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 92	98.41 77	91.73 118	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	98.08 185

PGM-MVS		96.81 50	96.53 61	97.65 43	99.35 20	93.53 61	97.65 117	98.98 2	92.22 148	97.14 67	98.44 55	91.17 67	99.85 18	94.35 133	99.46 41	99.57 30

MVS_111021_HR		96.68 61	96.58 60	96.99 77	98.46 73	92.31 100	96.20 264	98.90 3	94.30 76	95.86 120	97.74 118	92.33 42	99.38 125	96.04 83	99.42 51	99.28 70

test_fmvsmconf_n		97.49 16	97.56 10	97.29 59	97.44 154	92.37 97	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 88	98.25 35	98.81 5	92.99 125	94.56 151	98.39 59	88.96 96	99.85 18	94.57 131	97.63 150	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	96.39 109	98.23 95	91.35 139	96.24 262	98.79 6	93.99 83	95.80 122	97.65 125	89.92 86	99.24 137	95.87 87	99.20 79	98.58 140

patch_mono-2		96.83 49	97.44 18	95.01 190	99.05 39	85.39 317	96.98 195	98.77 7	94.70 56	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	96.04 133	98.07 110	90.28 182	97.97 69	98.76 8	94.93 40	98.84 24	99.06 10	88.80 100	99.65 70	99.06 14	98.63 113	98.18 173

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 56	98.21 96	92.75 84	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	96.20 125	97.64 140	90.72 168	98.00 61	98.73 9	94.55 63	98.91 20	99.08 6	88.22 111	99.63 79	98.91 17	98.37 126	98.25 168

FC-MVSNet-test		93.94 148	93.57 141	95.04 188	95.48 272	91.45 136	98.12 50	98.71 11	93.37 108	90.23 254	96.70 179	87.66 121	97.85 306	91.49 191	90.39 294	95.83 277

UniMVSNet (Re)		93.31 169	92.55 181	95.61 161	95.39 277	93.34 67	97.39 155	98.71 11	93.14 121	90.10 263	94.83 279	87.71 120	98.03 280	91.67 189	83.99 365	95.46 296

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 63	98.25 90	92.59 90	97.81 93	98.68 13	94.93 40	99.24 6	98.87 26	93.52 20	99.79 38	99.32 4	99.21 76	99.40 59

FIs		94.09 142	93.70 137	95.27 178	95.70 262	92.03 111	98.10 51	98.68 13	93.36 110	90.39 251	96.70 179	87.63 124	97.94 297	92.25 171	90.50 293	95.84 276

WR-MVS_H		92.00 224	91.35 221	93.95 251	95.09 304	89.47 209	98.04 58	98.68 13	91.46 173	88.34 313	94.68 286	85.86 154	97.56 334	85.77 307	84.24 363	94.82 340

fmvsm_s_conf0.5_n_4		96.75 54	97.07 26	95.79 148	97.76 131	89.57 203	97.66 116	98.66 16	95.36 24	99.03 12	98.90 21	88.39 107	99.73 52	99.17 9	98.66 111	98.08 185

VPA-MVSNet		93.24 171	92.48 186	95.51 167	95.70 262	92.39 96	97.86 82	98.66 16	92.30 146	92.09 212	95.37 255	80.49 249	98.40 234	93.95 139	85.86 336	95.75 285

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 93	97.98 116	91.19 147	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	98.59 139

fmvsm_s_conf0.5_n_8		97.32 22	97.48 17	96.85 79	98.28 86	91.07 155	97.76 97	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	96.02 135	97.98 116	90.43 178	97.50 138	98.59 21	96.59 6	99.31 2	99.08 6	84.47 171	99.75 49	99.37 3	98.45 123	97.88 197

UniMVSNet_NR-MVSNet		93.37 167	92.67 176	95.47 172	95.34 283	92.83 82	97.17 179	98.58 22	92.98 130	90.13 259	95.80 231	88.37 109	97.85 306	91.71 186	83.93 366	95.73 287

CSCG		96.05 81	95.91 81	96.46 103	99.24 28	90.47 175	98.30 28	98.57 23	89.01 258	93.97 167	97.57 133	92.62 37	99.76 45	94.66 126	99.27 69	99.15 80

fmvsm_s_conf0.5_n_6		97.08 31	97.17 22	96.81 80	97.28 159	91.73 118	97.75 99	98.50 24	94.86 44	99.22 7	98.78 35	89.75 89	99.76 45	99.10 13	99.29 67	98.94 103

MSLP-MVS++		96.94 40	97.06 27	96.59 89	98.72 58	91.86 116	97.67 113	98.49 25	94.66 59	97.24 63	98.41 58	92.31 44	98.94 181	96.61 60	99.46 41	98.96 100

HyFIR lowres test		93.66 158	92.92 164	95.87 143	98.24 91	89.88 195	94.58 334	98.49 25	85.06 354	93.78 170	95.78 235	82.86 205	98.67 212	91.77 184	95.71 197	99.07 91

CHOSEN 1792x2688		94.15 137	93.51 147	96.06 131	98.27 87	89.38 214	95.18 320	98.48 27	85.60 344	93.76 171	97.11 159	83.15 196	99.61 81	91.33 194	98.72 109	99.19 76

fmvsm_s_conf0.5_n_7		96.45 69	96.80 49	95.37 175	97.29 158	88.38 246	97.23 173	98.47 28	95.14 32	98.43 33	99.09 5	87.58 125	99.72 56	98.80 21	99.21 76	98.02 189

fmvsm_s_conf0.5_n_5		97.00 37	96.97 35	97.09 72	97.58 150	92.56 91	97.68 112	98.47 28	94.02 81	98.90 21	98.89 23	88.94 97	99.78 41	99.18 8	99.03 97	98.93 107

PHI-MVS		96.77 52	96.46 68	97.71 41	98.40 78	94.07 48	98.21 42	98.45 30	89.86 230	97.11 69	98.01 95	92.52 39	99.69 64	96.03 84	99.53 29	99.36 65

fmvsm_s_conf0.1_n		96.58 65	96.77 52	96.01 138	96.67 203	90.25 183	97.91 77	98.38 31	94.48 67	98.84 24	99.14 1	88.06 113	99.62 80	98.82 19	98.60 115	98.15 177

PVSNet_BlendedMVS		94.06 143	93.92 133	94.47 221	98.27 87	89.46 211	96.73 215	98.36 32	90.17 222	94.36 156	95.24 263	88.02 114	99.58 89	93.44 150	90.72 289	94.36 360

PVSNet_Blended		94.87 119	94.56 117	95.81 147	98.27 87	89.46 211	95.47 303	98.36 32	88.84 266	94.36 156	96.09 220	88.02 114	99.58 89	93.44 150	98.18 134	98.40 160

3Dnovator	91.36 5	95.19 109	94.44 125	97.44 53	96.56 212	93.36 66	98.65 11	98.36 32	94.12 78	89.25 292	98.06 89	82.20 221	99.77 44	93.41 152	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	97.21 176	98.35 35	95.16 31	98.71 28	98.80 33	95.05 10	99.89 3	96.70 58	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	96.16 127	95.48 272	90.69 169	97.91 77	98.33 37	94.07 79	98.93 16	99.14 1	87.44 132	99.61 81	98.63 22	98.32 128	98.18 173

HFP-MVS		97.14 29	96.92 39	97.83 26	99.42 7	94.12 46	98.52 15	98.32 38	93.21 113	97.18 64	98.29 75	92.08 46	99.83 26	95.63 100	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	93.21 113	97.15 66	98.33 69	91.35 61	99.86 9	95.63 100	99.59 19	99.62 21

test_fmvsmvis_n_1920		96.70 57	96.84 43	96.31 114	96.62 205	91.73 118	97.98 63	98.30 40	96.19 10	96.10 111	98.95 17	89.42 90	99.76 45	98.90 18	99.08 92	97.43 224

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 54	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 42	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	97.81 113	93.90 15	99.65 70	96.62 59	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 52	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	92.99 125	96.45 98	98.30 74	91.90 49	99.85 18	95.61 102	99.68 4	99.54 38

test_fmvsmconf0.1_n		97.09 30	97.06 27	97.19 68	95.67 264	92.21 104	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	92.37 145	98.27 36	98.65 40	93.33 23	99.72 56	96.49 64	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 62	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	94.91 108	96.38 110	98.20 97	90.86 162	97.27 167	98.25 53	90.21 221	94.18 161	97.27 150	87.48 131	99.73 52	93.53 147	97.77 148	98.55 141

region2R		97.07 33	96.84 43	97.77 34	99.46 2	93.79 55	98.52 15	98.24 55	93.19 116	97.14 67	98.34 66	91.59 56	99.87 7	95.46 106	99.59 19	99.64 19

PS-CasMVS		91.55 244	90.84 245	93.69 267	94.96 308	88.28 249	97.84 86	98.24 55	91.46 173	88.04 323	95.80 231	79.67 265	97.48 342	87.02 287	84.54 360	95.31 309

DU-MVS		92.90 189	92.04 197	95.49 169	94.95 309	92.83 82	97.16 180	98.24 55	93.02 124	90.13 259	95.71 238	83.47 188	97.85 306	91.71 186	83.93 366	95.78 281

9.14			96.75 53		98.93 50		97.73 103	98.23 58	91.28 182	97.88 46	98.44 55	93.00 26	99.65 70	95.76 93	99.47 40

reproduce_model		97.51 15	97.51 14	97.50 50	98.99 46	93.01 78	97.79 95	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		91.30 261	90.95 239	92.35 313	94.71 324	85.52 313	96.18 265	98.21 59	88.89 264	86.60 352	93.82 334	79.92 261	97.95 296	89.29 236	90.95 286	93.56 373

reproduce-ours		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 108	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	97.71 108	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		94.17 135	93.61 140	95.86 145	98.09 106	91.37 138	97.35 159	98.20 61	93.18 118	91.79 220	97.28 148	79.13 273	98.93 182	94.61 129	92.84 252	97.28 232

XVS		97.18 26	96.96 37	97.81 28	99.38 14	94.03 50	98.59 12	98.20 61	94.85 45	96.59 90	98.29 75	91.70 52	99.80 35	95.66 95	99.40 56	99.62 21

X-MVStestdata		91.71 233	89.67 298	97.81 28	99.38 14	94.03 50	98.59 12	98.20 61	94.85 45	96.59 90	32.69 433	91.70 52	99.80 35	95.66 95	99.40 56	99.62 21

ACMMP_NAP		97.20 25	96.86 41	98.23 11	99.09 34	95.16 22	97.60 126	98.19 66	92.82 136	97.93 45	98.74 37	91.60 55	99.86 9	96.26 67	99.52 30	99.67 13

CP-MVSNet		91.89 229	91.24 228	93.82 259	95.05 305	88.57 239	97.82 91	98.19 66	91.70 166	88.21 319	95.76 236	81.96 225	97.52 340	87.86 262	84.65 354	95.37 305

ZNCC-MVS		96.96 38	96.67 56	97.85 25	99.37 16	94.12 46	98.49 19	98.18 68	92.64 141	96.39 100	98.18 82	91.61 54	99.88 4	95.59 105	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	90.57 213	98.85 23	98.94 18	93.33 23	99.83 26	96.72 57	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		91.20 266	90.44 262	93.48 276	94.49 332	87.91 263	97.76 97	98.18 68	91.29 179	87.78 327	95.74 237	80.35 252	97.33 353	85.46 311	82.96 376	95.19 320

DELS-MVS		96.61 63	96.38 72	97.30 58	97.79 129	93.19 74	95.96 275	98.18 68	95.23 28	95.87 119	97.65 125	91.45 57	99.70 63	95.87 87	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		89.70 317	88.40 323	93.60 270	95.15 300	90.10 185	97.56 130	98.16 72	87.28 317	86.16 356	94.63 290	77.57 301	98.05 276	74.48 394	84.59 358	92.65 386

VNet		95.89 88	95.45 91	97.21 66	98.07 110	92.94 81	97.50 138	98.15 73	93.87 87	97.52 53	97.61 131	85.29 160	99.53 103	95.81 92	95.27 206	99.16 78

DeepPCF-MVS	93.97 1	96.61 63	97.09 25	95.15 182	98.09 106	86.63 293	96.00 273	98.15 73	95.43 22	97.95 44	98.56 42	93.40 21	99.36 126	96.77 54	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 49	99.01 13	98.55 44	94.18 14	97.41 349	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	92.72 138	96.70 82	98.06 89	91.35 61	99.86 9	94.83 120	99.28 68	99.47 51

UA-Net		95.95 86	95.53 87	97.20 67	97.67 136	92.98 80	97.65 117	98.13 76	94.81 50	96.61 88	98.35 63	88.87 98	99.51 108	90.36 211	97.35 160	99.11 86

QAPM		93.45 165	92.27 191	96.98 78	96.77 198	92.62 88	98.39 24	98.12 78	84.50 362	88.27 317	97.77 116	82.39 218	99.81 30	85.40 312	98.81 105	98.51 146

Vis-MVSNet		95.23 106	94.81 109	96.51 97	97.18 164	91.58 129	98.26 34	98.12 78	94.38 74	94.90 143	98.15 84	82.28 219	98.92 183	91.45 193	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	92.86 191	91.68 211	96.40 107	95.34 283	92.73 86	98.27 32	98.12 78	84.86 357	85.78 358	97.75 117	78.89 283	99.74 50	87.50 277	98.65 112	96.73 248

TranMVSNet+NR-MVSNet		92.50 200	91.63 212	95.14 183	94.76 320	92.07 109	97.53 135	98.11 81	92.90 134	89.56 280	96.12 215	83.16 195	97.60 332	89.30 235	83.20 375	95.75 285

CPTT-MVS		95.57 98	95.19 101	96.70 82	99.27 26	91.48 133	98.33 26	98.11 81	87.79 302	95.17 139	98.03 92	87.09 138	99.61 81	93.51 148	99.42 51	99.02 92

APD-MVS		96.95 39	96.60 58	98.01 20	99.03 41	94.93 27	97.72 106	98.10 83	91.50 171	98.01 41	98.32 71	92.33 42	99.58 89	94.85 118	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	93.27 112	95.95 118	98.33 69	91.04 69	99.88 4	95.20 109	99.57 25	99.60 25

ZD-MVS					99.05 39	94.59 32		98.08 85	89.22 251	97.03 72	98.10 85	92.52 39	99.65 70	94.58 130	99.31 66

MTGPA								98.08 85

MTAPA		97.08 31	96.78 51	97.97 23	99.37 16	94.42 36	97.24 169	98.08 85	95.07 37	96.11 110	98.59 41	90.88 74	99.90 2	96.18 79	99.50 35	99.58 29

CNVR-MVS		97.68 6	97.44 18	98.37 7	98.90 53	95.86 6	97.27 167	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	97.03 187	98.08 85	88.35 284	95.09 141	97.65 125	89.97 85	99.48 113	92.08 178	98.59 116	98.44 157

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 90	97.45 55	98.48 52	91.43 59	99.59 86	96.22 70	99.27 69	99.54 38

MCST-MVS		97.18 26	96.84 43	98.20 14	99.30 24	95.35 15	97.12 183	98.07 90	93.54 100	96.08 112	97.69 120	93.86 16	99.71 58	96.50 63	99.39 58	99.55 36

NR-MVSNet		92.34 208	91.27 227	95.53 166	94.95 309	93.05 77	97.39 155	98.07 90	92.65 140	84.46 369	95.71 238	85.00 164	97.77 317	89.71 223	83.52 372	95.78 281

MP-MVS-pluss		96.70 57	96.27 75	97.98 22	99.23 30	94.71 29	96.96 197	98.06 93	90.67 204	95.55 131	98.78 35	91.07 68	99.86 9	96.58 61	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	92.31 100	97.98 63	98.06 93	93.11 122	97.44 56	98.55 44	90.93 72	99.55 99	96.06 80	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	93.37 108	95.54 133	98.34 66	90.59 78	99.88 4	94.83 120	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 85	98.74 9	98.06 93	90.57 213	96.77 79	98.35 63	90.21 81	99.53 103	94.80 123	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	91.17 187	96.40 99	97.99 96	90.99 70	99.58 89	95.61 102	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		94.51 127	93.80 135	96.64 84	97.07 170	91.97 113	96.32 254	98.06 93	88.94 262	94.50 153	96.78 174	84.60 168	99.27 135	91.90 179	96.02 188	98.68 133

DeepC-MVS	93.07 3	96.06 80	95.66 85	97.29 59	97.96 118	93.17 75	97.30 165	98.06 93	93.92 85	93.38 180	98.66 38	86.83 140	99.73 52	95.60 104	99.22 75	98.96 100
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	97.34 160	98.04 100	95.96 11	97.09 70	97.88 104	93.18 25	99.71 58	95.84 91	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	97.41 150	98.04 100	94.81 50	96.59 90	98.37 61	91.24 64	99.64 78	95.16 111	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 98	97.98 63	98.03 102	93.52 103	97.43 58	98.51 47	91.40 60	99.56 97	96.05 81	99.26 71	99.43 56

RE-MVS-def			96.72 54		99.02 42	92.34 98	97.98 63	98.03 102	93.52 103	97.43 58	98.51 47	90.71 76		96.05 81	99.26 71	99.43 56

RPMNet		88.98 323	87.05 337	94.77 208	94.45 334	87.19 278	90.23 408	98.03 102	77.87 409	92.40 198	87.55 413	80.17 256	99.51 108	68.84 413	93.95 239	97.60 217

save fliter					98.91 52	94.28 38	97.02 189	98.02 105	95.35 25

TEST9					98.70 59	94.19 42	96.41 243	98.02 105	88.17 288	96.03 113	97.56 135	92.74 33	99.59 86

train_agg		96.30 76	95.83 84	97.72 39	98.70 59	94.19 42	96.41 243	98.02 105	88.58 275	96.03 113	97.56 135	92.73 34	99.59 86	95.04 113	99.37 62	99.39 61

test_8					98.67 61	94.06 49	96.37 250	98.01 108	88.58 275	95.98 117	97.55 137	92.73 34	99.58 89

agg_prior					98.67 61	93.79 55		98.00 109		95.68 127			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		92.34 208	91.53 216	94.77 208	95.13 302	90.83 163	96.40 247	97.98 111	91.88 161	89.29 289	95.54 249	82.50 214	97.80 313	89.79 222	85.27 345	95.69 288

HPM-MVS++		97.34 21	96.97 35	98.47 5	99.08 36	96.16 4	97.55 134	97.97 112	95.59 19	96.61 88	97.89 102	92.57 38	99.84 23	95.95 86	99.51 33	99.40 59

CANet		96.39 72	96.02 79	97.50 50	97.62 143	93.38 64	97.02 189	97.96 113	95.42 23	94.86 144	97.81 113	87.38 134	99.82 28	96.88 52	99.20 79	99.29 68

114514_t		93.95 147	93.06 160	96.63 86	99.07 37	91.61 126	97.46 147	97.96 113	77.99 407	93.00 189	97.57 133	86.14 152	99.33 127	89.22 239	99.15 86	98.94 103

IU-MVS					99.42 7	95.39 11		97.94 115	90.40 219	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	96.00 139	97.30 157	90.37 181	97.53 135	97.92 118	96.52 7	99.14 11	99.08 6	83.21 193	99.74 50	99.22 7	98.06 139	97.88 197

Anonymous20231211		90.63 290	89.42 305	94.27 235	98.24 91	89.19 226	98.05 57	97.89 119	79.95 399	88.25 318	94.96 271	72.56 339	98.13 259	89.70 224	85.14 347	95.49 292

原ACMM1				96.38 110	98.59 69	91.09 154		97.89 119	87.41 313	95.22 138	97.68 121	90.25 80	99.54 101	87.95 261	99.12 90	98.49 149

CDPH-MVS		95.97 85	95.38 96	97.77 34	98.93 50	94.44 35	96.35 251	97.88 121	86.98 321	96.65 86	97.89 102	91.99 48	99.47 114	92.26 169	99.46 41	99.39 61

test11								97.88 121

EIA-MVS		95.53 99	95.47 90	95.71 156	97.06 173	89.63 199	97.82 91	97.87 123	93.57 96	93.92 168	95.04 269	90.61 77	98.95 179	94.62 128	98.68 110	98.54 142

CS-MVS		96.86 44	97.06 27	96.26 120	98.16 102	91.16 152	99.09 3	97.87 123	95.30 27	97.06 71	98.03 92	91.72 50	98.71 209	97.10 47	99.17 82	98.90 112

无先验							95.79 285	97.87 123	83.87 370				99.65 70	87.68 271		98.89 116

3Dnovator+	91.43 4	95.40 100	94.48 123	98.16 16	96.90 184	95.34 16	98.48 20	97.87 123	94.65 60	88.53 309	98.02 94	83.69 184	99.71 58	93.18 156	98.96 100	99.44 54

VPNet		92.23 216	91.31 224	94.99 191	95.56 268	90.96 158	97.22 175	97.86 127	92.96 131	90.96 242	96.62 191	75.06 321	98.20 253	91.90 179	83.65 371	95.80 279

test_vis1_n_1920		94.17 135	94.58 116	92.91 297	97.42 155	82.02 364	97.83 89	97.85 128	94.68 57	98.10 39	98.49 49	70.15 358	99.32 129	97.91 26	98.82 104	97.40 226

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 42	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 91	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	96.45 104	98.29 85	91.66 125	99.03 4	97.85 128	95.84 12	96.90 74	97.97 98	91.24 64	98.75 202	96.92 51	99.33 64	98.94 103

test_fmvsmconf0.01_n		96.15 79	95.85 83	97.03 76	92.66 382	91.83 117	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	96.79 195	93.26 72	97.89 80	97.83 133	93.58 95	96.80 76	97.82 112	83.06 200	99.16 149	94.40 132	97.95 143	98.87 118

balanced_conf03		96.84 48	96.89 40	96.68 83	97.63 142	92.22 103	98.17 48	97.82 134	94.44 69	98.23 37	97.36 145	90.97 71	99.22 139	97.74 28	99.66 10	98.61 136

AdaColmap		94.34 131	93.68 138	96.31 114	98.59 69	91.68 124	96.59 234	97.81 135	89.87 229	92.15 208	97.06 162	83.62 187	99.54 101	89.34 234	98.07 138	97.70 210

MVSMamba_PlusPlus		96.51 66	96.48 64	96.59 89	98.07 110	91.97 113	98.14 49	97.79 136	90.43 217	97.34 61	97.52 138	91.29 63	99.19 142	98.12 24	99.64 14	98.60 137

mamv4		94.66 125	96.10 78	90.37 364	98.01 113	73.41 413	96.82 208	97.78 137	89.95 228	94.52 152	97.43 142	92.91 27	99.09 162	98.28 23	99.16 85	98.60 137

ETV-MVS		96.02 82	95.89 82	96.40 107	97.16 165	92.44 95	97.47 145	97.77 138	94.55 63	96.48 95	94.51 296	91.23 66	98.92 183	95.65 98	98.19 133	97.82 205

新几何1				97.32 57	98.60 68	93.59 59		97.75 139	81.58 390	95.75 124	97.85 108	90.04 83	99.67 68	86.50 293	99.13 88	98.69 132

旧先验1					98.38 81	93.38 64		97.75 139			98.09 87	92.30 45			99.01 98	99.16 78

EC-MVSNet		96.42 70	96.47 65	96.26 120	97.01 179	91.52 131	98.89 5	97.75 139	94.42 70	96.64 87	97.68 121	89.32 91	98.60 219	97.45 41	99.11 91	98.67 134

EI-MVSNet-Vis-set		96.51 66	96.47 65	96.63 86	98.24 91	91.20 146	96.89 201	97.73 142	94.74 55	96.49 94	98.49 49	90.88 74	99.58 89	96.44 65	98.32 128	99.13 82

PAPM_NR		95.01 111	94.59 115	96.26 120	98.89 54	90.68 170	97.24 169	97.73 142	91.80 162	92.93 194	96.62 191	89.13 94	99.14 154	89.21 240	97.78 147	98.97 99

Anonymous20240529		91.98 225	90.73 252	95.73 154	98.14 103	89.40 213	97.99 62	97.72 144	79.63 401	93.54 175	97.41 143	69.94 360	99.56 97	91.04 201	91.11 282	98.22 170

CHOSEN 280x420		93.12 177	92.72 175	94.34 229	96.71 202	87.27 274	90.29 407	97.72 144	86.61 328	91.34 231	95.29 257	84.29 176	98.41 233	93.25 154	98.94 101	97.35 229

EI-MVSNet-UG-set		96.34 74	96.30 74	96.47 101	98.20 97	90.93 160	96.86 203	97.72 144	94.67 58	96.16 109	98.46 53	90.43 79	99.58 89	96.23 69	97.96 142	98.90 112

LS3D		93.57 161	92.61 179	96.47 101	97.59 146	91.61 126	97.67 113	97.72 144	85.17 352	90.29 253	98.34 66	84.60 168	99.73 52	83.85 334	98.27 130	98.06 187

PAPR		94.18 134	93.42 153	96.48 100	97.64 140	91.42 137	95.55 298	97.71 148	88.99 259	92.34 204	95.82 230	89.19 92	99.11 157	86.14 299	97.38 158	98.90 112

UGNet		94.04 145	93.28 156	96.31 114	96.85 187	91.19 147	97.88 81	97.68 149	94.40 72	93.00 189	96.18 210	73.39 336	99.61 81	91.72 185	98.46 122	98.13 178
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				95.46 173	98.18 101	88.90 232		97.66 150	82.73 381	97.03 72	98.07 88	90.06 82	98.85 190	89.67 225	98.98 99	98.64 135

test12				97.65 43	98.46 73	94.26 39		97.66 150		95.52 134		90.89 73	99.46 115		99.25 73	99.22 75

DTE-MVSNet		90.56 291	89.75 296	93.01 293	93.95 347	87.25 275	97.64 121	97.65 152	90.74 199	87.12 340	95.68 241	79.97 260	97.00 365	83.33 335	81.66 382	94.78 347

TAPA-MVS	90.10 7	92.30 211	91.22 230	95.56 163	98.33 83	89.60 201	96.79 210	97.65 152	81.83 387	91.52 226	97.23 153	87.94 116	98.91 185	71.31 408	98.37 126	98.17 176
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 178	92.45 187	95.05 187	98.09 106	89.21 223	96.89 201	97.64 154	93.18 118	91.79 220	97.28 148	75.35 320	98.65 214	88.99 245	92.84 252	97.28 232

test_cas_vis1_n_1920		94.48 129	94.55 120	94.28 234	96.78 196	86.45 298	97.63 123	97.64 154	93.32 111	97.68 51	98.36 62	73.75 334	99.08 165	96.73 56	99.05 94	97.31 231

cdsmvs_eth3d_5k		23.24 403	30.99 405	0.00 421	0.00 444	0.00 446	0.00 432	97.63 156	0.00 439	0.00 440	96.88 171	84.38 173	0.00 440	0.00 439	0.00 438	0.00 436

DPM-MVS		95.69 92	94.92 107	98.01 20	98.08 109	95.71 9	95.27 314	97.62 157	90.43 217	95.55 131	97.07 161	91.72 50	99.50 111	89.62 227	98.94 101	98.82 124

sasdasda		96.02 82	95.45 91	97.75 36	97.59 146	95.15 23	98.28 30	97.60 158	94.52 65	96.27 104	96.12 215	87.65 122	99.18 145	96.20 75	94.82 215	98.91 109

canonicalmvs		96.02 82	95.45 91	97.75 36	97.59 146	95.15 23	98.28 30	97.60 158	94.52 65	96.27 104	96.12 215	87.65 122	99.18 145	96.20 75	94.82 215	98.91 109

test222					98.24 91	92.21 104	95.33 309	97.60 158	79.22 403	95.25 136	97.84 110	88.80 100			99.15 86	98.72 129

cascas		91.20 266	90.08 279	94.58 217	94.97 307	89.16 227	93.65 372	97.59 161	79.90 400	89.40 284	92.92 360	75.36 319	98.36 241	92.14 174	94.75 218	96.23 258

h-mvs33		94.15 137	93.52 146	96.04 133	97.81 128	90.22 184	97.62 125	97.58 162	95.19 29	96.74 80	97.45 139	83.67 185	99.61 81	95.85 89	79.73 389	98.29 167

MGCFI-Net		95.94 87	95.40 95	97.56 49	97.59 146	94.62 31	98.21 42	97.57 163	94.41 71	96.17 108	96.16 213	87.54 127	99.17 147	96.19 77	94.73 220	98.91 109

MVSFormer		95.37 101	95.16 102	95.99 140	96.34 233	91.21 144	98.22 40	97.57 163	91.42 175	96.22 106	97.32 146	86.20 150	97.92 300	94.07 136	99.05 94	98.85 120

test_djsdf		93.07 180	92.76 170	94.00 246	93.49 363	88.70 236	98.22 40	97.57 163	91.42 175	90.08 265	95.55 248	82.85 206	97.92 300	94.07 136	91.58 273	95.40 302

OMC-MVS		95.09 110	94.70 113	96.25 123	98.46 73	91.28 140	96.43 241	97.57 163	92.04 157	94.77 147	97.96 99	87.01 139	99.09 162	91.31 195	96.77 175	98.36 164

PS-MVSNAJss		93.74 156	93.51 147	94.44 223	93.91 349	89.28 221	97.75 99	97.56 167	92.50 142	89.94 267	96.54 194	88.65 103	98.18 256	93.83 145	90.90 287	95.86 273

casdiffmvs_mvg		95.81 91	95.57 86	96.51 97	96.87 185	91.49 132	97.50 138	97.56 167	93.99 83	95.13 140	97.92 101	87.89 117	98.78 197	95.97 85	97.33 161	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		92.42 204	91.89 204	94.03 245	93.33 369	88.50 243	97.73 103	97.53 169	92.00 159	88.85 301	96.50 196	75.62 318	98.11 263	93.88 143	91.56 274	95.48 293

mvs_tets		92.31 210	91.76 207	93.94 253	93.41 366	88.29 248	97.63 123	97.53 169	92.04 157	88.76 304	96.45 198	74.62 326	98.09 268	93.91 141	91.48 275	95.45 297

dcpmvs_2		96.37 73	97.05 30	94.31 232	98.96 49	84.11 338	97.56 130	97.51 171	93.92 85	97.43 58	98.52 46	92.75 32	99.32 129	97.32 46	99.50 35	99.51 42

HQP_MVS		93.78 155	93.43 151	94.82 201	96.21 237	89.99 189	97.74 101	97.51 171	94.85 45	91.34 231	96.64 184	81.32 235	98.60 219	93.02 162	92.23 261	95.86 273

plane_prior5								97.51 171					98.60 219	93.02 162	92.23 261	95.86 273

reproduce_monomvs		91.30 261	91.10 234	91.92 325	96.82 192	82.48 358	97.01 192	97.49 174	94.64 61	88.35 312	95.27 260	70.53 353	98.10 264	95.20 109	84.60 357	95.19 320

PS-MVSNAJ		95.37 101	95.33 98	95.49 169	97.35 156	90.66 171	95.31 311	97.48 175	93.85 88	96.51 93	95.70 240	88.65 103	99.65 70	94.80 123	98.27 130	96.17 262

API-MVS		94.84 120	94.49 122	95.90 142	97.90 124	92.00 112	97.80 94	97.48 175	89.19 252	94.81 145	96.71 177	88.84 99	99.17 147	88.91 247	98.76 108	96.53 251

MG-MVS		95.61 96	95.38 96	96.31 114	98.42 76	90.53 173	96.04 270	97.48 175	93.47 105	95.67 128	98.10 85	89.17 93	99.25 136	91.27 196	98.77 107	99.13 82

MAR-MVS		94.22 133	93.46 149	96.51 97	98.00 115	92.19 107	97.67 113	97.47 178	88.13 292	93.00 189	95.84 228	84.86 166	99.51 108	87.99 260	98.17 135	97.83 204
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		92.98 184	92.53 183	94.32 230	96.12 247	89.20 224	95.28 312	97.47 178	92.66 139	89.90 268	95.62 244	80.58 247	98.40 234	92.73 167	92.40 259	95.38 304
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 259	90.22 275	94.68 211	94.86 316	87.86 264	97.23 173	97.46 180	87.99 293	89.90 268	96.92 169	66.35 388	98.23 250	90.30 212	90.99 285	97.96 192

nrg030		94.05 144	93.31 155	96.27 119	95.22 294	94.59 32	98.34 25	97.46 180	92.93 132	91.21 240	96.64 184	87.23 137	98.22 251	94.99 116	85.80 337	95.98 272

XVG-OURS		93.72 157	93.35 154	94.80 206	97.07 170	88.61 237	94.79 329	97.46 180	91.97 160	93.99 165	97.86 107	81.74 230	98.88 187	92.64 168	92.67 257	96.92 243

LPG-MVS_test		92.94 187	92.56 180	94.10 240	96.16 242	88.26 250	97.65 117	97.46 180	91.29 179	90.12 261	97.16 156	79.05 276	98.73 205	92.25 171	91.89 269	95.31 309

LGP-MVS_train				94.10 240	96.16 242	88.26 250		97.46 180	91.29 179	90.12 261	97.16 156	79.05 276	98.73 205	92.25 171	91.89 269	95.31 309

MVS		91.71 233	90.44 262	95.51 167	95.20 296	91.59 128	96.04 270	97.45 185	73.44 417	87.36 336	95.60 245	85.42 159	99.10 159	85.97 304	97.46 153	95.83 277

XVG-OURS-SEG-HR		93.86 152	93.55 142	94.81 203	97.06 173	88.53 242	95.28 312	97.45 185	91.68 167	94.08 164	97.68 121	82.41 217	98.90 186	93.84 144	92.47 258	96.98 239

baseline		95.58 97	95.42 94	96.08 129	96.78 196	90.41 179	97.16 180	97.45 185	93.69 94	95.65 129	97.85 108	87.29 135	98.68 211	95.66 95	97.25 166	99.13 82

ab-mvs		93.57 161	92.55 181	96.64 84	97.28 159	91.96 115	95.40 305	97.45 185	89.81 234	93.22 186	96.28 206	79.62 267	99.46 115	90.74 205	93.11 249	98.50 147

xiu_mvs_v2_base		95.32 103	95.29 99	95.40 174	97.22 161	90.50 174	95.44 304	97.44 189	93.70 93	96.46 97	96.18 210	88.59 106	99.53 103	94.79 125	97.81 146	96.17 262

1314		92.81 195	92.03 198	95.14 183	95.33 286	89.52 208	96.04 270	97.44 189	87.72 306	86.25 355	95.33 256	83.84 182	98.79 196	89.26 237	97.05 171	97.11 237

casdiffmvs		95.64 94	95.49 88	96.08 129	96.76 201	90.45 176	97.29 166	97.44 189	94.00 82	95.46 135	97.98 97	87.52 130	98.73 205	95.64 99	97.33 161	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		92.16 218	91.23 229	94.95 197	94.75 321	90.94 159	97.47 145	97.43 192	89.14 253	88.90 297	96.43 199	79.71 264	98.24 249	89.56 228	87.68 318	95.67 289

anonymousdsp		92.16 218	91.55 215	93.97 249	92.58 384	89.55 205	97.51 137	97.42 193	89.42 246	88.40 311	94.84 278	80.66 246	97.88 305	91.87 181	91.28 279	94.48 355

Effi-MVS+		94.93 116	94.45 124	96.36 112	96.61 206	91.47 134	96.41 243	97.41 194	91.02 193	94.50 153	95.92 224	87.53 128	98.78 197	93.89 142	96.81 174	98.84 123

RRT-MVS		94.51 127	94.35 127	94.98 193	96.40 229	86.55 296	97.56 130	97.41 194	93.19 116	94.93 142	97.04 163	79.12 274	99.30 133	96.19 77	97.32 163	99.09 88

HQP3-MVS								97.39 196							92.10 266

HQP-MVS		93.19 174	92.74 173	94.54 219	95.86 254	89.33 217	96.65 225	97.39 196	93.55 97	90.14 255	95.87 226	80.95 239	98.50 227	92.13 175	92.10 266	95.78 281

PLC	91.00 6	94.11 141	93.43 151	96.13 128	98.58 71	91.15 153	96.69 221	97.39 196	87.29 316	91.37 230	96.71 177	88.39 107	99.52 107	87.33 280	97.13 170	97.73 208
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 283	89.86 289	93.45 278	93.54 360	87.60 270	97.70 111	97.37 199	88.85 265	87.65 329	94.08 325	81.08 238	98.10 264	84.68 321	83.79 370	94.66 352

UnsupCasMVSNet_eth		85.99 358	84.45 363	90.62 360	89.97 402	82.40 361	93.62 373	97.37 199	89.86 230	78.59 404	92.37 370	65.25 396	95.35 395	82.27 348	70.75 412	94.10 366

ACMM	89.79 8	92.96 185	92.50 185	94.35 227	96.30 235	88.71 235	97.58 127	97.36 201	91.40 177	90.53 248	96.65 183	79.77 263	98.75 202	91.24 197	91.64 271	95.59 291
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 111	94.76 110	95.75 151	96.58 209	91.71 121	96.25 259	97.35 202	92.99 125	96.70 82	96.63 188	82.67 209	99.44 118	96.22 70	97.46 153	96.11 268

xiu_mvs_v1_base		95.01 111	94.76 110	95.75 151	96.58 209	91.71 121	96.25 259	97.35 202	92.99 125	96.70 82	96.63 188	82.67 209	99.44 118	96.22 70	97.46 153	96.11 268

xiu_mvs_v1_base_debi		95.01 111	94.76 110	95.75 151	96.58 209	91.71 121	96.25 259	97.35 202	92.99 125	96.70 82	96.63 188	82.67 209	99.44 118	96.22 70	97.46 153	96.11 268

diffmvs		95.25 105	95.13 103	95.63 159	96.43 228	89.34 216	95.99 274	97.35 202	92.83 135	96.31 102	97.37 144	86.44 145	98.67 212	96.26 67	97.19 168	98.87 118
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		94.71 124	94.02 131	96.79 81	97.71 134	92.05 110	96.59 234	97.35 202	90.61 210	94.64 149	96.93 166	86.41 146	99.39 123	91.20 198	94.71 221	98.94 103

F-COLMAP		93.58 160	92.98 162	95.37 175	98.40 78	88.98 230	97.18 178	97.29 207	87.75 305	90.49 249	97.10 160	85.21 161	99.50 111	86.70 290	96.72 178	97.63 212

XVG-ACMP-BASELINE		90.93 279	90.21 276	93.09 291	94.31 340	85.89 308	95.33 309	97.26 208	91.06 192	89.38 285	95.44 254	68.61 371	98.60 219	89.46 230	91.05 283	94.79 345

PCF-MVS	89.48 11	91.56 243	89.95 286	96.36 112	96.60 207	92.52 93	92.51 392	97.26 208	79.41 402	88.90 297	96.56 193	84.04 181	99.55 99	77.01 385	97.30 164	97.01 238
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 199	92.14 194	94.05 243	96.40 229	88.20 253	97.36 158	97.25 210	91.52 170	88.30 315	96.64 184	78.46 288	98.72 208	91.86 182	91.48 275	95.23 316
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 170	92.76 170	94.82 201	94.63 327	90.77 166	96.65 225	97.18 211	93.72 91	91.68 224	97.26 151	79.33 271	98.63 216	92.13 175	92.28 260	95.07 323
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 189	92.02 199	95.56 163	98.19 99	90.80 164	95.27 314	97.18 211	87.96 294	91.86 219	95.68 241	80.44 250	98.99 177	84.01 329	97.54 152	96.89 244

alignmvs		95.87 90	95.23 100	97.78 32	97.56 152	95.19 21	97.86 82	97.17 213	94.39 73	96.47 96	96.40 201	85.89 153	99.20 141	96.21 74	95.11 211	98.95 102

MVS_Test		94.89 118	94.62 114	95.68 157	96.83 190	89.55 205	96.70 219	97.17 213	91.17 187	95.60 130	96.11 219	87.87 119	98.76 201	93.01 164	97.17 169	98.72 129

Fast-Effi-MVS+		93.46 164	92.75 172	95.59 162	96.77 198	90.03 186	96.81 209	97.13 215	88.19 287	91.30 234	94.27 313	86.21 149	98.63 216	87.66 272	96.46 185	98.12 180

EI-MVSNet		93.03 182	92.88 166	93.48 276	95.77 260	86.98 283	96.44 239	97.12 216	90.66 206	91.30 234	97.64 128	86.56 142	98.05 276	89.91 218	90.55 291	95.41 299

MVSTER		93.20 173	92.81 169	94.37 226	96.56 212	89.59 202	97.06 186	97.12 216	91.24 183	91.30 234	95.96 222	82.02 224	98.05 276	93.48 149	90.55 291	95.47 295

test_yl		94.78 122	94.23 128	96.43 105	97.74 132	91.22 142	96.85 204	97.10 218	91.23 184	95.71 125	96.93 166	84.30 174	99.31 131	93.10 157	95.12 209	98.75 126

DCV-MVSNet		94.78 122	94.23 128	96.43 105	97.74 132	91.22 142	96.85 204	97.10 218	91.23 184	95.71 125	96.93 166	84.30 174	99.31 131	93.10 157	95.12 209	98.75 126

LTVRE_ROB	88.41 13	90.99 275	89.92 288	94.19 236	96.18 240	89.55 205	96.31 255	97.09 220	87.88 297	85.67 359	95.91 225	78.79 284	98.57 223	81.50 351	89.98 296	94.44 358
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		92.73 197	92.88 166	92.29 316	96.08 250	81.05 372	97.98 63	97.08 221	90.72 201	96.79 78	98.18 82	63.07 400	98.45 231	97.62 35	98.42 125	97.36 227

v10		91.04 273	90.23 273	93.49 275	94.12 343	88.16 256	97.32 163	97.08 221	88.26 286	88.29 316	94.22 318	82.17 222	97.97 288	86.45 294	84.12 364	94.33 361

v144192		91.06 272	90.28 269	93.39 279	93.66 358	87.23 277	96.83 207	97.07 223	87.43 312	89.69 275	94.28 312	81.48 233	98.00 283	87.18 284	84.92 353	94.93 331

v1192		91.07 271	90.23 273	93.58 272	93.70 355	87.82 266	96.73 215	97.07 223	87.77 303	89.58 278	94.32 310	80.90 243	97.97 288	86.52 292	85.48 340	94.95 327

v8		91.29 263	90.53 261	93.57 273	94.15 342	88.12 257	97.34 160	97.06 225	88.99 259	88.32 314	94.26 315	83.08 198	98.01 282	87.62 274	83.92 368	94.57 354

mvs_anonymous		93.82 153	93.74 136	94.06 242	96.44 227	85.41 315	95.81 283	97.05 226	89.85 232	90.09 264	96.36 203	87.44 132	97.75 319	93.97 138	96.69 179	99.02 92

IterMVS-LS		92.29 212	91.94 202	93.34 281	96.25 236	86.97 284	96.57 237	97.05 226	90.67 204	89.50 283	94.80 281	86.59 141	97.64 327	89.91 218	86.11 335	95.40 302
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 281	90.03 284	93.29 283	93.55 359	86.96 285	96.74 214	97.04 228	87.36 314	89.52 282	94.34 307	80.23 255	97.97 288	86.27 295	85.21 346	94.94 329

CDS-MVSNet		94.14 140	93.54 143	95.93 141	96.18 240	91.46 135	96.33 253	97.04 228	88.97 261	93.56 173	96.51 195	87.55 126	97.89 304	89.80 221	95.95 190	98.44 157
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 316	89.26 309	91.19 349	95.16 297	80.29 383	94.53 336	97.03 230	91.79 163	88.86 300	94.10 322	69.94 360	97.82 310	85.29 313	86.66 331	95.45 297

v1144		91.37 256	90.60 257	93.68 268	93.89 350	88.23 252	96.84 206	97.03 230	88.37 283	89.69 275	94.39 303	82.04 223	97.98 285	87.80 264	85.37 342	94.84 337

v1240		90.70 287	89.85 290	93.23 285	93.51 362	86.80 286	96.61 231	97.02 232	87.16 319	89.58 278	94.31 311	79.55 268	97.98 285	85.52 310	85.44 341	94.90 334

EPP-MVSNet		95.22 107	95.04 106	95.76 149	97.49 153	89.56 204	98.67 10	97.00 233	90.69 202	94.24 159	97.62 130	89.79 88	98.81 194	93.39 153	96.49 183	98.92 108

V42		91.58 242	90.87 241	93.73 263	94.05 346	88.50 243	97.32 163	96.97 234	88.80 271	89.71 273	94.33 308	82.54 213	98.05 276	89.01 244	85.07 349	94.64 353

test_fmvs1		93.21 172	93.53 144	92.25 319	96.55 214	81.20 371	97.40 154	96.96 235	90.68 203	96.80 76	98.04 91	69.25 366	98.40 234	97.58 36	98.50 118	97.16 236

FMVSNet2		91.31 260	90.08 279	94.99 191	96.51 220	92.21 104	97.41 150	96.95 236	88.82 268	88.62 306	94.75 283	73.87 330	97.42 348	85.20 316	88.55 311	95.35 306

ACMH	87.59 16	90.53 292	89.42 305	93.87 257	96.21 237	87.92 261	97.24 169	96.94 237	88.45 281	83.91 379	96.27 207	71.92 342	98.62 218	84.43 324	89.43 302	95.05 325
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 257	90.27 270	94.59 213	96.51 220	91.18 149	97.50 138	96.93 238	88.82 268	89.35 286	94.51 296	73.87 330	97.29 355	86.12 300	88.82 306	95.31 309

test1		91.35 257	90.27 270	94.59 213	96.51 220	91.18 149	97.50 138	96.93 238	88.82 268	89.35 286	94.51 296	73.87 330	97.29 355	86.12 300	88.82 306	95.31 309

FMVSNet3		91.78 231	90.69 255	95.03 189	96.53 217	92.27 102	97.02 189	96.93 238	89.79 235	89.35 286	94.65 289	77.01 304	97.47 343	86.12 300	88.82 306	95.35 306

FMVSNet1		89.88 311	88.31 324	94.59 213	95.41 276	91.18 149	97.50 138	96.93 238	86.62 327	87.41 334	94.51 296	65.94 393	97.29 355	83.04 338	87.43 321	95.31 309

GeoE		93.89 150	93.28 156	95.72 155	96.96 182	89.75 198	98.24 38	96.92 242	89.47 243	92.12 210	97.21 154	84.42 172	98.39 239	87.71 267	96.50 182	99.01 95

miper_enhance_ethall		91.54 246	91.01 237	93.15 289	95.35 282	87.07 282	93.97 358	96.90 243	86.79 325	89.17 293	93.43 354	86.55 143	97.64 327	89.97 217	86.93 326	94.74 349

eth_miper_zixun_eth		91.02 274	90.59 258	92.34 315	95.33 286	84.35 334	94.10 355	96.90 243	88.56 277	88.84 302	94.33 308	84.08 179	97.60 332	88.77 250	84.37 362	95.06 324

TAMVS		94.01 146	93.46 149	95.64 158	96.16 242	90.45 176	96.71 218	96.89 245	89.27 250	93.46 178	96.92 169	87.29 135	97.94 297	88.70 252	95.74 195	98.53 143

miper_ehance_all_eth		91.59 240	91.13 233	92.97 295	95.55 269	86.57 294	94.47 339	96.88 246	87.77 303	88.88 299	94.01 327	86.22 148	97.54 336	89.49 229	86.93 326	94.79 345

v2v482		91.59 240	90.85 244	93.80 260	93.87 351	88.17 255	96.94 198	96.88 246	89.54 240	89.53 281	94.90 275	81.70 231	98.02 281	89.25 238	85.04 351	95.20 317

CNLPA		94.28 132	93.53 144	96.52 93	98.38 81	92.55 92	96.59 234	96.88 246	90.13 225	91.91 216	97.24 152	85.21 161	99.09 162	87.64 273	97.83 145	97.92 194

PAPM		91.52 247	90.30 268	95.20 180	95.30 289	89.83 196	93.38 378	96.85 249	86.26 335	88.59 307	95.80 231	84.88 165	98.15 258	75.67 390	95.93 191	97.63 212

c3_l		91.38 254	90.89 240	92.88 299	95.58 267	86.30 301	94.68 331	96.84 250	88.17 288	88.83 303	94.23 316	85.65 157	97.47 343	89.36 233	84.63 355	94.89 335

pm-mvs1		90.72 286	89.65 300	93.96 250	94.29 341	89.63 199	97.79 95	96.82 251	89.07 255	86.12 357	95.48 253	78.61 286	97.78 315	86.97 288	81.67 381	94.46 356

test_vis1_n		92.37 207	92.26 192	92.72 305	94.75 321	82.64 354	98.02 59	96.80 252	91.18 186	97.77 50	97.93 100	58.02 409	98.29 247	97.63 34	98.21 132	97.23 235

CMPMVS	62.92 21	85.62 363	84.92 359	87.74 385	89.14 407	73.12 415	94.17 353	96.80 252	73.98 414	73.65 413	94.93 273	66.36 387	97.61 331	83.95 331	91.28 279	92.48 391
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 299	89.77 294	91.78 334	94.33 338	84.72 331	95.55 298	96.73 254	86.17 337	86.36 354	95.28 259	71.28 347	97.80 313	84.09 328	98.14 136	92.81 383

Effi-MVS+-dtu		93.08 179	93.21 158	92.68 308	96.02 251	83.25 348	97.14 182	96.72 255	93.85 88	91.20 241	93.44 351	83.08 198	98.30 246	91.69 188	95.73 196	96.50 253

TSAR-MVS + GP.		96.69 59	96.49 63	97.27 62	98.31 84	93.39 63	96.79 210	96.72 255	94.17 77	97.44 56	97.66 124	92.76 31	99.33 127	96.86 53	97.76 149	99.08 89

1112_ss		93.37 167	92.42 188	96.21 124	97.05 175	90.99 156	96.31 255	96.72 255	86.87 324	89.83 271	96.69 181	86.51 144	99.14 154	88.12 257	93.67 243	98.50 147

PVSNet	86.66 18	92.24 215	91.74 210	93.73 263	97.77 130	83.69 345	92.88 387	96.72 255	87.91 296	93.00 189	94.86 277	78.51 287	99.05 172	86.53 291	97.45 157	98.47 152

miper_lstm_enhance		90.50 295	90.06 283	91.83 330	95.33 286	83.74 342	93.86 364	96.70 259	87.56 310	87.79 326	93.81 335	83.45 190	96.92 367	87.39 278	84.62 356	94.82 340

v148		90.99 275	90.38 264	92.81 302	93.83 352	85.80 309	96.78 212	96.68 260	89.45 245	88.75 305	93.93 331	82.96 204	97.82 310	87.83 263	83.25 373	94.80 343

ACMH+	87.92 14	90.20 303	89.18 311	93.25 284	96.48 223	86.45 298	96.99 194	96.68 260	88.83 267	84.79 368	96.22 209	70.16 357	98.53 225	84.42 325	88.04 314	94.77 348

CANet_DTU		94.37 130	93.65 139	96.55 91	96.46 226	92.13 108	96.21 263	96.67 262	94.38 74	93.53 176	97.03 164	79.34 270	99.71 58	90.76 204	98.45 123	97.82 205

cl____		90.96 278	90.32 266	92.89 298	95.37 280	86.21 304	94.46 341	96.64 263	87.82 299	88.15 321	94.18 319	82.98 202	97.54 336	87.70 268	85.59 338	94.92 333

HY-MVS	89.66 9	93.87 151	92.95 163	96.63 86	97.10 169	92.49 94	95.64 295	96.64 263	89.05 257	93.00 189	95.79 234	85.77 156	99.45 117	89.16 243	94.35 223	97.96 192

Test_1112_low_res		92.84 193	91.84 205	95.85 146	97.04 176	89.97 192	95.53 300	96.64 263	85.38 347	89.65 277	95.18 264	85.86 154	99.10 159	87.70 268	93.58 248	98.49 149

DIV-MVS_self_test		90.97 277	90.33 265	92.88 299	95.36 281	86.19 305	94.46 341	96.63 266	87.82 299	88.18 320	94.23 316	82.99 201	97.53 338	87.72 265	85.57 339	94.93 331

Fast-Effi-MVS+-dtu		92.29 212	91.99 200	93.21 287	95.27 290	85.52 313	97.03 187	96.63 266	92.09 155	89.11 295	95.14 266	80.33 253	98.08 269	87.54 276	94.74 219	96.03 271

UnsupCasMVSNet_bld		82.13 377	79.46 382	90.14 367	88.00 415	82.47 359	90.89 405	96.62 268	78.94 404	75.61 408	84.40 419	56.63 412	96.31 377	77.30 382	66.77 420	91.63 401

cl22		91.21 265	90.56 260	93.14 290	96.09 249	86.80 286	94.41 343	96.58 269	87.80 301	88.58 308	93.99 329	80.85 244	97.62 330	89.87 220	86.93 326	94.99 326

jason		94.84 120	94.39 126	96.18 126	95.52 270	90.93 160	96.09 268	96.52 270	89.28 249	96.01 116	97.32 146	84.70 167	98.77 200	95.15 112	98.91 103	98.85 120
jason: jason.
tt0805		91.09 270	90.07 282	94.16 238	95.61 265	88.31 247	97.56 130	96.51 271	89.56 239	89.17 293	95.64 243	67.08 385	98.38 240	91.07 200	88.44 312	95.80 279

AUN-MVS		91.76 232	90.75 250	94.81 203	97.00 180	88.57 239	96.65 225	96.49 272	89.63 237	92.15 208	96.12 215	78.66 285	98.50 227	90.83 202	79.18 392	97.36 227

hse-mvs2		93.45 165	92.99 161	94.81 203	97.02 178	88.59 238	96.69 221	96.47 273	95.19 29	96.74 80	96.16 213	83.67 185	98.48 230	95.85 89	79.13 393	97.35 229

EG-PatchMatch MVS		87.02 346	85.44 351	91.76 336	92.67 381	85.00 325	96.08 269	96.45 274	83.41 377	79.52 400	93.49 348	57.10 411	97.72 321	79.34 373	90.87 288	92.56 388

KD-MVS_self_test		85.95 359	84.95 358	88.96 379	89.55 406	79.11 398	95.13 321	96.42 275	85.91 340	84.07 377	90.48 391	70.03 359	94.82 398	80.04 365	72.94 409	92.94 381

pmmvs6		87.81 338	86.19 346	92.69 307	91.32 394	86.30 301	97.34 160	96.41 276	80.59 398	84.05 378	94.37 305	67.37 380	97.67 324	84.75 320	79.51 391	94.09 368

PMMVS		92.86 191	92.34 189	94.42 225	94.92 312	86.73 289	94.53 336	96.38 277	84.78 359	94.27 158	95.12 268	83.13 197	98.40 234	91.47 192	96.49 183	98.12 180

RPSCF		90.75 284	90.86 242	90.42 363	96.84 188	76.29 406	95.61 296	96.34 278	83.89 368	91.38 229	97.87 105	76.45 309	98.78 197	87.16 285	92.23 261	96.20 260

BP-MVS1		95.89 88	95.49 88	97.08 74	96.67 203	93.20 73	98.08 53	96.32 279	94.56 62	96.32 101	97.84 110	84.07 180	99.15 151	96.75 55	98.78 106	98.90 112

MSDG		91.42 252	90.24 272	94.96 196	97.15 167	88.91 231	93.69 370	96.32 279	85.72 343	86.93 349	96.47 197	80.24 254	98.98 178	80.57 362	95.05 212	96.98 239

WBMVS		90.69 289	89.99 285	92.81 302	96.48 223	85.00 325	95.21 319	96.30 281	89.46 244	89.04 296	94.05 326	72.45 340	97.82 310	89.46 230	87.41 323	95.61 290

OurMVSNet-221017-0		90.51 294	90.19 277	91.44 342	93.41 366	81.25 369	96.98 195	96.28 282	91.68 167	86.55 353	96.30 205	74.20 329	97.98 285	88.96 246	87.40 324	95.09 322

MVP-Stereo		90.74 285	90.08 279	92.71 306	93.19 371	88.20 253	95.86 280	96.27 283	86.07 338	84.86 367	94.76 282	77.84 299	97.75 319	83.88 333	98.01 140	92.17 398
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 115	94.56 117	96.29 118	96.34 233	91.21 144	95.83 282	96.27 283	88.93 263	96.22 106	96.88 171	86.20 150	98.85 190	95.27 108	99.05 94	98.82 124

BH-untuned		92.94 187	92.62 178	93.92 256	97.22 161	86.16 306	96.40 247	96.25 285	90.06 226	89.79 272	96.17 212	83.19 194	98.35 242	87.19 283	97.27 165	97.24 234

CL-MVSNet_self_test		86.31 354	85.15 355	89.80 371	88.83 410	81.74 367	93.93 361	96.22 286	86.67 326	85.03 365	90.80 389	78.09 295	94.50 399	74.92 393	71.86 411	93.15 379

IS-MVSNet		94.90 117	94.52 121	96.05 132	97.67 136	90.56 172	98.44 21	96.22 286	93.21 113	93.99 165	97.74 118	85.55 158	98.45 231	89.98 216	97.86 144	99.14 81

FA-MVS(test-final)		93.52 163	92.92 164	95.31 177	96.77 198	88.54 241	94.82 328	96.21 288	89.61 238	94.20 160	95.25 262	83.24 192	99.14 154	90.01 215	96.16 187	98.25 168

GA-MVS		91.38 254	90.31 267	94.59 213	94.65 326	87.62 269	94.34 346	96.19 289	90.73 200	90.35 252	93.83 332	71.84 343	97.96 292	87.22 282	93.61 246	98.21 171

IterMVS-SCA-FT		90.31 297	89.81 292	91.82 331	95.52 270	84.20 337	94.30 349	96.15 290	90.61 210	87.39 335	94.27 313	75.80 315	96.44 375	87.34 279	86.88 330	94.82 340

IterMVS		90.15 305	89.67 298	91.61 338	95.48 272	83.72 343	94.33 347	96.12 291	89.99 227	87.31 338	94.15 321	75.78 317	96.27 378	86.97 288	86.89 329	94.83 338
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 196	91.51 219	96.52 93	98.77 56	90.99 156	97.38 157	96.08 292	82.38 383	89.29 289	97.87 105	83.77 183	99.69 64	81.37 356	96.69 179	98.89 116

pmmvs4		90.93 279	89.85 290	94.17 237	93.34 368	90.79 165	94.60 333	96.02 293	84.62 360	87.45 332	95.15 265	81.88 228	97.45 345	87.70 268	87.87 316	94.27 365

ppachtmachnet_test		88.35 333	87.29 332	91.53 339	92.45 387	83.57 346	93.75 367	95.97 294	84.28 363	85.32 364	94.18 319	79.00 282	96.93 366	75.71 389	84.99 352	94.10 366

Anonymous20240521		86.42 352	85.44 351	89.34 377	90.33 399	79.79 389	96.73 215	95.92 295	83.71 373	83.25 383	91.36 386	63.92 398	96.01 379	78.39 377	85.36 343	92.22 396

ITE_SJBPF				92.43 311	95.34 283	85.37 318		95.92 295	91.47 172	87.75 328	96.39 202	71.00 349	97.96 292	82.36 347	89.86 298	93.97 369

test_fmvs2		89.77 315	89.93 287	89.31 378	93.68 357	76.37 405	97.64 121	95.90 297	89.84 233	91.49 227	96.26 208	58.77 408	97.10 359	94.65 127	91.13 281	94.46 356

USDC		88.94 324	87.83 329	92.27 317	94.66 325	84.96 327	93.86 364	95.90 297	87.34 315	83.40 381	95.56 247	67.43 379	98.19 255	82.64 346	89.67 300	93.66 372

COLMAP_ROB	87.81 15	90.40 296	89.28 308	93.79 261	97.95 119	87.13 281	96.92 199	95.89 299	82.83 380	86.88 351	97.18 155	73.77 333	99.29 134	78.44 376	93.62 245	94.95 327
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 153	93.08 159	96.02 135	97.88 125	89.96 193	97.72 106	95.85 300	92.43 143	95.86 120	98.44 55	68.42 375	99.39 123	96.31 66	94.85 213	98.71 131

VDDNet		93.05 181	92.07 195	96.02 135	96.84 188	90.39 180	98.08 53	95.85 300	86.22 336	95.79 123	98.46 53	67.59 378	99.19 142	94.92 117	94.85 213	98.47 152

mvsmamba		94.57 126	94.14 130	95.87 143	97.03 177	89.93 194	97.84 86	95.85 300	91.34 178	94.79 146	96.80 173	80.67 245	98.81 194	94.85 118	98.12 137	98.85 120

Vis-MVSNet (Re-imp)		94.15 137	93.88 134	94.95 197	97.61 144	87.92 261	98.10 51	95.80 303	92.22 148	93.02 188	97.45 139	84.53 170	97.91 303	88.24 256	97.97 141	99.02 92

MM		97.29 24	96.98 34	98.23 11	98.01 113	95.03 26	98.07 55	95.76 304	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		84.81 367	82.64 371	91.31 344	91.07 396	85.34 319	91.22 400	95.75 305	85.56 345	83.09 384	90.21 394	67.21 381	95.89 381	77.18 383	62.48 424	92.69 384

miper_refine_blended		84.81 367	82.64 371	91.31 344	91.07 396	85.34 319	91.22 400	95.75 305	85.56 345	83.09 384	90.21 394	67.21 381	95.89 381	77.18 383	62.48 424	92.69 384

FE-MVS		92.05 223	91.05 235	95.08 186	96.83 190	87.93 260	93.91 363	95.70 307	86.30 333	94.15 162	94.97 270	76.59 307	99.21 140	84.10 327	96.86 172	98.09 184

tpm cat1		88.36 332	87.21 335	91.81 332	95.13 302	80.55 378	92.58 391	95.70 307	74.97 413	87.45 332	91.96 380	78.01 298	98.17 257	80.39 364	88.74 309	96.72 249

our_test_3		88.78 328	87.98 328	91.20 348	92.45 387	82.53 356	93.61 374	95.69 309	85.77 342	84.88 366	93.71 337	79.99 259	96.78 372	79.47 370	86.24 332	94.28 364

BH-w/o		92.14 220	91.75 208	93.31 282	96.99 181	85.73 310	95.67 290	95.69 309	88.73 273	89.26 291	94.82 280	82.97 203	98.07 273	85.26 315	96.32 186	96.13 267

CR-MVSNet		90.82 282	89.77 294	93.95 251	94.45 334	87.19 278	90.23 408	95.68 311	86.89 323	92.40 198	92.36 373	80.91 241	97.05 361	81.09 360	93.95 239	97.60 217

Patchmtry		88.64 330	87.25 333	92.78 304	94.09 344	86.64 290	89.82 412	95.68 311	80.81 395	87.63 330	92.36 373	80.91 241	97.03 362	78.86 374	85.12 348	94.67 351

testing91		91.90 228	91.02 236	94.53 220	96.54 215	86.55 296	95.86 280	95.64 313	91.77 164	91.89 217	93.47 350	69.94 360	98.86 188	90.23 214	93.86 241	98.18 173

BH-RMVSNet		92.72 198	91.97 201	94.97 195	97.16 165	87.99 259	96.15 266	95.60 314	90.62 209	91.87 218	97.15 158	78.41 289	98.57 223	83.16 336	97.60 151	98.36 164

PVSNet_0	82.17 19	85.46 364	83.64 367	90.92 352	95.27 290	79.49 394	90.55 406	95.60 314	83.76 372	83.00 386	89.95 396	71.09 348	97.97 288	82.75 344	60.79 426	95.31 309

SCA		91.84 230	91.18 232	93.83 258	95.59 266	84.95 328	94.72 330	95.58 316	90.82 196	92.25 206	93.69 339	75.80 315	98.10 264	86.20 297	95.98 189	98.45 154

MonoMVSNet		91.92 226	91.77 206	92.37 312	92.94 375	83.11 350	97.09 185	95.55 317	92.91 133	90.85 244	94.55 293	81.27 237	96.52 374	93.01 164	87.76 317	97.47 223

AllTest		90.23 301	88.98 314	93.98 247	97.94 120	86.64 290	96.51 238	95.54 318	85.38 347	85.49 361	96.77 175	70.28 355	99.15 151	80.02 366	92.87 250	96.15 265

TestCases				93.98 247	97.94 120	86.64 290		95.54 318	85.38 347	85.49 361	96.77 175	70.28 355	99.15 151	80.02 366	92.87 250	96.15 265

mmtdpeth		89.70 317	88.96 315	91.90 327	95.84 259	84.42 333	97.46 147	95.53 320	90.27 220	94.46 155	90.50 390	69.74 364	98.95 179	97.39 45	69.48 415	92.34 392

tpmvs		89.83 314	89.15 312	91.89 328	94.92 312	80.30 382	93.11 383	95.46 321	86.28 334	88.08 322	92.65 363	80.44 250	98.52 226	81.47 352	89.92 297	96.84 245

pmmvs5		89.86 313	88.87 318	92.82 301	92.86 377	86.23 303	96.26 258	95.39 322	84.24 364	87.12 340	94.51 296	74.27 328	97.36 352	87.61 275	87.57 319	94.86 336

PatchmatchNet		91.91 227	91.35 221	93.59 271	95.38 278	84.11 338	93.15 382	95.39 322	89.54 240	92.10 211	93.68 341	82.82 207	98.13 259	84.81 319	95.32 205	98.52 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 251	91.32 223	91.79 333	95.15 300	79.20 397	93.42 377	95.37 324	88.55 278	93.49 177	93.67 342	82.49 215	98.27 248	90.41 209	89.34 303	97.90 195

Anonymous20231206		87.09 345	86.14 347	89.93 370	91.22 395	80.35 380	96.11 267	95.35 325	83.57 375	84.16 373	93.02 358	73.54 335	95.61 389	72.16 405	86.14 334	93.84 371

MIMVSNet1		84.93 366	83.05 368	90.56 361	89.56 405	84.84 330	95.40 305	95.35 325	83.91 367	80.38 396	92.21 377	57.23 410	93.34 411	70.69 411	82.75 379	93.50 374

TDRefinement		86.53 349	84.76 361	91.85 329	82.23 427	84.25 335	96.38 249	95.35 325	84.97 356	84.09 376	94.94 272	65.76 394	98.34 245	84.60 323	74.52 405	92.97 380

TR-MVS		91.48 250	90.59 258	94.16 238	96.40 229	87.33 271	95.67 290	95.34 328	87.68 307	91.46 228	95.52 250	76.77 306	98.35 242	82.85 341	93.61 246	96.79 247

EPNet_dtu		91.71 233	91.28 226	92.99 294	93.76 354	83.71 344	96.69 221	95.28 329	93.15 120	87.02 345	95.95 223	83.37 191	97.38 351	79.46 371	96.84 173	97.88 197
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 342	85.79 349	91.78 334	94.80 319	87.28 273	95.49 302	95.28 329	84.09 366	83.85 380	91.82 381	62.95 401	94.17 403	78.48 375	85.34 344	93.91 370

MDTV_nov1_ep13			90.76 248		95.22 294	80.33 381	93.03 385	95.28 329	88.14 291	92.84 195	93.83 332	81.34 234	98.08 269	82.86 339	94.34 224

LF4IMVS		87.94 336	87.25 333	89.98 369	92.38 389	80.05 388	94.38 344	95.25 332	87.59 309	84.34 370	94.74 284	64.31 397	97.66 326	84.83 318	87.45 320	92.23 395

TransMVSNet (Re)		88.94 324	87.56 330	93.08 292	94.35 337	88.45 245	97.73 103	95.23 333	87.47 311	84.26 372	95.29 257	79.86 262	97.33 353	79.44 372	74.44 406	93.45 376

test20.03		86.14 357	85.40 353	88.35 380	90.12 400	80.06 387	95.90 279	95.20 334	88.59 274	81.29 391	93.62 344	71.43 346	92.65 415	71.26 409	81.17 384	92.34 392

new-patchmatchnet		83.18 373	81.87 376	87.11 388	86.88 418	75.99 407	93.70 368	95.18 335	85.02 355	77.30 407	88.40 406	65.99 392	93.88 408	74.19 398	70.18 413	91.47 405

MDA-MVSNet_test_wron		85.87 361	84.23 365	90.80 358	92.38 389	82.57 355	93.17 380	95.15 336	82.15 384	67.65 419	92.33 376	78.20 291	95.51 392	77.33 380	79.74 388	94.31 363

YYNet1		85.87 361	84.23 365	90.78 359	92.38 389	82.46 360	93.17 380	95.14 337	82.12 385	67.69 417	92.36 373	78.16 294	95.50 393	77.31 381	79.73 389	94.39 359

Baseline_NR-MVSNet		91.20 266	90.62 256	92.95 296	93.83 352	88.03 258	97.01 192	95.12 338	88.42 282	89.70 274	95.13 267	83.47 188	97.44 346	89.66 226	83.24 374	93.37 377

thres200		92.23 216	91.39 220	94.75 210	97.61 144	89.03 229	96.60 233	95.09 339	92.08 156	93.28 183	94.00 328	78.39 290	99.04 175	81.26 359	94.18 230	96.19 261

ADS-MVSNet		89.89 310	88.68 320	93.53 274	95.86 254	84.89 329	90.93 403	95.07 340	83.23 378	91.28 237	91.81 382	79.01 280	97.85 306	79.52 368	91.39 277	97.84 202

pmmvs-eth3d		86.22 355	84.45 363	91.53 339	88.34 414	87.25 275	94.47 339	95.01 341	83.47 376	79.51 401	89.61 399	69.75 363	95.71 386	83.13 337	76.73 400	91.64 400

Anonymous202405211		92.07 222	90.83 246	95.76 149	98.19 99	88.75 234	97.58 127	95.00 342	86.00 339	93.64 172	97.45 139	66.24 390	99.53 103	90.68 207	92.71 255	99.01 95

MDA-MVSNet-bldmvs		85.00 365	82.95 370	91.17 350	93.13 373	83.33 347	94.56 335	95.00 342	84.57 361	65.13 423	92.65 363	70.45 354	95.85 383	73.57 401	77.49 396	94.33 361

ambc				86.56 391	83.60 424	70.00 418	85.69 422	94.97 344		80.60 395	88.45 405	37.42 426	96.84 370	82.69 345	75.44 404	92.86 382

testgi		87.97 335	87.21 335	90.24 366	92.86 377	80.76 373	96.67 224	94.97 344	91.74 165	85.52 360	95.83 229	62.66 403	94.47 401	76.25 387	88.36 313	95.48 293

myMVS_eth3d28		91.52 247	90.97 238	93.17 288	96.91 183	83.24 349	95.61 296	94.96 346	92.24 147	91.98 214	93.28 355	69.31 365	98.40 234	88.71 251	95.68 198	97.88 197

dp		88.90 326	88.26 326	90.81 356	94.58 330	76.62 404	92.85 388	94.93 347	85.12 353	90.07 266	93.07 357	75.81 314	98.12 262	80.53 363	87.42 322	97.71 209

test_fmvs3		83.21 372	83.02 369	83.78 395	86.77 419	68.34 421	96.76 213	94.91 348	86.49 329	84.14 375	89.48 400	36.04 427	91.73 417	91.86 182	80.77 386	91.26 407

test_0402		86.46 351	84.79 360	91.45 341	95.02 306	85.55 312	96.29 257	94.89 349	80.90 392	82.21 388	93.97 330	68.21 376	97.29 355	62.98 418	88.68 310	91.51 403

tfpn200view9		92.38 206	91.52 217	94.95 197	97.85 126	89.29 219	97.41 150	94.88 350	92.19 152	93.27 184	94.46 301	78.17 292	99.08 165	81.40 353	94.08 234	96.48 254

CVMVSNet		91.23 264	91.75 208	89.67 372	95.77 260	74.69 408	96.44 239	94.88 350	85.81 341	92.18 207	97.64 128	79.07 275	95.58 391	88.06 259	95.86 193	98.74 128

thres400		92.42 204	91.52 217	95.12 185	97.85 126	89.29 219	97.41 150	94.88 350	92.19 152	93.27 184	94.46 301	78.17 292	99.08 165	81.40 353	94.08 234	96.98 239

EPNet		95.20 108	94.56 117	97.14 69	92.80 379	92.68 87	97.85 85	94.87 353	96.64 5	92.46 197	97.80 115	86.23 147	99.65 70	93.72 146	98.62 114	99.10 87
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 238	90.72 253	94.32 230	96.48 223	86.11 307	95.81 283	94.76 354	91.55 169	91.75 222	93.44 351	68.55 373	98.82 192	90.43 208	93.69 242	98.04 188

SixPastTwentyTwo		89.15 322	88.54 322	90.98 351	93.49 363	80.28 384	96.70 219	94.70 355	90.78 197	84.15 374	95.57 246	71.78 344	97.71 322	84.63 322	85.07 349	94.94 329

thres100view900		92.43 203	91.58 214	94.98 193	97.92 122	89.37 215	97.71 108	94.66 356	92.20 150	93.31 182	94.90 275	78.06 296	99.08 165	81.40 353	94.08 234	96.48 254

thres600view7		92.49 202	91.60 213	95.18 181	97.91 123	89.47 209	97.65 117	94.66 356	92.18 154	93.33 181	94.91 274	78.06 296	99.10 159	81.61 350	94.06 238	96.98 239

PatchT		88.87 327	87.42 331	93.22 286	94.08 345	85.10 323	89.51 413	94.64 358	81.92 386	92.36 201	88.15 409	80.05 258	97.01 364	72.43 404	93.65 244	97.54 220

baseline1		92.82 194	91.90 203	95.55 165	97.20 163	90.77 166	97.19 177	94.58 359	92.20 150	92.36 201	96.34 204	84.16 178	98.21 252	89.20 241	83.90 369	97.68 211

UBG		91.55 244	90.76 248	93.94 253	96.52 219	85.06 324	95.22 317	94.54 360	90.47 216	91.98 214	92.71 362	72.02 341	98.74 204	88.10 258	95.26 207	98.01 190

Gipuma		67.86 393	65.41 395	75.18 408	92.66 382	73.45 412	66.50 429	94.52 361	53.33 428	57.80 429	66.07 429	30.81 429	89.20 421	48.15 427	78.88 395	62.90 429
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 236	90.75 250	94.47 221	96.53 217	86.56 295	95.76 287	94.51 362	91.10 191	91.24 239	93.59 345	68.59 372	98.86 188	91.10 199	94.29 226	98.00 191

CostFormer		91.18 269	90.70 254	92.62 309	94.84 317	81.76 366	94.09 356	94.43 363	84.15 365	92.72 196	93.77 336	79.43 269	98.20 253	90.70 206	92.18 264	97.90 195

tpm2		89.96 307	89.21 310	92.23 320	94.91 314	81.25 369	93.78 366	94.42 364	80.62 397	91.56 225	93.44 351	76.44 310	97.94 297	85.60 309	92.08 268	97.49 221

testing3-2		92.10 221	92.05 196	92.27 317	97.71 134	79.56 391	97.42 149	94.41 365	93.53 101	93.22 186	95.49 251	69.16 367	99.11 157	93.25 154	94.22 228	98.13 178

MVS_0304		96.74 56	96.31 73	98.02 19	96.87 185	94.65 30	97.58 127	94.39 366	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		88.26 334	87.04 338	91.91 326	93.52 361	81.42 368	89.38 414	94.38 367	80.84 394	90.93 243	80.74 421	79.22 272	97.92 300	82.76 343	91.62 272	96.38 257

dmvs_re		90.21 302	89.50 303	92.35 313	95.47 275	85.15 321	95.70 289	94.37 368	90.94 195	88.42 310	93.57 346	74.63 325	95.67 388	82.80 342	89.57 301	96.22 259

Patchmatch-test		89.42 320	87.99 327	93.70 266	95.27 290	85.11 322	88.98 415	94.37 368	81.11 391	87.10 343	93.69 339	82.28 219	97.50 341	74.37 396	94.76 217	98.48 151

LCM-MVSNet		72.55 386	69.39 390	82.03 397	70.81 437	65.42 426	90.12 410	94.36 370	55.02 427	65.88 421	81.72 420	24.16 435	89.96 418	74.32 397	68.10 418	90.71 410

ADS-MVSNet2		89.45 319	88.59 321	92.03 323	95.86 254	82.26 362	90.93 403	94.32 371	83.23 378	91.28 237	91.81 382	79.01 280	95.99 380	79.52 368	91.39 277	97.84 202

mvs5depth		86.53 349	85.08 356	90.87 353	88.74 412	82.52 357	91.91 396	94.23 372	86.35 332	87.11 342	93.70 338	66.52 386	97.76 318	81.37 356	75.80 402	92.31 394

EU-MVSNet		88.72 329	88.90 317	88.20 382	93.15 372	74.21 410	96.63 230	94.22 373	85.18 351	87.32 337	95.97 221	76.16 312	94.98 397	85.27 314	86.17 333	95.41 299

MIMVSNet		88.50 331	86.76 341	93.72 265	94.84 317	87.77 267	91.39 398	94.05 374	86.41 331	87.99 324	92.59 366	63.27 399	95.82 385	77.44 379	92.84 252	97.57 219

OpenMVS_ROB	81.14 20	84.42 369	82.28 375	90.83 354	90.06 401	84.05 340	95.73 288	94.04 375	73.89 416	80.17 399	91.53 385	59.15 407	97.64 327	66.92 416	89.05 305	90.80 409

TinyColmap		86.82 347	85.35 354	91.21 346	94.91 314	82.99 352	93.94 360	94.02 376	83.58 374	81.56 390	94.68 286	62.34 404	98.13 259	75.78 388	87.35 325	92.52 390

ETVMVS		90.52 293	89.14 313	94.67 212	96.81 194	87.85 265	95.91 278	93.97 377	89.71 236	92.34 204	92.48 368	65.41 395	97.96 292	81.37 356	94.27 227	98.21 171

IB-MVS	87.33 17	89.91 308	88.28 325	94.79 207	95.26 293	87.70 268	95.12 322	93.95 378	89.35 248	87.03 344	92.49 367	70.74 352	99.19 142	89.18 242	81.37 383	97.49 221
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		87.13 344	87.02 339	87.47 386	95.16 297	73.21 414	95.00 324	93.93 379	88.55 278	86.96 346	91.99 378	75.90 313	94.00 405	61.59 420	94.11 231	95.20 317

myMVS_eth3d		87.18 343	86.38 344	89.58 373	95.16 297	79.53 392	95.00 324	93.93 379	88.55 278	86.96 346	91.99 378	56.23 413	94.00 405	75.47 392	94.11 231	95.20 317

testing222		90.31 297	88.96 315	94.35 227	96.54 215	87.29 272	95.50 301	93.84 381	90.97 194	91.75 222	92.96 359	62.18 405	98.00 283	82.86 339	94.08 234	97.76 207

test_f		80.57 379	79.62 381	83.41 396	83.38 425	67.80 423	93.57 375	93.72 382	80.80 396	77.91 406	87.63 412	33.40 428	92.08 416	87.14 286	79.04 394	90.34 411

LCM-MVSNet-Re		92.50 200	92.52 184	92.44 310	96.82 192	81.89 365	96.92 199	93.71 383	92.41 144	84.30 371	94.60 291	85.08 163	97.03 362	91.51 190	97.36 159	98.40 160

tpm		90.25 300	89.74 297	91.76 336	93.92 348	79.73 390	93.98 357	93.54 384	88.28 285	91.99 213	93.25 356	77.51 302	97.44 346	87.30 281	87.94 315	98.12 180

ET-MVSNet_ETH3D		91.49 249	90.11 278	95.63 159	96.40 229	91.57 130	95.34 308	93.48 385	90.60 212	75.58 409	95.49 251	80.08 257	96.79 371	94.25 134	89.76 299	98.52 144

LFMVS		93.60 159	92.63 177	96.52 93	98.13 105	91.27 141	97.94 73	93.39 386	90.57 213	96.29 103	98.31 72	69.00 368	99.16 149	94.18 135	95.87 192	99.12 85

MVStest1		82.38 376	80.04 380	89.37 375	87.63 417	82.83 353	95.03 323	93.37 387	73.90 415	73.50 414	94.35 306	62.89 402	93.25 413	73.80 399	65.92 421	92.04 399

Patchmatch-RL test		87.38 341	86.24 345	90.81 356	88.74 412	78.40 401	88.12 420	93.17 388	87.11 320	82.17 389	89.29 401	81.95 226	95.60 390	88.64 253	77.02 397	98.41 159

ttmdpeth		85.91 360	84.76 361	89.36 376	89.14 407	80.25 385	95.66 293	93.16 389	83.77 371	83.39 382	95.26 261	66.24 390	95.26 396	80.65 361	75.57 403	92.57 387

test-LLR		91.42 252	91.19 231	92.12 321	94.59 328	80.66 375	94.29 350	92.98 390	91.11 189	90.76 246	92.37 370	79.02 278	98.07 273	88.81 248	96.74 176	97.63 212

test-mter		90.19 304	89.54 302	92.12 321	94.59 328	80.66 375	94.29 350	92.98 390	87.68 307	90.76 246	92.37 370	67.67 377	98.07 273	88.81 248	96.74 176	97.63 212

WB-MVSnew		89.88 311	89.56 301	90.82 355	94.57 331	83.06 351	95.65 294	92.85 392	87.86 298	90.83 245	94.10 322	79.66 266	96.88 368	76.34 386	94.19 229	92.54 389

testing3		87.67 339	86.88 340	90.05 368	96.14 245	80.71 374	97.10 184	92.85 392	90.15 224	87.54 331	94.55 293	55.70 414	94.10 404	73.77 400	94.10 233	95.35 306

test_method		66.11 394	64.89 396	69.79 411	72.62 435	35.23 443	65.19 430	92.83 394	20.35 433	65.20 422	88.08 410	43.14 424	82.70 428	73.12 403	63.46 423	91.45 406

test0.0.03 1		89.37 321	88.70 319	91.41 343	92.47 386	85.63 311	95.22 317	92.70 395	91.11 189	86.91 350	93.65 343	79.02 278	93.19 414	78.00 378	89.18 304	95.41 299

new_pmnet		82.89 374	81.12 379	88.18 383	89.63 404	80.18 386	91.77 397	92.57 396	76.79 411	75.56 410	88.23 408	61.22 406	94.48 400	71.43 407	82.92 377	89.87 412

mvsany_test1		93.93 149	93.98 132	93.78 262	94.94 311	86.80 286	94.62 332	92.55 397	88.77 272	96.85 75	98.49 49	88.98 95	98.08 269	95.03 114	95.62 200	96.46 256

thisisatest0515		92.29 212	91.30 225	95.25 179	96.60 207	88.90 232	94.36 345	92.32 398	87.92 295	93.43 179	94.57 292	77.28 303	99.00 176	89.42 232	95.86 193	97.86 201

thisisatest0530		93.03 182	92.21 193	95.49 169	97.07 170	89.11 228	97.49 144	92.19 399	90.16 223	94.09 163	96.41 200	76.43 311	99.05 172	90.38 210	95.68 198	98.31 166

tttt0517		92.96 185	92.33 190	94.87 200	97.11 168	87.16 280	97.97 69	92.09 400	90.63 208	93.88 169	97.01 165	76.50 308	99.06 171	90.29 213	95.45 203	98.38 162

K. test v3		87.64 340	86.75 342	90.32 365	93.02 374	79.48 395	96.61 231	92.08 401	90.66 206	80.25 398	94.09 324	67.21 381	96.65 373	85.96 305	80.83 385	94.83 338

TESTMET0.1,1		90.06 306	89.42 305	91.97 324	94.41 336	80.62 377	94.29 350	91.97 402	87.28 317	90.44 250	92.47 369	68.79 369	97.67 324	88.50 255	96.60 181	97.61 216

PM-MVS		83.48 371	81.86 377	88.31 381	87.83 416	77.59 403	93.43 376	91.75 403	86.91 322	80.63 394	89.91 397	44.42 423	95.84 384	85.17 317	76.73 400	91.50 404

baseline2		91.63 237	90.86 242	93.94 253	94.33 338	86.32 300	95.92 277	91.64 404	89.37 247	86.94 348	94.69 285	81.62 232	98.69 210	88.64 253	94.57 222	96.81 246

APD_test1		79.31 381	77.70 384	84.14 394	89.11 409	69.07 420	92.36 395	91.50 405	69.07 419	73.87 412	92.63 365	39.93 425	94.32 402	70.54 412	80.25 387	89.02 414

FPMVS		71.27 387	69.85 389	75.50 407	74.64 432	59.03 432	91.30 399	91.50 405	58.80 424	57.92 428	88.28 407	29.98 431	85.53 427	53.43 425	82.84 378	81.95 420

door								91.13 407

door-mid								91.06 408

EGC-MVSNET		68.77 392	63.01 398	86.07 393	92.49 385	82.24 363	93.96 359	90.96 409	0.71 438	2.62 439	90.89 388	53.66 415	93.46 409	57.25 423	84.55 359	82.51 419

mvsany_test3		83.59 370	82.44 374	87.03 389	83.80 422	73.82 411	93.70 368	90.92 410	86.42 330	82.51 387	90.26 393	46.76 422	95.71 386	90.82 203	76.76 399	91.57 402

pmmvs3		79.97 380	77.50 385	87.39 387	82.80 426	79.38 396	92.70 390	90.75 411	70.69 418	78.66 403	87.47 414	51.34 418	93.40 410	73.39 402	69.65 414	89.38 413

UWE-MVS		89.91 308	89.48 304	91.21 346	95.88 253	78.23 402	94.91 327	90.26 412	89.11 254	92.35 203	94.52 295	68.76 370	97.96 292	83.95 331	95.59 201	97.42 225

DSMNet-mixed		86.34 353	86.12 348	87.00 390	89.88 403	70.43 416	94.93 326	90.08 413	77.97 408	85.42 363	92.78 361	74.44 327	93.96 407	74.43 395	95.14 208	96.62 250

MVS-HIRNet		82.47 375	81.21 378	86.26 392	95.38 278	69.21 419	88.96 416	89.49 414	66.28 421	80.79 393	74.08 426	68.48 374	97.39 350	71.93 406	95.47 202	92.18 397

WB-MVS		76.77 383	76.63 386	77.18 402	85.32 420	56.82 434	94.53 336	89.39 415	82.66 382	71.35 415	89.18 402	75.03 322	88.88 422	35.42 431	66.79 419	85.84 416

test1111		93.19 174	92.82 168	94.30 233	97.58 150	84.56 332	98.21 42	89.02 416	93.53 101	94.58 150	98.21 79	72.69 337	99.05 172	93.06 160	98.48 121	99.28 70

SSC-MVS		76.05 384	75.83 387	76.72 406	84.77 421	56.22 435	94.32 348	88.96 417	81.82 388	70.52 416	88.91 403	74.79 324	88.71 423	33.69 432	64.71 422	85.23 417

ECVR-MVS		93.19 174	92.73 174	94.57 218	97.66 138	85.41 315	98.21 42	88.23 418	93.43 106	94.70 148	98.21 79	72.57 338	99.07 169	93.05 161	98.49 119	99.25 73

EPMVS		90.70 287	89.81 292	93.37 280	94.73 323	84.21 336	93.67 371	88.02 419	89.50 242	92.38 200	93.49 348	77.82 300	97.78 315	86.03 303	92.68 256	98.11 183

ANet_high		63.94 396	59.58 399	77.02 403	61.24 439	66.06 424	85.66 423	87.93 420	78.53 406	42.94 431	71.04 428	25.42 434	80.71 430	52.60 426	30.83 432	84.28 418

PMMVS2		70.19 388	66.92 392	80.01 398	76.35 431	65.67 425	86.22 421	87.58 421	64.83 423	62.38 424	80.29 423	26.78 433	88.49 425	63.79 417	54.07 428	85.88 415

lessismore_v0				90.45 362	91.96 392	79.09 399		87.19 422		80.32 397	94.39 303	66.31 389	97.55 335	84.00 330	76.84 398	94.70 350

PMVS	53.92 22	58.58 397	55.40 400	68.12 412	51.00 440	48.64 437	78.86 426	87.10 423	46.77 429	35.84 435	74.28 425	8.76 439	86.34 426	42.07 429	73.91 407	69.38 426
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 348	86.41 343	88.02 384	92.87 376	74.60 409	95.38 307	86.70 424	88.17 288	87.28 339	94.67 288	70.83 351	93.30 412	67.45 414	94.31 225	96.17 262

test_vis1_rt		86.16 356	85.06 357	89.46 374	93.47 365	80.46 379	96.41 243	86.61 425	85.22 350	79.15 402	88.64 404	52.41 417	97.06 360	93.08 159	90.57 290	90.87 408

testf1		69.31 390	66.76 393	76.94 404	78.61 429	61.93 428	88.27 418	86.11 426	55.62 425	59.69 425	85.31 417	20.19 437	89.32 419	57.62 421	69.44 416	79.58 421

APD_test2		69.31 390	66.76 393	76.94 404	78.61 429	61.93 428	88.27 418	86.11 426	55.62 425	59.69 425	85.31 417	20.19 437	89.32 419	57.62 421	69.44 416	79.58 421

gg-mvs-nofinetune		87.82 337	85.61 350	94.44 223	94.46 333	89.27 222	91.21 402	84.61 428	80.88 393	89.89 270	74.98 424	71.50 345	97.53 338	85.75 308	97.21 167	96.51 252

dmvs_testset		81.38 378	82.60 373	77.73 401	91.74 393	51.49 436	93.03 385	84.21 429	89.07 255	78.28 405	91.25 387	76.97 305	88.53 424	56.57 424	82.24 380	93.16 378

GG-mvs-BLEND				93.62 269	93.69 356	89.20 224	92.39 394	83.33 430		87.98 325	89.84 398	71.00 349	96.87 369	82.08 349	95.40 204	94.80 343

MTMP							97.86 82	82.03 431

DeepMVS_CX				74.68 409	90.84 398	64.34 427		81.61 432	65.34 422	67.47 420	88.01 411	48.60 421	80.13 431	62.33 419	73.68 408	79.58 421

E-PMN		53.28 398	52.56 402	55.43 415	74.43 433	47.13 438	83.63 425	76.30 433	42.23 430	42.59 432	62.22 431	28.57 432	74.40 432	31.53 433	31.51 431	44.78 430

test2506		91.60 239	90.78 247	94.04 244	97.66 138	83.81 341	98.27 32	75.53 434	93.43 106	95.23 137	98.21 79	67.21 381	99.07 169	93.01 164	98.49 119	99.25 73

EMVS		52.08 400	51.31 403	54.39 416	72.62 435	45.39 440	83.84 424	75.51 435	41.13 431	40.77 433	59.65 432	30.08 430	73.60 433	28.31 435	29.90 433	44.18 431

test_vis3_rt		72.73 385	70.55 388	79.27 399	80.02 428	68.13 422	93.92 362	74.30 436	76.90 410	58.99 427	73.58 427	20.29 436	95.37 394	84.16 326	72.80 410	74.31 424

MVE	50.73 23	53.25 399	48.81 404	66.58 414	65.34 438	57.50 433	72.49 428	70.94 437	40.15 432	39.28 434	63.51 430	6.89 441	73.48 434	38.29 430	42.38 430	68.76 428
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 401	53.82 401	46.29 417	33.73 441	45.30 441	78.32 427	67.24 438	18.02 434	50.93 430	87.05 415	52.99 416	53.11 436	70.76 410	25.29 434	40.46 432

kuosan		65.27 395	64.66 397	67.11 413	83.80 422	61.32 431	88.53 417	60.77 439	68.22 420	67.67 418	80.52 422	49.12 420	70.76 435	29.67 434	53.64 429	69.26 427

dongtai		69.99 389	69.33 391	71.98 410	88.78 411	61.64 430	89.86 411	59.93 440	75.67 412	74.96 411	85.45 416	50.19 419	81.66 429	43.86 428	55.27 427	72.63 425

N_pmnet		78.73 382	78.71 383	78.79 400	92.80 379	46.50 439	94.14 354	43.71 441	78.61 405	80.83 392	91.66 384	74.94 323	96.36 376	67.24 415	84.45 361	93.50 374

wuyk23d		25.11 402	24.57 406	26.74 418	73.98 434	39.89 442	57.88 431	9.80 442	12.27 435	10.39 436	6.97 438	7.03 440	36.44 437	25.43 436	17.39 435	3.89 435

testmvs		13.36 404	16.33 407	4.48 420	5.04 442	2.26 445	93.18 379	3.28 443	2.70 436	8.24 437	21.66 434	2.29 443	2.19 438	7.58 437	2.96 436	9.00 434

test123		13.04 405	15.66 408	5.18 419	4.51 443	3.45 444	92.50 393	1.81 444	2.50 437	7.58 438	20.15 435	3.67 442	2.18 439	7.13 438	1.07 437	9.90 433

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		7.39 407	9.85 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	88.65 103	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

n2								0.00 445

nn								0.00 445

ab-mvs-re		8.06 406	10.74 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	96.69 181	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						79.53 392								75.56 391

PC_three_1452									90.77 198	98.89 22	98.28 77	96.24 1	98.35 242	95.76 93	99.58 23	99.59 26

eth-test2					0.00 444

eth-test					0.00 444

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 78	96.04 2	99.24 137	95.36 107	99.59 19	99.56 33

test_0728_THIRD									94.78 52	98.73 26	98.87 26	95.87 4	99.84 23	97.45 41	99.72 2	99.77 2

GSMVS																98.45 154

test_part2					99.28 25	95.74 8				98.10 39

sam_mvs1												82.76 208				98.45 154

sam_mvs												81.94 227

test_post1							92.81 389				16.58 437	80.53 248	97.68 323	86.20 297

test_post											17.58 436	81.76 229	98.08 269

patchmatchnet-post											90.45 392	82.65 212	98.10 264

gm-plane-assit					93.22 370	78.89 400			84.82 358		93.52 347		98.64 215	87.72 265

test9_res														94.81 122	99.38 59	99.45 52

agg_prior2														93.94 140	99.38 59	99.50 45

test_prior4						93.66 58	96.42 242

test_prior2							96.35 251		92.80 137	96.03 113	97.59 132	92.01 47		95.01 115	99.38 59

旧先验2							95.94 276		81.66 389	97.34 61			98.82 192	92.26 169

新几何2							95.79 285

原ACMM2							95.67 290

testdata2													99.67 68	85.96 305

segment_acmp												92.89 30

testdata1							95.26 316		93.10 123

plane_prior7					96.21 237	89.98 191

plane_prior6					96.10 248	90.00 187						81.32 235

plane_prior4											96.64 184

plane_prior3						90.00 187			94.46 68	91.34 231

plane_prior2							97.74 101		94.85 45

plane_prior1					96.14 245

plane_prior						89.99 189	97.24 169		94.06 80						92.16 265

HQP5-MVS						89.33 217

HQP-NCC					95.86 254		96.65 225		93.55 97	90.14 255

ACMP_Plane					95.86 254		96.65 225		93.55 97	90.14 255

BP-MVS														92.13 175

HQP4-MVS										90.14 255			98.50 227			95.78 281

HQP2-MVS												80.95 239

NP-MVS					95.99 252	89.81 197					95.87 226

MDTV_nov1_ep13_2view						70.35 417	93.10 384		83.88 369	93.55 174		82.47 216		86.25 296		98.38 162

ACMMP++_ref															90.30 295

ACMMP++															91.02 284

Test By Simon												88.73 102

High-resolution multi-view benchmark