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 28	98.62 26	99.01 77	99.36 101	97.18 108	99.93 78	99.90 1	96.81 54	98.67 115	99.77 64	93.92 99	99.89 99	99.27 56	99.94 55	99.96 67

MVS_111021_LR		98.42 47	98.38 37	98.53 114	99.39 99	95.79 163	99.87 108	99.86 2	96.70 57	98.78 107	99.79 58	92.03 154	99.90 94	99.17 60	99.86 75	99.88 88

CHOSEN 1792x2688		96.81 130	96.53 129	97.64 168	98.91 134	93.07 246	99.65 186	99.80 3	95.64 87	95.39 211	98.86 184	84.35 253	99.90 94	96.98 164	99.16 128	99.95 74

HyFIR lowres test		96.66 141	96.43 132	97.36 187	99.05 116	93.91 227	99.70 179	99.80 3	90.54 270	96.26 194	98.08 232	92.15 151	98.23 252	96.84 170	95.46 221	99.93 79

test2506		97.53 94	97.19 100	98.58 107	98.66 150	96.90 121	98.81 301	99.77 5	94.93 103	97.95 145	98.96 168	92.51 141	99.20 177	94.93 196	98.15 160	99.64 124

MM		98.83 21	98.53 30	99.76 10	99.59 85	99.33 8	99.99 4	99.76 6	98.39 4	99.39 74	99.80 54	90.49 182	99.96 65	99.89 17	99.43 115	99.98 51

thres100view900		96.74 136	95.92 154	99.18 52	98.90 135	98.77 42	99.74 161	99.71 7	92.59 205	95.84 203	98.86 184	89.25 199	99.50 158	93.84 223	94.57 234	99.27 193

tfpn200view9		96.79 131	95.99 144	99.19 51	98.94 125	98.82 37	99.78 146	99.71 7	92.86 187	96.02 199	98.87 182	89.33 197	99.50 158	93.84 223	94.57 234	99.27 193

thres600view7		96.69 139	95.87 157	99.14 61	98.90 135	98.78 41	99.74 161	99.71 7	92.59 205	95.84 203	98.86 184	89.25 199	99.50 158	93.44 235	94.50 237	99.16 200

thres400		96.78 133	95.99 144	99.16 57	98.94 125	98.82 37	99.78 146	99.71 7	92.86 187	96.02 199	98.87 182	89.33 197	99.50 158	93.84 223	94.57 234	99.16 200

thres200		96.96 123	96.21 139	99.22 48	98.97 123	98.84 36	99.85 122	99.71 7	93.17 177	96.26 194	98.88 179	89.87 190	99.51 156	94.26 216	94.91 231	99.31 187

PVSNet	91.05 13	97.13 113	96.69 123	98.45 119	99.52 92	95.81 162	99.95 54	99.65 12	94.73 112	99.04 95	99.21 146	84.48 251	99.95 73	94.92 197	98.74 144	99.58 143

PVSNet_0	88.03 19	91.80 274	90.27 288	96.38 217	98.27 180	90.46 309	99.94 71	99.61 13	93.99 149	86.26 344	97.39 254	71.13 356	99.89 99	98.77 87	67.05 400	98.79 224

WTY-MVS		98.10 66	97.60 82	99.60 22	98.92 130	99.28 17	99.89 102	99.52 14	95.58 89	98.24 138	99.39 130	93.33 114	99.74 137	97.98 132	95.58 220	99.78 103

HY-MVS	92.50 7	97.79 84	97.17 102	99.63 17	98.98 122	99.32 9	97.49 355	99.52 14	95.69 86	98.32 133	97.41 252	93.32 115	99.77 131	98.08 126	95.75 217	99.81 97

EPNet		98.49 40	98.40 35	98.77 92	99.62 84	96.80 125	99.90 93	99.51 16	97.60 22	99.20 84	99.36 133	93.71 107	99.91 92	97.99 130	98.71 145	99.61 134
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PGM-MVS		98.34 51	98.13 55	98.99 78	99.92 31	97.00 116	99.75 158	99.50 17	93.90 156	99.37 75	99.76 66	93.24 120	100.00 1	97.75 147	99.96 46	99.98 51

ACMMP		97.74 87	97.44 89	98.66 99	99.92 31	96.13 154	99.18 256	99.45 18	94.84 109	96.41 191	99.71 86	91.40 161	99.99 36	97.99 130	98.03 167	99.87 90
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 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 190	99.44 19	97.33 31	99.00 97	99.72 84	94.03 97	99.98 47	98.73 90	100.00 1	100.00 1

EPMVS		96.53 145	96.01 143	98.09 140	98.43 167	96.12 156	96.36 376	99.43 20	93.53 165	97.64 155	95.04 341	94.41 78	98.38 236	91.13 264	98.11 163	99.75 106

CHOSEN 280x420		99.01 14	99.03 10	98.95 83	99.38 100	98.87 33	98.46 324	99.42 21	97.03 44	99.02 96	99.09 152	99.35 2	98.21 253	99.73 35	99.78 84	99.77 104

D2MVS		92.76 252	92.59 247	93.27 318	95.13 316	89.54 326	99.69 180	99.38 22	92.26 219	87.59 323	94.61 356	85.05 246	97.79 275	91.59 259	88.01 289	92.47 368

sss		97.57 93	97.03 107	99.18 52	98.37 171	98.04 71	99.73 168	99.38 22	93.46 167	98.76 111	99.06 155	91.21 163	99.89 99	96.33 174	97.01 189	99.62 130

PAPM		98.60 33	98.42 34	99.14 61	96.05 288	98.96 26	99.90 93	99.35 24	96.68 58	98.35 132	99.66 99	96.45 33	98.51 220	99.45 48	99.89 70	99.96 67

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 66	99.21 21	99.99 4	99.34 25	98.70 2	99.44 66	99.75 72	93.24 120	99.99 36	99.94 11	99.41 117	99.95 74

UGNet		95.33 184	94.57 193	97.62 171	98.55 159	94.85 200	98.67 314	99.32 26	95.75 85	96.80 180	96.27 291	72.18 349	99.96 65	94.58 209	99.05 134	98.04 244
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 77	97.37 92	99.21 49	99.18 108	97.98 74	99.64 190	99.27 27	91.43 245	97.88 149	98.99 162	95.84 42	99.84 119	98.82 83	95.32 226	99.79 100

DCV-MVSNet		97.83 77	97.37 92	99.21 49	99.18 108	97.98 74	99.64 190	99.27 27	91.43 245	97.88 149	98.99 162	95.84 42	99.84 119	98.82 83	95.32 226	99.79 100

VNet		97.21 110	96.57 128	99.13 65	98.97 123	97.82 81	99.03 275	99.21 29	94.31 133	99.18 87	98.88 179	86.26 235	99.89 99	98.93 75	94.32 238	99.69 115

testing3		93.92 221	94.23 201	92.99 326	97.54 231	90.23 313	99.99 4	99.16 30	90.57 269	91.33 259	98.63 202	92.99 126	92.52 398	82.46 354	95.39 224	96.22 269

PVSNet_BlendedMVS		96.05 162	95.82 158	96.72 206	99.59 85	96.99 117	99.95 54	99.10 31	94.06 146	98.27 135	95.80 303	89.00 204	99.95 73	99.12 61	87.53 296	93.24 355

PVSNet_Blended		97.94 69	97.64 80	98.83 88	99.59 85	96.99 117	100.00 1	99.10 31	95.38 94	98.27 135	99.08 153	89.00 204	99.95 73	99.12 61	99.25 124	99.57 145

UniMVSNet_NR-MVSNet		92.95 248	92.11 254	95.49 237	94.61 326	95.28 187	99.83 134	99.08 33	91.49 240	89.21 296	96.86 272	87.14 223	96.73 332	93.20 237	77.52 368	94.46 279

CSCG		97.10 114	97.04 106	97.27 191	99.89 45	91.92 275	99.90 93	99.07 34	88.67 307	95.26 214	99.82 49	93.17 123	99.98 47	98.15 121	99.47 110	99.90 86

PatchMatch-RL		96.04 163	95.40 168	97.95 146	99.59 85	95.22 191	99.52 210	99.07 34	93.96 151	96.49 187	98.35 222	82.28 265	99.82 123	90.15 286	99.22 127	98.81 223

VPA-MVSNet		92.70 254	91.55 266	96.16 222	95.09 317	96.20 150	98.88 292	99.00 36	91.02 259	91.82 254	95.29 333	76.05 328	97.96 268	95.62 187	81.19 339	94.30 293

SDMVSNet		94.80 195	93.96 209	97.33 189	98.92 130	95.42 181	99.59 197	98.99 37	92.41 214	92.55 247	97.85 243	75.81 329	98.93 194	97.90 136	91.62 259	97.64 252

CVMVSNet		94.68 202	94.94 186	93.89 302	96.80 271	86.92 355	99.06 268	98.98 38	94.45 121	94.23 227	99.02 157	85.60 238	95.31 372	90.91 271	95.39 224	99.43 171

UniMVSNet (Re)		93.07 246	92.13 253	95.88 229	94.84 321	96.24 149	99.88 105	98.98 38	92.49 212	89.25 293	95.40 323	87.09 224	97.14 304	93.13 241	78.16 363	94.26 295

fmvsm_s_conf0.5_n		97.80 82	97.85 73	97.67 166	99.06 115	94.41 211	99.98 15	98.97 40	97.34 29	99.63 44	99.69 90	87.27 221	99.97 57	99.62 40	99.06 133	98.62 232

h-mvs33		94.92 192	94.36 197	96.59 210	98.85 139	91.29 291	98.93 286	98.94 41	95.90 80	98.77 108	98.42 220	90.89 175	99.77 131	97.80 140	70.76 389	98.72 229

tfpnnormal		89.29 325	87.61 332	94.34 285	94.35 331	94.13 221	98.95 283	98.94 41	83.94 364	84.47 356	95.51 317	74.84 338	97.39 288	77.05 383	80.41 350	91.48 378

MVS		96.60 142	95.56 166	99.72 13	96.85 268	99.22 20	98.31 333	98.94 41	91.57 238	90.90 263	99.61 106	86.66 230	99.96 65	97.36 153	99.88 73	99.99 23

WR-MVS_H		91.30 281	90.35 285	94.15 288	94.17 334	92.62 261	99.17 257	98.94 41	88.87 302	86.48 340	94.46 361	84.36 252	96.61 337	88.19 305	78.51 361	93.21 356

FIs		94.10 219	93.43 223	96.11 223	94.70 324	96.82 123	99.58 199	98.93 45	92.54 208	89.34 291	97.31 255	87.62 217	97.10 308	94.22 218	86.58 300	94.40 285

fmvsm_s_conf0.5_n_a		97.73 89	97.72 76	97.77 160	98.63 154	94.26 217	99.96 35	98.92 46	97.18 39	99.75 29	99.69 90	87.00 226	99.97 57	99.46 47	98.89 138	99.08 209

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 150	99.27 106	95.18 193	100.00 1	98.90 47	98.05 12	99.80 17	99.73 81	92.64 136	99.99 36	99.58 41	99.51 108	98.59 233

EPNet_dtu		95.71 172	95.39 169	96.66 208	98.92 130	93.41 241	99.57 202	98.90 47	96.19 77	97.52 157	98.56 209	92.65 135	97.36 289	77.89 378	98.33 153	99.20 198
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
patch_mono-2		98.24 61	99.12 5	95.59 236	99.67 81	86.91 356	99.95 54	98.89 49	97.60 22	99.90 3	99.76 66	96.54 32	99.98 47	99.94 11	99.82 81	99.88 88

FC-MVSNet-test		93.81 225	93.15 232	95.80 233	94.30 332	96.20 150	99.42 226	98.89 49	92.33 218	89.03 301	97.27 257	87.39 220	96.83 328	93.20 237	86.48 301	94.36 287

baseline2		96.71 138	96.49 130	97.37 185	95.63 311	95.96 159	99.74 161	98.88 51	92.94 184	91.61 255	98.97 166	97.72 6	98.62 215	94.83 201	98.08 166	97.53 257

API-MVS		97.86 74	97.66 79	98.47 117	99.52 92	95.41 182	99.47 219	98.87 52	91.68 236	98.84 103	99.85 33	92.34 147	99.99 36	98.44 107	99.96 46	100.00 1

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 46	99.17 110	97.81 82	99.98 15	98.86 53	98.25 5	99.90 3	99.76 66	94.21 92	99.97 57	99.87 19	99.52 105	99.98 51

1314		96.84 129	95.96 150	99.48 34	96.74 275	98.52 58	98.31 333	98.86 53	95.82 82	89.91 274	98.98 164	87.49 218	99.96 65	97.80 140	99.73 87	99.96 67

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 15	98.86 53	97.10 40	99.80 17	99.94 4	95.92 40	100.00 1	99.51 43	100.00 1	100.00 1

reproduce_monomvs		95.38 182	95.07 181	96.32 219	99.32 104	96.60 131	99.76 154	98.85 56	96.65 59	87.83 320	96.05 300	99.52 1	98.11 258	96.58 172	81.07 344	94.25 297

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 45	99.21 107	97.91 79	99.98 15	98.85 56	98.25 5	99.92 2	99.75 72	94.72 69	99.97 57	99.87 19	99.64 92	99.95 74

sd_testset		93.55 234	92.83 237	95.74 234	98.92 130	90.89 299	98.24 337	98.85 56	92.41 214	92.55 247	97.85 243	71.07 357	98.68 212	93.93 220	91.62 259	97.64 252

AdaColmap		97.23 109	96.80 117	98.51 115	99.99 1	95.60 175	99.09 261	98.84 59	93.32 172	96.74 181	99.72 84	86.04 236	100.00 1	98.01 128	99.43 115	99.94 78

test_fmvsmconf_n		98.43 46	98.32 43	98.78 90	98.12 193	96.41 138	99.99 4	98.83 60	98.22 7	99.67 39	99.64 102	91.11 168	99.94 81	99.67 39	99.62 95	99.98 51

IB-MVS	92.85 6	94.99 191	93.94 210	98.16 134	97.72 219	95.69 171	99.99 4	98.81 61	94.28 136	92.70 245	96.90 269	95.08 56	99.17 180	96.07 178	73.88 383	99.60 136
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	96.28 158	95.34 171	99.08 70	96.82 270	97.47 98	99.45 224	98.81 61	95.52 92	89.39 289	99.00 161	81.97 267	99.95 73	97.27 155	99.83 77	99.84 93

PHI-MVS		98.41 48	98.21 48	99.03 73	99.86 53	97.10 113	99.98 15	98.80 63	90.78 266	99.62 47	99.78 62	95.30 52	100.00 1	99.80 25	99.93 61	99.99 23

MAR-MVS		97.43 97	97.19 100	98.15 137	99.47 96	94.79 204	99.05 272	98.76 64	92.65 201	98.66 116	99.82 49	88.52 209	99.98 47	98.12 122	99.63 94	99.67 118
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		92.46 260	91.45 269	95.49 237	94.05 335	95.28 187	99.81 139	98.74 65	92.25 220	89.21 296	96.64 280	81.66 271	96.73 332	93.20 237	77.52 368	94.46 279

tt0805		91.28 283	90.18 291	94.60 269	96.26 283	87.55 348	98.39 331	98.72 66	89.00 295	89.22 295	98.47 217	62.98 387	98.96 192	90.57 277	88.00 290	97.28 258

无先验							99.49 216	98.71 67	93.46 167				100.00 1	94.36 212		99.99 23

NR-MVSNet		91.56 279	90.22 289	95.60 235	94.05 335	95.76 165	98.25 336	98.70 68	91.16 254	80.78 375	96.64 280	83.23 261	96.57 338	91.41 260	77.73 367	94.46 279

FE-MVS		95.70 174	95.01 184	97.79 157	98.21 184	94.57 206	95.03 390	98.69 69	88.90 301	97.50 159	96.19 293	92.60 138	99.49 163	89.99 288	97.94 169	99.31 187

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 15	98.69 69	98.20 8	99.93 1	99.98 2	96.82 24	100.00 1	99.75 31	100.00 1	99.99 23

WR-MVS		92.31 263	91.25 271	95.48 240	94.45 329	95.29 186	99.60 196	98.68 71	90.10 278	88.07 317	96.89 270	80.68 284	96.80 330	93.14 240	79.67 356	94.36 287

ab-mvs		94.69 200	93.42 224	98.51 115	98.07 194	96.26 145	96.49 374	98.68 71	90.31 276	94.54 219	97.00 267	76.30 324	99.71 141	95.98 180	93.38 252	99.56 146

QAPM		95.40 181	94.17 203	99.10 67	96.92 262	97.71 85	99.40 227	98.68 71	89.31 289	88.94 302	98.89 178	82.48 264	99.96 65	93.12 242	99.83 77	99.62 130

Anonymous20240529		92.10 267	90.65 279	96.47 211	98.82 140	90.61 305	98.72 308	98.67 74	75.54 398	93.90 231	98.58 207	66.23 375	99.90 94	94.70 206	90.67 262	98.90 219

test_prior				99.43 35	99.94 13	98.49 60		98.65 75					99.80 124			99.99 23

TranMVSNet+NR-MVSNet		91.68 278	90.61 281	94.87 258	93.69 342	93.98 225	99.69 180	98.65 75	91.03 258	88.44 310	96.83 276	80.05 292	96.18 353	90.26 285	76.89 376	94.45 284

fmvsm_s_conf0.1_n		97.30 105	97.21 99	97.60 172	97.38 241	94.40 213	99.90 93	98.64 77	96.47 65	99.51 62	99.65 101	84.99 247	99.93 88	99.22 58	99.09 132	98.46 234

旧先验1					99.76 66	97.52 93		98.64 77			99.85 33	95.63 45			99.94 55	99.99 23

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 28	98.64 77	98.47 3	99.13 89	99.92 13	96.38 34	100.00 1	99.74 33	100.00 1	100.00 1

PVSNet_Blended_VisFu		97.27 107	96.81 116	98.66 99	98.81 141	96.67 128	99.92 81	98.64 77	94.51 120	96.38 192	98.49 213	89.05 203	99.88 105	97.10 160	98.34 152	99.43 171

新几何1				99.42 37	99.75 69	98.27 64		98.63 81	92.69 198	99.55 55	99.82 49	94.40 79	100.00 1	91.21 262	99.94 55	99.99 23

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 28	98.62 82	98.02 13	99.90 3	99.95 3	97.33 17	100.00 1	99.54 42	100.00 1	100.00 1

testing222		97.08 119	96.75 119	98.06 142	98.56 156	96.82 123	99.85 122	98.61 83	92.53 209	98.84 103	98.84 188	93.36 112	98.30 244	95.84 183	94.30 239	99.05 211

HFP-MVS		98.56 35	98.37 39	99.14 61	99.96 8	97.43 99	99.95 54	98.61 83	94.77 110	99.31 78	99.85 33	94.22 90	100.00 1	98.70 91	99.98 32	99.98 51

UWE-MVS		96.79 131	96.72 121	97.00 196	98.51 163	93.70 232	99.71 175	98.60 85	92.96 183	97.09 170	98.34 224	96.67 31	98.85 197	92.11 252	96.50 197	98.44 235

ACMMPR		98.50 39	98.32 43	99.05 71	99.96 8	97.18 108	99.95 54	98.60 85	94.77 110	99.31 78	99.84 44	93.73 106	100.00 1	98.70 91	99.98 32	99.98 51

VPNet		91.81 271	90.46 282	95.85 231	94.74 323	95.54 177	98.98 279	98.59 87	92.14 221	90.77 265	97.44 251	68.73 364	97.54 285	94.89 200	77.89 365	94.46 279

test0.0.03 1		93.86 222	93.61 215	94.64 267	95.02 320	92.18 269	99.93 78	98.58 88	94.07 144	87.96 318	98.50 212	93.90 101	94.96 376	81.33 361	93.17 253	96.78 261

DELS-MVS		98.54 36	98.22 47	99.50 30	99.15 112	98.65 53	100.00 1	98.58 88	97.70 20	98.21 139	99.24 144	92.58 139	99.94 81	98.63 98	99.94 55	99.92 84
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		97.03 120	96.64 124	98.20 133	98.67 149	97.12 112	99.89 102	98.57 90	91.10 256	98.17 140	98.59 204	93.86 103	98.19 254	95.64 186	95.24 228	99.28 192

CP-MVSNet		91.23 285	90.22 289	94.26 286	93.96 337	92.39 265	99.09 261	98.57 90	88.95 299	86.42 341	96.57 283	79.19 299	96.37 345	90.29 284	78.95 358	94.02 319

OpenMVS	90.15 15	94.77 198	93.59 218	98.33 126	96.07 287	97.48 97	99.56 204	98.57 90	90.46 271	86.51 338	98.95 173	78.57 306	99.94 81	93.86 222	99.74 86	97.57 256

hse-mvs2		94.38 212	94.08 205	95.31 246	98.27 180	90.02 318	99.29 246	98.56 93	95.90 80	98.77 108	98.00 235	90.89 175	98.26 251	97.80 140	69.20 395	97.64 252

AUN-MVS		93.28 239	92.60 243	95.34 244	98.29 177	90.09 317	99.31 241	98.56 93	91.80 234	96.35 193	98.00 235	89.38 196	98.28 247	92.46 247	69.22 394	97.64 252

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 54	98.56 93	97.56 25	99.44 66	99.85 33	95.38 51	100.00 1	99.31 54	99.99 21	99.87 90

testdata				98.42 122	99.47 96	95.33 185		98.56 93	93.78 159	99.79 25	99.85 33	93.64 109	99.94 81	94.97 195	99.94 55	100.00 1

EPP-MVSNet		96.69 139	96.60 126	96.96 198	97.74 214	93.05 248	99.37 234	98.56 93	88.75 305	95.83 205	99.01 159	96.01 36	98.56 217	96.92 168	97.20 183	99.25 195

DeepPCF-MVS	95.94 2	97.71 90	98.98 12	93.92 299	99.63 83	81.76 386	99.96 35	98.56 93	99.47 1	99.19 86	99.99 1	94.16 94	100.00 1	99.92 13	99.93 61	100.00 1

region2R		98.54 36	98.37 39	99.05 71	99.96 8	97.18 108	99.96 35	98.55 99	94.87 108	99.45 65	99.85 33	94.07 96	100.00 1	98.67 93	100.00 1	99.98 51

test222					99.55 90	97.41 101	99.34 237	98.55 99	91.86 230	99.27 82	99.83 46	93.84 104			99.95 50	99.99 23

tpmvs		94.28 217	93.57 219	96.40 215	98.55 159	91.50 289	95.70 389	98.55 99	87.47 324	92.15 250	94.26 364	91.42 160	98.95 193	88.15 306	95.85 213	98.76 225

thisisatest0530		97.10 114	96.72 121	98.22 132	97.60 228	96.70 126	99.92 81	98.54 102	91.11 255	97.07 172	98.97 166	97.47 12	99.03 188	93.73 231	96.09 205	98.92 216

tttt0517		96.85 128	96.49 130	97.92 150	97.48 236	95.89 161	99.85 122	98.54 102	90.72 268	96.63 183	98.93 177	97.47 12	99.02 189	93.03 243	95.76 216	98.85 220

thisisatest0515		97.41 102	97.02 108	98.59 106	97.71 221	97.52 93	99.97 28	98.54 102	91.83 231	97.45 160	99.04 156	97.50 9	99.10 185	94.75 204	96.37 201	99.16 200

kuosan		93.17 242	92.60 243	94.86 261	98.40 168	89.54 326	98.44 326	98.53 105	84.46 362	88.49 308	97.92 240	90.57 179	97.05 311	83.10 350	93.49 249	97.99 245

UBG		97.84 76	97.69 78	98.29 129	98.38 169	96.59 133	99.90 93	98.53 105	93.91 155	98.52 121	98.42 220	96.77 25	99.17 180	98.54 101	96.20 202	99.11 206

ZD-MVS					99.92 31	98.57 56		98.52 107	92.34 217	99.31 78	99.83 46	95.06 57	99.80 124	99.70 37	99.97 42

GG-mvs-BLEND				98.54 112	98.21 184	98.01 72	93.87 395	98.52 107		97.92 146	97.92 240	99.02 3	97.94 271	98.17 119	99.58 102	99.67 118

PS-CasMVS		90.63 298	89.51 305	93.99 297	93.83 339	91.70 284	98.98 279	98.52 107	88.48 311	86.15 345	96.53 285	75.46 331	96.31 349	88.83 297	78.86 360	93.95 327

dongtai		91.55 280	91.13 273	92.82 329	98.16 189	86.35 357	99.47 219	98.51 110	83.24 370	85.07 353	97.56 248	90.33 184	94.94 377	76.09 386	91.73 257	97.18 259

dmvs_re		93.20 241	93.15 232	93.34 315	96.54 279	83.81 372	98.71 309	98.51 110	91.39 249	92.37 249	98.56 209	78.66 305	97.83 274	93.89 221	89.74 263	98.38 237

CANet		98.27 56	97.82 74	99.63 17	99.72 75	99.10 23	99.98 15	98.51 110	97.00 46	98.52 121	99.71 86	87.80 214	99.95 73	99.75 31	99.38 118	99.83 94

gg-mvs-nofinetune		93.51 235	91.86 261	98.47 117	97.72 219	97.96 77	92.62 399	98.51 110	74.70 401	97.33 164	69.59 415	98.91 4	97.79 275	97.77 145	99.56 103	99.67 118

EI-MVSNet-Vis-set		98.27 56	98.11 57	98.75 93	99.83 57	96.59 133	99.40 227	98.51 110	95.29 97	98.51 123	99.76 66	93.60 110	99.71 141	98.53 103	99.52 105	99.95 74

原ACMM1				98.96 82	99.73 73	96.99 117		98.51 110	94.06 146	99.62 47	99.85 33	94.97 63	99.96 65	95.11 191	99.95 50	99.92 84

fmvsm_s_conf0.1_n_a		97.09 116	96.90 111	97.63 170	95.65 309	94.21 219	99.83 134	98.50 116	96.27 74	99.65 41	99.64 102	84.72 248	99.93 88	99.04 67	98.84 141	98.74 227

EI-MVSNet-UG-set		98.14 64	97.99 62	98.60 104	99.80 61	96.27 144	99.36 236	98.50 116	95.21 99	98.30 134	99.75 72	93.29 117	99.73 140	98.37 111	99.30 122	99.81 97

LS3D		95.84 168	95.11 179	98.02 144	99.85 54	95.10 195	98.74 306	98.50 116	87.22 329	93.66 232	99.86 29	87.45 219	99.95 73	90.94 270	99.81 83	99.02 213

PEN-MVS		90.19 310	89.06 313	93.57 311	93.06 354	90.90 298	99.06 268	98.47 119	88.11 316	85.91 347	96.30 290	76.67 318	95.94 363	87.07 320	76.91 375	93.89 332

DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 251	98.47 119	98.14 10	99.08 92	99.91 14	93.09 124	100.00 1	99.04 67	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 70	97.89 72	98.05 143	99.82 58	94.77 205	99.92 81	98.46 121	93.93 153	97.20 167	99.27 139	95.44 50	99.97 57	97.41 152	99.51 108	99.41 173
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
testing11		97.48 96	97.27 96	98.10 139	98.36 172	96.02 157	99.92 81	98.45 122	93.45 169	98.15 141	98.70 194	95.48 49	99.22 173	97.85 138	95.05 230	99.07 210

test_fmvsmvis_n_1920		97.67 91	97.59 84	97.91 152	97.02 257	95.34 184	99.95 54	98.45 122	97.87 15	97.02 173	99.59 107	89.64 192	99.98 47	99.41 51	99.34 121	98.42 236

test1111		95.57 177	94.98 185	97.37 185	98.56 156	93.37 243	98.86 296	98.45 122	94.95 102	96.63 183	98.95 173	75.21 336	99.11 183	95.02 193	98.14 162	99.64 124

ECVR-MVS		95.66 175	95.05 182	97.51 177	98.66 150	93.71 231	98.85 298	98.45 122	94.93 103	96.86 177	98.96 168	75.22 335	99.20 177	95.34 188	98.15 160	99.64 124

UA-Net		96.54 144	95.96 150	98.27 130	98.23 182	95.71 168	98.00 348	98.45 122	93.72 162	98.41 128	99.27 139	88.71 208	99.66 149	91.19 263	97.69 171	99.44 170

ZNCC-MVS		98.31 53	98.03 60	99.17 55	99.88 49	97.59 90	99.94 71	98.44 127	94.31 133	98.50 124	99.82 49	93.06 125	99.99 36	98.30 115	99.99 21	99.93 79

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 102	99.92 1	99.96 35	98.44 127	97.96 14	99.55 55	99.94 4	97.18 21	100.00 1	93.81 226	99.94 55	99.98 51

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 108	98.44 127	97.48 27	99.64 43	99.94 4	96.68 29	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 81	97.33 94	99.25 46	98.77 144	98.66 51	99.99 4	98.44 127	94.40 129	98.41 128	99.47 119	93.65 108	99.42 167	98.57 99	94.26 240	99.67 118

test11								98.44 127

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 52	98.72 146	97.71 85	99.98 15	98.44 127	96.85 49	99.80 17	99.91 14	97.57 8	99.85 111	99.44 49	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
MDTV_nov1_ep13			95.69 161		97.90 203	94.15 220	95.98 385	98.44 127	93.12 180	97.98 144	95.74 305	95.10 55	98.58 216	90.02 287	96.92 191

DP-MVS Recon		98.41 48	98.02 61	99.56 25	99.97 3	98.70 48	99.92 81	98.44 127	92.06 225	98.40 130	99.84 44	95.68 44	100.00 1	98.19 118	99.71 88	99.97 61

testing99		97.17 111	96.91 110	97.95 146	98.35 174	95.70 169	99.91 87	98.43 135	92.94 184	97.36 163	98.72 192	94.83 65	99.21 174	97.00 162	94.64 232	98.95 215

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 54	98.43 135	96.48 63	99.80 17	99.93 11	97.44 14	100.00 1	99.92 13	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 35	98.43 135	97.27 34	99.80 17	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 135	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		98.43 135	97.26 36	99.80 17	99.88 24	96.71 27	100.00 1

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 54	98.43 135					100.00 1	99.99 5	100.00 1	100.00 1

TEST9					99.92 31	98.92 29	99.96 35	98.43 135	93.90 156	99.71 35	99.86 29	95.88 41	99.85 111

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 35	98.43 135	94.35 130	99.71 35	99.86 29	95.94 38	99.85 111	99.69 38	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 35	98.43 135	94.35 130	99.69 37	99.85 33	95.94 38	99.85 111

agg_prior					99.93 24	98.77 42		98.43 135		99.63 44			99.85 111

PAPM_NR		98.12 65	97.93 69	98.70 96	99.94 13	96.13 154	99.82 137	98.43 135	94.56 118	97.52 157	99.70 88	94.40 79	99.98 47	97.00 162	99.98 32	99.99 23

PAPR		98.52 38	98.16 53	99.58 24	99.97 3	98.77 42	99.95 54	98.43 135	95.35 95	98.03 143	99.75 72	94.03 97	99.98 47	98.11 123	99.83 77	99.99 23

testing91		97.16 112	96.90 111	97.97 145	98.35 174	95.67 172	99.91 87	98.42 147	92.91 186	97.33 164	98.72 192	94.81 66	99.21 174	96.98 164	94.63 233	99.03 212

test0726					99.93 24	99.29 15	99.96 35	98.42 147	97.28 32	99.86 7	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 80	99.93 24	97.24 105	99.95 54	98.42 147	97.50 26	99.52 60	99.88 24	97.43 16	99.71 141	99.50 44	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 29	98.55 28	99.15 59	99.94 13	97.50 95	99.94 71	98.42 147	96.22 75	99.41 70	99.78 62	94.34 84	99.96 65	98.92 76	99.95 50	99.99 23

X-MVStestdata		93.83 223	92.06 256	99.15 59	99.94 13	97.50 95	99.94 71	98.42 147	96.22 75	99.41 70	41.37 424	94.34 84	99.96 65	98.92 76	99.95 50	99.99 23

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 152					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 152					100.00 1	99.96 9	100.00 1	100.00 1

test_one_0601					99.94 13	99.30 12		98.41 152	96.63 60	99.75 29	99.93 11	97.49 10

IU-MVS					99.93 24	99.31 10		98.41 152	97.71 19	99.84 12				100.00 1	100.00 1	100.00 1

save fliter					99.82 58	98.79 40	99.96 35	98.40 156	97.66 21

test12				99.43 35	99.74 70	98.56 57		98.40 156		99.65 41		94.76 67	99.75 135		99.98 32	99.99 23

PatchmatchNet		95.94 165	95.45 167	97.39 184	97.83 208	94.41 211	96.05 383	98.40 156	92.86 187	97.09 170	95.28 334	94.21 92	98.07 262	89.26 294	98.11 163	99.70 113
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GST-MVS		98.27 56	97.97 64	99.17 55	99.92 31	97.57 91	99.93 78	98.39 159	94.04 148	98.80 106	99.74 79	92.98 127	100.00 1	98.16 120	99.76 85	99.93 79

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 87	98.39 159	97.20 38	99.46 64	99.85 33	95.53 48	99.79 126	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 62	97.97 64	99.03 73	99.94 13	97.17 111	99.95 54	98.39 159	94.70 114	98.26 137	99.81 53	91.84 158	100.00 1	98.85 82	99.97 42	99.93 79
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		98.45 43	98.32 43	98.87 86	99.96 8	96.62 130	99.97 28	98.39 159	94.43 125	98.90 101	99.87 27	94.30 87	100.00 1	99.04 67	99.99 21	99.99 23

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 119	98.38 163	93.19 176	99.77 27	99.94 4	95.54 46	100.00 1	99.74 33	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 17	98.77 19	99.41 38	99.74 70	98.67 49	99.77 149	98.38 163	96.73 56	99.88 6	99.74 79	94.89 64	99.59 152	99.80 25	99.98 32	99.97 61
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 50	98.20 49	98.97 81	99.97 3	96.92 120	99.95 54	98.38 163	95.04 101	98.61 119	99.80 54	93.39 111	100.00 1	98.64 96	100.00 1	99.98 51

ACMMP_NAP		98.49 40	98.14 54	99.54 27	99.66 82	98.62 55	99.85 122	98.37 166	94.68 115	99.53 58	99.83 46	92.87 130	100.00 1	98.66 95	99.84 76	99.99 23

FOURS1					99.92 31	97.66 89	99.95 54	98.36 167	95.58 89	99.52 60

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 108	98.36 167	94.08 143	99.74 31	99.73 81	94.08 95	99.74 137	99.42 50	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Syy-MVS		90.00 314	90.63 280	88.11 374	97.68 222	74.66 401	99.71 175	98.35 169	90.79 264	92.10 251	98.67 196	79.10 301	93.09 394	63.35 408	95.95 210	96.59 264

myMVS_eth3d		94.46 210	94.76 190	93.55 312	97.68 222	90.97 294	99.71 175	98.35 169	90.79 264	92.10 251	98.67 196	92.46 144	93.09 394	87.13 319	95.95 210	96.59 264

SR-MVS		98.46 42	98.30 46	98.93 84	99.88 49	97.04 115	99.84 127	98.35 169	94.92 105	99.32 77	99.80 54	93.35 113	99.78 128	99.30 55	99.95 50	99.96 67

CPTT-MVS		97.64 92	97.32 95	98.58 107	99.97 3	95.77 164	99.96 35	98.35 169	89.90 283	98.36 131	99.79 58	91.18 167	99.99 36	98.37 111	99.99 21	99.99 23

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 78	98.73 46	99.94 71	98.34 173	96.38 69	99.81 15	99.76 66	94.59 72	99.98 47	99.84 22	99.96 46	99.97 61
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 37		99.87 51		99.91 87	98.33 174	93.22 175	99.78 26	99.89 22	94.57 75	99.85 111	99.84 22	99.97 42

CDPH-MVS		98.65 31	98.36 41	99.49 32	99.94 13	98.73 46	99.87 108	98.33 174	93.97 150	99.76 28	99.87 27	94.99 62	99.75 135	98.55 100	100.00 1	99.98 51

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 54	98.32 176	97.28 32	99.83 13	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 87
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		94.69 200	93.81 214	97.33 189	97.10 253	94.44 208	98.86 296	98.32 176	93.30 173	96.17 197	95.59 312	76.48 322	97.95 269	91.06 266	97.43 176	99.59 137

SR-MVS-dyc-post		98.31 53	98.17 52	98.71 95	99.79 62	96.37 142	99.76 154	98.31 178	94.43 125	99.40 72	99.75 72	93.28 118	99.78 128	98.90 79	99.92 64	99.97 61

RE-MVS-def			98.13 55		99.79 62	96.37 142	99.76 154	98.31 178	94.43 125	99.40 72	99.75 72	92.95 128		98.90 79	99.92 64	99.97 61

RPMNet		89.76 318	87.28 334	97.19 192	96.29 281	92.66 258	92.01 402	98.31 178	70.19 408	96.94 174	85.87 407	87.25 222	99.78 128	62.69 409	95.96 208	99.13 204

APD-MVS_3200maxsize		98.25 60	98.08 59	98.78 90	99.81 60	96.60 131	99.82 137	98.30 181	93.95 152	99.37 75	99.77 64	92.84 131	99.76 134	98.95 73	99.92 64	99.97 61

TESTMET0.1,1		96.74 136	96.26 136	98.16 134	97.36 243	96.48 135	99.96 35	98.29 182	91.93 228	95.77 206	98.07 233	95.54 46	98.29 245	90.55 278	98.89 138	99.70 113

MTGPA								98.28 183

MTAPA		98.29 55	97.96 67	99.30 44	99.85 54	97.93 78	99.39 231	98.28 183	95.76 84	97.18 169	99.88 24	92.74 134	100.00 1	98.67 93	99.88 73	99.99 23

114514_t		97.41 102	96.83 115	99.14 61	99.51 94	97.83 80	99.89 102	98.27 185	88.48 311	99.06 94	99.66 99	90.30 185	99.64 151	96.32 175	99.97 42	99.96 67

Anonymous20231211		89.86 316	88.44 323	94.13 290	98.93 127	90.68 303	98.54 321	98.26 186	76.28 394	86.73 334	95.54 314	70.60 358	97.56 284	90.82 273	80.27 353	94.15 309

reproduce-ours		98.78 24	98.67 21	99.09 68	99.70 78	97.30 103	99.74 161	98.25 187	97.10 40	99.10 90	99.90 18	94.59 72	99.99 36	99.77 28	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 68	99.70 78	97.30 103	99.74 161	98.25 187	97.10 40	99.10 90	99.90 18	94.59 72	99.99 36	99.77 28	99.91 67	99.99 23

Vis-MVSNet		95.72 170	95.15 178	97.45 179	97.62 227	94.28 216	99.28 247	98.24 189	94.27 138	96.84 178	98.94 175	79.39 296	98.76 203	93.25 236	98.49 149	99.30 189
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	91.53 11	96.31 155	95.24 174	99.52 28	96.88 267	98.64 54	99.72 172	98.24 189	95.27 98	88.42 314	98.98 164	82.76 263	99.94 81	97.10 160	99.83 77	99.96 67

reproduce_model		98.75 27	98.66 23	99.03 73	99.71 76	97.10 113	99.73 168	98.23 191	97.02 45	99.18 87	99.90 18	94.54 76	99.99 36	99.77 28	99.90 69	99.99 23

DTE-MVSNet		89.40 323	88.24 326	92.88 328	92.66 363	89.95 320	99.10 260	98.22 192	87.29 327	85.12 352	96.22 292	76.27 325	95.30 373	83.56 348	75.74 380	93.41 349

SF-MVS		98.67 30	98.40 35	99.50 30	99.77 65	98.67 49	99.90 93	98.21 193	93.53 165	99.81 15	99.89 22	94.70 71	99.86 110	99.84 22	99.93 61	99.96 67

VDDNet		93.12 244	91.91 259	96.76 204	96.67 278	92.65 260	98.69 312	98.21 193	82.81 375	97.75 154	99.28 136	61.57 392	99.48 164	98.09 125	94.09 242	98.15 241

test-LLR		96.47 146	96.04 142	97.78 158	97.02 257	95.44 179	99.96 35	98.21 193	94.07 144	95.55 208	96.38 286	93.90 101	98.27 249	90.42 281	98.83 142	99.64 124

test-mter		96.39 151	95.93 153	97.78 158	97.02 257	95.44 179	99.96 35	98.21 193	91.81 233	95.55 208	96.38 286	95.17 53	98.27 249	90.42 281	98.83 142	99.64 124

MP-MVS-pluss		98.07 67	97.64 80	99.38 42	99.74 70	98.41 63	99.74 161	98.18 197	93.35 170	96.45 188	99.85 33	92.64 136	99.97 57	98.91 78	99.89 70	99.77 104
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
BP-MVS1		98.33 52	98.18 51	98.81 89	97.44 237	97.98 74	99.96 35	98.17 198	94.88 107	98.77 108	99.59 107	97.59 7	99.08 186	98.24 116	98.93 137	99.36 179

FA-MVS(test-final)		95.86 166	95.09 180	98.15 137	97.74 214	95.62 174	96.31 378	98.17 198	91.42 247	96.26 194	96.13 296	90.56 180	99.47 165	92.18 251	97.07 185	99.35 182

PS-MVSNAJ		98.44 44	98.20 49	99.16 57	98.80 142	98.92 29	99.54 208	98.17 198	97.34 29	99.85 9	99.85 33	91.20 164	99.89 99	99.41 51	99.67 90	98.69 230

HPM-MVS		97.96 68	97.72 76	98.68 97	99.84 56	96.39 141	99.90 93	98.17 198	92.61 203	98.62 118	99.57 112	91.87 157	99.67 148	98.87 81	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		96.27 159	95.98 146	97.13 193	97.96 200	93.15 245	96.34 377	98.17 198	92.07 223	98.71 114	95.12 338	93.91 100	98.73 206	94.91 199	96.62 194	99.50 162

WB-MVSnew		92.90 249	92.77 240	93.26 319	96.95 261	93.63 234	99.71 175	98.16 203	91.49 240	94.28 225	98.14 230	81.33 276	96.48 341	79.47 369	95.46 221	89.68 395

ADS-MVSNet		94.79 196	94.02 207	97.11 195	97.87 205	93.79 228	94.24 391	98.16 203	90.07 279	96.43 189	94.48 359	90.29 186	98.19 254	87.44 313	97.23 181	99.36 179

HPM-MVS_fast		97.80 82	97.50 86	98.68 97	99.79 62	96.42 137	99.88 105	98.16 203	91.75 235	98.94 99	99.54 115	91.82 159	99.65 150	97.62 150	99.99 21	99.99 23

Vis-MVSNet (Re-imp)		96.32 154	95.98 146	97.35 188	97.93 202	94.82 202	99.47 219	98.15 206	91.83 231	95.09 215	99.11 151	91.37 162	97.47 287	93.47 234	97.43 176	99.74 107

CNLPA		97.76 86	97.38 91	98.92 85	99.53 91	96.84 122	99.87 108	98.14 207	93.78 159	96.55 186	99.69 90	92.28 148	99.98 47	97.13 158	99.44 114	99.93 79

JIA-IIPM		91.76 277	90.70 278	94.94 256	96.11 286	87.51 349	93.16 398	98.13 208	75.79 397	97.58 156	77.68 412	92.84 131	97.97 266	88.47 303	96.54 195	99.33 185

cl22		93.77 227	93.25 231	95.33 245	99.49 95	94.43 209	99.61 195	98.09 209	90.38 272	89.16 299	95.61 310	90.56 180	97.34 291	91.93 254	84.45 316	94.21 301

cdsmvs_eth3d_5k		23.43 391	31.24 394	0.00 408	0.00 431	0.00 433	0.00 419	98.09 209	0.00 426	0.00 427	99.67 97	83.37 259	0.00 427	0.00 426	0.00 425	0.00 423

xiu_mvs_v2_base		98.23 62	97.97 64	99.02 76	98.69 147	98.66 51	99.52 210	98.08 211	97.05 43	99.86 7	99.86 29	90.65 177	99.71 141	99.39 53	98.63 146	98.69 230

tpm cat1		93.51 235	92.52 249	96.47 211	97.77 212	91.47 290	96.13 381	98.06 212	80.98 383	92.91 242	93.78 368	89.66 191	98.87 195	87.03 322	96.39 200	99.09 207

DeepC-MVS	94.51 4	96.92 127	96.40 133	98.45 119	99.16 111	95.90 160	99.66 185	98.06 212	96.37 72	94.37 223	99.49 118	83.29 260	99.90 94	97.63 149	99.61 99	99.55 147
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 87	97.44 89	98.64 101	95.76 299	96.20 150	99.94 71	98.05 214	98.17 9	98.89 102	99.42 123	87.65 216	99.90 94	99.50 44	99.60 101	99.82 95

EU-MVSNet		90.14 312	90.34 286	89.54 362	92.55 364	81.06 390	98.69 312	98.04 215	91.41 248	86.59 337	96.84 275	80.83 282	93.31 393	86.20 329	81.91 334	94.26 295

TAPA-MVS	92.12 8	94.42 211	93.60 217	96.90 200	99.33 102	91.78 279	99.78 146	98.00 216	89.89 284	94.52 220	99.47 119	91.97 155	99.18 179	69.90 397	99.52 105	99.73 108
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		95.78 169	94.86 187	98.54 112	98.47 166	98.07 69	99.06 268	97.99 217	92.68 199	94.13 228	98.62 203	93.28 118	98.69 211	93.79 228	85.76 304	98.84 221

UnsupCasMVSNet_eth		85.52 345	83.99 347	90.10 358	89.36 394	83.51 374	96.65 372	97.99 217	89.14 290	75.89 395	93.83 367	63.25 386	93.92 386	81.92 359	67.90 399	92.88 361

LFMVS		94.75 199	93.56 220	98.30 128	99.03 117	95.70 169	98.74 306	97.98 219	87.81 322	98.47 125	99.39 130	67.43 371	99.53 153	98.01 128	95.20 229	99.67 118

dp		95.05 189	94.43 195	96.91 199	97.99 198	92.73 256	96.29 379	97.98 219	89.70 286	95.93 201	94.67 354	93.83 105	98.45 225	86.91 326	96.53 196	99.54 151

PMMVS		96.76 134	96.76 118	96.76 204	98.28 179	92.10 270	99.91 87	97.98 219	94.12 141	99.53 58	99.39 130	86.93 227	98.73 206	96.95 167	97.73 170	99.45 168

F-COLMAP		96.93 126	96.95 109	96.87 201	99.71 76	91.74 280	99.85 122	97.95 222	93.11 181	95.72 207	99.16 150	92.35 146	99.94 81	95.32 189	99.35 120	98.92 216

OMC-MVS		97.28 106	97.23 98	97.41 182	99.76 66	93.36 244	99.65 186	97.95 222	96.03 79	97.41 162	99.70 88	89.61 193	99.51 156	96.73 171	98.25 158	99.38 175

mvsany_test1		97.82 80	97.90 71	97.55 173	98.77 144	93.04 249	99.80 143	97.93 224	96.95 48	99.61 53	99.68 96	90.92 172	99.83 121	99.18 59	98.29 157	99.80 99

Anonymous202405211		93.10 245	91.99 257	96.40 215	99.10 113	89.65 324	98.88 292	97.93 224	83.71 367	94.00 229	98.75 191	68.79 362	99.88 105	95.08 192	91.71 258	99.68 116

tpm2		95.47 179	95.18 177	96.35 218	96.91 263	91.70 284	96.96 368	97.93 224	88.04 318	98.44 126	95.40 323	93.32 115	97.97 266	94.00 219	95.61 219	99.38 175

TSAR-MVS + GP.		98.60 33	98.51 31	98.86 87	99.73 73	96.63 129	99.97 28	97.92 227	98.07 11	98.76 111	99.55 113	95.00 61	99.94 81	99.91 16	97.68 172	99.99 23

CDS-MVSNet		96.34 153	96.07 141	97.13 193	97.37 242	94.96 197	99.53 209	97.91 228	91.55 239	95.37 212	98.32 225	95.05 58	97.13 305	93.80 227	95.75 217	99.30 189
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP3-MVS								97.89 229							89.60 264

HQP-MVS		94.61 204	94.50 194	94.92 257	95.78 295	91.85 276	99.87 108	97.89 229	96.82 51	93.37 234	98.65 199	80.65 285	98.39 232	97.92 134	89.60 264	94.53 274

HQP_MVS		94.49 209	94.36 197	94.87 258	95.71 305	91.74 280	99.84 127	97.87 231	96.38 69	93.01 239	98.59 204	80.47 289	98.37 238	97.79 143	89.55 267	94.52 276

plane_prior5								97.87 231					98.37 238	97.79 143	89.55 267	94.52 276

xiu_mvs_v1_base_debu		97.43 97	97.06 103	98.55 109	97.74 214	98.14 66	99.31 241	97.86 233	96.43 66	99.62 47	99.69 90	85.56 239	99.68 145	99.05 64	98.31 154	97.83 247

xiu_mvs_v1_base		97.43 97	97.06 103	98.55 109	97.74 214	98.14 66	99.31 241	97.86 233	96.43 66	99.62 47	99.69 90	85.56 239	99.68 145	99.05 64	98.31 154	97.83 247

xiu_mvs_v1_base_debi		97.43 97	97.06 103	98.55 109	97.74 214	98.14 66	99.31 241	97.86 233	96.43 66	99.62 47	99.69 90	85.56 239	99.68 145	99.05 64	98.31 154	97.83 247

CostFormer		96.10 161	95.88 156	96.78 203	97.03 256	92.55 262	97.08 365	97.83 236	90.04 281	98.72 113	94.89 348	95.01 60	98.29 245	96.54 173	95.77 215	99.50 162

TAMVS		95.85 167	95.58 165	96.65 209	97.07 254	93.50 238	99.17 257	97.82 237	91.39 249	95.02 216	98.01 234	92.20 149	97.30 295	93.75 230	95.83 214	99.14 203

balanced_conf03		98.27 56	97.99 62	99.11 66	98.64 153	98.43 62	99.47 219	97.79 238	94.56 118	99.74 31	98.35 222	94.33 86	99.25 171	99.12 61	99.96 46	99.64 124

VDD-MVS		93.77 227	92.94 235	96.27 220	98.55 159	90.22 314	98.77 305	97.79 238	90.85 262	96.82 179	99.42 123	61.18 394	99.77 131	98.95 73	94.13 241	98.82 222

cascas		94.64 203	93.61 215	97.74 164	97.82 209	96.26 145	99.96 35	97.78 240	85.76 347	94.00 229	97.54 249	76.95 316	99.21 174	97.23 156	95.43 223	97.76 251

MVSMamba_PlusPlus		97.83 77	97.45 88	98.99 78	98.60 155	98.15 65	99.58 199	97.74 241	90.34 275	99.26 83	98.32 225	94.29 88	99.23 172	99.03 70	99.89 70	99.58 143

CLD-MVS		94.06 220	93.90 211	94.55 273	96.02 289	90.69 302	99.98 15	97.72 242	96.62 62	91.05 262	98.85 187	77.21 311	98.47 221	98.11 123	89.51 269	94.48 278
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MS-PatchMatch		90.65 296	90.30 287	91.71 343	94.22 333	85.50 363	98.24 337	97.70 243	88.67 307	86.42 341	96.37 288	67.82 369	98.03 264	83.62 347	99.62 95	91.60 376

mvsmamba		96.94 124	96.73 120	97.55 173	97.99 198	94.37 214	99.62 193	97.70 243	93.13 179	98.42 127	97.92 240	88.02 213	98.75 205	98.78 86	99.01 135	99.52 157

XXY-MVS		91.82 270	90.46 282	95.88 229	93.91 338	95.40 183	98.87 295	97.69 245	88.63 309	87.87 319	97.08 262	74.38 342	97.89 272	91.66 258	84.07 320	94.35 290

EI-MVSNet		93.73 229	93.40 227	94.74 263	96.80 271	92.69 257	99.06 268	97.67 246	88.96 298	91.39 257	99.02 157	88.75 207	97.30 295	91.07 265	87.85 291	94.22 299

MVSTER		95.53 178	95.22 175	96.45 213	98.56 156	97.72 84	99.91 87	97.67 246	92.38 216	91.39 257	97.14 259	97.24 18	97.30 295	94.80 202	87.85 291	94.34 292

mamv4		95.24 185	96.90 111	90.25 356	98.65 152	72.11 403	98.28 335	97.64 248	89.99 282	95.93 201	98.25 227	94.74 68	99.11 183	99.01 72	99.64 92	99.53 155

WBMVS		94.52 208	94.03 206	95.98 226	98.38 169	96.68 127	99.92 81	97.63 249	90.75 267	89.64 284	95.25 335	96.77 25	96.90 322	94.35 214	83.57 323	94.35 290

ETV-MVS		97.92 71	97.80 75	98.25 131	98.14 191	96.48 135	99.98 15	97.63 249	95.61 88	99.29 81	99.46 121	92.55 140	98.82 198	99.02 71	98.54 148	99.46 166

CANet_DTU		96.76 134	96.15 140	98.60 104	98.78 143	97.53 92	99.84 127	97.63 249	97.25 37	99.20 84	99.64 102	81.36 275	99.98 47	92.77 246	98.89 138	98.28 239

LPG-MVS_test		92.96 247	92.71 241	93.71 306	95.43 313	88.67 336	99.75 158	97.62 252	92.81 190	90.05 269	98.49 213	75.24 333	98.40 230	95.84 183	89.12 271	94.07 316

LGP-MVS_train				93.71 306	95.43 313	88.67 336		97.62 252	92.81 190	90.05 269	98.49 213	75.24 333	98.40 230	95.84 183	89.12 271	94.07 316

FMVSNet3		92.69 255	91.58 264	95.99 225	98.29 177	97.42 100	99.26 250	97.62 252	89.80 285	89.68 280	95.32 329	81.62 273	96.27 350	87.01 323	85.65 305	94.29 294

ET-MVSNet_ETH3D		94.37 213	93.28 230	97.64 168	98.30 176	97.99 73	99.99 4	97.61 255	94.35 130	71.57 401	99.45 122	96.23 35	95.34 371	96.91 169	85.14 311	99.59 137

EIA-MVS		97.53 94	97.46 87	97.76 162	98.04 196	94.84 201	99.98 15	97.61 255	94.41 128	97.90 147	99.59 107	92.40 145	98.87 195	98.04 127	99.13 130	99.59 137

OPM-MVS		93.21 240	92.80 238	94.44 280	93.12 352	90.85 300	99.77 149	97.61 255	96.19 77	91.56 256	98.65 199	75.16 337	98.47 221	93.78 229	89.39 270	93.99 324
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
IS-MVSNet		96.29 157	95.90 155	97.45 179	98.13 192	94.80 203	99.08 263	97.61 255	92.02 227	95.54 210	98.96 168	90.64 178	98.08 260	93.73 231	97.41 179	99.47 165

CMPMVS	61.59 21	84.75 353	85.14 346	83.57 382	90.32 388	62.54 410	96.98 367	97.59 259	74.33 402	69.95 403	96.66 278	64.17 382	98.32 242	87.88 310	88.41 285	89.84 394
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UniMVSNet_ETH3D		90.06 313	88.58 321	94.49 277	94.67 325	88.09 345	97.81 353	97.57 260	83.91 366	88.44 310	97.41 252	57.44 398	97.62 282	91.41 260	88.59 282	97.77 250

lupinMVS		97.85 75	97.60 82	98.62 102	97.28 250	97.70 87	99.99 4	97.55 261	95.50 93	99.43 68	99.67 97	90.92 172	98.71 209	98.40 108	99.62 95	99.45 168

XVG-OURS		94.82 193	94.74 191	95.06 252	98.00 197	89.19 328	99.08 263	97.55 261	94.10 142	94.71 218	99.62 105	80.51 287	99.74 137	96.04 179	93.06 256	96.25 266

XVG-OURS-SEG-HR		94.79 196	94.70 192	95.08 251	98.05 195	89.19 328	99.08 263	97.54 263	93.66 163	94.87 217	99.58 110	78.78 303	99.79 126	97.31 154	93.40 251	96.25 266

PatchT		90.38 303	88.75 319	95.25 248	95.99 290	90.16 315	91.22 406	97.54 263	76.80 393	97.26 166	86.01 406	91.88 156	96.07 359	66.16 405	95.91 212	99.51 160

BH-RMVSNet		95.18 186	94.31 200	97.80 155	98.17 188	95.23 190	99.76 154	97.53 265	92.52 210	94.27 226	99.25 143	76.84 317	98.80 199	90.89 272	99.54 104	99.35 182

ACMP	92.05 9	92.74 253	92.42 251	93.73 304	95.91 293	88.72 335	99.81 139	97.53 265	94.13 140	87.00 332	98.23 228	74.07 343	98.47 221	96.22 177	88.86 276	93.99 324
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	91.95 10	92.88 250	92.52 249	93.98 298	95.75 301	89.08 332	99.77 149	97.52 267	93.00 182	89.95 273	97.99 237	76.17 326	98.46 224	93.63 233	88.87 275	94.39 286
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TR-MVS		94.54 205	93.56 220	97.49 178	97.96 200	94.34 215	98.71 309	97.51 268	90.30 277	94.51 221	98.69 195	75.56 330	98.77 202	92.82 245	95.99 207	99.35 182

BH-w/o		95.71 172	95.38 170	96.68 207	98.49 165	92.28 266	99.84 127	97.50 269	92.12 222	92.06 253	98.79 189	84.69 249	98.67 213	95.29 190	99.66 91	99.09 207

mvs_anonymous		95.65 176	95.03 183	97.53 175	98.19 186	95.74 166	99.33 238	97.49 270	90.87 261	90.47 267	97.10 261	88.23 211	97.16 302	95.92 181	97.66 173	99.68 116

DP-MVS		94.54 205	93.42 224	97.91 152	99.46 98	94.04 222	98.93 286	97.48 271	81.15 382	90.04 271	99.55 113	87.02 225	99.95 73	88.97 296	98.11 163	99.73 108

ACMH	89.72 17	90.64 297	89.63 300	93.66 310	95.64 310	88.64 338	98.55 319	97.45 272	89.03 293	81.62 370	97.61 247	69.75 360	98.41 228	89.37 292	87.62 295	93.92 330
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVG-ACMP-BASELINE		91.22 286	90.75 277	92.63 332	93.73 341	85.61 361	98.52 323	97.44 273	92.77 194	89.90 275	96.85 273	66.64 374	98.39 232	92.29 249	88.61 280	93.89 332

mvs_tets		91.81 271	91.08 274	94.00 296	91.63 377	90.58 306	98.67 314	97.43 274	92.43 213	87.37 329	97.05 265	71.76 350	97.32 293	94.75 204	88.68 279	94.11 314

LTVRE_ROB	88.28 18	90.29 307	89.05 314	94.02 294	95.08 318	90.15 316	97.19 361	97.43 274	84.91 359	83.99 359	97.06 264	74.00 344	98.28 247	84.08 342	87.71 293	93.62 346
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		91.92 269	91.18 272	94.15 288	91.35 380	90.95 297	99.00 278	97.42 276	92.61 203	87.38 328	97.08 262	72.46 348	97.36 289	94.53 210	88.77 277	94.13 313

K. test v3		88.05 334	87.24 335	90.47 354	91.82 375	82.23 382	98.96 282	97.42 276	89.05 292	76.93 391	95.60 311	68.49 365	95.42 369	85.87 334	81.01 346	93.75 340

FMVSNet2		91.02 288	89.56 302	95.41 242	97.53 232	95.74 166	98.98 279	97.41 278	87.05 330	88.43 312	95.00 344	71.34 353	96.24 352	85.12 337	85.21 310	94.25 297

jason		97.24 108	96.86 114	98.38 125	95.73 302	97.32 102	99.97 28	97.40 279	95.34 96	98.60 120	99.54 115	87.70 215	98.56 217	97.94 133	99.47 110	99.25 195
jason: jason.
PS-MVSNAJss		93.64 232	93.31 229	94.61 268	92.11 370	92.19 268	99.12 259	97.38 280	92.51 211	88.45 309	96.99 268	91.20 164	97.29 298	94.36 212	87.71 293	94.36 287

MSDG		94.37 213	93.36 228	97.40 183	98.88 137	93.95 226	99.37 234	97.38 280	85.75 349	90.80 264	99.17 149	84.11 255	99.88 105	86.35 327	98.43 151	98.36 238

GDP-MVS		97.88 72	97.59 84	98.75 93	97.59 229	97.81 82	99.95 54	97.37 282	94.44 124	99.08 92	99.58 110	97.13 23	99.08 186	94.99 194	98.17 159	99.37 177

sasdasda		97.09 116	96.32 134	99.39 40	98.93 127	98.95 27	99.72 172	97.35 283	94.45 121	97.88 149	99.42 123	86.71 228	99.52 154	98.48 104	93.97 244	99.72 110

CL-MVSNet_self_test		84.50 355	83.15 356	88.53 371	86.00 401	81.79 385	98.82 300	97.35 283	85.12 355	83.62 362	90.91 388	76.66 319	91.40 402	69.53 398	60.36 411	92.40 369

canonicalmvs		97.09 116	96.32 134	99.39 40	98.93 127	98.95 27	99.72 172	97.35 283	94.45 121	97.88 149	99.42 123	86.71 228	99.52 154	98.48 104	93.97 244	99.72 110

UnsupCasMVSNet_bld		79.97 371	77.03 376	88.78 368	85.62 402	81.98 383	93.66 396	97.35 283	75.51 399	70.79 402	83.05 409	48.70 407	94.91 378	78.31 377	60.29 412	89.46 399

MVS-HIRNet		86.22 342	83.19 355	95.31 246	96.71 277	90.29 312	92.12 401	97.33 287	62.85 409	86.82 333	70.37 414	69.37 361	97.49 286	75.12 388	97.99 168	98.15 241

BH-untuned		95.18 186	94.83 188	96.22 221	98.36 172	91.22 292	99.80 143	97.32 288	90.91 260	91.08 260	98.67 196	83.51 257	98.54 219	94.23 217	99.61 99	98.92 216

PCF-MVS	94.20 5	95.18 186	94.10 204	98.43 121	98.55 159	95.99 158	97.91 350	97.31 289	90.35 274	89.48 288	99.22 145	85.19 244	99.89 99	90.40 283	98.47 150	99.41 173
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MGCFI-Net		97.00 121	96.22 138	99.34 43	98.86 138	98.80 39	99.67 184	97.30 290	94.31 133	97.77 153	99.41 127	86.36 234	99.50 158	98.38 109	93.90 246	99.72 110

test_fmvsmconf0.01_n		96.39 151	95.74 159	98.32 127	91.47 379	95.56 176	99.84 127	97.30 290	97.74 18	97.89 148	99.35 134	79.62 294	99.85 111	99.25 57	99.24 125	99.55 147

test_vis1_n_1920		95.44 180	95.31 172	95.82 232	98.50 164	88.74 334	99.98 15	97.30 290	97.84 16	99.85 9	99.19 147	66.82 373	99.97 57	98.82 83	99.46 112	98.76 225

miper_enhance_ethall		94.36 215	93.98 208	95.49 237	98.68 148	95.24 189	99.73 168	97.29 293	93.28 174	89.86 276	95.97 301	94.37 83	97.05 311	92.20 250	84.45 316	94.19 302

casdiffmvs_mvg		96.43 148	95.94 152	97.89 154	97.44 237	95.47 178	99.86 119	97.29 293	93.35 170	96.03 198	99.19 147	85.39 242	98.72 208	97.89 137	97.04 187	99.49 164
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		96.94 124	96.60 126	97.95 146	97.28 250	97.70 87	99.55 206	97.27 295	91.17 252	99.43 68	99.54 115	90.92 172	96.89 323	94.67 207	99.62 95	99.25 195

test_djsdf		92.83 251	92.29 252	94.47 278	91.90 373	92.46 263	99.55 206	97.27 295	91.17 252	89.96 272	96.07 299	81.10 278	96.89 323	94.67 207	88.91 273	94.05 318

test_cas_vis1_n_1920		96.59 143	96.23 137	97.65 167	98.22 183	94.23 218	99.99 4	97.25 297	97.77 17	99.58 54	99.08 153	77.10 312	99.97 57	97.64 148	99.45 113	98.74 227

GA-MVS		93.83 223	92.84 236	96.80 202	95.73 302	93.57 235	99.88 105	97.24 298	92.57 207	92.92 241	96.66 278	78.73 304	97.67 280	87.75 311	94.06 243	99.17 199

Effi-MVS+		96.30 156	95.69 161	98.16 134	97.85 207	96.26 145	97.41 357	97.21 299	90.37 273	98.65 117	98.58 207	86.61 231	98.70 210	97.11 159	97.37 180	99.52 157

Patchmatch-test		92.65 257	91.50 267	96.10 224	96.85 268	90.49 308	91.50 404	97.19 300	82.76 376	90.23 268	95.59 312	95.02 59	98.00 265	77.41 380	96.98 190	99.82 95

diffmvs		97.00 121	96.64 124	98.09 140	97.64 226	96.17 153	99.81 139	97.19 300	94.67 116	98.95 98	99.28 136	86.43 232	98.76 203	98.37 111	97.42 178	99.33 185
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	90.35 304	89.54 303	92.78 331	95.99 290	86.12 359	98.81 301	97.18 302	89.38 288	83.14 363	97.76 246	68.42 366	98.43 226	89.11 295	86.05 303	93.78 339

anonymousdsp		91.79 276	90.92 276	94.41 283	90.76 385	92.93 251	98.93 286	97.17 303	89.08 291	87.46 327	95.30 330	78.43 309	96.92 321	92.38 248	88.73 278	93.39 351

baseline		96.43 148	95.98 146	97.76 162	97.34 244	95.17 194	99.51 212	97.17 303	93.92 154	96.90 176	99.28 136	85.37 243	98.64 214	97.50 151	96.86 193	99.46 166

nrg030		93.51 235	92.53 248	96.45 213	94.36 330	97.20 107	99.81 139	97.16 305	91.60 237	89.86 276	97.46 250	86.37 233	97.68 279	95.88 182	80.31 352	94.46 279

SPE-MVS-test		97.88 72	97.94 68	97.70 165	99.28 105	95.20 192	99.98 15	97.15 306	95.53 91	99.62 47	99.79 58	92.08 153	98.38 236	98.75 89	99.28 123	99.52 157

MVS_Test		96.46 147	95.74 159	98.61 103	98.18 187	97.23 106	99.31 241	97.15 306	91.07 257	98.84 103	97.05 265	88.17 212	98.97 190	94.39 211	97.50 175	99.61 134

MIMVSNet		90.30 306	88.67 320	95.17 250	96.45 280	91.64 286	92.39 400	97.15 306	85.99 344	90.50 266	93.19 375	66.95 372	94.86 379	82.01 358	93.43 250	99.01 214

KD-MVS_2432*1600		88.00 335	86.10 339	93.70 308	96.91 263	94.04 222	97.17 362	97.12 309	84.93 357	81.96 367	92.41 379	92.48 142	94.51 382	79.23 370	52.68 414	92.56 365

miper_refine_blended		88.00 335	86.10 339	93.70 308	96.91 263	94.04 222	97.17 362	97.12 309	84.93 357	81.96 367	92.41 379	92.48 142	94.51 382	79.23 370	52.68 414	92.56 365

CS-MVS		97.79 84	97.91 70	97.43 181	99.10 113	94.42 210	99.99 4	97.10 311	95.07 100	99.68 38	99.75 72	92.95 128	98.34 240	98.38 109	99.14 129	99.54 151

v7n		89.65 320	88.29 325	93.72 305	92.22 368	90.56 307	99.07 267	97.10 311	85.42 354	86.73 334	94.72 350	80.06 291	97.13 305	81.14 362	78.12 364	93.49 348

RRT-MVS		96.24 160	95.68 163	97.94 149	97.65 225	94.92 199	99.27 249	97.10 311	92.79 193	97.43 161	97.99 237	81.85 269	99.37 168	98.46 106	98.57 147	99.53 155

casdiffmvs		96.42 150	95.97 149	97.77 160	97.30 248	94.98 196	99.84 127	97.09 314	93.75 161	96.58 185	99.26 142	85.07 245	98.78 201	97.77 145	97.04 187	99.54 151
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+		95.02 190	94.19 202	97.52 176	97.88 204	94.55 207	99.97 28	97.08 315	88.85 303	94.47 222	97.96 239	84.59 250	98.41 228	89.84 290	97.10 184	99.59 137

miper_ehance_all_eth		93.16 243	92.60 243	94.82 262	97.57 230	93.56 236	99.50 214	97.07 316	88.75 305	88.85 303	95.52 316	90.97 171	96.74 331	90.77 274	84.45 316	94.17 303

MonoMVSNet		94.82 193	94.43 195	95.98 226	94.54 327	90.73 301	99.03 275	97.06 317	93.16 178	93.15 238	95.47 320	88.29 210	97.57 283	97.85 138	91.33 261	99.62 130

Effi-MVS+-dtu		94.53 207	95.30 173	92.22 335	97.77 212	82.54 379	99.59 197	97.06 317	94.92 105	95.29 213	95.37 327	85.81 237	97.89 272	94.80 202	97.07 185	96.23 268

EC-MVSNet		97.38 104	97.24 97	97.80 155	97.41 239	95.64 173	99.99 4	97.06 317	94.59 117	99.63 44	99.32 135	89.20 202	98.14 256	98.76 88	99.23 126	99.62 130

IterMVS		90.91 290	90.17 292	93.12 322	96.78 274	90.42 311	98.89 290	97.05 320	89.03 293	86.49 339	95.42 322	76.59 320	95.02 374	87.22 318	84.09 319	93.93 329
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1192		90.62 299	89.25 309	94.72 265	93.13 350	93.07 246	99.50 214	97.02 321	86.33 341	89.56 287	95.01 342	79.22 298	97.09 310	82.34 356	81.16 340	94.01 321

v2v482		91.30 281	90.07 295	95.01 253	93.13 350	93.79 228	99.77 149	97.02 321	88.05 317	89.25 293	95.37 327	80.73 283	97.15 303	87.28 317	80.04 355	94.09 315

V42		91.28 283	90.12 294	94.74 263	93.42 347	93.46 239	99.68 182	97.02 321	87.36 326	89.85 278	95.05 340	81.31 277	97.34 291	87.34 316	80.07 354	93.40 350

IterMVS-SCA-FT		90.85 293	90.16 293	92.93 327	96.72 276	89.96 319	98.89 290	96.99 324	88.95 299	86.63 336	95.67 308	76.48 322	95.00 375	87.04 321	84.04 322	93.84 336

v144192		90.79 294	89.52 304	94.59 270	93.11 353	92.77 252	99.56 204	96.99 324	86.38 340	89.82 279	94.95 347	80.50 288	97.10 308	83.98 344	80.41 350	93.90 331

v1921920		90.46 301	89.12 311	94.50 276	92.96 357	92.46 263	99.49 216	96.98 326	86.10 343	89.61 286	95.30 330	78.55 307	97.03 316	82.17 357	80.89 348	94.01 321

v1144		91.09 287	89.83 296	94.87 258	93.25 349	93.69 233	99.62 193	96.98 326	86.83 336	89.64 284	94.99 345	80.94 280	97.05 311	85.08 338	81.16 340	93.87 334

eth_miper_zixun_eth		92.41 261	91.93 258	93.84 303	97.28 250	90.68 303	98.83 299	96.97 328	88.57 310	89.19 298	95.73 307	89.24 201	96.69 334	89.97 289	81.55 336	94.15 309

dcpmvs_2		97.42 101	98.09 58	95.42 241	99.58 89	87.24 352	99.23 252	96.95 329	94.28 136	98.93 100	99.73 81	94.39 82	99.16 182	99.89 17	99.82 81	99.86 92

GBi-Net		90.88 291	89.82 297	94.08 291	97.53 232	91.97 271	98.43 327	96.95 329	87.05 330	89.68 280	94.72 350	71.34 353	96.11 355	87.01 323	85.65 305	94.17 303

test1		90.88 291	89.82 297	94.08 291	97.53 232	91.97 271	98.43 327	96.95 329	87.05 330	89.68 280	94.72 350	71.34 353	96.11 355	87.01 323	85.65 305	94.17 303

FMVSNet1		88.50 330	86.64 337	94.08 291	95.62 312	91.97 271	98.43 327	96.95 329	83.00 373	86.08 346	94.72 350	59.09 396	96.11 355	81.82 360	84.07 320	94.17 303

v8		90.54 300	89.17 310	94.66 266	93.43 346	93.40 242	99.20 254	96.94 333	85.76 347	87.56 324	94.51 357	81.96 268	97.19 301	84.94 339	78.25 362	93.38 352

c3_l		92.53 258	91.87 260	94.52 274	97.40 240	92.99 250	99.40 227	96.93 334	87.86 320	88.69 306	95.44 321	89.95 189	96.44 343	90.45 280	80.69 349	94.14 312

v1240		90.20 309	88.79 318	94.44 280	93.05 355	92.27 267	99.38 232	96.92 335	85.89 345	89.36 290	94.87 349	77.89 310	97.03 316	80.66 364	81.08 343	94.01 321

tpm		93.70 231	93.41 226	94.58 271	95.36 315	87.41 350	97.01 366	96.90 336	90.85 262	96.72 182	94.14 365	90.40 183	96.84 326	90.75 275	88.54 283	99.51 160

v148		90.70 295	89.63 300	93.92 299	92.97 356	90.97 294	99.75 158	96.89 337	87.51 323	88.27 315	95.01 342	81.67 270	97.04 314	87.40 315	77.17 373	93.75 340

IterMVS-LS		92.69 255	92.11 254	94.43 282	96.80 271	92.74 254	99.45 224	96.89 337	88.98 296	89.65 283	95.38 326	88.77 206	96.34 347	90.98 269	82.04 333	94.22 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v10		90.25 308	88.82 317	94.57 272	93.53 344	93.43 240	99.08 263	96.87 339	85.00 356	87.34 330	94.51 357	80.93 281	97.02 318	82.85 352	79.23 357	93.26 354

ADS-MVSNet2		93.80 226	93.88 212	93.55 312	97.87 205	85.94 360	94.24 391	96.84 340	90.07 279	96.43 189	94.48 359	90.29 186	95.37 370	87.44 313	97.23 181	99.36 179

Fast-Effi-MVS+-dtu		93.72 230	93.86 213	93.29 317	97.06 255	86.16 358	99.80 143	96.83 341	92.66 200	92.58 246	97.83 245	81.39 274	97.67 280	89.75 291	96.87 192	96.05 271

pmmvs4		92.10 267	91.07 275	95.18 249	92.82 361	94.96 197	99.48 218	96.83 341	87.45 325	88.66 307	96.56 284	83.78 256	96.83 328	89.29 293	84.77 314	93.75 340

AllTest		92.48 259	91.64 262	95.00 254	99.01 118	88.43 340	98.94 284	96.82 343	86.50 338	88.71 304	98.47 217	74.73 339	99.88 105	85.39 335	96.18 203	96.71 262

TestCases				95.00 254	99.01 118	88.43 340		96.82 343	86.50 338	88.71 304	98.47 217	74.73 339	99.88 105	85.39 335	96.18 203	96.71 262

miper_lstm_enhance		91.81 271	91.39 270	93.06 325	97.34 244	89.18 330	99.38 232	96.79 345	86.70 337	87.47 326	95.22 336	90.00 188	95.86 364	88.26 304	81.37 338	94.15 309

cl____		92.31 263	91.58 264	94.52 274	97.33 246	92.77 252	99.57 202	96.78 346	86.97 334	87.56 324	95.51 317	89.43 195	96.62 336	88.60 299	82.44 330	94.16 308

DIV-MVS_self_test		92.32 262	91.60 263	94.47 278	97.31 247	92.74 254	99.58 199	96.75 347	86.99 333	87.64 322	95.54 314	89.55 194	96.50 340	88.58 300	82.44 330	94.17 303

ppachtmachnet_test		89.58 321	88.35 324	93.25 320	92.40 366	90.44 310	99.33 238	96.73 348	85.49 352	85.90 348	95.77 304	81.09 279	96.00 362	76.00 387	82.49 329	93.30 353

GeoE		94.36 215	93.48 222	96.99 197	97.29 249	93.54 237	99.96 35	96.72 349	88.35 314	93.43 233	98.94 175	82.05 266	98.05 263	88.12 308	96.48 199	99.37 177

COLMAP_ROB	90.47 14	92.18 266	91.49 268	94.25 287	99.00 120	88.04 346	98.42 330	96.70 350	82.30 378	88.43 312	99.01 159	76.97 315	99.85 111	86.11 331	96.50 197	94.86 273
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
1112_ss		96.01 164	95.20 176	98.42 122	97.80 210	96.41 138	99.65 186	96.66 351	92.71 196	92.88 243	99.40 128	92.16 150	99.30 169	91.92 255	93.66 247	99.55 147

test_fmvs1		95.35 183	95.68 163	94.36 284	98.99 121	84.98 366	99.96 35	96.65 352	97.60 22	99.73 33	98.96 168	71.58 352	99.93 88	98.31 114	99.37 119	98.17 240

Test_1112_low_res		95.72 170	94.83 188	98.42 122	97.79 211	96.41 138	99.65 186	96.65 352	92.70 197	92.86 244	96.13 296	92.15 151	99.30 169	91.88 256	93.64 248	99.55 147

RPSCF		91.80 274	92.79 239	88.83 367	98.15 190	69.87 405	98.11 344	96.60 354	83.93 365	94.33 224	99.27 139	79.60 295	99.46 166	91.99 253	93.16 254	97.18 259

test_fmvs1_n		94.25 218	94.36 197	93.92 299	97.68 222	83.70 373	99.90 93	96.57 355	97.40 28	99.67 39	98.88 179	61.82 391	99.92 91	98.23 117	99.13 130	98.14 243

YYNet1		85.50 347	83.33 353	92.00 337	90.89 384	88.38 343	99.22 253	96.55 356	79.60 389	57.26 413	92.72 376	79.09 302	93.78 389	77.25 381	77.37 371	93.84 336

MDA-MVSNet_test_wron		85.51 346	83.32 354	92.10 336	90.96 383	88.58 339	99.20 254	96.52 357	79.70 388	57.12 414	92.69 377	79.11 300	93.86 388	77.10 382	77.46 370	93.86 335

MTMP							99.87 108	96.49 358

pm-mvs1		89.36 324	87.81 330	94.01 295	93.40 348	91.93 274	98.62 317	96.48 359	86.25 342	83.86 360	96.14 295	73.68 345	97.04 314	86.16 330	75.73 381	93.04 359

KD-MVS_self_test		83.59 361	82.06 361	88.20 373	86.93 399	80.70 392	97.21 360	96.38 360	82.87 374	82.49 365	88.97 395	67.63 370	92.32 399	73.75 391	62.30 410	91.58 377

test_vis1_n		93.61 233	93.03 234	95.35 243	95.86 294	86.94 354	99.87 108	96.36 361	96.85 49	99.54 57	98.79 189	52.41 404	99.83 121	98.64 96	98.97 136	99.29 191

our_test_3		90.39 302	89.48 307	93.12 322	92.40 366	89.57 325	99.33 238	96.35 362	87.84 321	85.30 350	94.99 345	84.14 254	96.09 358	80.38 365	84.56 315	93.71 345

CR-MVSNet		93.45 238	92.62 242	95.94 228	96.29 281	92.66 258	92.01 402	96.23 363	92.62 202	96.94 174	93.31 373	91.04 169	96.03 360	79.23 370	95.96 208	99.13 204

Patchmtry		89.70 319	88.49 322	93.33 316	96.24 284	89.94 322	91.37 405	96.23 363	78.22 391	87.69 321	93.31 373	91.04 169	96.03 360	80.18 368	82.10 332	94.02 319

MVP-Stereo		90.93 289	90.45 284	92.37 334	91.25 382	88.76 333	98.05 347	96.17 365	87.27 328	84.04 357	95.30 330	78.46 308	97.27 300	83.78 346	99.70 89	91.09 379
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pmmvs6		85.69 343	83.84 350	91.26 346	90.00 391	84.41 370	97.82 352	96.15 366	75.86 396	81.29 372	95.39 325	61.21 393	96.87 325	83.52 349	73.29 384	92.50 367

EG-PatchMatch MVS		85.35 348	83.81 351	89.99 360	90.39 387	81.89 384	98.21 341	96.09 367	81.78 380	74.73 397	93.72 369	51.56 406	97.12 307	79.16 373	88.61 280	90.96 382

DeepMVS_CX				82.92 384	95.98 292	58.66 415		96.01 368	92.72 195	78.34 385	95.51 317	58.29 397	98.08 260	82.57 353	85.29 308	92.03 373

test20.03		84.72 354	83.99 347	86.91 376	88.19 398	80.62 393	98.88 292	95.94 369	88.36 313	78.87 381	94.62 355	68.75 363	89.11 407	66.52 404	75.82 379	91.00 381

MDA-MVSNet-bldmvs		84.09 357	81.52 364	91.81 341	91.32 381	88.00 347	98.67 314	95.92 370	80.22 386	55.60 415	93.32 372	68.29 367	93.60 391	73.76 390	76.61 377	93.82 338

lessismore_v0				90.53 352	90.58 386	80.90 391		95.80 371		77.01 390	95.84 302	66.15 376	96.95 319	83.03 351	75.05 382	93.74 343

Anonymous20240521		85.15 349	83.81 351	89.16 365	88.32 396	82.69 377	98.80 303	95.74 372	79.72 387	81.53 371	90.99 386	65.38 379	94.16 384	72.69 392	81.11 342	90.63 386

ttmdpeth		88.23 333	87.06 336	91.75 342	89.91 392	87.35 351	98.92 289	95.73 373	87.92 319	84.02 358	96.31 289	68.23 368	96.84 326	86.33 328	76.12 378	91.06 380

ITE_SJBPF				92.38 333	95.69 308	85.14 364		95.71 374	92.81 190	89.33 292	98.11 231	70.23 359	98.42 227	85.91 333	88.16 288	93.59 347

FMVSNet5		88.32 331	87.47 333	90.88 347	96.90 266	88.39 342	97.28 359	95.68 375	82.60 377	84.67 355	92.40 381	79.83 293	91.16 403	76.39 385	81.51 337	93.09 357

testgi		89.01 327	88.04 328	91.90 339	93.49 345	84.89 367	99.73 168	95.66 376	93.89 158	85.14 351	98.17 229	59.68 395	94.66 381	77.73 379	88.88 274	96.16 270

new_pmnet		84.49 356	82.92 357	89.21 364	90.03 390	82.60 378	96.89 370	95.62 377	80.59 384	75.77 396	89.17 394	65.04 381	94.79 380	72.12 394	81.02 345	90.23 388

pmmvs5		90.17 311	89.09 312	93.40 314	92.10 371	89.77 323	99.74 161	95.58 378	85.88 346	87.24 331	95.74 305	73.41 346	96.48 341	88.54 301	83.56 324	93.95 327

USDC		90.00 314	88.96 315	93.10 324	94.81 322	88.16 344	98.71 309	95.54 379	93.66 163	83.75 361	97.20 258	65.58 377	98.31 243	83.96 345	87.49 297	92.85 362

test_method		80.79 366	79.70 370	84.08 381	92.83 360	67.06 407	99.51 212	95.42 380	54.34 413	81.07 374	93.53 370	44.48 409	92.22 400	78.90 374	77.23 372	92.94 360

MIMVSNet1		82.58 362	80.51 368	88.78 368	86.68 400	84.20 371	96.65 372	95.41 381	78.75 390	78.59 384	92.44 378	51.88 405	89.76 406	65.26 407	78.95 358	92.38 370

OurMVSNet-221017-0		89.81 317	89.48 307	90.83 350	91.64 376	81.21 388	98.17 342	95.38 382	91.48 242	85.65 349	97.31 255	72.66 347	97.29 298	88.15 306	84.83 313	93.97 326

Anonymous20231206		86.32 341	85.42 344	89.02 366	89.11 395	80.53 394	99.05 272	95.28 383	85.43 353	82.82 364	93.92 366	74.40 341	93.44 392	66.99 402	81.83 335	93.08 358

new-patchmatchnet		81.19 364	79.34 371	86.76 377	82.86 408	80.36 395	97.92 349	95.27 384	82.09 379	72.02 400	86.87 403	62.81 388	90.74 405	71.10 395	63.08 407	89.19 401

OpenMVS_ROB	79.82 20	83.77 360	81.68 363	90.03 359	88.30 397	82.82 376	98.46 324	95.22 385	73.92 403	76.00 394	91.29 385	55.00 400	96.94 320	68.40 400	88.51 284	90.34 387

test_0402		85.58 344	83.94 349	90.50 353	93.81 340	85.04 365	98.55 319	95.20 386	76.01 395	79.72 380	95.13 337	64.15 383	96.26 351	66.04 406	86.88 299	90.21 389

SixPastTwentyTwo		88.73 328	88.01 329	90.88 347	91.85 374	82.24 381	98.22 340	95.18 387	88.97 297	82.26 366	96.89 270	71.75 351	96.67 335	84.00 343	82.98 325	93.72 344

Gipuma		66.95 382	65.00 382	72.79 394	91.52 378	67.96 406	66.16 417	95.15 388	47.89 415	58.54 412	67.99 417	29.74 414	87.54 411	50.20 416	77.83 366	62.87 417
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
mmtdpeth		88.52 329	87.75 331	90.85 349	95.71 305	83.47 375	98.94 284	94.85 389	88.78 304	97.19 168	89.58 392	63.29 385	98.97 190	98.54 101	62.86 408	90.10 391

MVStest1		85.03 350	82.76 359	91.83 340	92.95 358	89.16 331	98.57 318	94.82 390	71.68 406	68.54 406	95.11 339	83.17 262	95.66 366	74.69 389	65.32 403	90.65 385

LF4IMVS		89.25 326	88.85 316	90.45 355	92.81 362	81.19 389	98.12 343	94.79 391	91.44 244	86.29 343	97.11 260	65.30 380	98.11 258	88.53 302	85.25 309	92.07 371

FPMVS		68.72 377	68.72 378	68.71 399	65.95 422	44.27 428	95.97 386	94.74 392	51.13 414	53.26 416	90.50 390	25.11 419	83.00 415	60.80 410	80.97 347	78.87 412

pmmvs-eth3d		84.03 358	81.97 362	90.20 357	84.15 405	87.09 353	98.10 345	94.73 393	83.05 372	74.10 399	87.77 401	65.56 378	94.01 385	81.08 363	69.24 393	89.49 398

test_fmvs2		89.47 322	89.70 299	88.77 370	94.54 327	75.74 398	99.83 134	94.70 394	94.71 113	91.08 260	96.82 277	54.46 401	97.78 277	92.87 244	88.27 286	92.80 363

TDRefinement		84.76 352	82.56 360	91.38 345	74.58 418	84.80 369	97.36 358	94.56 395	84.73 360	80.21 377	96.12 298	63.56 384	98.39 232	87.92 309	63.97 406	90.95 383

ambc				83.23 383	77.17 416	62.61 409	87.38 412	94.55 396		76.72 392	86.65 404	30.16 413	96.36 346	84.85 340	69.86 390	90.73 384

WB-MVS		76.28 373	77.28 375	73.29 393	81.18 410	54.68 418	97.87 351	94.19 397	81.30 381	69.43 404	90.70 389	77.02 314	82.06 416	35.71 421	68.11 398	83.13 407

TinyColmap		87.87 337	86.51 338	91.94 338	95.05 319	85.57 362	97.65 354	94.08 398	84.40 363	81.82 369	96.85 273	62.14 390	98.33 241	80.25 367	86.37 302	91.91 375

SSC-MVS		75.42 374	76.40 377	72.49 397	80.68 412	53.62 419	97.42 356	94.06 399	80.42 385	68.75 405	90.14 391	76.54 321	81.66 417	33.25 422	66.34 402	82.19 408

TransMVSNet (Re)		87.25 338	85.28 345	93.16 321	93.56 343	91.03 293	98.54 321	94.05 400	83.69 368	81.09 373	96.16 294	75.32 332	96.40 344	76.69 384	68.41 396	92.06 372

Baseline_NR-MVSNet		90.33 305	89.51 305	92.81 330	92.84 359	89.95 320	99.77 149	93.94 401	84.69 361	89.04 300	95.66 309	81.66 271	96.52 339	90.99 268	76.98 374	91.97 374

EGC-MVSNET		69.38 375	63.76 385	86.26 378	90.32 388	81.66 387	96.24 380	93.85 402	0.99 425	3.22 426	92.33 382	52.44 403	92.92 396	59.53 412	84.90 312	84.21 406

LCM-MVSNet		67.77 380	64.73 383	76.87 390	62.95 424	56.25 417	89.37 411	93.74 403	44.53 416	61.99 408	80.74 410	20.42 423	86.53 413	69.37 399	59.50 413	87.84 402

APD_test1		81.15 365	80.92 366	81.86 385	92.45 365	59.76 414	96.04 384	93.61 404	73.29 404	77.06 389	96.64 280	44.28 410	96.16 354	72.35 393	82.52 328	89.67 396

test_fmvs3		79.99 370	80.17 369	79.45 387	84.02 406	62.83 408	99.05 272	93.49 405	88.29 315	80.06 379	86.65 404	28.09 416	88.00 408	88.63 298	73.27 385	87.54 404

mvs5depth		84.87 351	82.90 358	90.77 351	85.59 403	84.84 368	91.10 407	93.29 406	83.14 371	85.07 353	94.33 363	62.17 389	97.32 293	78.83 375	72.59 387	90.14 390

test_f		78.40 372	77.59 374	80.81 386	80.82 411	62.48 411	96.96 368	93.08 407	83.44 369	74.57 398	84.57 408	27.95 417	92.63 397	84.15 341	72.79 386	87.32 405

Patchmatch-RL test		86.90 339	85.98 343	89.67 361	84.45 404	75.59 399	89.71 410	92.43 408	86.89 335	77.83 388	90.94 387	94.22 90	93.63 390	87.75 311	69.61 391	99.79 100

mvsany_test3		82.12 363	81.14 365	85.06 380	81.87 409	70.41 404	97.09 364	92.14 409	91.27 251	77.84 387	88.73 396	39.31 411	95.49 367	90.75 275	71.24 388	89.29 400

pmmvs3		80.27 368	77.77 373	87.76 375	80.32 413	82.43 380	98.23 339	91.97 410	72.74 405	78.75 382	87.97 400	57.30 399	90.99 404	70.31 396	62.37 409	89.87 393

LCM-MVSNet-Re		92.31 263	92.60 243	91.43 344	97.53 232	79.27 396	99.02 277	91.83 411	92.07 223	80.31 376	94.38 362	83.50 258	95.48 368	97.22 157	97.58 174	99.54 151

PM-MVS		80.47 367	78.88 372	85.26 379	83.79 407	72.22 402	95.89 387	91.08 412	85.71 350	76.56 393	88.30 397	36.64 412	93.90 387	82.39 355	69.57 392	89.66 397

door								90.31 413

dmvs_testset		83.79 359	86.07 341	76.94 389	92.14 369	48.60 424	96.75 371	90.27 414	89.48 287	78.65 383	98.55 211	79.25 297	86.65 412	66.85 403	82.69 327	95.57 272

DSMNet-mixed		88.28 332	88.24 326	88.42 372	89.64 393	75.38 400	98.06 346	89.86 415	85.59 351	88.20 316	92.14 383	76.15 327	91.95 401	78.46 376	96.05 206	97.92 246

door-mid								89.69 416

PMVS	49.05 23	53.75 385	51.34 389	60.97 402	40.80 428	34.68 429	74.82 416	89.62 417	37.55 418	28.67 424	72.12 413	7.09 428	81.63 418	43.17 419	68.21 397	66.59 416
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		65.23 383	62.94 386	72.13 398	44.90 427	50.03 423	81.05 414	89.42 418	38.45 417	48.51 419	99.90 18	54.09 402	78.70 419	91.84 257	18.26 421	87.64 403

PMMVS2		67.15 381	64.15 384	76.14 391	70.56 421	62.07 412	93.89 394	87.52 419	58.09 410	60.02 409	78.32 411	22.38 420	84.54 414	59.56 411	47.03 416	81.80 409

testf1		68.38 378	66.92 379	72.78 395	78.80 414	50.36 421	90.95 408	87.35 420	55.47 411	58.95 410	88.14 398	20.64 421	87.60 409	57.28 413	64.69 404	80.39 410

APD_test2		68.38 378	66.92 379	72.78 395	78.80 414	50.36 421	90.95 408	87.35 420	55.47 411	58.95 410	88.14 398	20.64 421	87.60 409	57.28 413	64.69 404	80.39 410

test_vis1_rt		86.87 340	86.05 342	89.34 363	96.12 285	78.07 397	99.87 108	83.54 422	92.03 226	78.21 386	89.51 393	45.80 408	99.91 92	96.25 176	93.11 255	90.03 392

ANet_high		56.10 384	52.24 387	67.66 400	49.27 426	56.82 416	83.94 413	82.02 423	70.47 407	33.28 423	64.54 418	17.23 425	69.16 421	45.59 418	23.85 420	77.02 413

MVE	53.74 22	51.54 387	47.86 391	62.60 401	59.56 425	50.93 420	79.41 415	77.69 424	35.69 420	36.27 422	61.76 421	5.79 430	69.63 420	37.97 420	36.61 417	67.24 415
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		52.30 386	52.18 388	52.67 403	71.51 419	45.40 425	93.62 397	76.60 425	36.01 419	43.50 420	64.13 419	27.11 418	67.31 422	31.06 423	26.06 418	45.30 421

EMVS		51.44 388	51.22 390	52.11 404	70.71 420	44.97 427	94.04 393	75.66 426	35.34 421	42.40 421	61.56 422	28.93 415	65.87 423	27.64 424	24.73 419	45.49 420

test_vis3_rt		68.82 376	66.69 381	75.21 392	76.24 417	60.41 413	96.44 375	68.71 427	75.13 400	50.54 418	69.52 416	16.42 426	96.32 348	80.27 366	66.92 401	68.89 414

N_pmnet		80.06 369	80.78 367	77.89 388	91.94 372	45.28 426	98.80 303	56.82 428	78.10 392	80.08 378	93.33 371	77.03 313	95.76 365	68.14 401	82.81 326	92.64 364

testmvs		40.60 389	44.45 392	29.05 406	19.49 430	14.11 432	99.68 182	18.47 429	20.74 422	64.59 407	98.48 216	10.95 427	17.09 426	56.66 415	11.01 422	55.94 419

test123		37.68 390	39.14 393	33.31 405	19.94 429	24.83 431	98.36 332	9.75 430	15.53 423	51.31 417	87.14 402	19.62 424	17.74 425	47.10 417	3.47 424	57.36 418

wuyk23d		20.37 392	20.84 395	18.99 407	65.34 423	27.73 430	50.43 418	7.67 431	9.50 424	8.01 425	6.34 425	6.13 429	26.24 424	23.40 425	10.69 423	2.99 422

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.02 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		7.60 394	10.13 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	91.20 164	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

n2								0.00 432

nn								0.00 432

ab-mvs-re		8.28 393	11.04 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	99.40 128	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						90.97 294								86.10 332

PC_three_1452									96.96 47	99.80 17	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

eth-test2					0.00 431

eth-test					0.00 431

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 35				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

test_0728_THIRD									96.48 63	99.83 13	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 137

test_part2					99.89 45	99.25 18				99.49 63

sam_mvs1												94.72 69				99.59 137

sam_mvs												94.25 89

test_post1							95.78 388				59.23 423	93.20 122	97.74 278	91.06 266

test_post											63.35 420	94.43 77	98.13 257

patchmatchnet-post											91.70 384	95.12 54	97.95 269

gm-plane-assit					96.97 260	93.76 230			91.47 243		98.96 168		98.79 200	94.92 197

test9_res														99.71 36	99.99 21	100.00 1

agg_prior2														99.48 46	100.00 1	100.00 1

test_prior4						98.05 70	99.94 71

test_prior2							99.95 54		95.78 83	99.73 33	99.76 66	96.00 37		99.78 27	100.00 1

旧先验2							99.46 223		94.21 139	99.85 9			99.95 73	96.96 166

新几何2							99.40 227

原ACMM2							99.90 93

testdata2													99.99 36	90.54 279

segment_acmp												96.68 29

testdata1							99.28 247		96.35 73

plane_prior7					95.71 305	91.59 288

plane_prior6					95.76 299	91.72 283						80.47 289

plane_prior4											98.59 204

plane_prior3						91.64 286			96.63 60	93.01 239

plane_prior2							99.84 127		96.38 69

plane_prior1					95.73 302

plane_prior						91.74 280	99.86 119		96.76 55						89.59 266

HQP5-MVS						91.85 276

HQP-NCC					95.78 295		99.87 108		96.82 51	93.37 234

ACMP_Plane					95.78 295		99.87 108		96.82 51	93.37 234

BP-MVS														97.92 134

HQP4-MVS										93.37 234			98.39 232			94.53 274

HQP2-MVS												80.65 285

NP-MVS					95.77 298	91.79 278					98.65 199

MDTV_nov1_ep13_2view						96.26 145	96.11 382		91.89 229	98.06 142		94.40 79		94.30 215		99.67 118

ACMMP++_ref															87.04 298

ACMMP++															88.23 287

Test By Simon												92.82 133

High-resolution multi-view benchmark