97.65 123	93.22 108	98.40 150	92.26 128	95.22 159	90.02 164	98.89 69	98.06 122	98.30 85	99.74 54	99.79 45

E6		96.66 118	97.04 138	96.21 102	95.52 146	99.46 67	97.65 123	93.22 108	98.40 150	92.26 128	95.22 159	90.02 164	98.89 69	98.06 122	98.30 85	99.74 54	99.79 45

ETV-MVS		98.05 56	99.25 35	96.65 81	95.61 132	99.61 39	98.26 87	93.52 87	98.90 103	93.74 97	99.32 19	99.20 60	98.90 66	99.21 30	98.72 57	99.87 8	99.79 45

DVP-MVS		99.45 3	99.54 8	99.35 2	99.72 6	99.76 6	99.63 14	98.37 2	99.63 8	99.03 5	98.95 41	99.98 2	99.60 7	99.60 7	99.05 31	99.74 54	99.79 45
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
thisisatest0515		94.61 170	96.89 145	91.95 192	92.00 200	98.47 167	92.01 234	90.73 154	98.18 163	83.96 186	94.51 168	95.13 111	93.38 231	97.38 166	94.74 216	99.61 144	99.79 45

MSP-MVS		99.34 8	99.52 11	99.14 8	99.68 13	99.75 9	99.64 10	98.31 9	99.44 22	98.10 15	99.28 20	99.98 2	99.30 36	99.34 24	99.05 31	99.81 23	99.79 45
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
UniMVSNet (Re)		94.58 172	95.34 182	93.71 158	92.25 197	98.08 185	94.97 197	91.29 147	97.03 203	87.94 160	93.97 175	86.25 193	96.07 176	96.27 201	95.97 186	99.72 79	99.79 45

DELS-MVS		98.19 54	98.77 60	97.52 54	98.29 63	99.71 16	99.12 43	94.58 65	98.80 117	95.38 55	96.24 133	98.24 75	97.92 123	99.06 41	99.52 1	99.82 16	99.79 45
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
tttt0517		97.23 84	98.24 77	96.04 115	95.60 135	99.60 44	96.94 156	93.23 106	99.15 65	92.56 120	98.74 54	96.12 100	98.17 112	98.21 106	96.10 181	99.73 67	99.78 53

v144192		92.38 216	93.55 215	91.00 211	91.44 218	97.47 217	94.27 222	87.41 206	96.52 215	78.03 224	87.50 231	82.65 229	95.32 206	95.82 212	95.15 204	99.55 171	99.78 53

V42		93.05 198	93.90 209	92.04 188	91.91 202	97.66 202	94.91 200	89.91 164	96.85 207	80.58 211	89.66 214	83.43 222	95.37 205	95.03 223	94.90 211	99.59 158	99.78 53

MVS_Test		97.30 80	98.54 64	95.87 121	95.74 119	99.28 113	98.19 90	91.40 140	99.18 58	91.59 139	98.17 75	96.18 98	98.63 98	98.61 78	98.55 64	99.66 126	99.78 53

TranMVSNet+NR-MVSNet		93.67 187	94.14 199	93.13 173	91.28 224	97.58 210	95.60 186	91.97 126	97.06 201	84.05 185	90.64 210	82.22 230	96.17 174	94.94 224	96.78 157	99.69 104	99.78 53

PVSNet_BlendedMVS		97.51 72	97.71 102	97.28 60	98.06 66	99.61 39	97.31 136	95.02 54	99.08 81	95.51 50	98.05 77	90.11 161	98.07 118	98.91 54	98.40 74	99.72 79	99.78 53

PVSNet_Blended		97.51 72	97.71 102	97.28 60	98.06 66	99.61 39	97.31 136	95.02 54	99.08 81	95.51 50	98.05 77	90.11 161	98.07 118	98.91 54	98.40 74	99.72 79	99.78 53

casdiffseed414692147		96.17 135	96.26 171	96.06 113	95.50 150	99.38 94	97.34 135	93.13 116	98.09 167	91.89 136	93.14 186	87.49 178	98.78 82	98.12 111	97.86 121	99.75 47	99.77 60

viewmacassd2359aftdt		96.50 126	97.01 141	95.91 120	95.65 129	99.45 71	97.65 123	93.31 100	98.36 154	90.30 148	94.48 170	90.82 155	98.77 84	97.91 136	98.26 92	99.76 41	99.77 60

SED-MVS		99.44 4	99.58 4	99.28 4	99.69 8	99.76 6	99.62 16	98.35 3	99.51 17	99.05 4	99.60 8	99.98 2	99.28 38	99.61 6	98.83 52	99.70 100	99.77 60

thisisatest0530		97.23 84	98.25 74	96.05 114	95.60 135	99.59 46	96.96 155	93.23 106	99.17 59	92.60 119	98.75 53	96.19 97	98.17 112	98.19 108	96.10 181	99.72 79	99.77 60

Fast-Effi-MVS+		95.38 153	96.52 158	94.05 151	94.15 171	99.14 126	97.24 141	86.79 210	98.53 140	87.62 164	94.51 168	87.06 181	98.76 86	98.60 81	98.04 111	99.72 79	99.77 60

APDe-MVS		99.49 2	99.64 1	99.32 3	99.74 4	99.74 12	99.75 3	98.34 4	99.56 11	98.72 8	99.57 9	99.97 8	99.53 15	99.65 2	99.25 16	99.84 12	99.77 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.30 10	99.54 8	99.03 17	99.66 17	99.64 28	99.68 6	98.25 16	99.56 11	97.12 32	99.19 23	99.95 17	99.72 1	99.43 17	99.25 16	99.72 79	99.77 60

dmvs_re		96.02 140	96.49 162	95.47 128	93.49 183	99.26 115	97.25 140	93.82 79	97.51 189	90.43 147	97.52 93	87.93 176	98.12 117	96.86 182	96.59 164	99.73 67	99.76 67

Anonymous202405211			97.40 119		96.45 93	99.54 55	98.08 100	93.79 80	98.24 162		93.55 177	94.41 120	98.88 73	98.04 125	98.24 94	99.75 47	99.76 67

SMA-MVS		99.38 7	99.60 3	99.12 10	99.76 2	99.62 34	99.39 32	98.23 20	99.52 16	98.03 19	99.45 13	99.98 2	99.64 5	99.58 8	99.30 12	99.68 112	99.76 67
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
v1144		92.81 202	94.03 204	91.40 203	91.68 209	97.60 209	94.73 211	88.40 195	96.71 210	78.48 223	88.14 227	84.46 207	95.45 204	96.31 199	95.22 202	99.65 131	99.76 67

HFP-MVS		99.32 9	99.53 10	99.07 14	99.69 8	99.59 46	99.63 14	98.31 9	99.56 11	97.37 28	99.27 21	99.97 8	99.70 3	99.35 23	99.24 18	99.71 90	99.76 67

MSLP-MVS++		99.15 19	99.24 36	99.04 16	99.52 33	99.49 64	99.09 46	98.07 31	99.37 28	98.47 10	97.79 84	99.89 36	99.50 16	98.93 51	99.45 4	99.61 144	99.76 67

ACMMP		98.74 36	99.03 50	98.40 33	99.36 40	99.64 28	99.20 38	97.75 39	98.82 114	95.24 63	98.85 47	99.87 38	99.17 46	98.74 69	97.50 139	99.71 90	99.76 67
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
ACMH	95.42 14	95.27 156	95.96 174	94.45 141	96.83 90	98.78 143	94.72 212	91.67 132	98.95 95	86.82 170	96.42 130	83.67 212	97.00 149	97.48 162	96.68 160	99.69 104	99.76 67
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E4		96.62 122	96.98 144	96.21 102	95.53 143	99.45 71	97.68 117	93.28 103	98.43 145	92.18 132	94.78 166	90.21 160	98.86 74	98.00 129	98.19 99	99.74 54	99.75 75

viewmanbaseed2359cas		96.92 102	97.60 108	96.14 109	95.71 121	99.44 80	97.82 107	93.39 89	98.93 99	91.34 142	96.10 135	92.27 143	98.82 77	98.40 94	98.30 85	99.75 47	99.75 75

Anonymous20231211		97.10 90	97.06 135	97.14 64	96.32 96	99.52 59	98.16 92	93.76 81	98.84 111	95.98 44	90.92 201	94.58 119	98.90 66	97.72 149	98.10 108	99.71 90	99.75 75

X-MVS		98.93 30	99.37 25	98.42 32	99.67 14	99.62 34	99.60 17	98.15 25	99.08 81	93.81 93	98.46 66	99.95 17	99.59 9	99.49 14	99.21 21	99.68 112	99.75 75

NR-MVSNet		94.01 179	94.51 194	93.44 166	92.56 190	97.77 195	95.67 183	91.57 135	97.17 198	85.84 175	93.13 187	80.53 238	95.29 207	97.01 179	96.17 178	99.69 104	99.75 75

Vis-MVSNet (Re-imp)		97.40 76	98.89 55	95.66 126	95.99 109	99.62 34	97.82 107	93.22 108	98.82 114	91.40 141	96.94 111	98.56 70	95.70 193	99.14 36	99.41 6	99.79 31	99.75 75

E5new		96.68 114	97.05 136	96.24 99	95.52 146	99.45 71	97.67 119	93.33 95	98.42 147	92.41 122	95.34 157	90.30 158	98.79 79	97.94 133	98.13 103	99.74 54	99.74 81

E5		96.68 114	97.05 136	96.24 99	95.52 146	99.45 71	97.67 119	93.33 95	98.42 147	92.41 122	95.34 157	90.30 158	98.79 79	97.94 133	98.13 103	99.74 54	99.74 81

E3new		96.98 96	97.47 116	96.40 94	95.57 140	99.44 80	97.67 119	93.32 97	98.72 130	93.30 105	96.50 127	91.42 150	98.83 76	98.28 101	98.21 95	99.73 67	99.74 81

E3		96.98 96	97.49 111	96.39 95	95.60 135	99.44 80	97.68 117	93.32 97	98.80 117	93.19 107	96.50 127	91.49 149	98.80 78	98.28 101	98.19 99	99.73 67	99.74 81

diffmvs_AUTHOR		96.68 114	97.10 131	96.19 107	95.71 121	99.37 99	97.91 103	93.19 113	99.36 32	91.97 134	95.90 141	89.02 172	98.67 95	98.01 128	98.30 85	99.68 112	99.74 81

viewmambaseed2359dif		96.82 105	97.19 129	96.39 95	95.64 130	99.38 94	98.15 93	93.24 105	98.78 124	92.85 115	95.93 140	91.24 151	98.75 88	97.41 164	97.86 121	99.70 100	99.74 81

ACMMP_NAP		99.05 26	99.45 15	98.58 31	99.73 5	99.60 44	99.64 10	98.28 15	99.23 49	94.57 75	99.35 18	99.97 8	99.55 13	99.63 3	98.66 59	99.70 100	99.74 81

v1192		92.43 214	93.61 212	91.05 210	91.53 216	97.43 218	94.61 217	87.99 201	96.60 213	76.72 228	87.11 234	82.74 228	95.85 185	96.35 196	95.30 200	99.60 152	99.74 81

PGM-MVS		98.86 32	99.35 29	98.29 35	99.77 1	99.63 31	99.67 7	95.63 47	98.66 133	95.27 62	99.11 30	99.82 43	99.67 4	99.33 25	99.19 22	99.73 67	99.74 81

CP-MVS		99.27 11	99.44 18	99.08 13	99.62 23	99.58 49	99.53 21	98.16 23	99.21 54	97.79 22	99.15 26	99.96 12	99.59 9	99.54 11	98.86 47	99.78 34	99.74 81

E2		97.34 77	98.05 85	96.50 89	95.61 132	99.43 83	97.83 106	93.38 92	99.15 65	93.69 98	97.79 84	93.65 130	98.79 79	98.36 96	98.28 91	99.73 67	99.73 91

viewdifsd2359ckpt07		97.07 92	97.81 98	96.22 101	95.75 118	99.42 88	98.19 90	93.27 104	99.14 70	91.92 135	95.46 156	93.66 129	98.53 104	98.75 67	98.48 68	99.65 131	99.73 91

viewdifsd2359ckpt13		96.93 100	97.71 102	96.03 116	95.58 139	99.43 83	97.42 131	93.30 102	99.09 78	91.43 140	96.95 110	92.45 140	98.70 89	98.30 100	97.98 112	99.72 79	99.73 91

viewcassd2359sk11		97.19 86	97.82 96	96.44 92	95.59 138	99.43 83	97.70 115	93.35 94	99.15 65	93.50 101	97.20 101	92.68 139	98.77 84	98.38 95	98.21 95	99.73 67	99.73 91

IterMVS-SCA-FT		94.89 162	97.87 95	91.42 201	94.86 165	97.70 198	97.24 141	84.88 225	98.93 99	75.74 232	94.26 172	98.25 74	96.69 158	98.52 87	97.68 130	99.10 211	99.73 91

v1921920		92.36 218	93.57 213	90.94 212	91.39 220	97.39 220	94.70 213	87.63 205	96.60 213	76.63 229	86.98 235	82.89 226	95.75 191	96.26 202	95.14 205	99.55 171	99.73 91

DI_MVS_pp		96.90 103	97.49 111	96.21 102	95.61 132	99.40 92	98.72 62	92.11 122	99.14 70	92.98 112	93.08 189	95.14 110	98.13 116	98.05 124	97.91 118	99.74 54	99.73 91

v1240		91.99 223	93.33 218	90.44 221	91.29 222	97.30 223	94.25 223	86.79 210	96.43 216	75.49 235	86.34 238	81.85 232	95.29 207	96.42 193	95.22 202	99.52 179	99.73 91

thres600view7		96.69 112	96.43 167	97.00 73	96.28 100	99.67 19	98.41 76	93.99 76	97.85 181	94.29 85	95.96 138	85.91 195	99.19 41	98.26 103	97.63 133	99.82 16	99.73 91

MP-MVS		99.07 24	99.36 26	98.74 28	99.63 21	99.57 51	99.66 8	98.25 16	99.00 92	95.62 48	98.97 39	99.94 25	99.54 14	99.51 12	98.79 56	99.71 90	99.73 91
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DTE-MVSNet		92.42 215	92.85 222	91.91 194	90.87 227	96.97 226	94.53 220	89.81 166	95.86 228	81.59 206	88.83 221	77.88 250	95.01 213	94.34 228	96.35 172	99.64 136	99.73 91

Baseline_NR-MVSNet		93.87 184	93.98 206	93.75 156	91.66 210	97.02 225	95.53 187	91.52 138	97.16 200	87.77 163	87.93 230	83.69 211	96.35 169	95.10 221	97.23 149	99.68 112	99.73 91

SixPastTwentyTwo		93.44 191	95.32 183	91.24 206	92.11 198	98.40 174	92.77 230	88.64 193	98.09 167	77.83 225	93.51 180	85.74 196	96.52 166	96.91 181	94.89 213	99.59 158	99.73 91

LGP-MVS_train		96.23 133	96.89 145	95.46 129	97.32 77	98.77 144	98.81 59	93.60 86	98.58 136	85.52 178	99.08 34	86.67 188	97.83 130	97.87 140	97.51 138	99.69 104	99.73 91

pm-mvs1		94.27 175	95.57 180	92.75 178	92.58 189	98.13 184	94.87 203	90.71 155	96.70 211	83.78 189	89.94 213	89.85 167	94.96 214	97.58 158	97.07 151	99.61 144	99.72 105

casdiffmvs		96.93 100	97.43 118	96.34 97	95.70 123	99.50 63	97.75 112	93.22 108	98.98 94	92.64 117	94.97 162	91.71 147	98.93 62	98.62 77	98.52 67	99.82 16	99.72 105
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IterMVS		94.81 165	97.71 102	91.42 201	94.83 166	97.63 205	97.38 132	85.08 222	98.93 99	75.67 233	94.02 173	97.64 80	96.66 161	98.45 90	97.60 135	98.90 216	99.72 105
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
viewdifsd2359ckpt09		97.00 95	97.68 107	96.21 102	95.54 142	99.40 92	97.73 113	93.31 100	99.17 59	92.24 130	96.62 121	92.71 138	98.76 86	98.19 108	97.95 114	99.66 126	99.71 108

MCST-MVS		99.11 21	99.27 34	98.93 22	99.67 14	99.33 109	99.51 23	98.31 9	99.28 42	96.57 37	99.10 32	99.90 34	99.71 2	99.19 32	98.35 79	99.82 16	99.71 108

ACMP	96.25 10	96.62 122	96.72 151	96.50 89	96.96 86	98.75 148	97.80 109	94.30 71	98.85 107	93.12 109	98.78 50	86.61 189	97.23 146	97.73 148	96.61 163	99.62 142	99.71 108
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DPE-MVS		99.39 6	99.55 7	99.20 5	99.63 21	99.71 16	99.66 8	98.33 6	99.29 41	98.40 13	99.64 7	99.98 2	99.31 34	99.56 9	98.96 40	99.85 10	99.70 111
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
tfpn200view9		96.75 108	96.51 159	97.03 68	96.31 97	99.67 19	98.41 76	93.99 76	97.35 192	94.52 76	95.90 141	86.93 184	99.14 49	98.26 103	97.80 126	99.82 16	99.70 111

thres400		96.71 111	96.45 165	97.02 70	96.28 100	99.63 31	98.41 76	94.00 75	97.82 182	94.42 82	95.74 148	86.26 192	99.18 44	98.20 107	97.79 127	99.81 23	99.70 111

diffmvs		96.83 104	97.33 122	96.25 98	95.76 117	99.34 106	98.06 101	93.22 108	99.43 23	92.30 126	96.90 113	89.83 168	98.55 102	98.00 129	98.14 102	99.64 136	99.70 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v148		92.36 218	92.88 221	91.75 197	91.63 213	97.66 202	92.64 231	90.55 157	96.09 221	83.34 194	88.19 225	80.00 241	92.74 235	93.98 229	94.58 217	99.58 162	99.69 115

v2v482		92.77 205	93.52 216	91.90 195	91.59 215	97.63 205	94.57 219	90.31 159	96.80 209	79.22 219	88.74 222	81.55 234	96.04 179	95.26 217	94.97 209	99.66 126	99.69 115

CPTT-MVS		99.14 20	99.20 38	99.06 15	99.58 26	99.53 56	99.45 28	97.80 38	99.19 57	98.32 14	98.58 59	99.95 17	99.60 7	99.28 27	98.20 98	99.64 136	99.69 115

FMVSNet1		95.77 145	96.41 168	95.03 132	93.42 184	97.86 194	97.11 150	89.89 165	98.53 140	92.00 133	89.17 217	93.23 136	98.15 115	98.07 118	98.34 81	99.61 144	99.69 115

Vis-MVSNet		96.16 137	98.22 78	93.75 156	95.33 156	99.70 18	97.27 138	90.85 150	98.30 158	85.51 179	95.72 150	96.45 91	93.69 230	98.70 72	99.00 37	99.84 12	99.69 115
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
viewdifsd2359ckpt11		96.47 127	96.78 149	96.10 112	95.69 124	99.24 118	97.16 145	93.19 113	99.37 28	92.90 114	95.88 145	89.35 170	98.69 92	96.32 198	97.65 131	98.99 213	99.68 120

viewmsd2359difaftdt		96.47 127	96.78 149	96.11 111	95.69 124	99.24 118	97.16 145	93.19 113	99.35 34	92.93 113	95.88 145	89.34 171	98.69 92	96.31 199	97.65 131	98.99 213	99.68 120

MVSTER		97.16 87	97.71 102	96.52 87	95.97 110	98.48 166	98.63 65	92.10 123	98.68 132	95.96 45	99.23 22	91.79 146	96.87 153	98.76 65	97.37 148	99.57 166	99.68 120

GBi-Net		96.98 96	98.00 90	95.78 122	93.81 176	97.98 187	98.09 97	91.32 142	98.80 117	93.92 89	97.21 97	95.94 103	97.89 124	98.07 118	98.34 81	99.68 112	99.67 123

test1		96.98 96	98.00 90	95.78 122	93.81 176	97.98 187	98.09 97	91.32 142	98.80 117	93.92 89	97.21 97	95.94 103	97.89 124	98.07 118	98.34 81	99.68 112	99.67 123

FMVSNet2		96.64 120	97.50 110	95.63 127	93.81 176	97.98 187	98.09 97	90.87 149	98.99 93	93.48 102	93.17 185	95.25 109	97.89 124	98.63 76	98.80 55	99.68 112	99.67 123

3Dnovator+	96.92 7	98.71 38	99.05 46	98.32 34	99.53 31	99.34 106	99.06 48	94.61 61	99.65 6	97.49 26	96.75 115	99.86 39	99.44 24	98.78 63	99.30 12	99.81 23	99.67 123

HPM-MVS++		99.10 22	99.30 32	98.86 24	99.69 8	99.48 65	99.59 18	98.34 4	99.26 46	96.55 38	99.10 32	99.96 12	99.36 29	99.25 28	98.37 78	99.64 136	99.66 127

thres200		96.76 107	96.53 157	97.03 68	96.31 97	99.67 19	98.37 79	93.99 76	97.68 187	94.49 79	95.83 147	86.77 186	99.18 44	98.26 103	97.82 125	99.82 16	99.66 127

3Dnovator	96.92 7	98.67 39	99.05 46	98.23 38	99.57 27	99.45 71	99.11 44	94.66 60	99.69 4	96.80 34	96.55 126	99.61 54	99.40 26	98.87 59	99.49 3	99.85 10	99.66 127

TSAR-MVS + GP.		98.66 41	99.36 26	97.85 46	97.16 83	99.46 67	99.03 50	94.59 64	99.09 78	97.19 31	99.73 3	99.95 17	99.39 27	98.95 49	98.69 58	99.75 47	99.65 130

FMVSNet3		97.02 94	98.12 83	95.73 125	93.59 182	97.98 187	98.34 83	91.32 142	98.80 117	93.92 89	97.21 97	95.94 103	97.63 134	98.61 78	98.62 61	99.61 144	99.65 130

CDS-MVSNet		96.59 124	98.02 89	94.92 134	94.45 169	98.96 134	97.46 130	91.75 129	97.86 180	90.07 150	96.02 137	97.25 86	96.21 171	98.04 125	98.38 76	99.60 152	99.65 130
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ACMH+	95.51 13	95.40 152	96.00 172	94.70 136	96.33 95	98.79 141	96.79 158	91.32 142	98.77 125	87.18 166	95.60 153	85.46 198	96.97 150	97.15 175	96.59 164	99.59 158	99.65 130

ME-MVS		99.51 1	99.57 5	99.44 1	99.71 7	99.65 23	99.83 1	98.29 12	99.50 19	99.61 1	99.69 5	99.94 25	99.50 16	99.50 13	99.06 29	99.71 90	99.64 134

QAPM		98.62 42	99.04 49	98.13 39	99.57 27	99.48 65	99.17 40	94.78 57	99.57 10	96.16 42	96.73 116	99.80 44	99.33 31	98.79 62	99.29 14	99.75 47	99.64 134

DeepC-MVS_fast	98.34 1	99.17 18	99.45 15	98.85 25	99.55 30	99.37 99	99.64 10	98.05 33	99.53 14	96.58 36	98.93 42	99.92 29	99.49 19	99.46 15	99.32 11	99.80 30	99.64 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test1111		97.09 91	96.83 148	97.39 56	96.92 89	99.81 3	98.44 74	94.45 67	99.17 59	95.85 46	92.10 193	88.97 173	98.78 82	99.02 44	99.11 24	99.88 4	99.63 137

thres100view900		96.72 110	96.47 163	97.00 73	96.31 97	99.52 59	98.28 85	94.01 74	97.35 192	94.52 76	95.90 141	86.93 184	99.09 54	98.07 118	97.87 120	99.81 23	99.63 137

test2506		97.16 87	96.68 153	97.73 48	96.95 87	99.79 4	98.48 70	94.42 68	99.17 59	97.74 24	99.15 26	80.93 236	98.89 69	99.03 42	99.09 25	99.88 4	99.62 139

Effi-MVS+-dtu		95.74 146	98.04 87	93.06 174	93.92 172	99.16 124	97.90 104	88.16 199	99.07 86	82.02 204	98.02 80	94.32 122	96.74 157	98.53 86	97.56 136	99.61 144	99.62 139

HQP-MVS		96.37 130	96.58 154	96.13 110	97.31 79	98.44 170	98.45 73	95.22 52	98.86 105	88.58 156	98.33 71	87.00 183	97.67 133	97.23 172	96.56 166	99.56 169	99.62 139

ECVR-MVS		97.27 81	97.09 132	97.48 55	96.95 87	99.79 4	98.48 70	94.42 68	99.17 59	96.28 41	93.54 178	89.39 169	98.89 69	99.03 42	99.09 25	99.88 4	99.61 142

IB-MVS	93.96 15	95.02 159	96.44 166	93.36 169	97.05 85	99.28 113	90.43 240	93.39 89	98.02 170	96.02 43	94.92 164	92.07 145	83.52 250	95.38 215	95.82 190	99.72 79	99.59 143
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
train_agg		98.73 37	99.11 41	98.28 36	99.36 40	99.35 104	99.48 26	97.96 35	98.83 112	93.86 92	98.70 56	99.86 39	99.44 24	99.08 40	98.38 76	99.61 144	99.58 144

CDPH-MVS		98.41 47	99.10 42	97.61 52	99.32 43	99.36 101	99.49 24	96.15 46	98.82 114	91.82 137	98.41 67	99.66 52	99.10 52	98.93 51	98.97 39	99.75 47	99.58 144

APD-MVS		99.25 13	99.38 24	99.09 12	99.69 8	99.58 49	99.56 20	98.32 8	98.85 107	97.87 21	98.91 44	99.92 29	99.30 36	99.45 16	99.38 8	99.79 31	99.58 144
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.67 39	99.41 23	97.81 47	99.37 38	99.53 56	98.51 69	95.52 50	99.27 44	94.85 70	99.56 10	99.69 51	99.04 57	99.36 21	98.88 46	99.60 152	99.58 144

PHI-MVS		99.08 23	99.43 21	98.67 29	99.15 46	99.59 46	99.11 44	97.35 41	99.14 70	97.30 29	99.44 14	99.96 12	99.32 33	98.89 56	99.39 7	99.79 31	99.58 144

MVS_111021_HR		98.59 43	99.36 26	97.68 49	99.42 36	99.61 39	98.14 94	94.81 56	99.31 38	95.00 68	99.51 11	99.79 46	99.00 60	98.94 50	98.83 52	99.69 104	99.57 149

SF-MVS		99.18 17	99.32 30	99.03 17	99.65 19	99.41 91	98.87 56	98.24 19	99.14 70	98.73 7	99.11 30	99.92 29	98.92 63	99.22 29	98.84 51	99.76 41	99.56 150

DeepPCF-MVS	97.74 3	98.34 49	99.46 14	97.04 67	98.82 53	99.33 109	96.28 174	97.47 40	99.58 9	94.70 73	98.99 38	99.85 41	97.24 145	99.55 10	99.34 9	97.73 230	99.56 150

CLD-MVS		96.74 109	96.51 159	97.01 72	96.71 91	98.62 157	98.73 61	94.38 70	98.94 97	94.46 80	97.33 94	87.03 182	98.07 118	97.20 174	96.87 156	99.72 79	99.54 152
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CANet_DTU		96.64 120	99.08 43	93.81 154	97.10 84	99.42 88	98.85 57	90.01 162	99.31 38	79.98 216	99.78 2	99.10 64	97.42 141	98.35 97	98.05 110	99.47 185	99.53 153

pmmvs6		91.90 224	92.53 227	91.17 208	91.81 206	97.63 205	93.23 227	88.37 196	93.43 249	80.61 210	77.32 251	87.47 179	94.12 222	96.58 188	95.72 192	98.88 217	99.53 153

baseline1		97.58 69	98.05 85	97.02 70	96.21 102	99.45 71	97.71 114	93.71 85	98.47 143	95.75 47	98.78 50	93.20 137	98.91 64	98.52 87	98.44 71	99.81 23	99.53 153

FA-MVS(training)		96.52 125	98.29 72	94.45 141	95.88 113	99.52 59	97.66 122	81.47 233	98.94 97	93.79 96	95.54 155	99.11 63	98.29 110	98.89 56	96.49 168	99.63 141	99.52 156

FC-MVSNet-test		96.07 139	97.94 93	93.89 152	93.60 181	98.67 154	96.62 165	90.30 161	98.76 126	88.62 155	95.57 154	97.63 81	94.48 217	97.97 131	97.48 142	99.71 90	99.52 156

CNVR-MVS		99.23 15	99.28 33	99.17 6	99.65 19	99.34 106	99.46 27	98.21 21	99.28 42	98.47 10	98.89 46	99.94 25	99.50 16	99.42 18	98.61 62	99.73 67	99.52 156

PLC	97.93 2	99.02 29	98.94 53	99.11 11	99.46 35	99.24 118	99.06 48	97.96 35	99.31 38	99.16 3	97.90 82	99.79 46	99.36 29	98.71 71	98.12 106	99.65 131	99.52 156
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MAR-MVS		97.71 65	98.04 87	97.32 58	99.35 42	98.91 136	97.65 123	91.68 131	98.00 171	97.01 33	97.72 89	94.83 114	98.85 75	98.44 92	98.86 47	99.41 194	99.52 156
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
NCCC		99.05 26	99.08 43	99.02 19	99.62 23	99.38 94	99.43 31	98.21 21	99.36 32	97.66 25	97.79 84	99.90 34	99.45 23	99.17 33	98.43 73	99.77 39	99.51 161

OpenMVS	96.23 11	97.95 59	98.45 68	97.35 57	99.52 33	99.42 88	98.91 55	94.61 61	98.87 104	92.24 130	94.61 167	99.05 65	99.10 52	98.64 75	99.05 31	99.74 54	99.51 161

Fast-Effi-MVS+-dtu		95.38 153	98.20 79	92.09 187	93.91 173	98.87 138	97.35 134	85.01 224	99.08 81	81.09 208	98.10 76	96.36 94	95.62 196	98.43 93	97.03 152	99.55 171	99.50 163

ACMM	96.26 9	96.67 117	96.69 152	96.66 80	97.29 80	98.46 168	96.48 169	95.09 53	99.21 54	93.19 107	98.78 50	86.73 187	98.17 112	97.84 142	96.32 173	99.74 54	99.49 164
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		97.99 58	99.24 36	96.53 86	98.34 62	99.61 39	98.36 81	89.80 168	99.27 44	95.08 67	99.81 1	98.58 69	98.64 97	99.02 44	98.92 43	98.93 215	99.48 165

TAPA-MVS	97.53 5	98.41 47	98.84 58	97.91 45	99.08 48	99.33 109	99.15 41	97.13 42	99.34 36	93.20 106	97.75 87	99.19 61	99.20 40	98.66 73	98.13 103	99.66 126	99.48 165
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GA-MVS		93.93 183	96.31 169	91.16 209	93.61 180	98.79 141	95.39 191	90.69 156	98.25 161	73.28 243	96.15 134	88.42 175	94.39 219	97.76 146	95.35 198	99.58 162	99.45 167

CVMVSNet		95.33 155	97.09 132	93.27 171	95.23 157	98.39 175	95.49 188	92.58 120	97.71 186	83.00 198	94.44 171	93.28 135	93.92 227	97.79 143	98.54 66	99.41 194	99.45 167

LS3D		97.79 61	98.25 74	97.26 62	98.40 61	99.63 31	99.53 21	98.63 1	99.25 48	88.13 158	96.93 112	94.14 124	99.19 41	99.14 36	99.23 19	99.69 104	99.42 169

ET-MVSNet_ETH3D		96.17 135	96.99 142	95.21 131	88.53 239	98.54 163	98.28 85	92.61 119	98.85 107	93.60 100	99.06 36	90.39 157	98.63 98	95.98 209	96.68 160	99.61 144	99.41 170

baseline2		96.36 131	97.82 96	94.65 137	94.60 168	99.09 127	96.45 170	89.63 170	98.36 154	91.29 144	97.60 92	94.13 125	96.37 168	98.45 90	97.70 129	99.54 175	99.41 170

usedtu_dtu_shiyan1		94.86 163	96.31 169	93.16 172	88.71 237	98.02 186	96.17 178	91.31 146	98.43 145	87.18 166	91.68 196	93.37 134	96.06 177	97.46 163	95.83 189	99.53 177	99.40 172

test0.0.03 1		96.69 112	98.12 83	95.01 133	95.49 151	98.99 131	95.86 181	90.82 151	98.38 152	92.54 121	96.66 119	97.33 83	95.75 191	97.75 147	98.34 81	99.60 152	99.40 172

testgi		95.67 147	97.48 113	93.56 162	95.07 160	99.00 129	95.33 192	88.47 194	98.80 117	86.90 169	97.30 95	92.33 142	95.97 180	97.66 151	97.91 118	99.60 152	99.38 174

TAMVS		95.53 149	96.50 161	94.39 143	93.86 175	99.03 128	96.67 163	89.55 172	97.33 194	90.64 146	93.02 190	91.58 148	96.21 171	97.72 149	97.43 146	99.43 191	99.36 175

AdaColmap		99.06 25	98.98 52	99.15 7	99.60 25	99.30 112	99.38 33	98.16 23	99.02 90	98.55 9	98.71 55	99.57 57	99.58 12	99.09 38	97.84 124	99.64 136	99.36 175

PM-MVS		89.55 237	90.30 242	88.67 232	87.06 240	95.60 237	90.88 237	84.51 228	96.14 220	75.75 231	86.89 236	63.47 261	94.64 216	96.85 183	93.89 222	99.17 209	99.29 177

TPM-MVS					99.57 27	98.90 137	98.79 60			96.52 39	98.62 58	99.91 32	97.56 136			99.44 189	99.28 178
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
DPM-MVS		98.31 51	98.53 65	98.05 41	98.76 56	98.77 144	99.13 42	98.07 31	99.10 77	94.27 86	96.70 117	99.84 42	98.70 89	97.90 138	98.11 107	99.40 196	99.28 178

pmmvs4		95.09 157	95.90 175	94.14 147	92.29 195	97.70 198	95.45 189	90.31 159	98.60 134	90.70 145	93.25 183	89.90 166	96.67 160	97.13 176	95.42 197	99.44 189	99.28 178

EG-PatchMatch MVS		92.45 211	93.92 208	90.72 219	92.56 190	98.43 172	94.88 202	84.54 227	97.18 197	79.55 218	86.12 239	83.23 223	93.15 234	97.22 173	96.00 183	99.67 121	99.27 181

UA-Net		97.13 89	99.14 40	94.78 135	97.21 81	99.38 94	97.56 127	92.04 124	98.48 142	88.03 159	98.39 69	99.91 32	94.03 224	99.33 25	99.23 19	99.81 23	99.25 182

pmmvs-eth3d		89.81 236	89.65 244	90.00 225	86.94 241	95.38 239	91.08 235	86.39 215	94.57 233	82.27 203	83.03 245	64.94 258	93.96 225	96.57 189	93.82 224	99.35 199	99.24 183

gg-mvs-nofinetune		90.85 229	94.14 199	87.02 237	94.89 164	99.25 116	98.64 64	76.29 255	88.24 254	57.50 260	79.93 248	95.45 106	95.18 210	98.77 64	98.07 109	99.62 142	99.24 183

PMMVS		97.52 71	98.39 69	96.51 88	95.82 116	98.73 151	97.80 109	93.05 118	98.76 126	94.39 84	99.07 35	97.03 89	98.55 102	98.31 99	97.61 134	99.43 191	99.21 185

CNLPA		99.03 28	99.05 46	99.01 20	99.27 44	99.22 122	99.03 50	97.98 34	99.34 36	99.00 6	98.25 73	99.71 50	99.31 34	98.80 61	98.82 54	99.48 183	99.17 186

CR-MVSNet		94.57 173	97.34 121	91.33 204	94.90 163	98.59 160	97.15 147	79.14 245	97.98 172	80.42 212	96.59 125	93.50 133	96.85 154	98.10 113	97.49 140	99.50 181	99.15 187

PatchT		93.96 182	97.36 120	90.00 225	94.76 167	98.65 155	90.11 243	78.57 250	97.96 175	80.42 212	96.07 136	94.10 126	96.85 154	98.10 113	97.49 140	99.26 205	99.15 187

COLMAP_ROB	96.15 12	97.78 62	98.17 80	97.32 58	98.84 51	99.45 71	99.28 36	95.43 51	99.48 20	91.80 138	94.83 165	98.36 73	98.90 66	98.09 115	97.85 123	99.68 112	99.15 187
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MSDG		98.27 52	98.29 72	98.24 37	99.20 45	99.22 122	99.20 38	97.82 37	99.37 28	94.43 81	95.90 141	97.31 84	99.12 50	98.76 65	98.35 79	99.67 121	99.14 190

test-mter		94.86 163	97.32 123	92.00 190	92.41 193	98.82 140	96.18 177	86.35 216	98.05 169	82.28 202	96.48 129	94.39 121	95.46 203	98.17 110	96.20 177	99.32 201	99.13 191

RPMNet		94.66 167	97.16 130	91.75 197	94.98 162	98.59 160	97.00 154	78.37 251	97.98 172	83.78 189	96.27 132	94.09 127	96.91 152	97.36 167	96.73 158	99.48 183	99.09 192

OMC-MVS		98.84 33	99.01 51	98.65 30	99.39 37	99.23 121	99.22 37	96.70 43	99.40 25	97.77 23	97.89 83	99.80 44	99.21 39	99.02 44	98.65 60	99.57 166	99.07 193

TSAR-MVS + COLMAP		96.79 106	96.55 156	97.06 66	97.70 72	98.46 168	99.07 47	96.23 45	99.38 26	91.32 143	98.80 48	85.61 197	98.69 92	97.64 155	96.92 155	99.37 198	99.06 194

tpm		92.38 216	94.79 189	89.56 229	94.30 170	97.50 215	94.24 224	78.97 248	97.72 185	74.93 237	97.97 81	82.91 225	96.60 163	93.65 230	94.81 214	98.33 222	98.98 195

PatchMatch-RL		97.77 63	98.25 74	97.21 63	99.11 47	99.25 116	97.06 153	94.09 73	98.72 130	95.14 66	98.47 65	96.29 95	98.43 107	98.65 74	97.44 145	99.45 187	98.94 196

pmmvs5		92.71 208	94.27 198	90.90 213	91.42 219	97.74 197	93.23 227	86.66 213	95.99 225	78.96 222	91.45 198	83.44 221	95.55 198	97.30 170	95.05 207	99.58 162	98.93 197

test-LLR		95.50 150	97.32 123	93.37 168	95.49 151	98.74 149	96.44 171	90.82 151	98.18 163	82.75 199	96.60 123	94.67 117	95.54 199	98.09 115	96.00 183	99.20 207	98.93 197

TESTMET0.1,1		94.95 160	97.32 123	92.20 185	92.62 188	98.74 149	96.44 171	86.67 212	98.18 163	82.75 199	96.60 123	94.67 117	95.54 199	98.09 115	96.00 183	99.20 207	98.93 197

EU-MVSNet		92.80 203	94.76 190	90.51 220	91.88 203	96.74 230	92.48 232	88.69 191	96.21 218	79.00 221	91.51 197	87.82 177	91.83 240	95.87 211	96.27 174	99.21 206	98.92 200

PCF-MVS	97.50 6	98.18 55	98.35 71	97.99 43	98.65 57	99.36 101	98.94 54	98.14 27	98.59 135	93.62 99	96.61 122	99.76 49	99.03 58	97.77 145	97.45 144	99.57 166	98.89 201
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EPNet_dtu		96.30 132	98.53 65	93.70 159	98.97 50	98.24 181	97.36 133	94.23 72	98.85 107	79.18 220	99.19 23	98.47 71	94.09 223	97.89 139	98.21 95	98.39 221	98.85 202
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
usedtu_blend_shiyan5		92.28 220	91.78 230	92.86 177	82.44 247	94.55 246	96.69 161	89.26 175	93.99 241	95.31 56	97.12 104	83.52 217	95.91 181	88.61 244	85.85 249	97.57 236	98.84 203

blend_shiyan4		92.70 209	91.74 232	93.81 154	88.98 235	94.51 250	96.29 173	88.71 190	94.00 240	95.31 56	97.12 104	83.52 217	95.91 181	88.20 248	85.99 248	97.69 233	98.84 203

blended_shiyan6		90.91 227	91.00 237	90.80 216	82.44 247	94.60 245	94.86 205	89.05 182	94.08 238	84.93 184	90.75 206	83.74 208	95.81 186	88.79 241	86.19 246	97.71 231	98.83 205

FE-MVSNET3		92.14 222	91.78 230	92.55 180	82.44 247	94.55 246	94.83 206	89.26 175	93.99 241	95.31 56	97.12 104	83.52 217	95.91 181	88.61 244	85.85 249	97.57 236	98.83 205

OPM-MVS		96.22 134	95.85 178	96.65 81	97.75 70	98.54 163	99.00 53	95.53 48	96.88 205	89.88 152	95.95 139	86.46 191	98.07 118	97.65 154	96.63 162	99.67 121	98.83 205
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
usedtu_dtu_shiyan2		84.24 246	84.83 249	83.55 245	75.12 261	92.45 253	88.33 249	81.21 234	87.18 255	73.36 241	64.78 255	73.58 254	86.68 246	88.73 243	88.30 244	96.59 251	98.82 208

blended_shiyan8		90.91 227	90.97 238	90.84 215	82.45 246	94.62 243	94.96 198	89.15 181	93.94 246	85.03 181	90.85 205	83.58 215	95.78 190	88.79 241	86.19 246	97.70 232	98.80 209

gbinet_0.2-2-1-0.02		91.19 226	91.20 235	91.18 207	83.37 244	94.62 243	95.06 194	89.43 173	94.06 239	85.87 174	91.99 194	84.54 206	95.79 189	88.81 240	85.62 253	97.56 240	98.74 210

wanda-best-256-512		90.85 229	90.88 239	90.80 216	82.44 247	94.55 246	94.83 206	89.26 175	93.99 241	84.94 182	90.86 203	83.70 209	95.80 187	88.61 244	85.85 249	97.57 236	98.64 211

FE-blended-shiyan7		90.85 229	90.88 239	90.80 216	82.44 247	94.55 246	94.83 206	89.26 175	93.99 241	84.94 182	90.86 203	83.70 209	95.80 187	88.61 244	85.85 249	97.57 236	98.64 211

GG-mvs-BLEND		69.11 252	98.13 82	35.26 256	3.49 266	98.20 183	94.89 201	2.38 263	98.42 147	5.82 268	96.37 131	98.60 68	5.97 262	98.75 67	97.98 112	99.01 212	98.61 213

ambc			80.99 252		80.04 256	90.84 254	90.91 236		96.09 221	74.18 239	62.81 256	30.59 267	82.44 251	96.25 203	91.77 234	95.91 255	98.56 214

MDTV_nov1_ep13_2view		92.44 212	95.66 179	88.68 231	91.05 226	97.92 191	92.17 233	79.64 241	98.83 112	76.20 230	91.45 198	93.51 132	95.04 212	95.68 213	93.70 225	97.96 226	98.53 215

USDC		94.26 176	94.83 188	93.59 161	96.02 106	98.44 170	97.84 105	88.65 192	98.86 105	82.73 201	94.02 173	80.56 237	96.76 156	97.28 171	96.15 180	99.55 171	98.50 216

0.4-1-1-0.1		93.46 189	92.78 225	94.25 144	89.58 232	95.89 235	96.90 157	89.00 183	94.50 234	95.29 60	97.21 97	83.62 213	97.58 135	88.01 249	91.72 236	97.15 246	98.48 217

FE-MVSNET2		87.81 242	88.02 247	87.56 235	80.30 255	96.14 233	90.86 238	87.34 207	93.58 247	74.84 238	71.50 253	65.61 257	92.53 238	96.74 185	94.12 220	99.50 181	98.47 218

MDA-MVSNet-bldmvs		87.84 241	89.22 245	86.23 239	81.74 252	96.77 229	83.74 255	89.57 171	94.50 234	72.83 247	96.64 120	64.47 260	92.71 236	81.43 255	92.28 231	96.81 250	98.47 218

test_method		87.27 243	91.58 233	82.25 247	75.65 259	87.52 259	86.81 253	72.60 258	97.51 189	73.20 244	85.07 241	79.97 242	88.69 243	97.31 169	95.24 201	96.53 252	98.41 220

gm-plane-assit		89.44 238	92.82 224	85.49 241	91.37 221	95.34 240	79.55 259	82.12 232	91.68 253	64.79 257	87.98 228	80.26 240	95.66 194	98.51 89	97.56 136	99.45 187	98.41 220

MS-PatchMatch		95.99 141	97.26 127	94.51 139	97.46 74	98.76 147	97.27 138	86.97 209	99.09 78	89.83 153	93.51 180	97.78 79	96.18 173	97.53 160	95.71 193	99.35 199	98.41 220

TransMVSNet (Re)		93.45 190	94.08 202	92.72 179	92.83 186	97.62 208	94.94 199	91.54 137	95.65 229	83.06 197	88.93 220	83.53 216	94.25 220	97.41 164	97.03 152	99.67 121	98.40 223

TinyColmap		94.00 180	94.35 197	93.60 160	95.89 111	98.26 179	97.49 129	88.82 187	98.56 138	83.21 195	91.28 200	80.48 239	96.68 159	97.34 168	96.26 176	99.53 177	98.24 224

0.3-1-1-0.015		93.30 193	92.54 226	94.20 145	89.52 234	95.62 236	96.78 159	88.89 185	94.12 237	95.31 56	97.26 96	83.52 217	97.69 131	87.57 251	91.45 238	96.99 247	98.23 225

TDRefinement		93.04 199	93.57 213	92.41 181	96.58 92	98.77 144	97.78 111	91.96 127	98.12 166	80.84 209	89.13 219	79.87 244	87.78 245	96.44 191	94.50 218	99.54 175	98.15 226

MDTV_nov1_ep13		95.57 148	97.48 113	93.35 170	95.43 153	98.97 133	97.19 144	83.72 231	98.92 102	87.91 161	97.75 87	96.12 100	97.88 127	96.84 184	95.64 194	97.96 226	98.10 227

MIMVSNet		94.49 174	97.59 109	90.87 214	91.74 208	98.70 153	94.68 214	78.73 249	97.98 172	83.71 192	97.71 90	94.81 115	96.96 151	97.97 131	97.92 116	99.40 196	98.04 228

0.4-1-1-0.2		93.21 195	92.46 228	94.08 149	89.56 233	95.52 238	96.71 160	88.73 189	93.97 245	95.29 60	97.17 103	83.59 214	97.33 143	87.65 250	91.30 239	96.89 249	98.03 229

CostFormer		94.25 177	94.88 187	93.51 165	95.43 153	98.34 178	96.21 176	80.64 237	97.94 176	94.01 87	98.30 72	86.20 194	97.52 137	92.71 232	92.69 228	97.23 245	98.02 230

pmnet_mix02		92.44 212	94.68 191	89.83 228	92.46 192	97.65 204	89.92 245	90.49 158	98.76 126	73.05 245	91.78 195	90.08 163	94.86 215	94.53 226	91.94 233	98.21 224	98.01 231

RPSCF		97.61 68	98.16 81	96.96 75	98.10 65	99.00 129	98.84 58	93.76 81	99.45 21	94.78 72	99.39 17	99.31 59	98.53 104	96.61 186	95.43 196	97.74 228	97.93 232

Anonymous20231206		90.70 233	93.93 207	86.92 238	90.21 231	96.79 228	90.30 242	86.61 214	96.05 223	69.25 250	88.46 224	84.86 204	85.86 248	97.11 177	96.47 170	99.30 202	97.80 233

SCA		94.95 160	97.44 117	92.04 188	95.55 141	99.16 124	96.26 175	79.30 244	99.02 90	85.73 177	98.18 74	97.13 87	97.69 131	96.03 207	94.91 210	97.69 233	97.65 234

FE-MVSNET		86.50 244	88.24 246	84.47 244	76.04 257	94.06 251	87.91 250	86.26 217	92.71 250	69.03 252	77.33 250	66.72 256	88.34 244	95.57 214	93.83 223	99.27 204	97.48 235

pmmvs3		88.19 240	91.27 234	84.60 243	85.60 243	93.66 252	85.68 254	81.13 235	92.36 252	63.66 259	89.51 215	77.10 251	93.22 233	96.37 194	92.40 229	98.30 223	97.46 236

N_pmnet		92.21 221	94.60 193	89.42 230	91.88 203	97.38 221	89.15 247	89.74 169	97.89 178	73.75 240	87.94 229	92.23 144	93.85 228	96.10 205	93.20 227	98.15 225	97.43 237

PatchmatchNet		94.70 166	97.08 134	91.92 193	95.53 143	98.85 139	95.77 182	79.54 242	98.95 95	85.98 173	98.52 60	96.45 91	97.39 142	95.32 216	94.09 221	97.32 242	97.38 238
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ADS-MVSNet		94.65 168	97.04 138	91.88 196	95.68 127	98.99 131	95.89 180	79.03 247	99.15 65	85.81 176	96.96 109	98.21 76	97.10 147	94.48 227	94.24 219	97.74 228	97.21 239

MVS-HIRNet		92.51 210	95.97 173	88.48 233	93.73 179	98.37 176	90.33 241	75.36 257	98.32 157	77.78 226	89.15 218	94.87 113	95.14 211	97.62 156	96.39 171	98.51 218	97.11 240

dps		94.63 169	95.31 184	93.84 153	95.53 143	98.71 152	96.54 166	80.12 239	97.81 184	97.21 30	96.98 108	92.37 141	96.34 170	92.46 234	91.77 234	97.26 244	97.08 241

test20.03		90.65 234	93.71 211	87.09 236	90.44 229	96.24 231	89.74 246	85.46 221	95.59 230	72.99 246	90.68 208	85.33 199	84.41 249	95.94 210	95.10 206	99.52 179	97.06 242

EPMVS		95.05 158	96.86 147	92.94 176	95.84 114	98.96 134	96.68 162	79.87 240	99.05 87	90.15 149	97.12 104	95.99 102	97.49 139	95.17 219	94.75 215	97.59 235	96.96 243

tpmrst		93.86 185	95.88 176	91.50 200	95.69 124	98.62 157	95.64 185	79.41 243	98.80 117	83.76 191	95.63 152	96.13 99	97.25 144	92.92 231	92.31 230	97.27 243	96.74 244

new-patchmatchnet		86.12 245	87.30 248	84.74 242	86.92 242	95.19 242	83.57 256	84.42 229	92.67 251	65.66 254	80.32 247	64.72 259	89.41 242	92.33 236	89.21 242	98.43 220	96.69 245

tpm cat1		94.06 178	94.90 186	93.06 174	95.42 155	98.52 165	96.64 164	80.67 236	97.82 182	92.63 118	93.39 182	95.00 112	96.06 177	91.36 238	91.58 237	96.98 248	96.66 246

FMVSNet5		95.42 151	96.47 163	94.20 145	92.26 196	95.99 234	95.66 184	87.15 208	97.87 179	93.46 103	96.68 118	93.79 128	97.52 137	97.10 178	97.21 150	99.11 210	96.62 247

DeepMVS_CX						96.85 227	87.43 252	89.27 174	98.30 158	75.55 234	95.05 161	79.47 245	92.62 237	89.48 239		95.18 256	95.96 248

MIMVSNet1		88.61 239	90.68 241	86.19 240	81.56 253	95.30 241	87.78 251	85.98 219	94.19 236	72.30 248	78.84 249	78.90 248	90.06 241	96.59 187	95.47 195	99.46 186	95.49 249

CMPMVS	70.31 18	90.74 232	91.06 236	90.36 223	97.32 77	97.43 218	92.97 229	87.82 204	93.50 248	75.34 236	83.27 244	84.90 203	92.19 239	92.64 233	91.21 240	96.50 253	94.46 250
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		90.45 235	92.84 223	87.66 234	88.96 236	96.16 232	88.71 248	84.66 226	97.56 188	71.91 249	85.60 240	86.58 190	93.28 232	96.07 206	93.54 226	98.46 219	94.39 251

Gipuma		81.40 248	81.78 251	80.96 249	83.21 245	85.61 260	79.73 258	76.25 256	97.33 194	64.21 258	55.32 257	55.55 262	86.04 247	92.43 235	92.20 232	96.32 254	93.99 252
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		77.26 250	79.47 253	74.70 251	76.00 258	88.37 257	74.22 260	76.34 254	78.31 257	54.13 261	69.96 254	52.50 263	70.14 256	84.83 253	88.71 243	97.35 241	93.58 253

MVE	67.97 19	65.53 255	67.43 257	63.31 255	59.33 263	74.20 261	53.09 266	70.43 259	66.27 260	43.13 262	45.98 261	30.62 266	70.65 255	79.34 257	86.30 245	83.25 263	89.33 254
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		81.36 249	89.93 243	71.35 252	88.65 238	87.85 258	71.46 261	88.12 200	96.23 217	32.21 265	92.61 192	83.00 224	56.27 259	91.92 237	89.43 241	91.39 259	88.49 255

FPMVS		83.82 247	84.61 250	82.90 246	90.39 230	90.71 255	90.85 239	84.10 230	95.47 231	65.15 255	83.44 243	74.46 253	75.48 252	81.63 254	79.42 256	91.42 258	87.14 256

EMVS		68.12 254	68.11 256	68.14 254	75.51 260	71.76 262	55.38 265	77.20 253	77.78 258	37.79 264	53.59 258	43.61 264	74.72 253	67.05 259	76.70 258	88.27 262	86.24 257

E-PMN		68.30 253	68.43 255	68.15 253	74.70 262	71.56 263	55.64 264	77.24 252	77.48 259	39.46 263	51.95 260	41.68 265	73.28 254	70.65 258	79.51 255	88.61 261	86.20 258

PMVS	72.60 17	76.39 251	77.66 254	74.92 250	81.04 254	69.37 264	68.47 262	80.54 238	85.39 256	65.07 256	73.52 252	72.91 255	65.67 258	80.35 256	76.81 257	88.71 260	85.25 259
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		31.24 256	40.15 258	20.86 257	12.61 264	17.99 265	25.16 267	13.30 261	48.42 261	24.82 266	53.07 259	30.13 268	28.47 260	42.73 260	37.65 259	20.79 264	51.04 260

test123		26.75 257	34.25 259	18.01 258	7.93 265	17.18 266	24.85 268	12.36 262	44.83 262	16.52 267	41.80 262	18.10 269	28.29 261	33.08 261	34.79 260	18.10 265	49.95 261

uanet_test		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet-low-res		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

sosnet		0.00 258	0.00 260	0.00 259	0.00 267	0.00 267	0.00 269	0.00 264	0.00 263	0.00 269	0.00 263	0.00 270	0.00 263	0.00 262	0.00 261	0.00 266	0.00 262

TestfortrainingZip							99.83 1	98.29 12		99.52 2						99.71 90

RE-MVS-def										69.05 251

9.14												99.79 46

SR-MVS					99.67 14			98.25 16				99.94 25

our_test_3					92.30 194	97.58 210	90.09 244

MTAPA										98.09 17		99.97 8

MTMP										98.46 12		99.96 12

Patchmatch-RL test							66.86 263

tmp_tt				82.25 247	97.73 71	88.71 256	80.18 257	68.65 260	99.15 65	86.98 168	99.47 12	85.31 200	68.35 257	87.51 252	83.81 254	91.64 257

XVS					97.42 75	99.62 34	98.59 67			93.81 93		99.95 17				99.69 104

X-MVStestdata					97.42 75	99.62 34	98.59 67			93.81 93		99.95 17				99.69 104

mPP-MVS					99.53 31							99.89 36

NP-MVS									98.57 137

Patchmtry						98.59 160	97.15 147	79.14 245		80.42 212

High-resolution multi-view benchmark