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.

test_fmvsm_n_1920		98.44 40	98.61 23	97.92 134	99.27 100	95.18 178	100.00 1	98.90 47	98.05 12	99.80 17	99.73 78	92.64 121	99.99 36	99.58 38	99.51 102	98.59 214

DELS-MVS		98.54 32	98.22 43	99.50 30	99.15 107	98.65 51	100.00 1	98.58 85	97.70 20	98.21 129	99.24 137	92.58 124	99.94 77	98.63 91	99.94 54	99.92 81
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
PVSNet_Blended		97.94 63	97.64 73	98.83 81	99.59 81	96.99 109	100.00 1	99.10 31	95.38 90	98.27 125	99.08 146	89.00 187	99.95 69	99.12 58	99.25 118	99.57 137

MM				99.76 10		99.33 8	99.99 4	99.76 6	98.39 3	99.39 72	99.80 51	90.49 166	99.96 61	99.89 16	99.43 110	99.98 48

testing3		93.92 201	94.23 181	92.99 308	97.54 210	90.23 295	99.99 4	99.16 30	90.57 253	91.33 240	98.63 191	92.99 110	92.52 374	82.46 334	95.39 211	96.22 247

test_fmvsmconf_n		98.43 42	98.32 39	98.78 82	98.12 175	96.41 126	99.99 4	98.83 59	98.22 6	99.67 38	99.64 99	91.11 153	99.94 77	99.67 36	99.62 89	99.98 48

test_cas_vis1_n_1920		96.59 125	96.23 119	97.65 151	98.22 166	94.23 201	99.99 4	97.25 275	97.77 17	99.58 53	99.08 146	77.10 291	99.97 53	97.64 133	99.45 107	98.74 208

ET-MVSNet_ETH3D		94.37 192	93.28 210	97.64 152	98.30 159	97.99 69	99.99 4	97.61 236	94.35 122	71.57 378	99.45 117	96.23 31	95.34 348	96.91 154	85.14 293	99.59 130

CS-MVS		97.79 75	97.91 64	97.43 164	99.10 108	94.42 194	99.99 4	97.10 289	95.07 96	99.68 37	99.75 69	92.95 112	98.34 222	98.38 98	99.14 123	99.54 143

alignmvs		97.81 72	97.33 85	99.25 44	98.77 137	98.66 49	99.99 4	98.44 119	94.40 121	98.41 118	99.47 114	93.65 94	99.42 162	98.57 92	94.26 222	99.67 113

lupinMVS		97.85 68	97.60 75	98.62 93	97.28 228	97.70 81	99.99 4	97.55 242	95.50 89	99.43 66	99.67 94	90.92 157	98.71 191	98.40 97	99.62 89	99.45 157

EC-MVSNet		97.38 94	97.24 87	97.80 139	97.41 217	95.64 158	99.99 4	97.06 294	94.59 112	99.63 43	99.32 128	89.20 185	98.14 236	98.76 81	99.23 120	99.62 124

IB-MVS	92.85 6	94.99 172	93.94 189	98.16 123	97.72 200	95.69 157	99.99 4	98.81 60	94.28 127	92.70 223	96.90 252	95.08 51	99.17 169	96.07 163	73.88 362	99.60 129
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
fmvsm_l_conf0.5_n_a		99.00 14	98.91 14	99.28 43	99.21 101	97.91 74	99.98 14	98.85 56	98.25 4	99.92 2	99.75 69	94.72 61	99.97 53	99.87 19	99.64 87	99.95 71

fmvsm_l_conf0.5_n		98.94 15	98.84 17	99.25 44	99.17 105	97.81 77	99.98 14	98.86 53	98.25 4	99.90 3	99.76 63	94.21 79	99.97 53	99.87 19	99.52 99	99.98 48

fmvsm_s_conf0.5_n		97.80 73	97.85 67	97.67 150	99.06 110	94.41 195	99.98 14	98.97 40	97.34 29	99.63 43	99.69 87	87.27 202	99.97 53	99.62 37	99.06 127	98.62 213

test_vis1_n_1920		95.44 163	95.31 154	95.82 213	98.50 151	88.74 315	99.98 14	97.30 269	97.84 16	99.85 9	99.19 140	66.82 351	99.97 53	98.82 77	99.46 106	98.76 206

EIA-MVS		97.53 85	97.46 79	97.76 146	98.04 178	94.84 185	99.98 14	97.61 236	94.41 120	97.90 135	99.59 104	92.40 130	98.87 179	98.04 114	99.13 124	99.59 130

ETV-MVS		97.92 65	97.80 69	98.25 121	98.14 173	96.48 123	99.98 14	97.63 231	95.61 84	99.29 79	99.46 116	92.55 125	98.82 181	99.02 66	98.54 139	99.46 155

CANet		98.27 51	97.82 68	99.63 17	99.72 74	99.10 23	99.98 14	98.51 104	97.00 43	98.52 113	99.71 83	87.80 195	99.95 69	99.75 28	99.38 112	99.83 91

CS-MVS-test		97.88 66	97.94 62	97.70 149	99.28 99	95.20 177	99.98 14	97.15 284	95.53 87	99.62 46	99.79 55	92.08 138	98.38 218	98.75 82	99.28 117	99.52 147

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 59	99.98 14	98.86 53	97.10 40	99.80 17	99.94 4	95.92 36	100.00 1	99.51 40	100.00 1	100.00 1

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 14	98.69 68	98.20 7	99.93 1	99.98 2	96.82 23	100.00 1	99.75 28	100.00 1	99.99 23

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 50	98.72 139	97.71 79	99.98 14	98.44 119	96.85 46	99.80 17	99.91 14	97.57 8	99.85 108	99.44 46	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		98.41 44	98.21 44	99.03 68	99.86 53	97.10 105	99.98 14	98.80 62	90.78 251	99.62 46	99.78 59	95.30 47	100.00 1	99.80 25	99.93 60	99.99 23

CLD-MVS		94.06 200	93.90 190	94.55 255	96.02 266	90.69 284	99.98 14	97.72 225	96.62 58	91.05 243	98.85 180	77.21 290	98.47 203	98.11 110	89.51 246	94.48 256
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thisisatest0515		97.41 92	97.02 98	98.59 97	97.71 202	97.52 87	99.97 27	98.54 98	91.83 218	97.45 146	99.04 149	97.50 9	99.10 172	94.75 187	96.37 190	99.16 186

Fast-Effi-MVS+		95.02 171	94.19 182	97.52 159	97.88 185	94.55 191	99.97 27	97.08 292	88.85 285	94.47 202	97.96 222	84.59 230	98.41 210	89.84 272	97.10 174	99.59 130

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 27	98.64 76	98.47 2	99.13 85	99.92 13	96.38 30	100.00 1	99.74 30	100.00 1	100.00 1

TSAR-MVS + GP.		98.60 29	98.51 27	98.86 80	99.73 72	96.63 119	99.97 27	97.92 212	98.07 11	98.76 102	99.55 108	95.00 56	99.94 77	99.91 15	97.68 162	99.99 23

jason		97.24 98	96.86 101	98.38 116	95.73 279	97.32 97	99.97 27	97.40 260	95.34 92	98.60 112	99.54 110	87.70 196	98.56 199	97.94 120	99.47 104	99.25 181
jason: jason.
NCCC		99.37 2	99.25 2	99.71 14	99.96 8	99.15 21	99.97 27	98.62 81	98.02 13	99.90 3	99.95 3	97.33 17	100.00 1	99.54 39	100.00 1	100.00 1

CP-MVS		98.45 39	98.32 39	98.87 79	99.96 8	96.62 120	99.97 27	98.39 149	94.43 117	98.90 94	99.87 24	94.30 75	100.00 1	99.04 63	99.99 21	99.99 23

fmvsm_s_conf0.5_n_a		97.73 80	97.72 70	97.77 144	98.63 144	94.26 200	99.96 34	98.92 46	97.18 39	99.75 29	99.69 87	87.00 207	99.97 53	99.46 44	98.89 130	99.08 194

test_fmvs1		95.35 165	95.68 146	94.36 266	98.99 116	84.98 345	99.96 34	96.65 330	97.60 22	99.73 32	98.96 161	71.58 331	99.93 85	98.31 102	99.37 113	98.17 220

GeoE		94.36 194	93.48 202	96.99 179	97.29 227	93.54 219	99.96 34	96.72 327	88.35 295	93.43 212	98.94 168	82.05 246	98.05 242	88.12 290	96.48 188	99.37 166

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 34	98.43 127	97.27 34	99.80 17	99.94 4	96.71 24	100.00 1	100.00 1	100.00 1	100.00 1

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 34				99.80 51	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

save fliter					99.82 58	98.79 38	99.96 34	98.40 146	97.66 21

test0726					99.93 24	99.29 15	99.96 34	98.42 138	97.28 32	99.86 7	99.94 4	97.22 19

DPM-MVS		98.83 21	98.46 29	99.97 1	99.33 97	99.92 1	99.96 34	98.44 119	97.96 14	99.55 54	99.94 4	97.18 21	100.00 1	93.81 209	99.94 54	99.98 48

TEST9					99.92 31	98.92 28	99.96 34	98.43 127	93.90 148	99.71 34	99.86 26	95.88 37	99.85 108

train_agg		98.88 19	98.65 20	99.59 23	99.92 31	98.92 28	99.96 34	98.43 127	94.35 122	99.71 34	99.86 26	95.94 34	99.85 108	99.69 35	99.98 32	99.99 23

test_8					99.92 31	98.88 31	99.96 34	98.43 127	94.35 122	99.69 36	99.85 30	95.94 34	99.85 108

region2R		98.54 32	98.37 35	99.05 66	99.96 8	97.18 101	99.96 34	98.55 95	94.87 103	99.45 64	99.85 30	94.07 83	100.00 1	98.67 86	100.00 1	99.98 48

test-LLR		96.47 128	96.04 123	97.78 142	97.02 235	95.44 164	99.96 34	98.21 180	94.07 136	95.55 188	96.38 269	93.90 88	98.27 230	90.42 263	98.83 134	99.64 119

TESTMET0.1,1		96.74 118	96.26 118	98.16 123	97.36 221	96.48 123	99.96 34	98.29 172	91.93 215	95.77 186	98.07 215	95.54 42	98.29 226	90.55 260	98.89 130	99.70 108

test-mter		96.39 133	95.93 135	97.78 142	97.02 235	95.44 164	99.96 34	98.21 180	91.81 220	95.55 188	96.38 269	95.17 48	98.27 230	90.42 263	98.83 134	99.64 119

CPTT-MVS		97.64 83	97.32 86	98.58 98	99.97 3	95.77 151	99.96 34	98.35 159	89.90 265	98.36 121	99.79 55	91.18 152	99.99 36	98.37 99	99.99 21	99.99 23

cascas		94.64 183	93.61 195	97.74 148	97.82 190	96.26 133	99.96 34	97.78 224	85.76 327	94.00 208	97.54 231	76.95 295	99.21 165	97.23 142	95.43 210	97.76 230

DeepPCF-MVS	95.94 2	97.71 81	98.98 12	93.92 281	99.63 79	81.76 363	99.96 34	98.56 89	99.47 1	99.19 83	99.99 1	94.16 81	100.00 1	99.92 12	99.93 60	100.00 1

test_fmvsmvis_n_1920		97.67 82	97.59 77	97.91 136	97.02 235	95.34 169	99.95 52	98.45 115	97.87 15	97.02 154	99.59 104	89.64 175	99.98 43	99.41 48	99.34 115	98.42 216

patch_mono-2		98.24 55	99.12 5	95.59 217	99.67 77	86.91 336	99.95 52	98.89 49	97.60 22	99.90 3	99.76 63	96.54 28	99.98 43	99.94 11	99.82 76	99.88 85

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 52	98.43 127	96.48 59	99.80 17	99.93 11	97.44 14	100.00 1	99.92 12	99.98 32	100.00 1

FOURS1					99.92 31	97.66 83	99.95 52	98.36 157	95.58 85	99.52 59

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 52	98.32 166	97.28 32	99.83 13	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 84
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
test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 52	98.43 127					100.00 1	99.99 5	100.00 1	100.00 1

MSP-MVS		99.09 9	99.12 5	98.98 73	99.93 24	97.24 98	99.95 52	98.42 138	97.50 26	99.52 59	99.88 21	97.43 16	99.71 138	99.50 41	99.98 32	100.00 1
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
HFP-MVS		98.56 31	98.37 35	99.14 59	99.96 8	97.43 94	99.95 52	98.61 82	94.77 105	99.31 76	99.85 30	94.22 77	100.00 1	98.70 84	99.98 32	99.98 48

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 52	98.56 89	97.56 25	99.44 65	99.85 30	95.38 46	100.00 1	99.31 51	99.99 21	99.87 87

test_prior2							99.95 52		95.78 79	99.73 32	99.76 63	96.00 33		99.78 27	100.00 1

ACMMPR		98.50 35	98.32 39	99.05 66	99.96 8	97.18 101	99.95 52	98.60 83	94.77 105	99.31 76	99.84 41	93.73 92	100.00 1	98.70 84	99.98 32	99.98 48

MP-MVS		98.23 56	97.97 58	99.03 68	99.94 13	97.17 104	99.95 52	98.39 149	94.70 109	98.26 127	99.81 50	91.84 143	100.00 1	98.85 76	99.97 42	99.93 76
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		98.39 46	98.20 45	98.97 74	99.97 3	96.92 112	99.95 52	98.38 153	95.04 97	98.61 111	99.80 51	93.39 97	100.00 1	98.64 89	100.00 1	99.98 48

PVSNet_BlendedMVS		96.05 144	95.82 141	96.72 188	99.59 81	96.99 109	99.95 52	99.10 31	94.06 138	98.27 125	95.80 284	89.00 187	99.95 69	99.12 58	87.53 277	93.24 336

PAPR		98.52 34	98.16 48	99.58 24	99.97 3	98.77 40	99.95 52	98.43 127	95.35 91	98.03 131	99.75 69	94.03 84	99.98 43	98.11 110	99.83 72	99.99 23

PVSNet	91.05 13	97.13 101	96.69 107	98.45 110	99.52 87	95.81 149	99.95 52	99.65 12	94.73 107	99.04 88	99.21 139	84.48 231	99.95 69	94.92 180	98.74 136	99.58 136

test_fmvsmconf0.1_n		97.74 78	97.44 80	98.64 92	95.76 276	96.20 138	99.94 68	98.05 199	98.17 8	98.89 95	99.42 118	87.65 197	99.90 91	99.50 41	99.60 95	99.82 92

ZNCC-MVS		98.31 48	98.03 55	99.17 53	99.88 49	97.59 84	99.94 68	98.44 119	94.31 125	98.50 115	99.82 46	93.06 109	99.99 36	98.30 103	99.99 21	99.93 76

test_prior4						98.05 66	99.94 68

XVS		98.70 25	98.55 25	99.15 57	99.94 13	97.50 90	99.94 68	98.42 138	96.22 71	99.41 68	99.78 59	94.34 73	99.96 61	98.92 70	99.95 49	99.99 23

X-MVStestdata		93.83 203	92.06 235	99.15 57	99.94 13	97.50 90	99.94 68	98.42 138	96.22 71	99.41 68	41.37 400	94.34 73	99.96 61	98.92 70	99.95 49	99.99 23

SD-MVS		98.92 17	98.70 19	99.56 25	99.70 76	98.73 44	99.94 68	98.34 163	96.38 65	99.81 15	99.76 63	94.59 64	99.98 43	99.84 22	99.96 46	99.97 58
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
PVSNet_0	88.03 19	91.80 254	90.27 267	96.38 200	98.27 163	90.46 291	99.94 68	99.61 14	93.99 142	86.26 324	97.39 237	71.13 335	99.89 96	98.77 80	67.05 378	98.79 205

GST-MVS		98.27 51	97.97 58	99.17 53	99.92 31	97.57 85	99.93 75	98.39 149	94.04 141	98.80 98	99.74 76	92.98 111	100.00 1	98.16 107	99.76 80	99.93 76

test0.0.03 1		93.86 202	93.61 195	94.64 249	95.02 296	92.18 252	99.93 75	98.58 85	94.07 136	87.96 299	98.50 200	93.90 88	94.96 353	81.33 341	93.17 232	96.78 239

MVS_111021_HR		98.72 24	98.62 22	99.01 71	99.36 96	97.18 101	99.93 75	99.90 1	96.81 51	98.67 107	99.77 61	93.92 86	99.89 96	99.27 53	99.94 54	99.96 64

thisisatest0530		97.10 102	96.72 106	98.22 122	97.60 208	96.70 117	99.92 78	98.54 98	91.11 241	97.07 153	98.97 159	97.47 12	99.03 173	93.73 214	96.09 193	98.92 197

PVSNet_Blended_VisFu		97.27 97	96.81 103	98.66 90	98.81 134	96.67 118	99.92 78	98.64 76	94.51 114	96.38 173	98.49 201	89.05 186	99.88 102	97.10 146	98.34 143	99.43 160

DP-MVS Recon		98.41 44	98.02 56	99.56 25	99.97 3	98.70 46	99.92 78	98.44 119	92.06 212	98.40 120	99.84 41	95.68 40	100.00 1	98.19 105	99.71 83	99.97 58

PLC	95.54 3	97.93 64	97.89 66	98.05 130	99.82 58	94.77 189	99.92 78	98.46 114	93.93 146	97.20 150	99.27 132	95.44 45	99.97 53	97.41 137	99.51 102	99.41 162
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
9.14			98.38 33		99.87 51		99.91 82	98.33 164	93.22 167	99.78 26	99.89 19	94.57 65	99.85 108	99.84 22	99.97 42

iter_conf05		96.07 143	95.95 133	96.44 197	98.43 154	97.52 87	99.91 82	96.85 317	94.16 131	92.49 228	97.98 220	98.20 4	97.34 269	97.26 141	88.29 264	94.45 263

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 43	99.91 82	98.39 149	97.20 38	99.46 63	99.85 30	95.53 44	99.79 123	99.86 21	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVSTER		95.53 161	95.22 157	96.45 195	98.56 145	97.72 78	99.91 82	97.67 229	92.38 203	91.39 237	97.14 242	97.24 18	97.30 274	94.80 185	87.85 271	94.34 273

PMMVS		96.76 116	96.76 105	96.76 186	98.28 162	92.10 253	99.91 82	97.98 204	94.12 133	99.53 57	99.39 123	86.93 208	98.73 188	96.95 152	97.73 160	99.45 157

fmvsm_s_conf0.1_n		97.30 95	97.21 89	97.60 156	97.38 219	94.40 197	99.90 87	98.64 76	96.47 61	99.51 61	99.65 98	84.99 227	99.93 85	99.22 55	99.09 126	98.46 215

test_fmvs1_n		94.25 197	94.36 177	93.92 281	97.68 203	83.70 351	99.90 87	96.57 333	97.40 28	99.67 38	98.88 172	61.82 367	99.92 88	98.23 104	99.13 124	98.14 223

SF-MVS		98.67 26	98.40 31	99.50 30	99.77 65	98.67 47	99.90 87	98.21 180	93.53 158	99.81 15	99.89 19	94.70 63	99.86 107	99.84 22	99.93 60	99.96 64

原ACMM2							99.90 87

HPM-MVS		97.96 62	97.72 70	98.68 88	99.84 56	96.39 129	99.90 87	98.17 185	92.61 190	98.62 110	99.57 107	91.87 142	99.67 145	98.87 75	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPNet		98.49 36	98.40 31	98.77 84	99.62 80	96.80 116	99.90 87	99.51 17	97.60 22	99.20 81	99.36 126	93.71 93	99.91 89	97.99 117	98.71 137	99.61 127
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CSCG		97.10 102	97.04 96	97.27 174	99.89 45	91.92 258	99.90 87	99.07 34	88.67 288	95.26 194	99.82 46	93.17 107	99.98 43	98.15 108	99.47 104	99.90 83

PAPM		98.60 29	98.42 30	99.14 59	96.05 265	98.96 26	99.90 87	99.35 25	96.68 55	98.35 122	99.66 96	96.45 29	98.51 202	99.45 45	99.89 66	99.96 64

114514_t		97.41 92	96.83 102	99.14 59	99.51 89	97.83 75	99.89 95	98.27 175	88.48 292	99.06 87	99.66 96	90.30 168	99.64 148	96.32 160	99.97 42	99.96 64

WTY-MVS		98.10 60	97.60 75	99.60 22	98.92 124	99.28 17	99.89 95	99.52 15	95.58 85	98.24 128	99.39 123	93.33 99	99.74 134	97.98 119	95.58 208	99.78 100

GA-MVS		93.83 203	92.84 217	96.80 184	95.73 279	93.57 217	99.88 97	97.24 276	92.57 194	92.92 219	96.66 261	78.73 282	97.67 259	87.75 293	94.06 225	99.17 185

UniMVSNet (Re)		93.07 226	92.13 232	95.88 210	94.84 297	96.24 137	99.88 97	98.98 38	92.49 199	89.25 274	95.40 303	87.09 205	97.14 284	93.13 224	78.16 343	94.26 276

HPM-MVS_fast		97.80 73	97.50 78	98.68 88	99.79 62	96.42 125	99.88 97	98.16 189	91.75 222	98.94 92	99.54 110	91.82 144	99.65 147	97.62 135	99.99 21	99.99 23

test_vis1_n		93.61 213	93.03 214	95.35 224	95.86 271	86.94 334	99.87 100	96.36 340	96.85 46	99.54 56	98.79 181	52.41 380	99.83 118	98.64 89	98.97 129	99.29 178

test_vis1_rt		86.87 317	86.05 319	89.34 339	96.12 262	78.07 374	99.87 100	83.54 398	92.03 213	78.21 363	89.51 369	45.80 384	99.91 89	96.25 161	93.11 234	90.03 369

iter_conf_final		96.01 146	95.93 135	96.28 202	98.38 156	97.03 107	99.87 100	97.03 297	94.05 140	92.61 224	97.98 220	98.01 5	97.34 269	97.02 148	88.39 263	94.47 257

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 100	98.44 119	97.48 27	99.64 42	99.94 4	96.68 26	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MVS_0304		98.87 20	98.61 23	99.67 16	99.18 102	99.13 22	99.87 100	99.65 12	98.17 8	98.75 104	99.75 69	92.76 118	99.94 77	99.88 18	99.44 108	99.94 74

MTMP							99.87 100	96.49 336

CDPH-MVS		98.65 27	98.36 37	99.49 32	99.94 13	98.73 44	99.87 100	98.33 164	93.97 143	99.76 28	99.87 24	94.99 57	99.75 132	98.55 93	100.00 1	99.98 48

HQP-NCC					95.78 272		99.87 100		96.82 48	93.37 213

ACMP_Plane					95.78 272		99.87 100		96.82 48	93.37 213

APD-MVS		98.62 28	98.35 38	99.41 38	99.90 42	98.51 57	99.87 100	98.36 157	94.08 135	99.74 31	99.73 78	94.08 82	99.74 134	99.42 47	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.42 43	98.38 33	98.53 105	99.39 94	95.79 150	99.87 100	99.86 2	96.70 54	98.78 99	99.79 55	92.03 139	99.90 91	99.17 57	99.86 70	99.88 85

HQP-MVS		94.61 184	94.50 175	94.92 239	95.78 272	91.85 259	99.87 100	97.89 214	96.82 48	93.37 213	98.65 188	80.65 263	98.39 214	97.92 121	89.60 241	94.53 252

CNLPA		97.76 77	97.38 82	98.92 78	99.53 86	96.84 114	99.87 100	98.14 192	93.78 151	96.55 167	99.69 87	92.28 133	99.98 43	97.13 144	99.44 108	99.93 76

SMA-MVS		98.76 23	98.48 28	99.62 20	99.87 51	98.87 32	99.86 113	98.38 153	93.19 168	99.77 27	99.94 4	95.54 42	100.00 1	99.74 30	99.99 21	100.00 1
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
plane_prior						91.74 263	99.86 113		96.76 52						89.59 243

casdiffmvs_mvg		96.43 130	95.94 134	97.89 138	97.44 216	95.47 163	99.86 113	97.29 271	93.35 162	96.03 179	99.19 140	85.39 222	98.72 190	97.89 124	97.04 177	99.49 153
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tttt0517		96.85 111	96.49 113	97.92 134	97.48 215	95.89 148	99.85 116	98.54 98	90.72 252	96.63 164	98.93 170	97.47 12	99.02 174	93.03 226	95.76 204	98.85 201

ACMMP_NAP		98.49 36	98.14 49	99.54 27	99.66 78	98.62 53	99.85 116	98.37 156	94.68 110	99.53 57	99.83 43	92.87 114	100.00 1	98.66 88	99.84 71	99.99 23

thres200		96.96 107	96.21 120	99.22 46	98.97 118	98.84 35	99.85 116	99.71 7	93.17 169	96.26 175	98.88 172	89.87 173	99.51 152	94.26 198	94.91 216	99.31 174

F-COLMAP		96.93 109	96.95 99	96.87 183	99.71 75	91.74 263	99.85 116	97.95 207	93.11 171	95.72 187	99.16 143	92.35 131	99.94 77	95.32 172	99.35 114	98.92 197

test_fmvsmconf0.01_n		96.39 133	95.74 142	98.32 118	91.47 356	95.56 161	99.84 120	97.30 269	97.74 18	97.89 136	99.35 127	79.62 272	99.85 108	99.25 54	99.24 119	99.55 139

SR-MVS		98.46 38	98.30 42	98.93 77	99.88 49	97.04 106	99.84 120	98.35 159	94.92 101	99.32 75	99.80 51	93.35 98	99.78 125	99.30 52	99.95 49	99.96 64

CANet_DTU		96.76 116	96.15 121	98.60 95	98.78 136	97.53 86	99.84 120	97.63 231	97.25 37	99.20 81	99.64 99	81.36 254	99.98 43	92.77 229	98.89 130	98.28 219

casdiffmvs		96.42 132	95.97 130	97.77 144	97.30 226	94.98 181	99.84 120	97.09 291	93.75 153	96.58 166	99.26 135	85.07 225	98.78 184	97.77 130	97.04 177	99.54 143
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HQP_MVS		94.49 188	94.36 177	94.87 240	95.71 282	91.74 263	99.84 120	97.87 216	96.38 65	93.01 217	98.59 193	80.47 267	98.37 220	97.79 128	89.55 244	94.52 254

plane_prior2							99.84 120		96.38 65

BH-w/o		95.71 155	95.38 152	96.68 189	98.49 152	92.28 249	99.84 120	97.50 250	92.12 209	92.06 233	98.79 181	84.69 229	98.67 195	95.29 173	99.66 86	99.09 192

fmvsm_s_conf0.1_n_a		97.09 104	96.90 100	97.63 154	95.65 285	94.21 202	99.83 127	98.50 109	96.27 70	99.65 40	99.64 99	84.72 228	99.93 85	99.04 63	98.84 133	98.74 208

test_fmvs2		89.47 301	89.70 278	88.77 346	94.54 303	75.74 375	99.83 127	94.70 371	94.71 108	91.08 241	96.82 260	54.46 377	97.78 256	92.87 227	88.27 265	92.80 344

UniMVSNet_NR-MVSNet		92.95 228	92.11 233	95.49 218	94.61 302	95.28 172	99.83 127	99.08 33	91.49 227	89.21 277	96.86 255	87.14 204	96.73 311	93.20 220	77.52 348	94.46 258

APD-MVS_3200maxsize		98.25 54	98.08 54	98.78 82	99.81 60	96.60 121	99.82 130	98.30 171	93.95 145	99.37 73	99.77 61	92.84 115	99.76 131	98.95 67	99.92 63	99.97 58

PAPM_NR		98.12 59	97.93 63	98.70 87	99.94 13	96.13 142	99.82 130	98.43 127	94.56 113	97.52 143	99.70 85	94.40 68	99.98 43	97.00 149	99.98 32	99.99 23

nrg030		93.51 215	92.53 227	96.45 195	94.36 305	97.20 100	99.81 132	97.16 283	91.60 224	89.86 258	97.46 233	86.37 213	97.68 258	95.88 167	80.31 332	94.46 258

diffmvs		97.00 106	96.64 108	98.09 128	97.64 206	96.17 141	99.81 132	97.19 278	94.67 111	98.95 91	99.28 129	86.43 212	98.76 186	98.37 99	97.42 168	99.33 172
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DU-MVS		92.46 240	91.45 249	95.49 218	94.05 310	95.28 172	99.81 132	98.74 64	92.25 207	89.21 277	96.64 263	81.66 250	96.73 311	93.20 220	77.52 348	94.46 258

ACMP	92.05 9	92.74 232	92.42 230	93.73 287	95.91 270	88.72 316	99.81 132	97.53 246	94.13 132	87.00 312	98.23 211	74.07 322	98.47 203	96.22 162	88.86 253	93.99 305
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
mvsany_test1		97.82 71	97.90 65	97.55 157	98.77 137	93.04 232	99.80 136	97.93 209	96.95 45	99.61 52	99.68 93	90.92 157	99.83 118	99.18 56	98.29 148	99.80 96

Fast-Effi-MVS+-dtu		93.72 210	93.86 192	93.29 300	97.06 233	86.16 337	99.80 136	96.83 319	92.66 187	92.58 225	97.83 226	81.39 253	97.67 259	89.75 273	96.87 182	96.05 249

BH-untuned		95.18 167	94.83 169	96.22 204	98.36 158	91.22 275	99.80 136	97.32 267	90.91 245	91.08 241	98.67 185	83.51 238	98.54 201	94.23 199	99.61 93	98.92 197

tfpn200view9		96.79 114	95.99 125	99.19 49	98.94 120	98.82 36	99.78 139	99.71 7	92.86 174	96.02 180	98.87 175	89.33 180	99.50 154	93.84 206	94.57 217	99.27 179

thres400		96.78 115	95.99 125	99.16 55	98.94 120	98.82 36	99.78 139	99.71 7	92.86 174	96.02 180	98.87 175	89.33 180	99.50 154	93.84 206	94.57 217	99.16 186

TAPA-MVS	92.12 8	94.42 190	93.60 197	96.90 182	99.33 97	91.78 262	99.78 139	98.00 201	89.89 266	94.52 200	99.47 114	91.97 140	99.18 168	69.90 373	99.52 99	99.73 105
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + MP.		98.93 16	98.77 18	99.41 38	99.74 69	98.67 47	99.77 142	98.38 153	96.73 53	99.88 6	99.74 76	94.89 59	99.59 149	99.80 25	99.98 32	99.97 58
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
OPM-MVS		93.21 220	92.80 219	94.44 262	93.12 329	90.85 283	99.77 142	97.61 236	96.19 73	91.56 236	98.65 188	75.16 316	98.47 203	93.78 212	89.39 247	93.99 305
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v2v482		91.30 260	90.07 274	95.01 235	93.13 327	93.79 212	99.77 142	97.02 298	88.05 298	89.25 274	95.37 307	80.73 261	97.15 283	87.28 299	80.04 335	94.09 296

Baseline_NR-MVSNet		90.33 284	89.51 284	92.81 311	92.84 336	89.95 303	99.77 142	93.94 378	84.69 341	89.04 281	95.66 290	81.66 250	96.52 318	90.99 250	76.98 354	91.97 355

ACMM	91.95 10	92.88 229	92.52 228	93.98 280	95.75 278	89.08 313	99.77 142	97.52 248	93.00 172	89.95 255	97.99 219	76.17 305	98.46 206	93.63 216	88.87 252	94.39 267
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SR-MVS-dyc-post		98.31 48	98.17 47	98.71 86	99.79 62	96.37 130	99.76 147	98.31 168	94.43 117	99.40 70	99.75 69	93.28 103	99.78 125	98.90 73	99.92 63	99.97 58

RE-MVS-def			98.13 50		99.79 62	96.37 130	99.76 147	98.31 168	94.43 117	99.40 70	99.75 69	92.95 112		98.90 73	99.92 63	99.97 58

BH-RMVSNet		95.18 167	94.31 180	97.80 139	98.17 171	95.23 175	99.76 147	97.53 246	92.52 197	94.27 205	99.25 136	76.84 296	98.80 182	90.89 254	99.54 98	99.35 169

v148		90.70 274	89.63 279	93.92 281	92.97 334	90.97 277	99.75 150	96.89 314	87.51 303	88.27 296	95.01 320	81.67 249	97.04 293	87.40 297	77.17 353	93.75 321

PGM-MVS		98.34 47	98.13 50	98.99 72	99.92 31	97.00 108	99.75 150	99.50 18	93.90 148	99.37 73	99.76 63	93.24 105	100.00 1	97.75 132	99.96 46	99.98 48

LPG-MVS_test		92.96 227	92.71 221	93.71 289	95.43 289	88.67 317	99.75 150	97.62 233	92.81 178	90.05 251	98.49 201	75.24 312	98.40 212	95.84 168	89.12 248	94.07 297

thres100view900		96.74 118	95.92 137	99.18 50	98.90 129	98.77 40	99.74 153	99.71 7	92.59 192	95.84 183	98.86 177	89.25 182	99.50 154	93.84 206	94.57 217	99.27 179

MP-MVS-pluss		98.07 61	97.64 73	99.38 41	99.74 69	98.41 60	99.74 153	98.18 184	93.35 162	96.45 169	99.85 30	92.64 121	99.97 53	98.91 72	99.89 66	99.77 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
pmmvs5		90.17 290	89.09 291	93.40 297	92.10 348	89.77 306	99.74 153	95.58 356	85.88 326	87.24 311	95.74 286	73.41 325	96.48 320	88.54 283	83.56 305	93.95 308

thres600view7		96.69 121	95.87 140	99.14 59	98.90 129	98.78 39	99.74 153	99.71 7	92.59 192	95.84 183	98.86 177	89.25 182	99.50 154	93.44 218	94.50 220	99.16 186

baseline2		96.71 120	96.49 113	97.37 168	95.63 287	95.96 146	99.74 153	98.88 51	92.94 173	91.61 235	98.97 159	97.72 7	98.62 197	94.83 184	98.08 156	97.53 236

miper_enhance_ethall		94.36 194	93.98 187	95.49 218	98.68 141	95.24 174	99.73 158	97.29 271	93.28 166	89.86 258	95.97 282	94.37 72	97.05 291	92.20 233	84.45 298	94.19 282

testgi		89.01 306	88.04 307	91.90 320	93.49 321	84.89 346	99.73 158	95.66 354	93.89 150	85.14 331	98.17 212	59.68 371	94.66 357	77.73 357	88.88 251	96.16 248

sss		97.57 84	97.03 97	99.18 50	98.37 157	98.04 67	99.73 158	99.38 23	93.46 160	98.76 102	99.06 148	91.21 148	99.89 96	96.33 159	97.01 179	99.62 124

canonicalmvs		97.09 104	96.32 117	99.39 40	98.93 122	98.95 27	99.72 161	97.35 263	94.45 115	97.88 137	99.42 118	86.71 209	99.52 151	98.48 95	93.97 226	99.72 107

3Dnovator+	91.53 11	96.31 137	95.24 156	99.52 28	96.88 244	98.64 52	99.72 161	98.24 177	95.27 94	88.42 295	98.98 157	82.76 243	99.94 77	97.10 146	99.83 72	99.96 64

Syy-MVS		90.00 293	90.63 259	88.11 350	97.68 203	74.66 378	99.71 163	98.35 159	90.79 249	92.10 231	98.67 185	79.10 279	93.09 370	63.35 384	95.95 198	96.59 242

myMVS_eth3d		94.46 189	94.76 171	93.55 295	97.68 203	90.97 277	99.71 163	98.35 159	90.79 249	92.10 231	98.67 185	92.46 129	93.09 370	87.13 301	95.95 198	96.59 242

HyFIR lowres test		96.66 123	96.43 115	97.36 170	99.05 111	93.91 211	99.70 165	99.80 3	90.54 254	96.26 175	98.08 214	92.15 136	98.23 233	96.84 155	95.46 209	99.93 76

D2MVS		92.76 231	92.59 226	93.27 301	95.13 292	89.54 309	99.69 166	99.38 23	92.26 206	87.59 303	94.61 334	85.05 226	97.79 254	91.59 241	88.01 269	92.47 349

TranMVSNet+NR-MVSNet		91.68 258	90.61 260	94.87 240	93.69 317	93.98 209	99.69 166	98.65 74	91.03 243	88.44 291	96.83 259	80.05 270	96.18 331	90.26 267	76.89 356	94.45 263

V42		91.28 262	90.12 273	94.74 245	93.42 323	93.46 221	99.68 168	97.02 298	87.36 306	89.85 260	95.05 318	81.31 255	97.34 269	87.34 298	80.07 334	93.40 331

testmvs		40.60 364	44.45 367	29.05 382	19.49 405	14.11 408	99.68 168	18.47 405	20.74 398	64.59 383	98.48 204	10.95 403	17.09 402	56.66 391	11.01 398	55.94 395

mvsmamba		94.10 198	93.72 194	95.25 229	93.57 318	94.13 204	99.67 170	96.45 338	93.63 157	91.34 239	97.77 227	86.29 214	97.22 280	96.65 157	88.10 268	94.40 265

RRT_MVS		93.14 223	92.92 216	93.78 286	93.31 325	90.04 300	99.66 171	97.69 227	92.53 196	88.91 284	97.76 228	84.36 232	96.93 301	95.10 175	86.99 280	94.37 268

DeepC-MVS	94.51 4	96.92 110	96.40 116	98.45 110	99.16 106	95.90 147	99.66 171	98.06 197	96.37 68	94.37 203	99.49 113	83.29 241	99.90 91	97.63 134	99.61 93	99.55 139
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CHOSEN 1792x2688		96.81 113	96.53 112	97.64 152	98.91 128	93.07 229	99.65 173	99.80 3	95.64 83	95.39 191	98.86 177	84.35 234	99.90 91	96.98 150	99.16 122	99.95 71

Test_1112_low_res		95.72 153	94.83 169	98.42 113	97.79 192	96.41 126	99.65 173	96.65 330	92.70 184	92.86 222	96.13 278	92.15 136	99.30 163	91.88 238	93.64 228	99.55 139

1112_ss		96.01 146	95.20 158	98.42 113	97.80 191	96.41 126	99.65 173	96.66 329	92.71 183	92.88 221	99.40 121	92.16 135	99.30 163	91.92 237	93.66 227	99.55 139

OMC-MVS		97.28 96	97.23 88	97.41 165	99.76 66	93.36 227	99.65 173	97.95 207	96.03 75	97.41 147	99.70 85	89.61 176	99.51 152	96.73 156	98.25 149	99.38 164

test_yl		97.83 69	97.37 83	99.21 47	99.18 102	97.98 70	99.64 177	99.27 27	91.43 231	97.88 137	98.99 155	95.84 38	99.84 116	98.82 77	95.32 213	99.79 97

DCV-MVSNet		97.83 69	97.37 83	99.21 47	99.18 102	97.98 70	99.64 177	99.27 27	91.43 231	97.88 137	98.99 155	95.84 38	99.84 116	98.82 77	95.32 213	99.79 97

MG-MVS		98.91 18	98.65 20	99.68 15	99.94 13	99.07 24	99.64 177	99.44 20	97.33 31	99.00 90	99.72 81	94.03 84	99.98 43	98.73 83	100.00 1	100.00 1

v1144		91.09 266	89.83 275	94.87 240	93.25 326	93.69 216	99.62 180	96.98 303	86.83 316	89.64 266	94.99 323	80.94 258	97.05 291	85.08 319	81.16 321	93.87 315

cl22		93.77 207	93.25 211	95.33 226	99.49 90	94.43 193	99.61 181	98.09 194	90.38 256	89.16 280	95.61 291	90.56 164	97.34 269	91.93 236	84.45 298	94.21 281

WR-MVS		92.31 243	91.25 251	95.48 221	94.45 304	95.29 171	99.60 182	98.68 70	90.10 261	88.07 298	96.89 253	80.68 262	96.80 309	93.14 223	79.67 336	94.36 269

SDMVSNet		94.80 175	93.96 188	97.33 172	98.92 124	95.42 166	99.59 183	98.99 37	92.41 201	92.55 226	97.85 224	75.81 308	98.93 178	97.90 123	91.62 237	97.64 231

Effi-MVS+-dtu		94.53 187	95.30 155	92.22 316	97.77 193	82.54 356	99.59 183	97.06 294	94.92 101	95.29 193	95.37 307	85.81 217	97.89 251	94.80 185	97.07 175	96.23 246

DIV-MVS_self_test		92.32 242	91.60 243	94.47 260	97.31 225	92.74 237	99.58 185	96.75 325	86.99 313	87.64 302	95.54 295	89.55 177	96.50 319	88.58 282	82.44 311	94.17 283

FIs		94.10 198	93.43 203	96.11 206	94.70 300	96.82 115	99.58 185	98.93 45	92.54 195	89.34 272	97.31 238	87.62 198	97.10 288	94.22 200	86.58 282	94.40 265

cl____		92.31 243	91.58 244	94.52 256	97.33 224	92.77 235	99.57 187	96.78 324	86.97 314	87.56 304	95.51 298	89.43 178	96.62 315	88.60 281	82.44 311	94.16 288

EPNet_dtu		95.71 155	95.39 151	96.66 190	98.92 124	93.41 224	99.57 187	98.90 47	96.19 73	97.52 143	98.56 197	92.65 120	97.36 267	77.89 356	98.33 144	99.20 184
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v144192		90.79 273	89.52 283	94.59 252	93.11 330	92.77 235	99.56 189	96.99 301	86.38 320	89.82 261	94.95 325	80.50 266	97.10 288	83.98 325	80.41 330	93.90 312

OpenMVS	90.15 15	94.77 178	93.59 198	98.33 117	96.07 264	97.48 92	99.56 189	98.57 87	90.46 255	86.51 318	98.95 166	78.57 284	99.94 77	93.86 205	99.74 81	97.57 235

MVSFormer		96.94 108	96.60 109	97.95 132	97.28 228	97.70 81	99.55 191	97.27 273	91.17 238	99.43 66	99.54 110	90.92 157	96.89 303	94.67 190	99.62 89	99.25 181

test_djsdf		92.83 230	92.29 231	94.47 260	91.90 350	92.46 246	99.55 191	97.27 273	91.17 238	89.96 254	96.07 281	81.10 256	96.89 303	94.67 190	88.91 250	94.05 299

PS-MVSNAJ		98.44 40	98.20 45	99.16 55	98.80 135	98.92 28	99.54 193	98.17 185	97.34 29	99.85 9	99.85 30	91.20 149	99.89 96	99.41 48	99.67 85	98.69 211

CDS-MVSNet		96.34 135	96.07 122	97.13 176	97.37 220	94.96 182	99.53 194	97.91 213	91.55 226	95.37 192	98.32 210	95.05 53	97.13 285	93.80 210	95.75 205	99.30 176
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
xiu_mvs_v2_base		98.23 56	97.97 58	99.02 70	98.69 140	98.66 49	99.52 195	98.08 196	97.05 41	99.86 7	99.86 26	90.65 162	99.71 138	99.39 50	98.63 138	98.69 211

PatchMatch-RL		96.04 145	95.40 150	97.95 132	99.59 81	95.22 176	99.52 195	99.07 34	93.96 144	96.49 168	98.35 209	82.28 245	99.82 120	90.15 268	99.22 121	98.81 204

test_method		80.79 341	79.70 345	84.08 357	92.83 337	67.06 383	99.51 197	95.42 358	54.34 389	81.07 351	93.53 347	44.48 385	92.22 376	78.90 353	77.23 352	92.94 341

baseline		96.43 130	95.98 127	97.76 146	97.34 222	95.17 179	99.51 197	97.17 281	93.92 147	96.90 157	99.28 129	85.37 223	98.64 196	97.50 136	96.86 183	99.46 155

miper_ehance_all_eth		93.16 222	92.60 223	94.82 244	97.57 209	93.56 218	99.50 199	97.07 293	88.75 286	88.85 285	95.52 297	90.97 156	96.74 310	90.77 256	84.45 298	94.17 283

v1192		90.62 278	89.25 288	94.72 247	93.13 327	93.07 229	99.50 199	97.02 298	86.33 321	89.56 268	95.01 320	79.22 276	97.09 290	82.34 336	81.16 321	94.01 302

v1921920		90.46 280	89.12 290	94.50 258	92.96 335	92.46 246	99.49 201	96.98 303	86.10 323	89.61 267	95.30 310	78.55 285	97.03 296	82.17 337	80.89 328	94.01 302

无先验							99.49 201	98.71 66	93.46 160				100.00 1	94.36 195		99.99 23

pmmvs4		92.10 247	91.07 254	95.18 231	92.82 338	94.96 182	99.48 203	96.83 319	87.45 305	88.66 289	96.56 267	83.78 237	96.83 307	89.29 275	84.77 296	93.75 321

Vis-MVSNet (Re-imp)		96.32 136	95.98 127	97.35 171	97.93 183	94.82 186	99.47 204	98.15 191	91.83 218	95.09 195	99.11 144	91.37 147	97.47 265	93.47 217	97.43 166	99.74 104

API-MVS		97.86 67	97.66 72	98.47 108	99.52 87	95.41 167	99.47 204	98.87 52	91.68 223	98.84 96	99.85 30	92.34 132	99.99 36	98.44 96	99.96 46	100.00 1

旧先验2							99.46 206		94.21 130	99.85 9			99.95 69	96.96 151

IterMVS-LS		92.69 235	92.11 233	94.43 264	96.80 248	92.74 237	99.45 207	96.89 314	88.98 278	89.65 265	95.38 306	88.77 189	96.34 325	90.98 251	82.04 314	94.22 279
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
3Dnovator	91.47 12	96.28 140	95.34 153	99.08 65	96.82 247	97.47 93	99.45 207	98.81 60	95.52 88	89.39 270	99.00 154	81.97 247	99.95 69	97.27 140	99.83 72	99.84 90

FC-MVSNet-test		93.81 205	93.15 212	95.80 214	94.30 307	96.20 138	99.42 209	98.89 49	92.33 205	89.03 282	97.27 240	87.39 201	96.83 307	93.20 220	86.48 283	94.36 269

c3_l		92.53 238	91.87 240	94.52 256	97.40 218	92.99 233	99.40 210	96.93 311	87.86 300	88.69 288	95.44 301	89.95 172	96.44 321	90.45 262	80.69 329	94.14 292

EI-MVSNet-Vis-set		98.27 51	98.11 52	98.75 85	99.83 57	96.59 122	99.40 210	98.51 104	95.29 93	98.51 114	99.76 63	93.60 96	99.71 138	98.53 94	99.52 99	99.95 71

新几何2							99.40 210

QAPM		95.40 164	94.17 183	99.10 64	96.92 239	97.71 79	99.40 210	98.68 70	89.31 271	88.94 283	98.89 171	82.48 244	99.96 61	93.12 225	99.83 72	99.62 124

MTAPA		98.29 50	97.96 61	99.30 42	99.85 54	97.93 73	99.39 214	98.28 173	95.76 80	97.18 151	99.88 21	92.74 119	100.00 1	98.67 86	99.88 68	99.99 23

miper_lstm_enhance		91.81 251	91.39 250	93.06 307	97.34 222	89.18 312	99.38 215	96.79 323	86.70 317	87.47 306	95.22 315	90.00 171	95.86 342	88.26 286	81.37 319	94.15 289

v1240		90.20 288	88.79 297	94.44 262	93.05 333	92.27 250	99.38 215	96.92 312	85.89 325	89.36 271	94.87 327	77.89 289	97.03 296	80.66 344	81.08 324	94.01 302

EPP-MVSNet		96.69 121	96.60 109	96.96 180	97.74 195	93.05 231	99.37 217	98.56 89	88.75 286	95.83 185	99.01 152	96.01 32	98.56 199	96.92 153	97.20 173	99.25 181

MSDG		94.37 192	93.36 208	97.40 166	98.88 131	93.95 210	99.37 217	97.38 261	85.75 329	90.80 245	99.17 142	84.11 236	99.88 102	86.35 309	98.43 142	98.36 218

EI-MVSNet-UG-set		98.14 58	97.99 57	98.60 95	99.80 61	96.27 132	99.36 219	98.50 109	95.21 95	98.30 124	99.75 69	93.29 102	99.73 137	98.37 99	99.30 116	99.81 94

test222					99.55 85	97.41 96	99.34 220	98.55 95	91.86 217	99.27 80	99.83 43	93.84 90			99.95 49	99.99 23

our_test_3		90.39 281	89.48 286	93.12 304	92.40 343	89.57 308	99.33 221	96.35 341	87.84 301	85.30 330	94.99 323	84.14 235	96.09 336	80.38 345	84.56 297	93.71 326

ppachtmachnet_test		89.58 300	88.35 303	93.25 302	92.40 343	90.44 292	99.33 221	96.73 326	85.49 332	85.90 328	95.77 285	81.09 257	96.00 340	76.00 364	82.49 310	93.30 334

mvs_anonymous		95.65 159	95.03 164	97.53 158	98.19 169	95.74 153	99.33 221	97.49 251	90.87 246	90.47 248	97.10 244	88.23 193	97.16 282	95.92 166	97.66 163	99.68 111

AUN-MVS		93.28 219	92.60 223	95.34 225	98.29 160	90.09 299	99.31 224	98.56 89	91.80 221	96.35 174	98.00 217	89.38 179	98.28 228	92.46 230	69.22 372	97.64 231

xiu_mvs_v1_base_debu		97.43 87	97.06 93	98.55 100	97.74 195	98.14 62	99.31 224	97.86 218	96.43 62	99.62 46	99.69 87	85.56 219	99.68 142	99.05 60	98.31 145	97.83 226

xiu_mvs_v1_base		97.43 87	97.06 93	98.55 100	97.74 195	98.14 62	99.31 224	97.86 218	96.43 62	99.62 46	99.69 87	85.56 219	99.68 142	99.05 60	98.31 145	97.83 226

xiu_mvs_v1_base_debi		97.43 87	97.06 93	98.55 100	97.74 195	98.14 62	99.31 224	97.86 218	96.43 62	99.62 46	99.69 87	85.56 219	99.68 142	99.05 60	98.31 145	97.83 226

MVS_Test		96.46 129	95.74 142	98.61 94	98.18 170	97.23 99	99.31 224	97.15 284	91.07 242	98.84 96	97.05 248	88.17 194	98.97 175	94.39 194	97.50 165	99.61 127

hse-mvs2		94.38 191	94.08 185	95.31 227	98.27 163	90.02 301	99.29 229	98.56 89	95.90 76	98.77 100	98.00 217	90.89 160	98.26 232	97.80 125	69.20 373	97.64 231

testdata1							99.28 230		96.35 69

Vis-MVSNet		95.72 153	95.15 160	97.45 162	97.62 207	94.28 199	99.28 230	98.24 177	94.27 129	96.84 159	98.94 168	79.39 274	98.76 186	93.25 219	98.49 140	99.30 176
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FMVSNet3		92.69 235	91.58 244	95.99 208	98.29 160	97.42 95	99.26 232	97.62 233	89.80 267	89.68 262	95.32 309	81.62 252	96.27 328	87.01 305	85.65 287	94.29 275

DeepC-MVS_fast	96.59 1	98.81 22	98.54 26	99.62 20	99.90 42	98.85 34	99.24 233	98.47 112	98.14 10	99.08 86	99.91 14	93.09 108	100.00 1	99.04 63	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
dcpmvs_2		97.42 91	98.09 53	95.42 222	99.58 84	87.24 332	99.23 234	96.95 306	94.28 127	98.93 93	99.73 78	94.39 71	99.16 170	99.89 16	99.82 76	99.86 89

YYNet1		85.50 324	83.33 330	92.00 318	90.89 361	88.38 324	99.22 235	96.55 334	79.60 366	57.26 389	92.72 353	79.09 280	93.78 365	77.25 359	77.37 351	93.84 317

v8		90.54 279	89.17 289	94.66 248	93.43 322	93.40 225	99.20 236	96.94 310	85.76 327	87.56 304	94.51 335	81.96 248	97.19 281	84.94 320	78.25 342	93.38 333

MDA-MVSNet_test_wron		85.51 323	83.32 331	92.10 317	90.96 360	88.58 320	99.20 236	96.52 335	79.70 365	57.12 390	92.69 354	79.11 278	93.86 364	77.10 360	77.46 350	93.86 316

ACMMP		97.74 78	97.44 80	98.66 90	99.92 31	96.13 142	99.18 238	99.45 19	94.84 104	96.41 172	99.71 83	91.40 146	99.99 36	97.99 117	98.03 157	99.87 87
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
WR-MVS_H		91.30 260	90.35 264	94.15 270	94.17 309	92.62 244	99.17 239	98.94 41	88.87 284	86.48 320	94.46 339	84.36 232	96.61 316	88.19 287	78.51 341	93.21 337

TAMVS		95.85 150	95.58 147	96.65 191	97.07 232	93.50 220	99.17 239	97.82 222	91.39 235	95.02 196	98.01 216	92.20 134	97.30 274	93.75 213	95.83 202	99.14 189

bld_raw_dy_0_64		92.74 232	92.03 236	94.87 240	93.09 331	93.46 221	99.12 241	95.41 359	92.84 177	90.44 249	97.54 231	78.08 288	97.04 293	93.94 202	87.77 273	94.11 294

PS-MVSNAJss		93.64 212	93.31 209	94.61 250	92.11 347	92.19 251	99.12 241	97.38 261	92.51 198	88.45 290	96.99 251	91.20 149	97.29 277	94.36 195	87.71 274	94.36 269

DTE-MVSNet		89.40 302	88.24 305	92.88 310	92.66 340	89.95 303	99.10 243	98.22 179	87.29 307	85.12 332	96.22 274	76.27 304	95.30 350	83.56 329	75.74 359	93.41 330

CP-MVSNet		91.23 264	90.22 268	94.26 268	93.96 312	92.39 248	99.09 244	98.57 87	88.95 281	86.42 321	96.57 266	79.19 277	96.37 323	90.29 266	78.95 338	94.02 300

AdaColmap		97.23 99	96.80 104	98.51 106	99.99 1	95.60 160	99.09 244	98.84 58	93.32 164	96.74 162	99.72 81	86.04 216	100.00 1	98.01 115	99.43 110	99.94 74

v10		90.25 287	88.82 296	94.57 254	93.53 320	93.43 223	99.08 246	96.87 316	85.00 336	87.34 310	94.51 335	80.93 259	97.02 298	82.85 332	79.23 337	93.26 335

XVG-OURS-SEG-HR		94.79 176	94.70 173	95.08 233	98.05 177	89.19 310	99.08 246	97.54 244	93.66 155	94.87 197	99.58 106	78.78 281	99.79 123	97.31 139	93.40 230	96.25 244

XVG-OURS		94.82 174	94.74 172	95.06 234	98.00 179	89.19 310	99.08 246	97.55 242	94.10 134	94.71 198	99.62 102	80.51 265	99.74 134	96.04 164	93.06 235	96.25 244

IS-MVSNet		96.29 139	95.90 138	97.45 162	98.13 174	94.80 187	99.08 246	97.61 236	92.02 214	95.54 190	98.96 161	90.64 163	98.08 239	93.73 214	97.41 169	99.47 154

v7n		89.65 299	88.29 304	93.72 288	92.22 345	90.56 289	99.07 250	97.10 289	85.42 334	86.73 314	94.72 328	80.06 269	97.13 285	81.14 342	78.12 344	93.49 329

EI-MVSNet		93.73 209	93.40 207	94.74 245	96.80 248	92.69 240	99.06 251	97.67 229	88.96 280	91.39 237	99.02 150	88.75 190	97.30 274	91.07 247	87.85 271	94.22 279

CVMVSNet		94.68 182	94.94 167	93.89 284	96.80 248	86.92 335	99.06 251	98.98 38	94.45 115	94.23 206	99.02 150	85.60 218	95.31 349	90.91 253	95.39 211	99.43 160

baseline1		95.78 152	94.86 168	98.54 103	98.47 153	98.07 65	99.06 251	97.99 202	92.68 186	94.13 207	98.62 192	93.28 103	98.69 193	93.79 211	85.76 286	98.84 202

PEN-MVS		90.19 289	89.06 292	93.57 294	93.06 332	90.90 281	99.06 251	98.47 112	88.11 297	85.91 327	96.30 272	76.67 297	95.94 341	87.07 302	76.91 355	93.89 313

test_fmvs3		79.99 345	80.17 344	79.45 363	84.02 381	62.83 384	99.05 255	93.49 382	88.29 296	80.06 356	86.65 380	28.09 392	88.00 384	88.63 280	73.27 364	87.54 380

Anonymous20231206		86.32 318	85.42 321	89.02 342	89.11 371	80.53 371	99.05 255	95.28 362	85.43 333	82.82 341	93.92 343	74.40 320	93.44 368	66.99 378	81.83 316	93.08 339

MAR-MVS		97.43 87	97.19 90	98.15 126	99.47 91	94.79 188	99.05 255	98.76 63	92.65 188	98.66 108	99.82 46	88.52 192	99.98 43	98.12 109	99.63 88	99.67 113
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
VNet		97.21 100	96.57 111	99.13 63	98.97 118	97.82 76	99.03 258	99.21 29	94.31 125	99.18 84	98.88 172	86.26 215	99.89 96	98.93 69	94.32 221	99.69 110

LCM-MVSNet-Re		92.31 243	92.60 223	91.43 323	97.53 211	79.27 373	99.02 259	91.83 387	92.07 210	80.31 353	94.38 340	83.50 239	95.48 345	97.22 143	97.58 164	99.54 143

jajsoiax		91.92 249	91.18 252	94.15 270	91.35 357	90.95 280	99.00 260	97.42 257	92.61 190	87.38 308	97.08 245	72.46 327	97.36 267	94.53 193	88.77 254	94.13 293

VPNet		91.81 251	90.46 261	95.85 212	94.74 299	95.54 162	98.98 261	98.59 84	92.14 208	90.77 246	97.44 234	68.73 343	97.54 263	94.89 183	77.89 345	94.46 258

PS-CasMVS		90.63 277	89.51 284	93.99 279	93.83 314	91.70 267	98.98 261	98.52 101	88.48 292	86.15 325	96.53 268	75.46 310	96.31 327	88.83 279	78.86 340	93.95 308

FMVSNet2		91.02 267	89.56 281	95.41 223	97.53 211	95.74 153	98.98 261	97.41 259	87.05 310	88.43 293	95.00 322	71.34 332	96.24 330	85.12 318	85.21 292	94.25 278

K. test v3		88.05 311	87.24 313	90.47 331	91.82 352	82.23 359	98.96 264	97.42 257	89.05 274	76.93 368	95.60 292	68.49 344	95.42 346	85.87 315	81.01 326	93.75 321

tfpnnormal		89.29 304	87.61 310	94.34 267	94.35 306	94.13 204	98.95 265	98.94 41	83.94 343	84.47 334	95.51 298	74.84 317	97.39 266	77.05 361	80.41 330	91.48 359

AllTest		92.48 239	91.64 242	95.00 236	99.01 113	88.43 321	98.94 266	96.82 321	86.50 318	88.71 286	98.47 205	74.73 318	99.88 102	85.39 316	96.18 191	96.71 240

h-mvs33		94.92 173	94.36 177	96.59 192	98.85 132	91.29 274	98.93 267	98.94 41	95.90 76	98.77 100	98.42 208	90.89 160	99.77 128	97.80 125	70.76 367	98.72 210

anonymousdsp		91.79 256	90.92 255	94.41 265	90.76 362	92.93 234	98.93 267	97.17 281	89.08 273	87.46 307	95.30 310	78.43 287	96.92 302	92.38 231	88.73 255	93.39 332

DP-MVS		94.54 185	93.42 204	97.91 136	99.46 93	94.04 206	98.93 267	97.48 252	81.15 359	90.04 253	99.55 108	87.02 206	99.95 69	88.97 278	98.11 153	99.73 105

IterMVS-SCA-FT		90.85 272	90.16 272	92.93 309	96.72 253	89.96 302	98.89 270	96.99 301	88.95 281	86.63 316	95.67 289	76.48 301	95.00 352	87.04 303	84.04 304	93.84 317

IterMVS		90.91 269	90.17 271	93.12 304	96.78 251	90.42 293	98.89 270	97.05 296	89.03 275	86.49 319	95.42 302	76.59 299	95.02 351	87.22 300	84.09 301	93.93 310
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous202405211		93.10 225	91.99 237	96.40 198	99.10 108	89.65 307	98.88 272	97.93 209	83.71 346	94.00 208	98.75 183	68.79 341	99.88 102	95.08 176	91.71 236	99.68 111

VPA-MVSNet		92.70 234	91.55 246	96.16 205	95.09 293	96.20 138	98.88 272	99.00 36	91.02 244	91.82 234	95.29 313	76.05 307	97.96 247	95.62 170	81.19 320	94.30 274

test20.03		84.72 329	83.99 324	86.91 352	88.19 374	80.62 370	98.88 272	95.94 348	88.36 294	78.87 358	94.62 333	68.75 342	89.11 383	66.52 380	75.82 358	91.00 361

XXY-MVS		91.82 250	90.46 261	95.88 210	93.91 313	95.40 168	98.87 275	97.69 227	88.63 290	87.87 300	97.08 245	74.38 321	97.89 251	91.66 240	84.07 302	94.35 272

test1111		95.57 160	94.98 166	97.37 168	98.56 145	93.37 226	98.86 276	98.45 115	94.95 98	96.63 164	98.95 166	75.21 315	99.11 171	95.02 177	98.14 152	99.64 119

SCA		94.69 180	93.81 193	97.33 172	97.10 231	94.44 192	98.86 276	98.32 166	93.30 165	96.17 178	95.59 293	76.48 301	97.95 248	91.06 248	97.43 166	99.59 130

ECVR-MVS		95.66 158	95.05 163	97.51 160	98.66 142	93.71 215	98.85 278	98.45 115	94.93 99	96.86 158	98.96 161	75.22 314	99.20 166	95.34 171	98.15 150	99.64 119

eth_miper_zixun_eth		92.41 241	91.93 238	93.84 285	97.28 228	90.68 285	98.83 279	96.97 305	88.57 291	89.19 279	95.73 288	89.24 184	96.69 313	89.97 271	81.55 317	94.15 289

CL-MVSNet_self_test		84.50 330	83.15 333	88.53 347	86.00 377	81.79 362	98.82 280	97.35 263	85.12 335	83.62 339	90.91 365	76.66 298	91.40 378	69.53 374	60.36 387	92.40 350

test2506		97.53 85	97.19 90	98.58 98	98.66 142	96.90 113	98.81 281	99.77 5	94.93 99	97.95 133	98.96 161	92.51 126	99.20 166	94.93 179	98.15 150	99.64 119

ACMH+	89.98 16	90.35 283	89.54 282	92.78 312	95.99 267	86.12 338	98.81 281	97.18 280	89.38 270	83.14 340	97.76 228	68.42 345	98.43 208	89.11 277	86.05 285	93.78 320

Anonymous20240521		85.15 326	83.81 328	89.16 341	88.32 372	82.69 354	98.80 283	95.74 351	79.72 364	81.53 348	90.99 363	65.38 357	94.16 360	72.69 368	81.11 323	90.63 365

N_pmnet		80.06 344	80.78 342	77.89 364	91.94 349	45.28 402	98.80 283	56.82 404	78.10 369	80.08 355	93.33 348	77.03 292	95.76 343	68.14 377	82.81 307	92.64 345

VDD-MVS		93.77 207	92.94 215	96.27 203	98.55 147	90.22 296	98.77 285	97.79 223	90.85 247	96.82 160	99.42 118	61.18 370	99.77 128	98.95 67	94.13 223	98.82 203

LFMVS		94.75 179	93.56 200	98.30 119	99.03 112	95.70 156	98.74 286	97.98 204	87.81 302	98.47 116	99.39 123	67.43 349	99.53 150	98.01 115	95.20 215	99.67 113

LS3D		95.84 151	95.11 161	98.02 131	99.85 54	95.10 180	98.74 286	98.50 109	87.22 309	93.66 211	99.86 26	87.45 200	99.95 69	90.94 252	99.81 78	99.02 195

Anonymous20240529		92.10 247	90.65 258	96.47 193	98.82 133	90.61 287	98.72 288	98.67 73	75.54 375	93.90 210	98.58 195	66.23 353	99.90 91	94.70 189	90.67 239	98.90 200

dmvs_re		93.20 221	93.15 212	93.34 298	96.54 256	83.81 350	98.71 289	98.51 104	91.39 235	92.37 229	98.56 197	78.66 283	97.83 253	93.89 204	89.74 240	98.38 217

TR-MVS		94.54 185	93.56 200	97.49 161	97.96 181	94.34 198	98.71 289	97.51 249	90.30 260	94.51 201	98.69 184	75.56 309	98.77 185	92.82 228	95.99 195	99.35 169

USDC		90.00 293	88.96 294	93.10 306	94.81 298	88.16 325	98.71 289	95.54 357	93.66 155	83.75 338	97.20 241	65.58 355	98.31 225	83.96 326	87.49 278	92.85 343

VDDNet		93.12 224	91.91 239	96.76 186	96.67 255	92.65 243	98.69 292	98.21 180	82.81 352	97.75 140	99.28 129	61.57 368	99.48 159	98.09 112	94.09 224	98.15 221

EU-MVSNet		90.14 291	90.34 265	89.54 338	92.55 341	81.06 367	98.69 292	98.04 200	91.41 234	86.59 317	96.84 258	80.83 260	93.31 369	86.20 310	81.91 315	94.26 276

mvs_tets		91.81 251	91.08 253	94.00 278	91.63 354	90.58 288	98.67 294	97.43 255	92.43 200	87.37 309	97.05 248	71.76 329	97.32 273	94.75 187	88.68 256	94.11 294

MDA-MVSNet-bldmvs		84.09 332	81.52 339	91.81 321	91.32 358	88.00 328	98.67 294	95.92 349	80.22 363	55.60 391	93.32 349	68.29 346	93.60 367	73.76 366	76.61 357	93.82 319

UGNet		95.33 166	94.57 174	97.62 155	98.55 147	94.85 184	98.67 294	99.32 26	95.75 81	96.80 161	96.27 273	72.18 328	99.96 61	94.58 192	99.05 128	98.04 224
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
pm-mvs1		89.36 303	87.81 309	94.01 277	93.40 324	91.93 257	98.62 297	96.48 337	86.25 322	83.86 337	96.14 277	73.68 324	97.04 293	86.16 311	75.73 360	93.04 340

test_0402		85.58 321	83.94 326	90.50 330	93.81 315	85.04 344	98.55 298	95.20 365	76.01 372	79.72 357	95.13 316	64.15 361	96.26 329	66.04 382	86.88 281	90.21 368

ACMH	89.72 17	90.64 276	89.63 279	93.66 293	95.64 286	88.64 319	98.55 298	97.45 253	89.03 275	81.62 347	97.61 230	69.75 339	98.41 210	89.37 274	87.62 276	93.92 311
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		89.86 295	88.44 302	94.13 272	98.93 122	90.68 285	98.54 300	98.26 176	76.28 371	86.73 314	95.54 295	70.60 337	97.56 262	90.82 255	80.27 333	94.15 289

TransMVSNet (Re)		87.25 315	85.28 322	93.16 303	93.56 319	91.03 276	98.54 300	94.05 377	83.69 347	81.09 350	96.16 276	75.32 311	96.40 322	76.69 362	68.41 374	92.06 353

XVG-ACMP-BASELINE		91.22 265	90.75 256	92.63 313	93.73 316	85.61 340	98.52 302	97.44 254	92.77 181	89.90 257	96.85 256	66.64 352	98.39 214	92.29 232	88.61 257	93.89 313

CHOSEN 280x420		99.01 13	99.03 10	98.95 76	99.38 95	98.87 32	98.46 303	99.42 22	97.03 42	99.02 89	99.09 145	99.35 1	98.21 234	99.73 32	99.78 79	99.77 101

OpenMVS_ROB	79.82 20	83.77 335	81.68 338	90.03 335	88.30 373	82.82 353	98.46 303	95.22 364	73.92 380	76.00 371	91.29 362	55.00 376	96.94 300	68.40 376	88.51 261	90.34 366

GBi-Net		90.88 270	89.82 276	94.08 273	97.53 211	91.97 254	98.43 305	96.95 306	87.05 310	89.68 262	94.72 328	71.34 332	96.11 333	87.01 305	85.65 287	94.17 283

test1		90.88 270	89.82 276	94.08 273	97.53 211	91.97 254	98.43 305	96.95 306	87.05 310	89.68 262	94.72 328	71.34 332	96.11 333	87.01 305	85.65 287	94.17 283

FMVSNet1		88.50 308	86.64 314	94.08 273	95.62 288	91.97 254	98.43 305	96.95 306	83.00 350	86.08 326	94.72 328	59.09 372	96.11 333	81.82 340	84.07 302	94.17 283

COLMAP_ROB	90.47 14	92.18 246	91.49 248	94.25 269	99.00 115	88.04 327	98.42 308	96.70 328	82.30 355	88.43 293	99.01 152	76.97 294	99.85 108	86.11 312	96.50 187	94.86 251
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tt0805		91.28 262	90.18 270	94.60 251	96.26 260	87.55 329	98.39 309	98.72 65	89.00 277	89.22 276	98.47 205	62.98 364	98.96 176	90.57 259	88.00 270	97.28 237

test123		37.68 365	39.14 368	33.31 381	19.94 404	24.83 407	98.36 310	9.75 406	15.53 399	51.31 393	87.14 378	19.62 400	17.74 401	47.10 393	3.47 400	57.36 394

1314		96.84 112	95.96 131	99.48 34	96.74 252	98.52 56	98.31 311	98.86 53	95.82 78	89.91 256	98.98 157	87.49 199	99.96 61	97.80 125	99.73 82	99.96 64

MVS		96.60 124	95.56 148	99.72 13	96.85 245	99.22 20	98.31 311	98.94 41	91.57 225	90.90 244	99.61 103	86.66 210	99.96 61	97.36 138	99.88 68	99.99 23

NR-MVSNet		91.56 259	90.22 268	95.60 216	94.05 310	95.76 152	98.25 313	98.70 67	91.16 240	80.78 352	96.64 263	83.23 242	96.57 317	91.41 242	77.73 347	94.46 258

sd_testset		93.55 214	92.83 218	95.74 215	98.92 124	90.89 282	98.24 314	98.85 56	92.41 201	92.55 226	97.85 224	71.07 336	98.68 194	93.93 203	91.62 237	97.64 231

MS-PatchMatch		90.65 275	90.30 266	91.71 322	94.22 308	85.50 342	98.24 314	97.70 226	88.67 288	86.42 321	96.37 271	67.82 347	98.03 243	83.62 328	99.62 89	91.60 357

pmmvs3		80.27 343	77.77 348	87.76 351	80.32 388	82.43 357	98.23 316	91.97 386	72.74 382	78.75 359	87.97 376	57.30 375	90.99 380	70.31 372	62.37 385	89.87 370

SixPastTwentyTwo		88.73 307	88.01 308	90.88 326	91.85 351	82.24 358	98.22 317	95.18 366	88.97 279	82.26 343	96.89 253	71.75 330	96.67 314	84.00 324	82.98 306	93.72 325

EG-PatchMatch MVS		85.35 325	83.81 328	89.99 336	90.39 364	81.89 361	98.21 318	96.09 346	81.78 357	74.73 374	93.72 346	51.56 382	97.12 287	79.16 352	88.61 257	90.96 362

OurMVSNet-221017-0		89.81 296	89.48 286	90.83 328	91.64 353	81.21 365	98.17 319	95.38 361	91.48 228	85.65 329	97.31 238	72.66 326	97.29 277	88.15 288	84.83 295	93.97 307

LF4IMVS		89.25 305	88.85 295	90.45 332	92.81 339	81.19 366	98.12 320	94.79 368	91.44 230	86.29 323	97.11 243	65.30 358	98.11 238	88.53 284	85.25 291	92.07 352

RPSCF		91.80 254	92.79 220	88.83 343	98.15 172	69.87 381	98.11 321	96.60 332	83.93 344	94.33 204	99.27 132	79.60 273	99.46 161	91.99 235	93.16 233	97.18 238

pmmvs-eth3d		84.03 333	81.97 337	90.20 333	84.15 380	87.09 333	98.10 322	94.73 370	83.05 349	74.10 376	87.77 377	65.56 356	94.01 361	81.08 343	69.24 371	89.49 374

DSMNet-mixed		88.28 310	88.24 305	88.42 348	89.64 369	75.38 377	98.06 323	89.86 391	85.59 331	88.20 297	92.14 360	76.15 306	91.95 377	78.46 354	96.05 194	97.92 225

MVP-Stereo		90.93 268	90.45 263	92.37 315	91.25 359	88.76 314	98.05 324	96.17 344	87.27 308	84.04 335	95.30 310	78.46 286	97.27 279	83.78 327	99.70 84	91.09 360
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UA-Net		96.54 126	95.96 131	98.27 120	98.23 165	95.71 155	98.00 325	98.45 115	93.72 154	98.41 118	99.27 132	88.71 191	99.66 146	91.19 245	97.69 161	99.44 159

new-patchmatchnet		81.19 339	79.34 346	86.76 353	82.86 383	80.36 372	97.92 326	95.27 363	82.09 356	72.02 377	86.87 379	62.81 365	90.74 381	71.10 371	63.08 384	89.19 377

PCF-MVS	94.20 5	95.18 167	94.10 184	98.43 112	98.55 147	95.99 145	97.91 327	97.31 268	90.35 258	89.48 269	99.22 138	85.19 224	99.89 96	90.40 265	98.47 141	99.41 162
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVS		76.28 348	77.28 350	73.29 369	81.18 385	54.68 394	97.87 328	94.19 374	81.30 358	69.43 381	90.70 366	77.02 293	82.06 392	35.71 397	68.11 376	83.13 383

pmmvs6		85.69 320	83.84 327	91.26 325	90.00 368	84.41 348	97.82 329	96.15 345	75.86 373	81.29 349	95.39 305	61.21 369	96.87 305	83.52 330	73.29 363	92.50 348

UniMVSNet_ETH3D		90.06 292	88.58 300	94.49 259	94.67 301	88.09 326	97.81 330	97.57 241	83.91 345	88.44 291	97.41 235	57.44 374	97.62 261	91.41 242	88.59 259	97.77 229

TinyColmap		87.87 314	86.51 315	91.94 319	95.05 295	85.57 341	97.65 331	94.08 375	84.40 342	81.82 346	96.85 256	62.14 366	98.33 223	80.25 347	86.37 284	91.91 356

HY-MVS	92.50 7	97.79 75	97.17 92	99.63 17	98.98 117	99.32 9	97.49 332	99.52 15	95.69 82	98.32 123	97.41 235	93.32 100	99.77 128	98.08 113	95.75 205	99.81 94

SSC-MVS		75.42 349	76.40 352	72.49 373	80.68 387	53.62 395	97.42 333	94.06 376	80.42 362	68.75 382	90.14 368	76.54 300	81.66 393	33.25 398	66.34 380	82.19 384

Effi-MVS+		96.30 138	95.69 144	98.16 123	97.85 188	96.26 133	97.41 334	97.21 277	90.37 257	98.65 109	98.58 195	86.61 211	98.70 192	97.11 145	97.37 170	99.52 147

TDRefinement		84.76 327	82.56 335	91.38 324	74.58 393	84.80 347	97.36 335	94.56 372	84.73 340	80.21 354	96.12 280	63.56 362	98.39 214	87.92 291	63.97 383	90.95 363

FMVSNet5		88.32 309	87.47 311	90.88 326	96.90 243	88.39 323	97.28 336	95.68 353	82.60 354	84.67 333	92.40 358	79.83 271	91.16 379	76.39 363	81.51 318	93.09 338

KD-MVS_self_test		83.59 336	82.06 336	88.20 349	86.93 375	80.70 369	97.21 337	96.38 339	82.87 351	82.49 342	88.97 371	67.63 348	92.32 375	73.75 367	62.30 386	91.58 358

LTVRE_ROB	88.28 18	90.29 286	89.05 293	94.02 276	95.08 294	90.15 298	97.19 338	97.43 255	84.91 339	83.99 336	97.06 247	74.00 323	98.28 228	84.08 323	87.71 274	93.62 327
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
KD-MVS_2432*1600		88.00 312	86.10 316	93.70 291	96.91 240	94.04 206	97.17 339	97.12 287	84.93 337	81.96 344	92.41 356	92.48 127	94.51 358	79.23 349	52.68 390	92.56 346

miper_refine_blended		88.00 312	86.10 316	93.70 291	96.91 240	94.04 206	97.17 339	97.12 287	84.93 337	81.96 344	92.41 356	92.48 127	94.51 358	79.23 349	52.68 390	92.56 346

mvsany_test3		82.12 338	81.14 340	85.06 356	81.87 384	70.41 380	97.09 341	92.14 385	91.27 237	77.84 364	88.73 372	39.31 387	95.49 344	90.75 257	71.24 366	89.29 376

CostFormer		96.10 142	95.88 139	96.78 185	97.03 234	92.55 245	97.08 342	97.83 221	90.04 264	98.72 105	94.89 326	95.01 55	98.29 226	96.54 158	95.77 203	99.50 151

tpm		93.70 211	93.41 206	94.58 253	95.36 291	87.41 331	97.01 343	96.90 313	90.85 247	96.72 163	94.14 342	90.40 167	96.84 306	90.75 257	88.54 260	99.51 149

CMPMVS	61.59 21	84.75 328	85.14 323	83.57 358	90.32 365	62.54 386	96.98 344	97.59 240	74.33 379	69.95 380	96.66 261	64.17 360	98.32 224	87.88 292	88.41 262	89.84 371
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_f		78.40 347	77.59 349	80.81 362	80.82 386	62.48 387	96.96 345	93.08 383	83.44 348	74.57 375	84.57 384	27.95 393	92.63 373	84.15 322	72.79 365	87.32 381

tpm2		95.47 162	95.18 159	96.35 201	96.91 240	91.70 267	96.96 345	97.93 209	88.04 299	98.44 117	95.40 303	93.32 100	97.97 245	94.00 201	95.61 207	99.38 164

new_pmnet		84.49 331	82.92 334	89.21 340	90.03 367	82.60 355	96.89 347	95.62 355	80.59 361	75.77 373	89.17 370	65.04 359	94.79 356	72.12 370	81.02 325	90.23 367

dmvs_testset		83.79 334	86.07 318	76.94 365	92.14 346	48.60 400	96.75 348	90.27 390	89.48 269	78.65 360	98.55 199	79.25 275	86.65 388	66.85 379	82.69 308	95.57 250

UnsupCasMVSNet_eth		85.52 322	83.99 324	90.10 334	89.36 370	83.51 352	96.65 349	97.99 202	89.14 272	75.89 372	93.83 344	63.25 363	93.92 362	81.92 339	67.90 377	92.88 342

MIMVSNet1		82.58 337	80.51 343	88.78 344	86.68 376	84.20 349	96.65 349	95.41 359	78.75 367	78.59 361	92.44 355	51.88 381	89.76 382	65.26 383	78.95 338	92.38 351

ab-mvs		94.69 180	93.42 204	98.51 106	98.07 176	96.26 133	96.49 351	98.68 70	90.31 259	94.54 199	97.00 250	76.30 303	99.71 138	95.98 165	93.38 231	99.56 138

test_vis3_rt		68.82 351	66.69 356	75.21 368	76.24 392	60.41 389	96.44 352	68.71 403	75.13 377	50.54 394	69.52 392	16.42 402	96.32 326	80.27 346	66.92 379	68.89 390

EPMVS		96.53 127	96.01 124	98.09 128	98.43 154	96.12 144	96.36 353	99.43 21	93.53 158	97.64 141	95.04 319	94.41 67	98.38 218	91.13 246	98.11 153	99.75 103

tpmrst		96.27 141	95.98 127	97.13 176	97.96 181	93.15 228	96.34 354	98.17 185	92.07 210	98.71 106	95.12 317	93.91 87	98.73 188	94.91 182	96.62 184	99.50 151

FA-MVS(test-final)		95.86 149	95.09 162	98.15 126	97.74 195	95.62 159	96.31 355	98.17 185	91.42 233	96.26 175	96.13 278	90.56 164	99.47 160	92.18 234	97.07 175	99.35 169

dp		95.05 170	94.43 176	96.91 181	97.99 180	92.73 239	96.29 356	97.98 204	89.70 268	95.93 182	94.67 332	93.83 91	98.45 207	86.91 308	96.53 186	99.54 143

EGC-MVSNET		69.38 350	63.76 360	86.26 354	90.32 365	81.66 364	96.24 357	93.85 379	0.99 401	3.22 402	92.33 359	52.44 379	92.92 372	59.53 388	84.90 294	84.21 382

tpm cat1		93.51 215	92.52 228	96.47 193	97.77 193	91.47 273	96.13 358	98.06 197	80.98 360	92.91 220	93.78 345	89.66 174	98.87 179	87.03 304	96.39 189	99.09 192

MDTV_nov1_ep13_2view						96.26 133	96.11 359		91.89 216	98.06 130		94.40 68		94.30 197		99.67 113

PatchmatchNet		95.94 148	95.45 149	97.39 167	97.83 189	94.41 195	96.05 360	98.40 146	92.86 174	97.09 152	95.28 314	94.21 79	98.07 241	89.26 276	98.11 153	99.70 108
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
APD_test1		81.15 340	80.92 341	81.86 361	92.45 342	59.76 390	96.04 361	93.61 381	73.29 381	77.06 366	96.64 263	44.28 386	96.16 332	72.35 369	82.52 309	89.67 372

MDTV_nov1_ep13			95.69 144		97.90 184	94.15 203	95.98 362	98.44 119	93.12 170	97.98 132	95.74 286	95.10 50	98.58 198	90.02 269	96.92 181

FPMVS		68.72 352	68.72 353	68.71 375	65.95 397	44.27 404	95.97 363	94.74 369	51.13 390	53.26 392	90.50 367	25.11 395	83.00 391	60.80 386	80.97 327	78.87 388

PM-MVS		80.47 342	78.88 347	85.26 355	83.79 382	72.22 379	95.89 364	91.08 388	85.71 330	76.56 370	88.30 373	36.64 388	93.90 363	82.39 335	69.57 370	89.66 373

test_post1							95.78 365				59.23 399	93.20 106	97.74 257	91.06 248

tpmvs		94.28 196	93.57 199	96.40 198	98.55 147	91.50 272	95.70 366	98.55 95	87.47 304	92.15 230	94.26 341	91.42 145	98.95 177	88.15 288	95.85 201	98.76 206

FE-MVS		95.70 157	95.01 165	97.79 141	98.21 167	94.57 190	95.03 367	98.69 68	88.90 283	97.50 145	96.19 275	92.60 123	99.49 158	89.99 270	97.94 159	99.31 174

ADS-MVSNet2		93.80 206	93.88 191	93.55 295	97.87 186	85.94 339	94.24 368	96.84 318	90.07 262	96.43 170	94.48 337	90.29 169	95.37 347	87.44 295	97.23 171	99.36 167

ADS-MVSNet		94.79 176	94.02 186	97.11 178	97.87 186	93.79 212	94.24 368	98.16 189	90.07 262	96.43 170	94.48 337	90.29 169	98.19 235	87.44 295	97.23 171	99.36 167

EMVS		51.44 363	51.22 365	52.11 380	70.71 395	44.97 403	94.04 370	75.66 402	35.34 397	42.40 397	61.56 398	28.93 391	65.87 399	27.64 400	24.73 395	45.49 396

PMMVS2		67.15 356	64.15 359	76.14 367	70.56 396	62.07 388	93.89 371	87.52 395	58.09 386	60.02 385	78.32 387	22.38 396	84.54 390	59.56 387	47.03 392	81.80 385

GG-mvs-BLEND				98.54 103	98.21 167	98.01 68	93.87 372	98.52 101		97.92 134	97.92 223	99.02 2	97.94 250	98.17 106	99.58 96	99.67 113

UnsupCasMVSNet_bld		79.97 346	77.03 351	88.78 344	85.62 378	81.98 360	93.66 373	97.35 263	75.51 376	70.79 379	83.05 385	48.70 383	94.91 354	78.31 355	60.29 388	89.46 375

E-PMN		52.30 361	52.18 363	52.67 379	71.51 394	45.40 401	93.62 374	76.60 401	36.01 395	43.50 396	64.13 395	27.11 394	67.31 398	31.06 399	26.06 394	45.30 397

JIA-IIPM		91.76 257	90.70 257	94.94 238	96.11 263	87.51 330	93.16 375	98.13 193	75.79 374	97.58 142	77.68 388	92.84 115	97.97 245	88.47 285	96.54 185	99.33 172

gg-mvs-nofinetune		93.51 215	91.86 241	98.47 108	97.72 200	97.96 72	92.62 376	98.51 104	74.70 378	97.33 148	69.59 391	98.91 3	97.79 254	97.77 130	99.56 97	99.67 113

MIMVSNet		90.30 285	88.67 299	95.17 232	96.45 257	91.64 269	92.39 377	97.15 284	85.99 324	90.50 247	93.19 352	66.95 350	94.86 355	82.01 338	93.43 229	99.01 196

MVS-HIRNet		86.22 319	83.19 332	95.31 227	96.71 254	90.29 294	92.12 378	97.33 266	62.85 385	86.82 313	70.37 390	69.37 340	97.49 264	75.12 365	97.99 158	98.15 221

CR-MVSNet		93.45 218	92.62 222	95.94 209	96.29 258	92.66 241	92.01 379	96.23 342	92.62 189	96.94 155	93.31 350	91.04 154	96.03 338	79.23 349	95.96 196	99.13 190

RPMNet		89.76 297	87.28 312	97.19 175	96.29 258	92.66 241	92.01 379	98.31 168	70.19 384	96.94 155	85.87 383	87.25 203	99.78 125	62.69 385	95.96 196	99.13 190

Patchmatch-test		92.65 237	91.50 247	96.10 207	96.85 245	90.49 290	91.50 381	97.19 278	82.76 353	90.23 250	95.59 293	95.02 54	98.00 244	77.41 358	96.98 180	99.82 92

Patchmtry		89.70 298	88.49 301	93.33 299	96.24 261	89.94 305	91.37 382	96.23 342	78.22 368	87.69 301	93.31 350	91.04 154	96.03 338	80.18 348	82.10 313	94.02 300

PatchT		90.38 282	88.75 298	95.25 229	95.99 267	90.16 297	91.22 383	97.54 244	76.80 370	97.26 149	86.01 382	91.88 141	96.07 337	66.16 381	95.91 200	99.51 149

testf1		68.38 353	66.92 354	72.78 371	78.80 389	50.36 397	90.95 384	87.35 396	55.47 387	58.95 386	88.14 374	20.64 397	87.60 385	57.28 389	64.69 381	80.39 386

APD_test2		68.38 353	66.92 354	72.78 371	78.80 389	50.36 397	90.95 384	87.35 396	55.47 387	58.95 386	88.14 374	20.64 397	87.60 385	57.28 389	64.69 381	80.39 386

Patchmatch-RL test		86.90 316	85.98 320	89.67 337	84.45 379	75.59 376	89.71 386	92.43 384	86.89 315	77.83 365	90.94 364	94.22 77	93.63 366	87.75 293	69.61 369	99.79 97

LCM-MVSNet		67.77 355	64.73 358	76.87 366	62.95 399	56.25 393	89.37 387	93.74 380	44.53 392	61.99 384	80.74 386	20.42 399	86.53 389	69.37 375	59.50 389	87.84 378

ambc				83.23 359	77.17 391	62.61 385	87.38 388	94.55 373		76.72 369	86.65 380	30.16 389	96.36 324	84.85 321	69.86 368	90.73 364

ANet_high		56.10 359	52.24 362	67.66 376	49.27 401	56.82 392	83.94 389	82.02 399	70.47 383	33.28 399	64.54 394	17.23 401	69.16 397	45.59 394	23.85 396	77.02 389

tmp_tt		65.23 358	62.94 361	72.13 374	44.90 402	50.03 399	81.05 390	89.42 394	38.45 393	48.51 395	99.90 18	54.09 378	78.70 395	91.84 239	18.26 397	87.64 379

MVE	53.74 22	51.54 362	47.86 366	62.60 377	59.56 400	50.93 396	79.41 391	77.69 400	35.69 396	36.27 398	61.76 397	5.79 406	69.63 396	37.97 396	36.61 393	67.24 391
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	49.05 23	53.75 360	51.34 364	60.97 378	40.80 403	34.68 405	74.82 392	89.62 393	37.55 394	28.67 400	72.12 389	7.09 404	81.63 394	43.17 395	68.21 375	66.59 392
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		66.95 357	65.00 357	72.79 370	91.52 355	67.96 382	66.16 393	95.15 367	47.89 391	58.54 388	67.99 393	29.74 390	87.54 387	50.20 392	77.83 346	62.87 393
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
wuyk23d		20.37 367	20.84 370	18.99 383	65.34 398	27.73 406	50.43 394	7.67 407	9.50 400	8.01 401	6.34 401	6.13 405	26.24 400	23.40 401	10.69 399	2.99 398

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.02 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 403	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 403	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

cdsmvs_eth3d_5k		23.43 366	31.24 369	0.00 384	0.00 406	0.00 409	0.00 395	98.09 194	0.00 402	0.00 403	99.67 94	83.37 240	0.00 403	0.00 402	0.00 401	0.00 399

pcd_1.5k_mvsjas		7.60 369	10.13 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 403	91.20 149	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 403	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 403	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 403	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 403	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

ab-mvs-re		8.28 368	11.04 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	99.40 121	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 403	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						90.97 277								86.10 313

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 142					100.00 1	99.96 9	100.00 1	100.00 1

PC_three_1452									96.96 44	99.80 17	99.79 55	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 142					100.00 1	99.96 9	100.00 1	100.00 1

test_one_0601					99.94 13	99.30 12		98.41 142	96.63 56	99.75 29	99.93 11	97.49 10

eth-test2					0.00 406

eth-test					0.00 406

ZD-MVS					99.92 31	98.57 54		98.52 101	92.34 204	99.31 76	99.83 43	95.06 52	99.80 121	99.70 34	99.97 42

IU-MVS					99.93 24	99.31 10		98.41 142	97.71 19	99.84 12				100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 127	97.27 34	99.80 17	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 127	97.26 36	99.80 17	99.88 21	96.71 24	100.00 1

test_0728_THIRD									96.48 59	99.83 13	99.91 14	97.87 6	100.00 1	99.92 12	100.00 1	100.00 1

GSMVS																99.59 130

test_part2					99.89 45	99.25 18				99.49 62

sam_mvs1												94.72 61				99.59 130

sam_mvs												94.25 76

MTGPA								98.28 173

test_post											63.35 396	94.43 66	98.13 237

patchmatchnet-post											91.70 361	95.12 49	97.95 248

gm-plane-assit					96.97 238	93.76 214			91.47 229		98.96 161		98.79 183	94.92 180

test9_res														99.71 33	99.99 21	100.00 1

agg_prior2														99.48 43	100.00 1	100.00 1

agg_prior					99.93 24	98.77 40		98.43 127		99.63 43			99.85 108

TestCases				95.00 236	99.01 113	88.43 321		96.82 321	86.50 318	88.71 286	98.47 205	74.73 318	99.88 102	85.39 316	96.18 191	96.71 240

test_prior				99.43 35	99.94 13	98.49 58		98.65 74					99.80 121			99.99 23

新几何1				99.42 37	99.75 68	98.27 61		98.63 80	92.69 185	99.55 54	99.82 46	94.40 68	100.00 1	91.21 244	99.94 54	99.99 23

旧先验1					99.76 66	97.52 87		98.64 76			99.85 30	95.63 41			99.94 54	99.99 23

原ACMM1				98.96 75	99.73 72	96.99 109		98.51 104	94.06 138	99.62 46	99.85 30	94.97 58	99.96 61	95.11 174	99.95 49	99.92 81

testdata2													99.99 36	90.54 261

segment_acmp												96.68 26

testdata				98.42 113	99.47 91	95.33 170		98.56 89	93.78 151	99.79 25	99.85 30	93.64 95	99.94 77	94.97 178	99.94 54	100.00 1

test12				99.43 35	99.74 69	98.56 55		98.40 146		99.65 40		94.76 60	99.75 132		99.98 32	99.99 23

plane_prior7					95.71 282	91.59 271

plane_prior6					95.76 276	91.72 266						80.47 267

plane_prior5								97.87 216					98.37 220	97.79 128	89.55 244	94.52 254

plane_prior4											98.59 193

plane_prior3						91.64 269			96.63 56	93.01 217

plane_prior1					95.73 279

n2								0.00 408

nn								0.00 408

door-mid								89.69 392

lessismore_v0				90.53 329	90.58 363	80.90 368		95.80 350		77.01 367	95.84 283	66.15 354	96.95 299	83.03 331	75.05 361	93.74 324

LGP-MVS_train				93.71 289	95.43 289	88.67 317		97.62 233	92.81 178	90.05 251	98.49 201	75.24 312	98.40 212	95.84 168	89.12 248	94.07 297

test11								98.44 119

door								90.31 389

HQP5-MVS						91.85 259

BP-MVS														97.92 121

HQP4-MVS										93.37 213			98.39 214			94.53 252

HQP3-MVS								97.89 214							89.60 241

HQP2-MVS												80.65 263

NP-MVS					95.77 275	91.79 261					98.65 188

ACMMP++_ref															87.04 279

ACMMP++															88.23 266

Test By Simon												92.82 117

ITE_SJBPF				92.38 314	95.69 284	85.14 343		95.71 352	92.81 178	89.33 273	98.11 213	70.23 338	98.42 209	85.91 314	88.16 267	93.59 328

DeepMVS_CX				82.92 360	95.98 269	58.66 391		96.01 347	92.72 182	78.34 362	95.51 298	58.29 373	98.08 239	82.57 333	85.29 290	92.03 354

High-resolution multi-view benchmark