High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_fmvsm_n_1920		97.55 12	97.89 3	96.53 95	98.41 77	91.73 122	98.01 60	99.02 1	96.37 9	99.30 3	98.92 19	92.39 41	99.79 38	99.16 10	99.46 41	98.08 190

PGM-MVS		96.81 50	96.53 61	97.65 43	99.35 20	93.53 61	97.65 118	98.98 2	92.22 153	97.14 67	98.44 55	91.17 67	99.85 18	94.35 137	99.46 41	99.57 30

MVS_111021_HR		96.68 61	96.58 60	96.99 77	98.46 73	92.31 103	96.20 272	98.90 3	94.30 79	95.86 122	97.74 119	92.33 42	99.38 125	96.04 86	99.42 51	99.28 70

test_fmvsmconf_n		97.49 16	97.56 10	97.29 59	97.44 154	92.37 100	97.91 77	98.88 4	95.83 13	98.92 19	99.05 11	91.45 57	99.80 35	99.12 12	99.46 41	99.69 12

ACMMP		96.27 77	95.93 80	97.28 61	99.24 28	92.62 91	98.25 35	98.81 5	92.99 128	94.56 157	98.39 59	88.96 96	99.85 18	94.57 135	97.63 153	99.36 65
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
MVS_111021_LR		96.24 78	96.19 77	96.39 113	98.23 95	91.35 143	96.24 270	98.79 6	93.99 86	95.80 124	97.65 127	89.92 86	99.24 138	95.87 90	99.20 79	98.58 143

patch_mono-2		96.83 49	97.44 18	95.01 196	99.05 39	85.39 327	96.98 200	98.77 7	94.70 59	97.99 42	98.66 38	93.61 19	99.91 1	97.67 33	99.50 35	99.72 11

fmvsm_s_conf0.5_n		96.85 46	97.13 23	96.04 137	98.07 110	90.28 186	97.97 69	98.76 8	94.93 41	98.84 24	99.06 10	88.80 100	99.65 70	99.06 14	98.63 113	98.18 176

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 56	98.21 96	92.75 85	97.83 89	98.73 9	95.04 38	99.30 3	98.84 31	93.34 22	99.78 41	99.32 4	99.13 88	99.50 45

fmvsm_s_conf0.5_n_a		96.75 54	96.93 38	96.20 129	97.64 140	90.72 172	98.00 61	98.73 9	94.55 66	98.91 20	99.08 6	88.22 111	99.63 79	98.91 17	98.37 126	98.25 171

FC-MVSNet-test		93.94 154	93.57 145	95.04 194	95.48 278	91.45 140	98.12 50	98.71 11	93.37 111	90.23 260	96.70 185	87.66 121	97.85 313	91.49 196	90.39 300	95.83 284

UniMVSNet (Re)		93.31 175	92.55 188	95.61 166	95.39 284	93.34 67	97.39 160	98.71 11	93.14 124	90.10 269	94.83 286	87.71 120	98.03 286	91.67 194	83.99 372	95.46 303

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 63	98.25 90	92.59 93	97.81 94	98.68 13	94.93 41	99.24 6	98.87 26	93.52 20	99.79 38	99.32 4	99.21 76	99.40 59

FIs		94.09 146	93.70 141	95.27 184	95.70 268	92.03 115	98.10 51	98.68 13	93.36 113	90.39 257	96.70 185	87.63 124	97.94 304	92.25 176	90.50 299	95.84 283

WR-MVS_H		92.00 231	91.35 228	93.95 257	95.09 311	89.47 214	98.04 58	98.68 13	91.46 178	88.34 320	94.68 293	85.86 154	97.56 342	85.77 314	84.24 370	94.82 348

fmvsm_s_conf0.5_n_4		96.75 54	97.07 26	95.79 153	97.76 131	89.57 208	97.66 117	98.66 16	95.36 24	99.03 12	98.90 21	88.39 107	99.73 52	99.17 9	98.66 111	98.08 190

VPA-MVSNet		93.24 177	92.48 193	95.51 172	95.70 268	92.39 99	97.86 82	98.66 16	92.30 151	92.09 218	95.37 261	80.49 254	98.40 240	93.95 143	85.86 343	95.75 292

fmvsm_l_conf0.5_n_3		97.64 8	97.60 9	97.79 30	98.14 103	93.94 52	97.93 75	98.65 18	96.70 4	99.38 1	99.07 9	89.92 86	99.81 30	99.16 10	99.43 48	99.61 24

fmvsm_s_conf0.5_n_3		97.15 28	97.36 20	96.52 97	97.98 116	91.19 151	97.84 86	98.65 18	97.08 3	99.25 5	99.10 4	87.88 118	99.79 38	99.32 4	99.18 81	98.59 142

fmvsm_s_conf0.5_n_8		97.32 22	97.48 17	96.85 79	98.28 86	91.07 159	97.76 98	98.62 20	97.53 2	99.20 8	99.12 3	88.24 110	99.81 30	99.41 2	99.17 82	99.67 13

fmvsm_s_conf0.5_n_2		96.62 62	96.82 47	96.02 139	97.98 116	90.43 182	97.50 141	98.59 21	96.59 6	99.31 2	99.08 6	84.47 171	99.75 49	99.37 3	98.45 123	97.88 203

UniMVSNet_NR-MVSNet		93.37 173	92.67 182	95.47 177	95.34 290	92.83 82	97.17 184	98.58 22	92.98 133	90.13 265	95.80 237	88.37 109	97.85 313	91.71 191	83.93 373	95.73 294

CSCG		96.05 81	95.91 81	96.46 107	99.24 28	90.47 179	98.30 28	98.57 23	89.01 265	93.97 173	97.57 135	92.62 37	99.76 45	94.66 129	99.27 69	99.15 80

fmvsm_s_conf0.5_n_6		97.08 31	97.17 22	96.81 80	97.28 159	91.73 122	97.75 100	98.50 24	94.86 45	99.22 7	98.78 35	89.75 89	99.76 45	99.10 13	99.29 67	98.94 106

MSLP-MVS++		96.94 40	97.06 27	96.59 92	98.72 58	91.86 120	97.67 114	98.49 25	94.66 62	97.24 63	98.41 58	92.31 44	98.94 184	96.61 62	99.46 41	98.96 102

HyFIR lowres test		93.66 164	92.92 170	95.87 147	98.24 91	89.88 199	94.58 344	98.49 25	85.06 361	93.78 176	95.78 241	82.86 206	98.67 218	91.77 189	95.71 203	99.07 91

CHOSEN 1792x2688		94.15 141	93.51 151	96.06 135	98.27 87	89.38 219	95.18 330	98.48 27	85.60 351	93.76 177	97.11 164	83.15 196	99.61 81	91.33 199	98.72 109	99.19 76

fmvsm_s_conf0.5_n_7		96.45 69	96.80 49	95.37 180	97.29 158	88.38 251	97.23 178	98.47 28	95.14 32	98.43 33	99.09 5	87.58 125	99.72 56	98.80 21	99.21 76	98.02 194

fmvsm_s_conf0.5_n_5		97.00 37	96.97 35	97.09 72	97.58 150	92.56 94	97.68 113	98.47 28	94.02 84	98.90 21	98.89 23	88.94 97	99.78 41	99.18 8	99.03 97	98.93 110

PHI-MVS		96.77 52	96.46 68	97.71 41	98.40 78	94.07 48	98.21 42	98.45 30	89.86 237	97.11 69	98.01 95	92.52 39	99.69 64	96.03 87	99.53 29	99.36 65

fmvsm_s_conf0.1_n		96.58 65	96.77 52	96.01 142	96.67 205	90.25 187	97.91 77	98.38 31	94.48 70	98.84 24	99.14 1	88.06 113	99.62 80	98.82 19	98.60 115	98.15 180

PVSNet_BlendedMVS		94.06 147	93.92 137	94.47 227	98.27 87	89.46 216	96.73 223	98.36 32	90.17 229	94.36 162	95.24 269	88.02 114	99.58 89	93.44 154	90.72 295	94.36 368

PVSNet_Blended		94.87 122	94.56 120	95.81 152	98.27 87	89.46 216	95.47 313	98.36 32	88.84 273	94.36 162	96.09 226	88.02 114	99.58 89	93.44 154	98.18 135	98.40 163

3Dnovator	91.36 5	95.19 110	94.44 128	97.44 53	96.56 215	93.36 66	98.65 11	98.36 32	94.12 81	89.25 299	98.06 89	82.20 223	99.77 44	93.41 156	99.32 65	99.18 77

FOURS1					99.55 1	93.34 67	99.29 1	98.35 35	94.98 39	98.49 31

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 181	98.35 35	95.16 31	98.71 28	98.80 33	95.05 10	99.89 3	96.70 60	99.73 1	99.73 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.1_n_a		96.40 71	96.47 65	96.16 131	95.48 278	90.69 173	97.91 77	98.33 37	94.07 82	98.93 16	99.14 1	87.44 132	99.61 81	98.63 22	98.32 128	98.18 176

HFP-MVS		97.14 29	96.92 39	97.83 26	99.42 7	94.12 46	98.52 15	98.32 38	93.21 116	97.18 64	98.29 75	92.08 46	99.83 26	95.63 103	99.59 19	99.54 38

ACMMPR		97.07 33	96.84 43	97.79 30	99.44 6	93.88 53	98.52 15	98.31 39	93.21 116	97.15 66	98.33 69	91.35 61	99.86 9	95.63 103	99.59 19	99.62 21

test_fmvsmvis_n_1920		96.70 57	96.84 43	96.31 118	96.62 207	91.73 122	97.98 63	98.30 40	96.19 10	96.10 112	98.95 17	89.42 90	99.76 45	98.90 18	99.08 92	97.43 230

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 40	94.76 57	98.30 35	98.90 21	93.77 17	99.68 66	97.93 25	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 3	95.36 13	98.31 27	98.29 42	94.92 43	98.99 14	98.92 19	95.08 8

MSP-MVS		97.59 11	97.54 11	97.73 38	99.40 11	93.77 57	98.53 14	98.29 42	95.55 21	98.56 30	97.81 114	93.90 15	99.65 70	96.62 61	99.21 76	99.77 2
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
DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 61	95.39 11	99.29 1	98.28 44	94.78 54	98.93 16	98.87 26	96.04 2	99.86 9	97.45 41	99.58 23	99.59 26

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 42	98.28 44					99.86 9	97.52 37	99.67 6	99.75 6

CP-MVS		97.02 35	96.81 48	97.64 45	99.33 21	93.54 60	98.80 8	98.28 44	92.99 128	96.45 99	98.30 74	91.90 49	99.85 18	95.61 105	99.68 4	99.54 38

test_fmvsmconf0.1_n		97.09 30	97.06 27	97.19 68	95.67 270	92.21 107	97.95 72	98.27 47	95.78 17	98.40 34	99.00 13	89.99 84	99.78 41	99.06 14	99.41 54	99.59 26

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 35	98.27 47	95.13 33	99.19 9	98.89 23	95.54 5	99.85 18	97.52 37	99.66 10	99.56 33

test_241102_TWO								98.27 47	95.13 33	98.93 16	98.89 23	94.99 11	99.85 18	97.52 37	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 47	95.09 36	99.19 9	98.81 32	95.54 5	99.65 70

SF-MVS		97.39 19	97.13 23	98.17 15	99.02 42	95.28 19	98.23 39	98.27 47	92.37 150	98.27 36	98.65 40	93.33 23	99.72 56	96.49 66	99.52 30	99.51 42

SteuartSystems-ACMMP		97.62 10	97.53 12	97.87 24	98.39 80	94.25 40	98.43 22	98.27 47	95.34 26	98.11 38	98.56 42	94.53 12	99.71 58	96.57 64	99.62 17	99.65 18
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 22	95.20 20		98.25 53	95.13 33	98.48 32	98.87 26	95.16 7

PVSNet_Blended_VisFu		95.27 104	94.91 109	96.38 114	98.20 97	90.86 166	97.27 172	98.25 53	90.21 228	94.18 167	97.27 153	87.48 131	99.73 52	93.53 151	97.77 151	98.55 144

region2R		97.07 33	96.84 43	97.77 34	99.46 2	93.79 55	98.52 15	98.24 55	93.19 119	97.14 67	98.34 66	91.59 56	99.87 7	95.46 109	99.59 19	99.64 19

PS-CasMVS		91.55 251	90.84 252	93.69 273	94.96 315	88.28 254	97.84 86	98.24 55	91.46 178	88.04 330	95.80 237	79.67 270	97.48 350	87.02 294	84.54 367	95.31 317

DU-MVS		92.90 195	92.04 204	95.49 174	94.95 316	92.83 82	97.16 185	98.24 55	93.02 127	90.13 265	95.71 244	83.47 188	97.85 313	91.71 191	83.93 373	95.78 288

9.14			96.75 53		98.93 50		97.73 104	98.23 58	91.28 187	97.88 46	98.44 55	93.00 26	99.65 70	95.76 96	99.47 40

reproduce_model		97.51 15	97.51 14	97.50 50	98.99 46	93.01 78	97.79 96	98.21 59	95.73 18	97.99 42	99.03 12	92.63 36	99.82 28	97.80 27	99.42 51	99.67 13

D2MVS		91.30 268	90.95 246	92.35 321	94.71 331	85.52 323	96.18 274	98.21 59	88.89 271	86.60 359	93.82 342	79.92 266	97.95 302	89.29 243	90.95 292	93.56 383

reproduce-ours		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 109	98.20 61	95.80 15	97.88 46	98.98 15	92.91 27	99.81 30	97.68 29	99.43 48	99.67 13

our_new_method		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 109	98.20 61	95.80 15	97.88 46	98.98 15	92.91 27	99.81 30	97.68 29	99.43 48	99.67 13

SDMVSNet		94.17 139	93.61 144	95.86 149	98.09 106	91.37 142	97.35 164	98.20 61	93.18 121	91.79 226	97.28 151	79.13 278	98.93 185	94.61 132	92.84 258	97.28 238

XVS		97.18 26	96.96 37	97.81 28	99.38 14	94.03 50	98.59 12	98.20 61	94.85 46	96.59 90	98.29 75	91.70 52	99.80 35	95.66 98	99.40 56	99.62 21

X-MVStestdata		91.71 240	89.67 305	97.81 28	99.38 14	94.03 50	98.59 12	98.20 61	94.85 46	96.59 90	32.69 443	91.70 52	99.80 35	95.66 98	99.40 56	99.62 21

ACMMP_NAP		97.20 25	96.86 41	98.23 11	99.09 34	95.16 22	97.60 127	98.19 66	92.82 140	97.93 45	98.74 37	91.60 55	99.86 9	96.26 70	99.52 30	99.67 13

CP-MVSNet		91.89 236	91.24 235	93.82 265	95.05 312	88.57 244	97.82 91	98.19 66	91.70 171	88.21 326	95.76 242	81.96 227	97.52 348	87.86 269	84.65 361	95.37 313

ZNCC-MVS		96.96 38	96.67 56	97.85 25	99.37 16	94.12 46	98.49 19	98.18 68	92.64 146	96.39 101	98.18 82	91.61 54	99.88 4	95.59 108	99.55 26	99.57 30

SMA-MVS		97.35 20	97.03 32	98.30 8	99.06 38	95.42 10	97.94 73	98.18 68	90.57 220	98.85 23	98.94 18	93.33 23	99.83 26	96.72 58	99.68 4	99.63 20
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
PEN-MVS		91.20 273	90.44 269	93.48 284	94.49 339	87.91 269	97.76 98	98.18 68	91.29 184	87.78 334	95.74 243	80.35 257	97.33 361	85.46 318	82.96 383	95.19 328

DELS-MVS		96.61 63	96.38 72	97.30 58	97.79 129	93.19 74	95.96 285	98.18 68	95.23 28	95.87 121	97.65 127	91.45 57	99.70 63	95.87 90	99.44 47	99.00 98
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
tfpnnormal		89.70 324	88.40 330	93.60 277	95.15 307	90.10 189	97.56 132	98.16 72	87.28 324	86.16 364	94.63 297	77.57 306	98.05 282	74.48 404	84.59 365	92.65 396

VNet		95.89 88	95.45 91	97.21 66	98.07 110	92.94 81	97.50 141	98.15 73	93.87 90	97.52 53	97.61 133	85.29 160	99.53 103	95.81 95	95.27 212	99.16 78

DeepPCF-MVS	93.97 1	96.61 63	97.09 25	95.15 188	98.09 106	86.63 300	96.00 283	98.15 73	95.43 22	97.95 44	98.56 42	93.40 21	99.36 126	96.77 55	99.48 39	99.45 52

SD-MVS		97.41 18	97.53 12	97.06 75	98.57 72	94.46 34	97.92 76	98.14 75	94.82 50	99.01 13	98.55 44	94.18 14	97.41 357	96.94 50	99.64 14	99.32 67
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
GST-MVS		96.85 46	96.52 62	97.82 27	99.36 18	94.14 45	98.29 29	98.13 76	92.72 143	96.70 82	98.06 89	91.35 61	99.86 9	94.83 123	99.28 68	99.47 51

UA-Net		95.95 86	95.53 87	97.20 67	97.67 136	92.98 80	97.65 118	98.13 76	94.81 52	96.61 88	98.35 63	88.87 98	99.51 108	90.36 218	97.35 163	99.11 86

QAPM		93.45 171	92.27 198	96.98 78	96.77 200	92.62 91	98.39 24	98.12 78	84.50 369	88.27 324	97.77 117	82.39 220	99.81 30	85.40 319	98.81 105	98.51 149

Vis-MVSNet		95.23 107	94.81 110	96.51 101	97.18 164	91.58 133	98.26 34	98.12 78	94.38 77	94.90 147	98.15 84	82.28 221	98.92 187	91.45 198	98.58 117	99.01 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 198	91.68 218	96.40 111	95.34 290	92.73 87	98.27 32	98.12 78	84.86 364	85.78 366	97.75 118	78.89 288	99.74 50	87.50 284	98.65 112	96.73 255

TranMVSNet+NR-MVSNet		92.50 207	91.63 219	95.14 189	94.76 327	92.07 112	97.53 138	98.11 81	92.90 137	89.56 287	96.12 221	83.16 195	97.60 340	89.30 242	83.20 382	95.75 292

CPTT-MVS		95.57 98	95.19 101	96.70 83	99.27 26	91.48 137	98.33 26	98.11 81	87.79 309	95.17 143	98.03 92	87.09 138	99.61 81	93.51 152	99.42 51	99.02 92

APD-MVS		96.95 39	96.60 58	98.01 20	99.03 41	94.93 27	97.72 107	98.10 83	91.50 176	98.01 41	98.32 71	92.33 42	99.58 89	94.85 121	99.51 33	99.53 41
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 44	96.60 58	97.64 45	99.40 11	93.44 62	98.50 18	98.09 84	93.27 115	95.95 119	98.33 69	91.04 69	99.88 4	95.20 112	99.57 25	99.60 25

ZD-MVS					99.05 39	94.59 32		98.08 85	89.22 258	97.03 72	98.10 85	92.52 39	99.65 70	94.58 134	99.31 66

MTGPA								98.08 85

MTAPA		97.08 31	96.78 51	97.97 23	99.37 16	94.42 36	97.24 174	98.08 85	95.07 37	96.11 111	98.59 41	90.88 74	99.90 2	96.18 82	99.50 35	99.58 29

CNVR-MVS		97.68 6	97.44 18	98.37 7	98.90 53	95.86 6	97.27 172	98.08 85	95.81 14	97.87 49	98.31 72	94.26 13	99.68 66	97.02 49	99.49 38	99.57 30

DP-MVS Recon		95.68 93	95.12 105	97.37 55	99.19 31	94.19 42	97.03 192	98.08 85	88.35 291	95.09 145	97.65 127	89.97 85	99.48 113	92.08 183	98.59 116	98.44 160

SR-MVS		97.01 36	96.86 41	97.47 52	99.09 34	93.27 71	97.98 63	98.07 90	93.75 93	97.45 55	98.48 52	91.43 59	99.59 86	96.22 73	99.27 69	99.54 38

MCST-MVS		97.18 26	96.84 43	98.20 14	99.30 24	95.35 15	97.12 188	98.07 90	93.54 103	96.08 113	97.69 122	93.86 16	99.71 58	96.50 65	99.39 58	99.55 36

NR-MVSNet		92.34 215	91.27 234	95.53 171	94.95 316	93.05 77	97.39 160	98.07 90	92.65 145	84.46 377	95.71 244	85.00 164	97.77 324	89.71 230	83.52 379	95.78 288

MP-MVS-pluss		96.70 57	96.27 75	97.98 22	99.23 30	94.71 29	96.96 202	98.06 93	90.67 211	95.55 135	98.78 35	91.07 68	99.86 9	96.58 63	99.55 26	99.38 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 50	96.71 55	97.12 70	99.01 45	92.31 103	97.98 63	98.06 93	93.11 125	97.44 56	98.55 44	90.93 72	99.55 99	96.06 83	99.25 73	99.51 42

MP-MVS		96.77 52	96.45 69	97.72 39	99.39 13	93.80 54	98.41 23	98.06 93	93.37 111	95.54 137	98.34 66	90.59 78	99.88 4	94.83 123	99.54 28	99.49 47
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 66	96.27 75	97.22 65	99.32 22	92.74 86	98.74 9	98.06 93	90.57 220	96.77 79	98.35 63	90.21 81	99.53 103	94.80 126	99.63 16	99.38 63

HPM-MVS		96.69 59	96.45 69	97.40 54	99.36 18	93.11 76	98.87 6	98.06 93	91.17 192	96.40 100	97.99 96	90.99 70	99.58 89	95.61 105	99.61 18	99.49 47
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 131	93.80 139	96.64 85	97.07 170	91.97 117	96.32 262	98.06 93	88.94 269	94.50 159	96.78 180	84.60 168	99.27 136	91.90 184	96.02 193	98.68 136

DeepC-MVS	93.07 3	96.06 80	95.66 85	97.29 59	97.96 118	93.17 75	97.30 170	98.06 93	93.92 88	93.38 186	98.66 38	86.83 140	99.73 52	95.60 107	99.22 75	98.96 102
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 23	97.03 32	98.11 17	98.77 56	95.06 25	97.34 165	98.04 100	95.96 11	97.09 70	97.88 105	93.18 25	99.71 58	95.84 94	99.17 82	99.56 33

DeepC-MVS_fast	93.89 2	96.93 41	96.64 57	97.78 32	98.64 67	94.30 37	97.41 155	98.04 100	94.81 52	96.59 90	98.37 61	91.24 64	99.64 78	95.16 114	99.52 30	99.42 58
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 43	96.80 49	97.11 71	99.02 42	92.34 101	97.98 63	98.03 102	93.52 106	97.43 58	98.51 47	91.40 60	99.56 97	96.05 84	99.26 71	99.43 56

RE-MVS-def			96.72 54		99.02 42	92.34 101	97.98 63	98.03 102	93.52 106	97.43 58	98.51 47	90.71 76		96.05 84	99.26 71	99.43 56

RPMNet		88.98 330	87.05 344	94.77 214	94.45 341	87.19 285	90.23 418	98.03 102	77.87 416	92.40 204	87.55 423	80.17 261	99.51 108	68.84 423	93.95 245	97.60 223

save fliter					98.91 52	94.28 38	97.02 194	98.02 105	95.35 25

TEST9					98.70 59	94.19 42	96.41 251	98.02 105	88.17 295	96.03 114	97.56 137	92.74 33	99.59 86

train_agg		96.30 76	95.83 84	97.72 39	98.70 59	94.19 42	96.41 251	98.02 105	88.58 282	96.03 114	97.56 137	92.73 34	99.59 86	95.04 116	99.37 62	99.39 61

test_8					98.67 61	94.06 49	96.37 258	98.01 108	88.58 282	95.98 118	97.55 139	92.73 34	99.58 89

agg_prior					98.67 61	93.79 55		98.00 109		95.68 131			99.57 96

test_prior				97.23 64	98.67 61	92.99 79		98.00 109					99.41 121			99.29 68

WR-MVS		92.34 215	91.53 223	94.77 214	95.13 309	90.83 167	96.40 255	97.98 111	91.88 166	89.29 296	95.54 255	82.50 216	97.80 320	89.79 229	85.27 352	95.69 295

HPM-MVS++		97.34 21	96.97 35	98.47 5	99.08 36	96.16 4	97.55 137	97.97 112	95.59 19	96.61 88	97.89 103	92.57 38	99.84 23	95.95 89	99.51 33	99.40 59

CANet		96.39 72	96.02 79	97.50 50	97.62 143	93.38 64	97.02 194	97.96 113	95.42 23	94.86 148	97.81 114	87.38 134	99.82 28	96.88 52	99.20 79	99.29 68

114514_t		93.95 153	93.06 166	96.63 89	99.07 37	91.61 130	97.46 152	97.96 113	77.99 414	93.00 195	97.57 135	86.14 152	99.33 128	89.22 246	99.15 86	98.94 106

IU-MVS					99.42 7	95.39 11		97.94 115	90.40 226	98.94 15				97.41 44	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 61	96.94 1		97.93 116					99.86 9	97.68 29	99.67 6	99.77 2

No_MVS				98.86 1	98.67 61	96.94 1		97.93 116					99.86 9	97.68 29	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 75	96.44 71	96.00 143	97.30 157	90.37 185	97.53 138	97.92 118	96.52 7	99.14 11	99.08 6	83.21 193	99.74 50	99.22 7	98.06 140	97.88 203

Anonymous20231211		90.63 297	89.42 312	94.27 241	98.24 91	89.19 231	98.05 57	97.89 119	79.95 406	88.25 325	94.96 278	72.56 346	98.13 265	89.70 231	85.14 354	95.49 299

原ACMM1				96.38 114	98.59 69	91.09 158		97.89 119	87.41 320	95.22 142	97.68 123	90.25 80	99.54 101	87.95 268	99.12 90	98.49 152

CDPH-MVS		95.97 85	95.38 96	97.77 34	98.93 50	94.44 35	96.35 259	97.88 121	86.98 328	96.65 86	97.89 103	91.99 48	99.47 114	92.26 174	99.46 41	99.39 61

test11								97.88 121

EIA-MVS		95.53 99	95.47 90	95.71 161	97.06 173	89.63 204	97.82 91	97.87 123	93.57 99	93.92 174	95.04 275	90.61 77	98.95 182	94.62 131	98.68 110	98.54 145

CS-MVS		96.86 44	97.06 27	96.26 124	98.16 102	91.16 156	99.09 3	97.87 123	95.30 27	97.06 71	98.03 92	91.72 50	98.71 215	97.10 47	99.17 82	98.90 115

无先验							95.79 295	97.87 123	83.87 377				99.65 70	87.68 278		98.89 119

3Dnovator+	91.43 4	95.40 100	94.48 126	98.16 16	96.90 186	95.34 16	98.48 20	97.87 123	94.65 63	88.53 316	98.02 94	83.69 184	99.71 58	93.18 160	98.96 100	99.44 54

VPNet		92.23 223	91.31 231	94.99 197	95.56 274	90.96 162	97.22 180	97.86 127	92.96 134	90.96 248	96.62 197	75.06 326	98.20 259	91.90 184	83.65 378	95.80 286

test_vis1_n_1920		94.17 139	94.58 119	92.91 305	97.42 155	82.02 374	97.83 89	97.85 128	94.68 60	98.10 39	98.49 49	70.15 365	99.32 130	97.91 26	98.82 104	97.40 232

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 42	97.85 128	94.92 43	98.73 26	98.87 26	95.08 8	99.84 23	97.52 37	99.67 6	99.48 49
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
TSAR-MVS + MP.		97.42 17	97.33 21	97.69 42	99.25 27	94.24 41	98.07 55	97.85 128	93.72 94	98.57 29	98.35 63	93.69 18	99.40 122	97.06 48	99.46 41	99.44 54
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		96.89 42	97.04 31	96.45 108	98.29 85	91.66 129	99.03 4	97.85 128	95.84 12	96.90 74	97.97 98	91.24 64	98.75 208	96.92 51	99.33 64	98.94 106

test_fmvsmconf0.01_n		96.15 79	95.85 83	97.03 76	92.66 392	91.83 121	97.97 69	97.84 132	95.57 20	97.53 52	99.00 13	84.20 177	99.76 45	98.82 19	99.08 92	99.48 49

GDP-MVS		95.62 95	95.13 103	97.09 72	96.79 197	93.26 72	97.89 80	97.83 133	93.58 98	96.80 76	97.82 113	83.06 200	99.16 150	94.40 136	97.95 146	98.87 121

balanced_conf03		96.84 48	96.89 40	96.68 84	97.63 142	92.22 106	98.17 48	97.82 134	94.44 72	98.23 37	97.36 148	90.97 71	99.22 140	97.74 28	99.66 10	98.61 139

AdaColmap		94.34 135	93.68 142	96.31 118	98.59 69	91.68 128	96.59 242	97.81 135	89.87 236	92.15 214	97.06 167	83.62 187	99.54 101	89.34 241	98.07 139	97.70 216

MVSMamba_PlusPlus		96.51 66	96.48 64	96.59 92	98.07 110	91.97 117	98.14 49	97.79 136	90.43 224	97.34 61	97.52 140	91.29 63	99.19 143	98.12 24	99.64 14	98.60 140

KinetiMVS		95.26 105	94.75 114	96.79 81	96.99 181	92.05 113	97.82 91	97.78 137	94.77 56	96.46 97	97.70 121	80.62 251	99.34 127	92.37 173	98.28 130	98.97 100

mamv4		94.66 129	96.10 78	90.37 374	98.01 113	73.41 423	96.82 215	97.78 137	89.95 235	94.52 158	97.43 144	92.91 27	99.09 163	98.28 23	99.16 85	98.60 140

ETV-MVS		96.02 82	95.89 82	96.40 111	97.16 165	92.44 98	97.47 150	97.77 139	94.55 66	96.48 95	94.51 303	91.23 66	98.92 187	95.65 101	98.19 134	97.82 211

新几何1				97.32 57	98.60 68	93.59 59		97.75 140	81.58 397	95.75 126	97.85 109	90.04 83	99.67 68	86.50 300	99.13 88	98.69 135

旧先验1					98.38 81	93.38 64		97.75 140			98.09 87	92.30 45			99.01 98	99.16 78

EC-MVSNet		96.42 70	96.47 65	96.26 124	97.01 179	91.52 135	98.89 5	97.75 140	94.42 73	96.64 87	97.68 123	89.32 91	98.60 225	97.45 41	99.11 91	98.67 137

EI-MVSNet-Vis-set		96.51 66	96.47 65	96.63 89	98.24 91	91.20 150	96.89 207	97.73 143	94.74 58	96.49 94	98.49 49	90.88 74	99.58 89	96.44 67	98.32 128	99.13 82

PAPM_NR		95.01 113	94.59 118	96.26 124	98.89 54	90.68 174	97.24 174	97.73 143	91.80 167	92.93 200	96.62 197	89.13 94	99.14 155	89.21 247	97.78 150	98.97 100

Anonymous20240529		91.98 232	90.73 259	95.73 159	98.14 103	89.40 218	97.99 62	97.72 145	79.63 408	93.54 181	97.41 146	69.94 367	99.56 97	91.04 206	91.11 288	98.22 173

CHOSEN 280x420		93.12 183	92.72 181	94.34 235	96.71 204	87.27 281	90.29 417	97.72 145	86.61 335	91.34 237	95.29 263	84.29 176	98.41 239	93.25 158	98.94 101	97.35 235

EI-MVSNet-UG-set		96.34 74	96.30 74	96.47 105	98.20 97	90.93 164	96.86 210	97.72 145	94.67 61	96.16 110	98.46 53	90.43 79	99.58 89	96.23 72	97.96 145	98.90 115

LS3D		93.57 167	92.61 186	96.47 105	97.59 146	91.61 130	97.67 114	97.72 145	85.17 359	90.29 259	98.34 66	84.60 168	99.73 52	83.85 342	98.27 131	98.06 192

PAPR		94.18 138	93.42 157	96.48 104	97.64 140	91.42 141	95.55 308	97.71 149	88.99 266	92.34 210	95.82 236	89.19 92	99.11 158	86.14 306	97.38 161	98.90 115

UGNet		94.04 149	93.28 160	96.31 118	96.85 189	91.19 151	97.88 81	97.68 150	94.40 75	93.00 195	96.18 216	73.39 343	99.61 81	91.72 190	98.46 122	98.13 181
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
testdata				95.46 178	98.18 101	88.90 237		97.66 151	82.73 388	97.03 72	98.07 88	90.06 82	98.85 194	89.67 232	98.98 99	98.64 138

test12				97.65 43	98.46 73	94.26 39		97.66 151		95.52 138		90.89 73	99.46 115		99.25 73	99.22 75

DTE-MVSNet		90.56 298	89.75 303	93.01 301	93.95 354	87.25 282	97.64 122	97.65 153	90.74 206	87.12 347	95.68 247	79.97 265	97.00 373	83.33 343	81.66 389	94.78 355

TAPA-MVS	90.10 7	92.30 218	91.22 237	95.56 168	98.33 83	89.60 206	96.79 217	97.65 153	81.83 394	91.52 232	97.23 156	87.94 116	98.91 189	71.31 418	98.37 126	98.17 179
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 184	92.45 194	95.05 193	98.09 106	89.21 228	96.89 207	97.64 155	93.18 121	91.79 226	97.28 151	75.35 325	98.65 220	88.99 252	92.84 258	97.28 238

test_cas_vis1_n_1920		94.48 133	94.55 123	94.28 240	96.78 198	86.45 305	97.63 124	97.64 155	93.32 114	97.68 51	98.36 62	73.75 341	99.08 166	96.73 57	99.05 94	97.31 237

ElysianMVS		94.00 151	93.12 163	96.64 85	96.08 254	92.72 88	97.50 141	97.63 157	91.15 194	94.82 149	97.12 162	74.98 328	99.06 172	90.78 209	98.02 141	98.12 183

StellarMVS		94.00 151	93.12 163	96.64 85	96.08 254	92.72 88	97.50 141	97.63 157	91.15 194	94.82 149	97.12 162	74.98 328	99.06 172	90.78 209	98.02 141	98.12 183

cdsmvs_eth3d_5k		23.24 413	30.99 415	0.00 431	0.00 454	0.00 456	0.00 442	97.63 157	0.00 449	0.00 450	96.88 176	84.38 173	0.00 450	0.00 449	0.00 448	0.00 446

DPM-MVS		95.69 92	94.92 108	98.01 20	98.08 109	95.71 9	95.27 324	97.62 160	90.43 224	95.55 135	97.07 166	91.72 50	99.50 111	89.62 234	98.94 101	98.82 127

sasdasda		96.02 82	95.45 91	97.75 36	97.59 146	95.15 23	98.28 30	97.60 161	94.52 68	96.27 105	96.12 221	87.65 122	99.18 146	96.20 78	94.82 221	98.91 112

canonicalmvs		96.02 82	95.45 91	97.75 36	97.59 146	95.15 23	98.28 30	97.60 161	94.52 68	96.27 105	96.12 221	87.65 122	99.18 146	96.20 78	94.82 221	98.91 112

test222					98.24 91	92.21 107	95.33 319	97.60 161	79.22 410	95.25 140	97.84 111	88.80 100			99.15 86	98.72 132

cascas		91.20 273	90.08 286	94.58 223	94.97 314	89.16 232	93.65 382	97.59 164	79.90 407	89.40 291	92.92 368	75.36 324	98.36 247	92.14 179	94.75 224	96.23 265

h-mvs33		94.15 141	93.52 150	96.04 137	97.81 128	90.22 188	97.62 126	97.58 165	95.19 29	96.74 80	97.45 141	83.67 185	99.61 81	95.85 92	79.73 396	98.29 170

MGCFI-Net		95.94 87	95.40 95	97.56 49	97.59 146	94.62 31	98.21 42	97.57 166	94.41 74	96.17 109	96.16 219	87.54 127	99.17 148	96.19 80	94.73 226	98.91 112

MVSFormer		95.37 101	95.16 102	95.99 144	96.34 237	91.21 148	98.22 40	97.57 166	91.42 180	96.22 107	97.32 149	86.20 150	97.92 307	94.07 140	99.05 94	98.85 123

test_djsdf		93.07 186	92.76 176	94.00 252	93.49 371	88.70 241	98.22 40	97.57 166	91.42 180	90.08 271	95.55 254	82.85 207	97.92 307	94.07 140	91.58 279	95.40 310

OMC-MVS		95.09 112	94.70 115	96.25 127	98.46 73	91.28 144	96.43 249	97.57 166	92.04 162	94.77 153	97.96 99	87.01 139	99.09 163	91.31 200	96.77 180	98.36 167

PS-MVSNAJss		93.74 162	93.51 151	94.44 229	93.91 356	89.28 226	97.75 100	97.56 170	92.50 147	89.94 273	96.54 200	88.65 103	98.18 262	93.83 149	90.90 293	95.86 280

casdiffmvs_mvg		95.81 91	95.57 86	96.51 101	96.87 187	91.49 136	97.50 141	97.56 170	93.99 86	95.13 144	97.92 101	87.89 117	98.78 203	95.97 88	97.33 164	99.26 72
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		92.42 211	91.89 211	94.03 251	93.33 379	88.50 248	97.73 104	97.53 172	92.00 164	88.85 308	96.50 202	75.62 323	98.11 269	93.88 147	91.56 280	95.48 300

mvs_tets		92.31 217	91.76 214	93.94 259	93.41 376	88.29 253	97.63 124	97.53 172	92.04 162	88.76 311	96.45 204	74.62 333	98.09 274	93.91 145	91.48 281	95.45 305

dcpmvs_2		96.37 73	97.05 30	94.31 238	98.96 49	84.11 348	97.56 132	97.51 174	93.92 88	97.43 58	98.52 46	92.75 32	99.32 130	97.32 46	99.50 35	99.51 42

HQP_MVS		93.78 161	93.43 155	94.82 207	96.21 241	89.99 193	97.74 102	97.51 174	94.85 46	91.34 237	96.64 190	81.32 239	98.60 225	93.02 166	92.23 267	95.86 280

plane_prior5								97.51 174					98.60 225	93.02 166	92.23 267	95.86 280

reproduce_monomvs		91.30 268	91.10 241	91.92 335	96.82 194	82.48 368	97.01 197	97.49 177	94.64 64	88.35 319	95.27 266	70.53 360	98.10 270	95.20 112	84.60 364	95.19 328

PS-MVSNAJ		95.37 101	95.33 98	95.49 174	97.35 156	90.66 175	95.31 321	97.48 178	93.85 91	96.51 93	95.70 246	88.65 103	99.65 70	94.80 126	98.27 131	96.17 269

API-MVS		94.84 123	94.49 125	95.90 146	97.90 124	92.00 116	97.80 95	97.48 178	89.19 259	94.81 151	96.71 183	88.84 99	99.17 148	88.91 254	98.76 108	96.53 258

MG-MVS		95.61 96	95.38 96	96.31 118	98.42 76	90.53 177	96.04 280	97.48 178	93.47 108	95.67 132	98.10 85	89.17 93	99.25 137	91.27 201	98.77 107	99.13 82

MAR-MVS		94.22 137	93.46 153	96.51 101	98.00 115	92.19 110	97.67 114	97.47 181	88.13 299	93.00 195	95.84 234	84.86 166	99.51 108	87.99 267	98.17 136	97.83 210
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
CLD-MVS		92.98 190	92.53 190	94.32 236	96.12 251	89.20 229	95.28 322	97.47 181	92.66 144	89.90 274	95.62 250	80.58 252	98.40 240	92.73 171	92.40 265	95.38 312
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 266	90.22 282	94.68 217	94.86 323	87.86 270	97.23 178	97.46 183	87.99 300	89.90 274	96.92 174	66.35 395	98.23 256	90.30 219	90.99 291	97.96 197

nrg030		94.05 148	93.31 159	96.27 123	95.22 301	94.59 32	98.34 25	97.46 183	92.93 135	91.21 246	96.64 190	87.23 137	98.22 257	94.99 119	85.80 344	95.98 279

XVG-OURS		93.72 163	93.35 158	94.80 212	97.07 170	88.61 242	94.79 339	97.46 183	91.97 165	93.99 171	97.86 108	81.74 233	98.88 191	92.64 172	92.67 263	96.92 250

LPG-MVS_test		92.94 193	92.56 187	94.10 246	96.16 246	88.26 255	97.65 118	97.46 183	91.29 184	90.12 267	97.16 159	79.05 281	98.73 211	92.25 176	91.89 275	95.31 317

LGP-MVS_train				94.10 246	96.16 246	88.26 255		97.46 183	91.29 184	90.12 267	97.16 159	79.05 281	98.73 211	92.25 176	91.89 275	95.31 317

MVS		91.71 240	90.44 269	95.51 172	95.20 303	91.59 132	96.04 280	97.45 188	73.44 424	87.36 343	95.60 251	85.42 159	99.10 160	85.97 311	97.46 156	95.83 284

XVG-OURS-SEG-HR		93.86 158	93.55 146	94.81 209	97.06 173	88.53 247	95.28 322	97.45 188	91.68 172	94.08 170	97.68 123	82.41 219	98.90 190	93.84 148	92.47 264	96.98 246

baseline		95.58 97	95.42 94	96.08 133	96.78 198	90.41 183	97.16 185	97.45 188	93.69 97	95.65 133	97.85 109	87.29 135	98.68 217	95.66 98	97.25 169	99.13 82

ab-mvs		93.57 167	92.55 188	96.64 85	97.28 159	91.96 119	95.40 315	97.45 188	89.81 241	93.22 192	96.28 212	79.62 272	99.46 115	90.74 212	93.11 255	98.50 150

xiu_mvs_v2_base		95.32 103	95.29 99	95.40 179	97.22 161	90.50 178	95.44 314	97.44 192	93.70 96	96.46 97	96.18 216	88.59 106	99.53 103	94.79 128	97.81 149	96.17 269

1314		92.81 202	92.03 205	95.14 189	95.33 293	89.52 213	96.04 280	97.44 192	87.72 313	86.25 363	95.33 262	83.84 182	98.79 202	89.26 244	97.05 175	97.11 244

casdiffmvs		95.64 94	95.49 88	96.08 133	96.76 203	90.45 180	97.29 171	97.44 192	94.00 85	95.46 139	97.98 97	87.52 130	98.73 211	95.64 102	97.33 164	99.08 89
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XXY-MVS		92.16 225	91.23 236	94.95 203	94.75 328	90.94 163	97.47 150	97.43 195	89.14 260	88.90 304	96.43 205	79.71 269	98.24 255	89.56 235	87.68 325	95.67 296

anonymousdsp		92.16 225	91.55 222	93.97 255	92.58 394	89.55 210	97.51 140	97.42 196	89.42 253	88.40 318	94.84 285	80.66 250	97.88 312	91.87 186	91.28 285	94.48 363

Effi-MVS+		94.93 118	94.45 127	96.36 116	96.61 208	91.47 138	96.41 251	97.41 197	91.02 200	94.50 159	95.92 230	87.53 128	98.78 203	93.89 146	96.81 179	98.84 126

RRT-MVS		94.51 131	94.35 130	94.98 199	96.40 232	86.55 303	97.56 132	97.41 197	93.19 119	94.93 146	97.04 168	79.12 279	99.30 134	96.19 80	97.32 166	99.09 88

HQP3-MVS								97.39 199							92.10 272

HQP-MVS		93.19 180	92.74 179	94.54 225	95.86 260	89.33 222	96.65 233	97.39 199	93.55 100	90.14 261	95.87 232	80.95 243	98.50 233	92.13 180	92.10 272	95.78 288

PLC	91.00 6	94.11 145	93.43 155	96.13 132	98.58 71	91.15 157	96.69 229	97.39 199	87.29 323	91.37 236	96.71 183	88.39 107	99.52 107	87.33 287	97.13 173	97.73 214
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 290	89.86 296	93.45 286	93.54 368	87.60 276	97.70 112	97.37 202	88.85 272	87.65 336	94.08 333	81.08 242	98.10 270	84.68 328	83.79 377	94.66 360

UnsupCasMVSNet_eth		85.99 366	84.45 370	90.62 370	89.97 412	82.40 371	93.62 383	97.37 202	89.86 237	78.59 414	92.37 378	65.25 403	95.35 405	82.27 356	70.75 422	94.10 374

ACMM	89.79 8	92.96 191	92.50 192	94.35 233	96.30 239	88.71 240	97.58 128	97.36 204	91.40 182	90.53 254	96.65 189	79.77 268	98.75 208	91.24 202	91.64 277	95.59 298
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 113	94.76 111	95.75 156	96.58 211	91.71 125	96.25 267	97.35 205	92.99 128	96.70 82	96.63 194	82.67 211	99.44 118	96.22 73	97.46 156	96.11 275

xiu_mvs_v1_base		95.01 113	94.76 111	95.75 156	96.58 211	91.71 125	96.25 267	97.35 205	92.99 128	96.70 82	96.63 194	82.67 211	99.44 118	96.22 73	97.46 156	96.11 275

xiu_mvs_v1_base_debi		95.01 113	94.76 111	95.75 156	96.58 211	91.71 125	96.25 267	97.35 205	92.99 128	96.70 82	96.63 194	82.67 211	99.44 118	96.22 73	97.46 156	96.11 275

diffmvs		95.25 106	95.13 103	95.63 164	96.43 231	89.34 221	95.99 284	97.35 205	92.83 139	96.31 103	97.37 147	86.44 145	98.67 218	96.26 70	97.19 171	98.87 121
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 128	94.02 135	96.79 81	97.71 134	92.05 113	96.59 242	97.35 205	90.61 217	94.64 155	96.93 171	86.41 146	99.39 123	91.20 203	94.71 227	98.94 106

F-COLMAP		93.58 166	92.98 168	95.37 180	98.40 78	88.98 235	97.18 183	97.29 210	87.75 312	90.49 255	97.10 165	85.21 161	99.50 111	86.70 297	96.72 183	97.63 218

VortexMVS		92.88 197	92.64 183	93.58 279	96.58 211	87.53 277	96.93 204	97.28 211	92.78 142	89.75 279	94.99 276	82.73 210	97.76 325	94.60 133	88.16 320	95.46 303

XVG-ACMP-BASELINE		90.93 286	90.21 283	93.09 299	94.31 347	85.89 316	95.33 319	97.26 212	91.06 199	89.38 292	95.44 260	68.61 378	98.60 225	89.46 237	91.05 289	94.79 353

PCF-MVS	89.48 11	91.56 250	89.95 293	96.36 116	96.60 209	92.52 96	92.51 402	97.26 212	79.41 409	88.90 304	96.56 199	84.04 181	99.55 99	77.01 395	97.30 167	97.01 245
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 206	92.14 201	94.05 249	96.40 232	88.20 258	97.36 163	97.25 214	91.52 175	88.30 322	96.64 190	78.46 293	98.72 214	91.86 187	91.48 281	95.23 324
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 176	92.76 176	94.82 207	94.63 334	90.77 170	96.65 233	97.18 215	93.72 94	91.68 230	97.26 154	79.33 276	98.63 222	92.13 180	92.28 266	95.07 331
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 195	92.02 206	95.56 168	98.19 99	90.80 168	95.27 324	97.18 215	87.96 301	91.86 225	95.68 247	80.44 255	98.99 180	84.01 337	97.54 155	96.89 251

alignmvs		95.87 90	95.23 100	97.78 32	97.56 152	95.19 21	97.86 82	97.17 217	94.39 76	96.47 96	96.40 207	85.89 153	99.20 142	96.21 77	95.11 217	98.95 105

MVS_Test		94.89 120	94.62 117	95.68 162	96.83 192	89.55 210	96.70 227	97.17 217	91.17 192	95.60 134	96.11 225	87.87 119	98.76 207	93.01 168	97.17 172	98.72 132

Fast-Effi-MVS+		93.46 170	92.75 178	95.59 167	96.77 200	90.03 190	96.81 216	97.13 219	88.19 294	91.30 240	94.27 321	86.21 149	98.63 222	87.66 279	96.46 190	98.12 183

EI-MVSNet		93.03 188	92.88 172	93.48 284	95.77 266	86.98 290	96.44 247	97.12 220	90.66 213	91.30 240	97.64 130	86.56 142	98.05 282	89.91 225	90.55 297	95.41 307

MVSTER		93.20 179	92.81 175	94.37 232	96.56 215	89.59 207	97.06 191	97.12 220	91.24 188	91.30 240	95.96 228	82.02 226	98.05 282	93.48 153	90.55 297	95.47 302

test_yl		94.78 126	94.23 132	96.43 109	97.74 132	91.22 146	96.85 211	97.10 222	91.23 189	95.71 128	96.93 171	84.30 174	99.31 132	93.10 161	95.12 215	98.75 129

DCV-MVSNet		94.78 126	94.23 132	96.43 109	97.74 132	91.22 146	96.85 211	97.10 222	91.23 189	95.71 128	96.93 171	84.30 174	99.31 132	93.10 161	95.12 215	98.75 129

LTVRE_ROB	88.41 13	90.99 282	89.92 295	94.19 242	96.18 244	89.55 210	96.31 263	97.09 224	87.88 304	85.67 367	95.91 231	78.79 289	98.57 229	81.50 359	89.98 302	94.44 366
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
test_fmvs1_n		92.73 204	92.88 172	92.29 325	96.08 254	81.05 382	97.98 63	97.08 225	90.72 208	96.79 78	98.18 82	63.07 407	98.45 237	97.62 35	98.42 125	97.36 233

v10		91.04 280	90.23 280	93.49 283	94.12 350	88.16 261	97.32 168	97.08 225	88.26 293	88.29 323	94.22 326	82.17 224	97.97 294	86.45 301	84.12 371	94.33 369

v144192		91.06 279	90.28 276	93.39 287	93.66 365	87.23 284	96.83 214	97.07 227	87.43 319	89.69 282	94.28 320	81.48 236	98.00 289	87.18 291	84.92 360	94.93 339

v1192		91.07 278	90.23 280	93.58 279	93.70 362	87.82 272	96.73 223	97.07 227	87.77 310	89.58 285	94.32 318	80.90 247	97.97 294	86.52 299	85.48 347	94.95 335

v8		91.29 270	90.53 268	93.57 281	94.15 349	88.12 262	97.34 165	97.06 229	88.99 266	88.32 321	94.26 323	83.08 198	98.01 288	87.62 281	83.92 375	94.57 362

mvs_anonymous		93.82 159	93.74 140	94.06 248	96.44 230	85.41 325	95.81 293	97.05 230	89.85 239	90.09 270	96.36 209	87.44 132	97.75 327	93.97 142	96.69 184	99.02 92

IterMVS-LS		92.29 219	91.94 209	93.34 289	96.25 240	86.97 291	96.57 245	97.05 230	90.67 211	89.50 290	94.80 288	86.59 141	97.64 335	89.91 225	86.11 342	95.40 310
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 288	90.03 291	93.29 291	93.55 367	86.96 292	96.74 222	97.04 232	87.36 321	89.52 289	94.34 315	80.23 260	97.97 294	86.27 302	85.21 353	94.94 337

CDS-MVSNet		94.14 144	93.54 147	95.93 145	96.18 244	91.46 139	96.33 261	97.04 232	88.97 268	93.56 179	96.51 201	87.55 126	97.89 311	89.80 228	95.95 195	98.44 160
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 323	89.26 316	91.19 359	95.16 304	80.29 393	94.53 346	97.03 234	91.79 168	88.86 307	94.10 330	69.94 367	97.82 317	85.29 320	86.66 338	95.45 305

v1144		91.37 263	90.60 264	93.68 274	93.89 357	88.23 257	96.84 213	97.03 234	88.37 290	89.69 282	94.39 310	82.04 225	97.98 291	87.80 271	85.37 349	94.84 345

v1240		90.70 294	89.85 297	93.23 293	93.51 370	86.80 293	96.61 239	97.02 236	87.16 326	89.58 285	94.31 319	79.55 273	97.98 291	85.52 317	85.44 348	94.90 342

EPP-MVSNet		95.22 108	95.04 106	95.76 154	97.49 153	89.56 209	98.67 10	97.00 237	90.69 209	94.24 165	97.62 132	89.79 88	98.81 200	93.39 157	96.49 188	98.92 111

V42		91.58 249	90.87 248	93.73 269	94.05 353	88.50 248	97.32 168	96.97 238	88.80 278	89.71 280	94.33 316	82.54 215	98.05 282	89.01 251	85.07 356	94.64 361

test_fmvs1		93.21 178	93.53 148	92.25 328	96.55 217	81.20 381	97.40 159	96.96 239	90.68 210	96.80 76	98.04 91	69.25 373	98.40 240	97.58 36	98.50 118	97.16 243

FMVSNet2		91.31 267	90.08 286	94.99 197	96.51 223	92.21 107	97.41 155	96.95 240	88.82 275	88.62 313	94.75 290	73.87 337	97.42 356	85.20 323	88.55 317	95.35 314

ACMH	87.59 16	90.53 299	89.42 312	93.87 263	96.21 241	87.92 267	97.24 174	96.94 241	88.45 288	83.91 387	96.27 213	71.92 349	98.62 224	84.43 331	89.43 308	95.05 333
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 264	90.27 277	94.59 219	96.51 223	91.18 153	97.50 141	96.93 242	88.82 275	89.35 293	94.51 303	73.87 337	97.29 363	86.12 307	88.82 312	95.31 317

test1		91.35 264	90.27 277	94.59 219	96.51 223	91.18 153	97.50 141	96.93 242	88.82 275	89.35 293	94.51 303	73.87 337	97.29 363	86.12 307	88.82 312	95.31 317

FMVSNet3		91.78 238	90.69 262	95.03 195	96.53 220	92.27 105	97.02 194	96.93 242	89.79 242	89.35 293	94.65 296	77.01 309	97.47 351	86.12 307	88.82 312	95.35 314

FMVSNet1		89.88 318	88.31 331	94.59 219	95.41 283	91.18 153	97.50 141	96.93 242	86.62 334	87.41 341	94.51 303	65.94 400	97.29 363	83.04 346	87.43 328	95.31 317

GeoE		93.89 156	93.28 160	95.72 160	96.96 184	89.75 202	98.24 38	96.92 246	89.47 250	92.12 216	97.21 157	84.42 172	98.39 245	87.71 274	96.50 187	99.01 95

miper_enhance_ethall		91.54 253	91.01 244	93.15 297	95.35 289	87.07 289	93.97 368	96.90 247	86.79 332	89.17 300	93.43 362	86.55 143	97.64 335	89.97 224	86.93 333	94.74 357

eth_miper_zixun_eth		91.02 281	90.59 265	92.34 323	95.33 293	84.35 344	94.10 365	96.90 247	88.56 284	88.84 309	94.33 316	84.08 179	97.60 340	88.77 257	84.37 369	95.06 332

TAMVS		94.01 150	93.46 153	95.64 163	96.16 246	90.45 180	96.71 226	96.89 249	89.27 257	93.46 184	96.92 174	87.29 135	97.94 304	88.70 259	95.74 201	98.53 146

miper_ehance_all_eth		91.59 247	91.13 240	92.97 303	95.55 275	86.57 301	94.47 349	96.88 250	87.77 310	88.88 306	94.01 335	86.22 148	97.54 344	89.49 236	86.93 333	94.79 353

v2v482		91.59 247	90.85 251	93.80 266	93.87 358	88.17 260	96.94 203	96.88 250	89.54 247	89.53 288	94.90 282	81.70 234	98.02 287	89.25 245	85.04 358	95.20 325

CNLPA		94.28 136	93.53 148	96.52 97	98.38 81	92.55 95	96.59 242	96.88 250	90.13 232	91.91 222	97.24 155	85.21 161	99.09 163	87.64 280	97.83 148	97.92 200

PAPM		91.52 254	90.30 275	95.20 186	95.30 296	89.83 200	93.38 388	96.85 253	86.26 342	88.59 314	95.80 237	84.88 165	98.15 264	75.67 400	95.93 196	97.63 218

c3_l		91.38 261	90.89 247	92.88 307	95.58 273	86.30 308	94.68 341	96.84 254	88.17 295	88.83 310	94.23 324	85.65 157	97.47 351	89.36 240	84.63 362	94.89 343

pm-mvs1		90.72 293	89.65 307	93.96 256	94.29 348	89.63 204	97.79 96	96.82 255	89.07 262	86.12 365	95.48 259	78.61 291	97.78 322	86.97 295	81.67 388	94.46 364

test_vis1_n		92.37 214	92.26 199	92.72 313	94.75 328	82.64 364	98.02 59	96.80 256	91.18 191	97.77 50	97.93 100	58.02 417	98.29 253	97.63 34	98.21 133	97.23 241

CMPMVS	62.92 21	85.62 371	84.92 366	87.74 395	89.14 417	73.12 425	94.17 363	96.80 256	73.98 421	73.65 423	94.93 280	66.36 394	97.61 339	83.95 339	91.28 285	92.48 401
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 306	89.77 301	91.78 344	94.33 345	84.72 341	95.55 308	96.73 258	86.17 344	86.36 362	95.28 265	71.28 354	97.80 320	84.09 336	98.14 137	92.81 393

Effi-MVS+-dtu		93.08 185	93.21 162	92.68 316	96.02 257	83.25 358	97.14 187	96.72 259	93.85 91	91.20 247	93.44 359	83.08 198	98.30 252	91.69 193	95.73 202	96.50 260

TSAR-MVS + GP.		96.69 59	96.49 63	97.27 62	98.31 84	93.39 63	96.79 217	96.72 259	94.17 80	97.44 56	97.66 126	92.76 31	99.33 128	96.86 54	97.76 152	99.08 89

1112_ss		93.37 173	92.42 195	96.21 128	97.05 175	90.99 160	96.31 263	96.72 259	86.87 331	89.83 277	96.69 187	86.51 144	99.14 155	88.12 264	93.67 249	98.50 150

PVSNet	86.66 18	92.24 222	91.74 217	93.73 269	97.77 130	83.69 355	92.88 397	96.72 259	87.91 303	93.00 195	94.86 284	78.51 292	99.05 175	86.53 298	97.45 160	98.47 155

miper_lstm_enhance		90.50 302	90.06 290	91.83 340	95.33 293	83.74 352	93.86 374	96.70 263	87.56 317	87.79 333	93.81 343	83.45 190	96.92 375	87.39 285	84.62 363	94.82 348

v148		90.99 282	90.38 271	92.81 310	93.83 359	85.80 317	96.78 220	96.68 264	89.45 252	88.75 312	93.93 339	82.96 204	97.82 317	87.83 270	83.25 380	94.80 351

ACMH+	87.92 14	90.20 310	89.18 318	93.25 292	96.48 226	86.45 305	96.99 199	96.68 264	88.83 274	84.79 376	96.22 215	70.16 364	98.53 231	84.42 332	88.04 321	94.77 356

CANet_DTU		94.37 134	93.65 143	96.55 94	96.46 229	92.13 111	96.21 271	96.67 266	94.38 77	93.53 182	97.03 169	79.34 275	99.71 58	90.76 211	98.45 123	97.82 211

cl____		90.96 285	90.32 273	92.89 306	95.37 287	86.21 311	94.46 351	96.64 267	87.82 306	88.15 328	94.18 327	82.98 202	97.54 344	87.70 275	85.59 345	94.92 341

HY-MVS	89.66 9	93.87 157	92.95 169	96.63 89	97.10 169	92.49 97	95.64 305	96.64 267	89.05 264	93.00 195	95.79 240	85.77 156	99.45 117	89.16 250	94.35 229	97.96 197

Test_1112_low_res		92.84 200	91.84 212	95.85 150	97.04 176	89.97 196	95.53 310	96.64 267	85.38 354	89.65 284	95.18 270	85.86 154	99.10 160	87.70 275	93.58 254	98.49 152

DIV-MVS_self_test		90.97 284	90.33 272	92.88 307	95.36 288	86.19 313	94.46 351	96.63 270	87.82 306	88.18 327	94.23 324	82.99 201	97.53 346	87.72 272	85.57 346	94.93 339

Fast-Effi-MVS+-dtu		92.29 219	91.99 207	93.21 295	95.27 297	85.52 323	97.03 192	96.63 270	92.09 160	89.11 302	95.14 272	80.33 258	98.08 275	87.54 283	94.74 225	96.03 278

UnsupCasMVSNet_bld		82.13 387	79.46 392	90.14 377	88.00 425	82.47 369	90.89 415	96.62 272	78.94 411	75.61 418	84.40 429	56.63 420	96.31 387	77.30 392	66.77 430	91.63 411

cl22		91.21 272	90.56 267	93.14 298	96.09 253	86.80 293	94.41 353	96.58 273	87.80 308	88.58 315	93.99 337	80.85 248	97.62 338	89.87 227	86.93 333	94.99 334

jason		94.84 123	94.39 129	96.18 130	95.52 276	90.93 164	96.09 278	96.52 274	89.28 256	96.01 117	97.32 149	84.70 167	98.77 206	95.15 115	98.91 103	98.85 123
jason: jason.
tt0805		91.09 277	90.07 289	94.16 244	95.61 271	88.31 252	97.56 132	96.51 275	89.56 246	89.17 300	95.64 249	67.08 392	98.38 246	91.07 205	88.44 318	95.80 286

AUN-MVS		91.76 239	90.75 257	94.81 209	97.00 180	88.57 244	96.65 233	96.49 276	89.63 244	92.15 214	96.12 221	78.66 290	98.50 233	90.83 207	79.18 399	97.36 233

hse-mvs2		93.45 171	92.99 167	94.81 209	97.02 178	88.59 243	96.69 229	96.47 277	95.19 29	96.74 80	96.16 219	83.67 185	98.48 236	95.85 92	79.13 400	97.35 235

EG-PatchMatch MVS		87.02 353	85.44 358	91.76 346	92.67 391	85.00 335	96.08 279	96.45 278	83.41 384	79.52 410	93.49 356	57.10 419	97.72 329	79.34 383	90.87 294	92.56 398

KD-MVS_self_test		85.95 367	84.95 365	88.96 389	89.55 416	79.11 408	95.13 331	96.42 279	85.91 347	84.07 385	90.48 401	70.03 366	94.82 408	80.04 375	72.94 419	92.94 391

pmmvs6		87.81 345	86.19 353	92.69 315	91.32 404	86.30 308	97.34 165	96.41 280	80.59 405	84.05 386	94.37 312	67.37 387	97.67 332	84.75 327	79.51 398	94.09 376

PMMVS		92.86 198	92.34 196	94.42 231	94.92 319	86.73 296	94.53 346	96.38 281	84.78 366	94.27 164	95.12 274	83.13 197	98.40 240	91.47 197	96.49 188	98.12 183

RPSCF		90.75 291	90.86 249	90.42 373	96.84 190	76.29 416	95.61 306	96.34 282	83.89 375	91.38 235	97.87 106	76.45 314	98.78 203	87.16 292	92.23 267	96.20 267

BP-MVS1		95.89 88	95.49 88	97.08 74	96.67 205	93.20 73	98.08 53	96.32 283	94.56 65	96.32 102	97.84 111	84.07 180	99.15 152	96.75 56	98.78 106	98.90 115

MSDG		91.42 259	90.24 279	94.96 202	97.15 167	88.91 236	93.69 380	96.32 283	85.72 350	86.93 356	96.47 203	80.24 259	98.98 181	80.57 372	95.05 218	96.98 246

WBMVS		90.69 296	89.99 292	92.81 310	96.48 226	85.00 335	95.21 329	96.30 285	89.46 251	89.04 303	94.05 334	72.45 347	97.82 317	89.46 237	87.41 330	95.61 297

OurMVSNet-221017-0		90.51 301	90.19 284	91.44 352	93.41 376	81.25 379	96.98 200	96.28 286	91.68 172	86.55 360	96.30 211	74.20 336	97.98 291	88.96 253	87.40 331	95.09 330

MVP-Stereo		90.74 292	90.08 286	92.71 314	93.19 381	88.20 258	95.86 290	96.27 287	86.07 345	84.86 375	94.76 289	77.84 304	97.75 327	83.88 341	98.01 143	92.17 408
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 117	94.56 120	96.29 122	96.34 237	91.21 148	95.83 292	96.27 287	88.93 270	96.22 107	96.88 176	86.20 150	98.85 194	95.27 111	99.05 94	98.82 127

BH-untuned		92.94 193	92.62 185	93.92 262	97.22 161	86.16 314	96.40 255	96.25 289	90.06 233	89.79 278	96.17 218	83.19 194	98.35 248	87.19 290	97.27 168	97.24 240

CL-MVSNet_self_test		86.31 362	85.15 362	89.80 381	88.83 420	81.74 377	93.93 371	96.22 290	86.67 333	85.03 373	90.80 399	78.09 300	94.50 409	74.92 403	71.86 421	93.15 389

IS-MVSNet		94.90 119	94.52 124	96.05 136	97.67 136	90.56 176	98.44 21	96.22 290	93.21 116	93.99 171	97.74 119	85.55 158	98.45 237	89.98 223	97.86 147	99.14 81

FA-MVS(test-final)		93.52 169	92.92 170	95.31 183	96.77 200	88.54 246	94.82 338	96.21 292	89.61 245	94.20 166	95.25 268	83.24 192	99.14 155	90.01 222	96.16 192	98.25 171

GA-MVS		91.38 261	90.31 274	94.59 219	94.65 333	87.62 275	94.34 356	96.19 293	90.73 207	90.35 258	93.83 340	71.84 350	97.96 298	87.22 289	93.61 252	98.21 174

LuminaMVS		94.89 120	94.35 130	96.53 95	95.48 278	92.80 84	96.88 209	96.18 294	92.85 138	95.92 120	96.87 178	81.44 237	98.83 197	96.43 68	97.10 174	97.94 199

IterMVS-SCA-FT		90.31 304	89.81 299	91.82 341	95.52 276	84.20 347	94.30 359	96.15 295	90.61 217	87.39 342	94.27 321	75.80 320	96.44 385	87.34 286	86.88 337	94.82 348

IterMVS		90.15 312	89.67 305	91.61 348	95.48 278	83.72 353	94.33 357	96.12 296	89.99 234	87.31 345	94.15 329	75.78 322	96.27 388	86.97 295	86.89 336	94.83 346
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 203	91.51 226	96.52 97	98.77 56	90.99 160	97.38 162	96.08 297	82.38 390	89.29 296	97.87 106	83.77 183	99.69 64	81.37 365	96.69 184	98.89 119

pmmvs4		90.93 286	89.85 297	94.17 243	93.34 378	90.79 169	94.60 343	96.02 298	84.62 367	87.45 339	95.15 271	81.88 231	97.45 353	87.70 275	87.87 323	94.27 373

ppachtmachnet_test		88.35 340	87.29 339	91.53 349	92.45 397	83.57 356	93.75 377	95.97 299	84.28 370	85.32 372	94.18 327	79.00 287	96.93 374	75.71 399	84.99 359	94.10 374

Anonymous20240521		86.42 360	85.44 358	89.34 387	90.33 409	79.79 399	96.73 223	95.92 300	83.71 380	83.25 391	91.36 396	63.92 405	96.01 389	78.39 387	85.36 350	92.22 406

ITE_SJBPF				92.43 319	95.34 290	85.37 328		95.92 300	91.47 177	87.75 335	96.39 208	71.00 356	97.96 298	82.36 355	89.86 304	93.97 379

test_fmvs2		89.77 322	89.93 294	89.31 388	93.68 364	76.37 415	97.64 122	95.90 302	89.84 240	91.49 233	96.26 214	58.77 415	97.10 367	94.65 130	91.13 287	94.46 364

USDC		88.94 331	87.83 336	92.27 326	94.66 332	84.96 337	93.86 374	95.90 302	87.34 322	83.40 389	95.56 253	67.43 386	98.19 261	82.64 354	89.67 306	93.66 382

COLMAP_ROB	87.81 15	90.40 303	89.28 315	93.79 267	97.95 119	87.13 288	96.92 205	95.89 304	82.83 387	86.88 358	97.18 158	73.77 340	99.29 135	78.44 386	93.62 251	94.95 335
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 159	93.08 165	96.02 139	97.88 125	89.96 197	97.72 107	95.85 305	92.43 148	95.86 122	98.44 55	68.42 382	99.39 123	96.31 69	94.85 219	98.71 134

VDDNet		93.05 187	92.07 202	96.02 139	96.84 190	90.39 184	98.08 53	95.85 305	86.22 343	95.79 125	98.46 53	67.59 385	99.19 143	94.92 120	94.85 219	98.47 155

mvsmamba		94.57 130	94.14 134	95.87 147	97.03 177	89.93 198	97.84 86	95.85 305	91.34 183	94.79 152	96.80 179	80.67 249	98.81 200	94.85 121	98.12 138	98.85 123

Vis-MVSNet (Re-imp)		94.15 141	93.88 138	94.95 203	97.61 144	87.92 267	98.10 51	95.80 308	92.22 153	93.02 194	97.45 141	84.53 170	97.91 310	88.24 263	97.97 144	99.02 92

MM		97.29 24	96.98 34	98.23 11	98.01 113	95.03 26	98.07 55	95.76 309	97.78 1	97.52 53	98.80 33	88.09 112	99.86 9	99.44 1	99.37 62	99.80 1

KD-MVS_2432*1600		84.81 377	82.64 380	91.31 354	91.07 406	85.34 329	91.22 410	95.75 310	85.56 352	83.09 392	90.21 404	67.21 388	95.89 391	77.18 393	62.48 434	92.69 394

miper_refine_blended		84.81 377	82.64 380	91.31 354	91.07 406	85.34 329	91.22 410	95.75 310	85.56 352	83.09 392	90.21 404	67.21 388	95.89 391	77.18 393	62.48 434	92.69 394

FE-MVS		92.05 230	91.05 242	95.08 192	96.83 192	87.93 266	93.91 373	95.70 312	86.30 340	94.15 168	94.97 277	76.59 312	99.21 141	84.10 335	96.86 177	98.09 189

tpm cat1		88.36 339	87.21 342	91.81 342	95.13 309	80.55 388	92.58 401	95.70 312	74.97 420	87.45 339	91.96 389	78.01 303	98.17 263	80.39 374	88.74 315	96.72 256

our_test_3		88.78 335	87.98 335	91.20 358	92.45 397	82.53 366	93.61 384	95.69 314	85.77 349	84.88 374	93.71 345	79.99 264	96.78 381	79.47 380	86.24 339	94.28 372

BH-w/o		92.14 227	91.75 215	93.31 290	96.99 181	85.73 320	95.67 300	95.69 314	88.73 280	89.26 298	94.82 287	82.97 203	98.07 279	85.26 322	96.32 191	96.13 274

CR-MVSNet		90.82 289	89.77 301	93.95 257	94.45 341	87.19 285	90.23 418	95.68 316	86.89 330	92.40 204	92.36 381	80.91 245	97.05 369	81.09 369	93.95 245	97.60 223

Patchmtry		88.64 337	87.25 340	92.78 312	94.09 351	86.64 297	89.82 422	95.68 316	80.81 402	87.63 337	92.36 381	80.91 245	97.03 370	78.86 384	85.12 355	94.67 359

testing91		91.90 235	91.02 243	94.53 226	96.54 218	86.55 303	95.86 290	95.64 318	91.77 169	91.89 223	93.47 358	69.94 367	98.86 192	90.23 221	93.86 247	98.18 176

BH-RMVSNet		92.72 205	91.97 208	94.97 201	97.16 165	87.99 265	96.15 276	95.60 319	90.62 216	91.87 224	97.15 161	78.41 294	98.57 229	83.16 344	97.60 154	98.36 167

PVSNet_0	82.17 19	85.46 372	83.64 375	90.92 362	95.27 297	79.49 404	90.55 416	95.60 319	83.76 379	83.00 394	89.95 406	71.09 355	97.97 294	82.75 352	60.79 436	95.31 317

guyue		95.17 111	94.96 107	95.82 151	96.97 183	89.65 203	97.56 132	95.58 321	94.82 50	95.72 127	97.42 145	82.90 205	98.84 196	96.71 59	96.93 176	98.96 102

SCA		91.84 237	91.18 239	93.83 264	95.59 272	84.95 338	94.72 340	95.58 321	90.82 203	92.25 212	93.69 347	75.80 320	98.10 270	86.20 304	95.98 194	98.45 157

MonoMVSNet		91.92 233	91.77 213	92.37 320	92.94 385	83.11 360	97.09 190	95.55 323	92.91 136	90.85 250	94.55 300	81.27 241	96.52 384	93.01 168	87.76 324	97.47 229

AllTest		90.23 308	88.98 321	93.98 253	97.94 120	86.64 297	96.51 246	95.54 324	85.38 354	85.49 369	96.77 181	70.28 362	99.15 152	80.02 376	92.87 256	96.15 272

TestCases				93.98 253	97.94 120	86.64 297		95.54 324	85.38 354	85.49 369	96.77 181	70.28 362	99.15 152	80.02 376	92.87 256	96.15 272

mmtdpeth		89.70 324	88.96 322	91.90 337	95.84 265	84.42 343	97.46 152	95.53 326	90.27 227	94.46 161	90.50 400	69.74 371	98.95 182	97.39 45	69.48 425	92.34 402

tpmvs		89.83 321	89.15 319	91.89 338	94.92 319	80.30 392	93.11 393	95.46 327	86.28 341	88.08 329	92.65 371	80.44 255	98.52 232	81.47 361	89.92 303	96.84 252

pmmvs5		89.86 320	88.87 325	92.82 309	92.86 387	86.23 310	96.26 266	95.39 328	84.24 371	87.12 347	94.51 303	74.27 335	97.36 360	87.61 282	87.57 326	94.86 344

PatchmatchNet		91.91 234	91.35 228	93.59 278	95.38 285	84.11 348	93.15 392	95.39 328	89.54 247	92.10 217	93.68 349	82.82 208	98.13 265	84.81 326	95.32 211	98.52 147
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 258	91.32 230	91.79 343	95.15 307	79.20 407	93.42 387	95.37 330	88.55 285	93.49 183	93.67 350	82.49 217	98.27 254	90.41 216	89.34 309	97.90 201

Anonymous20231206		87.09 352	86.14 354	89.93 380	91.22 405	80.35 390	96.11 277	95.35 331	83.57 382	84.16 381	93.02 366	73.54 342	95.61 399	72.16 415	86.14 341	93.84 381

MIMVSNet1		84.93 375	83.05 377	90.56 371	89.56 415	84.84 340	95.40 315	95.35 331	83.91 374	80.38 406	92.21 386	57.23 418	93.34 421	70.69 421	82.75 386	93.50 384

TDRefinement		86.53 356	84.76 368	91.85 339	82.23 437	84.25 345	96.38 257	95.35 331	84.97 363	84.09 384	94.94 279	65.76 401	98.34 251	84.60 330	74.52 415	92.97 390

TR-MVS		91.48 257	90.59 265	94.16 244	96.40 232	87.33 278	95.67 300	95.34 334	87.68 314	91.46 234	95.52 256	76.77 311	98.35 248	82.85 349	93.61 252	96.79 254

EPNet_dtu		91.71 240	91.28 233	92.99 302	93.76 361	83.71 354	96.69 229	95.28 335	93.15 123	87.02 352	95.95 229	83.37 191	97.38 359	79.46 381	96.84 178	97.88 203
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 349	85.79 356	91.78 344	94.80 326	87.28 280	95.49 312	95.28 335	84.09 373	83.85 388	91.82 390	62.95 408	94.17 413	78.48 385	85.34 351	93.91 380

MDTV_nov1_ep13			90.76 255		95.22 301	80.33 391	93.03 395	95.28 335	88.14 298	92.84 201	93.83 340	81.34 238	98.08 275	82.86 347	94.34 230

LF4IMVS		87.94 343	87.25 340	89.98 379	92.38 399	80.05 398	94.38 354	95.25 338	87.59 316	84.34 378	94.74 291	64.31 404	97.66 334	84.83 325	87.45 327	92.23 405

TransMVSNet (Re)		88.94 331	87.56 337	93.08 300	94.35 344	88.45 250	97.73 104	95.23 339	87.47 318	84.26 380	95.29 263	79.86 267	97.33 361	79.44 382	74.44 416	93.45 386

test20.03		86.14 365	85.40 360	88.35 390	90.12 410	80.06 397	95.90 289	95.20 340	88.59 281	81.29 401	93.62 352	71.43 353	92.65 425	71.26 419	81.17 391	92.34 402

new-patchmatchnet		83.18 383	81.87 386	87.11 398	86.88 428	75.99 417	93.70 378	95.18 341	85.02 362	77.30 417	88.40 416	65.99 399	93.88 418	74.19 408	70.18 423	91.47 415

MDA-MVSNet_test_wron		85.87 369	84.23 372	90.80 368	92.38 399	82.57 365	93.17 390	95.15 342	82.15 391	67.65 429	92.33 384	78.20 296	95.51 402	77.33 390	79.74 395	94.31 371

YYNet1		85.87 369	84.23 372	90.78 369	92.38 399	82.46 370	93.17 390	95.14 343	82.12 392	67.69 427	92.36 381	78.16 299	95.50 403	77.31 391	79.73 396	94.39 367

Baseline_NR-MVSNet		91.20 273	90.62 263	92.95 304	93.83 359	88.03 264	97.01 197	95.12 344	88.42 289	89.70 281	95.13 273	83.47 188	97.44 354	89.66 233	83.24 381	93.37 387

thres200		92.23 223	91.39 227	94.75 216	97.61 144	89.03 234	96.60 241	95.09 345	92.08 161	93.28 189	94.00 336	78.39 295	99.04 178	81.26 368	94.18 236	96.19 268

ADS-MVSNet		89.89 317	88.68 327	93.53 282	95.86 260	84.89 339	90.93 413	95.07 346	83.23 385	91.28 243	91.81 391	79.01 285	97.85 313	79.52 378	91.39 283	97.84 208

pmmvs-eth3d		86.22 363	84.45 370	91.53 349	88.34 424	87.25 282	94.47 349	95.01 347	83.47 383	79.51 411	89.61 409	69.75 370	95.71 396	83.13 345	76.73 409	91.64 410

Anonymous202405211		92.07 229	90.83 253	95.76 154	98.19 99	88.75 239	97.58 128	95.00 348	86.00 346	93.64 178	97.45 141	66.24 397	99.53 103	90.68 214	92.71 261	99.01 95

MDA-MVSNet-bldmvs		85.00 374	82.95 379	91.17 360	93.13 383	83.33 357	94.56 345	95.00 348	84.57 368	65.13 433	92.65 371	70.45 361	95.85 393	73.57 411	77.49 405	94.33 369

ambc				86.56 401	83.60 434	70.00 428	85.69 432	94.97 350		80.60 405	88.45 415	37.42 436	96.84 378	82.69 353	75.44 413	92.86 392

testgi		87.97 342	87.21 342	90.24 376	92.86 387	80.76 383	96.67 232	94.97 350	91.74 170	85.52 368	95.83 235	62.66 410	94.47 411	76.25 397	88.36 319	95.48 300

myMVS_eth3d28		91.52 254	90.97 245	93.17 296	96.91 185	83.24 359	95.61 306	94.96 352	92.24 152	91.98 220	93.28 363	69.31 372	98.40 240	88.71 258	95.68 204	97.88 203

dp		88.90 333	88.26 333	90.81 366	94.58 337	76.62 414	92.85 398	94.93 353	85.12 360	90.07 272	93.07 365	75.81 319	98.12 268	80.53 373	87.42 329	97.71 215

test_fmvs3		83.21 382	83.02 378	83.78 405	86.77 429	68.34 431	96.76 221	94.91 354	86.49 336	84.14 383	89.48 410	36.04 437	91.73 427	91.86 187	80.77 393	91.26 417

test_0402		86.46 359	84.79 367	91.45 351	95.02 313	85.55 322	96.29 265	94.89 355	80.90 399	82.21 397	93.97 338	68.21 383	97.29 363	62.98 428	88.68 316	91.51 413

tfpn200view9		92.38 213	91.52 224	94.95 203	97.85 126	89.29 224	97.41 155	94.88 356	92.19 157	93.27 190	94.46 308	78.17 297	99.08 166	81.40 362	94.08 240	96.48 261

CVMVSNet		91.23 271	91.75 215	89.67 382	95.77 266	74.69 418	96.44 247	94.88 356	85.81 348	92.18 213	97.64 130	79.07 280	95.58 401	88.06 266	95.86 199	98.74 131

thres400		92.42 211	91.52 224	95.12 191	97.85 126	89.29 224	97.41 155	94.88 356	92.19 157	93.27 190	94.46 308	78.17 297	99.08 166	81.40 362	94.08 240	96.98 246

tt0320		85.39 373	83.12 376	92.19 330	93.44 375	85.79 318	96.19 273	94.87 359	71.19 427	82.92 395	91.76 393	58.43 416	96.81 379	81.03 370	78.26 404	93.98 378

EPNet		95.20 109	94.56 120	97.14 69	92.80 389	92.68 90	97.85 85	94.87 359	96.64 5	92.46 203	97.80 116	86.23 147	99.65 70	93.72 150	98.62 114	99.10 87
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 245	90.72 260	94.32 236	96.48 226	86.11 315	95.81 293	94.76 361	91.55 174	91.75 228	93.44 359	68.55 380	98.82 198	90.43 215	93.69 248	98.04 193

sc_t1		86.48 358	84.10 374	93.63 275	93.45 374	85.76 319	96.79 217	94.71 362	73.06 425	86.45 361	94.35 313	55.13 423	97.95 302	84.38 333	78.55 403	97.18 242

SixPastTwentyTwo		89.15 329	88.54 329	90.98 361	93.49 371	80.28 394	96.70 227	94.70 363	90.78 204	84.15 382	95.57 252	71.78 351	97.71 330	84.63 329	85.07 356	94.94 337

thres100view900		92.43 210	91.58 221	94.98 199	97.92 122	89.37 220	97.71 109	94.66 364	92.20 155	93.31 188	94.90 282	78.06 301	99.08 166	81.40 362	94.08 240	96.48 261

thres600view7		92.49 209	91.60 220	95.18 187	97.91 123	89.47 214	97.65 118	94.66 364	92.18 159	93.33 187	94.91 281	78.06 301	99.10 160	81.61 358	94.06 244	96.98 246

PatchT		88.87 334	87.42 338	93.22 294	94.08 352	85.10 333	89.51 423	94.64 366	81.92 393	92.36 207	88.15 419	80.05 263	97.01 372	72.43 414	93.65 250	97.54 226

baseline1		92.82 201	91.90 210	95.55 170	97.20 163	90.77 170	97.19 182	94.58 367	92.20 155	92.36 207	96.34 210	84.16 178	98.21 258	89.20 248	83.90 376	97.68 217

AstraMVS		94.82 125	94.64 116	95.34 182	96.36 236	88.09 263	97.58 128	94.56 368	94.98 39	95.70 130	97.92 101	81.93 230	98.93 185	96.87 53	95.88 197	98.99 99

UBG		91.55 251	90.76 255	93.94 259	96.52 222	85.06 334	95.22 327	94.54 369	90.47 223	91.98 220	92.71 370	72.02 348	98.74 210	88.10 265	95.26 213	98.01 195

Gipuma		67.86 403	65.41 405	75.18 418	92.66 392	73.45 422	66.50 439	94.52 370	53.33 438	57.80 439	66.07 439	30.81 439	89.20 431	48.15 437	78.88 402	62.90 439
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 243	90.75 257	94.47 227	96.53 220	86.56 302	95.76 297	94.51 371	91.10 198	91.24 245	93.59 353	68.59 379	98.86 192	91.10 204	94.29 232	98.00 196

CostFormer		91.18 276	90.70 261	92.62 317	94.84 324	81.76 376	94.09 366	94.43 372	84.15 372	92.72 202	93.77 344	79.43 274	98.20 259	90.70 213	92.18 270	97.90 201

tpm2		89.96 314	89.21 317	92.23 329	94.91 321	81.25 379	93.78 376	94.42 373	80.62 404	91.56 231	93.44 359	76.44 315	97.94 304	85.60 316	92.08 274	97.49 227

testing3-2		92.10 228	92.05 203	92.27 326	97.71 134	79.56 401	97.42 154	94.41 374	93.53 104	93.22 192	95.49 257	69.16 374	99.11 158	93.25 158	94.22 234	98.13 181

MVS_0304		96.74 56	96.31 73	98.02 19	96.87 187	94.65 30	97.58 128	94.39 375	96.47 8	97.16 65	98.39 59	87.53 128	99.87 7	98.97 16	99.41 54	99.55 36

JIA-IIPM		88.26 341	87.04 345	91.91 336	93.52 369	81.42 378	89.38 424	94.38 376	80.84 401	90.93 249	80.74 431	79.22 277	97.92 307	82.76 351	91.62 278	96.38 264

dmvs_re		90.21 309	89.50 310	92.35 321	95.47 282	85.15 331	95.70 299	94.37 377	90.94 202	88.42 317	93.57 354	74.63 332	95.67 398	82.80 350	89.57 307	96.22 266

Patchmatch-test		89.42 327	87.99 334	93.70 272	95.27 297	85.11 332	88.98 425	94.37 377	81.11 398	87.10 350	93.69 347	82.28 221	97.50 349	74.37 406	94.76 223	98.48 154

LCM-MVSNet		72.55 396	69.39 400	82.03 407	70.81 447	65.42 436	90.12 420	94.36 379	55.02 437	65.88 431	81.72 430	24.16 445	89.96 428	74.32 407	68.10 428	90.71 420

ADS-MVSNet2		89.45 326	88.59 328	92.03 333	95.86 260	82.26 372	90.93 413	94.32 380	83.23 385	91.28 243	91.81 391	79.01 285	95.99 390	79.52 378	91.39 283	97.84 208

mvs5depth		86.53 356	85.08 363	90.87 363	88.74 422	82.52 367	91.91 406	94.23 381	86.35 339	87.11 349	93.70 346	66.52 393	97.76 325	81.37 365	75.80 411	92.31 404

EU-MVSNet		88.72 336	88.90 324	88.20 392	93.15 382	74.21 420	96.63 238	94.22 382	85.18 358	87.32 344	95.97 227	76.16 317	94.98 407	85.27 321	86.17 340	95.41 307

tt0320-xc		84.83 376	82.33 384	92.31 324	93.66 365	86.20 312	96.17 275	94.06 383	71.26 426	82.04 399	92.22 385	55.07 424	96.72 382	81.49 360	75.04 414	94.02 377

MIMVSNet		88.50 338	86.76 348	93.72 271	94.84 324	87.77 273	91.39 408	94.05 384	86.41 338	87.99 331	92.59 374	63.27 406	95.82 395	77.44 389	92.84 258	97.57 225

OpenMVS_ROB	81.14 20	84.42 379	82.28 385	90.83 364	90.06 411	84.05 350	95.73 298	94.04 385	73.89 423	80.17 409	91.53 395	59.15 414	97.64 335	66.92 426	89.05 311	90.80 419

TinyColmap		86.82 354	85.35 361	91.21 356	94.91 321	82.99 362	93.94 370	94.02 386	83.58 381	81.56 400	94.68 293	62.34 411	98.13 265	75.78 398	87.35 332	92.52 400

ETVMVS		90.52 300	89.14 320	94.67 218	96.81 196	87.85 271	95.91 288	93.97 387	89.71 243	92.34 210	92.48 376	65.41 402	97.96 298	81.37 365	94.27 233	98.21 174

IB-MVS	87.33 17	89.91 315	88.28 332	94.79 213	95.26 300	87.70 274	95.12 332	93.95 388	89.35 255	87.03 351	92.49 375	70.74 359	99.19 143	89.18 249	81.37 390	97.49 227
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
Syy-MVS		87.13 351	87.02 346	87.47 396	95.16 304	73.21 424	95.00 334	93.93 389	88.55 285	86.96 353	91.99 387	75.90 318	94.00 415	61.59 430	94.11 237	95.20 325

myMVS_eth3d		87.18 350	86.38 351	89.58 383	95.16 304	79.53 402	95.00 334	93.93 389	88.55 285	86.96 353	91.99 387	56.23 421	94.00 415	75.47 402	94.11 237	95.20 325

testing222		90.31 304	88.96 322	94.35 233	96.54 218	87.29 279	95.50 311	93.84 391	90.97 201	91.75 228	92.96 367	62.18 412	98.00 289	82.86 347	94.08 240	97.76 213

test_f		80.57 389	79.62 391	83.41 406	83.38 435	67.80 433	93.57 385	93.72 392	80.80 403	77.91 416	87.63 422	33.40 438	92.08 426	87.14 293	79.04 401	90.34 421

LCM-MVSNet-Re		92.50 207	92.52 191	92.44 318	96.82 194	81.89 375	96.92 205	93.71 393	92.41 149	84.30 379	94.60 298	85.08 163	97.03 370	91.51 195	97.36 162	98.40 163

tpm		90.25 307	89.74 304	91.76 346	93.92 355	79.73 400	93.98 367	93.54 394	88.28 292	91.99 219	93.25 364	77.51 307	97.44 354	87.30 288	87.94 322	98.12 183

ET-MVSNet_ETH3D		91.49 256	90.11 285	95.63 164	96.40 232	91.57 134	95.34 318	93.48 395	90.60 219	75.58 419	95.49 257	80.08 262	96.79 380	94.25 138	89.76 305	98.52 147

LFMVS		93.60 165	92.63 184	96.52 97	98.13 105	91.27 145	97.94 73	93.39 396	90.57 220	96.29 104	98.31 72	69.00 375	99.16 150	94.18 139	95.87 198	99.12 85

MVStest1		82.38 386	80.04 390	89.37 385	87.63 427	82.83 363	95.03 333	93.37 397	73.90 422	73.50 424	94.35 313	62.89 409	93.25 423	73.80 409	65.92 431	92.04 409

Patchmatch-RL test		87.38 348	86.24 352	90.81 366	88.74 422	78.40 411	88.12 430	93.17 398	87.11 327	82.17 398	89.29 411	81.95 228	95.60 400	88.64 260	77.02 406	98.41 162

ttmdpeth		85.91 368	84.76 368	89.36 386	89.14 417	80.25 395	95.66 303	93.16 399	83.77 378	83.39 390	95.26 267	66.24 397	95.26 406	80.65 371	75.57 412	92.57 397

test-LLR		91.42 259	91.19 238	92.12 331	94.59 335	80.66 385	94.29 360	92.98 400	91.11 196	90.76 252	92.37 378	79.02 283	98.07 279	88.81 255	96.74 181	97.63 218

test-mter		90.19 311	89.54 309	92.12 331	94.59 335	80.66 385	94.29 360	92.98 400	87.68 314	90.76 252	92.37 378	67.67 384	98.07 279	88.81 255	96.74 181	97.63 218

WB-MVSnew		89.88 318	89.56 308	90.82 365	94.57 338	83.06 361	95.65 304	92.85 402	87.86 305	90.83 251	94.10 330	79.66 271	96.88 376	76.34 396	94.19 235	92.54 399

testing3		87.67 346	86.88 347	90.05 378	96.14 249	80.71 384	97.10 189	92.85 402	90.15 231	87.54 338	94.55 300	55.70 422	94.10 414	73.77 410	94.10 239	95.35 314

test_method		66.11 404	64.89 406	69.79 421	72.62 445	35.23 453	65.19 440	92.83 404	20.35 443	65.20 432	88.08 420	43.14 434	82.70 438	73.12 413	63.46 433	91.45 416

test0.0.03 1		89.37 328	88.70 326	91.41 353	92.47 396	85.63 321	95.22 327	92.70 405	91.11 196	86.91 357	93.65 351	79.02 283	93.19 424	78.00 388	89.18 310	95.41 307

new_pmnet		82.89 384	81.12 389	88.18 393	89.63 414	80.18 396	91.77 407	92.57 406	76.79 418	75.56 420	88.23 418	61.22 413	94.48 410	71.43 417	82.92 384	89.87 422

mvsany_test1		93.93 155	93.98 136	93.78 268	94.94 318	86.80 293	94.62 342	92.55 407	88.77 279	96.85 75	98.49 49	88.98 95	98.08 275	95.03 117	95.62 206	96.46 263

thisisatest0515		92.29 219	91.30 232	95.25 185	96.60 209	88.90 237	94.36 355	92.32 408	87.92 302	93.43 185	94.57 299	77.28 308	99.00 179	89.42 239	95.86 199	97.86 207

thisisatest0530		93.03 188	92.21 200	95.49 174	97.07 170	89.11 233	97.49 149	92.19 409	90.16 230	94.09 169	96.41 206	76.43 316	99.05 175	90.38 217	95.68 204	98.31 169

tttt0517		92.96 191	92.33 197	94.87 206	97.11 168	87.16 287	97.97 69	92.09 410	90.63 215	93.88 175	97.01 170	76.50 313	99.06 172	90.29 220	95.45 209	98.38 165

K. test v3		87.64 347	86.75 349	90.32 375	93.02 384	79.48 405	96.61 239	92.08 411	90.66 213	80.25 408	94.09 332	67.21 388	96.65 383	85.96 312	80.83 392	94.83 346

TESTMET0.1,1		90.06 313	89.42 312	91.97 334	94.41 343	80.62 387	94.29 360	91.97 412	87.28 324	90.44 256	92.47 377	68.79 376	97.67 332	88.50 262	96.60 186	97.61 222

PM-MVS		83.48 381	81.86 387	88.31 391	87.83 426	77.59 413	93.43 386	91.75 413	86.91 329	80.63 404	89.91 407	44.42 433	95.84 394	85.17 324	76.73 409	91.50 414

baseline2		91.63 244	90.86 249	93.94 259	94.33 345	86.32 307	95.92 287	91.64 414	89.37 254	86.94 355	94.69 292	81.62 235	98.69 216	88.64 260	94.57 228	96.81 253

APD_test1		79.31 391	77.70 394	84.14 404	89.11 419	69.07 430	92.36 405	91.50 415	69.07 429	73.87 422	92.63 373	39.93 435	94.32 412	70.54 422	80.25 394	89.02 424

FPMVS		71.27 397	69.85 399	75.50 417	74.64 442	59.03 442	91.30 409	91.50 415	58.80 434	57.92 438	88.28 417	29.98 441	85.53 437	53.43 435	82.84 385	81.95 430

door								91.13 417

door-mid								91.06 418

EGC-MVSNET		68.77 402	63.01 408	86.07 403	92.49 395	82.24 373	93.96 369	90.96 419	0.71 448	2.62 449	90.89 398	53.66 425	93.46 419	57.25 433	84.55 366	82.51 429

mvsany_test3		83.59 380	82.44 383	87.03 399	83.80 432	73.82 421	93.70 378	90.92 420	86.42 337	82.51 396	90.26 403	46.76 432	95.71 396	90.82 208	76.76 408	91.57 412

pmmvs3		79.97 390	77.50 395	87.39 397	82.80 436	79.38 406	92.70 400	90.75 421	70.69 428	78.66 413	87.47 424	51.34 428	93.40 420	73.39 412	69.65 424	89.38 423

UWE-MVS		89.91 315	89.48 311	91.21 356	95.88 259	78.23 412	94.91 337	90.26 422	89.11 261	92.35 209	94.52 302	68.76 377	97.96 298	83.95 339	95.59 207	97.42 231

DSMNet-mixed		86.34 361	86.12 355	87.00 400	89.88 413	70.43 426	94.93 336	90.08 423	77.97 415	85.42 371	92.78 369	74.44 334	93.96 417	74.43 405	95.14 214	96.62 257

MVS-HIRNet		82.47 385	81.21 388	86.26 402	95.38 285	69.21 429	88.96 426	89.49 424	66.28 431	80.79 403	74.08 436	68.48 381	97.39 358	71.93 416	95.47 208	92.18 407

WB-MVS		76.77 393	76.63 396	77.18 412	85.32 430	56.82 444	94.53 346	89.39 425	82.66 389	71.35 425	89.18 412	75.03 327	88.88 432	35.42 441	66.79 429	85.84 426

test1111		93.19 180	92.82 174	94.30 239	97.58 150	84.56 342	98.21 42	89.02 426	93.53 104	94.58 156	98.21 79	72.69 344	99.05 175	93.06 164	98.48 121	99.28 70

SSC-MVS		76.05 394	75.83 397	76.72 416	84.77 431	56.22 445	94.32 358	88.96 427	81.82 395	70.52 426	88.91 413	74.79 331	88.71 433	33.69 442	64.71 432	85.23 427

ECVR-MVS		93.19 180	92.73 180	94.57 224	97.66 138	85.41 325	98.21 42	88.23 428	93.43 109	94.70 154	98.21 79	72.57 345	99.07 170	93.05 165	98.49 119	99.25 73

EPMVS		90.70 294	89.81 299	93.37 288	94.73 330	84.21 346	93.67 381	88.02 429	89.50 249	92.38 206	93.49 356	77.82 305	97.78 322	86.03 310	92.68 262	98.11 188

ANet_high		63.94 406	59.58 409	77.02 413	61.24 449	66.06 434	85.66 433	87.93 430	78.53 413	42.94 441	71.04 438	25.42 444	80.71 440	52.60 436	30.83 442	84.28 428

PMMVS2		70.19 398	66.92 402	80.01 408	76.35 441	65.67 435	86.22 431	87.58 431	64.83 433	62.38 434	80.29 433	26.78 443	88.49 435	63.79 427	54.07 438	85.88 425

lessismore_v0				90.45 372	91.96 402	79.09 409		87.19 432		80.32 407	94.39 310	66.31 396	97.55 343	84.00 338	76.84 407	94.70 358

PMVS	53.92 22	58.58 407	55.40 410	68.12 422	51.00 450	48.64 447	78.86 436	87.10 433	46.77 439	35.84 445	74.28 435	8.76 449	86.34 436	42.07 439	73.91 417	69.38 436
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 355	86.41 350	88.02 394	92.87 386	74.60 419	95.38 317	86.70 434	88.17 295	87.28 346	94.67 295	70.83 358	93.30 422	67.45 424	94.31 231	96.17 269

test_vis1_rt		86.16 364	85.06 364	89.46 384	93.47 373	80.46 389	96.41 251	86.61 435	85.22 357	79.15 412	88.64 414	52.41 427	97.06 368	93.08 163	90.57 296	90.87 418

testf1		69.31 400	66.76 403	76.94 414	78.61 439	61.93 438	88.27 428	86.11 436	55.62 435	59.69 435	85.31 427	20.19 447	89.32 429	57.62 431	69.44 426	79.58 431

APD_test2		69.31 400	66.76 403	76.94 414	78.61 439	61.93 438	88.27 428	86.11 436	55.62 435	59.69 435	85.31 427	20.19 447	89.32 429	57.62 431	69.44 426	79.58 431

gg-mvs-nofinetune		87.82 344	85.61 357	94.44 229	94.46 340	89.27 227	91.21 412	84.61 438	80.88 400	89.89 276	74.98 434	71.50 352	97.53 346	85.75 315	97.21 170	96.51 259

dmvs_testset		81.38 388	82.60 382	77.73 411	91.74 403	51.49 446	93.03 395	84.21 439	89.07 262	78.28 415	91.25 397	76.97 310	88.53 434	56.57 434	82.24 387	93.16 388

GG-mvs-BLEND				93.62 276	93.69 363	89.20 229	92.39 404	83.33 440		87.98 332	89.84 408	71.00 356	96.87 377	82.08 357	95.40 210	94.80 351

MTMP							97.86 82	82.03 441

DeepMVS_CX				74.68 419	90.84 408	64.34 437		81.61 442	65.34 432	67.47 430	88.01 421	48.60 431	80.13 441	62.33 429	73.68 418	79.58 431

E-PMN		53.28 408	52.56 412	55.43 425	74.43 443	47.13 448	83.63 435	76.30 443	42.23 440	42.59 442	62.22 441	28.57 442	74.40 442	31.53 443	31.51 441	44.78 440

test2506		91.60 246	90.78 254	94.04 250	97.66 138	83.81 351	98.27 32	75.53 444	93.43 109	95.23 141	98.21 79	67.21 388	99.07 170	93.01 168	98.49 119	99.25 73

EMVS		52.08 410	51.31 413	54.39 426	72.62 445	45.39 450	83.84 434	75.51 445	41.13 441	40.77 443	59.65 442	30.08 440	73.60 443	28.31 445	29.90 443	44.18 441

test_vis3_rt		72.73 395	70.55 398	79.27 409	80.02 438	68.13 432	93.92 372	74.30 446	76.90 417	58.99 437	73.58 437	20.29 446	95.37 404	84.16 334	72.80 420	74.31 434

MVE	50.73 23	53.25 409	48.81 414	66.58 424	65.34 448	57.50 443	72.49 438	70.94 447	40.15 442	39.28 444	63.51 440	6.89 451	73.48 444	38.29 440	42.38 440	68.76 438
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 411	53.82 411	46.29 427	33.73 451	45.30 451	78.32 437	67.24 448	18.02 444	50.93 440	87.05 425	52.99 426	53.11 446	70.76 420	25.29 444	40.46 442

kuosan		65.27 405	64.66 407	67.11 423	83.80 432	61.32 441	88.53 427	60.77 449	68.22 430	67.67 428	80.52 432	49.12 430	70.76 445	29.67 444	53.64 439	69.26 437

dongtai		69.99 399	69.33 401	71.98 420	88.78 421	61.64 440	89.86 421	59.93 450	75.67 419	74.96 421	85.45 426	50.19 429	81.66 439	43.86 438	55.27 437	72.63 435

N_pmnet		78.73 392	78.71 393	78.79 410	92.80 389	46.50 449	94.14 364	43.71 451	78.61 412	80.83 402	91.66 394	74.94 330	96.36 386	67.24 425	84.45 368	93.50 384

wuyk23d		25.11 412	24.57 416	26.74 428	73.98 444	39.89 452	57.88 441	9.80 452	12.27 445	10.39 446	6.97 448	7.03 450	36.44 447	25.43 446	17.39 445	3.89 445

testmvs		13.36 414	16.33 417	4.48 430	5.04 452	2.26 455	93.18 389	3.28 453	2.70 446	8.24 447	21.66 444	2.29 453	2.19 448	7.58 447	2.96 446	9.00 444

test123		13.04 415	15.66 418	5.18 429	4.51 453	3.45 454	92.50 403	1.81 454	2.50 447	7.58 448	20.15 445	3.67 452	2.18 449	7.13 448	1.07 447	9.90 443

mmdepth		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

monomultidepth		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

test_blank		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

uanet_test		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

DCPMVS		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

pcd_1.5k_mvsjas		7.39 417	9.85 420	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	88.65 103	0.00 450	0.00 449	0.00 448	0.00 446

sosnet-low-res		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

sosnet		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

uncertanet		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

Regformer		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

n2								0.00 455

nn								0.00 455

ab-mvs-re		8.06 416	10.74 419	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	96.69 187	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

uanet		0.00 418	0.00 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.00 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

WAC-MVS						79.53 402								75.56 401

PC_three_1452									90.77 205	98.89 22	98.28 77	96.24 1	98.35 248	95.76 96	99.58 23	99.59 26

eth-test2					0.00 454

eth-test					0.00 454

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 78	96.04 2	99.24 138	95.36 110	99.59 19	99.56 33

test_0728_THIRD									94.78 54	98.73 26	98.87 26	95.87 4	99.84 23	97.45 41	99.72 2	99.77 2

GSMVS																98.45 157

test_part2					99.28 25	95.74 8				98.10 39

sam_mvs1												82.76 209				98.45 157

sam_mvs												81.94 229

test_post1							92.81 399				16.58 447	80.53 253	97.68 331	86.20 304

test_post											17.58 446	81.76 232	98.08 275

patchmatchnet-post											90.45 402	82.65 214	98.10 270

gm-plane-assit					93.22 380	78.89 410			84.82 365		93.52 355		98.64 221	87.72 272

test9_res														94.81 125	99.38 59	99.45 52

agg_prior2														93.94 144	99.38 59	99.50 45

test_prior4						93.66 58	96.42 250

test_prior2							96.35 259		92.80 141	96.03 114	97.59 134	92.01 47		95.01 118	99.38 59

旧先验2							95.94 286		81.66 396	97.34 61			98.82 198	92.26 174

新几何2							95.79 295

原ACMM2							95.67 300

testdata2													99.67 68	85.96 312

segment_acmp												92.89 30

testdata1							95.26 326		93.10 126

plane_prior7					96.21 241	89.98 195

plane_prior6					96.10 252	90.00 191						81.32 239

plane_prior4											96.64 190

plane_prior3						90.00 191			94.46 71	91.34 237

plane_prior2							97.74 102		94.85 46

plane_prior1					96.14 249

plane_prior						89.99 193	97.24 174		94.06 83						92.16 271

HQP5-MVS						89.33 222

HQP-NCC					95.86 260		96.65 233		93.55 100	90.14 261

ACMP_Plane					95.86 260		96.65 233		93.55 100	90.14 261

BP-MVS														92.13 180

HQP4-MVS										90.14 261			98.50 233			95.78 288

HQP2-MVS												80.95 243

NP-MVS					95.99 258	89.81 201					95.87 232

MDTV_nov1_ep13_2view						70.35 427	93.10 394		83.88 376	93.55 180		82.47 218		86.25 303		98.38 165

ACMMP++_ref															90.30 301

ACMMP++															91.02 290

Test By Simon												88.73 102

High-resolution multi-view benchmark