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 80	99.36 101	97.18 115	99.93 85	99.90 1	96.81 61	98.67 122	99.77 64	93.92 101	99.89 106	99.27 63	99.94 55	99.96 67

MVS_111021_LR		98.42 47	98.38 37	98.53 120	99.39 99	95.79 171	99.87 117	99.86 2	96.70 64	98.78 114	99.79 58	92.03 157	99.90 101	99.17 67	99.86 75	99.88 89

CHOSEN 1792x2688		96.81 139	96.53 138	97.64 176	98.91 138	93.07 255	99.65 195	99.80 3	95.64 94	95.39 221	98.86 191	84.35 260	99.90 101	96.98 173	99.16 132	99.95 74

HyFIR lowres test		96.66 150	96.43 142	97.36 196	99.05 117	93.91 236	99.70 188	99.80 3	90.54 280	96.26 204	98.08 242	92.15 154	98.23 261	96.84 179	95.46 230	99.93 79

test2506		97.53 102	97.19 108	98.58 113	98.66 155	96.90 129	98.81 312	99.77 5	94.93 110	97.95 153	98.96 175	92.51 144	99.20 186	94.93 205	98.15 167	99.64 126

MM		98.83 21	98.53 30	99.76 10	99.59 85	99.33 8	99.99 5	99.76 6	98.39 4	99.39 81	99.80 54	90.49 185	99.96 67	99.89 17	99.43 117	99.98 51

thres100view900		96.74 145	95.92 164	99.18 54	98.90 139	98.77 42	99.74 170	99.71 7	92.59 215	95.84 213	98.86 191	89.25 202	99.50 166	93.84 232	94.57 244	99.27 197

tfpn200view9		96.79 140	95.99 154	99.19 53	98.94 129	98.82 37	99.78 155	99.71 7	92.86 197	96.02 209	98.87 189	89.33 200	99.50 166	93.84 232	94.57 244	99.27 197

thres600view7		96.69 148	95.87 167	99.14 64	98.90 139	98.78 41	99.74 170	99.71 7	92.59 215	95.84 213	98.86 191	89.25 202	99.50 166	93.44 245	94.50 247	99.16 204

thres400		96.78 142	95.99 154	99.16 60	98.94 129	98.82 37	99.78 155	99.71 7	92.86 197	96.02 209	98.87 189	89.33 200	99.50 166	93.84 232	94.57 244	99.16 204

thres200		96.96 132	96.21 149	99.22 50	98.97 127	98.84 36	99.85 131	99.71 7	93.17 186	96.26 204	98.88 186	89.87 193	99.51 164	94.26 225	94.91 240	99.31 190

PVSNet	91.05 13	97.13 122	96.69 132	98.45 126	99.52 92	95.81 170	99.95 61	99.65 12	94.73 119	99.04 102	99.21 153	84.48 258	99.95 76	94.92 206	98.74 150	99.58 146

PVSNet_0	88.03 19	91.80 284	90.27 298	96.38 226	98.27 188	90.46 318	99.94 78	99.61 13	93.99 156	86.26 355	97.39 264	71.13 366	99.89 106	98.77 95	67.05 411	98.79 229

WTY-MVS		98.10 68	97.60 87	99.60 22	98.92 134	99.28 17	99.89 111	99.52 14	95.58 96	98.24 146	99.39 137	93.33 117	99.74 144	97.98 141	95.58 229	99.78 105

HY-MVS	92.50 7	97.79 89	97.17 110	99.63 17	98.98 126	99.32 9	97.49 366	99.52 14	95.69 93	98.32 140	97.41 262	93.32 118	99.77 138	98.08 135	95.75 226	99.81 99

EPNet		98.49 40	98.40 35	98.77 96	99.62 84	96.80 133	99.90 102	99.51 16	97.60 28	99.20 91	99.36 140	93.71 109	99.91 99	97.99 139	98.71 151	99.61 137
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PGM-MVS		98.34 52	98.13 55	98.99 81	99.92 31	97.00 124	99.75 167	99.50 17	93.90 163	99.37 82	99.76 66	93.24 123	100.00 1	97.75 156	99.96 46	99.98 51

ACMMP		97.74 93	97.44 95	98.66 104	99.92 31	96.13 162	99.18 267	99.45 18	94.84 116	96.41 201	99.71 89	91.40 164	99.99 36	97.99 139	98.03 174	99.87 91
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	99.64 199	99.44 19	97.33 38	99.00 104	99.72 86	94.03 99	99.98 47	98.73 98	100.00 1	100.00 1

EPMVS		96.53 154	96.01 153	98.09 148	98.43 175	96.12 164	96.36 387	99.43 20	93.53 174	97.64 164	95.04 352	94.41 80	98.38 245	91.13 274	98.11 170	99.75 108

CHOSEN 280x420		99.01 14	99.03 10	98.95 86	99.38 100	98.87 33	98.46 335	99.42 21	97.03 51	99.02 103	99.09 159	99.35 2	98.21 262	99.73 38	99.78 84	99.77 106

D2MVS		92.76 262	92.59 257	93.27 328	95.13 326	89.54 336	99.69 189	99.38 22	92.26 229	87.59 334	94.61 367	85.05 253	97.79 284	91.59 269	88.01 299	92.47 379

sss		97.57 101	97.03 115	99.18 54	98.37 179	98.04 76	99.73 177	99.38 22	93.46 176	98.76 118	99.06 162	91.21 166	99.89 106	96.33 183	97.01 196	99.62 133

PAPM		98.60 33	98.42 34	99.14 64	96.05 298	98.96 26	99.90 102	99.35 24	96.68 65	98.35 139	99.66 104	96.45 33	98.51 229	99.45 55	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 5	99.34 25	98.70 2	99.44 73	99.75 74	93.24 123	99.99 36	99.94 11	99.41 119	99.95 74

UGNet		95.33 194	94.57 203	97.62 179	98.55 164	94.85 208	98.67 325	99.32 26	95.75 92	96.80 190	96.27 301	72.18 359	99.96 67	94.58 218	99.05 139	98.04 251
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 82	97.37 99	99.21 51	99.18 108	97.98 79	99.64 199	99.27 27	91.43 255	97.88 158	98.99 169	95.84 42	99.84 126	98.82 91	95.32 235	99.79 102

DCV-MVSNet		97.83 82	97.37 99	99.21 51	99.18 108	97.98 79	99.64 199	99.27 27	91.43 255	97.88 158	98.99 169	95.84 42	99.84 126	98.82 91	95.32 235	99.79 102

testing3-2		97.72 96	97.43 97	98.60 109	98.55 164	97.11 120	100.00 1	99.23 29	93.78 167	97.90 155	98.73 200	95.50 49	99.69 152	98.53 111	94.63 242	98.99 219

VNet		97.21 119	96.57 137	99.13 68	98.97 127	97.82 86	99.03 286	99.21 30	94.31 140	99.18 94	98.88 186	86.26 241	99.89 106	98.93 82	94.32 248	99.69 117

testing3		93.92 231	94.23 211	92.99 336	97.54 241	90.23 322	99.99 5	99.16 31	90.57 279	91.33 269	98.63 211	92.99 129	92.52 409	82.46 365	95.39 233	96.22 279

PVSNet_BlendedMVS		96.05 171	95.82 168	96.72 215	99.59 85	96.99 125	99.95 61	99.10 32	94.06 153	98.27 142	95.80 313	89.00 207	99.95 76	99.12 68	87.53 306	93.24 366

PVSNet_Blended		97.94 73	97.64 85	98.83 91	99.59 85	96.99 125	100.00 1	99.10 32	95.38 101	98.27 142	99.08 160	89.00 207	99.95 76	99.12 68	99.25 128	99.57 148

UniMVSNet_NR-MVSNet		92.95 258	92.11 264	95.49 246	94.61 336	95.28 195	99.83 143	99.08 34	91.49 250	89.21 306	96.86 282	87.14 228	96.73 342	93.20 247	77.52 379	94.46 289

CSCG		97.10 123	97.04 114	97.27 200	99.89 45	91.92 284	99.90 102	99.07 35	88.67 318	95.26 224	99.82 49	93.17 126	99.98 47	98.15 130	99.47 112	99.90 87

PatchMatch-RL		96.04 172	95.40 178	97.95 154	99.59 85	95.22 199	99.52 219	99.07 35	93.96 158	96.49 197	98.35 231	82.28 273	99.82 130	90.15 296	99.22 131	98.81 228

VPA-MVSNet		92.70 264	91.55 276	96.16 231	95.09 327	96.20 158	98.88 303	99.00 37	91.02 269	91.82 264	95.29 343	76.05 338	97.96 277	95.62 196	81.19 350	94.30 303

SDMVSNet		94.80 205	93.96 219	97.33 198	98.92 134	95.42 189	99.59 206	98.99 38	92.41 224	92.55 257	97.85 253	75.81 339	98.93 203	97.90 145	91.62 269	97.64 259

CVMVSNet		94.68 212	94.94 196	93.89 312	96.80 281	86.92 365	99.06 279	98.98 39	94.45 128	94.23 237	99.02 164	85.60 245	95.31 382	90.91 281	95.39 233	99.43 174

UniMVSNet (Re)		93.07 256	92.13 263	95.88 238	94.84 331	96.24 157	99.88 114	98.98 39	92.49 222	89.25 303	95.40 333	87.09 229	97.14 313	93.13 251	78.16 374	94.26 305

fmvsm_s_conf0.5_n		97.80 87	97.85 76	97.67 174	99.06 116	94.41 220	99.98 17	98.97 41	97.34 36	99.63 51	99.69 94	87.27 226	99.97 57	99.62 46	99.06 138	98.62 237

h-mvs33		94.92 202	94.36 207	96.59 219	98.85 143	91.29 300	98.93 297	98.94 42	95.90 87	98.77 115	98.42 229	90.89 178	99.77 138	97.80 149	70.76 400	98.72 234

tfpnnormal		89.29 336	87.61 343	94.34 294	94.35 341	94.13 230	98.95 294	98.94 42	83.94 375	84.47 367	95.51 327	74.84 348	97.39 297	77.05 394	80.41 361	91.48 389

MVS		96.60 151	95.56 176	99.72 13	96.85 278	99.22 20	98.31 344	98.94 42	91.57 248	90.90 273	99.61 112	86.66 236	99.96 67	97.36 162	99.88 73	99.99 23

WR-MVS_H		91.30 291	90.35 295	94.15 298	94.17 345	92.62 270	99.17 268	98.94 42	88.87 313	86.48 351	94.46 372	84.36 259	96.61 347	88.19 315	78.51 372	93.21 367

FIs		94.10 229	93.43 233	96.11 232	94.70 334	96.82 131	99.58 208	98.93 46	92.54 218	89.34 301	97.31 265	87.62 222	97.10 317	94.22 227	86.58 310	94.40 295

fmvsm_s_conf0.5_n_a		97.73 95	97.72 79	97.77 168	98.63 159	94.26 226	99.96 42	98.92 47	97.18 46	99.75 34	99.69 94	87.00 231	99.97 57	99.46 54	98.89 143	99.08 213

test_fmvsm_n_1920		98.44 44	98.61 27	97.92 158	99.27 106	95.18 201	100.00 1	98.90 48	98.05 15	99.80 22	99.73 83	92.64 139	99.99 36	99.58 48	99.51 109	98.59 238

EPNet_dtu		95.71 182	95.39 179	96.66 217	98.92 134	93.41 250	99.57 211	98.90 48	96.19 84	97.52 166	98.56 218	92.65 138	97.36 298	77.89 389	98.33 159	99.20 202
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
patch_mono-2		98.24 63	99.12 5	95.59 245	99.67 81	86.91 366	99.95 61	98.89 50	97.60 28	99.90 3	99.76 66	96.54 32	99.98 47	99.94 11	99.82 81	99.88 89

FC-MVSNet-test		93.81 235	93.15 242	95.80 242	94.30 342	96.20 158	99.42 236	98.89 50	92.33 228	89.03 311	97.27 267	87.39 225	96.83 338	93.20 247	86.48 311	94.36 297

baseline2		96.71 147	96.49 139	97.37 194	95.63 321	95.96 167	99.74 170	98.88 52	92.94 194	91.61 265	98.97 173	97.72 6	98.62 224	94.83 210	98.08 173	97.53 265

API-MVS		97.86 78	97.66 83	98.47 124	99.52 92	95.41 190	99.47 229	98.87 53	91.68 246	98.84 110	99.85 33	92.34 150	99.99 36	98.44 116	99.96 46	100.00 1

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 47	99.17 110	97.81 87	99.98 17	98.86 54	98.25 5	99.90 3	99.76 66	94.21 94	99.97 57	99.87 19	99.52 106	99.98 51

1314		96.84 138	95.96 160	99.48 34	96.74 285	98.52 58	98.31 344	98.86 54	95.82 89	89.91 284	98.98 171	87.49 223	99.96 67	97.80 149	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 17	98.86 54	97.10 47	99.80 22	99.94 4	95.92 40	100.00 1	99.51 50	100.00 1	100.00 1

reproduce_monomvs		95.38 192	95.07 191	96.32 228	99.32 104	96.60 139	99.76 163	98.85 57	96.65 66	87.83 331	96.05 310	99.52 1	98.11 267	96.58 181	81.07 355	94.25 307

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 46	99.21 107	97.91 84	99.98 17	98.85 57	98.25 5	99.92 2	99.75 74	94.72 71	99.97 57	99.87 19	99.64 92	99.95 74

sd_testset		93.55 244	92.83 247	95.74 243	98.92 134	90.89 308	98.24 348	98.85 57	92.41 224	92.55 257	97.85 253	71.07 367	98.68 221	93.93 229	91.62 269	97.64 259

AdaColmap		97.23 118	96.80 126	98.51 122	99.99 1	95.60 183	99.09 272	98.84 60	93.32 181	96.74 191	99.72 86	86.04 242	100.00 1	98.01 137	99.43 117	99.94 78

test_fmvsmconf_n		98.43 46	98.32 43	98.78 94	98.12 201	96.41 146	99.99 5	98.83 61	98.22 7	99.67 45	99.64 107	91.11 171	99.94 84	99.67 43	99.62 95	99.98 51

fmvsm_s_conf0.5_n_3		97.95 72	97.66 83	98.81 92	98.99 124	98.07 73	99.98 17	98.81 62	98.18 9	99.89 6	99.70 91	84.15 261	99.97 57	99.76 33	99.50 111	98.39 242

IB-MVS	92.85 6	94.99 201	93.94 220	98.16 142	97.72 228	95.69 179	99.99 5	98.81 62	94.28 143	92.70 255	96.90 279	95.08 58	99.17 189	96.07 187	73.88 394	99.60 139
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	96.28 167	95.34 181	99.08 73	96.82 280	97.47 104	99.45 234	98.81 62	95.52 99	89.39 299	99.00 168	81.97 275	99.95 76	97.27 164	99.83 77	99.84 95

PHI-MVS		98.41 48	98.21 48	99.03 76	99.86 53	97.10 121	99.98 17	98.80 65	90.78 276	99.62 54	99.78 62	95.30 53	100.00 1	99.80 25	99.93 61	99.99 23

fmvsm_s_conf0.5_n_4		97.75 92	97.86 75	97.42 190	99.01 119	94.69 214	99.97 34	98.76 66	97.91 19	99.87 9	99.76 66	86.70 235	99.93 92	99.67 43	99.12 136	97.64 259

MAR-MVS		97.43 105	97.19 108	98.15 145	99.47 96	94.79 212	99.05 283	98.76 66	92.65 211	98.66 123	99.82 49	88.52 213	99.98 47	98.12 131	99.63 94	99.67 120
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		92.46 270	91.45 279	95.49 246	94.05 346	95.28 195	99.81 148	98.74 68	92.25 230	89.21 306	96.64 290	81.66 280	96.73 342	93.20 247	77.52 379	94.46 289

tt0805		91.28 293	90.18 301	94.60 278	96.26 293	87.55 358	98.39 342	98.72 69	89.00 306	89.22 305	98.47 226	62.98 398	98.96 201	90.57 287	88.00 300	97.28 268

无先验							99.49 225	98.71 70	93.46 176				100.00 1	94.36 221		99.99 23

NR-MVSNet		91.56 289	90.22 299	95.60 244	94.05 346	95.76 173	98.25 347	98.70 71	91.16 264	80.78 386	96.64 290	83.23 269	96.57 348	91.41 270	77.73 378	94.46 289

FE-MVS		95.70 184	95.01 194	97.79 165	98.21 192	94.57 215	95.03 401	98.69 72	88.90 312	97.50 168	96.19 303	92.60 141	99.49 171	89.99 298	97.94 176	99.31 190

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 17	98.69 72	98.20 8	99.93 1	99.98 2	96.82 24	100.00 1	99.75 34	100.00 1	99.99 23

WR-MVS		92.31 273	91.25 281	95.48 249	94.45 339	95.29 194	99.60 205	98.68 74	90.10 289	88.07 328	96.89 280	80.68 294	96.80 340	93.14 250	79.67 367	94.36 297

ab-mvs		94.69 210	93.42 234	98.51 122	98.07 203	96.26 153	96.49 385	98.68 74	90.31 286	94.54 229	97.00 277	76.30 334	99.71 148	95.98 189	93.38 262	99.56 149

QAPM		95.40 191	94.17 213	99.10 70	96.92 272	97.71 90	99.40 237	98.68 74	89.31 300	88.94 312	98.89 185	82.48 272	99.96 67	93.12 252	99.83 77	99.62 133

Anonymous20240529		92.10 277	90.65 289	96.47 220	98.82 144	90.61 314	98.72 319	98.67 77	75.54 409	93.90 241	98.58 216	66.23 385	99.90 101	94.70 215	90.67 272	98.90 224

test_prior				99.43 35	99.94 13	98.49 60		98.65 78					99.80 131			99.99 23

TranMVSNet+NR-MVSNet		91.68 288	90.61 291	94.87 267	93.69 353	93.98 234	99.69 189	98.65 78	91.03 268	88.44 321	96.83 286	80.05 302	96.18 363	90.26 295	76.89 387	94.45 294

fmvsm_s_conf0.5_n_6		98.27 57	97.96 68	99.23 49	97.66 234	98.11 71	99.98 17	98.64 80	97.85 21	99.87 9	99.72 86	88.86 209	99.93 92	99.64 45	99.36 123	99.63 132

fmvsm_l_conf0.5_n_3		98.41 48	98.08 59	99.39 40	99.12 113	98.29 64	99.98 17	98.64 80	98.14 12	99.86 11	99.76 66	87.99 218	99.97 57	99.72 39	99.54 104	99.91 86

fmvsm_s_conf0.1_n		97.30 113	97.21 107	97.60 180	97.38 251	94.40 222	99.90 102	98.64 80	96.47 72	99.51 69	99.65 106	84.99 254	99.93 92	99.22 65	99.09 137	98.46 239

旧先验1					99.76 66	97.52 99		98.64 80			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 34	98.64 80	98.47 3	99.13 96	99.92 13	96.38 34	100.00 1	99.74 36	100.00 1	100.00 1

PVSNet_Blended_VisFu		97.27 115	96.81 125	98.66 104	98.81 145	96.67 136	99.92 88	98.64 80	94.51 127	96.38 202	98.49 222	89.05 206	99.88 112	97.10 169	98.34 158	99.43 174

新几何1				99.42 37	99.75 69	98.27 65		98.63 86	92.69 208	99.55 62	99.82 49	94.40 81	100.00 1	91.21 272	99.94 55	99.99 23

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 34	98.62 87	98.02 17	99.90 3	99.95 3	97.33 17	100.00 1	99.54 49	100.00 1	100.00 1

testing222		97.08 128	96.75 128	98.06 150	98.56 161	96.82 131	99.85 131	98.61 88	92.53 219	98.84 110	98.84 195	93.36 115	98.30 253	95.84 192	94.30 249	99.05 215

HFP-MVS		98.56 35	98.37 39	99.14 64	99.96 8	97.43 105	99.95 61	98.61 88	94.77 117	99.31 85	99.85 33	94.22 92	100.00 1	98.70 99	99.98 32	99.98 51

UWE-MVS		96.79 140	96.72 130	97.00 205	98.51 169	93.70 241	99.71 184	98.60 90	92.96 193	97.09 180	98.34 233	96.67 31	98.85 206	92.11 262	96.50 204	98.44 240

ACMMPR		98.50 39	98.32 43	99.05 74	99.96 8	97.18 115	99.95 61	98.60 90	94.77 117	99.31 85	99.84 44	93.73 108	100.00 1	98.70 99	99.98 32	99.98 51

fmvsm_s_conf0.5_n_2		97.59 100	97.28 103	98.53 120	99.01 119	98.15 66	99.98 17	98.59 92	98.17 10	99.75 34	99.63 110	81.83 278	99.94 84	99.78 28	98.79 149	97.51 266

VPNet		91.81 281	90.46 292	95.85 240	94.74 333	95.54 185	98.98 290	98.59 92	92.14 231	90.77 275	97.44 261	68.73 374	97.54 294	94.89 209	77.89 376	94.46 289

test0.0.03 1		93.86 232	93.61 225	94.64 276	95.02 330	92.18 278	99.93 85	98.58 94	94.07 151	87.96 329	98.50 221	93.90 103	94.96 386	81.33 372	93.17 263	96.78 271

DELS-MVS		98.54 36	98.22 47	99.50 30	99.15 112	98.65 53	100.00 1	98.58 94	97.70 26	98.21 147	99.24 151	92.58 142	99.94 84	98.63 106	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
fmvsm_s_conf0.5_n_5		98.08 69	97.71 81	99.17 57	98.67 153	97.69 94	99.99 5	98.57 96	97.40 34	99.89 6	99.69 94	85.99 243	99.96 67	99.80 25	99.40 120	99.85 94

UWE-MVS-28		95.95 174	96.49 139	94.34 294	98.51 169	89.99 328	99.39 241	98.57 96	93.14 188	97.33 173	98.31 236	93.44 113	94.68 391	93.69 242	95.98 216	98.34 245

ETVMVS		97.03 129	96.64 133	98.20 141	98.67 153	97.12 119	99.89 111	98.57 96	91.10 266	98.17 148	98.59 213	93.86 105	98.19 263	95.64 195	95.24 237	99.28 196

CP-MVSNet		91.23 295	90.22 299	94.26 296	93.96 348	92.39 274	99.09 272	98.57 96	88.95 310	86.42 352	96.57 293	79.19 309	96.37 355	90.29 294	78.95 369	94.02 330

OpenMVS	90.15 15	94.77 208	93.59 228	98.33 134	96.07 297	97.48 103	99.56 213	98.57 96	90.46 281	86.51 349	98.95 180	78.57 316	99.94 84	93.86 231	99.74 86	97.57 264

hse-mvs2		94.38 222	94.08 215	95.31 255	98.27 188	90.02 327	99.29 257	98.56 101	95.90 87	98.77 115	98.00 245	90.89 178	98.26 260	97.80 149	69.20 406	97.64 259

AUN-MVS		93.28 249	92.60 253	95.34 253	98.29 185	90.09 326	99.31 252	98.56 101	91.80 244	96.35 203	98.00 245	89.38 199	98.28 256	92.46 257	69.22 405	97.64 259

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 61	98.56 101	97.56 31	99.44 73	99.85 33	95.38 52	100.00 1	99.31 61	99.99 21	99.87 91

testdata				98.42 130	99.47 96	95.33 193		98.56 101	93.78 167	99.79 30	99.85 33	93.64 111	99.94 84	94.97 204	99.94 55	100.00 1

EPP-MVSNet		96.69 148	96.60 135	96.96 207	97.74 223	93.05 257	99.37 245	98.56 101	88.75 316	95.83 215	99.01 166	96.01 36	98.56 226	96.92 177	97.20 190	99.25 199

DeepPCF-MVS	95.94 2	97.71 97	98.98 12	93.92 309	99.63 83	81.76 397	99.96 42	98.56 101	99.47 1	99.19 93	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

myMVS_eth3d28		97.86 78	97.59 89	98.68 101	98.50 171	97.26 111	99.92 88	98.55 107	93.79 166	98.26 144	98.75 198	95.20 54	99.48 172	98.93 82	96.40 207	99.29 194

region2R		98.54 36	98.37 39	99.05 74	99.96 8	97.18 115	99.96 42	98.55 107	94.87 115	99.45 72	99.85 33	94.07 98	100.00 1	98.67 101	100.00 1	99.98 51

test222					99.55 90	97.41 107	99.34 248	98.55 107	91.86 240	99.27 89	99.83 46	93.84 106			99.95 50	99.99 23

tpmvs		94.28 227	93.57 229	96.40 224	98.55 164	91.50 298	95.70 400	98.55 107	87.47 335	92.15 260	94.26 375	91.42 163	98.95 202	88.15 316	95.85 222	98.76 230

thisisatest0530		97.10 123	96.72 130	98.22 140	97.60 238	96.70 134	99.92 88	98.54 111	91.11 265	97.07 182	98.97 173	97.47 12	99.03 197	93.73 240	96.09 213	98.92 221

tttt0517		96.85 137	96.49 139	97.92 158	97.48 246	95.89 169	99.85 131	98.54 111	90.72 278	96.63 193	98.93 184	97.47 12	99.02 198	93.03 253	95.76 225	98.85 225

thisisatest0515		97.41 110	97.02 116	98.59 112	97.71 230	97.52 99	99.97 34	98.54 111	91.83 241	97.45 169	99.04 163	97.50 9	99.10 194	94.75 213	96.37 209	99.16 204

kuosan		93.17 252	92.60 253	94.86 270	98.40 176	89.54 336	98.44 337	98.53 114	84.46 373	88.49 319	97.92 250	90.57 182	97.05 320	83.10 361	93.49 259	97.99 252

UBG		97.84 81	97.69 82	98.29 137	98.38 177	96.59 141	99.90 102	98.53 114	93.91 162	98.52 128	98.42 229	96.77 25	99.17 189	98.54 109	96.20 210	99.11 210

ZD-MVS					99.92 31	98.57 56		98.52 116	92.34 227	99.31 85	99.83 46	95.06 59	99.80 131	99.70 41	99.97 42

GG-mvs-BLEND				98.54 118	98.21 192	98.01 77	93.87 406	98.52 116		97.92 154	97.92 250	99.02 3	97.94 280	98.17 128	99.58 102	99.67 120

PS-CasMVS		90.63 308	89.51 315	93.99 307	93.83 350	91.70 293	98.98 290	98.52 116	88.48 322	86.15 356	96.53 295	75.46 341	96.31 359	88.83 307	78.86 371	93.95 338

dongtai		91.55 290	91.13 283	92.82 339	98.16 197	86.35 367	99.47 229	98.51 119	83.24 381	85.07 364	97.56 258	90.33 187	94.94 387	76.09 397	91.73 267	97.18 269

dmvs_re		93.20 251	93.15 242	93.34 325	96.54 289	83.81 383	98.71 320	98.51 119	91.39 259	92.37 259	98.56 218	78.66 315	97.83 283	93.89 230	89.74 273	98.38 243

CANet		98.27 57	97.82 77	99.63 17	99.72 75	99.10 23	99.98 17	98.51 119	97.00 53	98.52 128	99.71 89	87.80 219	99.95 76	99.75 34	99.38 121	99.83 96

gg-mvs-nofinetune		93.51 245	91.86 271	98.47 124	97.72 228	97.96 82	92.62 410	98.51 119	74.70 412	97.33 173	69.59 426	98.91 4	97.79 284	97.77 154	99.56 103	99.67 120

EI-MVSNet-Vis-set		98.27 57	98.11 57	98.75 97	99.83 57	96.59 141	99.40 237	98.51 119	95.29 104	98.51 130	99.76 66	93.60 112	99.71 148	98.53 111	99.52 106	99.95 74

原ACMM1				98.96 85	99.73 73	96.99 125		98.51 119	94.06 153	99.62 54	99.85 33	94.97 65	99.96 67	95.11 200	99.95 50	99.92 84

fmvsm_s_conf0.1_n_a		97.09 125	96.90 119	97.63 178	95.65 319	94.21 228	99.83 143	98.50 125	96.27 81	99.65 47	99.64 107	84.72 255	99.93 92	99.04 74	98.84 146	98.74 232

EI-MVSNet-UG-set		98.14 66	97.99 63	98.60 109	99.80 61	96.27 152	99.36 247	98.50 125	95.21 106	98.30 141	99.75 74	93.29 120	99.73 147	98.37 120	99.30 126	99.81 99

LS3D		95.84 178	95.11 189	98.02 152	99.85 54	95.10 203	98.74 317	98.50 125	87.22 340	93.66 242	99.86 29	87.45 224	99.95 76	90.94 280	99.81 83	99.02 217

PEN-MVS		90.19 320	89.06 323	93.57 321	93.06 365	90.90 307	99.06 279	98.47 128	88.11 327	85.91 358	96.30 300	76.67 328	95.94 373	87.07 330	76.91 386	93.89 343

DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 262	98.47 128	98.14 12	99.08 99	99.91 14	93.09 127	100.00 1	99.04 74	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 74	97.89 74	98.05 151	99.82 58	94.77 213	99.92 88	98.46 130	93.93 160	97.20 177	99.27 146	95.44 51	99.97 57	97.41 161	99.51 109	99.41 176
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
testing11		97.48 104	97.27 104	98.10 147	98.36 180	96.02 165	99.92 88	98.45 131	93.45 178	98.15 149	98.70 203	95.48 50	99.22 182	97.85 147	95.05 239	99.07 214

test_fmvsmvis_n_1920		97.67 98	97.59 89	97.91 160	97.02 267	95.34 192	99.95 61	98.45 131	97.87 20	97.02 183	99.59 113	89.64 195	99.98 47	99.41 58	99.34 125	98.42 241

test1111		95.57 187	94.98 195	97.37 194	98.56 161	93.37 252	98.86 307	98.45 131	94.95 109	96.63 193	98.95 180	75.21 346	99.11 192	95.02 202	98.14 169	99.64 126

ECVR-MVS		95.66 185	95.05 192	97.51 185	98.66 155	93.71 240	98.85 309	98.45 131	94.93 110	96.86 187	98.96 175	75.22 345	99.20 186	95.34 197	98.15 167	99.64 126

UA-Net		96.54 153	95.96 160	98.27 138	98.23 190	95.71 176	98.00 359	98.45 131	93.72 171	98.41 135	99.27 146	88.71 212	99.66 157	91.19 273	97.69 178	99.44 173

ZNCC-MVS		98.31 54	98.03 61	99.17 57	99.88 49	97.59 96	99.94 78	98.44 136	94.31 140	98.50 131	99.82 49	93.06 128	99.99 36	98.30 124	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 42	98.44 136	97.96 18	99.55 62	99.94 4	97.18 21	100.00 1	93.81 235	99.94 55	99.98 51

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 117	98.44 136	97.48 33	99.64 50	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 86	97.33 101	99.25 47	98.77 148	98.66 51	99.99 5	98.44 136	94.40 136	98.41 135	99.47 126	93.65 110	99.42 176	98.57 107	94.26 250	99.67 120

test11								98.44 136

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 54	98.72 150	97.71 90	99.98 17	98.44 136	96.85 56	99.80 22	99.91 14	97.57 8	99.85 118	99.44 56	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
MDTV_nov1_ep13			95.69 171		97.90 212	94.15 229	95.98 396	98.44 136	93.12 190	97.98 152	95.74 315	95.10 57	98.58 225	90.02 297	96.92 198

DP-MVS Recon		98.41 48	98.02 62	99.56 25	99.97 3	98.70 48	99.92 88	98.44 136	92.06 235	98.40 137	99.84 44	95.68 44	100.00 1	98.19 127	99.71 88	99.97 61

testing99		97.17 120	96.91 118	97.95 154	98.35 182	95.70 177	99.91 96	98.43 144	92.94 194	97.36 172	98.72 201	94.83 67	99.21 183	97.00 171	94.64 241	98.95 220

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 61	98.43 144	96.48 70	99.80 22	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 42	98.43 144	97.27 41	99.80 22	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 144	97.27 41	99.80 22	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		98.43 144	97.26 43	99.80 22	99.88 24	96.71 27	100.00 1

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 61	98.43 144					100.00 1	99.99 5	100.00 1	100.00 1

TEST9					99.92 31	98.92 29	99.96 42	98.43 144	93.90 163	99.71 41	99.86 29	95.88 41	99.85 118

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 42	98.43 144	94.35 137	99.71 41	99.86 29	95.94 38	99.85 118	99.69 42	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 42	98.43 144	94.35 137	99.69 43	99.85 33	95.94 38	99.85 118

agg_prior					99.93 24	98.77 42		98.43 144		99.63 51			99.85 118

PAPM_NR		98.12 67	97.93 71	98.70 100	99.94 13	96.13 162	99.82 146	98.43 144	94.56 125	97.52 166	99.70 91	94.40 81	99.98 47	97.00 171	99.98 32	99.99 23

PAPR		98.52 38	98.16 53	99.58 24	99.97 3	98.77 42	99.95 61	98.43 144	95.35 102	98.03 151	99.75 74	94.03 99	99.98 47	98.11 132	99.83 77	99.99 23

testing91		97.16 121	96.90 119	97.97 153	98.35 182	95.67 180	99.91 96	98.42 156	92.91 196	97.33 173	98.72 201	94.81 68	99.21 183	96.98 173	94.63 242	99.03 216

test0726					99.93 24	99.29 15	99.96 42	98.42 156	97.28 39	99.86 11	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 83	99.93 24	97.24 112	99.95 61	98.42 156	97.50 32	99.52 67	99.88 24	97.43 16	99.71 148	99.50 51	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 62	99.94 13	97.50 101	99.94 78	98.42 156	96.22 82	99.41 77	99.78 62	94.34 86	99.96 67	98.92 84	99.95 50	99.99 23

X-MVStestdata		93.83 233	92.06 266	99.15 62	99.94 13	97.50 101	99.94 78	98.42 156	96.22 82	99.41 77	41.37 435	94.34 86	99.96 67	98.92 84	99.95 50	99.99 23

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 161					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 161					100.00 1	99.96 9	100.00 1	100.00 1

test_one_0601					99.94 13	99.30 12		98.41 161	96.63 67	99.75 34	99.93 11	97.49 10

IU-MVS					99.93 24	99.31 10		98.41 161	97.71 25	99.84 17				100.00 1	100.00 1	100.00 1

save fliter					99.82 58	98.79 40	99.96 42	98.40 165	97.66 27

test12				99.43 35	99.74 70	98.56 57		98.40 165		99.65 47		94.76 69	99.75 142		99.98 32	99.99 23

PatchmatchNet		95.94 175	95.45 177	97.39 193	97.83 217	94.41 220	96.05 394	98.40 165	92.86 197	97.09 180	95.28 344	94.21 94	98.07 271	89.26 304	98.11 170	99.70 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GST-MVS		98.27 57	97.97 65	99.17 57	99.92 31	97.57 97	99.93 85	98.39 168	94.04 155	98.80 113	99.74 81	92.98 130	100.00 1	98.16 129	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 96	98.39 168	97.20 45	99.46 71	99.85 33	95.53 48	99.79 133	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 64	97.97 65	99.03 76	99.94 13	97.17 118	99.95 61	98.39 168	94.70 121	98.26 144	99.81 53	91.84 161	100.00 1	98.85 90	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 89	99.96 8	96.62 138	99.97 34	98.39 168	94.43 132	98.90 108	99.87 27	94.30 89	100.00 1	99.04 74	99.99 21	99.99 23

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 128	98.38 172	93.19 185	99.77 32	99.94 4	95.54 46	100.00 1	99.74 36	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	99.77 158	98.38 172	96.73 63	99.88 8	99.74 81	94.89 66	99.59 160	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 51	98.20 49	98.97 84	99.97 3	96.92 128	99.95 61	98.38 172	95.04 108	98.61 126	99.80 54	93.39 114	100.00 1	98.64 104	100.00 1	99.98 51

ACMMP_NAP		98.49 40	98.14 54	99.54 27	99.66 82	98.62 55	99.85 131	98.37 175	94.68 122	99.53 65	99.83 46	92.87 133	100.00 1	98.66 103	99.84 76	99.99 23

FOURS1					99.92 31	97.66 95	99.95 61	98.36 176	95.58 96	99.52 67

APD-MVS		98.62 32	98.35 42	99.41 38	99.90 42	98.51 59	99.87 117	98.36 176	94.08 150	99.74 37	99.73 83	94.08 97	99.74 144	99.42 57	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Syy-MVS		90.00 324	90.63 290	88.11 385	97.68 231	74.66 412	99.71 184	98.35 178	90.79 274	92.10 261	98.67 205	79.10 311	93.09 405	63.35 419	95.95 219	96.59 274

myMVS_eth3d		94.46 220	94.76 200	93.55 322	97.68 231	90.97 303	99.71 184	98.35 178	90.79 274	92.10 261	98.67 205	92.46 147	93.09 405	87.13 329	95.95 219	96.59 274

SR-MVS		98.46 42	98.30 46	98.93 87	99.88 49	97.04 123	99.84 136	98.35 178	94.92 112	99.32 84	99.80 54	93.35 116	99.78 135	99.30 62	99.95 50	99.96 67

CPTT-MVS		97.64 99	97.32 102	98.58 113	99.97 3	95.77 172	99.96 42	98.35 178	89.90 294	98.36 138	99.79 58	91.18 170	99.99 36	98.37 120	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 78	98.34 182	96.38 76	99.81 20	99.76 66	94.59 74	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 96	98.33 183	93.22 184	99.78 31	99.89 22	94.57 77	99.85 118	99.84 22	99.97 42

CDPH-MVS		98.65 31	98.36 41	99.49 32	99.94 13	98.73 46	99.87 117	98.33 183	93.97 157	99.76 33	99.87 27	94.99 64	99.75 142	98.55 108	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 61	98.32 185	97.28 39	99.83 18	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 88
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		94.69 210	93.81 224	97.33 198	97.10 263	94.44 217	98.86 307	98.32 185	93.30 182	96.17 207	95.59 322	76.48 332	97.95 278	91.06 276	97.43 183	99.59 140

SR-MVS-dyc-post		98.31 54	98.17 52	98.71 99	99.79 62	96.37 150	99.76 163	98.31 187	94.43 132	99.40 79	99.75 74	93.28 121	99.78 135	98.90 87	99.92 64	99.97 61

RE-MVS-def			98.13 55		99.79 62	96.37 150	99.76 163	98.31 187	94.43 132	99.40 79	99.75 74	92.95 131		98.90 87	99.92 64	99.97 61

RPMNet		89.76 328	87.28 345	97.19 201	96.29 291	92.66 267	92.01 413	98.31 187	70.19 419	96.94 184	85.87 418	87.25 227	99.78 135	62.69 420	95.96 217	99.13 208

APD-MVS_3200maxsize		98.25 62	98.08 59	98.78 94	99.81 60	96.60 139	99.82 146	98.30 190	93.95 159	99.37 82	99.77 64	92.84 134	99.76 141	98.95 80	99.92 64	99.97 61

TESTMET0.1,1		96.74 145	96.26 146	98.16 142	97.36 253	96.48 143	99.96 42	98.29 191	91.93 238	95.77 216	98.07 243	95.54 46	98.29 254	90.55 288	98.89 143	99.70 115

MTGPA								98.28 192

MTAPA		98.29 56	97.96 68	99.30 45	99.85 54	97.93 83	99.39 241	98.28 192	95.76 91	97.18 179	99.88 24	92.74 137	100.00 1	98.67 101	99.88 73	99.99 23

114514_t		97.41 110	96.83 124	99.14 64	99.51 94	97.83 85	99.89 111	98.27 194	88.48 322	99.06 101	99.66 104	90.30 188	99.64 159	96.32 184	99.97 42	99.96 67

Anonymous20231211		89.86 326	88.44 334	94.13 300	98.93 131	90.68 312	98.54 332	98.26 195	76.28 405	86.73 345	95.54 324	70.60 368	97.56 293	90.82 283	80.27 364	94.15 319

reproduce-ours		98.78 24	98.67 21	99.09 71	99.70 78	97.30 109	99.74 170	98.25 196	97.10 47	99.10 97	99.90 18	94.59 74	99.99 36	99.77 30	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 71	99.70 78	97.30 109	99.74 170	98.25 196	97.10 47	99.10 97	99.90 18	94.59 74	99.99 36	99.77 30	99.91 67	99.99 23

Vis-MVSNet		95.72 180	95.15 188	97.45 187	97.62 237	94.28 225	99.28 258	98.24 198	94.27 145	96.84 188	98.94 182	79.39 306	98.76 212	93.25 246	98.49 155	99.30 192
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator+	91.53 11	96.31 164	95.24 184	99.52 28	96.88 277	98.64 54	99.72 181	98.24 198	95.27 105	88.42 325	98.98 171	82.76 271	99.94 84	97.10 169	99.83 77	99.96 67

reproduce_model		98.75 27	98.66 23	99.03 76	99.71 76	97.10 121	99.73 177	98.23 200	97.02 52	99.18 94	99.90 18	94.54 78	99.99 36	99.77 30	99.90 69	99.99 23

DTE-MVSNet		89.40 334	88.24 337	92.88 338	92.66 374	89.95 330	99.10 271	98.22 201	87.29 338	85.12 363	96.22 302	76.27 335	95.30 383	83.56 359	75.74 391	93.41 360

SF-MVS		98.67 30	98.40 35	99.50 30	99.77 65	98.67 49	99.90 102	98.21 202	93.53 174	99.81 20	99.89 22	94.70 73	99.86 117	99.84 22	99.93 61	99.96 67

VDDNet		93.12 254	91.91 269	96.76 213	96.67 288	92.65 269	98.69 323	98.21 202	82.81 386	97.75 163	99.28 143	61.57 403	99.48 172	98.09 134	94.09 252	98.15 248

test-LLR		96.47 155	96.04 152	97.78 166	97.02 267	95.44 187	99.96 42	98.21 202	94.07 151	95.55 218	96.38 296	93.90 103	98.27 258	90.42 291	98.83 147	99.64 126

test-mter		96.39 160	95.93 163	97.78 166	97.02 267	95.44 187	99.96 42	98.21 202	91.81 243	95.55 218	96.38 296	95.17 55	98.27 258	90.42 291	98.83 147	99.64 126

MP-MVS-pluss		98.07 70	97.64 85	99.38 43	99.74 70	98.41 63	99.74 170	98.18 206	93.35 179	96.45 198	99.85 33	92.64 139	99.97 57	98.91 86	99.89 70	99.77 106
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
BP-MVS1		98.33 53	98.18 51	98.81 92	97.44 247	97.98 79	99.96 42	98.17 207	94.88 114	98.77 115	99.59 113	97.59 7	99.08 195	98.24 125	98.93 142	99.36 182

FA-MVS(test-final)		95.86 176	95.09 190	98.15 145	97.74 223	95.62 182	96.31 389	98.17 207	91.42 257	96.26 204	96.13 306	90.56 183	99.47 174	92.18 261	97.07 192	99.35 185

PS-MVSNAJ		98.44 44	98.20 49	99.16 60	98.80 146	98.92 29	99.54 217	98.17 207	97.34 36	99.85 14	99.85 33	91.20 167	99.89 106	99.41 58	99.67 90	98.69 235

HPM-MVS		97.96 71	97.72 79	98.68 101	99.84 56	96.39 149	99.90 102	98.17 207	92.61 213	98.62 125	99.57 119	91.87 160	99.67 156	98.87 89	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		96.27 168	95.98 156	97.13 202	97.96 209	93.15 254	96.34 388	98.17 207	92.07 233	98.71 121	95.12 349	93.91 102	98.73 215	94.91 208	96.62 201	99.50 165

WB-MVSnew		92.90 259	92.77 250	93.26 329	96.95 271	93.63 243	99.71 184	98.16 212	91.49 250	94.28 235	98.14 240	81.33 285	96.48 351	79.47 380	95.46 230	89.68 406

ADS-MVSNet		94.79 206	94.02 217	97.11 204	97.87 214	93.79 237	94.24 402	98.16 212	90.07 290	96.43 199	94.48 370	90.29 189	98.19 263	87.44 323	97.23 188	99.36 182

HPM-MVS_fast		97.80 87	97.50 92	98.68 101	99.79 62	96.42 145	99.88 114	98.16 212	91.75 245	98.94 106	99.54 122	91.82 162	99.65 158	97.62 159	99.99 21	99.99 23

Vis-MVSNet (Re-imp)		96.32 163	95.98 156	97.35 197	97.93 211	94.82 210	99.47 229	98.15 215	91.83 241	95.09 225	99.11 158	91.37 165	97.47 296	93.47 244	97.43 183	99.74 109

CNLPA		97.76 91	97.38 98	98.92 88	99.53 91	96.84 130	99.87 117	98.14 216	93.78 167	96.55 196	99.69 94	92.28 151	99.98 47	97.13 167	99.44 116	99.93 79

JIA-IIPM		91.76 287	90.70 288	94.94 265	96.11 296	87.51 359	93.16 409	98.13 217	75.79 408	97.58 165	77.68 423	92.84 134	97.97 275	88.47 313	96.54 202	99.33 188

cl22		93.77 237	93.25 241	95.33 254	99.49 95	94.43 218	99.61 204	98.09 218	90.38 282	89.16 309	95.61 320	90.56 183	97.34 300	91.93 264	84.45 326	94.21 311

cdsmvs_eth3d_5k		23.43 402	31.24 405	0.00 419	0.00 442	0.00 444	0.00 430	98.09 218	0.00 437	0.00 438	99.67 102	83.37 267	0.00 438	0.00 437	0.00 436	0.00 434

xiu_mvs_v2_base		98.23 64	97.97 65	99.02 79	98.69 151	98.66 51	99.52 219	98.08 220	97.05 50	99.86 11	99.86 29	90.65 180	99.71 148	99.39 60	98.63 152	98.69 235

tpm cat1		93.51 245	92.52 259	96.47 220	97.77 221	91.47 299	96.13 392	98.06 221	80.98 394	92.91 252	93.78 379	89.66 194	98.87 204	87.03 332	96.39 208	99.09 211

DeepC-MVS	94.51 4	96.92 136	96.40 143	98.45 126	99.16 111	95.90 168	99.66 194	98.06 221	96.37 79	94.37 233	99.49 125	83.29 268	99.90 101	97.63 158	99.61 99	99.55 150
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 93	97.44 95	98.64 106	95.76 309	96.20 158	99.94 78	98.05 223	98.17 10	98.89 109	99.42 130	87.65 221	99.90 101	99.50 51	99.60 101	99.82 97

EU-MVSNet		90.14 322	90.34 296	89.54 373	92.55 375	81.06 401	98.69 323	98.04 224	91.41 258	86.59 348	96.84 285	80.83 292	93.31 404	86.20 339	81.91 345	94.26 305

TAPA-MVS	92.12 8	94.42 221	93.60 227	96.90 209	99.33 102	91.78 288	99.78 155	98.00 225	89.89 295	94.52 230	99.47 126	91.97 158	99.18 188	69.90 408	99.52 106	99.73 110
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		95.78 179	94.86 197	98.54 118	98.47 174	98.07 73	99.06 279	97.99 226	92.68 209	94.13 238	98.62 212	93.28 121	98.69 220	93.79 237	85.76 314	98.84 226

UnsupCasMVSNet_eth		85.52 356	83.99 358	90.10 369	89.36 405	83.51 385	96.65 383	97.99 226	89.14 301	75.89 406	93.83 378	63.25 397	93.92 397	81.92 370	67.90 410	92.88 372

LFMVS		94.75 209	93.56 230	98.30 136	99.03 118	95.70 177	98.74 317	97.98 228	87.81 333	98.47 132	99.39 137	67.43 381	99.53 161	98.01 137	95.20 238	99.67 120

dp		95.05 199	94.43 205	96.91 208	97.99 207	92.73 265	96.29 390	97.98 228	89.70 297	95.93 211	94.67 365	93.83 107	98.45 234	86.91 336	96.53 203	99.54 154

PMMVS		96.76 143	96.76 127	96.76 213	98.28 187	92.10 279	99.91 96	97.98 228	94.12 148	99.53 65	99.39 137	86.93 232	98.73 215	96.95 176	97.73 177	99.45 171

F-COLMAP		96.93 135	96.95 117	96.87 210	99.71 76	91.74 289	99.85 131	97.95 231	93.11 191	95.72 217	99.16 157	92.35 149	99.94 84	95.32 198	99.35 124	98.92 221

OMC-MVS		97.28 114	97.23 106	97.41 191	99.76 66	93.36 253	99.65 195	97.95 231	96.03 86	97.41 171	99.70 91	89.61 196	99.51 164	96.73 180	98.25 164	99.38 178

mvsany_test1		97.82 85	97.90 73	97.55 181	98.77 148	93.04 258	99.80 152	97.93 233	96.95 55	99.61 60	99.68 101	90.92 175	99.83 128	99.18 66	98.29 163	99.80 101

Anonymous202405211		93.10 255	91.99 267	96.40 224	99.10 114	89.65 334	98.88 303	97.93 233	83.71 378	94.00 239	98.75 198	68.79 372	99.88 112	95.08 201	91.71 268	99.68 118

tpm2		95.47 189	95.18 187	96.35 227	96.91 273	91.70 293	96.96 379	97.93 233	88.04 329	98.44 133	95.40 333	93.32 118	97.97 275	94.00 228	95.61 228	99.38 178

TSAR-MVS + GP.		98.60 33	98.51 31	98.86 90	99.73 73	96.63 137	99.97 34	97.92 236	98.07 14	98.76 118	99.55 120	95.00 63	99.94 84	99.91 16	97.68 179	99.99 23

CDS-MVSNet		96.34 162	96.07 151	97.13 202	97.37 252	94.96 205	99.53 218	97.91 237	91.55 249	95.37 222	98.32 234	95.05 60	97.13 314	93.80 236	95.75 226	99.30 192
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP3-MVS								97.89 238							89.60 274

HQP-MVS		94.61 214	94.50 204	94.92 266	95.78 305	91.85 285	99.87 117	97.89 238	96.82 58	93.37 244	98.65 208	80.65 295	98.39 241	97.92 143	89.60 274	94.53 284

HQP_MVS		94.49 219	94.36 207	94.87 267	95.71 315	91.74 289	99.84 136	97.87 240	96.38 76	93.01 249	98.59 213	80.47 299	98.37 247	97.79 152	89.55 277	94.52 286

plane_prior5								97.87 240					98.37 247	97.79 152	89.55 277	94.52 286

xiu_mvs_v1_base_debu		97.43 105	97.06 111	98.55 115	97.74 223	98.14 68	99.31 252	97.86 242	96.43 73	99.62 54	99.69 94	85.56 246	99.68 153	99.05 71	98.31 160	97.83 254

xiu_mvs_v1_base		97.43 105	97.06 111	98.55 115	97.74 223	98.14 68	99.31 252	97.86 242	96.43 73	99.62 54	99.69 94	85.56 246	99.68 153	99.05 71	98.31 160	97.83 254

xiu_mvs_v1_base_debi		97.43 105	97.06 111	98.55 115	97.74 223	98.14 68	99.31 252	97.86 242	96.43 73	99.62 54	99.69 94	85.56 246	99.68 153	99.05 71	98.31 160	97.83 254

CostFormer		96.10 170	95.88 166	96.78 212	97.03 266	92.55 271	97.08 376	97.83 245	90.04 292	98.72 120	94.89 359	95.01 62	98.29 254	96.54 182	95.77 224	99.50 165

TAMVS		95.85 177	95.58 175	96.65 218	97.07 264	93.50 247	99.17 268	97.82 246	91.39 259	95.02 226	98.01 244	92.20 152	97.30 304	93.75 239	95.83 223	99.14 207

balanced_conf03		98.27 57	97.99 63	99.11 69	98.64 158	98.43 62	99.47 229	97.79 247	94.56 125	99.74 37	98.35 231	94.33 88	99.25 180	99.12 68	99.96 46	99.64 126

VDD-MVS		93.77 237	92.94 245	96.27 229	98.55 164	90.22 323	98.77 316	97.79 247	90.85 272	96.82 189	99.42 130	61.18 405	99.77 138	98.95 80	94.13 251	98.82 227

cascas		94.64 213	93.61 225	97.74 172	97.82 218	96.26 153	99.96 42	97.78 249	85.76 358	94.00 239	97.54 259	76.95 326	99.21 183	97.23 165	95.43 232	97.76 258

fmvsm_s_conf0.1_n_2		97.25 116	96.85 123	98.43 128	98.08 202	98.08 72	99.92 88	97.76 250	98.05 15	99.65 47	99.58 116	80.88 291	99.93 92	99.59 47	98.17 165	97.29 267

MVSMamba_PlusPlus		97.83 82	97.45 94	98.99 81	98.60 160	98.15 66	99.58 208	97.74 251	90.34 285	99.26 90	98.32 234	94.29 90	99.23 181	99.03 77	99.89 70	99.58 146

CLD-MVS		94.06 230	93.90 221	94.55 282	96.02 299	90.69 311	99.98 17	97.72 252	96.62 69	91.05 272	98.85 194	77.21 321	98.47 230	98.11 132	89.51 279	94.48 288
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MS-PatchMatch		90.65 306	90.30 297	91.71 354	94.22 344	85.50 374	98.24 348	97.70 253	88.67 318	86.42 352	96.37 298	67.82 379	98.03 273	83.62 358	99.62 95	91.60 387

mvsmamba		96.94 133	96.73 129	97.55 181	97.99 207	94.37 223	99.62 202	97.70 253	93.13 189	98.42 134	97.92 250	88.02 217	98.75 214	98.78 94	99.01 140	99.52 160

XXY-MVS		91.82 280	90.46 292	95.88 238	93.91 349	95.40 191	98.87 306	97.69 255	88.63 320	87.87 330	97.08 272	74.38 352	97.89 281	91.66 268	84.07 330	94.35 300

EI-MVSNet		93.73 239	93.40 237	94.74 272	96.80 281	92.69 266	99.06 279	97.67 256	88.96 309	91.39 267	99.02 164	88.75 211	97.30 304	91.07 275	87.85 301	94.22 309

MVSTER		95.53 188	95.22 185	96.45 222	98.56 161	97.72 89	99.91 96	97.67 256	92.38 226	91.39 267	97.14 269	97.24 18	97.30 304	94.80 211	87.85 301	94.34 302

SSC-MVS3.2		89.59 331	88.66 331	92.38 343	94.29 343	86.12 369	99.49 225	97.66 258	90.28 288	88.63 318	95.18 347	64.46 392	96.88 334	85.30 347	82.66 338	94.14 322

mamv4		95.24 195	96.90 119	90.25 367	98.65 157	72.11 414	98.28 346	97.64 259	89.99 293	95.93 211	98.25 237	94.74 70	99.11 192	99.01 79	99.64 92	99.53 158

WBMVS		94.52 218	94.03 216	95.98 235	98.38 177	96.68 135	99.92 88	97.63 260	90.75 277	89.64 294	95.25 345	96.77 25	96.90 331	94.35 223	83.57 333	94.35 300

ETV-MVS		97.92 75	97.80 78	98.25 139	98.14 199	96.48 143	99.98 17	97.63 260	95.61 95	99.29 88	99.46 128	92.55 143	98.82 207	99.02 78	98.54 154	99.46 169

CANet_DTU		96.76 143	96.15 150	98.60 109	98.78 147	97.53 98	99.84 136	97.63 260	97.25 44	99.20 91	99.64 107	81.36 284	99.98 47	92.77 256	98.89 143	98.28 246

LPG-MVS_test		92.96 257	92.71 251	93.71 316	95.43 323	88.67 346	99.75 167	97.62 263	92.81 200	90.05 279	98.49 222	75.24 343	98.40 239	95.84 192	89.12 281	94.07 327

LGP-MVS_train				93.71 316	95.43 323	88.67 346		97.62 263	92.81 200	90.05 279	98.49 222	75.24 343	98.40 239	95.84 192	89.12 281	94.07 327

FMVSNet3		92.69 265	91.58 274	95.99 234	98.29 185	97.42 106	99.26 261	97.62 263	89.80 296	89.68 290	95.32 339	81.62 282	96.27 360	87.01 333	85.65 315	94.29 304

ET-MVSNet_ETH3D		94.37 223	93.28 240	97.64 176	98.30 184	97.99 78	99.99 5	97.61 266	94.35 137	71.57 412	99.45 129	96.23 35	95.34 381	96.91 178	85.14 321	99.59 140

EIA-MVS		97.53 102	97.46 93	97.76 170	98.04 205	94.84 209	99.98 17	97.61 266	94.41 135	97.90 155	99.59 113	92.40 148	98.87 204	98.04 136	99.13 134	99.59 140

OPM-MVS		93.21 250	92.80 248	94.44 289	93.12 363	90.85 309	99.77 158	97.61 266	96.19 84	91.56 266	98.65 208	75.16 347	98.47 230	93.78 238	89.39 280	93.99 335
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
IS-MVSNet		96.29 166	95.90 165	97.45 187	98.13 200	94.80 211	99.08 274	97.61 266	92.02 237	95.54 220	98.96 175	90.64 181	98.08 269	93.73 240	97.41 186	99.47 168

CMPMVS	61.59 21	84.75 364	85.14 357	83.57 393	90.32 399	62.54 421	96.98 378	97.59 270	74.33 413	69.95 414	96.66 288	64.17 393	98.32 251	87.88 320	88.41 295	89.84 405
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UniMVSNet_ETH3D		90.06 323	88.58 332	94.49 286	94.67 335	88.09 355	97.81 364	97.57 271	83.91 377	88.44 321	97.41 262	57.44 409	97.62 291	91.41 270	88.59 292	97.77 257

lupinMVS		97.85 80	97.60 87	98.62 107	97.28 260	97.70 92	99.99 5	97.55 272	95.50 100	99.43 75	99.67 102	90.92 175	98.71 218	98.40 117	99.62 95	99.45 171

XVG-OURS		94.82 203	94.74 201	95.06 261	98.00 206	89.19 338	99.08 274	97.55 272	94.10 149	94.71 228	99.62 111	80.51 297	99.74 144	96.04 188	93.06 266	96.25 276

XVG-OURS-SEG-HR		94.79 206	94.70 202	95.08 260	98.05 204	89.19 338	99.08 274	97.54 274	93.66 172	94.87 227	99.58 116	78.78 313	99.79 133	97.31 163	93.40 261	96.25 276

PatchT		90.38 313	88.75 329	95.25 257	95.99 300	90.16 324	91.22 417	97.54 274	76.80 404	97.26 176	86.01 417	91.88 159	96.07 369	66.16 416	95.91 221	99.51 163

BH-RMVSNet		95.18 196	94.31 210	97.80 163	98.17 196	95.23 198	99.76 163	97.53 276	92.52 220	94.27 236	99.25 150	76.84 327	98.80 208	90.89 282	99.54 104	99.35 185

ACMP	92.05 9	92.74 263	92.42 261	93.73 314	95.91 303	88.72 345	99.81 148	97.53 276	94.13 147	87.00 343	98.23 238	74.07 353	98.47 230	96.22 186	88.86 286	93.99 335
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	91.95 10	92.88 260	92.52 259	93.98 308	95.75 311	89.08 342	99.77 158	97.52 278	93.00 192	89.95 283	97.99 247	76.17 336	98.46 233	93.63 243	88.87 285	94.39 296
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TR-MVS		94.54 215	93.56 230	97.49 186	97.96 209	94.34 224	98.71 320	97.51 279	90.30 287	94.51 231	98.69 204	75.56 340	98.77 211	92.82 255	95.99 215	99.35 185

BH-w/o		95.71 182	95.38 180	96.68 216	98.49 173	92.28 275	99.84 136	97.50 280	92.12 232	92.06 263	98.79 196	84.69 256	98.67 222	95.29 199	99.66 91	99.09 211

mvs_anonymous		95.65 186	95.03 193	97.53 183	98.19 194	95.74 174	99.33 249	97.49 281	90.87 271	90.47 277	97.10 271	88.23 215	97.16 311	95.92 190	97.66 180	99.68 118

DP-MVS		94.54 215	93.42 234	97.91 160	99.46 98	94.04 231	98.93 297	97.48 282	81.15 393	90.04 281	99.55 120	87.02 230	99.95 76	88.97 306	98.11 170	99.73 110

ACMH	89.72 17	90.64 307	89.63 310	93.66 320	95.64 320	88.64 348	98.55 330	97.45 283	89.03 304	81.62 381	97.61 257	69.75 370	98.41 237	89.37 302	87.62 305	93.92 341
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVG-ACMP-BASELINE		91.22 296	90.75 287	92.63 342	93.73 352	85.61 372	98.52 334	97.44 284	92.77 204	89.90 285	96.85 283	66.64 384	98.39 241	92.29 259	88.61 290	93.89 343

mvs_tets		91.81 281	91.08 284	94.00 306	91.63 388	90.58 315	98.67 325	97.43 285	92.43 223	87.37 340	97.05 275	71.76 360	97.32 302	94.75 213	88.68 289	94.11 325

LTVRE_ROB	88.28 18	90.29 317	89.05 324	94.02 304	95.08 328	90.15 325	97.19 372	97.43 285	84.91 370	83.99 370	97.06 274	74.00 354	98.28 256	84.08 353	87.71 303	93.62 357
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		91.92 279	91.18 282	94.15 298	91.35 391	90.95 306	99.00 289	97.42 287	92.61 213	87.38 339	97.08 272	72.46 358	97.36 298	94.53 219	88.77 287	94.13 324

K. test v3		88.05 345	87.24 346	90.47 365	91.82 386	82.23 393	98.96 293	97.42 287	89.05 303	76.93 402	95.60 321	68.49 375	95.42 379	85.87 344	81.01 357	93.75 351

FMVSNet2		91.02 298	89.56 312	95.41 251	97.53 242	95.74 174	98.98 290	97.41 289	87.05 341	88.43 323	95.00 355	71.34 363	96.24 362	85.12 348	85.21 320	94.25 307

jason		97.24 117	96.86 122	98.38 133	95.73 312	97.32 108	99.97 34	97.40 290	95.34 103	98.60 127	99.54 122	87.70 220	98.56 226	97.94 142	99.47 112	99.25 199
jason: jason.
PS-MVSNAJss		93.64 242	93.31 239	94.61 277	92.11 381	92.19 277	99.12 270	97.38 291	92.51 221	88.45 320	96.99 278	91.20 167	97.29 307	94.36 221	87.71 303	94.36 297

MSDG		94.37 223	93.36 238	97.40 192	98.88 141	93.95 235	99.37 245	97.38 291	85.75 360	90.80 274	99.17 156	84.11 263	99.88 112	86.35 337	98.43 157	98.36 244

GDP-MVS		97.88 76	97.59 89	98.75 97	97.59 239	97.81 87	99.95 61	97.37 293	94.44 131	99.08 99	99.58 116	97.13 23	99.08 195	94.99 203	98.17 165	99.37 180

sasdasda		97.09 125	96.32 144	99.39 40	98.93 131	98.95 27	99.72 181	97.35 294	94.45 128	97.88 158	99.42 130	86.71 233	99.52 162	98.48 113	93.97 254	99.72 112

CL-MVSNet_self_test		84.50 366	83.15 367	88.53 382	86.00 412	81.79 396	98.82 311	97.35 294	85.12 366	83.62 373	90.91 399	76.66 329	91.40 413	69.53 409	60.36 422	92.40 380

canonicalmvs		97.09 125	96.32 144	99.39 40	98.93 131	98.95 27	99.72 181	97.35 294	94.45 128	97.88 158	99.42 130	86.71 233	99.52 162	98.48 113	93.97 254	99.72 112

UnsupCasMVSNet_bld		79.97 382	77.03 387	88.78 379	85.62 413	81.98 394	93.66 407	97.35 294	75.51 410	70.79 413	83.05 420	48.70 418	94.91 388	78.31 388	60.29 423	89.46 410

MVS-HIRNet		86.22 353	83.19 366	95.31 255	96.71 287	90.29 321	92.12 412	97.33 298	62.85 420	86.82 344	70.37 425	69.37 371	97.49 295	75.12 399	97.99 175	98.15 248

BH-untuned		95.18 196	94.83 198	96.22 230	98.36 180	91.22 301	99.80 152	97.32 299	90.91 270	91.08 270	98.67 205	83.51 265	98.54 228	94.23 226	99.61 99	98.92 221

PCF-MVS	94.20 5	95.18 196	94.10 214	98.43 128	98.55 164	95.99 166	97.91 361	97.31 300	90.35 284	89.48 298	99.22 152	85.19 251	99.89 106	90.40 293	98.47 156	99.41 176
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MGCFI-Net		97.00 130	96.22 148	99.34 44	98.86 142	98.80 39	99.67 193	97.30 301	94.31 140	97.77 162	99.41 134	86.36 240	99.50 166	98.38 118	93.90 256	99.72 112

test_fmvsmconf0.01_n		96.39 160	95.74 169	98.32 135	91.47 390	95.56 184	99.84 136	97.30 301	97.74 24	97.89 157	99.35 141	79.62 304	99.85 118	99.25 64	99.24 129	99.55 150

test_vis1_n_1920		95.44 190	95.31 182	95.82 241	98.50 171	88.74 344	99.98 17	97.30 301	97.84 22	99.85 14	99.19 154	66.82 383	99.97 57	98.82 91	99.46 114	98.76 230

miper_enhance_ethall		94.36 225	93.98 218	95.49 246	98.68 152	95.24 197	99.73 177	97.29 304	93.28 183	89.86 286	95.97 311	94.37 85	97.05 320	92.20 260	84.45 326	94.19 312

casdiffmvs_mvg		96.43 157	95.94 162	97.89 162	97.44 247	95.47 186	99.86 128	97.29 304	93.35 179	96.03 208	99.19 154	85.39 249	98.72 217	97.89 146	97.04 194	99.49 167
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		96.94 133	96.60 135	97.95 154	97.28 260	97.70 92	99.55 215	97.27 306	91.17 262	99.43 75	99.54 122	90.92 175	96.89 332	94.67 216	99.62 95	99.25 199

test_djsdf		92.83 261	92.29 262	94.47 287	91.90 384	92.46 272	99.55 215	97.27 306	91.17 262	89.96 282	96.07 309	81.10 287	96.89 332	94.67 216	88.91 283	94.05 329

test_cas_vis1_n_1920		96.59 152	96.23 147	97.65 175	98.22 191	94.23 227	99.99 5	97.25 308	97.77 23	99.58 61	99.08 160	77.10 322	99.97 57	97.64 157	99.45 115	98.74 232

GA-MVS		93.83 233	92.84 246	96.80 211	95.73 312	93.57 244	99.88 114	97.24 309	92.57 217	92.92 251	96.66 288	78.73 314	97.67 289	87.75 321	94.06 253	99.17 203

Effi-MVS+		96.30 165	95.69 171	98.16 142	97.85 216	96.26 153	97.41 368	97.21 310	90.37 283	98.65 124	98.58 216	86.61 237	98.70 219	97.11 168	97.37 187	99.52 160

Patchmatch-test		92.65 267	91.50 277	96.10 233	96.85 278	90.49 317	91.50 415	97.19 311	82.76 387	90.23 278	95.59 322	95.02 61	98.00 274	77.41 391	96.98 197	99.82 97

diffmvs		97.00 130	96.64 133	98.09 148	97.64 236	96.17 161	99.81 148	97.19 311	94.67 123	98.95 105	99.28 143	86.43 238	98.76 212	98.37 120	97.42 185	99.33 188
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	90.35 314	89.54 313	92.78 341	95.99 300	86.12 369	98.81 312	97.18 313	89.38 299	83.14 374	97.76 256	68.42 376	98.43 235	89.11 305	86.05 313	93.78 350

anonymousdsp		91.79 286	90.92 286	94.41 292	90.76 396	92.93 260	98.93 297	97.17 314	89.08 302	87.46 338	95.30 340	78.43 319	96.92 330	92.38 258	88.73 288	93.39 362

baseline		96.43 157	95.98 156	97.76 170	97.34 254	95.17 202	99.51 221	97.17 314	93.92 161	96.90 186	99.28 143	85.37 250	98.64 223	97.50 160	96.86 200	99.46 169

nrg030		93.51 245	92.53 258	96.45 222	94.36 340	97.20 114	99.81 148	97.16 316	91.60 247	89.86 286	97.46 260	86.37 239	97.68 288	95.88 191	80.31 363	94.46 289

SPE-MVS-test		97.88 76	97.94 70	97.70 173	99.28 105	95.20 200	99.98 17	97.15 317	95.53 98	99.62 54	99.79 58	92.08 156	98.38 245	98.75 97	99.28 127	99.52 160

MVS_Test		96.46 156	95.74 169	98.61 108	98.18 195	97.23 113	99.31 252	97.15 317	91.07 267	98.84 110	97.05 275	88.17 216	98.97 199	94.39 220	97.50 182	99.61 137

MIMVSNet		90.30 316	88.67 330	95.17 259	96.45 290	91.64 295	92.39 411	97.15 317	85.99 355	90.50 276	93.19 386	66.95 382	94.86 389	82.01 369	93.43 260	99.01 218

KD-MVS_2432*1600		88.00 346	86.10 350	93.70 318	96.91 273	94.04 231	97.17 373	97.12 320	84.93 368	81.96 378	92.41 390	92.48 145	94.51 393	79.23 381	52.68 425	92.56 376

miper_refine_blended		88.00 346	86.10 350	93.70 318	96.91 273	94.04 231	97.17 373	97.12 320	84.93 368	81.96 378	92.41 390	92.48 145	94.51 393	79.23 381	52.68 425	92.56 376

CS-MVS		97.79 89	97.91 72	97.43 189	99.10 114	94.42 219	99.99 5	97.10 322	95.07 107	99.68 44	99.75 74	92.95 131	98.34 249	98.38 118	99.14 133	99.54 154

v7n		89.65 330	88.29 336	93.72 315	92.22 379	90.56 316	99.07 278	97.10 322	85.42 365	86.73 345	94.72 361	80.06 301	97.13 314	81.14 373	78.12 375	93.49 359

RRT-MVS		96.24 169	95.68 173	97.94 157	97.65 235	94.92 207	99.27 260	97.10 322	92.79 203	97.43 170	97.99 247	81.85 277	99.37 177	98.46 115	98.57 153	99.53 158

casdiffmvs		96.42 159	95.97 159	97.77 168	97.30 258	94.98 204	99.84 136	97.09 325	93.75 170	96.58 195	99.26 149	85.07 252	98.78 210	97.77 154	97.04 194	99.54 154
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+		95.02 200	94.19 212	97.52 184	97.88 213	94.55 216	99.97 34	97.08 326	88.85 314	94.47 232	97.96 249	84.59 257	98.41 237	89.84 300	97.10 191	99.59 140

miper_ehance_all_eth		93.16 253	92.60 253	94.82 271	97.57 240	93.56 245	99.50 223	97.07 327	88.75 316	88.85 313	95.52 326	90.97 174	96.74 341	90.77 284	84.45 326	94.17 313

MonoMVSNet		94.82 203	94.43 205	95.98 235	94.54 337	90.73 310	99.03 286	97.06 328	93.16 187	93.15 248	95.47 330	88.29 214	97.57 292	97.85 147	91.33 271	99.62 133

Effi-MVS+-dtu		94.53 217	95.30 183	92.22 346	97.77 221	82.54 390	99.59 206	97.06 328	94.92 112	95.29 223	95.37 337	85.81 244	97.89 281	94.80 211	97.07 192	96.23 278

EC-MVSNet		97.38 112	97.24 105	97.80 163	97.41 249	95.64 181	99.99 5	97.06 328	94.59 124	99.63 51	99.32 142	89.20 205	98.14 265	98.76 96	99.23 130	99.62 133

IterMVS		90.91 300	90.17 302	93.12 332	96.78 284	90.42 320	98.89 301	97.05 331	89.03 304	86.49 350	95.42 332	76.59 330	95.02 384	87.22 328	84.09 329	93.93 340
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1192		90.62 309	89.25 319	94.72 274	93.13 361	93.07 255	99.50 223	97.02 332	86.33 352	89.56 297	95.01 353	79.22 308	97.09 319	82.34 367	81.16 351	94.01 332

v2v482		91.30 291	90.07 305	95.01 262	93.13 361	93.79 237	99.77 158	97.02 332	88.05 328	89.25 303	95.37 337	80.73 293	97.15 312	87.28 327	80.04 366	94.09 326

V42		91.28 293	90.12 304	94.74 272	93.42 358	93.46 248	99.68 191	97.02 332	87.36 337	89.85 288	95.05 351	81.31 286	97.34 300	87.34 326	80.07 365	93.40 361

IterMVS-SCA-FT		90.85 303	90.16 303	92.93 337	96.72 286	89.96 329	98.89 301	96.99 335	88.95 310	86.63 347	95.67 318	76.48 332	95.00 385	87.04 331	84.04 332	93.84 347

v144192		90.79 304	89.52 314	94.59 279	93.11 364	92.77 261	99.56 213	96.99 335	86.38 351	89.82 289	94.95 358	80.50 298	97.10 317	83.98 355	80.41 361	93.90 342

v1921920		90.46 311	89.12 321	94.50 285	92.96 368	92.46 272	99.49 225	96.98 337	86.10 354	89.61 296	95.30 340	78.55 317	97.03 325	82.17 368	80.89 359	94.01 332

v1144		91.09 297	89.83 306	94.87 267	93.25 360	93.69 242	99.62 202	96.98 337	86.83 347	89.64 294	94.99 356	80.94 289	97.05 320	85.08 349	81.16 351	93.87 345

eth_miper_zixun_eth		92.41 271	91.93 268	93.84 313	97.28 260	90.68 312	98.83 310	96.97 339	88.57 321	89.19 308	95.73 317	89.24 204	96.69 344	89.97 299	81.55 347	94.15 319

dcpmvs_2		97.42 109	98.09 58	95.42 250	99.58 89	87.24 362	99.23 263	96.95 340	94.28 143	98.93 107	99.73 83	94.39 84	99.16 191	99.89 17	99.82 81	99.86 93

GBi-Net		90.88 301	89.82 307	94.08 301	97.53 242	91.97 280	98.43 338	96.95 340	87.05 341	89.68 290	94.72 361	71.34 363	96.11 365	87.01 333	85.65 315	94.17 313

test1		90.88 301	89.82 307	94.08 301	97.53 242	91.97 280	98.43 338	96.95 340	87.05 341	89.68 290	94.72 361	71.34 363	96.11 365	87.01 333	85.65 315	94.17 313

FMVSNet1		88.50 341	86.64 348	94.08 301	95.62 322	91.97 280	98.43 338	96.95 340	83.00 384	86.08 357	94.72 361	59.09 407	96.11 365	81.82 371	84.07 330	94.17 313

v8		90.54 310	89.17 320	94.66 275	93.43 357	93.40 251	99.20 265	96.94 344	85.76 358	87.56 335	94.51 368	81.96 276	97.19 310	84.94 350	78.25 373	93.38 363

c3_l		92.53 268	91.87 270	94.52 283	97.40 250	92.99 259	99.40 237	96.93 345	87.86 331	88.69 316	95.44 331	89.95 192	96.44 353	90.45 290	80.69 360	94.14 322

v1240		90.20 319	88.79 328	94.44 289	93.05 366	92.27 276	99.38 243	96.92 346	85.89 356	89.36 300	94.87 360	77.89 320	97.03 325	80.66 375	81.08 354	94.01 332

tpm		93.70 241	93.41 236	94.58 280	95.36 325	87.41 360	97.01 377	96.90 347	90.85 272	96.72 192	94.14 376	90.40 186	96.84 336	90.75 285	88.54 293	99.51 163

v148		90.70 305	89.63 310	93.92 309	92.97 367	90.97 303	99.75 167	96.89 348	87.51 334	88.27 326	95.01 353	81.67 279	97.04 323	87.40 325	77.17 384	93.75 351

IterMVS-LS		92.69 265	92.11 264	94.43 291	96.80 281	92.74 263	99.45 234	96.89 348	88.98 307	89.65 293	95.38 336	88.77 210	96.34 357	90.98 279	82.04 344	94.22 309
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v10		90.25 318	88.82 327	94.57 281	93.53 355	93.43 249	99.08 274	96.87 350	85.00 367	87.34 341	94.51 368	80.93 290	97.02 327	82.85 363	79.23 368	93.26 365

ADS-MVSNet2		93.80 236	93.88 222	93.55 322	97.87 214	85.94 371	94.24 402	96.84 351	90.07 290	96.43 199	94.48 370	90.29 189	95.37 380	87.44 323	97.23 188	99.36 182

Fast-Effi-MVS+-dtu		93.72 240	93.86 223	93.29 327	97.06 265	86.16 368	99.80 152	96.83 352	92.66 210	92.58 256	97.83 255	81.39 283	97.67 289	89.75 301	96.87 199	96.05 281

pmmvs4		92.10 277	91.07 285	95.18 258	92.82 372	94.96 205	99.48 228	96.83 352	87.45 336	88.66 317	96.56 294	83.78 264	96.83 338	89.29 303	84.77 324	93.75 351

AllTest		92.48 269	91.64 272	95.00 263	99.01 119	88.43 350	98.94 295	96.82 354	86.50 349	88.71 314	98.47 226	74.73 349	99.88 112	85.39 345	96.18 211	96.71 272

TestCases				95.00 263	99.01 119	88.43 350		96.82 354	86.50 349	88.71 314	98.47 226	74.73 349	99.88 112	85.39 345	96.18 211	96.71 272

miper_lstm_enhance		91.81 281	91.39 280	93.06 335	97.34 254	89.18 340	99.38 243	96.79 356	86.70 348	87.47 337	95.22 346	90.00 191	95.86 374	88.26 314	81.37 349	94.15 319

cl____		92.31 273	91.58 274	94.52 283	97.33 256	92.77 261	99.57 211	96.78 357	86.97 345	87.56 335	95.51 327	89.43 198	96.62 346	88.60 309	82.44 341	94.16 318

DIV-MVS_self_test		92.32 272	91.60 273	94.47 287	97.31 257	92.74 263	99.58 208	96.75 358	86.99 344	87.64 333	95.54 324	89.55 197	96.50 350	88.58 310	82.44 341	94.17 313

ppachtmachnet_test		89.58 332	88.35 335	93.25 330	92.40 377	90.44 319	99.33 249	96.73 359	85.49 363	85.90 359	95.77 314	81.09 288	96.00 372	76.00 398	82.49 340	93.30 364

GeoE		94.36 225	93.48 232	96.99 206	97.29 259	93.54 246	99.96 42	96.72 360	88.35 325	93.43 243	98.94 182	82.05 274	98.05 272	88.12 318	96.48 206	99.37 180

COLMAP_ROB	90.47 14	92.18 276	91.49 278	94.25 297	99.00 123	88.04 356	98.42 341	96.70 361	82.30 389	88.43 323	99.01 166	76.97 325	99.85 118	86.11 341	96.50 204	94.86 283
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
1112_ss		96.01 173	95.20 186	98.42 130	97.80 219	96.41 146	99.65 195	96.66 362	92.71 206	92.88 253	99.40 135	92.16 153	99.30 178	91.92 265	93.66 257	99.55 150

test_fmvs1		95.35 193	95.68 173	94.36 293	98.99 124	84.98 377	99.96 42	96.65 363	97.60 28	99.73 39	98.96 175	71.58 362	99.93 92	98.31 123	99.37 122	98.17 247

Test_1112_low_res		95.72 180	94.83 198	98.42 130	97.79 220	96.41 146	99.65 195	96.65 363	92.70 207	92.86 254	96.13 306	92.15 154	99.30 178	91.88 266	93.64 258	99.55 150

RPSCF		91.80 284	92.79 249	88.83 378	98.15 198	69.87 416	98.11 355	96.60 365	83.93 376	94.33 234	99.27 146	79.60 305	99.46 175	91.99 263	93.16 264	97.18 269

test_fmvs1_n		94.25 228	94.36 207	93.92 309	97.68 231	83.70 384	99.90 102	96.57 366	97.40 34	99.67 45	98.88 186	61.82 402	99.92 98	98.23 126	99.13 134	98.14 250

YYNet1		85.50 358	83.33 364	92.00 348	90.89 395	88.38 353	99.22 264	96.55 367	79.60 400	57.26 424	92.72 387	79.09 312	93.78 400	77.25 392	77.37 382	93.84 347

MDA-MVSNet_test_wron		85.51 357	83.32 365	92.10 347	90.96 394	88.58 349	99.20 265	96.52 368	79.70 399	57.12 425	92.69 388	79.11 310	93.86 399	77.10 393	77.46 381	93.86 346

MTMP							99.87 117	96.49 369

pm-mvs1		89.36 335	87.81 341	94.01 305	93.40 359	91.93 283	98.62 328	96.48 370	86.25 353	83.86 371	96.14 305	73.68 355	97.04 323	86.16 340	75.73 392	93.04 370

KD-MVS_self_test		83.59 372	82.06 372	88.20 384	86.93 410	80.70 403	97.21 371	96.38 371	82.87 385	82.49 376	88.97 406	67.63 380	92.32 410	73.75 402	62.30 421	91.58 388

test_vis1_n		93.61 243	93.03 244	95.35 252	95.86 304	86.94 364	99.87 117	96.36 372	96.85 56	99.54 64	98.79 196	52.41 415	99.83 128	98.64 104	98.97 141	99.29 194

our_test_3		90.39 312	89.48 317	93.12 332	92.40 377	89.57 335	99.33 249	96.35 373	87.84 332	85.30 361	94.99 356	84.14 262	96.09 368	80.38 376	84.56 325	93.71 356

CR-MVSNet		93.45 248	92.62 252	95.94 237	96.29 291	92.66 267	92.01 413	96.23 374	92.62 212	96.94 184	93.31 384	91.04 172	96.03 370	79.23 381	95.96 217	99.13 208

Patchmtry		89.70 329	88.49 333	93.33 326	96.24 294	89.94 332	91.37 416	96.23 374	78.22 402	87.69 332	93.31 384	91.04 172	96.03 370	80.18 379	82.10 343	94.02 330

MVP-Stereo		90.93 299	90.45 294	92.37 345	91.25 393	88.76 343	98.05 358	96.17 376	87.27 339	84.04 368	95.30 340	78.46 318	97.27 309	83.78 357	99.70 89	91.09 390
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pmmvs6		85.69 354	83.84 361	91.26 357	90.00 402	84.41 381	97.82 363	96.15 377	75.86 407	81.29 383	95.39 335	61.21 404	96.87 335	83.52 360	73.29 395	92.50 378

EG-PatchMatch MVS		85.35 359	83.81 362	89.99 371	90.39 398	81.89 395	98.21 352	96.09 378	81.78 391	74.73 408	93.72 380	51.56 417	97.12 316	79.16 384	88.61 290	90.96 393

DeepMVS_CX				82.92 395	95.98 302	58.66 426		96.01 379	92.72 205	78.34 396	95.51 327	58.29 408	98.08 269	82.57 364	85.29 318	92.03 384

test20.03		84.72 365	83.99 358	86.91 387	88.19 409	80.62 404	98.88 303	95.94 380	88.36 324	78.87 392	94.62 366	68.75 373	89.11 418	66.52 415	75.82 390	91.00 392

MDA-MVSNet-bldmvs		84.09 368	81.52 375	91.81 352	91.32 392	88.00 357	98.67 325	95.92 381	80.22 397	55.60 426	93.32 383	68.29 377	93.60 402	73.76 401	76.61 388	93.82 349

lessismore_v0				90.53 363	90.58 397	80.90 402		95.80 382		77.01 401	95.84 312	66.15 386	96.95 328	83.03 362	75.05 393	93.74 354

Anonymous20240521		85.15 360	83.81 362	89.16 376	88.32 407	82.69 388	98.80 314	95.74 383	79.72 398	81.53 382	90.99 397	65.38 389	94.16 395	72.69 403	81.11 353	90.63 397

ttmdpeth		88.23 344	87.06 347	91.75 353	89.91 403	87.35 361	98.92 300	95.73 384	87.92 330	84.02 369	96.31 299	68.23 378	96.84 336	86.33 338	76.12 389	91.06 391

ITE_SJBPF				92.38 343	95.69 318	85.14 375		95.71 385	92.81 200	89.33 302	98.11 241	70.23 369	98.42 236	85.91 343	88.16 298	93.59 358

FMVSNet5		88.32 342	87.47 344	90.88 358	96.90 276	88.39 352	97.28 370	95.68 386	82.60 388	84.67 366	92.40 392	79.83 303	91.16 414	76.39 396	81.51 348	93.09 368

testgi		89.01 338	88.04 339	91.90 350	93.49 356	84.89 378	99.73 177	95.66 387	93.89 165	85.14 362	98.17 239	59.68 406	94.66 392	77.73 390	88.88 284	96.16 280

new_pmnet		84.49 367	82.92 368	89.21 375	90.03 401	82.60 389	96.89 381	95.62 388	80.59 395	75.77 407	89.17 405	65.04 391	94.79 390	72.12 405	81.02 356	90.23 399

pmmvs5		90.17 321	89.09 322	93.40 324	92.10 382	89.77 333	99.74 170	95.58 389	85.88 357	87.24 342	95.74 315	73.41 356	96.48 351	88.54 311	83.56 334	93.95 338

USDC		90.00 324	88.96 325	93.10 334	94.81 332	88.16 354	98.71 320	95.54 390	93.66 172	83.75 372	97.20 268	65.58 387	98.31 252	83.96 356	87.49 307	92.85 373

test_method		80.79 377	79.70 381	84.08 392	92.83 371	67.06 418	99.51 221	95.42 391	54.34 424	81.07 385	93.53 381	44.48 420	92.22 411	78.90 385	77.23 383	92.94 371

MIMVSNet1		82.58 373	80.51 379	88.78 379	86.68 411	84.20 382	96.65 383	95.41 392	78.75 401	78.59 395	92.44 389	51.88 416	89.76 417	65.26 418	78.95 369	92.38 381

OurMVSNet-221017-0		89.81 327	89.48 317	90.83 361	91.64 387	81.21 399	98.17 353	95.38 393	91.48 252	85.65 360	97.31 265	72.66 357	97.29 307	88.15 316	84.83 323	93.97 337

Anonymous20231206		86.32 352	85.42 355	89.02 377	89.11 406	80.53 405	99.05 283	95.28 394	85.43 364	82.82 375	93.92 377	74.40 351	93.44 403	66.99 413	81.83 346	93.08 369

new-patchmatchnet		81.19 375	79.34 382	86.76 388	82.86 419	80.36 406	97.92 360	95.27 395	82.09 390	72.02 411	86.87 414	62.81 399	90.74 416	71.10 406	63.08 418	89.19 412

OpenMVS_ROB	79.82 20	83.77 371	81.68 374	90.03 370	88.30 408	82.82 387	98.46 335	95.22 396	73.92 414	76.00 405	91.29 396	55.00 411	96.94 329	68.40 411	88.51 294	90.34 398

test_0402		85.58 355	83.94 360	90.50 364	93.81 351	85.04 376	98.55 330	95.20 397	76.01 406	79.72 391	95.13 348	64.15 394	96.26 361	66.04 417	86.88 309	90.21 400

SixPastTwentyTwo		88.73 339	88.01 340	90.88 358	91.85 385	82.24 392	98.22 351	95.18 398	88.97 308	82.26 377	96.89 280	71.75 361	96.67 345	84.00 354	82.98 335	93.72 355

Gipuma		66.95 393	65.00 393	72.79 405	91.52 389	67.96 417	66.16 428	95.15 399	47.89 426	58.54 423	67.99 428	29.74 425	87.54 422	50.20 427	77.83 377	62.87 428
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
mmtdpeth		88.52 340	87.75 342	90.85 360	95.71 315	83.47 386	98.94 295	94.85 400	88.78 315	97.19 178	89.58 403	63.29 396	98.97 199	98.54 109	62.86 419	90.10 402

MVStest1		85.03 361	82.76 370	91.83 351	92.95 369	89.16 341	98.57 329	94.82 401	71.68 417	68.54 417	95.11 350	83.17 270	95.66 376	74.69 400	65.32 414	90.65 396

LF4IMVS		89.25 337	88.85 326	90.45 366	92.81 373	81.19 400	98.12 354	94.79 402	91.44 254	86.29 354	97.11 270	65.30 390	98.11 267	88.53 312	85.25 319	92.07 382

FPMVS		68.72 388	68.72 389	68.71 410	65.95 433	44.27 439	95.97 397	94.74 403	51.13 425	53.26 427	90.50 401	25.11 430	83.00 426	60.80 421	80.97 358	78.87 423

pmmvs-eth3d		84.03 369	81.97 373	90.20 368	84.15 416	87.09 363	98.10 356	94.73 404	83.05 383	74.10 410	87.77 412	65.56 388	94.01 396	81.08 374	69.24 404	89.49 409

test_fmvs2		89.47 333	89.70 309	88.77 381	94.54 337	75.74 409	99.83 143	94.70 405	94.71 120	91.08 270	96.82 287	54.46 412	97.78 286	92.87 254	88.27 296	92.80 374

TDRefinement		84.76 363	82.56 371	91.38 356	74.58 429	84.80 380	97.36 369	94.56 406	84.73 371	80.21 388	96.12 308	63.56 395	98.39 241	87.92 319	63.97 417	90.95 394

ambc				83.23 394	77.17 427	62.61 420	87.38 423	94.55 407		76.72 403	86.65 415	30.16 424	96.36 356	84.85 351	69.86 401	90.73 395

WB-MVS		76.28 384	77.28 386	73.29 404	81.18 421	54.68 429	97.87 362	94.19 408	81.30 392	69.43 415	90.70 400	77.02 324	82.06 427	35.71 432	68.11 409	83.13 418

TinyColmap		87.87 348	86.51 349	91.94 349	95.05 329	85.57 373	97.65 365	94.08 409	84.40 374	81.82 380	96.85 283	62.14 401	98.33 250	80.25 378	86.37 312	91.91 386

SSC-MVS		75.42 385	76.40 388	72.49 408	80.68 423	53.62 430	97.42 367	94.06 410	80.42 396	68.75 416	90.14 402	76.54 331	81.66 428	33.25 433	66.34 413	82.19 419

TransMVSNet (Re)		87.25 349	85.28 356	93.16 331	93.56 354	91.03 302	98.54 332	94.05 411	83.69 379	81.09 384	96.16 304	75.32 342	96.40 354	76.69 395	68.41 407	92.06 383

Baseline_NR-MVSNet		90.33 315	89.51 315	92.81 340	92.84 370	89.95 330	99.77 158	93.94 412	84.69 372	89.04 310	95.66 319	81.66 280	96.52 349	90.99 278	76.98 385	91.97 385

EGC-MVSNET		69.38 386	63.76 396	86.26 389	90.32 399	81.66 398	96.24 391	93.85 413	0.99 436	3.22 437	92.33 393	52.44 414	92.92 407	59.53 423	84.90 322	84.21 417

LCM-MVSNet		67.77 391	64.73 394	76.87 401	62.95 435	56.25 428	89.37 422	93.74 414	44.53 427	61.99 419	80.74 421	20.42 434	86.53 424	69.37 410	59.50 424	87.84 413

APD_test1		81.15 376	80.92 377	81.86 396	92.45 376	59.76 425	96.04 395	93.61 415	73.29 415	77.06 400	96.64 290	44.28 421	96.16 364	72.35 404	82.52 339	89.67 407

test_fmvs3		79.99 381	80.17 380	79.45 398	84.02 417	62.83 419	99.05 283	93.49 416	88.29 326	80.06 390	86.65 415	28.09 427	88.00 419	88.63 308	73.27 396	87.54 415

mvs5depth		84.87 362	82.90 369	90.77 362	85.59 414	84.84 379	91.10 418	93.29 417	83.14 382	85.07 364	94.33 374	62.17 400	97.32 302	78.83 386	72.59 398	90.14 401

test_f		78.40 383	77.59 385	80.81 397	80.82 422	62.48 422	96.96 379	93.08 418	83.44 380	74.57 409	84.57 419	27.95 428	92.63 408	84.15 352	72.79 397	87.32 416

Patchmatch-RL test		86.90 350	85.98 354	89.67 372	84.45 415	75.59 410	89.71 421	92.43 419	86.89 346	77.83 399	90.94 398	94.22 92	93.63 401	87.75 321	69.61 402	99.79 102

mvsany_test3		82.12 374	81.14 376	85.06 391	81.87 420	70.41 415	97.09 375	92.14 420	91.27 261	77.84 398	88.73 407	39.31 422	95.49 377	90.75 285	71.24 399	89.29 411

pmmvs3		80.27 379	77.77 384	87.76 386	80.32 424	82.43 391	98.23 350	91.97 421	72.74 416	78.75 393	87.97 411	57.30 410	90.99 415	70.31 407	62.37 420	89.87 404

LCM-MVSNet-Re		92.31 273	92.60 253	91.43 355	97.53 242	79.27 407	99.02 288	91.83 422	92.07 233	80.31 387	94.38 373	83.50 266	95.48 378	97.22 166	97.58 181	99.54 154

PM-MVS		80.47 378	78.88 383	85.26 390	83.79 418	72.22 413	95.89 398	91.08 423	85.71 361	76.56 404	88.30 408	36.64 423	93.90 398	82.39 366	69.57 403	89.66 408

door								90.31 424

dmvs_testset		83.79 370	86.07 352	76.94 400	92.14 380	48.60 435	96.75 382	90.27 425	89.48 298	78.65 394	98.55 220	79.25 307	86.65 423	66.85 414	82.69 337	95.57 282

DSMNet-mixed		88.28 343	88.24 337	88.42 383	89.64 404	75.38 411	98.06 357	89.86 426	85.59 362	88.20 327	92.14 394	76.15 337	91.95 412	78.46 387	96.05 214	97.92 253

door-mid								89.69 427

PMVS	49.05 23	53.75 396	51.34 400	60.97 413	40.80 439	34.68 440	74.82 427	89.62 428	37.55 429	28.67 435	72.12 424	7.09 439	81.63 429	43.17 430	68.21 408	66.59 427
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		65.23 394	62.94 397	72.13 409	44.90 438	50.03 434	81.05 425	89.42 429	38.45 428	48.51 430	99.90 18	54.09 413	78.70 430	91.84 267	18.26 432	87.64 414

PMMVS2		67.15 392	64.15 395	76.14 402	70.56 432	62.07 423	93.89 405	87.52 430	58.09 421	60.02 420	78.32 422	22.38 431	84.54 425	59.56 422	47.03 427	81.80 420

testf1		68.38 389	66.92 390	72.78 406	78.80 425	50.36 432	90.95 419	87.35 431	55.47 422	58.95 421	88.14 409	20.64 432	87.60 420	57.28 424	64.69 415	80.39 421

APD_test2		68.38 389	66.92 390	72.78 406	78.80 425	50.36 432	90.95 419	87.35 431	55.47 422	58.95 421	88.14 409	20.64 432	87.60 420	57.28 424	64.69 415	80.39 421

test_vis1_rt		86.87 351	86.05 353	89.34 374	96.12 295	78.07 408	99.87 117	83.54 433	92.03 236	78.21 397	89.51 404	45.80 419	99.91 99	96.25 185	93.11 265	90.03 403

ANet_high		56.10 395	52.24 398	67.66 411	49.27 437	56.82 427	83.94 424	82.02 434	70.47 418	33.28 434	64.54 429	17.23 436	69.16 432	45.59 429	23.85 431	77.02 424

MVE	53.74 22	51.54 398	47.86 402	62.60 412	59.56 436	50.93 431	79.41 426	77.69 435	35.69 431	36.27 433	61.76 432	5.79 441	69.63 431	37.97 431	36.61 428	67.24 426
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		52.30 397	52.18 399	52.67 414	71.51 430	45.40 436	93.62 408	76.60 436	36.01 430	43.50 431	64.13 430	27.11 429	67.31 433	31.06 434	26.06 429	45.30 432

EMVS		51.44 399	51.22 401	52.11 415	70.71 431	44.97 438	94.04 404	75.66 437	35.34 432	42.40 432	61.56 433	28.93 426	65.87 434	27.64 435	24.73 430	45.49 431

test_vis3_rt		68.82 387	66.69 392	75.21 403	76.24 428	60.41 424	96.44 386	68.71 438	75.13 411	50.54 429	69.52 427	16.42 437	96.32 358	80.27 377	66.92 412	68.89 425

N_pmnet		80.06 380	80.78 378	77.89 399	91.94 383	45.28 437	98.80 314	56.82 439	78.10 403	80.08 389	93.33 382	77.03 323	95.76 375	68.14 412	82.81 336	92.64 375

testmvs		40.60 400	44.45 403	29.05 417	19.49 441	14.11 443	99.68 191	18.47 440	20.74 433	64.59 418	98.48 225	10.95 438	17.09 437	56.66 426	11.01 433	55.94 430

test123		37.68 401	39.14 404	33.31 416	19.94 440	24.83 442	98.36 343	9.75 441	15.53 434	51.31 428	87.14 413	19.62 435	17.74 436	47.10 428	3.47 435	57.36 429

wuyk23d		20.37 403	20.84 406	18.99 418	65.34 434	27.73 441	50.43 429	7.67 442	9.50 435	8.01 436	6.34 436	6.13 440	26.24 435	23.40 436	10.69 434	2.99 433

mmdepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

monomultidepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

test_blank		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.02 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet_test		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

DCPMVS		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

pcd_1.5k_mvsjas		7.60 405	10.13 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	91.20 167	0.00 438	0.00 437	0.00 436	0.00 434

sosnet-low-res		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uncertanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

Regformer		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

n2								0.00 443

nn								0.00 443

ab-mvs-re		8.28 404	11.04 407	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	99.40 135	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 438	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

WAC-MVS						90.97 303								86.10 342

PC_three_1452									96.96 54	99.80 22	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

eth-test2					0.00 442

eth-test					0.00 442

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 42				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

test_0728_THIRD									96.48 70	99.83 18	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 140

test_part2					99.89 45	99.25 18				99.49 70

sam_mvs1												94.72 71				99.59 140

sam_mvs												94.25 91

test_post1							95.78 399				59.23 434	93.20 125	97.74 287	91.06 276

test_post											63.35 431	94.43 79	98.13 266

patchmatchnet-post											91.70 395	95.12 56	97.95 278

gm-plane-assit					96.97 270	93.76 239			91.47 253		98.96 175		98.79 209	94.92 206

test9_res														99.71 40	99.99 21	100.00 1

agg_prior2														99.48 53	100.00 1	100.00 1

test_prior4						98.05 75	99.94 78

test_prior2							99.95 61		95.78 90	99.73 39	99.76 66	96.00 37		99.78 28	100.00 1

旧先验2							99.46 233		94.21 146	99.85 14			99.95 76	96.96 175

新几何2							99.40 237

原ACMM2							99.90 102

testdata2													99.99 36	90.54 289

segment_acmp												96.68 29

testdata1							99.28 258		96.35 80

plane_prior7					95.71 315	91.59 297

plane_prior6					95.76 309	91.72 292						80.47 299

plane_prior4											98.59 213

plane_prior3						91.64 295			96.63 67	93.01 249

plane_prior2							99.84 136		96.38 76

plane_prior1					95.73 312

plane_prior						91.74 289	99.86 128		96.76 62						89.59 276

HQP5-MVS						91.85 285

HQP-NCC					95.78 305		99.87 117		96.82 58	93.37 244

ACMP_Plane					95.78 305		99.87 117		96.82 58	93.37 244

BP-MVS														97.92 143

HQP4-MVS										93.37 244			98.39 241			94.53 284

HQP2-MVS												80.65 295

NP-MVS					95.77 308	91.79 287					98.65 208

MDTV_nov1_ep13_2view						96.26 153	96.11 393		91.89 239	98.06 150		94.40 81		94.30 224		99.67 120

ACMMP++_ref															87.04 308

ACMMP++															88.23 297

Test By Simon												92.82 136

High-resolution multi-view benchmark