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.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 3	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 6

fmvsm_s_conf0.5_n_9		97.98 65	98.32 48	96.96 194	98.92 136	91.45 259	95.87 237	99.53 26	97.44 86	99.56 19	99.05 62	95.34 175	99.67 156	99.52 2	99.70 94	99.77 15

fmvsm_s_conf0.5_n_10		97.74 104	98.11 60	96.62 221	98.72 168	90.95 274	95.99 225	99.50 28	96.22 151	99.20 45	98.93 77	95.13 186	99.77 70	99.49 3	99.76 69	99.15 189

fmvsm_s_conf0.1_n_2		97.68 111	98.18 56	96.20 261	99.06 110	89.08 319	95.51 265	99.72 6	96.06 163	99.48 22	99.24 36	95.18 182	99.60 194	99.45 4	99.88 28	99.94 3

test_fmvsmvis_n_1920		98.08 56	98.47 33	96.93 197	99.03 118	93.29 203	96.32 190	99.65 13	95.59 195	99.71 8	99.01 66	97.66 38	99.60 194	99.44 5	99.83 52	97.90 368

fmvsm_s_conf0.5_n_2		97.59 123	98.07 64	96.17 265	98.78 160	89.10 318	95.33 283	99.55 24	95.96 172	99.41 31	99.10 56	95.18 182	99.59 196	99.43 6	99.86 35	99.81 10

test_fmvsmconf0.01_n		98.57 22	98.74 20	98.06 99	99.39 49	94.63 147	96.70 168	99.82 1	95.44 205	99.64 14	99.52 12	98.96 4	99.74 94	99.38 7	99.86 35	99.81 10

fmvsm_s_conf0.5_n_3		97.88 87	98.37 41	96.41 245	98.73 165	89.82 297	95.94 232	99.49 29	96.81 118	99.09 53	99.03 65	97.09 66	99.65 167	99.37 8	99.76 69	99.76 21

mamv4		99.05 8	98.91 11	99.46 2	98.94 129	99.62 2	97.98 67	99.70 8	99.49 6	99.78 3	99.22 39	95.92 144	99.95 3	99.31 9	99.83 52	98.83 262

fmvsm_s_conf0.5_n_4		97.43 138	97.77 101	96.39 249	98.48 216	89.89 295	95.65 255	99.26 47	94.73 236	98.72 95	98.58 120	95.58 166	99.57 205	99.28 10	99.67 103	99.73 26

v7n		98.73 15	98.99 8	97.95 109	99.64 14	94.20 167	98.67 18	99.14 69	99.08 17	99.42 29	99.23 38	96.53 114	99.91 14	99.27 11	99.93 11	99.73 26

test_fmvs3		97.38 143	97.56 129	96.84 207	98.63 188	92.81 215	97.60 101	99.61 18	90.87 359	98.76 91	99.66 6	94.03 224	97.90 439	99.24 12	99.68 100	99.81 10

test_fmvsmconf0.1_n		98.41 35	98.54 31	98.03 104	99.16 90	94.61 148	96.18 202	99.73 5	95.05 224	99.60 18	99.34 29	98.68 8	99.72 108	99.21 13	99.85 45	99.76 21

test_fmvsm_n_1920		98.08 56	98.29 52	97.43 155	98.88 143	93.95 176	96.17 206	99.57 21	95.66 190	99.52 21	98.71 103	97.04 73	99.64 173	99.21 13	99.87 33	98.69 287

Elysia		98.19 47	98.37 41	97.66 130	99.28 62	93.52 193	97.35 120	98.90 141	98.63 33	99.45 25	98.32 157	94.31 216	99.91 14	99.19 15	99.88 28	99.54 71

StellarMVS		98.19 47	98.37 41	97.66 130	99.28 62	93.52 193	97.35 120	98.90 141	98.63 33	99.45 25	98.32 157	94.31 216	99.91 14	99.19 15	99.88 28	99.54 71

fmvsm_s_conf0.5_n_8		97.66 113	98.12 58	96.27 255	98.79 156	89.43 309	95.76 245	99.42 34	97.49 84	99.16 48	99.04 63	94.56 208	99.69 141	99.18 17	99.73 82	99.70 31

fmvsm_l_conf0.5_n_9		97.92 79	98.37 41	96.57 228	98.94 129	90.54 284	95.39 275	99.58 19	96.82 117	99.56 19	98.77 94	97.23 60	99.61 191	99.17 18	99.86 35	99.57 57

MM		96.87 180	96.62 198	97.62 134	97.72 322	93.30 202	96.39 182	92.61 424	97.90 65	96.76 277	98.64 113	90.46 305	99.81 44	99.16 19	99.94 8	99.76 21

fmvsm_s_conf0.5_n_6		97.45 134	97.79 96	96.44 238	98.58 196	90.31 288	95.77 244	99.33 38	94.52 247	98.85 79	98.44 139	95.68 160	99.62 183	99.15 20	99.81 57	99.38 135

test_fmvsmconf_n		98.30 41	98.41 40	97.99 107	98.94 129	94.60 149	96.00 222	99.64 16	94.99 227	99.43 28	99.18 46	98.51 12	99.71 124	99.13 21	99.84 48	99.67 34

fmvsm_s_conf0.5_n_5		97.63 117	97.83 91	97.04 189	98.77 162	92.33 227	95.63 260	99.58 19	93.53 287	99.10 52	98.66 108	96.44 122	99.65 167	99.12 22	99.68 100	99.12 203

fmvsm_l_conf0.5_n_3		98.29 42	98.46 34	97.79 118	98.90 141	94.05 172	96.06 214	99.63 17	96.07 162	99.37 33	98.93 77	98.29 16	99.68 147	99.11 23	99.79 63	99.65 39

fmvsm_l_conf0.5_n		97.68 111	97.81 94	97.27 168	98.92 136	92.71 220	95.89 236	99.41 37	93.36 294	99.00 62	98.44 139	96.46 121	99.65 167	99.09 24	99.76 69	99.45 110

fmvsm_l_conf0.5_n_a		97.60 120	97.76 102	97.11 180	98.92 136	92.28 230	95.83 240	99.32 39	93.22 300	98.91 73	98.49 131	96.31 129	99.64 173	99.07 25	99.76 69	99.40 128

fmvsm_s_conf0.1_n_a		97.80 99	98.01 72	97.18 175	99.17 89	92.51 223	96.57 172	99.15 66	93.68 283	98.89 74	99.30 32	96.42 124	99.37 279	99.03 26	99.83 52	99.66 36

fmvsm_s_conf0.1_n		97.73 105	98.02 70	96.85 205	99.09 105	91.43 261	96.37 186	99.11 73	94.19 264	99.01 60	99.25 35	96.30 130	99.38 274	99.00 27	99.88 28	99.73 26

fmvsm_s_conf0.5_n_a		97.65 114	97.83 91	97.13 179	98.80 153	92.51 223	96.25 197	99.06 91	93.67 284	98.64 101	99.00 67	96.23 134	99.36 283	98.99 28	99.80 61	99.53 76

fmvsm_s_conf0.5_n		97.62 118	97.89 83	96.80 210	98.79 156	91.44 260	96.14 208	99.06 91	94.19 264	98.82 83	98.98 70	96.22 135	99.38 274	98.98 29	99.86 35	99.58 49

mvs_tets		98.90 9	98.94 9	98.75 35	99.69 11	96.48 64	98.54 26	99.22 50	96.23 150	99.71 8	99.48 15	98.77 7	99.93 4	98.89 30	99.95 5	99.84 8

test_fmvs2		96.38 219	96.45 216	96.16 266	97.85 287	91.30 262	96.81 154	99.45 31	89.24 381	98.49 117	99.38 23	88.68 330	97.62 444	98.83 31	99.32 236	99.57 57

PS-MVSNAJss		98.53 28	98.63 24	98.21 86	99.68 12	94.82 140	98.10 59	99.21 51	96.91 114	99.75 6	99.45 18	95.82 151	99.92 6	98.80 32	99.96 4	99.89 4

jajsoiax		98.77 13	98.79 16	98.74 38	99.66 13	96.48 64	98.45 34	99.12 72	95.83 184	99.67 11	99.37 24	98.25 17	99.92 6	98.77 33	99.94 8	99.82 9

v10		97.55 125	97.97 76	96.31 253	98.60 192	89.64 303	97.44 115	99.02 110	96.60 126	98.72 95	99.16 50	93.48 240	99.72 108	98.76 34	99.92 15	99.58 49

KinetiMVS		97.82 96	98.02 70	97.24 173	99.24 70	92.32 229	96.92 145	98.38 252	98.56 40	99.03 57	98.33 154	93.22 245	99.83 36	98.74 35	99.71 90	99.57 57

MVSFormer		96.14 231	96.36 223	95.49 305	97.68 325	87.81 353	98.67 18	99.02 110	96.50 135	94.48 371	96.15 363	86.90 352	99.92 6	98.73 36	99.13 265	98.74 279

test_djsdf		98.73 15	98.74 20	98.69 43	99.63 15	96.30 72	98.67 18	99.02 110	96.50 135	99.32 37	99.44 19	97.43 46	99.92 6	98.73 36	99.95 5	99.86 5

OurMVSNet-221017-0		98.61 20	98.61 28	98.63 48	99.77 5	96.35 69	99.17 7	99.05 97	98.05 61	99.61 17	99.52 12	93.72 234	99.88 23	98.72 38	99.88 28	99.65 39

tt0805		97.44 136	97.56 129	97.11 180	99.55 24	96.36 68	98.66 21	95.66 375	98.31 48	97.09 252	95.45 388	97.17 62	98.50 413	98.67 39	97.45 394	96.48 431

v8		97.60 120	98.06 67	96.23 258	98.71 172	89.44 308	97.43 117	98.82 180	97.29 100	98.74 93	99.10 56	93.86 228	99.68 147	98.61 40	99.94 8	99.56 65

anonymousdsp		98.72 18	98.63 24	98.99 14	99.62 16	97.29 41	98.65 22	99.19 55	95.62 193	99.35 36	99.37 24	97.38 48	99.90 18	98.59 41	99.91 19	99.77 15

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 41	99.71 10	96.99 48	99.69 2	99.57 21	99.02 22	99.62 16	99.36 26	98.53 11	99.52 220	98.58 42	99.95 5	99.66 36
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
mmtdpeth		98.33 37	98.53 32	97.71 124	99.07 108	93.44 197	98.80 15	99.78 4	99.10 16	96.61 289	99.63 10	95.42 172	99.73 100	98.53 43	99.86 35	99.95 2

mvs5depth		98.06 59	98.58 30	96.51 234	98.97 125	89.65 302	99.43 4	99.81 2	99.30 10	98.36 135	99.86 2	93.15 247	99.88 23	98.50 44	99.84 48	99.99 1

v1240		96.74 192	97.02 171	95.91 280	98.18 254	88.52 330	95.39 275	98.88 152	93.15 309	98.46 122	98.40 146	92.80 258	99.71 124	98.45 45	99.49 177	99.49 94

fmvsm_s_conf0.5_n_7		97.13 159	97.50 138	96.04 270	98.43 223	89.03 320	94.92 313	99.00 121	94.51 248	98.42 126	98.96 73	94.97 193	99.54 214	98.42 46	99.85 45	99.56 65

MVSMamba_PlusPlus		97.43 138	97.98 75	95.78 285	98.88 143	89.70 299	98.03 65	98.85 161	99.18 14	96.84 271	99.12 54	93.04 251	99.91 14	98.38 47	99.55 147	97.73 382

v1192		96.83 185	97.06 168	96.15 267	98.28 239	89.29 311	95.36 278	98.77 191	93.73 279	98.11 168	98.34 153	93.02 255	99.67 156	98.35 48	99.58 135	99.50 86

v1921920		96.72 196	96.96 175	95.99 272	98.21 248	88.79 326	95.42 271	98.79 186	93.22 300	98.19 161	98.26 173	92.68 261	99.70 133	98.34 49	99.55 147	99.49 94

MGCNet		95.71 252	95.18 270	97.33 163	94.85 440	92.82 213	95.36 278	90.89 442	95.51 200	95.61 342	97.82 236	88.39 334	99.78 59	98.23 50	99.91 19	99.40 128

Anonymous20231211		98.55 25	98.76 17	97.94 110	98.79 156	94.37 159	98.84 14	99.15 66	99.37 7	99.67 11	99.43 20	95.61 164	99.72 108	98.12 51	99.86 35	99.73 26

tt0320		99.07 6	99.29 4	98.43 63	99.55 24	95.92 87	98.97 10	99.53 26	99.67 3	99.79 2	99.71 3	98.33 14	99.78 59	98.11 52	99.92 15	99.57 57

v144192		96.69 199	96.90 181	96.03 271	98.25 244	88.92 321	95.49 266	98.77 191	93.05 311	98.09 171	98.29 167	92.51 272	99.70 133	98.11 52	99.56 141	99.47 104

test_fmvs1_n		95.21 280	95.28 266	94.99 327	98.15 261	89.13 317	96.81 154	99.43 33	86.97 411	97.21 238	98.92 80	83.00 386	97.13 448	98.09 54	98.94 288	98.72 282

Anonymous20240521		97.07 165	97.51 136	95.76 286	99.35 56	88.18 341	97.78 82	98.40 249	97.11 104	98.34 139	99.04 63	89.58 318	99.79 54	98.09 54	99.93 11	99.30 153

sc_t1		99.09 5	99.28 5	98.53 55	99.72 8	96.21 74	98.87 12	99.19 55	99.71 2	99.76 5	99.65 8	98.64 9	99.79 54	98.07 56	99.90 25	99.58 49

v1144		96.84 182	97.08 166	96.13 268	98.42 225	89.28 312	95.41 273	98.67 213	94.21 262	97.97 189	98.31 159	93.06 250	99.65 167	98.06 57	99.62 114	99.45 110

tt0320-xc		99.10 4	99.31 3	98.49 58	99.57 20	96.09 80	98.91 11	99.55 24	99.67 3	99.78 3	99.69 4	98.63 10	99.77 70	98.02 58	99.93 11	99.60 45

SixPastTwentyTwo		97.49 130	97.57 128	97.26 170	99.56 22	92.33 227	98.28 45	96.97 347	98.30 50	99.45 25	99.35 28	88.43 333	99.89 21	98.01 59	99.76 69	99.54 71

LuminaMVS		96.76 191	96.58 202	97.30 165	98.94 129	92.96 211	96.17 206	96.15 363	95.54 199	98.96 68	98.18 185	87.73 344	99.80 51	97.98 60	99.61 120	99.15 189

test_vis1_n_1920		95.77 249	96.41 219	93.85 375	98.55 201	84.86 405	95.91 235	99.71 7	92.72 324	97.67 209	98.90 84	87.44 347	98.73 388	97.96 61	98.85 301	97.96 364

WR-MVS_H		98.65 19	98.62 26	98.75 35	99.51 31	96.61 60	98.55 25	99.17 59	99.05 20	99.17 47	98.79 90	95.47 169	99.89 21	97.95 62	99.91 19	99.75 24

BP-MVS1		95.36 272	94.86 287	96.89 202	98.35 231	91.72 252	96.76 160	95.21 389	96.48 138	96.23 313	97.19 294	75.97 422	99.80 51	97.91 63	99.60 127	99.15 189

UA-Net		98.88 11	98.76 17	99.22 3	99.11 102	97.89 17	99.47 3	99.32 39	99.08 17	97.87 201	99.67 5	96.47 119	99.92 6	97.88 64	99.98 2	99.85 6

test_fmvs1		94.51 316	94.60 303	94.26 369	95.91 410	87.92 348	95.35 281	99.02 110	86.56 415	96.79 272	98.52 128	82.64 388	97.00 451	97.87 65	98.71 320	97.88 370

FC-MVSNet-test		98.16 49	98.37 41	97.56 137	99.49 35	93.10 208	98.35 38	99.21 51	98.43 43	98.89 74	98.83 89	94.30 218	99.81 44	97.87 65	99.91 19	99.77 15

Vis-MVSNet		98.27 43	98.34 46	98.07 97	99.33 58	95.21 131	98.04 63	99.46 30	97.32 98	97.82 205	99.11 55	96.75 100	99.86 28	97.84 67	99.36 221	99.15 189
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
K. test v3		96.44 214	96.28 227	96.95 195	99.41 45	91.53 255	97.65 98	90.31 450	98.89 27	98.93 70	99.36 26	84.57 374	99.92 6	97.81 68	99.56 141	99.39 133

v2v482		96.78 189	97.06 168	95.95 277	98.57 198	88.77 327	95.36 278	98.26 265	95.18 217	97.85 203	98.23 177	92.58 265	99.63 178	97.80 69	99.69 96	99.45 110

PS-CasMVS		98.73 15	98.85 14	98.39 67	99.55 24	95.47 111	98.49 31	99.13 71	99.22 13	99.22 44	98.96 73	97.35 49	99.92 6	97.79 70	99.93 11	99.79 13

MVStest1		91.89 380	91.45 375	93.21 393	89.01 473	84.87 404	95.82 242	95.05 392	91.50 348	98.75 92	99.19 42	57.56 459	95.11 462	97.78 71	98.37 348	99.64 43

nrg030		98.54 26	98.62 26	98.32 72	99.22 76	95.66 99	97.90 75	99.08 86	98.31 48	99.02 59	98.74 98	97.68 35	99.61 191	97.77 72	99.85 45	99.70 31

pmmvs6		99.07 6	99.24 7	98.56 52	99.81 2	96.38 66	98.87 12	99.30 41	99.01 23	99.63 15	99.66 6	99.27 2	99.68 147	97.75 73	99.89 26	99.62 44

ACMH	93.61 9	98.44 33	98.76 17	97.51 142	99.43 42	93.54 192	98.23 49	99.05 97	97.40 93	99.37 33	99.08 60	98.79 6	99.47 236	97.74 74	99.71 90	99.50 86
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_f		95.82 247	95.88 250	95.66 294	97.61 337	93.21 207	95.61 261	98.17 279	86.98 410	98.42 126	99.47 16	90.46 305	94.74 465	97.71 75	98.45 343	99.03 221

DTE-MVSNet		98.79 12	98.86 12	98.59 50	99.55 24	96.12 78	98.48 33	99.10 77	99.36 8	99.29 39	99.06 61	97.27 53	99.93 4	97.71 75	99.91 19	99.70 31

test_vis1_n		95.67 256	95.89 249	95.03 324	98.18 254	89.89 295	96.94 144	99.28 45	88.25 397	98.20 157	98.92 80	86.69 355	97.19 447	97.70 77	98.82 305	98.00 362

EC-MVSNet		97.90 85	97.94 79	97.79 118	98.66 180	95.14 132	98.31 42	99.66 12	97.57 79	95.95 326	97.01 313	96.99 77	99.82 39	97.66 78	99.64 109	98.39 316

PEN-MVS		98.75 14	98.85 14	98.44 62	99.58 19	95.67 98	98.45 34	99.15 66	99.33 9	99.30 38	99.00 67	97.27 53	99.92 6	97.64 79	99.92 15	99.75 24

AstraMVS		96.41 218	96.48 215	96.20 261	98.91 139	89.69 300	96.28 192	93.29 414	96.11 158	98.70 97	98.36 149	89.41 325	99.66 164	97.60 80	99.63 111	99.26 166

CP-MVSNet		98.42 34	98.46 34	98.30 75	99.46 39	95.22 129	98.27 47	98.84 165	99.05 20	99.01 60	98.65 112	95.37 174	99.90 18	97.57 81	99.91 19	99.77 15

EI-MVSNet-UG-set		97.32 149	97.40 142	97.09 184	97.34 361	92.01 245	95.33 283	97.65 320	97.74 70	98.30 147	98.14 188	95.04 188	99.69 141	97.55 82	99.52 165	99.58 49

ANet_high		98.31 40	98.94 9	96.41 245	99.33 58	89.64 303	97.92 73	99.56 23	99.27 11	99.66 13	99.50 14	97.67 36	99.83 36	97.55 82	99.98 2	99.77 15

CS-MVS		98.09 55	98.01 72	98.32 72	98.45 221	96.69 56	98.52 29	99.69 9	98.07 60	96.07 322	97.19 294	96.88 92	99.86 28	97.50 84	99.73 82	98.41 313

EI-MVSNet-Vis-set		97.32 149	97.39 143	97.11 180	97.36 358	92.08 242	95.34 282	97.65 320	97.74 70	98.29 148	98.11 195	95.05 187	99.68 147	97.50 84	99.50 174	99.56 65

EU-MVSNet		94.25 322	94.47 311	93.60 382	98.14 263	82.60 427	97.24 127	92.72 421	85.08 429	98.48 119	98.94 76	82.59 389	98.76 386	97.47 86	99.53 157	99.44 120

lecture		98.59 21	98.60 29	98.55 53	99.48 36	96.38 66	98.08 61	99.09 82	98.46 42	98.68 100	98.73 99	97.88 27	99.80 51	97.43 87	99.59 130	99.48 100

TestfortrainingZip a		97.99 64	97.86 86	98.38 68	99.36 53	95.77 93	97.75 86	99.30 41	94.02 272	98.88 76	97.54 262	96.99 77	99.73 100	97.40 88	99.53 157	99.65 39

V42		97.04 166	97.16 162	96.68 219	98.59 194	91.05 267	96.33 189	98.36 255	94.60 242	97.99 183	98.30 163	93.32 242	99.62 183	97.40 88	99.53 157	99.38 135

guyue		96.21 227	96.29 226	95.98 274	98.80 153	89.14 316	96.40 180	94.34 402	95.99 171	98.58 108	98.13 190	87.42 348	99.64 173	97.39 90	99.55 147	99.16 188

KD-MVS_self_test		97.86 91	98.07 64	97.25 171	99.22 76	92.81 215	97.55 106	98.94 137	97.10 105	98.85 79	98.88 86	95.03 189	99.67 156	97.39 90	99.65 107	99.26 166

VortexMVS		96.04 235	96.56 205	94.49 358	97.60 339	84.36 412	96.05 215	98.67 213	94.74 234	98.95 69	98.78 93	87.13 351	99.50 225	97.37 92	99.76 69	99.60 45

lessismore_v0				97.05 187	99.36 53	92.12 238		84.07 467		98.77 90	98.98 70	85.36 366	99.74 94	97.34 93	99.37 217	99.30 153

FIs		97.93 78	98.07 64	97.48 150	99.38 51	92.95 212	98.03 65	99.11 73	98.04 62	98.62 103	98.66 108	93.75 233	99.78 59	97.23 94	99.84 48	99.73 26

UniMVSNet_ETH3D		99.12 3	99.28 5	98.65 46	99.77 5	96.34 70	99.18 6	99.20 53	99.67 3	99.73 7	99.65 8	99.15 3	99.86 28	97.22 95	99.92 15	99.77 15

MVS_Test		96.27 223	96.79 190	94.73 344	96.94 379	86.63 375	96.18 202	98.33 259	94.94 228	96.07 322	98.28 168	95.25 180	99.26 317	97.21 96	97.90 368	98.30 329

TDRefinement		98.90 9	98.86 12	99.02 10	99.54 28	98.06 9	99.34 5	99.44 32	98.85 28	99.00 62	99.20 41	97.42 47	99.59 196	97.21 96	99.76 69	99.40 128

EG-PatchMatch MVS		97.69 109	97.79 96	97.40 159	99.06 110	93.52 193	95.96 230	98.97 131	94.55 246	98.82 83	98.76 97	97.31 51	99.29 309	97.20 98	99.44 193	99.38 135

GDP-MVS		95.39 271	94.89 284	96.90 201	98.26 243	91.91 247	96.48 178	99.28 45	95.06 223	96.54 296	97.12 303	74.83 426	99.82 39	97.19 99	99.27 245	98.96 236

VPA-MVSNet		98.27 43	98.46 34	97.70 126	99.06 110	93.80 181	97.76 85	99.00 121	98.40 45	99.07 56	98.98 70	96.89 90	99.75 85	97.19 99	99.79 63	99.55 69

test_vis3_rt		97.04 166	96.98 172	97.23 174	98.44 222	95.88 88	96.82 153	99.67 10	90.30 368	99.27 40	99.33 31	94.04 223	96.03 460	97.14 101	97.83 371	99.78 14

UniMVSNet (Re)		97.83 93	97.65 114	98.35 71	98.80 153	95.86 90	95.92 234	99.04 105	97.51 83	98.22 156	97.81 238	94.68 201	99.78 59	97.14 101	99.75 79	99.41 127

reproduce_model		98.54 26	98.33 47	99.15 4	99.06 110	98.04 12	97.04 139	99.09 82	98.42 44	99.03 57	98.71 103	96.93 83	99.83 36	97.09 103	99.63 111	99.56 65

pm-mvs1		98.47 32	98.67 22	97.86 114	99.52 30	94.58 150	98.28 45	99.00 121	97.57 79	99.27 40	99.22 39	98.32 15	99.50 225	97.09 103	99.75 79	99.50 86

baseline		97.44 136	97.78 100	96.43 240	98.52 205	90.75 279	96.84 151	99.03 106	96.51 134	97.86 202	98.02 211	96.67 102	99.36 283	97.09 103	99.47 184	99.19 181

IterMVS-SCA-FT		95.86 245	96.19 231	94.85 335	97.68 325	85.53 391	92.42 407	97.63 324	96.99 106	98.36 135	98.54 127	87.94 338	99.75 85	97.07 106	99.08 274	99.27 165

balanced_conf03		96.88 179	97.29 152	95.63 295	97.66 330	89.47 307	97.95 70	98.89 145	95.94 175	97.77 208	98.55 125	92.23 276	99.68 147	97.05 107	99.61 120	97.73 382

UniMVSNet_NR-MVSNet		97.83 93	97.65 114	98.37 69	98.72 168	95.78 91	95.66 253	99.02 110	98.11 58	98.31 145	97.69 251	94.65 203	99.85 31	97.02 108	99.71 90	99.48 100

DU-MVS		97.79 100	97.60 125	98.36 70	98.73 165	95.78 91	95.65 255	98.87 154	97.57 79	98.31 145	97.83 233	94.69 199	99.85 31	97.02 108	99.71 90	99.46 106

casdiffmvs_mvg		97.83 93	98.11 60	97.00 193	98.57 198	92.10 241	95.97 228	99.18 57	97.67 78	99.00 62	98.48 135	97.64 39	99.50 225	96.96 110	99.54 153	99.40 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet		96.63 202	96.93 177	95.74 288	97.26 366	88.13 344	95.29 289	97.65 320	96.99 106	97.94 193	98.19 182	92.55 267	99.58 199	96.91 111	99.56 141	99.50 86

IterMVS-LS		96.92 175	97.29 152	95.79 284	98.51 207	88.13 344	95.10 301	98.66 216	96.99 106	98.46 122	98.68 107	92.55 267	99.74 94	96.91 111	99.79 63	99.50 86
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SPE-MVS-test		97.91 83	97.84 88	98.14 93	98.52 205	96.03 84	98.38 37	99.67 10	98.11 58	95.50 347	96.92 320	96.81 98	99.87 26	96.87 113	99.76 69	98.51 305

reproduce-ours		98.48 30	98.27 53	99.12 5	98.99 121	98.02 13	96.81 154	99.02 110	98.29 51	98.97 66	98.61 115	97.27 53	99.82 39	96.86 114	99.61 120	99.51 83

our_new_method		98.48 30	98.27 53	99.12 5	98.99 121	98.02 13	96.81 154	99.02 110	98.29 51	98.97 66	98.61 115	97.27 53	99.82 39	96.86 114	99.61 120	99.51 83

test_cas_vis1_n_1920		95.34 274	95.67 258	94.35 364	98.21 248	86.83 373	95.61 261	99.26 47	90.45 366	98.17 162	98.96 73	84.43 375	98.31 427	96.74 116	99.17 260	97.90 368

test1111		94.53 315	94.81 292	93.72 379	99.06 110	81.94 432	98.31 42	83.87 468	96.37 141	98.49 117	99.17 49	81.49 391	99.73 100	96.64 117	99.86 35	99.49 94

APDe-MVS		98.14 50	98.03 69	98.47 61	98.72 168	96.04 82	98.07 62	99.10 77	95.96 172	98.59 107	98.69 106	96.94 81	99.81 44	96.64 117	99.58 135	99.57 57
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS-pluss		97.69 109	97.36 147	98.70 42	99.50 34	96.84 51	95.38 277	98.99 125	92.45 329	98.11 168	98.31 159	97.25 58	99.77 70	96.60 119	99.62 114	99.48 100
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mvs_anonymous		95.36 272	96.07 237	93.21 393	96.29 394	81.56 434	94.60 329	97.66 318	93.30 297	96.95 263	98.91 83	93.03 254	99.38 274	96.60 119	97.30 399	98.69 287

casdiffmvs		97.50 129	97.81 94	96.56 230	98.51 207	91.04 268	95.83 240	99.09 82	97.23 101	98.33 142	98.30 163	97.03 74	99.37 279	96.58 121	99.38 216	99.28 161
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TransMVSNet (Re)		98.38 36	98.67 22	97.51 142	99.51 31	93.39 201	98.20 54	98.87 154	98.23 54	99.48 22	99.27 34	98.47 13	99.55 211	96.52 122	99.53 157	99.60 45

HPM-MVS_fast		98.32 39	98.13 57	98.88 27	99.54 28	97.48 34	98.35 38	99.03 106	95.88 180	97.88 198	98.22 180	98.15 20	99.74 94	96.50 123	99.62 114	99.42 125

MIMVSNet1		98.51 29	98.45 37	98.67 44	99.72 8	96.71 54	98.76 16	98.89 145	98.49 41	99.38 32	99.14 53	95.44 171	99.84 34	96.47 124	99.80 61	99.47 104

viewdifsd2359ckpt11		97.13 159	97.62 121	95.67 292	98.64 181	88.36 334	94.84 318	98.95 134	96.24 148	98.70 97	98.61 115	96.66 103	99.29 309	96.46 125	99.45 190	99.36 142

viewmsd2359difaftdt		97.13 159	97.62 121	95.67 292	98.64 181	88.36 334	94.84 318	98.95 134	96.24 148	98.70 97	98.61 115	96.66 103	99.29 309	96.46 125	99.45 190	99.36 142

TranMVSNet+NR-MVSNet		98.33 37	98.30 51	98.43 63	99.07 108	95.87 89	96.73 166	99.05 97	98.67 31	98.84 81	98.45 137	97.58 43	99.88 23	96.45 127	99.86 35	99.54 71

diffmvs_AUTHOR		96.50 209	96.81 186	95.57 298	98.03 270	88.26 338	93.73 367	99.14 69	94.92 231	97.24 235	97.84 232	94.62 204	99.33 292	96.44 128	99.37 217	99.13 197

MGCFI-Net		97.20 155	97.23 157	97.08 185	97.68 325	93.71 185	97.79 81	99.09 82	97.40 93	96.59 290	93.96 413	97.67 36	99.35 287	96.43 129	98.50 340	98.17 344

test2506		89.86 405	89.16 410	91.97 423	98.95 126	76.83 460	98.54 26	61.07 478	96.20 152	97.07 253	99.16 50	55.19 471	99.69 141	96.43 129	99.83 52	99.38 135

Gipuma		98.07 58	98.31 49	97.36 161	99.76 7	96.28 73	98.51 30	99.10 77	98.76 30	96.79 272	99.34 29	96.61 108	98.82 378	96.38 131	99.50 174	96.98 410
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
reproduce_monomvs		92.05 377	92.26 364	91.43 428	95.42 431	75.72 464	95.68 251	97.05 344	94.47 253	97.95 192	98.35 151	55.58 468	99.05 354	96.36 132	99.44 193	99.51 83

MVSTER		94.21 325	93.93 332	95.05 323	95.83 416	86.46 376	95.18 297	97.65 320	92.41 330	97.94 193	98.00 215	72.39 438	99.58 199	96.36 132	99.56 141	99.12 203

GeoE		97.75 103	97.70 106	97.89 112	98.88 143	94.53 151	97.10 135	98.98 128	95.75 188	97.62 210	97.59 258	97.61 42	99.77 70	96.34 134	99.44 193	99.36 142

SSC-MVS3.2		95.75 251	96.56 205	93.34 386	98.69 177	80.75 441	91.60 424	97.43 331	97.37 96	96.99 258	97.02 310	93.69 235	99.71 124	96.32 135	99.89 26	99.55 69

sasdasda		97.23 153	97.21 159	97.30 165	97.65 332	94.39 156	97.84 78	99.05 97	97.42 88	96.68 281	93.85 415	97.63 40	99.33 292	96.29 136	98.47 341	98.18 342

canonicalmvs		97.23 153	97.21 159	97.30 165	97.65 332	94.39 156	97.84 78	99.05 97	97.42 88	96.68 281	93.85 415	97.63 40	99.33 292	96.29 136	98.47 341	98.18 342

testf1		98.57 22	98.45 37	98.93 22	99.79 3	98.78 3	97.69 94	99.42 34	97.69 75	98.92 71	98.77 94	97.80 30	99.25 320	96.27 138	99.69 96	98.76 277

APD_test2		98.57 22	98.45 37	98.93 22	99.79 3	98.78 3	97.69 94	99.42 34	97.69 75	98.92 71	98.77 94	97.80 30	99.25 320	96.27 138	99.69 96	98.76 277

alignmvs		96.01 238	95.52 264	97.50 146	97.77 314	94.71 142	96.07 212	96.84 350	97.48 85	96.78 276	94.28 410	85.50 365	99.40 264	96.22 140	98.73 319	98.40 314

tttt0517		93.31 353	92.56 361	95.57 298	98.71 172	87.86 350	97.44 115	87.17 462	95.79 185	97.47 224	96.84 324	64.12 452	99.81 44	96.20 141	99.32 236	99.02 224

DeepC-MVS	95.41 4	97.82 96	97.70 106	98.16 89	98.78 160	95.72 94	96.23 200	99.02 110	93.92 276	98.62 103	98.99 69	97.69 34	99.62 183	96.18 142	99.87 33	99.15 189
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MTAPA		98.14 50	97.84 88	99.06 7	99.44 41	97.90 16	97.25 125	98.73 198	97.69 75	97.90 196	97.96 218	95.81 155	99.82 39	96.13 143	99.61 120	99.45 110

ZNCC-MVS		97.92 79	97.62 121	98.83 29	99.32 60	97.24 43	97.45 114	98.84 165	95.76 186	96.93 264	97.43 273	97.26 57	99.79 54	96.06 144	99.53 157	99.45 110

Patchmatch-RL test		94.66 308	94.49 309	95.19 315	98.54 203	88.91 322	92.57 400	98.74 197	91.46 350	98.32 143	97.75 245	77.31 414	98.81 380	96.06 144	99.61 120	97.85 372

ACMMP_NAP		97.89 86	97.63 119	98.67 44	99.35 56	96.84 51	96.36 187	98.79 186	95.07 222	97.88 198	98.35 151	97.24 59	99.72 108	96.05 146	99.58 135	99.45 110

v148		96.58 206	96.97 173	95.42 308	98.63 188	87.57 357	95.09 302	97.90 302	95.91 179	98.24 154	97.96 218	93.42 241	99.39 271	96.04 147	99.52 165	99.29 160

ACMM	93.33 11	98.05 60	97.79 96	98.85 28	99.15 93	97.55 30	96.68 169	98.83 172	95.21 214	98.36 135	98.13 190	98.13 22	99.62 183	96.04 147	99.54 153	99.39 133
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
VDD-MVS		97.37 145	97.25 155	97.74 122	98.69 177	94.50 154	97.04 139	95.61 379	98.59 36	98.51 114	98.72 100	92.54 269	99.58 199	96.02 149	99.49 177	99.12 203

IterMVS		95.42 270	95.83 253	94.20 370	97.52 344	83.78 419	92.41 408	97.47 329	95.49 202	98.06 176	98.49 131	87.94 338	99.58 199	96.02 149	99.02 281	99.23 175
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs		96.04 235	96.23 229	95.46 307	97.35 359	88.03 347	93.42 378	99.08 86	94.09 270	96.66 285	96.93 318	93.85 229	99.29 309	96.01 151	98.67 324	99.06 218
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PM-MVS		97.36 147	97.10 164	98.14 93	98.91 139	96.77 53	96.20 201	98.63 222	93.82 277	98.54 111	98.33 154	93.98 225	99.05 354	95.99 152	99.45 190	98.61 296

Baseline_NR-MVSNet		97.72 107	97.79 96	97.50 146	99.56 22	93.29 203	95.44 269	98.86 157	98.20 56	98.37 132	99.24 36	94.69 199	99.55 211	95.98 153	99.79 63	99.65 39

ECVR-MVS		94.37 321	94.48 310	94.05 374	98.95 126	83.10 422	98.31 42	82.48 470	96.20 152	98.23 155	99.16 50	81.18 394	99.66 164	95.95 154	99.83 52	99.38 135

3Dnovator	96.53 2	97.61 119	97.64 117	97.50 146	97.74 320	93.65 190	98.49 31	98.88 152	96.86 116	97.11 246	98.55 125	95.82 151	99.73 100	95.94 155	99.42 206	99.13 197

viewmacassd2359aftdt		97.25 152	97.52 134	96.43 240	98.83 148	90.49 287	95.45 268	99.18 57	95.44 205	97.98 188	98.47 136	96.90 89	99.37 279	95.93 156	99.55 147	99.43 123

PatchT		93.75 339	93.57 337	94.29 368	95.05 438	87.32 364	96.05 215	92.98 417	97.54 82	94.25 374	98.72 100	75.79 423	99.24 324	95.92 157	95.81 432	96.32 433

NR-MVSNet		97.96 68	97.86 86	98.26 78	98.73 165	95.54 104	98.14 57	98.73 198	97.79 66	99.42 29	97.83 233	94.40 214	99.78 59	95.91 158	99.76 69	99.46 106

h-mvs33		96.29 222	95.63 261	98.26 78	98.50 213	96.11 79	96.90 147	97.09 341	96.58 130	97.21 238	98.19 182	84.14 376	99.78 59	95.89 159	96.17 429	98.89 253

hse-mvs2		95.77 249	95.09 274	97.79 118	97.84 293	95.51 106	95.66 253	95.43 384	96.58 130	97.21 238	96.16 362	84.14 376	99.54 214	95.89 159	96.92 403	98.32 325

MSC_two_6792asdad				98.22 83	97.75 317	95.34 121		98.16 283					99.75 85	95.87 161	99.51 170	99.57 57

No_MVS				98.22 83	97.75 317	95.34 121		98.16 283					99.75 85	95.87 161	99.51 170	99.57 57

new-patchmatchnet		95.67 256	96.58 202	92.94 403	97.48 348	80.21 444	92.96 389	98.19 278	94.83 232	98.82 83	98.79 90	93.31 243	99.51 224	95.83 163	99.04 280	99.12 203

FMVSNet1		97.95 72	98.08 63	97.56 137	99.14 100	93.67 186	98.23 49	98.66 216	97.41 92	99.00 62	99.19 42	95.47 169	99.73 100	95.83 163	99.76 69	99.30 153

patch_mono-2		96.59 203	96.93 177	95.55 302	98.88 143	87.12 367	94.47 333	99.30 41	94.12 267	96.65 287	98.41 143	94.98 192	99.87 26	95.81 165	99.78 67	99.66 36

DVP-MVS++		97.96 68	97.90 80	98.12 95	97.75 317	95.40 112	99.03 8	98.89 145	96.62 124	98.62 103	98.30 163	96.97 79	99.75 85	95.70 166	99.25 249	99.21 177

test_0728_THIRD									96.62 124	98.40 129	98.28 168	97.10 64	99.71 124	95.70 166	99.62 114	99.58 49

EGC-MVSNET		83.08 436	77.93 439	98.53 55	99.57 20	97.55 30	98.33 41	98.57 231	4.71 475	10.38 476	98.90 84	95.60 165	99.50 225	95.69 168	99.61 120	98.55 301

RPMNet		94.68 307	94.60 303	94.90 332	95.44 429	88.15 342	96.18 202	98.86 157	97.43 87	94.10 379	98.49 131	79.40 401	99.76 77	95.69 168	95.81 432	96.81 421

TSAR-MVS + MP.		97.42 140	97.23 157	98.00 106	99.38 51	95.00 136	97.63 100	98.20 273	93.00 313	98.16 163	98.06 206	95.89 146	99.72 108	95.67 170	99.10 272	99.28 161
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVS		97.96 68	97.63 119	98.94 19	99.15 93	97.66 23	97.77 83	98.83 172	97.42 88	96.32 305	97.64 254	96.49 117	99.72 108	95.66 171	99.37 217	99.45 110

X-MVStestdata		92.86 361	90.83 390	98.94 19	99.15 93	97.66 23	97.77 83	98.83 172	97.42 88	96.32 305	36.50 473	96.49 117	99.72 108	95.66 171	99.37 217	99.45 110

3Dnovator+	96.13 3	97.73 105	97.59 126	98.15 92	98.11 267	95.60 100	98.04 63	98.70 207	98.13 57	96.93 264	98.45 137	95.30 178	99.62 183	95.64 173	98.96 285	99.24 173

NormalMVS		96.87 180	96.39 220	98.30 75	99.48 36	95.57 101	96.87 149	98.90 141	96.94 112	96.85 269	97.88 226	85.36 366	99.76 77	95.63 174	99.59 130	99.57 57

SymmetryMVS		96.43 216	95.85 251	98.17 87	98.58 196	95.57 101	96.87 149	95.29 388	96.94 112	96.85 269	97.88 226	85.36 366	99.76 77	95.63 174	99.27 245	99.19 181

DELS-MVS		96.17 230	96.23 229	95.99 272	97.55 343	90.04 292	92.38 410	98.52 234	94.13 266	96.55 295	97.06 307	94.99 191	99.58 199	95.62 176	99.28 243	98.37 318
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
HFP-MVS		97.94 75	97.64 117	98.83 29	99.15 93	97.50 33	97.59 103	98.84 165	96.05 164	97.49 219	97.54 262	97.07 68	99.70 133	95.61 177	99.46 187	99.30 153

ACMMPR		97.95 72	97.62 121	98.94 19	99.20 85	97.56 29	97.59 103	98.83 172	96.05 164	97.46 225	97.63 255	96.77 99	99.76 77	95.61 177	99.46 187	99.49 94

UGNet		96.81 187	96.56 205	97.58 136	96.64 385	93.84 180	97.75 86	97.12 340	96.47 139	93.62 396	98.88 86	93.22 245	99.53 217	95.61 177	99.69 96	99.36 142
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
viewdifsd2359ckpt07		97.10 164	97.55 132	95.76 286	98.64 181	88.58 329	94.54 331	99.11 73	96.96 109	98.54 111	98.18 185	96.91 87	99.44 247	95.58 180	99.49 177	99.26 166

HPM-MVS		98.11 54	97.83 91	98.92 25	99.42 44	97.46 35	98.57 23	99.05 97	95.43 207	97.41 228	97.50 269	97.98 23	99.79 54	95.58 180	99.57 138	99.50 86
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
dcpmvs_2		97.12 162	97.99 74	94.51 356	99.11 102	84.00 417	97.75 86	99.65 13	97.38 95	99.14 49	98.42 141	95.16 184	99.96 2	95.52 182	99.78 67	99.58 49

SR-MVS-dyc-post		98.14 50	97.84 88	99.02 10	98.81 150	98.05 10	97.55 106	98.86 157	97.77 67	98.20 157	98.07 201	96.60 110	99.76 77	95.49 183	99.20 254	99.26 166

RE-MVS-def			97.88 85		98.81 150	98.05 10	97.55 106	98.86 157	97.77 67	98.20 157	98.07 201	96.94 81		95.49 183	99.20 254	99.26 166

Anonymous20240529		97.96 68	98.04 68	97.71 124	98.69 177	94.28 165	97.86 77	98.31 263	98.79 29	99.23 43	98.86 88	95.76 157	99.61 191	95.49 183	99.36 221	99.23 175

RRT-MVS		95.78 248	96.25 228	94.35 364	96.68 384	84.47 410	97.72 93	99.11 73	97.23 101	97.27 233	98.72 100	86.39 356	99.79 54	95.49 183	97.67 382	98.80 266

DVP-MVS		97.78 101	97.65 114	98.16 89	99.24 70	95.51 106	96.74 162	98.23 269	95.92 177	98.40 129	98.28 168	97.06 69	99.71 124	95.48 187	99.52 165	99.26 166
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				98.25 81	99.23 73	95.49 110	96.74 162	98.89 145					99.75 85	95.48 187	99.52 165	99.53 76

region2R		97.92 79	97.59 126	98.92 25	99.22 76	97.55 30	97.60 101	98.84 165	96.00 169	97.22 236	97.62 256	96.87 94	99.76 77	95.48 187	99.43 203	99.46 106

pmmvs-eth3d		96.49 210	96.18 232	97.42 157	98.25 244	94.29 162	94.77 323	98.07 295	89.81 375	97.97 189	98.33 154	93.11 248	99.08 351	95.46 190	99.84 48	98.89 253

SED-MVS		97.94 75	97.90 80	98.07 97	99.22 76	95.35 117	96.79 158	98.83 172	96.11 158	99.08 54	98.24 175	97.87 28	99.72 108	95.44 191	99.51 170	99.14 195

test_241102_TWO								98.83 172	96.11 158	98.62 103	98.24 175	96.92 86	99.72 108	95.44 191	99.49 177	99.49 94

APD-MVS_3200maxsize		98.13 53	97.90 80	98.79 33	98.79 156	97.31 40	97.55 106	98.92 139	97.72 72	98.25 153	98.13 190	97.10 64	99.75 85	95.44 191	99.24 252	99.32 148

xiu_mvs_v1_base_debu		95.62 259	95.96 244	94.60 349	98.01 274	88.42 331	93.99 355	98.21 270	92.98 314	95.91 328	94.53 404	96.39 125	99.72 108	95.43 194	98.19 355	95.64 443

xiu_mvs_v1_base		95.62 259	95.96 244	94.60 349	98.01 274	88.42 331	93.99 355	98.21 270	92.98 314	95.91 328	94.53 404	96.39 125	99.72 108	95.43 194	98.19 355	95.64 443

xiu_mvs_v1_base_debi		95.62 259	95.96 244	94.60 349	98.01 274	88.42 331	93.99 355	98.21 270	92.98 314	95.91 328	94.53 404	96.39 125	99.72 108	95.43 194	98.19 355	95.64 443

c3_l		95.20 281	95.32 265	94.83 337	96.19 399	86.43 378	91.83 420	98.35 258	93.47 291	97.36 229	97.26 290	88.69 329	99.28 313	95.41 197	99.36 221	98.78 269

mvsany_test3		96.21 227	95.93 247	97.05 187	97.40 356	94.33 161	95.76 245	94.20 403	89.10 382	99.36 35	99.60 11	93.97 226	97.85 440	95.40 198	98.63 329	98.99 229

MED-MVS test				98.17 87	99.36 53	95.35 117	97.75 86	99.30 41	94.02 272	98.88 76	97.54 262		99.73 100	95.36 199	99.53 157	99.44 120

ME-MVS		97.53 128	97.32 150	98.16 89	98.70 174	95.35 117	96.04 217	98.60 224	96.16 157	97.99 183	97.54 262	95.94 142	99.70 133	95.36 199	99.53 157	99.44 120

ACMMP		98.05 60	97.75 104	98.93 22	99.23 73	97.60 26	98.09 60	98.96 132	95.75 188	97.91 195	98.06 206	96.89 90	99.76 77	95.32 201	99.57 138	99.43 123
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
miper_lstm_enhance		94.81 299	94.80 293	94.85 335	96.16 401	86.45 377	91.14 437	98.20 273	93.49 290	97.03 255	97.37 283	84.97 371	99.26 317	95.28 202	99.56 141	98.83 262

MSLP-MVS++		96.42 217	96.71 193	95.57 298	97.82 300	90.56 283	95.71 247	98.84 165	94.72 237	96.71 280	97.39 279	94.91 195	98.10 436	95.28 202	99.02 281	98.05 357

SteuartSystems-ACMMP		98.02 62	97.76 102	98.79 33	99.43 42	97.21 45	97.15 131	98.90 141	96.58 130	98.08 173	97.87 229	97.02 75	99.76 77	95.25 204	99.59 130	99.40 128
Skip Steuart: Steuart Systems R&D Blog.
SD-MVS		97.37 145	97.70 106	96.35 250	98.14 263	95.13 133	96.54 175	98.92 139	95.94 175	99.19 46	98.08 199	97.74 33	95.06 463	95.24 205	99.54 153	98.87 259
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
IU-MVS					99.22 76	95.40 112		98.14 286	85.77 423	98.36 135				95.23 206	99.51 170	99.49 94

SSM_0407		97.39 142	97.67 111	96.54 233	98.51 207	90.96 271	96.40 180	99.16 60	96.95 110	98.27 149	98.09 197	97.05 71	99.67 156	95.21 207	99.40 211	98.98 232

SSM_0404		97.47 132	97.75 104	96.64 220	98.81 150	91.26 264	96.57 172	99.16 60	96.95 110	98.44 125	98.09 197	97.05 71	99.72 108	95.21 207	99.44 193	98.95 238

CP-MVS		97.92 79	97.56 129	98.99 14	98.99 121	97.82 19	97.93 72	98.96 132	96.11 158	96.89 267	97.45 271	96.85 95	99.78 59	95.19 209	99.63 111	99.38 135

LS3D		97.77 102	97.50 138	98.57 51	96.24 395	97.58 28	98.45 34	98.85 161	98.58 37	97.51 217	97.94 221	95.74 158	99.63 178	95.19 209	98.97 284	98.51 305

viewmanbaseed2359cas		96.77 190	96.94 176	96.27 255	98.41 227	90.24 289	95.11 300	99.03 106	94.28 261	97.45 226	97.85 230	95.92 144	99.32 300	95.18 211	99.19 258	99.24 173

SMA-MVS		97.48 131	97.11 163	98.60 49	98.83 148	96.67 57	96.74 162	98.73 198	91.61 344	98.48 119	98.36 149	96.53 114	99.68 147	95.17 212	99.54 153	99.45 110
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
CR-MVSNet		93.29 355	92.79 353	94.78 340	95.44 429	88.15 342	96.18 202	97.20 335	84.94 434	94.10 379	98.57 122	77.67 409	99.39 271	95.17 212	95.81 432	96.81 421

OPM-MVS		97.54 126	97.25 155	98.41 65	99.11 102	96.61 60	95.24 292	98.46 239	94.58 245	98.10 170	98.07 201	97.09 66	99.39 271	95.16 214	99.44 193	99.21 177
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
mPP-MVS		97.91 83	97.53 133	99.04 8	99.22 76	97.87 18	97.74 91	98.78 190	96.04 166	97.10 247	97.73 248	96.53 114	99.78 59	95.16 214	99.50 174	99.46 106

DIV-MVS_self_test		94.73 300	94.64 299	95.01 325	95.86 414	87.00 369	91.33 431	98.08 291	93.34 295	97.10 247	97.34 285	84.02 379	99.31 301	95.15 216	99.55 147	98.72 282

cl____		94.73 300	94.64 299	95.01 325	95.85 415	87.00 369	91.33 431	98.08 291	93.34 295	97.10 247	97.33 286	84.01 380	99.30 305	95.14 217	99.56 141	98.71 286

MSP-MVS		97.45 134	96.92 179	99.03 9	99.26 66	97.70 22	97.66 97	98.89 145	95.65 191	98.51 114	96.46 348	92.15 278	99.81 44	95.14 217	98.58 334	99.58 49
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
VDDNet		96.98 172	96.84 184	97.41 158	99.40 48	93.26 205	97.94 71	95.31 387	99.26 12	98.39 131	99.18 46	87.85 343	99.62 183	95.13 219	99.09 273	99.35 146

CANet		95.86 245	95.65 260	96.49 236	96.41 392	90.82 276	94.36 335	98.41 247	94.94 228	92.62 425	96.73 333	92.68 261	99.71 124	95.12 220	99.60 127	98.94 241

CNVR-MVS		96.92 175	96.55 208	98.03 104	98.00 278	95.54 104	94.87 316	98.17 279	94.60 242	96.38 302	97.05 308	95.67 162	99.36 283	95.12 220	99.08 274	99.19 181

eth_miper_zixun_eth		94.89 295	94.93 281	94.75 342	95.99 408	86.12 382	91.35 430	98.49 237	93.40 292	97.12 245	97.25 291	86.87 354	99.35 287	95.08 222	98.82 305	98.78 269

mamba_0408		97.17 157	97.38 145	96.55 232	98.51 207	90.96 271	95.19 295	99.06 91	96.60 126	98.27 149	97.78 240	96.58 111	99.72 108	95.04 223	99.40 211	98.98 232

SSM_04072		97.14 158	97.38 145	96.42 242	98.51 207	90.96 271	95.19 295	99.06 91	96.60 126	98.27 149	97.78 240	96.58 111	99.31 301	95.04 223	99.40 211	98.98 232

GST-MVS		97.82 96	97.49 140	98.81 31	99.23 73	97.25 42	97.16 130	98.79 186	95.96 172	97.53 215	97.40 275	96.93 83	99.77 70	95.04 223	99.35 226	99.42 125

DP-MVS		97.87 89	97.89 83	97.81 117	98.62 190	94.82 140	97.13 134	98.79 186	98.98 24	98.74 93	98.49 131	95.80 156	99.49 231	95.04 223	99.44 193	99.11 208

D2MVS		95.18 282	95.17 271	95.21 314	97.76 315	87.76 355	94.15 347	97.94 299	89.77 376	96.99 258	97.68 252	87.45 346	99.14 338	95.03 227	99.81 57	98.74 279

icg_test_0407_2		95.88 243	96.39 220	94.36 362	97.83 296	86.11 383	91.82 421	98.82 180	94.48 249	97.57 212	97.14 297	96.08 138	98.20 434	95.00 228	98.78 308	98.78 269

IMVS_0407		96.35 220	96.88 183	94.74 343	97.83 296	86.11 383	96.25 197	98.82 180	94.48 249	97.57 212	97.14 297	96.08 138	99.33 292	95.00 228	98.78 308	98.78 269

IMVS_0404		95.66 258	96.03 239	94.55 353	97.83 296	86.11 383	93.24 384	98.82 180	94.48 249	95.51 346	97.14 297	93.49 239	98.78 382	95.00 228	98.78 308	98.78 269

IMVS_0403		96.27 223	96.77 191	94.76 341	97.83 296	86.11 383	96.00 222	98.82 180	94.48 249	97.49 219	97.14 297	95.38 173	99.40 264	95.00 228	98.78 308	98.78 269

SSC-MVS		95.92 241	97.03 170	92.58 412	99.28 62	78.39 449	96.68 169	95.12 391	98.90 26	99.11 51	98.66 108	91.36 293	99.68 147	95.00 228	99.16 261	99.67 34

SR-MVS		98.00 63	97.66 113	99.01 12	98.77 162	97.93 15	97.38 119	98.83 172	97.32 98	98.06 176	97.85 230	96.65 105	99.77 70	95.00 228	99.11 269	99.32 148

FMVSNet2		96.72 196	96.67 196	96.87 204	97.96 280	91.88 248	97.15 131	98.06 296	95.59 195	98.50 116	98.62 114	89.51 322	99.65 167	94.99 234	99.60 127	99.07 215

viewcassd2359sk11		96.73 194	96.89 182	96.24 257	98.46 220	90.20 290	94.94 312	99.07 90	94.43 255	97.33 230	98.05 209	95.69 159	99.40 264	94.98 235	99.11 269	99.12 203

SDMVSNet		97.97 66	98.26 55	97.11 180	99.41 45	92.21 233	96.92 145	98.60 224	98.58 37	98.78 86	99.39 21	97.80 30	99.62 183	94.98 235	99.86 35	99.52 79

miper_ehance_all_eth		94.69 305	94.70 296	94.64 345	95.77 421	86.22 381	91.32 433	98.24 268	91.67 341	97.05 254	96.65 338	88.39 334	99.22 328	94.88 237	98.34 349	98.49 309

XVG-OURS-SEG-HR		97.38 143	97.07 167	98.30 75	99.01 120	97.41 38	94.66 327	99.02 110	95.20 215	98.15 165	97.52 267	98.83 5	98.43 418	94.87 238	96.41 421	99.07 215

MVS_111021_HR		96.73 194	96.54 210	97.27 168	98.35 231	93.66 189	93.42 378	98.36 255	94.74 234	96.58 291	96.76 332	96.54 113	98.99 362	94.87 238	99.27 245	99.15 189

test_0402		97.84 92	97.97 76	97.47 151	99.19 87	94.07 170	96.71 167	98.73 198	98.66 32	98.56 110	98.41 143	96.84 96	99.69 141	94.82 240	99.81 57	98.64 291

MVS_111021_LR		96.82 186	96.55 208	97.62 134	98.27 241	95.34 121	93.81 365	98.33 259	94.59 244	96.56 293	96.63 339	96.61 108	98.73 388	94.80 241	99.34 229	98.78 269

WR-MVS		96.90 177	96.81 186	97.16 176	98.56 200	92.20 236	94.33 336	98.12 288	97.34 97	98.20 157	97.33 286	92.81 257	99.75 85	94.79 242	99.81 57	99.54 71

ACMH+	93.58 10	98.23 46	98.31 49	97.98 108	99.39 49	95.22 129	97.55 106	99.20 53	98.21 55	99.25 42	98.51 130	98.21 18	99.40 264	94.79 242	99.72 87	99.32 148

thisisatest0530		92.71 364	91.76 373	95.56 301	98.42 225	88.23 339	96.03 219	87.35 461	94.04 271	96.56 293	95.47 387	64.03 453	99.77 70	94.78 244	99.11 269	98.68 290

PGM-MVS		97.88 87	97.52 134	98.96 17	99.20 85	97.62 25	97.09 136	99.06 91	95.45 203	97.55 214	97.94 221	97.11 63	99.78 59	94.77 245	99.46 187	99.48 100

TSAR-MVS + GP.		96.47 212	96.12 233	97.49 149	97.74 320	95.23 126	94.15 347	96.90 349	93.26 298	98.04 179	96.70 335	94.41 212	98.89 372	94.77 245	99.14 263	98.37 318

Syy-MVS		92.09 375	91.80 372	92.93 404	95.19 435	82.65 425	92.46 404	91.35 436	90.67 363	91.76 433	87.61 465	85.64 364	98.50 413	94.73 247	96.84 407	97.65 387

VNet		96.84 182	96.83 185	96.88 203	98.06 269	92.02 244	96.35 188	97.57 326	97.70 74	97.88 198	97.80 239	92.40 274	99.54 214	94.73 247	98.96 285	99.08 213

APD_test1		97.95 72	97.68 110	98.75 35	99.60 17	98.60 6	97.21 129	99.08 86	96.57 133	98.07 175	98.38 147	96.22 135	99.14 338	94.71 249	99.31 239	98.52 304

VPNet		97.26 151	97.49 140	96.59 225	99.47 38	90.58 281	96.27 193	98.53 233	97.77 67	98.46 122	98.41 143	94.59 205	99.68 147	94.61 250	99.29 242	99.52 79

GBi-Net		96.99 169	96.80 188	97.56 137	97.96 280	93.67 186	98.23 49	98.66 216	95.59 195	97.99 183	99.19 42	89.51 322	99.73 100	94.60 251	99.44 193	99.30 153

test1		96.99 169	96.80 188	97.56 137	97.96 280	93.67 186	98.23 49	98.66 216	95.59 195	97.99 183	99.19 42	89.51 322	99.73 100	94.60 251	99.44 193	99.30 153

FMVSNet3		95.26 279	94.94 279	96.22 260	96.53 388	90.06 291	95.99 225	97.66 318	94.11 268	97.99 183	97.91 225	80.22 400	99.63 178	94.60 251	99.44 193	98.96 236

SF-MVS		97.60 120	97.39 143	98.22 83	98.93 134	95.69 96	97.05 138	99.10 77	95.32 211	97.83 204	97.88 226	96.44 122	99.72 108	94.59 254	99.39 215	99.25 172

XXY-MVS		97.54 126	97.70 106	97.07 186	99.46 39	92.21 233	97.22 128	99.00 121	94.93 230	98.58 108	98.92 80	97.31 51	99.41 262	94.44 255	99.43 203	99.59 48

UnsupCasMVSNet_eth		95.91 242	95.73 257	96.44 238	98.48 216	91.52 256	95.31 286	98.45 240	95.76 186	97.48 222	97.54 262	89.53 321	98.69 394	94.43 256	94.61 447	99.13 197

LPG-MVS_test		97.94 75	97.67 111	98.74 38	99.15 93	97.02 46	97.09 136	99.02 110	95.15 218	98.34 139	98.23 177	97.91 25	99.70 133	94.41 257	99.73 82	99.50 86

LGP-MVS_train				98.74 38	99.15 93	97.02 46		99.02 110	95.15 218	98.34 139	98.23 177	97.91 25	99.70 133	94.41 257	99.73 82	99.50 86

DeepPCF-MVS	94.58 5	96.90 177	96.43 217	98.31 74	97.48 348	97.23 44	92.56 401	98.60 224	92.84 321	98.54 111	97.40 275	96.64 107	98.78 382	94.40 259	99.41 210	98.93 245

XVG-ACMP-BASELINE		97.58 124	97.28 154	98.49 58	99.16 90	96.90 50	96.39 182	98.98 128	95.05 224	98.06 176	98.02 211	95.86 147	99.56 207	94.37 260	99.64 109	99.00 225

RPSCF		97.87 89	97.51 136	98.95 18	99.15 93	98.43 7	97.56 105	99.06 91	96.19 154	98.48 119	98.70 105	94.72 197	99.24 324	94.37 260	99.33 234	99.17 185

CSCG		97.40 141	97.30 151	97.69 128	98.95 126	94.83 139	97.28 124	98.99 125	96.35 144	98.13 167	95.95 374	95.99 141	99.66 164	94.36 262	99.73 82	98.59 297

HPM-MVS++		96.99 169	96.38 222	98.81 31	98.64 181	97.59 27	95.97 228	98.20 273	95.51 200	95.06 356	96.53 344	94.10 222	99.70 133	94.29 263	99.15 262	99.13 197

XVG-OURS		97.12 162	96.74 192	98.26 78	98.99 121	97.45 36	93.82 363	99.05 97	95.19 216	98.32 143	97.70 250	95.22 181	98.41 419	94.27 264	98.13 358	98.93 245

jason		94.39 320	94.04 327	95.41 310	98.29 236	87.85 352	92.74 396	96.75 355	85.38 428	95.29 351	96.15 363	88.21 337	99.65 167	94.24 265	99.34 229	98.74 279
jason: jason.
CVMVSNet		92.33 370	92.79 353	90.95 432	97.26 366	75.84 463	95.29 289	92.33 427	81.86 445	96.27 310	98.19 182	81.44 392	98.46 417	94.23 266	98.29 352	98.55 301

EIA-MVS		96.04 235	95.77 256	96.85 205	97.80 305	92.98 210	96.12 209	99.16 60	94.65 240	93.77 390	91.69 445	95.68 160	99.67 156	94.18 267	98.85 301	97.91 367

ET-MVSNet_ETH3D		91.12 389	89.67 403	95.47 306	96.41 392	89.15 315	91.54 426	90.23 451	89.07 383	86.78 465	92.84 429	69.39 447	99.44 247	94.16 268	96.61 417	97.82 374

cl22		93.25 356	92.84 352	94.46 359	94.30 448	86.00 387	91.09 439	96.64 360	90.74 360	95.79 334	96.31 357	78.24 406	98.77 384	94.15 269	98.34 349	98.62 294

MCST-MVS		96.24 225	95.80 254	97.56 137	98.75 164	94.13 169	94.66 327	98.17 279	90.17 371	96.21 315	96.10 368	95.14 185	99.43 250	94.13 270	98.85 301	99.13 197

COLMAP_ROB	94.48 6	98.25 45	98.11 60	98.64 47	99.21 83	97.35 39	97.96 68	99.16 60	98.34 47	98.78 86	98.52 128	97.32 50	99.45 244	94.08 271	99.67 103	99.13 197
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous202405211		96.34 221	95.98 243	97.43 155	98.25 244	93.85 179	96.74 162	94.41 400	97.72 72	98.37 132	98.03 210	87.15 350	99.53 217	94.06 272	99.07 276	98.92 248

Effi-MVS+-dtu		96.81 187	96.09 235	98.99 14	96.90 381	98.69 5	96.42 179	98.09 290	95.86 182	95.15 354	95.54 385	94.26 219	99.81 44	94.06 272	98.51 339	98.47 310

ambc				96.56 230	98.23 247	91.68 254	97.88 76	98.13 287		98.42 126	98.56 124	94.22 220	99.04 356	94.05 274	99.35 226	98.95 238

FE-MVSNET		96.59 203	96.65 197	96.41 245	98.94 129	90.51 286	96.07 212	99.05 97	92.94 319	98.03 180	98.00 215	93.08 249	99.42 252	94.04 275	99.74 81	99.30 153

our_test_3		94.20 327	94.58 306	93.07 396	96.16 401	81.20 438	90.42 446	96.84 350	90.72 361	97.14 243	97.13 301	90.47 304	99.11 345	94.04 275	98.25 353	98.91 249

viewdifsd2359ckpt13		96.47 212	96.42 218	96.61 223	98.35 231	91.50 257	95.31 286	98.84 165	93.21 302	96.73 278	97.58 260	95.28 179	99.26 317	94.02 277	98.45 343	99.07 215

pmmvs5		94.63 310	94.34 317	95.50 304	97.63 336	88.34 336	94.02 353	97.13 339	87.15 407	95.22 353	97.15 296	87.50 345	99.27 316	93.99 278	99.26 248	98.88 257

DPE-MVS		97.64 115	97.35 148	98.50 57	98.85 147	96.18 75	95.21 294	98.99 125	95.84 183	98.78 86	98.08 199	96.84 96	99.81 44	93.98 279	99.57 138	99.52 79
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ppachtmachnet_test		94.49 317	94.84 289	93.46 385	96.16 401	82.10 429	90.59 444	97.48 328	90.53 365	97.01 257	97.59 258	91.01 297	99.36 283	93.97 280	99.18 259	98.94 241

viewmambaseed2359dif		95.68 255	95.85 251	95.17 317	97.51 345	87.41 361	93.61 373	98.58 229	91.06 357	96.68 281	97.66 253	94.71 198	99.11 345	93.93 281	98.94 288	98.99 229

tfpnnormal		97.72 107	97.97 76	96.94 196	99.26 66	92.23 232	97.83 80	98.45 240	98.25 53	99.13 50	98.66 108	96.65 105	99.69 141	93.92 282	99.62 114	98.91 249

LFMVS		95.32 276	94.88 286	96.62 221	98.03 270	91.47 258	97.65 98	90.72 445	99.11 15	97.89 197	98.31 159	79.20 402	99.48 234	93.91 283	99.12 268	98.93 245

EPP-MVSNet		96.84 182	96.58 202	97.65 132	99.18 88	93.78 183	98.68 17	96.34 361	97.91 64	97.30 231	98.06 206	88.46 332	99.85 31	93.85 284	99.40 211	99.32 148

Fast-Effi-MVS+-dtu		96.44 214	96.12 233	97.39 160	97.18 369	94.39 156	95.46 267	98.73 198	96.03 168	94.72 364	94.92 398	96.28 133	99.69 141	93.81 285	97.98 363	98.09 347

PHI-MVS		96.96 173	96.53 211	98.25 81	97.48 348	96.50 63	96.76 160	98.85 161	93.52 288	96.19 317	96.85 323	95.94 142	99.42 252	93.79 286	99.43 203	98.83 262

viewdifsd2359ckpt09		96.23 226	96.04 238	96.82 208	98.29 236	92.06 243	95.25 291	99.03 106	91.51 347	96.19 317	97.01 313	94.41 212	99.40 264	93.76 287	98.90 293	99.00 225

miper_enhance_ethall		93.14 358	92.78 355	94.20 370	93.65 458	85.29 396	89.97 450	97.85 305	85.05 430	96.15 321	94.56 403	85.74 361	99.14 338	93.74 288	98.34 349	98.17 344

DeepC-MVS_fast	94.34 7	96.74 192	96.51 213	97.44 154	97.69 324	94.15 168	96.02 220	98.43 243	93.17 308	97.30 231	97.38 281	95.48 168	99.28 313	93.74 288	99.34 229	98.88 257
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AUN-MVS		93.95 337	92.69 357	97.74 122	97.80 305	95.38 114	95.57 264	95.46 383	91.26 354	92.64 423	96.10 368	74.67 427	99.55 211	93.72 290	96.97 402	98.30 329

MP-MVS		97.64 115	97.18 161	99.00 13	99.32 60	97.77 21	97.49 112	98.73 198	96.27 145	95.59 343	97.75 245	96.30 130	99.78 59	93.70 291	99.48 182	99.45 110
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PVSNet_Blended_VisFu		95.95 240	95.80 254	96.42 242	99.28 62	90.62 280	95.31 286	99.08 86	88.40 394	96.97 262	98.17 187	92.11 280	99.78 59	93.64 292	99.21 253	98.86 260

lupinMVS		93.77 338	93.28 342	95.24 313	97.68 325	87.81 353	92.12 414	96.05 365	84.52 437	94.48 371	95.06 394	86.90 352	99.63 178	93.62 293	99.13 265	98.27 333

NCCC		96.52 208	95.99 242	98.10 96	97.81 301	95.68 97	95.00 310	98.20 273	95.39 208	95.40 350	96.36 355	93.81 230	99.45 244	93.55 294	98.42 346	99.17 185

test_vis1_rt		94.03 334	93.65 335	95.17 317	95.76 422	93.42 199	93.97 358	98.33 259	84.68 435	93.17 410	95.89 376	92.53 271	94.79 464	93.50 295	94.97 443	97.31 404

WB-MVS		95.50 263	96.62 198	92.11 422	99.21 83	77.26 459	96.12 209	95.40 385	98.62 35	98.84 81	98.26 173	91.08 296	99.50 225	93.37 296	98.70 322	99.58 49

ETV-MVS		96.13 232	95.90 248	96.82 208	97.76 315	93.89 177	95.40 274	98.95 134	95.87 181	95.58 344	91.00 451	96.36 128	99.72 108	93.36 297	98.83 304	96.85 417

FA-MVS(test-final)		94.91 293	94.89 284	94.99 327	97.51 345	88.11 346	98.27 47	95.20 390	92.40 331	96.68 281	98.60 119	83.44 382	99.28 313	93.34 298	98.53 335	97.59 392

MDA-MVSNet_test_wron		94.73 300	94.83 291	94.42 360	97.48 348	85.15 399	90.28 448	95.87 372	92.52 326	97.48 222	97.76 242	91.92 287	99.17 335	93.32 299	96.80 411	98.94 241

YYNet1		94.73 300	94.84 289	94.41 361	97.47 352	85.09 401	90.29 447	95.85 373	92.52 326	97.53 215	97.76 242	91.97 284	99.18 331	93.31 300	96.86 406	98.95 238

pmmvs4		94.82 298	94.19 322	96.70 217	97.42 355	92.75 219	92.09 416	96.76 354	86.80 413	95.73 339	97.22 292	89.28 326	98.89 372	93.28 301	99.14 263	98.46 312

CANet_DTU		94.65 309	94.21 321	95.96 275	95.90 411	89.68 301	93.92 360	97.83 309	93.19 304	90.12 447	95.64 382	88.52 331	99.57 205	93.27 302	99.47 184	98.62 294

ACMP	92.54 13	97.47 132	97.10 164	98.55 53	99.04 117	96.70 55	96.24 199	98.89 145	93.71 280	97.97 189	97.75 245	97.44 45	99.63 178	93.22 303	99.70 94	99.32 148
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Effi-MVS+		96.19 229	96.01 240	96.71 216	97.43 354	92.19 237	96.12 209	99.10 77	95.45 203	93.33 408	94.71 401	97.23 60	99.56 207	93.21 304	97.54 388	98.37 318

MDA-MVSNet-bldmvs		95.69 253	95.67 258	95.74 288	98.48 216	88.76 328	92.84 391	97.25 333	96.00 169	97.59 211	97.95 220	91.38 292	99.46 239	93.16 305	96.35 424	98.99 229

IS-MVSNet		96.93 174	96.68 195	97.70 126	99.25 69	94.00 174	98.57 23	96.74 356	98.36 46	98.14 166	97.98 217	88.23 336	99.71 124	93.10 306	99.72 87	99.38 135

9.14			96.69 194		98.53 204		96.02 220	98.98 128	93.23 299	97.18 241	97.46 270	96.47 119	99.62 183	92.99 307	99.32 236

MS-PatchMatch		94.83 297	94.91 283	94.57 352	96.81 382	87.10 368	94.23 342	97.34 332	88.74 389	97.14 243	97.11 304	91.94 286	98.23 431	92.99 307	97.92 366	98.37 318

Patchmtry		95.03 290	94.59 305	96.33 251	94.83 442	90.82 276	96.38 185	97.20 335	96.59 129	97.49 219	98.57 122	77.67 409	99.38 274	92.95 309	99.62 114	98.80 266

sd_testset		97.97 66	98.12 58	97.51 142	99.41 45	93.44 197	97.96 68	98.25 266	98.58 37	98.78 86	99.39 21	98.21 18	99.56 207	92.65 310	99.86 35	99.52 79

Fast-Effi-MVS+		95.49 264	95.07 275	96.75 214	97.67 329	92.82 213	94.22 343	98.60 224	91.61 344	93.42 406	92.90 426	96.73 101	99.70 133	92.60 311	97.89 369	97.74 381

HQP_MVS		96.66 201	96.33 225	97.68 129	98.70 174	94.29 162	96.50 176	98.75 195	96.36 142	96.16 319	96.77 330	91.91 288	99.46 239	92.59 312	99.20 254	99.28 161

plane_prior5								98.75 195					99.46 239	92.59 312	99.20 254	99.28 161

mvsany_test1		93.47 349	93.03 346	94.79 339	94.05 455	92.12 238	90.82 442	90.01 454	85.02 432	97.26 234	98.28 168	93.57 237	97.03 449	92.51 314	95.75 437	95.23 449

GA-MVS		92.83 362	92.15 367	94.87 334	96.97 376	87.27 365	90.03 449	96.12 364	91.83 340	94.05 382	94.57 402	76.01 421	98.97 368	92.46 315	97.34 397	98.36 323

mvsmamba		94.91 293	94.41 315	96.40 248	97.65 332	91.30 262	97.92 73	95.32 386	91.50 348	95.54 345	98.38 147	83.06 385	99.68 147	92.46 315	97.84 370	98.23 336

CPTT-MVS		96.69 199	96.08 236	98.49 58	98.89 142	96.64 59	97.25 125	98.77 191	92.89 320	96.01 325	97.13 301	92.23 276	99.67 156	92.24 317	99.34 229	99.17 185

EPNet		93.72 341	92.62 360	97.03 191	87.61 476	92.25 231	96.27 193	91.28 438	96.74 121	87.65 461	97.39 279	85.00 370	99.64 173	92.14 318	99.48 182	99.20 180
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PC_three_1452									87.24 406	98.37 132	97.44 272	97.00 76	96.78 455	92.01 319	99.25 249	99.21 177

APD-MVS		97.00 168	96.53 211	98.41 65	98.55 201	96.31 71	96.32 190	98.77 191	92.96 318	97.44 227	97.58 260	95.84 148	99.74 94	91.96 320	99.35 226	99.19 181
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CL-MVSNet_self_test		95.04 288	94.79 294	95.82 283	97.51 345	89.79 298	91.14 437	96.82 352	93.05 311	96.72 279	96.40 353	90.82 300	99.16 336	91.95 321	98.66 326	98.50 308

test_prior2							93.33 382		94.21 262	94.02 384	96.25 359	93.64 236		91.90 322	98.96 285

test-LLR		89.97 403	89.90 401	90.16 436	94.24 450	74.98 465	89.89 451	89.06 455	92.02 335	89.97 448	90.77 453	73.92 430	98.57 406	91.88 323	97.36 395	96.92 412

test-mter		87.92 425	87.17 425	90.16 436	94.24 450	74.98 465	89.89 451	89.06 455	86.44 416	89.97 448	90.77 453	54.96 473	98.57 406	91.88 323	97.36 395	96.92 412

MVP-Stereo		95.69 253	95.28 266	96.92 198	98.15 261	93.03 209	95.64 259	98.20 273	90.39 367	96.63 288	97.73 248	91.63 290	99.10 349	91.84 325	97.31 398	98.63 293
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
testing3		89.72 407	88.26 416	94.10 373	97.66 330	84.30 415	94.80 320	88.25 459	94.66 239	95.07 355	92.51 435	41.15 477	99.43 250	91.81 326	98.44 345	98.55 301

1112_ss		94.12 328	93.42 340	96.23 258	98.59 194	90.85 275	94.24 341	98.85 161	85.49 424	92.97 414	94.94 396	86.01 359	99.64 173	91.78 327	97.92 366	98.20 340

train_agg		95.46 268	94.66 297	97.88 113	97.84 293	95.23 126	93.62 371	98.39 250	87.04 408	93.78 388	95.99 370	94.58 206	99.52 220	91.76 328	98.90 293	98.89 253

LF4IMVS		96.07 233	95.63 261	97.36 161	98.19 251	95.55 103	95.44 269	98.82 180	92.29 332	95.70 340	96.55 342	92.63 264	98.69 394	91.75 329	99.33 234	97.85 372

N_pmnet		95.18 282	94.23 319	98.06 99	97.85 287	96.55 62	92.49 402	91.63 433	89.34 379	98.09 171	97.41 274	90.33 308	99.06 353	91.58 330	99.31 239	98.56 299

AllTest		97.20 155	96.92 179	98.06 99	99.08 106	96.16 76	97.14 133	99.16 60	94.35 258	97.78 206	98.07 201	95.84 148	99.12 342	91.41 331	99.42 206	98.91 249

TestCases				98.06 99	99.08 106	96.16 76		99.16 60	94.35 258	97.78 206	98.07 201	95.84 148	99.12 342	91.41 331	99.42 206	98.91 249

test9_res														91.29 333	98.89 297	99.00 225

xiu_mvs_v2_base		94.22 323	94.63 301	92.99 401	97.32 364	84.84 406	92.12 414	97.84 307	91.96 337	94.17 377	93.43 417	96.07 140	99.71 124	91.27 334	97.48 391	94.42 453

PS-MVSNAJ		94.10 329	94.47 311	93.00 400	97.35 359	84.88 403	91.86 419	97.84 307	91.96 337	94.17 377	92.50 436	95.82 151	99.71 124	91.27 334	97.48 391	94.40 454

tpm		91.08 392	90.85 389	91.75 425	95.33 433	78.09 451	95.03 309	91.27 439	88.75 388	93.53 401	97.40 275	71.24 440	99.30 305	91.25 336	93.87 451	97.87 371

OPU-MVS				97.64 133	98.01 274	95.27 124	96.79 158				97.35 284	96.97 79	98.51 412	91.21 337	99.25 249	99.14 195

ZD-MVS					98.43 223	95.94 86		98.56 232	90.72 361	96.66 285	97.07 306	95.02 190	99.74 94	91.08 338	98.93 291

tpmrst		90.31 397	90.61 395	89.41 441	94.06 454	72.37 472	95.06 306	93.69 406	88.01 399	92.32 428	96.86 322	77.45 411	98.82 378	91.04 339	87.01 466	97.04 409

sss		94.22 323	93.72 334	95.74 288	97.71 323	89.95 294	93.84 362	96.98 346	88.38 395	93.75 391	95.74 378	87.94 338	98.89 372	91.02 340	98.10 359	98.37 318

ttmdpeth		94.05 332	94.15 324	93.75 378	95.81 418	85.32 394	96.00 222	94.93 394	92.07 333	94.19 376	99.09 58	85.73 362	96.41 459	90.98 341	98.52 336	99.53 76

ITE_SJBPF				97.85 115	98.64 181	96.66 58		98.51 236	95.63 192	97.22 236	97.30 288	95.52 167	98.55 409	90.97 342	98.90 293	98.34 324

Test_1112_low_res		93.53 348	92.86 350	95.54 303	98.60 192	88.86 324	92.75 394	98.69 208	82.66 444	92.65 422	96.92 320	84.75 372	99.56 207	90.94 343	97.76 374	98.19 341

TESTMET0.1,1		87.20 431	86.57 431	89.07 443	93.62 459	72.84 471	89.89 451	87.01 463	85.46 426	89.12 455	90.20 456	56.00 466	97.72 443	90.91 344	96.92 403	96.64 425

FMVSNet5		93.39 351	92.35 362	96.50 235	95.83 416	90.81 278	97.31 122	98.27 264	92.74 323	96.27 310	98.28 168	62.23 454	99.67 156	90.86 345	99.36 221	99.03 221

PatchmatchNet		91.98 379	91.87 369	92.30 418	94.60 445	79.71 445	95.12 298	93.59 411	89.52 378	93.61 397	97.02 310	77.94 407	99.18 331	90.84 346	94.57 449	98.01 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CLD-MVS		95.47 267	95.07 275	96.69 218	98.27 241	92.53 222	91.36 429	98.67 213	91.22 355	95.78 336	94.12 411	95.65 163	98.98 364	90.81 347	99.72 87	98.57 298
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
cascas		91.89 380	91.35 378	93.51 384	94.27 449	85.60 390	88.86 459	98.61 223	79.32 457	92.16 429	91.44 447	89.22 327	98.12 435	90.80 348	97.47 393	96.82 420

MonoMVSNet		93.30 354	93.96 331	91.33 430	94.14 453	81.33 437	97.68 96	96.69 358	95.38 209	96.32 305	98.42 141	84.12 378	96.76 456	90.78 349	92.12 457	95.89 438

test20.03		96.58 206	96.61 200	96.48 237	98.49 214	91.72 252	95.68 251	97.69 315	96.81 118	98.27 149	97.92 224	94.18 221	98.71 391	90.78 349	99.66 106	99.00 225

test_yl		94.40 318	94.00 328	95.59 296	96.95 377	89.52 305	94.75 324	95.55 381	96.18 155	96.79 272	96.14 365	81.09 395	99.18 331	90.75 351	97.77 372	98.07 350

DCV-MVSNet		94.40 318	94.00 328	95.59 296	96.95 377	89.52 305	94.75 324	95.55 381	96.18 155	96.79 272	96.14 365	81.09 395	99.18 331	90.75 351	97.77 372	98.07 350

EPMVS		89.26 411	88.55 413	91.39 429	92.36 467	79.11 448	95.65 255	79.86 471	88.60 391	93.12 411	96.53 344	70.73 444	98.10 436	90.75 351	89.32 463	96.98 410

旧先验2							93.35 381		77.95 462	95.77 338			98.67 398	90.74 354

USDC		94.56 313	94.57 308	94.55 353	97.78 313	86.43 378	92.75 394	98.65 221	85.96 419	96.91 266	97.93 223	90.82 300	98.74 387	90.71 355	99.59 130	98.47 310

OpenMVS	94.22 8	95.48 266	95.20 268	96.32 252	97.16 370	91.96 246	97.74 91	98.84 165	87.26 405	94.36 373	98.01 213	93.95 227	99.67 156	90.70 356	98.75 315	97.35 402

testing3-2		90.09 399	90.38 398	89.24 442	98.07 268	69.88 475	95.12 298	90.71 446	96.65 123	93.60 399	94.03 412	55.81 467	99.33 292	90.69 357	98.71 320	98.51 305

Patchmatch-test		93.60 346	93.25 343	94.63 347	96.14 405	87.47 359	96.04 217	94.50 399	93.57 285	96.47 298	96.97 315	76.50 417	98.61 403	90.67 358	98.41 347	97.81 376

thisisatest0515		90.43 396	89.18 409	94.17 372	97.07 374	85.44 392	89.75 455	87.58 460	88.28 396	93.69 395	91.72 444	65.27 451	99.58 199	90.59 359	98.67 324	97.50 397

DP-MVS Recon		95.55 262	95.13 272	96.80 210	98.51 207	93.99 175	94.60 329	98.69 208	90.20 370	95.78 336	96.21 361	92.73 260	98.98 364	90.58 360	98.86 300	97.42 399

TinyColmap		96.00 239	96.34 224	94.96 329	97.90 285	87.91 349	94.13 350	98.49 237	94.41 256	98.16 163	97.76 242	96.29 132	98.68 397	90.52 361	99.42 206	98.30 329

BP-MVS														90.51 362

HQP-MVS		95.17 284	94.58 306	96.92 198	97.85 287	92.47 225	94.26 337	98.43 243	93.18 305	92.86 416	95.08 392	90.33 308	99.23 326	90.51 362	98.74 316	99.05 220

OMC-MVS		96.48 211	96.00 241	97.91 111	98.30 235	96.01 85	94.86 317	98.60 224	91.88 339	97.18 241	97.21 293	96.11 137	99.04 356	90.49 364	99.34 229	98.69 287

ab-mvs		96.59 203	96.59 201	96.60 224	98.64 181	92.21 233	98.35 38	97.67 316	94.45 254	96.99 258	98.79 90	94.96 194	99.49 231	90.39 365	99.07 276	98.08 348

HyFIR lowres test		93.72 341	92.65 358	96.91 200	98.93 134	91.81 251	91.23 435	98.52 234	82.69 443	96.46 299	96.52 346	80.38 399	99.90 18	90.36 366	98.79 307	99.03 221

agg_prior2														90.34 367	98.90 293	99.10 212

LCM-MVSNet-Re		97.33 148	97.33 149	97.32 164	98.13 266	93.79 182	96.99 142	99.65 13	96.74 121	99.47 24	98.93 77	96.91 87	99.84 34	90.11 368	99.06 279	98.32 325

CDS-MVSNet		94.88 296	94.12 325	97.14 178	97.64 335	93.57 191	93.96 359	97.06 343	90.05 372	96.30 309	96.55 342	86.10 358	99.47 236	90.10 369	99.31 239	98.40 314
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CDPH-MVS		95.45 269	94.65 298	97.84 116	98.28 239	94.96 137	93.73 367	98.33 259	85.03 431	95.44 348	96.60 340	95.31 177	99.44 247	90.01 370	99.13 265	99.11 208

baseline1		93.14 358	92.64 359	94.62 348	97.34 361	87.20 366	96.67 171	93.02 416	94.71 238	96.51 297	95.83 377	81.64 390	98.60 405	90.00 371	88.06 465	98.07 350

WBMVS		91.11 390	90.72 392	92.26 419	95.99 408	77.98 454	91.47 427	95.90 371	91.63 342	95.90 331	96.45 349	59.60 456	99.46 239	89.97 372	99.59 130	99.33 147

TAPA-MVS	93.32 12	94.93 292	94.23 319	97.04 189	98.18 254	94.51 152	95.22 293	98.73 198	81.22 450	96.25 312	95.95 374	93.80 231	98.98 364	89.89 373	98.87 298	97.62 389
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PMMVS		92.39 367	91.08 384	96.30 254	93.12 462	92.81 215	90.58 445	95.96 369	79.17 458	91.85 432	92.27 437	90.29 312	98.66 399	89.85 374	96.68 416	97.43 398

PVSNet_BlendedMVS		95.02 291	94.93 281	95.27 312	97.79 310	87.40 362	94.14 349	98.68 210	88.94 386	94.51 369	98.01 213	93.04 251	99.30 305	89.77 375	99.49 177	99.11 208

PVSNet_Blended		93.96 335	93.65 335	94.91 330	97.79 310	87.40 362	91.43 428	98.68 210	84.50 438	94.51 369	94.48 407	93.04 251	99.30 305	89.77 375	98.61 331	98.02 360

MSDG		95.33 275	95.13 272	95.94 279	97.40 356	91.85 249	91.02 440	98.37 254	95.30 212	96.31 308	95.99 370	94.51 210	98.38 422	89.59 377	97.65 385	97.60 391

PMVS	89.60 17	96.71 198	96.97 173	95.95 277	99.51 31	97.81 20	97.42 118	97.49 327	97.93 63	95.95 326	98.58 120	96.88 92	96.91 452	89.59 377	99.36 221	93.12 461
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_post1							94.98 311				10.37 477	76.21 420	99.04 356	89.47 379

SCA		93.38 352	93.52 338	92.96 402	96.24 395	81.40 436	93.24 384	94.00 404	91.58 346	94.57 367	96.97 315	87.94 338	99.42 252	89.47 379	97.66 384	98.06 354

tpmvs		90.79 395	90.87 388	90.57 435	92.75 466	76.30 461	95.79 243	93.64 410	91.04 358	91.91 431	96.26 358	77.19 415	98.86 376	89.38 381	89.85 462	96.56 428

Anonymous20231206		95.27 278	95.06 277	95.88 281	98.72 168	89.37 310	95.70 248	97.85 305	88.00 400	96.98 261	97.62 256	91.95 285	99.34 290	89.21 382	99.53 157	98.94 241

CHOSEN 1792x2688		94.10 329	93.41 341	96.18 264	99.16 90	90.04 292	92.15 413	98.68 210	79.90 455	96.22 314	97.83 233	87.92 342	99.42 252	89.18 383	99.65 107	99.08 213

114514_t		93.96 335	93.22 344	96.19 263	99.06 110	90.97 270	95.99 225	98.94 137	73.88 468	93.43 405	96.93 318	92.38 275	99.37 279	89.09 384	99.28 243	98.25 335

pmmvs3		90.00 401	88.90 411	93.32 387	94.20 452	85.34 393	91.25 434	92.56 425	78.59 459	93.82 387	95.17 391	67.36 450	98.69 394	89.08 385	98.03 362	95.92 437

testdata				95.70 291	98.16 259	90.58 281		97.72 314	80.38 453	95.62 341	97.02 310	92.06 283	98.98 364	89.06 386	98.52 336	97.54 394

MDTV_nov1_ep13			91.28 380		94.31 447	73.51 470	94.80 320	93.16 415	86.75 414	93.45 404	97.40 275	76.37 418	98.55 409	88.85 387	96.43 420

PMMVS2		93.66 344	94.07 326	92.45 416	97.57 340	80.67 442	86.46 462	96.00 367	93.99 274	97.10 247	97.38 281	89.90 315	97.82 441	88.76 388	99.47 184	98.86 260

QAPM		95.88 243	95.57 263	96.80 210	97.90 285	91.84 250	98.18 56	98.73 198	88.41 393	96.42 300	98.13 190	94.73 196	99.75 85	88.72 389	98.94 288	98.81 265

CHOSEN 280x420		89.98 402	89.19 408	92.37 417	95.60 426	81.13 439	86.22 463	97.09 341	81.44 449	87.44 462	93.15 418	73.99 428	99.47 236	88.69 390	99.07 276	96.52 429

testgi		96.07 233	96.50 214	94.80 338	99.26 66	87.69 356	95.96 230	98.58 229	95.08 221	98.02 182	96.25 359	97.92 24	97.60 445	88.68 391	98.74 316	99.11 208

CostFormer		89.75 406	89.25 404	91.26 431	94.69 444	78.00 453	95.32 285	91.98 430	81.50 448	90.55 440	96.96 317	71.06 442	98.89 372	88.59 392	92.63 455	96.87 415

UnsupCasMVSNet_bld		94.72 304	94.26 318	96.08 269	98.62 190	90.54 284	93.38 380	98.05 297	90.30 368	97.02 256	96.80 329	89.54 319	99.16 336	88.44 393	96.18 428	98.56 299

TAMVS		95.49 264	94.94 279	97.16 176	98.31 234	93.41 200	95.07 305	96.82 352	91.09 356	97.51 217	97.82 236	89.96 314	99.42 252	88.42 394	99.44 193	98.64 291

Vis-MVSNet (Re-imp)		95.11 285	94.85 288	95.87 282	99.12 101	89.17 313	97.54 111	94.92 395	96.50 135	96.58 291	97.27 289	83.64 381	99.48 234	88.42 394	99.67 103	98.97 235

EPNet_dtu		91.39 388	90.75 391	93.31 388	90.48 472	82.61 426	94.80 320	92.88 418	93.39 293	81.74 470	94.90 399	81.36 393	99.11 345	88.28 396	98.87 298	98.21 339
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
JIA-IIPM		91.79 382	90.69 393	95.11 319	93.80 457	90.98 269	94.16 346	91.78 432	96.38 140	90.30 444	99.30 32	72.02 439	98.90 371	88.28 396	90.17 461	95.45 447

新几何1				97.25 171	98.29 236	94.70 144		97.73 313	77.98 461	94.83 363	96.67 337	92.08 282	99.45 244	88.17 398	98.65 328	97.61 390

testdata2													99.46 239	87.84 399

FE-MVS		92.95 360	92.22 365	95.11 319	97.21 368	88.33 337	98.54 26	93.66 409	89.91 374	96.21 315	98.14 188	70.33 445	99.50 225	87.79 400	98.24 354	97.51 395

无先验							93.20 386	97.91 301	80.78 451				99.40 264	87.71 401		97.94 366

WTY-MVS		93.55 347	93.00 348	95.19 315	97.81 301	87.86 350	93.89 361	96.00 367	89.02 384	94.07 381	95.44 389	86.27 357	99.33 292	87.69 402	96.82 409	98.39 316

原ACMM1				96.58 226	98.16 259	92.12 238		98.15 285	85.90 421	93.49 402	96.43 350	92.47 273	99.38 274	87.66 403	98.62 330	98.23 336

BH-untuned		94.69 305	94.75 295	94.52 355	97.95 283	87.53 358	94.07 352	97.01 345	93.99 274	97.10 247	95.65 381	92.65 263	98.95 369	87.60 404	96.74 412	97.09 407

PAPM_NR		94.61 311	94.17 323	95.96 275	98.36 230	91.23 265	95.93 233	97.95 298	92.98 314	93.42 406	94.43 408	90.53 303	98.38 422	87.60 404	96.29 426	98.27 333

testing99		89.21 412	88.04 418	92.70 410	95.78 420	81.00 440	92.65 399	92.03 428	93.20 303	89.90 450	90.08 459	55.25 469	99.14 338	87.54 406	95.95 431	97.97 363

DPM-MVS		93.68 343	92.77 356	96.42 242	97.91 284	92.54 221	91.17 436	97.47 329	84.99 433	93.08 412	94.74 400	89.90 315	99.00 360	87.54 406	98.09 360	97.72 384

MG-MVS		94.08 331	94.00 328	94.32 366	97.09 373	85.89 388	93.19 387	95.96 369	92.52 326	94.93 362	97.51 268	89.54 319	98.77 384	87.52 408	97.71 378	98.31 327

F-COLMAP		95.30 277	94.38 316	98.05 103	98.64 181	96.04 82	95.61 261	98.66 216	89.00 385	93.22 409	96.40 353	92.90 256	99.35 287	87.45 409	97.53 389	98.77 276

PatchMatch-RL		94.61 311	93.81 333	97.02 192	98.19 251	95.72 94	93.66 369	97.23 334	88.17 398	94.94 361	95.62 383	91.43 291	98.57 406	87.36 410	97.68 381	96.76 423

testing11		88.93 414	87.63 423	92.80 407	95.87 413	81.49 435	92.48 403	91.54 434	91.62 343	88.27 459	90.24 455	55.12 472	99.11 345	87.30 411	96.28 427	97.81 376

IB-MVS	85.98 20	88.63 417	86.95 429	93.68 381	95.12 437	84.82 407	90.85 441	90.17 452	87.55 404	88.48 458	91.34 448	58.01 458	99.59 196	87.24 412	93.80 452	96.63 427
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
testing91		89.67 408	88.55 413	93.04 397	95.90 411	81.80 433	92.71 398	93.71 405	93.71 280	90.18 445	90.15 457	57.11 460	99.22 328	87.17 413	96.32 425	98.12 346

dp		88.08 423	88.05 417	88.16 449	92.85 464	68.81 476	94.17 345	92.88 418	85.47 425	91.38 436	96.14 365	68.87 448	98.81 380	86.88 414	83.80 469	96.87 415

1314		92.38 368	92.30 363	92.64 411	95.42 431	85.15 399	95.86 238	96.97 347	85.40 427	90.62 438	93.06 424	91.12 295	97.80 442	86.74 415	95.49 440	94.97 451

CNLPA		95.04 288	94.47 311	96.75 214	97.81 301	95.25 125	94.12 351	97.89 303	94.41 256	94.57 367	95.69 379	90.30 311	98.35 425	86.72 416	98.76 314	96.64 425

baseline2		89.65 409	88.44 415	93.25 390	95.62 425	82.71 424	93.82 363	85.94 465	88.89 387	87.35 463	92.54 434	71.23 441	99.33 292	86.01 417	94.60 448	97.72 384

BH-RMVSNet		94.56 313	94.44 314	94.91 330	97.57 340	87.44 360	93.78 366	96.26 362	93.69 282	96.41 301	96.50 347	92.10 281	99.00 360	85.96 418	97.71 378	98.31 327

E-PMN		89.52 410	89.78 402	88.73 444	93.14 461	77.61 455	83.26 468	92.02 429	94.82 233	93.71 392	93.11 419	75.31 424	96.81 453	85.81 419	96.81 410	91.77 464

API-MVS		95.09 287	95.01 278	95.31 311	96.61 386	94.02 173	96.83 152	97.18 337	95.60 194	95.79 334	94.33 409	94.54 209	98.37 424	85.70 420	98.52 336	93.52 458

AdaColmap		95.11 285	94.62 302	96.58 226	97.33 363	94.45 155	94.92 313	98.08 291	93.15 309	93.98 386	95.53 386	94.34 215	99.10 349	85.69 421	98.61 331	96.20 436

ADS-MVSNet2		91.47 387	90.51 396	94.36 362	95.51 427	85.63 389	95.05 307	95.70 374	83.46 441	92.69 420	96.84 324	79.15 403	99.41 262	85.66 422	90.52 459	98.04 358

ADS-MVSNet		90.95 394	90.26 399	93.04 397	95.51 427	82.37 428	95.05 307	93.41 412	83.46 441	92.69 420	96.84 324	79.15 403	98.70 392	85.66 422	90.52 459	98.04 358

MDTV_nov1_ep13_2view						57.28 478	94.89 315		80.59 452	94.02 384		78.66 405		85.50 424		97.82 374

WAC-MVS						79.32 446								85.41 425

OpenMVS_ROB	91.80 14	93.64 345	93.05 345	95.42 308	97.31 365	91.21 266	95.08 304	96.68 359	81.56 447	96.88 268	96.41 351	90.44 307	99.25 320	85.39 426	97.67 382	95.80 441

KD-MVS_2432*1600		88.93 414	87.74 419	92.49 413	88.04 474	81.99 430	89.63 456	95.62 377	91.35 352	95.06 356	93.11 419	56.58 462	98.63 401	85.19 427	95.07 441	96.85 417

miper_refine_blended		88.93 414	87.74 419	92.49 413	88.04 474	81.99 430	89.63 456	95.62 377	91.35 352	95.06 356	93.11 419	56.58 462	98.63 401	85.19 427	95.07 441	96.85 417

PVSNet	86.72 19	91.10 391	90.97 387	91.49 427	97.56 342	78.04 452	87.17 461	94.60 398	84.65 436	92.34 427	92.20 439	87.37 349	98.47 416	85.17 429	97.69 380	97.96 364

PLC	91.02 16	94.05 332	92.90 349	97.51 142	98.00 278	95.12 134	94.25 340	98.25 266	86.17 417	91.48 435	95.25 390	91.01 297	99.19 330	85.02 430	96.69 415	98.22 338
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
gm-plane-assit					91.79 468	71.40 474			81.67 446		90.11 458		98.99 362	84.86 431

CMPMVS	73.10 23	92.74 363	91.39 377	96.77 213	93.57 460	94.67 145	94.21 344	97.67 316	80.36 454	93.61 397	96.60 340	82.85 387	97.35 446	84.86 431	98.78 308	98.29 332
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		92.34 369	91.69 374	94.32 366	96.23 397	89.16 314	92.27 411	92.88 418	84.39 440	95.29 351	96.35 356	85.66 363	96.74 457	84.53 433	97.56 387	97.05 408

tpm cat1		88.01 424	87.33 424	90.05 440	94.48 446	76.28 462	94.47 333	94.35 401	73.84 469	89.26 454	95.61 384	73.64 432	98.30 428	84.13 434	86.20 467	95.57 446

MAR-MVS		94.21 325	93.03 346	97.76 121	96.94 379	97.44 37	96.97 143	97.15 338	87.89 402	92.00 430	92.73 432	92.14 279	99.12 342	83.92 435	97.51 390	96.73 424
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
DSMNet-mixed		92.19 372	91.83 370	93.25 390	96.18 400	83.68 420	96.27 193	93.68 408	76.97 465	92.54 426	99.18 46	89.20 328	98.55 409	83.88 436	98.60 333	97.51 395

EMVS		89.06 413	89.22 405	88.61 445	93.00 463	77.34 457	82.91 469	90.92 441	94.64 241	92.63 424	91.81 443	76.30 419	97.02 450	83.83 437	96.90 405	91.48 465

HY-MVS	91.43 15	92.58 365	91.81 371	94.90 332	96.49 389	88.87 323	97.31 122	94.62 397	85.92 420	90.50 441	96.84 324	85.05 369	99.40 264	83.77 438	95.78 435	96.43 432

test0.0.03 1		90.11 398	89.21 406	92.83 406	93.89 456	86.87 372	91.74 422	88.74 458	92.02 335	94.71 365	91.14 450	73.92 430	94.48 466	83.75 439	92.94 453	97.16 406

tpm2		88.47 418	87.69 422	90.79 433	94.98 439	77.34 457	95.09 302	91.83 431	77.51 464	89.40 453	96.41 351	67.83 449	98.73 388	83.58 440	92.60 456	96.29 434

myMVS_eth3d		87.16 432	85.61 435	91.82 424	95.19 435	79.32 446	92.46 404	91.35 436	90.67 363	91.76 433	87.61 465	41.96 476	98.50 413	82.66 441	96.84 407	97.65 387

MVS-HIRNet		88.40 419	90.20 400	82.99 452	97.01 375	60.04 477	93.11 388	85.61 466	84.45 439	88.72 457	99.09 58	84.72 373	98.23 431	82.52 442	96.59 418	90.69 467

myMVS_eth3d28		88.32 420	87.73 421	90.11 439	96.42 391	74.96 468	92.21 412	92.37 426	93.56 286	90.14 446	89.61 460	56.13 465	98.05 438	81.84 443	97.26 400	97.33 403

UWE-MVS		87.57 428	86.72 430	90.13 438	95.21 434	73.56 469	91.94 418	83.78 469	88.73 390	93.00 413	92.87 428	55.22 470	99.25 320	81.74 444	97.96 364	97.59 392

BH-w/o		92.14 373	91.94 368	92.73 409	97.13 372	85.30 395	92.46 404	95.64 376	89.33 380	94.21 375	92.74 431	89.60 317	98.24 430	81.68 445	94.66 446	94.66 452

MIMVSNet		93.42 350	92.86 350	95.10 321	98.17 257	88.19 340	98.13 58	93.69 406	92.07 333	95.04 359	98.21 181	80.95 397	99.03 359	81.42 446	98.06 361	98.07 350

UBG		88.29 421	87.17 425	91.63 426	96.08 406	78.21 450	91.61 423	91.50 435	89.67 377	89.71 451	88.97 462	59.01 457	98.91 370	81.28 447	96.72 414	97.77 379

TR-MVS		92.54 366	92.20 366	93.57 383	96.49 389	86.66 374	93.51 376	94.73 396	89.96 373	94.95 360	93.87 414	90.24 313	98.61 403	81.18 448	94.88 444	95.45 447

dmvs_re		92.08 376	91.27 381	94.51 356	97.16 370	92.79 218	95.65 255	92.64 423	94.11 268	92.74 419	90.98 452	83.41 383	94.44 467	80.72 449	94.07 450	96.29 434

thres600view7		92.03 378	91.43 376	93.82 376	98.19 251	84.61 408	96.27 193	90.39 447	96.81 118	96.37 303	93.11 419	73.44 436	99.49 231	80.32 450	97.95 365	97.36 400

WB-MVSnew		91.50 386	91.29 379	92.14 421	94.85 440	80.32 443	93.29 383	88.77 457	88.57 392	94.03 383	92.21 438	92.56 266	98.28 429	80.21 451	97.08 401	97.81 376

PAPR		92.22 371	91.27 381	95.07 322	95.73 424	88.81 325	91.97 417	97.87 304	85.80 422	90.91 437	92.73 432	91.16 294	98.33 426	79.48 452	95.76 436	98.08 348

MVS		90.02 400	89.20 407	92.47 415	94.71 443	86.90 371	95.86 238	96.74 356	64.72 470	90.62 438	92.77 430	92.54 269	98.39 421	79.30 453	95.56 439	92.12 462

gg-mvs-nofinetune		88.28 422	86.96 428	92.23 420	92.84 465	84.44 411	98.19 55	74.60 474	99.08 17	87.01 464	99.47 16	56.93 461	98.23 431	78.91 454	95.61 438	94.01 456

thres100view900		91.76 383	91.26 383	93.26 389	98.21 248	84.50 409	96.39 182	90.39 447	96.87 115	96.33 304	93.08 423	73.44 436	99.42 252	78.85 455	97.74 375	95.85 439

tfpn200view9		91.55 385	91.00 385	93.21 393	98.02 272	84.35 413	95.70 248	90.79 443	96.26 146	95.90 331	92.13 440	73.62 433	99.42 252	78.85 455	97.74 375	95.85 439

thres400		91.68 384	91.00 385	93.71 380	98.02 272	84.35 413	95.70 248	90.79 443	96.26 146	95.90 331	92.13 440	73.62 433	99.42 252	78.85 455	97.74 375	97.36 400

thres200		91.00 393	90.42 397	92.77 408	97.47 352	83.98 418	94.01 354	91.18 440	95.12 220	95.44 348	91.21 449	73.93 429	99.31 301	77.76 458	97.63 386	95.01 450

wuyk23d		93.25 356	95.20 268	87.40 451	96.07 407	95.38 114	97.04 139	94.97 393	95.33 210	99.70 10	98.11 195	98.14 21	91.94 469	77.76 458	99.68 100	74.89 469

test_method		66.88 437	66.13 440	69.11 454	62.68 479	25.73 482	49.76 471	96.04 366	14.32 474	64.27 474	91.69 445	73.45 435	88.05 471	76.06 460	66.94 471	93.54 457

testing222		87.35 429	85.50 436	92.93 404	95.79 419	82.83 423	92.40 409	90.10 453	92.80 322	88.87 456	89.02 461	48.34 475	98.70 392	75.40 461	96.74 412	97.27 405

ETVMVS		87.62 427	85.75 434	93.22 392	96.15 404	83.26 421	92.94 390	90.37 449	91.39 351	90.37 442	88.45 463	51.93 474	98.64 400	73.76 462	96.38 423	97.75 380

PCF-MVS	89.43 18	92.12 374	90.64 394	96.57 228	97.80 305	93.48 196	89.88 454	98.45 240	74.46 467	96.04 324	95.68 380	90.71 302	99.31 301	73.73 463	99.01 283	96.91 414
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
SD_0403		93.73 340	93.43 339	94.64 345	97.85 287	86.35 380	97.47 113	97.94 299	93.50 289	93.71 392	96.73 333	93.77 232	98.84 377	73.48 464	96.39 422	98.72 282

PVSNet_0	81.89 21	84.49 434	83.21 437	88.34 446	95.76 422	74.97 467	83.49 467	92.70 422	78.47 460	87.94 460	86.90 468	83.38 384	96.63 458	73.44 465	66.86 472	93.40 459

GG-mvs-BLEND				90.60 434	91.00 469	84.21 416	98.23 49	72.63 477		82.76 468	84.11 469	56.14 464	96.79 454	72.20 466	92.09 458	90.78 466

FPMVS		89.92 404	88.63 412	93.82 376	98.37 229	96.94 49	91.58 425	93.34 413	88.00 400	90.32 443	97.10 305	70.87 443	91.13 470	71.91 467	96.16 430	93.39 460

MVE	73.61 22	86.48 433	85.92 432	88.18 448	96.23 397	85.28 397	81.78 470	75.79 473	86.01 418	82.53 469	91.88 442	92.74 259	87.47 472	71.42 468	94.86 445	91.78 463
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		57.23 439	62.50 442	41.44 457	34.77 480	49.21 481	83.93 466	60.22 479	15.31 473	71.11 473	79.37 470	70.09 446	44.86 476	64.76 469	82.93 470	30.25 472

PAPM		87.64 426	85.84 433	93.04 397	96.54 387	84.99 402	88.42 460	95.57 380	79.52 456	83.82 467	93.05 425	80.57 398	98.41 419	62.29 470	92.79 454	95.71 442

dmvs_testset		87.30 430	86.99 427	88.24 447	96.71 383	77.48 456	94.68 326	86.81 464	92.64 325	89.61 452	87.01 467	85.91 360	93.12 468	61.04 471	88.49 464	94.13 455

DeepMVS_CX				77.17 453	90.94 470	85.28 397		74.08 476	52.51 472	80.87 472	88.03 464	75.25 425	70.63 474	59.23 472	84.94 468	75.62 468

UWE-MVS-28		83.78 435	82.36 438	88.03 450	90.72 471	71.58 473	93.64 370	77.87 472	87.62 403	85.91 466	92.89 427	59.94 455	95.99 461	56.06 473	96.56 419	96.52 429

dongtai		63.43 438	63.37 441	63.60 455	83.91 477	53.17 479	85.14 464	43.40 481	77.91 463	80.96 471	79.17 471	36.36 478	77.10 473	37.88 474	45.63 473	60.54 470

kuosan		54.81 440	54.94 443	54.42 456	74.43 478	50.03 480	84.98 465	44.27 480	61.80 471	62.49 475	70.43 472	35.16 479	58.04 475	19.30 475	41.61 474	55.19 471

test123		12.59 442	15.49 445	3.87 458	6.07 481	2.55 483	90.75 443	2.59 483	2.52 476	5.20 478	13.02 475	4.96 480	1.85 478	5.20 476	9.09 475	7.23 473

testmvs		12.33 443	15.23 446	3.64 459	5.77 482	2.23 484	88.99 458	3.62 482	2.30 477	5.29 477	13.09 474	4.52 481	1.95 477	5.16 477	8.32 476	6.75 474

mmdepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

monomultidepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

test_blank		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet_test		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

DCPMVS		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

cdsmvs_eth3d_5k		24.22 441	32.30 444	0.00 460	0.00 483	0.00 485	0.00 472	98.10 289	0.00 478	0.00 479	95.06 394	97.54 44	0.00 479	0.00 478	0.00 477	0.00 475

pcd_1.5k_mvsjas		7.98 444	10.65 447	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	95.82 151	0.00 479	0.00 478	0.00 477	0.00 475

sosnet-low-res		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uncertanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

Regformer		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

ab-mvs-re		7.91 445	10.55 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	94.94 396	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

TestfortrainingZip							97.75 86

FOURS1					99.59 18	98.20 8	99.03 8	99.25 49	98.96 25	98.87 78

test_one_0601					99.05 116	95.50 109		98.87 154	97.21 103	98.03 180	98.30 163	96.93 83

eth-test2					0.00 483

eth-test					0.00 483

test_241102_ONE					99.22 76	95.35 117		98.83 172	96.04 166	99.08 54	98.13 190	97.87 28	99.33 292

save fliter					98.48 216	94.71 142	94.53 332	98.41 247	95.02 226

test0726					99.24 70	95.51 106	96.89 148	98.89 145	95.92 177	98.64 101	98.31 159	97.06 69

GSMVS																98.06 354

test_part2					99.03 118	96.07 81				98.08 173

sam_mvs1												77.80 408				98.06 354

sam_mvs												77.38 412

MTGPA								98.73 198

test_post											10.87 476	76.83 416	99.07 352

patchmatchnet-post											96.84 324	77.36 413	99.42 252

MTMP							96.55 174	74.60 474

TEST9					97.84 293	95.23 126	93.62 371	98.39 250	86.81 412	93.78 388	95.99 370	94.68 201	99.52 220

test_8					97.81 301	95.07 135	93.54 375	98.38 252	87.04 408	93.71 392	95.96 373	94.58 206	99.52 220

agg_prior					97.80 305	94.96 137		98.36 255		93.49 402			99.53 217

test_prior4						95.38 114	93.61 373

test_prior				97.46 152	97.79 310	94.26 166		98.42 246					99.34 290			98.79 268

新几何2							93.43 377

旧先验1					97.80 305	93.87 178		97.75 312			97.04 309	93.57 237			98.68 323	98.72 282

原ACMM2							92.82 392

test222					98.17 257	93.24 206	92.74 396	97.61 325	75.17 466	94.65 366	96.69 336	90.96 299			98.66 326	97.66 386

segment_acmp												95.34 175

testdata1							92.77 393		93.78 278

test12				97.46 152	97.61 337	94.07 170		97.78 311		93.57 400		93.31 243	99.42 252		98.78 308	98.89 253

plane_prior7					98.70 174	94.67 145

plane_prior6					98.38 228	94.37 159						91.91 288

plane_prior4											96.77 330

plane_prior3						94.51 152			95.29 213	96.16 319

plane_prior2							96.50 176		96.36 142

plane_prior1					98.49 214

plane_prior						94.29 162	95.42 271		94.31 260						98.93 291

n2								0.00 484

nn								0.00 484

door-mid								98.17 279

test11								98.08 291

door								97.81 310

HQP5-MVS						92.47 225

HQP-NCC					97.85 287		94.26 337		93.18 305	92.86 416

ACMP_Plane					97.85 287		94.26 337		93.18 305	92.86 416

HQP4-MVS										92.87 415			99.23 326			99.06 218

HQP3-MVS								98.43 243							98.74 316

HQP2-MVS												90.33 308

NP-MVS					98.14 263	93.72 184					95.08 392

ACMMP++_ref															99.52 165

ACMMP++															99.55 147

Test By Simon												94.51 210

High-resolution multi-view benchmark