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.

MVS_111021_HR		98.72 25	98.62 22	99.01 71	99.36 97	97.18 101	99.93 75	99.90 1	96.81 51	98.67 108	99.77 61	93.92 90	99.89 96	99.27 53	99.94 54	99.96 64

MVS_111021_LR		98.42 44	98.38 34	98.53 105	99.39 95	95.79 153	99.87 104	99.86 2	96.70 54	98.78 100	99.79 55	92.03 145	99.90 91	99.17 57	99.86 70	99.88 85

CHOSEN 1792x2688		96.81 119	96.53 119	97.64 157	98.91 129	93.07 236	99.65 180	99.80 3	95.64 83	95.39 197	98.86 177	84.35 240	99.90 91	96.98 152	99.16 122	99.95 71

HyFIR lowres test		96.66 130	96.43 122	97.36 175	99.05 112	93.91 216	99.70 172	99.80 3	90.54 261	96.26 181	98.08 221	92.15 142	98.23 238	96.84 158	95.46 210	99.93 76

test2506		97.53 86	97.19 92	98.58 98	98.66 144	96.90 114	98.81 288	99.77 5	94.93 99	97.95 136	98.96 161	92.51 132	99.20 169	94.93 184	98.15 150	99.64 119

MM		98.83 21	98.53 27	99.76 10	99.59 81	99.33 8	99.99 4	99.76 6	98.39 3	99.39 72	99.80 51	90.49 172	99.96 61	99.89 16	99.43 110	99.98 48

thres100view900		96.74 125	95.92 144	99.18 50	98.90 130	98.77 40	99.74 158	99.71 7	92.59 196	95.84 189	98.86 177	89.25 188	99.50 154	93.84 211	94.57 223	99.27 180

tfpn200view9		96.79 120	95.99 132	99.19 49	98.94 121	98.82 36	99.78 144	99.71 7	92.86 178	96.02 186	98.87 175	89.33 186	99.50 154	93.84 211	94.57 223	99.27 180

thres600view7		96.69 128	95.87 147	99.14 59	98.90 130	98.78 39	99.74 158	99.71 7	92.59 196	95.84 189	98.86 177	89.25 188	99.50 154	93.44 223	94.50 226	99.16 187

thres400		96.78 122	95.99 132	99.16 55	98.94 121	98.82 36	99.78 144	99.71 7	92.86 178	96.02 186	98.87 175	89.33 186	99.50 154	93.84 211	94.57 223	99.16 187

thres200		96.96 113	96.21 127	99.22 46	98.97 119	98.84 35	99.85 120	99.71 7	93.17 170	96.26 181	98.88 172	89.87 179	99.51 152	94.26 203	94.91 220	99.31 174

MVS_0304		98.87 20	98.61 23	99.67 16	99.18 103	99.13 22	99.87 104	99.65 12	98.17 8	98.75 105	99.75 69	92.76 124	99.94 77	99.88 18	99.44 108	99.94 74

PVSNet	91.05 13	97.13 105	96.69 113	98.45 110	99.52 88	95.81 152	99.95 52	99.65 12	94.73 107	99.04 88	99.21 139	84.48 237	99.95 69	94.92 185	98.74 136	99.58 136

PVSNet_0	88.03 19	91.80 262	90.27 275	96.38 206	98.27 170	90.46 298	99.94 68	99.61 14	93.99 142	86.26 331	97.39 244	71.13 342	99.89 96	98.77 80	67.05 385	98.79 210

WTY-MVS		98.10 61	97.60 76	99.60 22	98.92 125	99.28 17	99.89 98	99.52 15	95.58 85	98.24 129	99.39 123	93.33 105	99.74 134	97.98 119	95.58 209	99.78 100

HY-MVS	92.50 7	97.79 76	97.17 94	99.63 17	98.98 118	99.32 9	97.49 339	99.52 15	95.69 82	98.32 124	97.41 242	93.32 106	99.77 128	98.08 113	95.75 206	99.81 94

EPNet		98.49 37	98.40 32	98.77 84	99.62 80	96.80 118	99.90 90	99.51 17	97.60 22	99.20 81	99.36 126	93.71 98	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
PGM-MVS		98.34 48	98.13 51	98.99 72	99.92 31	97.00 109	99.75 155	99.50 18	93.90 148	99.37 73	99.76 63	93.24 111	100.00 1	97.75 133	99.96 46	99.98 48

ACMMP		97.74 79	97.44 81	98.66 90	99.92 31	96.13 144	99.18 245	99.45 19	94.84 104	96.41 178	99.71 83	91.40 152	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
MG-MVS		98.91 18	98.65 20	99.68 15	99.94 13	99.07 24	99.64 184	99.44 20	97.33 31	99.00 90	99.72 81	94.03 88	99.98 43	98.73 83	100.00 1	100.00 1

EPMVS		96.53 134	96.01 131	98.09 130	98.43 158	96.12 146	96.36 360	99.43 21	93.53 158	97.64 144	95.04 326	94.41 71	98.38 222	91.13 252	98.11 153	99.75 103

CHOSEN 280x420		99.01 13	99.03 10	98.95 76	99.38 96	98.87 32	98.46 310	99.42 22	97.03 42	99.02 89	99.09 145	99.35 1	98.21 239	99.73 32	99.78 79	99.77 101

D2MVS		92.76 239	92.59 234	93.27 307	95.13 300	89.54 316	99.69 173	99.38 23	92.26 211	87.59 310	94.61 341	85.05 232	97.79 260	91.59 247	88.01 276	92.47 355

sss		97.57 85	97.03 99	99.18 50	98.37 161	98.04 67	99.73 163	99.38 23	93.46 160	98.76 103	99.06 148	91.21 154	99.89 96	96.33 162	97.01 179	99.62 124

PAPM		98.60 30	98.42 31	99.14 59	96.05 273	98.96 26	99.90 90	99.35 25	96.68 55	98.35 123	99.66 96	96.45 30	98.51 206	99.45 45	99.89 66	99.96 64

UGNet		95.33 173	94.57 181	97.62 160	98.55 150	94.85 189	98.67 301	99.32 26	95.75 81	96.80 167	96.27 280	72.18 335	99.96 61	94.58 197	99.05 128	98.04 230
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
test_yl		97.83 70	97.37 84	99.21 47	99.18 103	97.98 70	99.64 184	99.27 27	91.43 237	97.88 140	98.99 155	95.84 39	99.84 116	98.82 77	95.32 215	99.79 97

DCV-MVSNet		97.83 70	97.37 84	99.21 47	99.18 103	97.98 70	99.64 184	99.27 27	91.43 237	97.88 140	98.99 155	95.84 39	99.84 116	98.82 77	95.32 215	99.79 97

VNet		97.21 102	96.57 118	99.13 63	98.97 119	97.82 76	99.03 265	99.21 29	94.31 125	99.18 84	98.88 172	86.26 221	99.89 96	98.93 69	94.32 227	99.69 110

testing3		93.92 208	94.23 188	92.99 315	97.54 217	90.23 302	99.99 4	99.16 30	90.57 260	91.33 247	98.63 195	92.99 116	92.52 381	82.46 340	95.39 213	96.22 253

PVSNet_BlendedMVS		96.05 151	95.82 148	96.72 194	99.59 81	96.99 110	99.95 52	99.10 31	94.06 138	98.27 126	95.80 291	89.00 193	99.95 69	99.12 58	87.53 284	93.24 342

PVSNet_Blended		97.94 64	97.64 74	98.83 81	99.59 81	96.99 110	100.00 1	99.10 31	95.38 90	98.27 126	99.08 146	89.00 193	99.95 69	99.12 58	99.25 118	99.57 137

UniMVSNet_NR-MVSNet		92.95 235	92.11 241	95.49 224	94.61 310	95.28 177	99.83 132	99.08 33	91.49 232	89.21 284	96.86 262	87.14 210	96.73 317	93.20 225	77.52 355	94.46 264

CSCG		97.10 106	97.04 98	97.27 179	99.89 45	91.92 265	99.90 90	99.07 34	88.67 295	95.26 200	99.82 46	93.17 113	99.98 43	98.15 108	99.47 104	99.90 83

PatchMatch-RL		96.04 152	95.40 157	97.95 136	99.59 81	95.22 181	99.52 202	99.07 34	93.96 144	96.49 174	98.35 214	82.28 251	99.82 120	90.15 274	99.22 121	98.81 209

VPA-MVSNet		92.70 242	91.55 254	96.16 211	95.09 301	96.20 140	98.88 279	99.00 36	91.02 251	91.82 241	95.29 320	76.05 314	97.96 253	95.62 175	81.19 327	94.30 280

SDMVSNet		94.80 182	93.96 195	97.33 177	98.92 125	95.42 171	99.59 190	98.99 37	92.41 206	92.55 233	97.85 231	75.81 315	98.93 181	97.90 123	91.62 244	97.64 237

CVMVSNet		94.68 189	94.94 174	93.89 290	96.80 256	86.92 342	99.06 258	98.98 38	94.45 115	94.23 213	99.02 150	85.60 224	95.31 356	90.91 259	95.39 213	99.43 160

UniMVSNet (Re)		93.07 233	92.13 240	95.88 216	94.84 305	96.24 139	99.88 101	98.98 38	92.49 204	89.25 281	95.40 310	87.09 211	97.14 290	93.13 229	78.16 350	94.26 282

fmvsm_s_conf0.5_n		97.80 74	97.85 68	97.67 155	99.06 111	94.41 200	99.98 14	98.97 40	97.34 29	99.63 43	99.69 87	87.27 208	99.97 53	99.62 37	99.06 127	98.62 218

h-mvs33		94.92 180	94.36 184	96.59 198	98.85 133	91.29 281	98.93 274	98.94 41	95.90 76	98.77 101	98.42 213	90.89 166	99.77 128	97.80 126	70.76 374	98.72 215

tfpnnormal		89.29 312	87.61 318	94.34 273	94.35 314	94.13 209	98.95 272	98.94 41	83.94 350	84.47 341	95.51 305	74.84 324	97.39 272	77.05 368	80.41 337	91.48 365

MVS		96.60 131	95.56 155	99.72 13	96.85 253	99.22 20	98.31 318	98.94 41	91.57 230	90.90 251	99.61 103	86.66 216	99.96 61	97.36 139	99.88 68	99.99 23

WR-MVS_H		91.30 268	90.35 272	94.15 276	94.17 317	92.62 251	99.17 246	98.94 41	88.87 291	86.48 327	94.46 346	84.36 238	96.61 322	88.19 293	78.51 348	93.21 343

FIs		94.10 205	93.43 210	96.11 212	94.70 308	96.82 116	99.58 192	98.93 45	92.54 199	89.34 279	97.31 245	87.62 204	97.10 294	94.22 205	86.58 289	94.40 271

fmvsm_s_conf0.5_n_a		97.73 81	97.72 71	97.77 149	98.63 146	94.26 205	99.96 34	98.92 46	97.18 39	99.75 29	99.69 87	87.00 213	99.97 53	99.46 44	98.89 130	99.08 195

test_fmvsm_n_1920		98.44 41	98.61 23	97.92 139	99.27 101	95.18 183	100.00 1	98.90 47	98.05 12	99.80 17	99.73 78	92.64 127	99.99 36	99.58 38	99.51 102	98.59 219

EPNet_dtu		95.71 162	95.39 158	96.66 196	98.92 125	93.41 231	99.57 194	98.90 47	96.19 73	97.52 146	98.56 202	92.65 126	97.36 273	77.89 363	98.33 144	99.20 185
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
patch_mono-2		98.24 56	99.12 5	95.59 223	99.67 77	86.91 343	99.95 52	98.89 49	97.60 22	99.90 3	99.76 63	96.54 29	99.98 43	99.94 11	99.82 76	99.88 85

FC-MVSNet-test		93.81 212	93.15 219	95.80 220	94.30 315	96.20 140	99.42 216	98.89 49	92.33 210	89.03 289	97.27 247	87.39 207	96.83 313	93.20 225	86.48 290	94.36 275

baseline2		96.71 127	96.49 120	97.37 173	95.63 295	95.96 149	99.74 158	98.88 51	92.94 175	91.61 242	98.97 159	97.72 7	98.62 201	94.83 189	98.08 156	97.53 242

API-MVS		97.86 68	97.66 73	98.47 108	99.52 88	95.41 172	99.47 211	98.87 52	91.68 228	98.84 96	99.85 30	92.34 138	99.99 36	98.44 96	99.96 46	100.00 1

fmvsm_l_conf0.5_n		98.94 15	98.84 17	99.25 44	99.17 106	97.81 77	99.98 14	98.86 53	98.25 4	99.90 3	99.76 63	94.21 83	99.97 53	99.87 19	99.52 99	99.98 48

1314		96.84 118	95.96 138	99.48 34	96.74 260	98.52 56	98.31 318	98.86 53	95.82 78	89.91 263	98.98 157	87.49 205	99.96 61	97.80 126	99.73 82	99.96 64

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 37	100.00 1	99.51 40	100.00 1	100.00 1

fmvsm_l_conf0.5_n_a		99.00 14	98.91 14	99.28 43	99.21 102	97.91 74	99.98 14	98.85 56	98.25 4	99.92 2	99.75 69	94.72 65	99.97 53	99.87 19	99.64 87	99.95 71

sd_testset		93.55 221	92.83 225	95.74 221	98.92 125	90.89 289	98.24 321	98.85 56	92.41 206	92.55 233	97.85 231	71.07 343	98.68 198	93.93 208	91.62 244	97.64 237

AdaColmap		97.23 101	96.80 108	98.51 106	99.99 1	95.60 165	99.09 251	98.84 58	93.32 165	96.74 168	99.72 81	86.04 222	100.00 1	98.01 115	99.43 110	99.94 74

test_fmvsmconf_n		98.43 43	98.32 40	98.78 82	98.12 182	96.41 128	99.99 4	98.83 59	98.22 6	99.67 38	99.64 99	91.11 159	99.94 77	99.67 36	99.62 89	99.98 48

IB-MVS	92.85 6	94.99 179	93.94 196	98.16 124	97.72 207	95.69 161	99.99 4	98.81 60	94.28 127	92.70 230	96.90 259	95.08 53	99.17 172	96.07 166	73.88 369	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
3Dnovator	91.47 12	96.28 147	95.34 160	99.08 65	96.82 255	97.47 93	99.45 214	98.81 60	95.52 88	89.39 277	99.00 154	81.97 253	99.95 69	97.27 141	99.83 72	99.84 90

PHI-MVS		98.41 45	98.21 45	99.03 68	99.86 53	97.10 106	99.98 14	98.80 62	90.78 258	99.62 46	99.78 59	95.30 49	100.00 1	99.80 25	99.93 60	99.99 23

MAR-MVS		97.43 89	97.19 92	98.15 127	99.47 92	94.79 193	99.05 262	98.76 63	92.65 192	98.66 109	99.82 46	88.52 198	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
DU-MVS		92.46 248	91.45 257	95.49 224	94.05 318	95.28 177	99.81 137	98.74 64	92.25 212	89.21 284	96.64 270	81.66 256	96.73 317	93.20 225	77.52 355	94.46 264

tt0805		91.28 270	90.18 278	94.60 257	96.26 268	87.55 336	98.39 316	98.72 65	89.00 284	89.22 283	98.47 210	62.98 371	98.96 179	90.57 265	88.00 277	97.28 243

无先验							99.49 208	98.71 66	93.46 160				100.00 1	94.36 200		99.99 23

NR-MVSNet		91.56 267	90.22 276	95.60 222	94.05 318	95.76 155	98.25 320	98.70 67	91.16 246	80.78 359	96.64 270	83.23 248	96.57 323	91.41 248	77.73 354	94.46 264

FE-MVS		95.70 164	95.01 172	97.79 146	98.21 174	94.57 195	95.03 374	98.69 68	88.90 290	97.50 148	96.19 282	92.60 129	99.49 158	89.99 276	97.94 159	99.31 174

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

WR-MVS		92.31 251	91.25 259	95.48 227	94.45 312	95.29 176	99.60 189	98.68 70	90.10 268	88.07 305	96.89 260	80.68 269	96.80 315	93.14 228	79.67 343	94.36 275

ab-mvs		94.69 187	93.42 211	98.51 106	98.07 183	96.26 135	96.49 358	98.68 70	90.31 266	94.54 205	97.00 257	76.30 310	99.71 138	95.98 168	93.38 238	99.56 138

QAPM		95.40 171	94.17 190	99.10 64	96.92 247	97.71 79	99.40 217	98.68 70	89.31 278	88.94 290	98.89 171	82.48 250	99.96 61	93.12 230	99.83 72	99.62 124

Anonymous20240529		92.10 255	90.65 266	96.47 199	98.82 134	90.61 294	98.72 295	98.67 73	75.54 382	93.90 217	98.58 200	66.23 360	99.90 91	94.70 194	90.67 246	98.90 205

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

TranMVSNet+NR-MVSNet		91.68 266	90.61 268	94.87 246	93.69 325	93.98 214	99.69 173	98.65 74	91.03 250	88.44 298	96.83 266	80.05 277	96.18 338	90.26 273	76.89 363	94.45 269

fmvsm_s_conf0.1_n		97.30 97	97.21 91	97.60 161	97.38 226	94.40 202	99.90 90	98.64 76	96.47 61	99.51 61	99.65 98	84.99 233	99.93 85	99.22 55	99.09 126	98.46 220

旧先验1					99.76 66	97.52 87		98.64 76			99.85 30	95.63 42			99.94 54	99.99 23

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 31	100.00 1	99.74 30	100.00 1	100.00 1

PVSNet_Blended_VisFu		97.27 99	96.81 107	98.66 90	98.81 135	96.67 120	99.92 78	98.64 76	94.51 114	96.38 179	98.49 206	89.05 192	99.88 102	97.10 147	98.34 143	99.43 160

新几何1				99.42 37	99.75 68	98.27 61		98.63 80	92.69 189	99.55 54	99.82 46	94.40 72	100.00 1	91.21 250	99.94 54	99.99 23

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

testing222		97.08 110	96.75 110	98.06 132	98.56 147	96.82 116	99.85 120	98.61 82	92.53 200	98.84 96	98.84 181	93.36 103	98.30 230	95.84 171	94.30 228	99.05 197

HFP-MVS		98.56 32	98.37 36	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 81	100.00 1	98.70 84	99.98 32	99.98 48

UWE-MVS		96.79 120	96.72 111	97.00 184	98.51 154	93.70 221	99.71 168	98.60 84	92.96 174	97.09 157	98.34 215	96.67 28	98.85 184	92.11 240	96.50 187	98.44 221

ACMMPR		98.50 36	98.32 40	99.05 66	99.96 8	97.18 101	99.95 52	98.60 84	94.77 105	99.31 76	99.84 41	93.73 97	100.00 1	98.70 84	99.98 32	99.98 48

VPNet		91.81 259	90.46 269	95.85 218	94.74 307	95.54 167	98.98 268	98.59 86	92.14 213	90.77 253	97.44 241	68.73 350	97.54 269	94.89 188	77.89 352	94.46 264

test0.0.03 1		93.86 209	93.61 202	94.64 255	95.02 304	92.18 259	99.93 75	98.58 87	94.07 136	87.96 306	98.50 205	93.90 92	94.96 360	81.33 347	93.17 239	96.78 245

DELS-MVS		98.54 33	98.22 44	99.50 30	99.15 108	98.65 51	100.00 1	98.58 87	97.70 20	98.21 130	99.24 137	92.58 130	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
ETVMVS		97.03 111	96.64 114	98.20 123	98.67 143	97.12 105	99.89 98	98.57 89	91.10 248	98.17 131	98.59 197	93.86 94	98.19 240	95.64 174	95.24 217	99.28 179

CP-MVSNet		91.23 272	90.22 276	94.26 274	93.96 320	92.39 255	99.09 251	98.57 89	88.95 288	86.42 328	96.57 273	79.19 284	96.37 330	90.29 272	78.95 345	94.02 306

OpenMVS	90.15 15	94.77 185	93.59 205	98.33 117	96.07 272	97.48 92	99.56 196	98.57 89	90.46 262	86.51 325	98.95 166	78.57 291	99.94 77	93.86 210	99.74 81	97.57 241

hse-mvs2		94.38 198	94.08 192	95.31 233	98.27 170	90.02 308	99.29 236	98.56 92	95.90 76	98.77 101	98.00 224	90.89 166	98.26 237	97.80 126	69.20 380	97.64 237

AUN-MVS		93.28 226	92.60 231	95.34 231	98.29 167	90.09 306	99.31 231	98.56 92	91.80 226	96.35 180	98.00 224	89.38 185	98.28 233	92.46 235	69.22 379	97.64 237

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 52	98.56 92	97.56 25	99.44 65	99.85 30	95.38 48	100.00 1	99.31 51	99.99 21	99.87 87

testdata				98.42 113	99.47 92	95.33 175		98.56 92	93.78 151	99.79 25	99.85 30	93.64 100	99.94 77	94.97 183	99.94 54	100.00 1

EPP-MVSNet		96.69 128	96.60 116	96.96 186	97.74 202	93.05 238	99.37 224	98.56 92	88.75 293	95.83 191	99.01 152	96.01 33	98.56 203	96.92 156	97.20 173	99.25 182

DeepPCF-MVS	95.94 2	97.71 82	98.98 12	93.92 287	99.63 79	81.76 370	99.96 34	98.56 92	99.47 1	99.19 83	99.99 1	94.16 85	100.00 1	99.92 12	99.93 60	100.00 1

region2R		98.54 33	98.37 36	99.05 66	99.96 8	97.18 101	99.96 34	98.55 98	94.87 103	99.45 64	99.85 30	94.07 87	100.00 1	98.67 86	100.00 1	99.98 48

test222					99.55 86	97.41 96	99.34 227	98.55 98	91.86 222	99.27 80	99.83 43	93.84 95			99.95 49	99.99 23

tpmvs		94.28 203	93.57 206	96.40 204	98.55 150	91.50 279	95.70 373	98.55 98	87.47 311	92.15 237	94.26 348	91.42 151	98.95 180	88.15 294	95.85 202	98.76 211

thisisatest0530		97.10 106	96.72 111	98.22 122	97.60 215	96.70 119	99.92 78	98.54 101	91.11 247	97.07 159	98.97 159	97.47 12	99.03 176	93.73 219	96.09 194	98.92 202

tttt0517		96.85 117	96.49 120	97.92 139	97.48 222	95.89 151	99.85 120	98.54 101	90.72 259	96.63 170	98.93 170	97.47 12	99.02 177	93.03 231	95.76 205	98.85 206

thisisatest0515		97.41 94	97.02 100	98.59 97	97.71 209	97.52 87	99.97 27	98.54 101	91.83 223	97.45 149	99.04 149	97.50 9	99.10 175	94.75 192	96.37 191	99.16 187

ZD-MVS					99.92 31	98.57 54		98.52 104	92.34 209	99.31 76	99.83 43	95.06 54	99.80 121	99.70 34	99.97 42

GG-mvs-BLEND				98.54 103	98.21 174	98.01 68	93.87 379	98.52 104		97.92 137	97.92 230	99.02 2	97.94 256	98.17 106	99.58 96	99.67 113

PS-CasMVS		90.63 285	89.51 292	93.99 285	93.83 322	91.70 274	98.98 268	98.52 104	88.48 299	86.15 332	96.53 275	75.46 317	96.31 334	88.83 285	78.86 347	93.95 314

dmvs_re		93.20 228	93.15 219	93.34 304	96.54 264	83.81 357	98.71 296	98.51 107	91.39 241	92.37 236	98.56 202	78.66 290	97.83 259	93.89 209	89.74 247	98.38 223

CANet		98.27 52	97.82 69	99.63 17	99.72 74	99.10 23	99.98 14	98.51 107	97.00 43	98.52 114	99.71 83	87.80 201	99.95 69	99.75 28	99.38 112	99.83 91

gg-mvs-nofinetune		93.51 222	91.86 249	98.47 108	97.72 207	97.96 72	92.62 383	98.51 107	74.70 385	97.33 152	69.59 398	98.91 3	97.79 260	97.77 131	99.56 97	99.67 113

EI-MVSNet-Vis-set		98.27 52	98.11 53	98.75 85	99.83 57	96.59 124	99.40 217	98.51 107	95.29 93	98.51 115	99.76 63	93.60 101	99.71 138	98.53 94	99.52 99	99.95 71

原ACMM1				98.96 75	99.73 72	96.99 110		98.51 107	94.06 138	99.62 46	99.85 30	94.97 60	99.96 61	95.11 179	99.95 49	99.92 81

fmvsm_s_conf0.1_n_a		97.09 108	96.90 103	97.63 159	95.65 293	94.21 207	99.83 132	98.50 112	96.27 70	99.65 40	99.64 99	84.72 234	99.93 85	99.04 63	98.84 133	98.74 213

EI-MVSNet-UG-set		98.14 59	97.99 58	98.60 95	99.80 61	96.27 134	99.36 226	98.50 112	95.21 95	98.30 125	99.75 69	93.29 108	99.73 137	98.37 99	99.30 116	99.81 94

LS3D		95.84 158	95.11 168	98.02 134	99.85 54	95.10 185	98.74 293	98.50 112	87.22 316	93.66 218	99.86 26	87.45 206	99.95 69	90.94 258	99.81 78	99.02 199

PEN-MVS		90.19 297	89.06 300	93.57 300	93.06 340	90.90 288	99.06 258	98.47 115	88.11 304	85.91 334	96.30 279	76.67 304	95.94 348	87.07 308	76.91 362	93.89 319

DeepC-MVS_fast	96.59 1	98.81 23	98.54 26	99.62 20	99.90 42	98.85 34	99.24 240	98.47 115	98.14 10	99.08 86	99.91 14	93.09 114	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
PLC	95.54 3	97.93 65	97.89 67	98.05 133	99.82 58	94.77 194	99.92 78	98.46 117	93.93 146	97.20 155	99.27 132	95.44 47	99.97 53	97.41 138	99.51 102	99.41 162
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
testing11		97.48 88	97.27 88	98.10 129	98.36 162	96.02 147	99.92 78	98.45 118	93.45 162	98.15 132	98.70 187	95.48 46	99.22 165	97.85 125	95.05 219	99.07 196

test_fmvsmvis_n_1920		97.67 83	97.59 78	97.91 141	97.02 242	95.34 174	99.95 52	98.45 118	97.87 15	97.02 160	99.59 104	89.64 181	99.98 43	99.41 48	99.34 115	98.42 222

test1111		95.57 167	94.98 173	97.37 173	98.56 147	93.37 233	98.86 283	98.45 118	94.95 98	96.63 170	98.95 166	75.21 322	99.11 174	95.02 182	98.14 152	99.64 119

ECVR-MVS		95.66 165	95.05 170	97.51 165	98.66 144	93.71 220	98.85 285	98.45 118	94.93 99	96.86 164	98.96 161	75.22 321	99.20 169	95.34 176	98.15 150	99.64 119

UA-Net		96.54 133	95.96 138	98.27 120	98.23 172	95.71 158	98.00 332	98.45 118	93.72 154	98.41 119	99.27 132	88.71 197	99.66 146	91.19 251	97.69 161	99.44 159

ZNCC-MVS		98.31 49	98.03 56	99.17 53	99.88 49	97.59 84	99.94 68	98.44 123	94.31 125	98.50 116	99.82 46	93.06 115	99.99 36	98.30 103	99.99 21	99.93 76

DPM-MVS		98.83 21	98.46 30	99.97 1	99.33 98	99.92 1	99.96 34	98.44 123	97.96 14	99.55 54	99.94 4	97.18 21	100.00 1	93.81 214	99.94 54	99.98 48

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 104	98.44 123	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
alignmvs		97.81 73	97.33 86	99.25 44	98.77 138	98.66 49	99.99 4	98.44 123	94.40 121	98.41 119	99.47 114	93.65 99	99.42 162	98.57 92	94.26 229	99.67 113

test11								98.44 123

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 50	98.72 140	97.71 79	99.98 14	98.44 123	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.
MDTV_nov1_ep13			95.69 151		97.90 191	94.15 208	95.98 369	98.44 123	93.12 171	97.98 135	95.74 293	95.10 52	98.58 202	90.02 275	96.92 181

DP-MVS Recon		98.41 45	98.02 57	99.56 25	99.97 3	98.70 46	99.92 78	98.44 123	92.06 217	98.40 121	99.84 41	95.68 41	100.00 1	98.19 105	99.71 83	99.97 58

testing99		97.17 103	96.91 102	97.95 136	98.35 164	95.70 159	99.91 83	98.43 131	92.94 175	97.36 151	98.72 185	94.83 62	99.21 166	97.00 150	94.64 221	98.95 201

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 52	98.43 131	96.48 59	99.80 17	99.93 11	97.44 14	100.00 1	99.92 12	99.98 32	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 34	98.43 131	97.27 34	99.80 17	99.94 4	96.71 24	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 131	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		98.43 131	97.26 36	99.80 17	99.88 21	96.71 24	100.00 1

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 52	98.43 131					100.00 1	99.99 5	100.00 1	100.00 1

TEST9					99.92 31	98.92 28	99.96 34	98.43 131	93.90 148	99.71 34	99.86 26	95.88 38	99.85 108

train_agg		98.88 19	98.65 20	99.59 23	99.92 31	98.92 28	99.96 34	98.43 131	94.35 122	99.71 34	99.86 26	95.94 35	99.85 108	99.69 35	99.98 32	99.99 23

test_8					99.92 31	98.88 31	99.96 34	98.43 131	94.35 122	99.69 36	99.85 30	95.94 35	99.85 108

agg_prior					99.93 24	98.77 40		98.43 131		99.63 43			99.85 108

PAPM_NR		98.12 60	97.93 64	98.70 87	99.94 13	96.13 144	99.82 135	98.43 131	94.56 113	97.52 146	99.70 85	94.40 72	99.98 43	97.00 150	99.98 32	99.99 23

PAPR		98.52 35	98.16 49	99.58 24	99.97 3	98.77 40	99.95 52	98.43 131	95.35 91	98.03 134	99.75 69	94.03 88	99.98 43	98.11 110	99.83 72	99.99 23

testing91		97.16 104	96.90 103	97.97 135	98.35 164	95.67 162	99.91 83	98.42 143	92.91 177	97.33 152	98.72 185	94.81 63	99.21 166	96.98 152	94.63 222	99.03 198

test0726					99.93 24	99.29 15	99.96 34	98.42 143	97.28 32	99.86 7	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 73	99.93 24	97.24 98	99.95 52	98.42 143	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
XVS		98.70 26	98.55 25	99.15 57	99.94 13	97.50 90	99.94 68	98.42 143	96.22 71	99.41 68	99.78 59	94.34 77	99.96 61	98.92 70	99.95 49	99.99 23

X-MVStestdata		93.83 210	92.06 243	99.15 57	99.94 13	97.50 90	99.94 68	98.42 143	96.22 71	99.41 68	41.37 407	94.34 77	99.96 61	98.92 70	99.95 49	99.99 23

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 148					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 148					100.00 1	99.96 9	100.00 1	100.00 1

test_one_0601					99.94 13	99.30 12		98.41 148	96.63 56	99.75 29	99.93 11	97.49 10

IU-MVS					99.93 24	99.31 10		98.41 148	97.71 19	99.84 12				100.00 1	100.00 1	100.00 1

save fliter					99.82 58	98.79 38	99.96 34	98.40 152	97.66 21

test12				99.43 35	99.74 69	98.56 55		98.40 152		99.65 40		94.76 64	99.75 132		99.98 32	99.99 23

PatchmatchNet		95.94 155	95.45 156	97.39 172	97.83 196	94.41 200	96.05 367	98.40 152	92.86 178	97.09 157	95.28 321	94.21 83	98.07 247	89.26 282	98.11 153	99.70 108
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GST-MVS		98.27 52	97.97 59	99.17 53	99.92 31	97.57 85	99.93 75	98.39 155	94.04 141	98.80 99	99.74 76	92.98 117	100.00 1	98.16 107	99.76 80	99.93 76

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 43	99.91 83	98.39 155	97.20 38	99.46 63	99.85 30	95.53 45	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
MP-MVS		98.23 57	97.97 59	99.03 68	99.94 13	97.17 104	99.95 52	98.39 155	94.70 109	98.26 128	99.81 50	91.84 149	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.
CP-MVS		98.45 40	98.32 40	98.87 79	99.96 8	96.62 122	99.97 27	98.39 155	94.43 117	98.90 94	99.87 24	94.30 79	100.00 1	99.04 63	99.99 21	99.99 23

SMA-MVS		98.76 24	98.48 29	99.62 20	99.87 51	98.87 32	99.86 117	98.38 159	93.19 169	99.77 27	99.94 4	95.54 43	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
TSAR-MVS + MP.		98.93 16	98.77 18	99.41 38	99.74 69	98.67 47	99.77 147	98.38 159	96.73 53	99.88 6	99.74 76	94.89 61	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
mPP-MVS		98.39 47	98.20 46	98.97 74	99.97 3	96.92 113	99.95 52	98.38 159	95.04 97	98.61 112	99.80 51	93.39 102	100.00 1	98.64 89	100.00 1	99.98 48

ACMMP_NAP		98.49 37	98.14 50	99.54 27	99.66 78	98.62 53	99.85 120	98.37 162	94.68 110	99.53 57	99.83 43	92.87 120	100.00 1	98.66 88	99.84 71	99.99 23

FOURS1					99.92 31	97.66 83	99.95 52	98.36 163	95.58 85	99.52 59

APD-MVS		98.62 29	98.35 39	99.41 38	99.90 42	98.51 57	99.87 104	98.36 163	94.08 135	99.74 31	99.73 78	94.08 86	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
Syy-MVS		90.00 301	90.63 267	88.11 357	97.68 210	74.66 385	99.71 168	98.35 165	90.79 256	92.10 238	98.67 189	79.10 286	93.09 377	63.35 391	95.95 199	96.59 248

myMVS_eth3d		94.46 196	94.76 178	93.55 301	97.68 210	90.97 284	99.71 168	98.35 165	90.79 256	92.10 238	98.67 189	92.46 135	93.09 377	87.13 307	95.95 199	96.59 248

SR-MVS		98.46 39	98.30 43	98.93 77	99.88 49	97.04 107	99.84 125	98.35 165	94.92 101	99.32 75	99.80 51	93.35 104	99.78 125	99.30 52	99.95 49	99.96 64

CPTT-MVS		97.64 84	97.32 87	98.58 98	99.97 3	95.77 154	99.96 34	98.35 165	89.90 272	98.36 122	99.79 55	91.18 158	99.99 36	98.37 99	99.99 21	99.99 23

SD-MVS		98.92 17	98.70 19	99.56 25	99.70 76	98.73 44	99.94 68	98.34 169	96.38 65	99.81 15	99.76 63	94.59 68	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
9.14			98.38 34		99.87 51		99.91 83	98.33 170	93.22 168	99.78 26	99.89 19	94.57 69	99.85 108	99.84 22	99.97 42

CDPH-MVS		98.65 28	98.36 38	99.49 32	99.94 13	98.73 44	99.87 104	98.33 170	93.97 143	99.76 28	99.87 24	94.99 59	99.75 132	98.55 93	100.00 1	99.98 48

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 52	98.32 172	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
SCA		94.69 187	93.81 200	97.33 177	97.10 238	94.44 197	98.86 283	98.32 172	93.30 166	96.17 184	95.59 300	76.48 308	97.95 254	91.06 254	97.43 166	99.59 130

SR-MVS-dyc-post		98.31 49	98.17 48	98.71 86	99.79 62	96.37 132	99.76 152	98.31 174	94.43 117	99.40 70	99.75 69	93.28 109	99.78 125	98.90 73	99.92 63	99.97 58

RE-MVS-def			98.13 51		99.79 62	96.37 132	99.76 152	98.31 174	94.43 117	99.40 70	99.75 69	92.95 118		98.90 73	99.92 63	99.97 58

RPMNet		89.76 305	87.28 320	97.19 180	96.29 266	92.66 248	92.01 386	98.31 174	70.19 391	96.94 161	85.87 390	87.25 209	99.78 125	62.69 392	95.96 197	99.13 191

APD-MVS_3200maxsize		98.25 55	98.08 55	98.78 82	99.81 60	96.60 123	99.82 135	98.30 177	93.95 145	99.37 73	99.77 61	92.84 121	99.76 131	98.95 67	99.92 63	99.97 58

TESTMET0.1,1		96.74 125	96.26 125	98.16 124	97.36 228	96.48 125	99.96 34	98.29 178	91.93 220	95.77 192	98.07 222	95.54 43	98.29 231	90.55 266	98.89 130	99.70 108

MTGPA								98.28 179

MTAPA		98.29 51	97.96 62	99.30 42	99.85 54	97.93 73	99.39 221	98.28 179	95.76 80	97.18 156	99.88 21	92.74 125	100.00 1	98.67 86	99.88 68	99.99 23

114514_t		97.41 94	96.83 106	99.14 59	99.51 90	97.83 75	99.89 98	98.27 181	88.48 299	99.06 87	99.66 96	90.30 174	99.64 148	96.32 163	99.97 42	99.96 64

Anonymous20231211		89.86 303	88.44 310	94.13 278	98.93 123	90.68 292	98.54 307	98.26 182	76.28 378	86.73 321	95.54 302	70.60 344	97.56 268	90.82 261	80.27 340	94.15 295

Vis-MVSNet		95.72 160	95.15 167	97.45 167	97.62 214	94.28 204	99.28 237	98.24 183	94.27 129	96.84 165	98.94 168	79.39 281	98.76 190	93.25 224	98.49 140	99.30 176
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	91.53 11	96.31 144	95.24 163	99.52 28	96.88 252	98.64 52	99.72 166	98.24 183	95.27 94	88.42 302	98.98 157	82.76 249	99.94 77	97.10 147	99.83 72	99.96 64

DTE-MVSNet		89.40 310	88.24 313	92.88 317	92.66 348	89.95 310	99.10 250	98.22 185	87.29 314	85.12 339	96.22 281	76.27 311	95.30 357	83.56 335	75.74 366	93.41 336

SF-MVS		98.67 27	98.40 32	99.50 30	99.77 65	98.67 47	99.90 90	98.21 186	93.53 158	99.81 15	99.89 19	94.70 67	99.86 107	99.84 22	99.93 60	99.96 64

VDDNet		93.12 231	91.91 247	96.76 192	96.67 263	92.65 250	98.69 299	98.21 186	82.81 359	97.75 143	99.28 129	61.57 375	99.48 159	98.09 112	94.09 231	98.15 227

test-LLR		96.47 135	96.04 130	97.78 147	97.02 242	95.44 169	99.96 34	98.21 186	94.07 136	95.55 194	96.38 276	93.90 92	98.27 235	90.42 269	98.83 134	99.64 119

test-mter		96.39 140	95.93 142	97.78 147	97.02 242	95.44 169	99.96 34	98.21 186	91.81 225	95.55 194	96.38 276	95.17 50	98.27 235	90.42 269	98.83 134	99.64 119

MP-MVS-pluss		98.07 62	97.64 74	99.38 41	99.74 69	98.41 60	99.74 158	98.18 190	93.35 163	96.45 175	99.85 30	92.64 127	99.97 53	98.91 72	99.89 66	99.77 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FA-MVS(test-final)		95.86 156	95.09 169	98.15 127	97.74 202	95.62 164	96.31 362	98.17 191	91.42 239	96.26 181	96.13 285	90.56 170	99.47 160	92.18 239	97.07 175	99.35 169

PS-MVSNAJ		98.44 41	98.20 46	99.16 55	98.80 136	98.92 28	99.54 200	98.17 191	97.34 29	99.85 9	99.85 30	91.20 155	99.89 96	99.41 48	99.67 85	98.69 216

HPM-MVS		97.96 63	97.72 71	98.68 88	99.84 56	96.39 131	99.90 90	98.17 191	92.61 194	98.62 111	99.57 107	91.87 148	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
tpmrst		96.27 148	95.98 134	97.13 181	97.96 188	93.15 235	96.34 361	98.17 191	92.07 215	98.71 107	95.12 324	93.91 91	98.73 192	94.91 187	96.62 184	99.50 151

WB-MVSnew		92.90 236	92.77 228	93.26 308	96.95 246	93.63 223	99.71 168	98.16 195	91.49 232	94.28 211	98.14 219	81.33 261	96.48 326	79.47 355	95.46 210	89.68 378

ADS-MVSNet		94.79 183	94.02 193	97.11 183	97.87 193	93.79 217	94.24 375	98.16 195	90.07 269	96.43 176	94.48 344	90.29 175	98.19 240	87.44 301	97.23 171	99.36 167

HPM-MVS_fast		97.80 74	97.50 79	98.68 88	99.79 62	96.42 127	99.88 101	98.16 195	91.75 227	98.94 92	99.54 110	91.82 150	99.65 147	97.62 136	99.99 21	99.99 23

Vis-MVSNet (Re-imp)		96.32 143	95.98 134	97.35 176	97.93 190	94.82 191	99.47 211	98.15 198	91.83 223	95.09 201	99.11 144	91.37 153	97.47 271	93.47 222	97.43 166	99.74 104

CNLPA		97.76 78	97.38 83	98.92 78	99.53 87	96.84 115	99.87 104	98.14 199	93.78 151	96.55 173	99.69 87	92.28 139	99.98 43	97.13 145	99.44 108	99.93 76

JIA-IIPM		91.76 265	90.70 265	94.94 244	96.11 271	87.51 337	93.16 382	98.13 200	75.79 381	97.58 145	77.68 395	92.84 121	97.97 251	88.47 291	96.54 185	99.33 172

cl22		93.77 214	93.25 218	95.33 232	99.49 91	94.43 198	99.61 188	98.09 201	90.38 263	89.16 287	95.61 298	90.56 170	97.34 275	91.93 242	84.45 305	94.21 287

cdsmvs_eth3d_5k		23.43 374	31.24 377	0.00 391	0.00 414	0.00 416	0.00 402	98.09 201	0.00 409	0.00 410	99.67 94	83.37 246	0.00 410	0.00 409	0.00 408	0.00 406

xiu_mvs_v2_base		98.23 57	97.97 59	99.02 70	98.69 141	98.66 49	99.52 202	98.08 203	97.05 41	99.86 7	99.86 26	90.65 168	99.71 138	99.39 50	98.63 138	98.69 216

tpm cat1		93.51 222	92.52 236	96.47 199	97.77 200	91.47 280	96.13 365	98.06 204	80.98 367	92.91 227	93.78 352	89.66 180	98.87 182	87.03 310	96.39 190	99.09 193

DeepC-MVS	94.51 4	96.92 116	96.40 123	98.45 110	99.16 107	95.90 150	99.66 178	98.06 204	96.37 68	94.37 209	99.49 113	83.29 247	99.90 91	97.63 135	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
test_fmvsmconf0.1_n		97.74 79	97.44 81	98.64 92	95.76 284	96.20 140	99.94 68	98.05 206	98.17 8	98.89 95	99.42 118	87.65 203	99.90 91	99.50 41	99.60 95	99.82 92

EU-MVSNet		90.14 299	90.34 273	89.54 345	92.55 349	81.06 374	98.69 299	98.04 207	91.41 240	86.59 324	96.84 265	80.83 267	93.31 376	86.20 316	81.91 322	94.26 282

TAPA-MVS	92.12 8	94.42 197	93.60 204	96.90 188	99.33 98	91.78 269	99.78 144	98.00 208	89.89 273	94.52 206	99.47 114	91.97 146	99.18 171	69.90 380	99.52 99	99.73 105
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		95.78 159	94.86 175	98.54 103	98.47 157	98.07 65	99.06 258	97.99 209	92.68 190	94.13 214	98.62 196	93.28 109	98.69 197	93.79 216	85.76 293	98.84 207

UnsupCasMVSNet_eth		85.52 330	83.99 332	90.10 341	89.36 378	83.51 359	96.65 356	97.99 209	89.14 279	75.89 379	93.83 351	63.25 370	93.92 369	81.92 345	67.90 384	92.88 348

LFMVS		94.75 186	93.56 207	98.30 119	99.03 113	95.70 159	98.74 293	97.98 211	87.81 309	98.47 117	99.39 123	67.43 356	99.53 150	98.01 115	95.20 218	99.67 113

dp		95.05 177	94.43 183	96.91 187	97.99 187	92.73 246	96.29 363	97.98 211	89.70 275	95.93 188	94.67 339	93.83 96	98.45 211	86.91 314	96.53 186	99.54 143

PMMVS		96.76 123	96.76 109	96.76 192	98.28 169	92.10 260	99.91 83	97.98 211	94.12 133	99.53 57	99.39 123	86.93 214	98.73 192	96.95 155	97.73 160	99.45 157

F-COLMAP		96.93 115	96.95 101	96.87 189	99.71 75	91.74 270	99.85 120	97.95 214	93.11 172	95.72 193	99.16 143	92.35 137	99.94 77	95.32 177	99.35 114	98.92 202

OMC-MVS		97.28 98	97.23 90	97.41 170	99.76 66	93.36 234	99.65 180	97.95 214	96.03 75	97.41 150	99.70 85	89.61 182	99.51 152	96.73 159	98.25 149	99.38 164

mvsany_test1		97.82 72	97.90 66	97.55 162	98.77 138	93.04 239	99.80 141	97.93 216	96.95 45	99.61 52	99.68 93	90.92 163	99.83 118	99.18 56	98.29 148	99.80 96

Anonymous202405211		93.10 232	91.99 245	96.40 204	99.10 109	89.65 314	98.88 279	97.93 216	83.71 353	94.00 215	98.75 184	68.79 348	99.88 102	95.08 181	91.71 243	99.68 111

tpm2		95.47 169	95.18 166	96.35 207	96.91 248	91.70 274	96.96 352	97.93 216	88.04 306	98.44 118	95.40 310	93.32 106	97.97 251	94.00 206	95.61 208	99.38 164

TSAR-MVS + GP.		98.60 30	98.51 28	98.86 80	99.73 72	96.63 121	99.97 27	97.92 219	98.07 11	98.76 103	99.55 108	95.00 58	99.94 77	99.91 15	97.68 162	99.99 23

CDS-MVSNet		96.34 142	96.07 129	97.13 181	97.37 227	94.96 187	99.53 201	97.91 220	91.55 231	95.37 198	98.32 216	95.05 55	97.13 291	93.80 215	95.75 206	99.30 176
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP3-MVS								97.89 221							89.60 248

HQP-MVS		94.61 191	94.50 182	94.92 245	95.78 280	91.85 266	99.87 104	97.89 221	96.82 48	93.37 220	98.65 192	80.65 270	98.39 218	97.92 121	89.60 248	94.53 258

HQP_MVS		94.49 195	94.36 184	94.87 246	95.71 290	91.74 270	99.84 125	97.87 223	96.38 65	93.01 224	98.59 197	80.47 274	98.37 224	97.79 129	89.55 251	94.52 260

plane_prior5								97.87 223					98.37 224	97.79 129	89.55 251	94.52 260

xiu_mvs_v1_base_debu		97.43 89	97.06 95	98.55 100	97.74 202	98.14 62	99.31 231	97.86 225	96.43 62	99.62 46	99.69 87	85.56 225	99.68 142	99.05 60	98.31 145	97.83 232

xiu_mvs_v1_base		97.43 89	97.06 95	98.55 100	97.74 202	98.14 62	99.31 231	97.86 225	96.43 62	99.62 46	99.69 87	85.56 225	99.68 142	99.05 60	98.31 145	97.83 232

xiu_mvs_v1_base_debi		97.43 89	97.06 95	98.55 100	97.74 202	98.14 62	99.31 231	97.86 225	96.43 62	99.62 46	99.69 87	85.56 225	99.68 142	99.05 60	98.31 145	97.83 232

CostFormer		96.10 149	95.88 146	96.78 191	97.03 241	92.55 252	97.08 349	97.83 228	90.04 271	98.72 106	94.89 333	95.01 57	98.29 231	96.54 161	95.77 204	99.50 151

TAMVS		95.85 157	95.58 154	96.65 197	97.07 239	93.50 227	99.17 246	97.82 229	91.39 241	95.02 202	98.01 223	92.20 140	97.30 280	93.75 218	95.83 203	99.14 190

VDD-MVS		93.77 214	92.94 222	96.27 209	98.55 150	90.22 303	98.77 292	97.79 230	90.85 254	96.82 166	99.42 118	61.18 377	99.77 128	98.95 67	94.13 230	98.82 208

cascas		94.64 190	93.61 202	97.74 153	97.82 197	96.26 135	99.96 34	97.78 231	85.76 334	94.00 215	97.54 238	76.95 302	99.21 166	97.23 143	95.43 212	97.76 236

CLD-MVS		94.06 207	93.90 197	94.55 261	96.02 274	90.69 291	99.98 14	97.72 232	96.62 58	91.05 250	98.85 180	77.21 297	98.47 207	98.11 110	89.51 253	94.48 262
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MS-PatchMatch		90.65 283	90.30 274	91.71 329	94.22 316	85.50 349	98.24 321	97.70 233	88.67 295	86.42 328	96.37 278	67.82 354	98.03 249	83.62 334	99.62 89	91.60 363

RRT_MVS		93.14 230	92.92 223	93.78 292	93.31 333	90.04 307	99.66 178	97.69 234	92.53 200	88.91 291	97.76 235	84.36 238	96.93 307	95.10 180	86.99 287	94.37 274

XXY-MVS		91.82 258	90.46 269	95.88 216	93.91 321	95.40 173	98.87 282	97.69 234	88.63 297	87.87 307	97.08 252	74.38 328	97.89 257	91.66 246	84.07 309	94.35 278

EI-MVSNet		93.73 216	93.40 214	94.74 251	96.80 256	92.69 247	99.06 258	97.67 236	88.96 287	91.39 244	99.02 150	88.75 196	97.30 280	91.07 253	87.85 278	94.22 285

MVSTER		95.53 168	95.22 164	96.45 201	98.56 147	97.72 78	99.91 83	97.67 236	92.38 208	91.39 244	97.14 249	97.24 18	97.30 280	94.80 190	87.85 278	94.34 279

ETV-MVS		97.92 66	97.80 70	98.25 121	98.14 180	96.48 125	99.98 14	97.63 238	95.61 84	99.29 79	99.46 116	92.55 131	98.82 185	99.02 66	98.54 139	99.46 155

CANet_DTU		96.76 123	96.15 128	98.60 95	98.78 137	97.53 86	99.84 125	97.63 238	97.25 37	99.20 81	99.64 99	81.36 260	99.98 43	92.77 234	98.89 130	98.28 225

LPG-MVS_test		92.96 234	92.71 229	93.71 295	95.43 297	88.67 324	99.75 155	97.62 240	92.81 182	90.05 258	98.49 206	75.24 319	98.40 216	95.84 171	89.12 255	94.07 303

LGP-MVS_train				93.71 295	95.43 297	88.67 324		97.62 240	92.81 182	90.05 258	98.49 206	75.24 319	98.40 216	95.84 171	89.12 255	94.07 303

FMVSNet3		92.69 243	91.58 252	95.99 214	98.29 167	97.42 95	99.26 239	97.62 240	89.80 274	89.68 269	95.32 316	81.62 258	96.27 335	87.01 311	85.65 294	94.29 281

ET-MVSNet_ETH3D		94.37 199	93.28 217	97.64 157	98.30 166	97.99 69	99.99 4	97.61 243	94.35 122	71.57 385	99.45 117	96.23 32	95.34 355	96.91 157	85.14 300	99.59 130

EIA-MVS		97.53 86	97.46 80	97.76 151	98.04 185	94.84 190	99.98 14	97.61 243	94.41 120	97.90 138	99.59 104	92.40 136	98.87 182	98.04 114	99.13 124	99.59 130

OPM-MVS		93.21 227	92.80 226	94.44 268	93.12 337	90.85 290	99.77 147	97.61 243	96.19 73	91.56 243	98.65 192	75.16 323	98.47 207	93.78 217	89.39 254	93.99 311
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
IS-MVSNet		96.29 146	95.90 145	97.45 167	98.13 181	94.80 192	99.08 253	97.61 243	92.02 219	95.54 196	98.96 161	90.64 169	98.08 245	93.73 219	97.41 169	99.47 154

CMPMVS	61.59 21	84.75 336	85.14 331	83.57 365	90.32 373	62.54 393	96.98 351	97.59 247	74.33 386	69.95 387	96.66 268	64.17 367	98.32 228	87.88 298	88.41 269	89.84 377
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UniMVSNet_ETH3D		90.06 300	88.58 308	94.49 265	94.67 309	88.09 333	97.81 337	97.57 248	83.91 352	88.44 298	97.41 242	57.44 381	97.62 267	91.41 248	88.59 266	97.77 235

lupinMVS		97.85 69	97.60 76	98.62 93	97.28 235	97.70 81	99.99 4	97.55 249	95.50 89	99.43 66	99.67 94	90.92 163	98.71 195	98.40 97	99.62 89	99.45 157

XVG-OURS		94.82 181	94.74 179	95.06 240	98.00 186	89.19 317	99.08 253	97.55 249	94.10 134	94.71 204	99.62 102	80.51 272	99.74 134	96.04 167	93.06 242	96.25 250

XVG-OURS-SEG-HR		94.79 183	94.70 180	95.08 239	98.05 184	89.19 317	99.08 253	97.54 251	93.66 155	94.87 203	99.58 106	78.78 288	99.79 123	97.31 140	93.40 237	96.25 250

PatchT		90.38 290	88.75 306	95.25 235	95.99 275	90.16 304	91.22 390	97.54 251	76.80 377	97.26 154	86.01 389	91.88 147	96.07 344	66.16 388	95.91 201	99.51 149

BH-RMVSNet		95.18 174	94.31 187	97.80 144	98.17 178	95.23 180	99.76 152	97.53 253	92.52 202	94.27 212	99.25 136	76.84 303	98.80 186	90.89 260	99.54 98	99.35 169

ACMP	92.05 9	92.74 240	92.42 238	93.73 293	95.91 278	88.72 323	99.81 137	97.53 253	94.13 132	87.00 319	98.23 217	74.07 329	98.47 207	96.22 165	88.86 260	93.99 311
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	91.95 10	92.88 237	92.52 236	93.98 286	95.75 286	89.08 320	99.77 147	97.52 255	93.00 173	89.95 262	97.99 226	76.17 312	98.46 210	93.63 221	88.87 259	94.39 273
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TR-MVS		94.54 192	93.56 207	97.49 166	97.96 188	94.34 203	98.71 296	97.51 256	90.30 267	94.51 207	98.69 188	75.56 316	98.77 189	92.82 233	95.99 196	99.35 169

BH-w/o		95.71 162	95.38 159	96.68 195	98.49 156	92.28 256	99.84 125	97.50 257	92.12 214	92.06 240	98.79 182	84.69 235	98.67 199	95.29 178	99.66 86	99.09 193

mvs_anonymous		95.65 166	95.03 171	97.53 163	98.19 176	95.74 156	99.33 228	97.49 258	90.87 253	90.47 255	97.10 251	88.23 199	97.16 288	95.92 169	97.66 163	99.68 111

DP-MVS		94.54 192	93.42 211	97.91 141	99.46 94	94.04 211	98.93 274	97.48 259	81.15 366	90.04 260	99.55 108	87.02 212	99.95 69	88.97 284	98.11 153	99.73 105

ACMH	89.72 17	90.64 284	89.63 287	93.66 299	95.64 294	88.64 326	98.55 305	97.45 260	89.03 282	81.62 354	97.61 237	69.75 346	98.41 214	89.37 280	87.62 283	93.92 317
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVG-ACMP-BASELINE		91.22 273	90.75 264	92.63 320	93.73 324	85.61 347	98.52 309	97.44 261	92.77 185	89.90 264	96.85 263	66.64 359	98.39 218	92.29 237	88.61 264	93.89 319

mvs_tets		91.81 259	91.08 261	94.00 284	91.63 362	90.58 295	98.67 301	97.43 262	92.43 205	87.37 316	97.05 255	71.76 336	97.32 279	94.75 192	88.68 263	94.11 300

LTVRE_ROB	88.28 18	90.29 294	89.05 301	94.02 282	95.08 302	90.15 305	97.19 345	97.43 262	84.91 346	83.99 343	97.06 254	74.00 330	98.28 233	84.08 329	87.71 281	93.62 333
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
jajsoiax		91.92 257	91.18 260	94.15 276	91.35 365	90.95 287	99.00 267	97.42 264	92.61 194	87.38 315	97.08 252	72.46 334	97.36 273	94.53 198	88.77 261	94.13 299

K. test v3		88.05 319	87.24 321	90.47 338	91.82 360	82.23 366	98.96 271	97.42 264	89.05 281	76.93 375	95.60 299	68.49 351	95.42 353	85.87 321	81.01 333	93.75 327

FMVSNet2		91.02 275	89.56 289	95.41 229	97.53 218	95.74 156	98.98 268	97.41 266	87.05 317	88.43 300	95.00 329	71.34 339	96.24 337	85.12 324	85.21 299	94.25 284

jason		97.24 100	96.86 105	98.38 116	95.73 287	97.32 97	99.97 27	97.40 267	95.34 92	98.60 113	99.54 110	87.70 202	98.56 203	97.94 120	99.47 104	99.25 182
jason: jason.
PS-MVSNAJss		93.64 219	93.31 216	94.61 256	92.11 355	92.19 258	99.12 248	97.38 268	92.51 203	88.45 297	96.99 258	91.20 155	97.29 283	94.36 200	87.71 281	94.36 275

MSDG		94.37 199	93.36 215	97.40 171	98.88 132	93.95 215	99.37 224	97.38 268	85.75 336	90.80 252	99.17 142	84.11 242	99.88 102	86.35 315	98.43 142	98.36 224

CL-MVSNet_self_test		84.50 338	83.15 341	88.53 354	86.00 385	81.79 369	98.82 287	97.35 270	85.12 342	83.62 346	90.91 372	76.66 305	91.40 385	69.53 381	60.36 394	92.40 356

canonicalmvs		97.09 108	96.32 124	99.39 40	98.93 123	98.95 27	99.72 166	97.35 270	94.45 115	97.88 140	99.42 118	86.71 215	99.52 151	98.48 95	93.97 233	99.72 107

UnsupCasMVSNet_bld		79.97 354	77.03 359	88.78 351	85.62 386	81.98 367	93.66 380	97.35 270	75.51 383	70.79 386	83.05 392	48.70 390	94.91 361	78.31 362	60.29 395	89.46 382

MVS-HIRNet		86.22 327	83.19 340	95.31 233	96.71 262	90.29 301	92.12 385	97.33 273	62.85 392	86.82 320	70.37 397	69.37 347	97.49 270	75.12 372	97.99 158	98.15 227

BH-untuned		95.18 174	94.83 176	96.22 210	98.36 162	91.22 282	99.80 141	97.32 274	90.91 252	91.08 248	98.67 189	83.51 244	98.54 205	94.23 204	99.61 93	98.92 202

PCF-MVS	94.20 5	95.18 174	94.10 191	98.43 112	98.55 150	95.99 148	97.91 334	97.31 275	90.35 265	89.48 276	99.22 138	85.19 230	99.89 96	90.40 271	98.47 141	99.41 162
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_fmvsmconf0.01_n		96.39 140	95.74 149	98.32 118	91.47 364	95.56 166	99.84 125	97.30 276	97.74 18	97.89 139	99.35 127	79.62 279	99.85 108	99.25 54	99.24 119	99.55 139

test_vis1_n_1920		95.44 170	95.31 161	95.82 219	98.50 155	88.74 322	99.98 14	97.30 276	97.84 16	99.85 9	99.19 140	66.82 358	99.97 53	98.82 77	99.46 106	98.76 211

miper_enhance_ethall		94.36 201	93.98 194	95.49 224	98.68 142	95.24 179	99.73 163	97.29 278	93.28 167	89.86 265	95.97 289	94.37 76	97.05 297	92.20 238	84.45 305	94.19 288

casdiffmvs_mvg		96.43 137	95.94 141	97.89 143	97.44 223	95.47 168	99.86 117	97.29 278	93.35 163	96.03 185	99.19 140	85.39 228	98.72 194	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
MVSFormer		96.94 114	96.60 116	97.95 136	97.28 235	97.70 81	99.55 198	97.27 280	91.17 244	99.43 66	99.54 110	90.92 163	96.89 309	94.67 195	99.62 89	99.25 182

test_djsdf		92.83 238	92.29 239	94.47 266	91.90 358	92.46 253	99.55 198	97.27 280	91.17 244	89.96 261	96.07 288	81.10 263	96.89 309	94.67 195	88.91 257	94.05 305

test_cas_vis1_n_1920		96.59 132	96.23 126	97.65 156	98.22 173	94.23 206	99.99 4	97.25 282	97.77 17	99.58 53	99.08 146	77.10 298	99.97 53	97.64 134	99.45 107	98.74 213

GA-MVS		93.83 210	92.84 224	96.80 190	95.73 287	93.57 224	99.88 101	97.24 283	92.57 198	92.92 226	96.66 268	78.73 289	97.67 265	87.75 299	94.06 232	99.17 186

Effi-MVS+		96.30 145	95.69 151	98.16 124	97.85 195	96.26 135	97.41 341	97.21 284	90.37 264	98.65 110	98.58 200	86.61 217	98.70 196	97.11 146	97.37 170	99.52 147

Patchmatch-test		92.65 245	91.50 255	96.10 213	96.85 253	90.49 297	91.50 388	97.19 285	82.76 360	90.23 257	95.59 300	95.02 56	98.00 250	77.41 365	96.98 180	99.82 92

diffmvs		97.00 112	96.64 114	98.09 130	97.64 213	96.17 143	99.81 137	97.19 285	94.67 111	98.95 91	99.28 129	86.43 218	98.76 190	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
ACMH+	89.98 16	90.35 291	89.54 290	92.78 319	95.99 275	86.12 345	98.81 288	97.18 287	89.38 277	83.14 347	97.76 235	68.42 352	98.43 212	89.11 283	86.05 292	93.78 326

anonymousdsp		91.79 264	90.92 263	94.41 271	90.76 370	92.93 241	98.93 274	97.17 288	89.08 280	87.46 314	95.30 317	78.43 294	96.92 308	92.38 236	88.73 262	93.39 338

baseline		96.43 137	95.98 134	97.76 151	97.34 229	95.17 184	99.51 204	97.17 288	93.92 147	96.90 163	99.28 129	85.37 229	98.64 200	97.50 137	96.86 183	99.46 155

nrg030		93.51 222	92.53 235	96.45 201	94.36 313	97.20 100	99.81 137	97.16 290	91.60 229	89.86 265	97.46 240	86.37 219	97.68 264	95.88 170	80.31 339	94.46 264

CS-MVS-test		97.88 67	97.94 63	97.70 154	99.28 100	95.20 182	99.98 14	97.15 291	95.53 87	99.62 46	99.79 55	92.08 144	98.38 222	98.75 82	99.28 117	99.52 147

MVS_Test		96.46 136	95.74 149	98.61 94	98.18 177	97.23 99	99.31 231	97.15 291	91.07 249	98.84 96	97.05 255	88.17 200	98.97 178	94.39 199	97.50 165	99.61 127

MIMVSNet		90.30 293	88.67 307	95.17 238	96.45 265	91.64 276	92.39 384	97.15 291	85.99 331	90.50 254	93.19 359	66.95 357	94.86 362	82.01 344	93.43 236	99.01 200

KD-MVS_2432*1600		88.00 320	86.10 324	93.70 297	96.91 248	94.04 211	97.17 346	97.12 294	84.93 344	81.96 351	92.41 363	92.48 133	94.51 365	79.23 356	52.68 397	92.56 352

miper_refine_blended		88.00 320	86.10 324	93.70 297	96.91 248	94.04 211	97.17 346	97.12 294	84.93 344	81.96 351	92.41 363	92.48 133	94.51 365	79.23 356	52.68 397	92.56 352

CS-MVS		97.79 76	97.91 65	97.43 169	99.10 109	94.42 199	99.99 4	97.10 296	95.07 96	99.68 37	99.75 69	92.95 118	98.34 226	98.38 98	99.14 123	99.54 143

v7n		89.65 307	88.29 312	93.72 294	92.22 353	90.56 296	99.07 257	97.10 296	85.42 341	86.73 321	94.72 335	80.06 276	97.13 291	81.14 348	78.12 351	93.49 335

casdiffmvs		96.42 139	95.97 137	97.77 149	97.30 233	94.98 186	99.84 125	97.09 298	93.75 153	96.58 172	99.26 135	85.07 231	98.78 188	97.77 131	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
Fast-Effi-MVS+		95.02 178	94.19 189	97.52 164	97.88 192	94.55 196	99.97 27	97.08 299	88.85 292	94.47 208	97.96 229	84.59 236	98.41 214	89.84 278	97.10 174	99.59 130

miper_ehance_all_eth		93.16 229	92.60 231	94.82 250	97.57 216	93.56 225	99.50 206	97.07 300	88.75 293	88.85 292	95.52 304	90.97 162	96.74 316	90.77 262	84.45 305	94.17 289

Effi-MVS+-dtu		94.53 194	95.30 162	92.22 323	97.77 200	82.54 363	99.59 190	97.06 301	94.92 101	95.29 199	95.37 314	85.81 223	97.89 257	94.80 190	97.07 175	96.23 252

EC-MVSNet		97.38 96	97.24 89	97.80 144	97.41 224	95.64 163	99.99 4	97.06 301	94.59 112	99.63 43	99.32 128	89.20 191	98.14 242	98.76 81	99.23 120	99.62 124

IterMVS		90.91 277	90.17 279	93.12 311	96.78 259	90.42 300	98.89 277	97.05 303	89.03 282	86.49 326	95.42 309	76.59 306	95.02 358	87.22 306	84.09 308	93.93 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
iter_conf_final		96.01 153	95.93 142	96.28 208	98.38 160	97.03 108	99.87 104	97.03 304	94.05 140	92.61 231	97.98 227	98.01 5	97.34 275	97.02 149	88.39 270	94.47 263

v1192		90.62 286	89.25 296	94.72 253	93.13 335	93.07 236	99.50 206	97.02 305	86.33 328	89.56 275	95.01 327	79.22 283	97.09 296	82.34 342	81.16 328	94.01 308

v2v482		91.30 268	90.07 282	95.01 241	93.13 335	93.79 217	99.77 147	97.02 305	88.05 305	89.25 281	95.37 314	80.73 268	97.15 289	87.28 305	80.04 342	94.09 302

V42		91.28 270	90.12 281	94.74 251	93.42 331	93.46 228	99.68 175	97.02 305	87.36 313	89.85 267	95.05 325	81.31 262	97.34 275	87.34 304	80.07 341	93.40 337

IterMVS-SCA-FT		90.85 280	90.16 280	92.93 316	96.72 261	89.96 309	98.89 277	96.99 308	88.95 288	86.63 323	95.67 296	76.48 308	95.00 359	87.04 309	84.04 311	93.84 323

v144192		90.79 281	89.52 291	94.59 258	93.11 338	92.77 242	99.56 196	96.99 308	86.38 327	89.82 268	94.95 332	80.50 273	97.10 294	83.98 331	80.41 337	93.90 318

v1921920		90.46 288	89.12 298	94.50 264	92.96 343	92.46 253	99.49 208	96.98 310	86.10 330	89.61 274	95.30 317	78.55 292	97.03 302	82.17 343	80.89 335	94.01 308

v1144		91.09 274	89.83 283	94.87 246	93.25 334	93.69 222	99.62 187	96.98 310	86.83 323	89.64 273	94.99 330	80.94 265	97.05 297	85.08 325	81.16 328	93.87 321

eth_miper_zixun_eth		92.41 249	91.93 246	93.84 291	97.28 235	90.68 292	98.83 286	96.97 312	88.57 298	89.19 286	95.73 295	89.24 190	96.69 319	89.97 277	81.55 324	94.15 295

dcpmvs_2		97.42 93	98.09 54	95.42 228	99.58 85	87.24 339	99.23 241	96.95 313	94.28 127	98.93 93	99.73 78	94.39 75	99.16 173	99.89 16	99.82 76	99.86 89

GBi-Net		90.88 278	89.82 284	94.08 279	97.53 218	91.97 261	98.43 312	96.95 313	87.05 317	89.68 269	94.72 335	71.34 339	96.11 340	87.01 311	85.65 294	94.17 289

test1		90.88 278	89.82 284	94.08 279	97.53 218	91.97 261	98.43 312	96.95 313	87.05 317	89.68 269	94.72 335	71.34 339	96.11 340	87.01 311	85.65 294	94.17 289

FMVSNet1		88.50 316	86.64 322	94.08 279	95.62 296	91.97 261	98.43 312	96.95 313	83.00 357	86.08 333	94.72 335	59.09 379	96.11 340	81.82 346	84.07 309	94.17 289

v8		90.54 287	89.17 297	94.66 254	93.43 330	93.40 232	99.20 243	96.94 317	85.76 334	87.56 311	94.51 342	81.96 254	97.19 287	84.94 326	78.25 349	93.38 339

c3_l		92.53 246	91.87 248	94.52 262	97.40 225	92.99 240	99.40 217	96.93 318	87.86 307	88.69 295	95.44 308	89.95 178	96.44 328	90.45 268	80.69 336	94.14 298

v1240		90.20 296	88.79 305	94.44 268	93.05 341	92.27 257	99.38 222	96.92 319	85.89 332	89.36 278	94.87 334	77.89 296	97.03 302	80.66 350	81.08 331	94.01 308

tpm		93.70 218	93.41 213	94.58 259	95.36 299	87.41 338	97.01 350	96.90 320	90.85 254	96.72 169	94.14 349	90.40 173	96.84 312	90.75 263	88.54 267	99.51 149

v148		90.70 282	89.63 287	93.92 287	92.97 342	90.97 284	99.75 155	96.89 321	87.51 310	88.27 303	95.01 327	81.67 255	97.04 299	87.40 303	77.17 360	93.75 327

IterMVS-LS		92.69 243	92.11 241	94.43 270	96.80 256	92.74 244	99.45 214	96.89 321	88.98 285	89.65 272	95.38 313	88.77 195	96.34 332	90.98 257	82.04 321	94.22 285
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v10		90.25 295	88.82 304	94.57 260	93.53 328	93.43 230	99.08 253	96.87 323	85.00 343	87.34 317	94.51 342	80.93 266	97.02 304	82.85 338	79.23 344	93.26 341

iter_conf05		96.07 150	95.95 140	96.44 203	98.43 158	97.52 87	99.91 83	96.85 324	94.16 131	92.49 235	97.98 227	98.20 4	97.34 275	97.26 142	88.29 271	94.45 269

ADS-MVSNet2		93.80 213	93.88 198	93.55 301	97.87 193	85.94 346	94.24 375	96.84 325	90.07 269	96.43 176	94.48 344	90.29 175	95.37 354	87.44 301	97.23 171	99.36 167

Fast-Effi-MVS+-dtu		93.72 217	93.86 199	93.29 306	97.06 240	86.16 344	99.80 141	96.83 326	92.66 191	92.58 232	97.83 233	81.39 259	97.67 265	89.75 279	96.87 182	96.05 255

pmmvs4		92.10 255	91.07 262	95.18 237	92.82 346	94.96 187	99.48 210	96.83 326	87.45 312	88.66 296	96.56 274	83.78 243	96.83 313	89.29 281	84.77 303	93.75 327

AllTest		92.48 247	91.64 250	95.00 242	99.01 114	88.43 328	98.94 273	96.82 328	86.50 325	88.71 293	98.47 210	74.73 325	99.88 102	85.39 322	96.18 192	96.71 246

TestCases				95.00 242	99.01 114	88.43 328		96.82 328	86.50 325	88.71 293	98.47 210	74.73 325	99.88 102	85.39 322	96.18 192	96.71 246

miper_lstm_enhance		91.81 259	91.39 258	93.06 314	97.34 229	89.18 319	99.38 222	96.79 330	86.70 324	87.47 313	95.22 322	90.00 177	95.86 349	88.26 292	81.37 326	94.15 295

cl____		92.31 251	91.58 252	94.52 262	97.33 231	92.77 242	99.57 194	96.78 331	86.97 321	87.56 311	95.51 305	89.43 184	96.62 321	88.60 287	82.44 318	94.16 294

DIV-MVS_self_test		92.32 250	91.60 251	94.47 266	97.31 232	92.74 244	99.58 192	96.75 332	86.99 320	87.64 309	95.54 302	89.55 183	96.50 325	88.58 288	82.44 318	94.17 289

ppachtmachnet_test		89.58 308	88.35 311	93.25 309	92.40 351	90.44 299	99.33 228	96.73 333	85.49 339	85.90 335	95.77 292	81.09 264	96.00 347	76.00 371	82.49 317	93.30 340

GeoE		94.36 201	93.48 209	96.99 185	97.29 234	93.54 226	99.96 34	96.72 334	88.35 302	93.43 219	98.94 168	82.05 252	98.05 248	88.12 296	96.48 189	99.37 166

COLMAP_ROB	90.47 14	92.18 254	91.49 256	94.25 275	99.00 116	88.04 334	98.42 315	96.70 335	82.30 362	88.43 300	99.01 152	76.97 301	99.85 108	86.11 318	96.50 187	94.86 257
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
1112_ss		96.01 153	95.20 165	98.42 113	97.80 198	96.41 128	99.65 180	96.66 336	92.71 187	92.88 228	99.40 121	92.16 141	99.30 163	91.92 243	93.66 234	99.55 139

test_fmvs1		95.35 172	95.68 153	94.36 272	98.99 117	84.98 352	99.96 34	96.65 337	97.60 22	99.73 32	98.96 161	71.58 338	99.93 85	98.31 102	99.37 113	98.17 226

Test_1112_low_res		95.72 160	94.83 176	98.42 113	97.79 199	96.41 128	99.65 180	96.65 337	92.70 188	92.86 229	96.13 285	92.15 142	99.30 163	91.88 244	93.64 235	99.55 139

RPSCF		91.80 262	92.79 227	88.83 350	98.15 179	69.87 388	98.11 328	96.60 339	83.93 351	94.33 210	99.27 132	79.60 280	99.46 161	91.99 241	93.16 240	97.18 244

test_fmvs1_n		94.25 204	94.36 184	93.92 287	97.68 210	83.70 358	99.90 90	96.57 340	97.40 28	99.67 38	98.88 172	61.82 374	99.92 88	98.23 104	99.13 124	98.14 229

YYNet1		85.50 332	83.33 338	92.00 325	90.89 369	88.38 331	99.22 242	96.55 341	79.60 373	57.26 396	92.72 360	79.09 287	93.78 372	77.25 366	77.37 358	93.84 323

MDA-MVSNet_test_wron		85.51 331	83.32 339	92.10 324	90.96 368	88.58 327	99.20 243	96.52 342	79.70 372	57.12 397	92.69 361	79.11 285	93.86 371	77.10 367	77.46 357	93.86 322

MTMP							99.87 104	96.49 343

pm-mvs1		89.36 311	87.81 317	94.01 283	93.40 332	91.93 264	98.62 304	96.48 344	86.25 329	83.86 344	96.14 284	73.68 331	97.04 299	86.16 317	75.73 367	93.04 346

mvsmamba		94.10 205	93.72 201	95.25 235	93.57 326	94.13 209	99.67 177	96.45 345	93.63 157	91.34 246	97.77 234	86.29 220	97.22 286	96.65 160	88.10 275	94.40 271

KD-MVS_self_test		83.59 344	82.06 344	88.20 356	86.93 383	80.70 376	97.21 344	96.38 346	82.87 358	82.49 349	88.97 378	67.63 355	92.32 382	73.75 374	62.30 393	91.58 364

test_vis1_n		93.61 220	93.03 221	95.35 230	95.86 279	86.94 341	99.87 104	96.36 347	96.85 46	99.54 56	98.79 182	52.41 387	99.83 118	98.64 89	98.97 129	99.29 178

our_test_3		90.39 289	89.48 294	93.12 311	92.40 351	89.57 315	99.33 228	96.35 348	87.84 308	85.30 337	94.99 330	84.14 241	96.09 343	80.38 351	84.56 304	93.71 332

CR-MVSNet		93.45 225	92.62 230	95.94 215	96.29 266	92.66 248	92.01 386	96.23 349	92.62 193	96.94 161	93.31 357	91.04 160	96.03 345	79.23 356	95.96 197	99.13 191

Patchmtry		89.70 306	88.49 309	93.33 305	96.24 269	89.94 312	91.37 389	96.23 349	78.22 375	87.69 308	93.31 357	91.04 160	96.03 345	80.18 354	82.10 320	94.02 306

MVP-Stereo		90.93 276	90.45 271	92.37 322	91.25 367	88.76 321	98.05 331	96.17 351	87.27 315	84.04 342	95.30 317	78.46 293	97.27 285	83.78 333	99.70 84	91.09 366
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pmmvs6		85.69 328	83.84 335	91.26 332	90.00 376	84.41 355	97.82 336	96.15 352	75.86 380	81.29 356	95.39 312	61.21 376	96.87 311	83.52 336	73.29 370	92.50 354

EG-PatchMatch MVS		85.35 333	83.81 336	89.99 343	90.39 372	81.89 368	98.21 325	96.09 353	81.78 364	74.73 381	93.72 353	51.56 389	97.12 293	79.16 359	88.61 264	90.96 368

DeepMVS_CX				82.92 367	95.98 277	58.66 398		96.01 354	92.72 186	78.34 369	95.51 305	58.29 380	98.08 245	82.57 339	85.29 297	92.03 360

test20.03		84.72 337	83.99 332	86.91 359	88.19 382	80.62 377	98.88 279	95.94 355	88.36 301	78.87 365	94.62 340	68.75 349	89.11 390	66.52 387	75.82 365	91.00 367

MDA-MVSNet-bldmvs		84.09 340	81.52 347	91.81 328	91.32 366	88.00 335	98.67 301	95.92 356	80.22 370	55.60 398	93.32 356	68.29 353	93.60 374	73.76 373	76.61 364	93.82 325

lessismore_v0				90.53 336	90.58 371	80.90 375		95.80 357		77.01 374	95.84 290	66.15 361	96.95 305	83.03 337	75.05 368	93.74 330

Anonymous20240521		85.15 334	83.81 336	89.16 348	88.32 380	82.69 361	98.80 290	95.74 358	79.72 371	81.53 355	90.99 370	65.38 364	94.16 367	72.69 375	81.11 330	90.63 371

ITE_SJBPF				92.38 321	95.69 292	85.14 350		95.71 359	92.81 182	89.33 280	98.11 220	70.23 345	98.42 213	85.91 320	88.16 274	93.59 334

FMVSNet5		88.32 317	87.47 319	90.88 333	96.90 251	88.39 330	97.28 343	95.68 360	82.60 361	84.67 340	92.40 365	79.83 278	91.16 386	76.39 370	81.51 325	93.09 344

testgi		89.01 314	88.04 315	91.90 327	93.49 329	84.89 353	99.73 163	95.66 361	93.89 150	85.14 338	98.17 218	59.68 378	94.66 364	77.73 364	88.88 258	96.16 254

new_pmnet		84.49 339	82.92 342	89.21 347	90.03 375	82.60 362	96.89 354	95.62 362	80.59 368	75.77 380	89.17 377	65.04 366	94.79 363	72.12 377	81.02 332	90.23 373

pmmvs5		90.17 298	89.09 299	93.40 303	92.10 356	89.77 313	99.74 158	95.58 363	85.88 333	87.24 318	95.74 293	73.41 332	96.48 326	88.54 289	83.56 312	93.95 314

USDC		90.00 301	88.96 302	93.10 313	94.81 306	88.16 332	98.71 296	95.54 364	93.66 155	83.75 345	97.20 248	65.58 362	98.31 229	83.96 332	87.49 285	92.85 349

test_method		80.79 349	79.70 353	84.08 364	92.83 345	67.06 390	99.51 204	95.42 365	54.34 396	81.07 358	93.53 354	44.48 392	92.22 383	78.90 360	77.23 359	92.94 347

bld_raw_dy_0_64		92.74 240	92.03 244	94.87 246	93.09 339	93.46 228	99.12 248	95.41 366	92.84 181	90.44 256	97.54 238	78.08 295	97.04 299	93.94 207	87.77 280	94.11 300

MIMVSNet1		82.58 345	80.51 351	88.78 351	86.68 384	84.20 356	96.65 356	95.41 366	78.75 374	78.59 368	92.44 362	51.88 388	89.76 389	65.26 390	78.95 345	92.38 357

OurMVSNet-221017-0		89.81 304	89.48 294	90.83 335	91.64 361	81.21 372	98.17 326	95.38 368	91.48 234	85.65 336	97.31 245	72.66 333	97.29 283	88.15 294	84.83 302	93.97 313

Anonymous20231206		86.32 326	85.42 329	89.02 349	89.11 379	80.53 378	99.05 262	95.28 369	85.43 340	82.82 348	93.92 350	74.40 327	93.44 375	66.99 385	81.83 323	93.08 345

new-patchmatchnet		81.19 347	79.34 354	86.76 360	82.86 391	80.36 379	97.92 333	95.27 370	82.09 363	72.02 384	86.87 386	62.81 372	90.74 388	71.10 378	63.08 391	89.19 384

OpenMVS_ROB	79.82 20	83.77 343	81.68 346	90.03 342	88.30 381	82.82 360	98.46 310	95.22 371	73.92 387	76.00 378	91.29 369	55.00 383	96.94 306	68.40 383	88.51 268	90.34 372

test_0402		85.58 329	83.94 334	90.50 337	93.81 323	85.04 351	98.55 305	95.20 372	76.01 379	79.72 364	95.13 323	64.15 368	96.26 336	66.04 389	86.88 288	90.21 374

SixPastTwentyTwo		88.73 315	88.01 316	90.88 333	91.85 359	82.24 365	98.22 324	95.18 373	88.97 286	82.26 350	96.89 260	71.75 337	96.67 320	84.00 330	82.98 313	93.72 331

Gipuma		66.95 365	65.00 365	72.79 377	91.52 363	67.96 389	66.16 400	95.15 374	47.89 398	58.54 395	67.99 400	29.74 397	87.54 394	50.20 399	77.83 353	62.87 400
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LF4IMVS		89.25 313	88.85 303	90.45 339	92.81 347	81.19 373	98.12 327	94.79 375	91.44 236	86.29 330	97.11 250	65.30 365	98.11 244	88.53 290	85.25 298	92.07 358

FPMVS		68.72 360	68.72 361	68.71 382	65.95 405	44.27 411	95.97 370	94.74 376	51.13 397	53.26 399	90.50 374	25.11 402	83.00 398	60.80 393	80.97 334	78.87 395

pmmvs-eth3d		84.03 341	81.97 345	90.20 340	84.15 388	87.09 340	98.10 329	94.73 377	83.05 356	74.10 383	87.77 384	65.56 363	94.01 368	81.08 349	69.24 378	89.49 381

test_fmvs2		89.47 309	89.70 286	88.77 353	94.54 311	75.74 382	99.83 132	94.70 378	94.71 108	91.08 248	96.82 267	54.46 384	97.78 262	92.87 232	88.27 272	92.80 350

TDRefinement		84.76 335	82.56 343	91.38 331	74.58 401	84.80 354	97.36 342	94.56 379	84.73 347	80.21 361	96.12 287	63.56 369	98.39 218	87.92 297	63.97 390	90.95 369

ambc				83.23 366	77.17 399	62.61 392	87.38 395	94.55 380		76.72 376	86.65 387	30.16 396	96.36 331	84.85 327	69.86 375	90.73 370

WB-MVS		76.28 356	77.28 358	73.29 376	81.18 393	54.68 401	97.87 335	94.19 381	81.30 365	69.43 388	90.70 373	77.02 300	82.06 399	35.71 404	68.11 383	83.13 390

TinyColmap		87.87 322	86.51 323	91.94 326	95.05 303	85.57 348	97.65 338	94.08 382	84.40 349	81.82 353	96.85 263	62.14 373	98.33 227	80.25 353	86.37 291	91.91 362

SSC-MVS		75.42 357	76.40 360	72.49 380	80.68 395	53.62 402	97.42 340	94.06 383	80.42 369	68.75 389	90.14 375	76.54 307	81.66 400	33.25 405	66.34 387	82.19 391

TransMVSNet (Re)		87.25 323	85.28 330	93.16 310	93.56 327	91.03 283	98.54 307	94.05 384	83.69 354	81.09 357	96.16 283	75.32 318	96.40 329	76.69 369	68.41 381	92.06 359

Baseline_NR-MVSNet		90.33 292	89.51 292	92.81 318	92.84 344	89.95 310	99.77 147	93.94 385	84.69 348	89.04 288	95.66 297	81.66 256	96.52 324	90.99 256	76.98 361	91.97 361

EGC-MVSNET		69.38 358	63.76 368	86.26 361	90.32 373	81.66 371	96.24 364	93.85 386	0.99 408	3.22 409	92.33 366	52.44 386	92.92 379	59.53 395	84.90 301	84.21 389

LCM-MVSNet		67.77 363	64.73 366	76.87 373	62.95 407	56.25 400	89.37 394	93.74 387	44.53 399	61.99 391	80.74 393	20.42 406	86.53 396	69.37 382	59.50 396	87.84 385

APD_test1		81.15 348	80.92 349	81.86 368	92.45 350	59.76 397	96.04 368	93.61 388	73.29 388	77.06 373	96.64 270	44.28 393	96.16 339	72.35 376	82.52 316	89.67 379

test_fmvs3		79.99 353	80.17 352	79.45 370	84.02 389	62.83 391	99.05 262	93.49 389	88.29 303	80.06 363	86.65 387	28.09 399	88.00 391	88.63 286	73.27 371	87.54 387

test_f		78.40 355	77.59 357	80.81 369	80.82 394	62.48 394	96.96 352	93.08 390	83.44 355	74.57 382	84.57 391	27.95 400	92.63 380	84.15 328	72.79 372	87.32 388

Patchmatch-RL test		86.90 324	85.98 328	89.67 344	84.45 387	75.59 383	89.71 393	92.43 391	86.89 322	77.83 372	90.94 371	94.22 81	93.63 373	87.75 299	69.61 376	99.79 97

mvsany_test3		82.12 346	81.14 348	85.06 363	81.87 392	70.41 387	97.09 348	92.14 392	91.27 243	77.84 371	88.73 379	39.31 394	95.49 351	90.75 263	71.24 373	89.29 383

pmmvs3		80.27 351	77.77 356	87.76 358	80.32 396	82.43 364	98.23 323	91.97 393	72.74 389	78.75 366	87.97 383	57.30 382	90.99 387	70.31 379	62.37 392	89.87 376

LCM-MVSNet-Re		92.31 251	92.60 231	91.43 330	97.53 218	79.27 380	99.02 266	91.83 394	92.07 215	80.31 360	94.38 347	83.50 245	95.48 352	97.22 144	97.58 164	99.54 143

PM-MVS		80.47 350	78.88 355	85.26 362	83.79 390	72.22 386	95.89 371	91.08 395	85.71 337	76.56 377	88.30 380	36.64 395	93.90 370	82.39 341	69.57 377	89.66 380

door								90.31 396

dmvs_testset		83.79 342	86.07 326	76.94 372	92.14 354	48.60 407	96.75 355	90.27 397	89.48 276	78.65 367	98.55 204	79.25 282	86.65 395	66.85 386	82.69 315	95.57 256

DSMNet-mixed		88.28 318	88.24 313	88.42 355	89.64 377	75.38 384	98.06 330	89.86 398	85.59 338	88.20 304	92.14 367	76.15 313	91.95 384	78.46 361	96.05 195	97.92 231

door-mid								89.69 399

PMVS	49.05 23	53.75 368	51.34 372	60.97 385	40.80 411	34.68 412	74.82 399	89.62 400	37.55 401	28.67 407	72.12 396	7.09 411	81.63 401	43.17 402	68.21 382	66.59 399
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		65.23 366	62.94 369	72.13 381	44.90 410	50.03 406	81.05 397	89.42 401	38.45 400	48.51 402	99.90 18	54.09 385	78.70 402	91.84 245	18.26 404	87.64 386

PMMVS2		67.15 364	64.15 367	76.14 374	70.56 404	62.07 395	93.89 378	87.52 402	58.09 393	60.02 392	78.32 394	22.38 403	84.54 397	59.56 394	47.03 399	81.80 392

testf1		68.38 361	66.92 362	72.78 378	78.80 397	50.36 404	90.95 391	87.35 403	55.47 394	58.95 393	88.14 381	20.64 404	87.60 392	57.28 396	64.69 388	80.39 393

APD_test2		68.38 361	66.92 362	72.78 378	78.80 397	50.36 404	90.95 391	87.35 403	55.47 394	58.95 393	88.14 381	20.64 404	87.60 392	57.28 396	64.69 388	80.39 393

test_vis1_rt		86.87 325	86.05 327	89.34 346	96.12 270	78.07 381	99.87 104	83.54 405	92.03 218	78.21 370	89.51 376	45.80 391	99.91 89	96.25 164	93.11 241	90.03 375

ANet_high		56.10 367	52.24 370	67.66 383	49.27 409	56.82 399	83.94 396	82.02 406	70.47 390	33.28 406	64.54 401	17.23 408	69.16 404	45.59 401	23.85 403	77.02 396

MVE	53.74 22	51.54 370	47.86 374	62.60 384	59.56 408	50.93 403	79.41 398	77.69 407	35.69 403	36.27 405	61.76 404	5.79 413	69.63 403	37.97 403	36.61 400	67.24 398
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		52.30 369	52.18 371	52.67 386	71.51 402	45.40 408	93.62 381	76.60 408	36.01 402	43.50 403	64.13 402	27.11 401	67.31 405	31.06 406	26.06 401	45.30 404

EMVS		51.44 371	51.22 373	52.11 387	70.71 403	44.97 410	94.04 377	75.66 409	35.34 404	42.40 404	61.56 405	28.93 398	65.87 406	27.64 407	24.73 402	45.49 403

test_vis3_rt		68.82 359	66.69 364	75.21 375	76.24 400	60.41 396	96.44 359	68.71 410	75.13 384	50.54 401	69.52 399	16.42 409	96.32 333	80.27 352	66.92 386	68.89 397

N_pmnet		80.06 352	80.78 350	77.89 371	91.94 357	45.28 409	98.80 290	56.82 411	78.10 376	80.08 362	93.33 355	77.03 299	95.76 350	68.14 384	82.81 314	92.64 351

testmvs		40.60 372	44.45 375	29.05 389	19.49 413	14.11 415	99.68 175	18.47 412	20.74 405	64.59 390	98.48 209	10.95 410	17.09 409	56.66 398	11.01 405	55.94 402

test123		37.68 373	39.14 376	33.31 388	19.94 412	24.83 414	98.36 317	9.75 413	15.53 406	51.31 400	87.14 385	19.62 407	17.74 408	47.10 400	3.47 407	57.36 401

wuyk23d		20.37 375	20.84 378	18.99 390	65.34 406	27.73 413	50.43 401	7.67 414	9.50 407	8.01 408	6.34 408	6.13 412	26.24 407	23.40 408	10.69 406	2.99 405

test_blank		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.02 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

pcd_1.5k_mvsjas		7.60 377	10.13 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 410	91.20 155	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

n2								0.00 415

nn								0.00 415

ab-mvs-re		8.28 376	11.04 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	99.40 121	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 410	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

WAC-MVS						90.97 284								86.10 319

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

eth-test2					0.00 414

eth-test					0.00 414

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

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 65				99.59 130

sam_mvs												94.25 80

test_post1							95.78 372				59.23 406	93.20 112	97.74 263	91.06 254

test_post											63.35 403	94.43 70	98.13 243

patchmatchnet-post											91.70 368	95.12 51	97.95 254

gm-plane-assit					96.97 245	93.76 219			91.47 235		98.96 161		98.79 187	94.92 185

test9_res														99.71 33	99.99 21	100.00 1

agg_prior2														99.48 43	100.00 1	100.00 1

test_prior4						98.05 66	99.94 68

test_prior2							99.95 52		95.78 79	99.73 32	99.76 63	96.00 34		99.78 27	100.00 1

旧先验2							99.46 213		94.21 130	99.85 9			99.95 69	96.96 154

新几何2							99.40 217

原ACMM2							99.90 90

testdata2													99.99 36	90.54 267

segment_acmp												96.68 26

testdata1							99.28 237		96.35 69

plane_prior7					95.71 290	91.59 278

plane_prior6					95.76 284	91.72 273						80.47 274

plane_prior4											98.59 197

plane_prior3						91.64 276			96.63 56	93.01 224

plane_prior2							99.84 125		96.38 65

plane_prior1					95.73 287

plane_prior						91.74 270	99.86 117		96.76 52						89.59 250

HQP5-MVS						91.85 266

HQP-NCC					95.78 280		99.87 104		96.82 48	93.37 220

ACMP_Plane					95.78 280		99.87 104		96.82 48	93.37 220

BP-MVS														97.92 121

HQP4-MVS										93.37 220			98.39 218			94.53 258

HQP2-MVS												80.65 270

NP-MVS					95.77 283	91.79 268					98.65 192

MDTV_nov1_ep13_2view						96.26 135	96.11 366		91.89 221	98.06 133		94.40 72		94.30 202		99.67 113

ACMMP++_ref															87.04 286

ACMMP++															88.23 273

Test By Simon												92.82 123

High-resolution multi-view benchmark