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 13	97.89 3	96.53 99	98.41 80	91.73 125	98.01 61	99.02 1	96.37 10	99.30 4	98.92 20	92.39 41	99.79 40	99.16 11	99.46 41	98.08 205

PGM-MVS		96.81 52	96.53 63	97.65 43	99.35 22	93.53 61	97.65 122	98.98 2	92.22 158	97.14 69	98.44 57	91.17 68	99.85 18	94.35 142	99.46 41	99.57 31

MVS_111021_HR		96.68 63	96.58 62	96.99 80	98.46 75	92.31 106	96.20 281	98.90 3	94.30 83	95.86 126	97.74 124	92.33 42	99.38 129	96.04 88	99.42 51	99.28 72

test_fmvsmconf_n		97.49 17	97.56 12	97.29 60	97.44 158	92.37 103	97.91 80	98.88 4	95.83 16	98.92 20	99.05 12	91.45 58	99.80 35	99.12 13	99.46 41	99.69 13

lecture		97.58 12	97.63 9	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 31	98.65 30	98.90 22	91.97 49	99.80 35	97.63 35	99.21 76	99.57 31

ACMMP		96.27 80	95.93 83	97.28 62	99.24 30	92.62 94	98.25 36	98.81 6	92.99 132	94.56 163	98.39 61	88.96 97	99.85 18	94.57 140	97.63 156	99.36 67
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 81	96.19 79	96.39 117	98.23 98	91.35 146	96.24 279	98.79 7	93.99 90	95.80 128	97.65 133	89.92 87	99.24 142	95.87 92	99.20 81	98.58 152

patch_mono-2		96.83 51	97.44 20	95.01 205	99.05 41	85.39 341	96.98 205	98.77 8	94.70 63	97.99 44	98.66 40	93.61 19	99.91 1	97.67 34	99.50 35	99.72 12

fmvsm_s_conf0.5_n		96.85 48	97.13 25	96.04 141	98.07 113	90.28 194	97.97 72	98.76 9	94.93 45	98.84 25	99.06 11	88.80 101	99.65 72	99.06 15	98.63 116	98.18 191

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 57	98.21 99	92.75 88	97.83 92	98.73 10	95.04 42	99.30 4	98.84 33	93.34 22	99.78 43	99.32 5	99.13 91	99.50 47

fmvsm_s_conf0.5_n_a		96.75 56	96.93 40	96.20 133	97.64 144	90.72 176	98.00 62	98.73 10	94.55 70	98.91 21	99.08 7	88.22 113	99.63 81	98.91 18	98.37 129	98.25 186

FC-MVSNet-test		93.94 163	93.57 155	95.04 203	95.48 293	91.45 143	98.12 51	98.71 12	93.37 115	90.23 273	96.70 199	87.66 123	97.85 324	91.49 204	90.39 315	95.83 299

UniMVSNet (Re)		93.31 188	92.55 201	95.61 174	95.39 299	93.34 67	97.39 164	98.71 12	93.14 128	90.10 282	94.83 301	87.71 122	98.03 297	91.67 202	83.99 387	95.46 318

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 64	98.25 93	92.59 96	97.81 97	98.68 14	94.93 45	99.24 7	98.87 28	93.52 20	99.79 40	99.32 5	99.21 76	99.40 61

FIs		94.09 154	93.70 151	95.27 192	95.70 282	92.03 118	98.10 52	98.68 14	93.36 117	90.39 270	96.70 199	87.63 126	97.94 315	92.25 182	90.50 314	95.84 298

WR-MVS_H		92.00 245	91.35 242	93.95 270	95.09 326	89.47 223	98.04 59	98.68 14	91.46 187	88.34 333	94.68 308	85.86 158	97.56 353	85.77 328	84.24 385	94.82 363

fmvsm_s_conf0.5_n_4		96.75 56	97.07 28	95.79 161	97.76 135	89.57 217	97.66 121	98.66 17	95.36 27	99.03 13	98.90 22	88.39 109	99.73 54	99.17 10	98.66 114	98.08 205

VPA-MVSNet		93.24 190	92.48 206	95.51 180	95.70 282	92.39 102	97.86 85	98.66 17	92.30 155	92.09 231	95.37 276	80.49 268	98.40 251	93.95 148	85.86 358	95.75 307

fmvsm_l_conf0.5_n_3		97.64 8	97.60 10	97.79 30	98.14 106	93.94 52	97.93 78	98.65 19	96.70 5	99.38 2	99.07 10	89.92 87	99.81 30	99.16 11	99.43 48	99.61 25

fmvsm_s_conf0.5_n_3		97.15 30	97.36 22	96.52 101	97.98 119	91.19 154	97.84 89	98.65 19	97.08 4	99.25 6	99.10 5	87.88 120	99.79 40	99.32 5	99.18 83	98.59 151

fmvsm_s_conf0.5_n_8		97.32 24	97.48 19	96.85 82	98.28 89	91.07 162	97.76 102	98.62 21	97.53 2	99.20 9	99.12 4	88.24 112	99.81 30	99.41 3	99.17 84	99.67 14

fmvsm_s_conf0.5_n_2		96.62 64	96.82 49	96.02 143	97.98 119	90.43 186	97.50 145	98.59 22	96.59 7	99.31 3	99.08 7	84.47 184	99.75 51	99.37 4	98.45 126	97.88 218

UniMVSNet_NR-MVSNet		93.37 186	92.67 195	95.47 185	95.34 305	92.83 85	97.17 188	98.58 23	92.98 137	90.13 278	95.80 252	88.37 111	97.85 324	91.71 199	83.93 388	95.73 309

CSCG		96.05 84	95.91 84	96.46 111	99.24 30	90.47 183	98.30 29	98.57 24	89.01 279	93.97 180	97.57 143	92.62 37	99.76 47	94.66 134	99.27 69	99.15 82

fmvsm_s_conf0.5_n_9		97.33 23	97.57 11	96.62 95	98.43 78	90.32 193	97.80 98	98.53 25	97.24 3	99.62 1	99.14 1	88.65 104	99.80 35	99.54 1	99.15 88	99.74 8

fmvsm_s_conf0.5_n_6		97.08 33	97.17 24	96.81 83	97.28 163	91.73 125	97.75 104	98.50 26	94.86 49	99.22 8	98.78 37	89.75 90	99.76 47	99.10 14	99.29 67	98.94 111

MSLP-MVS++		96.94 42	97.06 29	96.59 96	98.72 60	91.86 123	97.67 118	98.49 27	94.66 66	97.24 65	98.41 60	92.31 44	98.94 188	96.61 64	99.46 41	98.96 107

HyFIR lowres test		93.66 175	92.92 183	95.87 153	98.24 94	89.88 208	94.58 355	98.49 27	85.06 376	93.78 183	95.78 256	82.86 219	98.67 226	91.77 197	95.71 213	99.07 93

CHOSEN 1792x2688		94.15 149	93.51 161	96.06 139	98.27 90	89.38 228	95.18 341	98.48 29	85.60 366	93.76 184	97.11 174	83.15 209	99.61 83	91.33 207	98.72 112	99.19 78

fmvsm_s_conf0.5_n_7		96.45 71	96.80 51	95.37 188	97.29 162	88.38 260	97.23 182	98.47 30	95.14 36	98.43 35	99.09 6	87.58 127	99.72 58	98.80 22	99.21 76	98.02 209

fmvsm_s_conf0.5_n_5		97.00 39	96.97 37	97.09 75	97.58 154	92.56 97	97.68 117	98.47 30	94.02 88	98.90 22	98.89 25	88.94 98	99.78 43	99.18 9	99.03 100	98.93 115

PHI-MVS		96.77 54	96.46 70	97.71 41	98.40 81	94.07 48	98.21 43	98.45 32	89.86 251	97.11 71	98.01 97	92.52 39	99.69 66	96.03 89	99.53 29	99.36 67

fmvsm_s_conf0.1_n		96.58 67	96.77 54	96.01 146	96.67 214	90.25 195	97.91 80	98.38 33	94.48 74	98.84 25	99.14 1	88.06 115	99.62 82	98.82 20	98.60 118	98.15 195

PVSNet_BlendedMVS		94.06 155	93.92 145	94.47 239	98.27 90	89.46 225	96.73 230	98.36 34	90.17 243	94.36 168	95.24 284	88.02 116	99.58 91	93.44 160	90.72 310	94.36 383

PVSNet_Blended		94.87 127	94.56 125	95.81 159	98.27 90	89.46 225	95.47 324	98.36 34	88.84 288	94.36 168	96.09 241	88.02 116	99.58 91	93.44 160	98.18 138	98.40 173

3Dnovator	91.36 5	95.19 115	94.44 133	97.44 53	96.56 224	93.36 66	98.65 12	98.36 34	94.12 85	89.25 312	98.06 91	82.20 236	99.77 46	93.41 162	99.32 65	99.18 79

FOURS1					99.55 1	93.34 67	99.29 1	98.35 37	94.98 43	98.49 33

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 34	95.78 7	97.21 185	98.35 37	95.16 35	98.71 29	98.80 35	95.05 10	99.89 3	96.70 62	99.73 1	99.73 11
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 73	96.47 67	96.16 135	95.48 293	90.69 177	97.91 80	98.33 39	94.07 86	98.93 17	99.14 1	87.44 134	99.61 83	98.63 23	98.32 131	98.18 191

HFP-MVS		97.14 31	96.92 41	97.83 26	99.42 7	94.12 46	98.52 16	98.32 40	93.21 120	97.18 66	98.29 77	92.08 46	99.83 26	95.63 105	99.59 19	99.54 40

ACMMPR		97.07 35	96.84 45	97.79 30	99.44 6	93.88 53	98.52 16	98.31 41	93.21 120	97.15 68	98.33 71	91.35 62	99.86 9	95.63 105	99.59 19	99.62 22

test_fmvsmvis_n_1920		96.70 59	96.84 45	96.31 122	96.62 216	91.73 125	97.98 66	98.30 42	96.19 11	96.10 116	98.95 18	89.42 91	99.76 47	98.90 19	99.08 95	97.43 245

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 35	94.82 28	98.81 8	98.30 42	94.76 61	98.30 37	98.90 22	93.77 17	99.68 68	97.93 26	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 28	98.29 44	94.92 47	98.99 15	98.92 20	95.08 8

MSP-MVS		97.59 11	97.54 13	97.73 38	99.40 11	93.77 57	98.53 15	98.29 44	95.55 24	98.56 32	97.81 119	93.90 15	99.65 72	96.62 63	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 63	95.39 11	99.29 1	98.28 46	94.78 58	98.93 17	98.87 28	96.04 2	99.86 9	97.45 43	99.58 23	99.59 27

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 46					99.86 9	97.52 39	99.67 6	99.75 6

CP-MVS		97.02 37	96.81 50	97.64 45	99.33 23	93.54 60	98.80 9	98.28 46	92.99 132	96.45 103	98.30 76	91.90 50	99.85 18	95.61 107	99.68 4	99.54 40

test_fmvsmconf0.1_n		97.09 32	97.06 29	97.19 69	95.67 284	92.21 110	97.95 75	98.27 49	95.78 20	98.40 36	99.00 14	89.99 85	99.78 43	99.06 15	99.41 54	99.59 27

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 49	95.13 37	99.19 10	98.89 25	95.54 5	99.85 18	97.52 39	99.66 10	99.56 35

test_241102_TWO								98.27 49	95.13 37	98.93 17	98.89 25	94.99 11	99.85 18	97.52 39	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 49	95.09 40	99.19 10	98.81 34	95.54 5	99.65 72

SF-MVS		97.39 20	97.13 25	98.17 15	99.02 44	95.28 19	98.23 40	98.27 49	92.37 154	98.27 38	98.65 42	93.33 23	99.72 58	96.49 68	99.52 30	99.51 44

SteuartSystems-ACMMP		97.62 10	97.53 14	97.87 24	98.39 83	94.25 40	98.43 23	98.27 49	95.34 29	98.11 40	98.56 44	94.53 12	99.71 60	96.57 66	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 24	95.20 20		98.25 55	95.13 37	98.48 34	98.87 28	95.16 7

PVSNet_Blended_VisFu		95.27 108	94.91 114	96.38 118	98.20 100	90.86 170	97.27 176	98.25 55	90.21 242	94.18 173	97.27 163	87.48 133	99.73 54	93.53 157	97.77 154	98.55 154

region2R		97.07 35	96.84 45	97.77 34	99.46 2	93.79 55	98.52 16	98.24 57	93.19 123	97.14 69	98.34 68	91.59 57	99.87 7	95.46 111	99.59 19	99.64 20

PS-CasMVS		91.55 265	90.84 266	93.69 287	94.96 330	88.28 263	97.84 89	98.24 57	91.46 187	88.04 344	95.80 252	79.67 284	97.48 361	87.02 308	84.54 382	95.31 332

DU-MVS		92.90 208	92.04 217	95.49 182	94.95 331	92.83 85	97.16 189	98.24 57	93.02 131	90.13 278	95.71 259	83.47 201	97.85 324	91.71 199	83.93 388	95.78 303

9.14			96.75 55		98.93 52		97.73 108	98.23 60	91.28 196	97.88 48	98.44 57	93.00 26	99.65 72	95.76 98	99.47 40

reproduce_model		97.51 16	97.51 16	97.50 50	98.99 48	93.01 78	97.79 100	98.21 61	95.73 21	97.99 44	99.03 13	92.63 36	99.82 28	97.80 28	99.42 51	99.67 14

D2MVS		91.30 282	90.95 260	92.35 335	94.71 346	85.52 337	96.18 283	98.21 61	88.89 286	86.60 373	93.82 357	79.92 280	97.95 313	89.29 257	90.95 307	93.56 398

reproduce-ours		97.53 14	97.51 16	97.60 47	98.97 49	93.31 69	97.71 113	98.20 63	95.80 18	97.88 48	98.98 16	92.91 27	99.81 30	97.68 30	99.43 48	99.67 14

our_new_method		97.53 14	97.51 16	97.60 47	98.97 49	93.31 69	97.71 113	98.20 63	95.80 18	97.88 48	98.98 16	92.91 27	99.81 30	97.68 30	99.43 48	99.67 14

SDMVSNet		94.17 147	93.61 154	95.86 155	98.09 109	91.37 145	97.35 168	98.20 63	93.18 125	91.79 239	97.28 161	79.13 292	98.93 189	94.61 137	92.84 273	97.28 253

XVS		97.18 28	96.96 39	97.81 28	99.38 14	94.03 50	98.59 13	98.20 63	94.85 50	96.59 92	98.29 77	91.70 53	99.80 35	95.66 100	99.40 56	99.62 22

X-MVStestdata		91.71 254	89.67 320	97.81 28	99.38 14	94.03 50	98.59 13	98.20 63	94.85 50	96.59 92	32.69 458	91.70 53	99.80 35	95.66 100	99.40 56	99.62 22

ACMMP_NAP		97.20 27	96.86 43	98.23 11	99.09 36	95.16 22	97.60 131	98.19 68	92.82 144	97.93 47	98.74 39	91.60 56	99.86 9	96.26 72	99.52 30	99.67 14

CP-MVSNet		91.89 250	91.24 249	93.82 279	95.05 327	88.57 253	97.82 94	98.19 68	91.70 176	88.21 339	95.76 257	81.96 241	97.52 359	87.86 283	84.65 376	95.37 328

ZNCC-MVS		96.96 40	96.67 58	97.85 25	99.37 16	94.12 46	98.49 20	98.18 70	92.64 150	96.39 105	98.18 84	91.61 55	99.88 4	95.59 110	99.55 26	99.57 31

SMA-MVS		97.35 21	97.03 34	98.30 8	99.06 40	95.42 10	97.94 76	98.18 70	90.57 234	98.85 24	98.94 19	93.33 23	99.83 26	96.72 60	99.68 4	99.63 21
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		91.20 287	90.44 283	93.48 298	94.49 354	87.91 278	97.76 102	98.18 70	91.29 193	87.78 348	95.74 258	80.35 271	97.33 372	85.46 332	82.96 398	95.19 343

DELS-MVS		96.61 65	96.38 74	97.30 59	97.79 133	93.19 74	95.96 294	98.18 70	95.23 32	95.87 125	97.65 133	91.45 58	99.70 65	95.87 92	99.44 47	99.00 102
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		89.70 339	88.40 345	93.60 291	95.15 322	90.10 197	97.56 136	98.16 74	87.28 339	86.16 379	94.63 312	77.57 320	98.05 293	74.48 418	84.59 380	92.65 411

VNet		95.89 92	95.45 95	97.21 67	98.07 113	92.94 81	97.50 145	98.15 75	93.87 94	97.52 55	97.61 139	85.29 169	99.53 105	95.81 97	95.27 226	99.16 80

DeepPCF-MVS	93.97 1	96.61 65	97.09 27	95.15 196	98.09 109	86.63 310	96.00 292	98.15 75	95.43 25	97.95 46	98.56 44	93.40 21	99.36 130	96.77 57	99.48 39	99.45 54

SD-MVS		97.41 19	97.53 14	97.06 78	98.57 74	94.46 34	97.92 79	98.14 77	94.82 54	99.01 14	98.55 46	94.18 14	97.41 368	96.94 52	99.64 14	99.32 69
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 48	96.52 64	97.82 27	99.36 20	94.14 45	98.29 30	98.13 78	92.72 147	96.70 84	98.06 91	91.35 62	99.86 9	94.83 127	99.28 68	99.47 53

UA-Net		95.95 89	95.53 91	97.20 68	97.67 140	92.98 80	97.65 122	98.13 78	94.81 56	96.61 90	98.35 65	88.87 99	99.51 110	90.36 232	97.35 166	99.11 88

QAPM		93.45 184	92.27 211	96.98 81	96.77 209	92.62 94	98.39 25	98.12 80	84.50 384	88.27 337	97.77 122	82.39 233	99.81 30	85.40 333	98.81 108	98.51 159

Vis-MVSNet		95.23 112	94.81 115	96.51 105	97.18 168	91.58 136	98.26 35	98.12 80	94.38 81	94.90 153	98.15 86	82.28 234	98.92 191	91.45 206	98.58 120	99.01 99
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 211	91.68 232	96.40 115	95.34 305	92.73 90	98.27 33	98.12 80	84.86 379	85.78 381	97.75 123	78.89 302	99.74 52	87.50 298	98.65 115	96.73 270

TranMVSNet+NR-MVSNet		92.50 220	91.63 233	95.14 197	94.76 342	92.07 115	97.53 142	98.11 83	92.90 141	89.56 300	96.12 236	83.16 208	97.60 351	89.30 256	83.20 397	95.75 307

CPTT-MVS		95.57 102	95.19 105	96.70 86	99.27 28	91.48 140	98.33 27	98.11 83	87.79 324	95.17 148	98.03 94	87.09 140	99.61 83	93.51 158	99.42 51	99.02 96

APD-MVS		96.95 41	96.60 60	98.01 20	99.03 43	94.93 27	97.72 111	98.10 85	91.50 185	98.01 43	98.32 73	92.33 42	99.58 91	94.85 125	99.51 33	99.53 43
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 46	96.60 60	97.64 45	99.40 11	93.44 62	98.50 19	98.09 86	93.27 119	95.95 123	98.33 71	91.04 70	99.88 4	95.20 114	99.57 25	99.60 26

ZD-MVS					99.05 41	94.59 32		98.08 87	89.22 272	97.03 74	98.10 87	92.52 39	99.65 72	94.58 139	99.31 66

MTGPA								98.08 87

MTAPA		97.08 33	96.78 53	97.97 23	99.37 16	94.42 36	97.24 178	98.08 87	95.07 41	96.11 115	98.59 43	90.88 75	99.90 2	96.18 84	99.50 35	99.58 30

CNVR-MVS		97.68 6	97.44 20	98.37 7	98.90 55	95.86 6	97.27 176	98.08 87	95.81 17	97.87 51	98.31 74	94.26 13	99.68 68	97.02 51	99.49 38	99.57 31

DP-MVS Recon		95.68 97	95.12 109	97.37 56	99.19 33	94.19 42	97.03 196	98.08 87	88.35 306	95.09 150	97.65 133	89.97 86	99.48 117	92.08 191	98.59 119	98.44 170

SR-MVS		97.01 38	96.86 43	97.47 52	99.09 36	93.27 71	97.98 66	98.07 92	93.75 97	97.45 57	98.48 54	91.43 60	99.59 88	96.22 75	99.27 69	99.54 40

MCST-MVS		97.18 28	96.84 45	98.20 14	99.30 26	95.35 15	97.12 192	98.07 92	93.54 107	96.08 117	97.69 128	93.86 16	99.71 60	96.50 67	99.39 58	99.55 38

NR-MVSNet		92.34 229	91.27 248	95.53 179	94.95 331	93.05 77	97.39 164	98.07 92	92.65 149	84.46 392	95.71 259	85.00 175	97.77 335	89.71 244	83.52 394	95.78 303

MP-MVS-pluss		96.70 59	96.27 77	97.98 22	99.23 32	94.71 29	96.96 207	98.06 95	90.67 224	95.55 139	98.78 37	91.07 69	99.86 9	96.58 65	99.55 26	99.38 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 52	96.71 57	97.12 72	99.01 47	92.31 106	97.98 66	98.06 95	93.11 129	97.44 58	98.55 46	90.93 73	99.55 101	96.06 85	99.25 73	99.51 44

MP-MVS		96.77 54	96.45 71	97.72 39	99.39 13	93.80 54	98.41 24	98.06 95	93.37 115	95.54 141	98.34 68	90.59 79	99.88 4	94.83 127	99.54 28	99.49 49
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 68	96.27 77	97.22 66	99.32 24	92.74 89	98.74 10	98.06 95	90.57 234	96.77 81	98.35 65	90.21 82	99.53 105	94.80 130	99.63 16	99.38 65

HPM-MVS		96.69 61	96.45 71	97.40 55	99.36 20	93.11 76	98.87 6	98.06 95	91.17 203	96.40 104	97.99 98	90.99 71	99.58 91	95.61 107	99.61 18	99.49 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 138	93.80 147	96.64 88	97.07 174	91.97 120	96.32 271	98.06 95	88.94 284	94.50 165	96.78 194	84.60 181	99.27 140	91.90 192	96.02 203	98.68 145

DeepC-MVS	93.07 3	96.06 83	95.66 88	97.29 60	97.96 121	93.17 75	97.30 174	98.06 95	93.92 92	93.38 199	98.66 40	86.83 142	99.73 54	95.60 109	99.22 75	98.96 107
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 25	97.03 34	98.11 17	98.77 58	95.06 25	97.34 169	98.04 102	95.96 12	97.09 72	97.88 109	93.18 25	99.71 60	95.84 96	99.17 84	99.56 35

DeepC-MVS_fast	93.89 2	96.93 43	96.64 59	97.78 32	98.64 69	94.30 37	97.41 159	98.04 102	94.81 56	96.59 92	98.37 63	91.24 65	99.64 80	95.16 116	99.52 30	99.42 60
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 45	96.80 51	97.11 74	99.02 44	92.34 104	97.98 66	98.03 104	93.52 110	97.43 60	98.51 49	91.40 61	99.56 99	96.05 86	99.26 71	99.43 58

RE-MVS-def			96.72 56		99.02 44	92.34 104	97.98 66	98.03 104	93.52 110	97.43 60	98.51 49	90.71 77		96.05 86	99.26 71	99.43 58

RPMNet		88.98 345	87.05 359	94.77 223	94.45 356	87.19 294	90.23 431	98.03 104	77.87 431	92.40 217	87.55 438	80.17 275	99.51 110	68.84 438	93.95 259	97.60 238

save fliter					98.91 54	94.28 38	97.02 198	98.02 107	95.35 28

TEST9					98.70 61	94.19 42	96.41 258	98.02 107	88.17 310	96.03 118	97.56 145	92.74 33	99.59 88

train_agg		96.30 79	95.83 87	97.72 39	98.70 61	94.19 42	96.41 258	98.02 107	88.58 297	96.03 118	97.56 145	92.73 34	99.59 88	95.04 118	99.37 62	99.39 63

test_8					98.67 63	94.06 49	96.37 265	98.01 110	88.58 297	95.98 122	97.55 147	92.73 34	99.58 91

agg_prior					98.67 63	93.79 55		98.00 111		95.68 135			99.57 98

test_prior				97.23 65	98.67 63	92.99 79		98.00 111					99.41 125			99.29 70

WR-MVS		92.34 229	91.53 237	94.77 223	95.13 324	90.83 171	96.40 262	97.98 113	91.88 171	89.29 309	95.54 270	82.50 229	97.80 331	89.79 243	85.27 367	95.69 310

HPM-MVS++		97.34 22	96.97 37	98.47 5	99.08 38	96.16 4	97.55 141	97.97 114	95.59 22	96.61 90	97.89 107	92.57 38	99.84 23	95.95 91	99.51 33	99.40 61

CANet		96.39 74	96.02 82	97.50 50	97.62 147	93.38 64	97.02 198	97.96 115	95.42 26	94.86 154	97.81 119	87.38 136	99.82 28	96.88 54	99.20 81	99.29 70

114514_t		93.95 162	93.06 177	96.63 92	99.07 39	91.61 133	97.46 156	97.96 115	77.99 429	93.00 208	97.57 143	86.14 155	99.33 132	89.22 260	99.15 88	98.94 111

IU-MVS					99.42 7	95.39 11		97.94 117	90.40 240	98.94 16				97.41 46	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 63	96.94 1		97.93 118					99.86 9	97.68 30	99.67 6	99.77 2

No_MVS				98.86 1	98.67 63	96.94 1		97.93 118					99.86 9	97.68 30	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 78	96.44 73	96.00 147	97.30 161	90.37 192	97.53 142	97.92 120	96.52 8	99.14 12	99.08 7	83.21 206	99.74 52	99.22 8	98.06 143	97.88 218

Anonymous20231211		90.63 311	89.42 327	94.27 253	98.24 94	89.19 240	98.05 58	97.89 121	79.95 421	88.25 338	94.96 293	72.56 361	98.13 276	89.70 245	85.14 369	95.49 314

原ACMM1				96.38 118	98.59 71	91.09 161		97.89 121	87.41 335	95.22 147	97.68 129	90.25 81	99.54 103	87.95 282	99.12 93	98.49 162

CDPH-MVS		95.97 88	95.38 100	97.77 34	98.93 52	94.44 35	96.35 266	97.88 123	86.98 343	96.65 88	97.89 107	91.99 48	99.47 118	92.26 180	99.46 41	99.39 63

test11								97.88 123

EIA-MVS		95.53 103	95.47 94	95.71 169	97.06 177	89.63 213	97.82 94	97.87 125	93.57 103	93.92 181	95.04 290	90.61 78	98.95 186	94.62 136	98.68 113	98.54 155

CS-MVS		96.86 46	97.06 29	96.26 128	98.16 105	91.16 159	99.09 3	97.87 125	95.30 30	97.06 73	98.03 94	91.72 51	98.71 222	97.10 49	99.17 84	98.90 120

无先验							95.79 305	97.87 125	83.87 392				99.65 72	87.68 292		98.89 124

3Dnovator+	91.43 4	95.40 104	94.48 131	98.16 16	96.90 191	95.34 16	98.48 21	97.87 125	94.65 67	88.53 329	98.02 96	83.69 197	99.71 60	93.18 166	98.96 103	99.44 56

VPNet		92.23 237	91.31 245	94.99 206	95.56 289	90.96 165	97.22 184	97.86 129	92.96 138	90.96 261	96.62 211	75.06 341	98.20 270	91.90 192	83.65 393	95.80 301

test_vis1_n_1920		94.17 147	94.58 124	92.91 319	97.42 159	82.02 388	97.83 92	97.85 130	94.68 64	98.10 41	98.49 51	70.15 380	99.32 134	97.91 27	98.82 107	97.40 247

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 130	94.92 47	98.73 27	98.87 28	95.08 8	99.84 23	97.52 39	99.67 6	99.48 51
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 18	97.33 23	97.69 42	99.25 29	94.24 41	98.07 56	97.85 130	93.72 98	98.57 31	98.35 65	93.69 18	99.40 126	97.06 50	99.46 41	99.44 56
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 44	97.04 33	96.45 112	98.29 88	91.66 132	99.03 4	97.85 130	95.84 15	96.90 76	97.97 100	91.24 65	98.75 214	96.92 53	99.33 64	98.94 111

test_fmvsmconf0.01_n		96.15 82	95.85 86	97.03 79	92.66 407	91.83 124	97.97 72	97.84 134	95.57 23	97.53 54	99.00 14	84.20 190	99.76 47	98.82 20	99.08 95	99.48 51

GDP-MVS		95.62 99	95.13 107	97.09 75	96.79 203	93.26 72	97.89 83	97.83 135	93.58 102	96.80 78	97.82 117	83.06 213	99.16 154	94.40 141	97.95 149	98.87 126

balanced_conf03		96.84 50	96.89 42	96.68 87	97.63 146	92.22 109	98.17 49	97.82 136	94.44 76	98.23 39	97.36 156	90.97 72	99.22 144	97.74 29	99.66 10	98.61 148

AdaColmap		94.34 142	93.68 152	96.31 122	98.59 71	91.68 131	96.59 249	97.81 137	89.87 250	92.15 227	97.06 177	83.62 200	99.54 103	89.34 255	98.07 142	97.70 231

MVSMamba_PlusPlus		96.51 68	96.48 66	96.59 96	98.07 113	91.97 120	98.14 50	97.79 138	90.43 238	97.34 63	97.52 148	91.29 64	99.19 147	98.12 25	99.64 14	98.60 149

KinetiMVS		95.26 109	94.75 119	96.79 84	96.99 186	92.05 116	97.82 94	97.78 139	94.77 60	96.46 101	97.70 126	80.62 265	99.34 131	92.37 179	98.28 133	98.97 104

mamv4		94.66 135	96.10 81	90.37 388	98.01 116	73.41 438	96.82 220	97.78 139	89.95 249	94.52 164	97.43 152	92.91 27	99.09 167	98.28 24	99.16 87	98.60 149

ETV-MVS		96.02 85	95.89 85	96.40 115	97.16 169	92.44 101	97.47 154	97.77 141	94.55 70	96.48 99	94.51 318	91.23 67	98.92 191	95.65 103	98.19 137	97.82 226

新几何1				97.32 58	98.60 70	93.59 59		97.75 142	81.58 412	95.75 130	97.85 113	90.04 84	99.67 70	86.50 314	99.13 91	98.69 144

旧先验1					98.38 84	93.38 64		97.75 142			98.09 89	92.30 45			99.01 101	99.16 80

EC-MVSNet		96.42 72	96.47 67	96.26 128	97.01 184	91.52 138	98.89 5	97.75 142	94.42 77	96.64 89	97.68 129	89.32 92	98.60 234	97.45 43	99.11 94	98.67 146

EI-MVSNet-Vis-set		96.51 68	96.47 67	96.63 92	98.24 94	91.20 153	96.89 212	97.73 145	94.74 62	96.49 98	98.49 51	90.88 75	99.58 91	96.44 69	98.32 131	99.13 84

PAPM_NR		95.01 118	94.59 123	96.26 128	98.89 56	90.68 178	97.24 178	97.73 145	91.80 172	92.93 213	96.62 211	89.13 95	99.14 159	89.21 261	97.78 153	98.97 104

Anonymous20240529		91.98 246	90.73 273	95.73 167	98.14 106	89.40 227	97.99 63	97.72 147	79.63 423	93.54 192	97.41 154	69.94 382	99.56 99	91.04 214	91.11 303	98.22 188

CHOSEN 280x420		93.12 196	92.72 194	94.34 247	96.71 213	87.27 290	90.29 430	97.72 147	86.61 350	91.34 250	95.29 278	84.29 189	98.41 250	93.25 164	98.94 104	97.35 250

EI-MVSNet-UG-set		96.34 77	96.30 76	96.47 109	98.20 100	90.93 167	96.86 215	97.72 147	94.67 65	96.16 114	98.46 55	90.43 80	99.58 91	96.23 74	97.96 148	98.90 120

LS3D		93.57 179	92.61 199	96.47 109	97.59 150	91.61 133	97.67 118	97.72 147	85.17 374	90.29 272	98.34 68	84.60 181	99.73 54	83.85 356	98.27 134	98.06 207

PAPR		94.18 146	93.42 168	96.48 108	97.64 144	91.42 144	95.55 319	97.71 151	88.99 281	92.34 223	95.82 251	89.19 93	99.11 162	86.14 320	97.38 164	98.90 120

UGNet		94.04 157	93.28 171	96.31 122	96.85 195	91.19 154	97.88 84	97.68 152	94.40 79	93.00 208	96.18 231	73.39 358	99.61 83	91.72 198	98.46 125	98.13 196
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				95.46 186	98.18 104	88.90 246		97.66 153	82.73 403	97.03 74	98.07 90	90.06 83	98.85 198	89.67 246	98.98 102	98.64 147

test12				97.65 43	98.46 75	94.26 39		97.66 153		95.52 142		90.89 74	99.46 119		99.25 73	99.22 77

DTE-MVSNet		90.56 312	89.75 318	93.01 315	93.95 369	87.25 291	97.64 126	97.65 155	90.74 219	87.12 361	95.68 262	79.97 279	97.00 385	83.33 357	81.66 404	94.78 370

TAPA-MVS	90.10 7	92.30 232	91.22 251	95.56 176	98.33 86	89.60 215	96.79 223	97.65 155	81.83 409	91.52 245	97.23 166	87.94 118	98.91 193	71.31 433	98.37 129	98.17 194
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 197	92.45 207	95.05 201	98.09 109	89.21 237	96.89 212	97.64 157	93.18 125	91.79 239	97.28 161	75.35 340	98.65 229	88.99 266	92.84 273	97.28 253

test_cas_vis1_n_1920		94.48 140	94.55 128	94.28 252	96.78 207	86.45 315	97.63 128	97.64 157	93.32 118	97.68 53	98.36 64	73.75 356	99.08 170	96.73 59	99.05 97	97.31 252

NormalMVS		96.36 76	96.11 80	97.12 72	99.37 16	92.90 83	97.99 63	97.63 159	95.92 13	96.57 95	97.93 102	85.34 167	99.50 113	94.99 121	99.21 76	98.97 104

Elysia		94.00 159	93.12 174	96.64 88	96.08 268	92.72 91	97.50 145	97.63 159	91.15 205	94.82 155	97.12 172	74.98 343	99.06 176	90.78 219	98.02 144	98.12 198

StellarMVS		94.00 159	93.12 174	96.64 88	96.08 268	92.72 91	97.50 145	97.63 159	91.15 205	94.82 155	97.12 172	74.98 343	99.06 176	90.78 219	98.02 144	98.12 198

cdsmvs_eth3d_5k		23.24 428	30.99 430	0.00 446	0.00 469	0.00 471	0.00 457	97.63 159	0.00 464	0.00 465	96.88 190	84.38 186	0.00 465	0.00 464	0.00 463	0.00 461

DPM-MVS		95.69 96	94.92 113	98.01 20	98.08 112	95.71 9	95.27 335	97.62 163	90.43 238	95.55 139	97.07 176	91.72 51	99.50 113	89.62 248	98.94 104	98.82 132

sasdasda		96.02 85	95.45 95	97.75 36	97.59 150	95.15 23	98.28 31	97.60 164	94.52 72	96.27 109	96.12 236	87.65 124	99.18 150	96.20 80	94.82 235	98.91 117

canonicalmvs		96.02 85	95.45 95	97.75 36	97.59 150	95.15 23	98.28 31	97.60 164	94.52 72	96.27 109	96.12 236	87.65 124	99.18 150	96.20 80	94.82 235	98.91 117

test222					98.24 94	92.21 110	95.33 330	97.60 164	79.22 425	95.25 145	97.84 115	88.80 101			99.15 88	98.72 141

cascas		91.20 287	90.08 300	94.58 233	94.97 329	89.16 241	93.65 395	97.59 167	79.90 422	89.40 304	92.92 383	75.36 339	98.36 258	92.14 185	94.75 238	96.23 280

h-mvs33		94.15 149	93.52 160	96.04 141	97.81 132	90.22 196	97.62 130	97.58 168	95.19 33	96.74 82	97.45 149	83.67 198	99.61 83	95.85 94	79.73 411	98.29 184

MGCFI-Net		95.94 90	95.40 99	97.56 49	97.59 150	94.62 31	98.21 43	97.57 169	94.41 78	96.17 113	96.16 234	87.54 129	99.17 152	96.19 82	94.73 240	98.91 117

MVSFormer		95.37 105	95.16 106	95.99 148	96.34 246	91.21 151	98.22 41	97.57 169	91.42 189	96.22 111	97.32 157	86.20 153	97.92 318	94.07 145	99.05 97	98.85 128

test_djsdf		93.07 199	92.76 189	94.00 264	93.49 386	88.70 250	98.22 41	97.57 169	91.42 189	90.08 284	95.55 269	82.85 220	97.92 318	94.07 145	91.58 294	95.40 325

OMC-MVS		95.09 117	94.70 120	96.25 131	98.46 75	91.28 147	96.43 256	97.57 169	92.04 167	94.77 159	97.96 101	87.01 141	99.09 167	91.31 208	96.77 185	98.36 177

PS-MVSNAJss		93.74 172	93.51 161	94.44 241	93.91 371	89.28 235	97.75 104	97.56 173	92.50 151	89.94 286	96.54 214	88.65 104	98.18 273	93.83 154	90.90 308	95.86 295

casdiffmvs_mvg		95.81 95	95.57 89	96.51 105	96.87 192	91.49 139	97.50 145	97.56 173	93.99 90	95.13 149	97.92 105	87.89 119	98.78 207	95.97 90	97.33 167	99.26 74
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		92.42 225	91.89 225	94.03 263	93.33 394	88.50 257	97.73 108	97.53 175	92.00 169	88.85 321	96.50 216	75.62 338	98.11 280	93.88 152	91.56 295	95.48 315

mvs_tets		92.31 231	91.76 228	93.94 272	93.41 391	88.29 262	97.63 128	97.53 175	92.04 167	88.76 324	96.45 218	74.62 348	98.09 285	93.91 150	91.48 296	95.45 320

dcpmvs_2		96.37 75	97.05 32	94.31 250	98.96 51	84.11 362	97.56 136	97.51 177	93.92 92	97.43 60	98.52 48	92.75 32	99.32 134	97.32 48	99.50 35	99.51 44

HQP_MVS		93.78 171	93.43 166	94.82 216	96.21 250	89.99 201	97.74 106	97.51 177	94.85 50	91.34 250	96.64 204	81.32 253	98.60 234	93.02 172	92.23 282	95.86 295

plane_prior5								97.51 177					98.60 234	93.02 172	92.23 282	95.86 295

viewmanbaseed2359cas		95.24 111	95.02 111	95.91 151	96.87 192	89.98 203	96.82 220	97.49 180	92.26 156	95.47 143	97.82 117	86.47 147	98.69 223	94.80 130	97.20 175	99.06 94

reproduce_monomvs		91.30 282	91.10 255	91.92 349	96.82 200	82.48 382	97.01 201	97.49 180	94.64 68	88.35 332	95.27 281	70.53 375	98.10 281	95.20 114	84.60 379	95.19 343

PS-MVSNAJ		95.37 105	95.33 102	95.49 182	97.35 160	90.66 179	95.31 332	97.48 182	93.85 95	96.51 97	95.70 261	88.65 104	99.65 72	94.80 130	98.27 134	96.17 284

API-MVS		94.84 128	94.49 130	95.90 152	97.90 127	92.00 119	97.80 98	97.48 182	89.19 273	94.81 157	96.71 197	88.84 100	99.17 152	88.91 268	98.76 111	96.53 273

MG-MVS		95.61 100	95.38 100	96.31 122	98.42 79	90.53 181	96.04 289	97.48 182	93.47 112	95.67 136	98.10 87	89.17 94	99.25 141	91.27 209	98.77 110	99.13 84

MAR-MVS		94.22 145	93.46 163	96.51 105	98.00 118	92.19 113	97.67 118	97.47 185	88.13 314	93.00 208	95.84 249	84.86 179	99.51 110	87.99 281	98.17 139	97.83 225
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		92.98 203	92.53 203	94.32 248	96.12 265	89.20 238	95.28 333	97.47 185	92.66 148	89.90 287	95.62 265	80.58 266	98.40 251	92.73 177	92.40 280	95.38 327
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 280	90.22 296	94.68 227	94.86 338	87.86 279	97.23 182	97.46 187	87.99 315	89.90 287	96.92 188	66.35 410	98.23 267	90.30 233	90.99 306	97.96 212

nrg030		94.05 156	93.31 170	96.27 127	95.22 316	94.59 32	98.34 26	97.46 187	92.93 139	91.21 259	96.64 204	87.23 139	98.22 268	94.99 121	85.80 359	95.98 294

XVG-OURS		93.72 173	93.35 169	94.80 221	97.07 174	88.61 251	94.79 350	97.46 187	91.97 170	93.99 178	97.86 112	81.74 247	98.88 195	92.64 178	92.67 278	96.92 265

LPG-MVS_test		92.94 206	92.56 200	94.10 258	96.16 260	88.26 264	97.65 122	97.46 187	91.29 193	90.12 280	97.16 169	79.05 295	98.73 217	92.25 182	91.89 290	95.31 332

LGP-MVS_train				94.10 258	96.16 260	88.26 264		97.46 187	91.29 193	90.12 280	97.16 169	79.05 295	98.73 217	92.25 182	91.89 290	95.31 332

MVS		91.71 254	90.44 283	95.51 180	95.20 318	91.59 135	96.04 289	97.45 192	73.44 439	87.36 357	95.60 266	85.42 166	99.10 164	85.97 325	97.46 159	95.83 299

XVG-OURS-SEG-HR		93.86 168	93.55 156	94.81 218	97.06 177	88.53 256	95.28 333	97.45 192	91.68 177	94.08 177	97.68 129	82.41 232	98.90 194	93.84 153	92.47 279	96.98 261

baseline		95.58 101	95.42 98	96.08 137	96.78 207	90.41 187	97.16 189	97.45 192	93.69 101	95.65 137	97.85 113	87.29 137	98.68 225	95.66 100	97.25 173	99.13 84

ab-mvs		93.57 179	92.55 201	96.64 88	97.28 163	91.96 122	95.40 326	97.45 192	89.81 255	93.22 205	96.28 227	79.62 286	99.46 119	90.74 222	93.11 270	98.50 160

xiu_mvs_v2_base		95.32 107	95.29 103	95.40 187	97.22 165	90.50 182	95.44 325	97.44 196	93.70 100	96.46 101	96.18 231	88.59 108	99.53 105	94.79 133	97.81 152	96.17 284

1314		92.81 215	92.03 218	95.14 197	95.33 308	89.52 222	96.04 289	97.44 196	87.72 328	86.25 378	95.33 277	83.84 195	98.79 206	89.26 258	97.05 180	97.11 259

casdiffmvs		95.64 98	95.49 92	96.08 137	96.76 212	90.45 184	97.29 175	97.44 196	94.00 89	95.46 144	97.98 99	87.52 132	98.73 217	95.64 104	97.33 167	99.08 91
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		92.16 239	91.23 250	94.95 212	94.75 343	90.94 166	97.47 154	97.43 199	89.14 274	88.90 317	96.43 219	79.71 283	98.24 266	89.56 249	87.68 340	95.67 311

anonymousdsp		92.16 239	91.55 236	93.97 268	92.58 409	89.55 219	97.51 144	97.42 200	89.42 267	88.40 331	94.84 300	80.66 264	97.88 323	91.87 194	91.28 300	94.48 378

Effi-MVS+		94.93 123	94.45 132	96.36 120	96.61 217	91.47 141	96.41 258	97.41 201	91.02 211	94.50 165	95.92 245	87.53 130	98.78 207	93.89 151	96.81 184	98.84 131

RRT-MVS		94.51 138	94.35 135	94.98 208	96.40 241	86.55 313	97.56 136	97.41 201	93.19 123	94.93 152	97.04 178	79.12 293	99.30 138	96.19 82	97.32 169	99.09 90

HQP3-MVS								97.39 203							92.10 287

HQP-MVS		93.19 193	92.74 192	94.54 236	95.86 274	89.33 231	96.65 240	97.39 203	93.55 104	90.14 274	95.87 247	80.95 257	98.50 244	92.13 188	92.10 287	95.78 303

PLC	91.00 6	94.11 153	93.43 166	96.13 136	98.58 73	91.15 160	96.69 236	97.39 203	87.29 338	91.37 249	96.71 197	88.39 109	99.52 109	87.33 301	97.13 178	97.73 229
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 304	89.86 311	93.45 300	93.54 383	87.60 285	97.70 116	97.37 206	88.85 287	87.65 350	94.08 348	81.08 256	98.10 281	84.68 342	83.79 392	94.66 375

UnsupCasMVSNet_eth		85.99 381	84.45 385	90.62 384	89.97 427	82.40 385	93.62 396	97.37 206	89.86 251	78.59 429	92.37 393	65.25 418	95.35 419	82.27 370	70.75 437	94.10 389

ACMM	89.79 8	92.96 204	92.50 205	94.35 245	96.30 248	88.71 249	97.58 132	97.36 208	91.40 191	90.53 267	96.65 203	79.77 282	98.75 214	91.24 210	91.64 292	95.59 313
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 118	94.76 116	95.75 164	96.58 220	91.71 128	96.25 276	97.35 209	92.99 132	96.70 84	96.63 208	82.67 224	99.44 122	96.22 75	97.46 159	96.11 290

xiu_mvs_v1_base		95.01 118	94.76 116	95.75 164	96.58 220	91.71 128	96.25 276	97.35 209	92.99 132	96.70 84	96.63 208	82.67 224	99.44 122	96.22 75	97.46 159	96.11 290

xiu_mvs_v1_base_debi		95.01 118	94.76 116	95.75 164	96.58 220	91.71 128	96.25 276	97.35 209	92.99 132	96.70 84	96.63 208	82.67 224	99.44 122	96.22 75	97.46 159	96.11 290

diffmvs		95.25 110	95.13 107	95.63 172	96.43 240	89.34 230	95.99 293	97.35 209	92.83 143	96.31 107	97.37 155	86.44 148	98.67 226	96.26 72	97.19 176	98.87 126
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		94.71 134	94.02 143	96.79 84	97.71 138	92.05 116	96.59 249	97.35 209	90.61 230	94.64 161	96.93 185	86.41 149	99.39 127	91.20 211	94.71 241	98.94 111

mamba_test_0407		94.54 137	94.12 142	95.80 160	96.79 203	90.38 189	96.79 223	97.29 214	91.24 197	93.68 185	97.60 140	85.03 173	98.67 226	92.14 185	96.51 193	98.35 179

mamba_0404		94.73 133	94.31 137	95.98 149	97.05 179	90.90 169	97.01 201	97.29 214	91.24 197	94.17 174	97.60 140	85.03 173	98.76 211	92.14 185	97.30 170	98.29 184

F-COLMAP		93.58 177	92.98 181	95.37 188	98.40 81	88.98 244	97.18 187	97.29 214	87.75 327	90.49 268	97.10 175	85.21 170	99.50 113	86.70 311	96.72 188	97.63 233

VortexMVS		92.88 210	92.64 196	93.58 293	96.58 220	87.53 286	96.93 209	97.28 217	92.78 146	89.75 292	94.99 291	82.73 223	97.76 336	94.60 138	88.16 335	95.46 318

XVG-ACMP-BASELINE		90.93 300	90.21 297	93.09 313	94.31 362	85.89 330	95.33 330	97.26 218	91.06 210	89.38 305	95.44 275	68.61 393	98.60 234	89.46 251	91.05 304	94.79 368

PCF-MVS	89.48 11	91.56 264	89.95 308	96.36 120	96.60 218	92.52 99	92.51 415	97.26 218	79.41 424	88.90 317	96.56 213	84.04 194	99.55 101	77.01 409	97.30 170	97.01 260
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 219	92.14 214	94.05 261	96.40 241	88.20 267	97.36 167	97.25 220	91.52 184	88.30 335	96.64 204	78.46 307	98.72 221	91.86 195	91.48 296	95.23 339
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 177	93.46 163	93.94 272	96.19 254	86.16 324	93.73 390	97.24 221	91.54 180	93.50 194	97.04 178	85.64 163	96.91 388	90.68 224	95.59 217	98.76 134

icg_test_0407		93.94 163	93.75 149	94.49 238	96.19 254	86.16 324	96.35 266	97.24 221	91.54 180	93.50 194	97.04 178	85.64 163	98.54 241	90.68 224	95.59 217	98.76 134

ICG_test_0404		92.44 223	91.92 223	94.00 264	96.19 254	86.16 324	93.84 387	97.24 221	91.54 180	88.17 341	97.04 178	76.96 325	97.09 379	90.68 224	95.59 217	98.76 134

icg_test_0403		93.98 161	93.79 148	94.55 235	96.19 254	86.16 324	96.35 266	97.24 221	91.54 180	93.59 189	97.04 178	85.86 158	98.73 217	90.68 224	95.59 217	98.76 134

OPM-MVS		93.28 189	92.76 189	94.82 216	94.63 349	90.77 174	96.65 240	97.18 225	93.72 98	91.68 243	97.26 164	79.33 290	98.63 231	92.13 188	92.28 281	95.07 346
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 208	92.02 219	95.56 176	98.19 102	90.80 172	95.27 335	97.18 225	87.96 316	91.86 238	95.68 262	80.44 269	98.99 184	84.01 351	97.54 158	96.89 266

alignmvs		95.87 94	95.23 104	97.78 32	97.56 156	95.19 21	97.86 85	97.17 227	94.39 80	96.47 100	96.40 221	85.89 157	99.20 146	96.21 79	95.11 231	98.95 110

MVS_Test		94.89 125	94.62 122	95.68 170	96.83 198	89.55 219	96.70 234	97.17 227	91.17 203	95.60 138	96.11 240	87.87 121	98.76 211	93.01 174	97.17 177	98.72 141

Fast-Effi-MVS+		93.46 183	92.75 191	95.59 175	96.77 209	90.03 198	96.81 222	97.13 229	88.19 309	91.30 253	94.27 336	86.21 152	98.63 231	87.66 293	96.46 199	98.12 198

EI-MVSNet		93.03 201	92.88 185	93.48 298	95.77 280	86.98 299	96.44 254	97.12 230	90.66 226	91.30 253	97.64 136	86.56 144	98.05 293	89.91 239	90.55 312	95.41 322

MVSTER		93.20 192	92.81 188	94.37 244	96.56 224	89.59 216	97.06 195	97.12 230	91.24 197	91.30 253	95.96 243	82.02 240	98.05 293	93.48 159	90.55 312	95.47 317

viewmambaseed2359dif		94.28 143	94.14 140	94.71 226	96.21 250	86.97 300	95.93 296	97.11 232	89.00 280	95.00 151	97.70 126	86.02 156	98.59 238	93.71 156	96.59 192	98.57 153

test_yl		94.78 131	94.23 138	96.43 113	97.74 136	91.22 149	96.85 216	97.10 233	91.23 200	95.71 132	96.93 185	84.30 187	99.31 136	93.10 167	95.12 229	98.75 138

DCV-MVSNet		94.78 131	94.23 138	96.43 113	97.74 136	91.22 149	96.85 216	97.10 233	91.23 200	95.71 132	96.93 185	84.30 187	99.31 136	93.10 167	95.12 229	98.75 138

LTVRE_ROB	88.41 13	90.99 296	89.92 310	94.19 254	96.18 258	89.55 219	96.31 272	97.09 235	87.88 319	85.67 382	95.91 246	78.79 303	98.57 239	81.50 373	89.98 317	94.44 381
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		92.73 217	92.88 185	92.29 339	96.08 268	81.05 396	97.98 66	97.08 236	90.72 221	96.79 80	98.18 84	63.07 422	98.45 248	97.62 37	98.42 128	97.36 248

v10		91.04 294	90.23 294	93.49 297	94.12 365	88.16 270	97.32 172	97.08 236	88.26 308	88.29 336	94.22 341	82.17 237	97.97 305	86.45 315	84.12 386	94.33 384

mamba_0408		93.70 174	92.99 178	95.83 157	96.79 203	90.38 189	88.69 440	97.07 238	90.96 213	93.68 185	97.31 159	84.97 176	98.76 211	90.95 215	96.51 193	98.35 179

mamba_test_0407_2		93.51 182	92.99 178	95.05 201	96.79 203	90.38 189	88.69 440	97.07 238	90.96 213	93.68 185	97.31 159	84.97 176	96.42 399	90.95 215	96.51 193	98.35 179

v144192		91.06 293	90.28 290	93.39 301	93.66 380	87.23 293	96.83 219	97.07 238	87.43 334	89.69 295	94.28 335	81.48 250	98.00 300	87.18 305	84.92 375	94.93 354

v1192		91.07 292	90.23 294	93.58 293	93.70 377	87.82 281	96.73 230	97.07 238	87.77 325	89.58 298	94.32 333	80.90 261	97.97 305	86.52 313	85.48 362	94.95 350

v8		91.29 284	90.53 282	93.57 295	94.15 364	88.12 271	97.34 169	97.06 242	88.99 281	88.32 334	94.26 338	83.08 211	98.01 299	87.62 295	83.92 390	94.57 377

mvs_anonymous		93.82 169	93.74 150	94.06 260	96.44 239	85.41 339	95.81 303	97.05 243	89.85 253	90.09 283	96.36 223	87.44 134	97.75 338	93.97 147	96.69 189	99.02 96

IterMVS-LS		92.29 233	91.94 222	93.34 303	96.25 249	86.97 300	96.57 252	97.05 243	90.67 224	89.50 303	94.80 303	86.59 143	97.64 346	89.91 239	86.11 357	95.40 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 302	90.03 305	93.29 305	93.55 382	86.96 302	96.74 229	97.04 245	87.36 336	89.52 302	94.34 330	80.23 274	97.97 305	86.27 316	85.21 368	94.94 352

CDS-MVSNet		94.14 152	93.54 157	95.93 150	96.18 258	91.46 142	96.33 270	97.04 245	88.97 283	93.56 190	96.51 215	87.55 128	97.89 322	89.80 242	95.95 205	98.44 170
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 338	89.26 331	91.19 373	95.16 319	80.29 407	94.53 357	97.03 247	91.79 173	88.86 320	94.10 345	69.94 382	97.82 328	85.29 334	86.66 353	95.45 320

v1144		91.37 277	90.60 278	93.68 288	93.89 372	88.23 266	96.84 218	97.03 247	88.37 305	89.69 295	94.39 325	82.04 239	97.98 302	87.80 285	85.37 364	94.84 360

v1240		90.70 308	89.85 312	93.23 307	93.51 385	86.80 303	96.61 246	97.02 249	87.16 341	89.58 298	94.31 334	79.55 287	97.98 302	85.52 331	85.44 363	94.90 357

EPP-MVSNet		95.22 113	95.04 110	95.76 162	97.49 157	89.56 218	98.67 11	97.00 250	90.69 222	94.24 171	97.62 138	89.79 89	98.81 204	93.39 163	96.49 197	98.92 116

V42		91.58 263	90.87 262	93.73 283	94.05 368	88.50 257	97.32 172	96.97 251	88.80 293	89.71 293	94.33 331	82.54 228	98.05 293	89.01 265	85.07 371	94.64 376

test_fmvs1		93.21 191	93.53 158	92.25 342	96.55 226	81.20 395	97.40 163	96.96 252	90.68 223	96.80 78	98.04 93	69.25 388	98.40 251	97.58 38	98.50 121	97.16 258

FMVSNet2		91.31 281	90.08 300	94.99 206	96.51 232	92.21 110	97.41 159	96.95 253	88.82 290	88.62 326	94.75 305	73.87 352	97.42 367	85.20 337	88.55 332	95.35 329

ACMH	87.59 16	90.53 313	89.42 327	93.87 277	96.21 250	87.92 276	97.24 178	96.94 254	88.45 303	83.91 402	96.27 228	71.92 364	98.62 233	84.43 345	89.43 323	95.05 348
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 278	90.27 291	94.59 229	96.51 232	91.18 156	97.50 145	96.93 255	88.82 290	89.35 306	94.51 318	73.87 352	97.29 374	86.12 321	88.82 327	95.31 332

test1		91.35 278	90.27 291	94.59 229	96.51 232	91.18 156	97.50 145	96.93 255	88.82 290	89.35 306	94.51 318	73.87 352	97.29 374	86.12 321	88.82 327	95.31 332

FMVSNet3		91.78 252	90.69 276	95.03 204	96.53 229	92.27 108	97.02 198	96.93 255	89.79 256	89.35 306	94.65 311	77.01 323	97.47 362	86.12 321	88.82 327	95.35 329

FMVSNet1		89.88 333	88.31 346	94.59 229	95.41 298	91.18 156	97.50 145	96.93 255	86.62 349	87.41 355	94.51 318	65.94 415	97.29 374	83.04 360	87.43 343	95.31 332

GeoE		93.89 166	93.28 171	95.72 168	96.96 189	89.75 211	98.24 39	96.92 259	89.47 264	92.12 229	97.21 167	84.42 185	98.39 256	87.71 288	96.50 196	99.01 99

SymmetryMVS		95.94 90	95.54 90	97.15 70	97.85 129	92.90 83	97.99 63	96.91 260	95.92 13	96.57 95	97.93 102	85.34 167	99.50 113	94.99 121	96.39 200	99.05 95

miper_enhance_ethall		91.54 267	91.01 258	93.15 311	95.35 304	87.07 298	93.97 379	96.90 261	86.79 347	89.17 313	93.43 377	86.55 145	97.64 346	89.97 238	86.93 348	94.74 372

eth_miper_zixun_eth		91.02 295	90.59 279	92.34 337	95.33 308	84.35 358	94.10 376	96.90 261	88.56 299	88.84 322	94.33 331	84.08 192	97.60 351	88.77 271	84.37 384	95.06 347

TAMVS		94.01 158	93.46 163	95.64 171	96.16 260	90.45 184	96.71 233	96.89 263	89.27 271	93.46 197	96.92 188	87.29 137	97.94 315	88.70 273	95.74 211	98.53 156

miper_ehance_all_eth		91.59 261	91.13 254	92.97 317	95.55 290	86.57 311	94.47 360	96.88 264	87.77 325	88.88 319	94.01 350	86.22 151	97.54 355	89.49 250	86.93 348	94.79 368

v2v482		91.59 261	90.85 265	93.80 280	93.87 373	88.17 269	96.94 208	96.88 264	89.54 261	89.53 301	94.90 297	81.70 248	98.02 298	89.25 259	85.04 373	95.20 340

CNLPA		94.28 143	93.53 158	96.52 101	98.38 84	92.55 98	96.59 249	96.88 264	90.13 246	91.91 235	97.24 165	85.21 170	99.09 167	87.64 294	97.83 151	97.92 215

PAPM		91.52 268	90.30 289	95.20 194	95.30 311	89.83 209	93.38 401	96.85 267	86.26 357	88.59 327	95.80 252	84.88 178	98.15 275	75.67 414	95.93 206	97.63 233

c3_l		91.38 275	90.89 261	92.88 321	95.58 288	86.30 318	94.68 352	96.84 268	88.17 310	88.83 323	94.23 339	85.65 162	97.47 362	89.36 254	84.63 377	94.89 358

pm-mvs1		90.72 307	89.65 322	93.96 269	94.29 363	89.63 213	97.79 100	96.82 269	89.07 276	86.12 380	95.48 274	78.61 305	97.78 333	86.97 309	81.67 403	94.46 379

test_vis1_n		92.37 228	92.26 212	92.72 327	94.75 343	82.64 378	98.02 60	96.80 270	91.18 202	97.77 52	97.93 102	58.02 432	98.29 264	97.63 35	98.21 136	97.23 256

CMPMVS	62.92 21	85.62 386	84.92 381	87.74 410	89.14 432	73.12 440	94.17 374	96.80 270	73.98 436	73.65 438	94.93 295	66.36 409	97.61 350	83.95 353	91.28 300	92.48 416
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 320	89.77 316	91.78 358	94.33 360	84.72 355	95.55 319	96.73 272	86.17 359	86.36 377	95.28 280	71.28 369	97.80 331	84.09 350	98.14 140	92.81 408

Effi-MVS+-dtu		93.08 198	93.21 173	92.68 330	96.02 271	83.25 372	97.14 191	96.72 273	93.85 95	91.20 260	93.44 374	83.08 211	98.30 263	91.69 201	95.73 212	96.50 275

TSAR-MVS + GP.		96.69 61	96.49 65	97.27 63	98.31 87	93.39 63	96.79 223	96.72 273	94.17 84	97.44 58	97.66 132	92.76 31	99.33 132	96.86 56	97.76 155	99.08 91

1112_ss		93.37 186	92.42 208	96.21 132	97.05 179	90.99 163	96.31 272	96.72 273	86.87 346	89.83 290	96.69 201	86.51 146	99.14 159	88.12 278	93.67 264	98.50 160

PVSNet	86.66 18	92.24 236	91.74 231	93.73 283	97.77 134	83.69 369	92.88 410	96.72 273	87.91 318	93.00 208	94.86 299	78.51 306	99.05 179	86.53 312	97.45 163	98.47 165

miper_lstm_enhance		90.50 316	90.06 304	91.83 354	95.33 308	83.74 366	93.86 385	96.70 277	87.56 332	87.79 347	93.81 358	83.45 203	96.92 387	87.39 299	84.62 378	94.82 363

v148		90.99 296	90.38 285	92.81 324	93.83 374	85.80 331	96.78 227	96.68 278	89.45 266	88.75 325	93.93 354	82.96 217	97.82 328	87.83 284	83.25 395	94.80 366

ACMH+	87.92 14	90.20 324	89.18 333	93.25 306	96.48 235	86.45 315	96.99 204	96.68 278	88.83 289	84.79 391	96.22 230	70.16 379	98.53 242	84.42 346	88.04 336	94.77 371

CANet_DTU		94.37 141	93.65 153	96.55 98	96.46 238	92.13 114	96.21 280	96.67 280	94.38 81	93.53 193	97.03 183	79.34 289	99.71 60	90.76 221	98.45 126	97.82 226

cl____		90.96 299	90.32 287	92.89 320	95.37 302	86.21 321	94.46 362	96.64 281	87.82 321	88.15 342	94.18 342	82.98 215	97.54 355	87.70 289	85.59 360	94.92 356

HY-MVS	89.66 9	93.87 167	92.95 182	96.63 92	97.10 173	92.49 100	95.64 316	96.64 281	89.05 278	93.00 208	95.79 255	85.77 161	99.45 121	89.16 264	94.35 243	97.96 212

Test_1112_low_res		92.84 213	91.84 226	95.85 156	97.04 181	89.97 205	95.53 321	96.64 281	85.38 369	89.65 297	95.18 285	85.86 158	99.10 164	87.70 289	93.58 269	98.49 162

DIV-MVS_self_test		90.97 298	90.33 286	92.88 321	95.36 303	86.19 323	94.46 362	96.63 284	87.82 321	88.18 340	94.23 339	82.99 214	97.53 357	87.72 286	85.57 361	94.93 354

Fast-Effi-MVS+-dtu		92.29 233	91.99 220	93.21 309	95.27 312	85.52 337	97.03 196	96.63 284	92.09 165	89.11 315	95.14 287	80.33 272	98.08 286	87.54 297	94.74 239	96.03 293

UnsupCasMVSNet_bld		82.13 402	79.46 407	90.14 391	88.00 440	82.47 383	90.89 428	96.62 286	78.94 426	75.61 433	84.40 444	56.63 435	96.31 401	77.30 406	66.77 445	91.63 426

cl22		91.21 286	90.56 281	93.14 312	96.09 267	86.80 303	94.41 364	96.58 287	87.80 323	88.58 328	93.99 352	80.85 262	97.62 349	89.87 241	86.93 348	94.99 349

jason		94.84 128	94.39 134	96.18 134	95.52 291	90.93 167	96.09 287	96.52 288	89.28 270	96.01 121	97.32 157	84.70 180	98.77 210	95.15 117	98.91 106	98.85 128
jason: jason.
tt0805		91.09 291	90.07 303	94.16 256	95.61 286	88.31 261	97.56 136	96.51 289	89.56 260	89.17 313	95.64 264	67.08 407	98.38 257	91.07 213	88.44 333	95.80 301

AUN-MVS		91.76 253	90.75 271	94.81 218	97.00 185	88.57 253	96.65 240	96.49 290	89.63 258	92.15 227	96.12 236	78.66 304	98.50 244	90.83 217	79.18 414	97.36 248

hse-mvs2		93.45 184	92.99 178	94.81 218	97.02 183	88.59 252	96.69 236	96.47 291	95.19 33	96.74 82	96.16 234	83.67 198	98.48 247	95.85 94	79.13 415	97.35 250

SD_0403		90.01 328	90.02 306	89.96 394	95.65 285	76.76 428	95.76 307	96.46 292	90.58 233	86.59 374	96.29 226	82.12 238	94.78 423	73.00 428	93.76 262	98.35 179

EG-PatchMatch MVS		87.02 368	85.44 373	91.76 360	92.67 406	85.00 349	96.08 288	96.45 293	83.41 399	79.52 425	93.49 371	57.10 434	97.72 340	79.34 397	90.87 309	92.56 413

KD-MVS_self_test		85.95 382	84.95 380	88.96 404	89.55 431	79.11 422	95.13 342	96.42 294	85.91 362	84.07 400	90.48 416	70.03 381	94.82 422	80.04 389	72.94 434	92.94 406

pmmvs6		87.81 360	86.19 368	92.69 329	91.32 419	86.30 318	97.34 169	96.41 295	80.59 420	84.05 401	94.37 327	67.37 402	97.67 343	84.75 341	79.51 413	94.09 391

PMMVS		92.86 211	92.34 209	94.42 243	94.92 334	86.73 306	94.53 357	96.38 296	84.78 381	94.27 170	95.12 289	83.13 210	98.40 251	91.47 205	96.49 197	98.12 198

RPSCF		90.75 305	90.86 263	90.42 387	96.84 196	76.29 431	95.61 317	96.34 297	83.89 390	91.38 248	97.87 110	76.45 329	98.78 207	87.16 306	92.23 282	96.20 282

BP-MVS1		95.89 92	95.49 92	97.08 77	96.67 214	93.20 73	98.08 54	96.32 298	94.56 69	96.32 106	97.84 115	84.07 193	99.15 156	96.75 58	98.78 109	98.90 120

MSDG		91.42 273	90.24 293	94.96 211	97.15 171	88.91 245	93.69 393	96.32 298	85.72 365	86.93 370	96.47 217	80.24 273	98.98 185	80.57 386	95.05 232	96.98 261

WBMVS		90.69 310	89.99 307	92.81 324	96.48 235	85.00 349	95.21 340	96.30 300	89.46 265	89.04 316	94.05 349	72.45 362	97.82 328	89.46 251	87.41 345	95.61 312

OurMVSNet-221017-0		90.51 315	90.19 298	91.44 366	93.41 391	81.25 393	96.98 205	96.28 301	91.68 177	86.55 375	96.30 225	74.20 351	97.98 302	88.96 267	87.40 346	95.09 345

MVP-Stereo		90.74 306	90.08 300	92.71 328	93.19 396	88.20 267	95.86 300	96.27 302	86.07 360	84.86 390	94.76 304	77.84 318	97.75 338	83.88 355	98.01 146	92.17 423
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 122	94.56 125	96.29 126	96.34 246	91.21 151	95.83 302	96.27 302	88.93 285	96.22 111	96.88 190	86.20 153	98.85 198	95.27 113	99.05 97	98.82 132

BH-untuned		92.94 206	92.62 198	93.92 276	97.22 165	86.16 324	96.40 262	96.25 304	90.06 247	89.79 291	96.17 233	83.19 207	98.35 259	87.19 304	97.27 172	97.24 255

CL-MVSNet_self_test		86.31 377	85.15 377	89.80 396	88.83 435	81.74 391	93.93 382	96.22 305	86.67 348	85.03 388	90.80 414	78.09 314	94.50 424	74.92 417	71.86 436	93.15 404

IS-MVSNet		94.90 124	94.52 129	96.05 140	97.67 140	90.56 180	98.44 22	96.22 305	93.21 120	93.99 178	97.74 124	85.55 165	98.45 248	89.98 237	97.86 150	99.14 83

FA-MVS(test-final)		93.52 181	92.92 183	95.31 191	96.77 209	88.54 255	94.82 349	96.21 307	89.61 259	94.20 172	95.25 283	83.24 205	99.14 159	90.01 236	96.16 202	98.25 186

GA-MVS		91.38 275	90.31 288	94.59 229	94.65 348	87.62 284	94.34 367	96.19 308	90.73 220	90.35 271	93.83 355	71.84 365	97.96 309	87.22 303	93.61 267	98.21 189

LuminaMVS		94.89 125	94.35 135	96.53 99	95.48 293	92.80 87	96.88 214	96.18 309	92.85 142	95.92 124	96.87 192	81.44 251	98.83 201	96.43 70	97.10 179	97.94 214

IterMVS-SCA-FT		90.31 318	89.81 314	91.82 355	95.52 291	84.20 361	94.30 370	96.15 310	90.61 230	87.39 356	94.27 336	75.80 335	96.44 398	87.34 300	86.88 352	94.82 363

IterMVS		90.15 326	89.67 320	91.61 362	95.48 293	83.72 367	94.33 368	96.12 311	89.99 248	87.31 359	94.15 344	75.78 337	96.27 402	86.97 309	86.89 351	94.83 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 216	91.51 240	96.52 101	98.77 58	90.99 163	97.38 166	96.08 312	82.38 405	89.29 309	97.87 110	83.77 196	99.69 66	81.37 379	96.69 189	98.89 124

pmmvs4		90.93 300	89.85 312	94.17 255	93.34 393	90.79 173	94.60 354	96.02 313	84.62 382	87.45 353	95.15 286	81.88 245	97.45 364	87.70 289	87.87 338	94.27 388

ppachtmachnet_test		88.35 355	87.29 354	91.53 363	92.45 412	83.57 370	93.75 389	95.97 314	84.28 385	85.32 387	94.18 342	79.00 301	96.93 386	75.71 413	84.99 374	94.10 389

Anonymous20240521		86.42 375	85.44 373	89.34 402	90.33 424	79.79 413	96.73 230	95.92 315	83.71 395	83.25 406	91.36 411	63.92 420	96.01 403	78.39 401	85.36 365	92.22 421

ITE_SJBPF				92.43 333	95.34 305	85.37 342		95.92 315	91.47 186	87.75 349	96.39 222	71.00 371	97.96 309	82.36 369	89.86 319	93.97 394

test_fmvs2		89.77 337	89.93 309	89.31 403	93.68 379	76.37 430	97.64 126	95.90 317	89.84 254	91.49 246	96.26 229	58.77 430	97.10 378	94.65 135	91.13 302	94.46 379

USDC		88.94 346	87.83 351	92.27 340	94.66 347	84.96 351	93.86 385	95.90 317	87.34 337	83.40 404	95.56 268	67.43 401	98.19 272	82.64 368	89.67 321	93.66 397

COLMAP_ROB	87.81 15	90.40 317	89.28 330	93.79 281	97.95 122	87.13 297	96.92 210	95.89 319	82.83 402	86.88 372	97.18 168	73.77 355	99.29 139	78.44 400	93.62 266	94.95 350
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 169	93.08 176	96.02 143	97.88 128	89.96 206	97.72 111	95.85 320	92.43 152	95.86 126	98.44 57	68.42 397	99.39 127	96.31 71	94.85 233	98.71 143

VDDNet		93.05 200	92.07 215	96.02 143	96.84 196	90.39 188	98.08 54	95.85 320	86.22 358	95.79 129	98.46 55	67.59 400	99.19 147	94.92 124	94.85 233	98.47 165

mvsmamba		94.57 136	94.14 140	95.87 153	97.03 182	89.93 207	97.84 89	95.85 320	91.34 192	94.79 158	96.80 193	80.67 263	98.81 204	94.85 125	98.12 141	98.85 128

Vis-MVSNet (Re-imp)		94.15 149	93.88 146	94.95 212	97.61 148	87.92 276	98.10 52	95.80 323	92.22 158	93.02 207	97.45 149	84.53 183	97.91 321	88.24 277	97.97 147	99.02 96

MM		97.29 26	96.98 36	98.23 11	98.01 116	95.03 26	98.07 56	95.76 324	97.78 1	97.52 55	98.80 35	88.09 114	99.86 9	99.44 2	99.37 62	99.80 1

KD-MVS_2432*1600		84.81 392	82.64 395	91.31 368	91.07 421	85.34 343	91.22 423	95.75 325	85.56 367	83.09 407	90.21 419	67.21 403	95.89 405	77.18 407	62.48 449	92.69 409

miper_refine_blended		84.81 392	82.64 395	91.31 368	91.07 421	85.34 343	91.22 423	95.75 325	85.56 367	83.09 407	90.21 419	67.21 403	95.89 405	77.18 407	62.48 449	92.69 409

FE-MVS		92.05 244	91.05 256	95.08 200	96.83 198	87.93 275	93.91 384	95.70 327	86.30 355	94.15 175	94.97 292	76.59 327	99.21 145	84.10 349	96.86 182	98.09 204

tpm cat1		88.36 354	87.21 357	91.81 356	95.13 324	80.55 402	92.58 414	95.70 327	74.97 435	87.45 353	91.96 404	78.01 317	98.17 274	80.39 388	88.74 330	96.72 271

our_test_3		88.78 350	87.98 350	91.20 372	92.45 412	82.53 380	93.61 397	95.69 329	85.77 364	84.88 389	93.71 360	79.99 278	96.78 394	79.47 394	86.24 354	94.28 387

BH-w/o		92.14 241	91.75 229	93.31 304	96.99 186	85.73 334	95.67 311	95.69 329	88.73 295	89.26 311	94.82 302	82.97 216	98.07 290	85.26 336	96.32 201	96.13 289

CR-MVSNet		90.82 303	89.77 316	93.95 270	94.45 356	87.19 294	90.23 431	95.68 331	86.89 345	92.40 217	92.36 396	80.91 259	97.05 381	81.09 383	93.95 259	97.60 238

Patchmtry		88.64 352	87.25 355	92.78 326	94.09 366	86.64 307	89.82 435	95.68 331	80.81 417	87.63 351	92.36 396	80.91 259	97.03 382	78.86 398	85.12 370	94.67 374

testing91		91.90 249	91.02 257	94.53 237	96.54 227	86.55 313	95.86 300	95.64 333	91.77 174	91.89 236	93.47 373	69.94 382	98.86 196	90.23 235	93.86 261	98.18 191

BH-RMVSNet		92.72 218	91.97 221	94.97 210	97.16 169	87.99 274	96.15 285	95.60 334	90.62 229	91.87 237	97.15 171	78.41 308	98.57 239	83.16 358	97.60 157	98.36 177

PVSNet_0	82.17 19	85.46 387	83.64 390	90.92 376	95.27 312	79.49 418	90.55 429	95.60 334	83.76 394	83.00 409	89.95 421	71.09 370	97.97 305	82.75 366	60.79 451	95.31 332

guyue		95.17 116	94.96 112	95.82 158	96.97 188	89.65 212	97.56 136	95.58 336	94.82 54	95.72 131	97.42 153	82.90 218	98.84 200	96.71 61	96.93 181	98.96 107

SCA		91.84 251	91.18 253	93.83 278	95.59 287	84.95 352	94.72 351	95.58 336	90.82 216	92.25 225	93.69 362	75.80 335	98.10 281	86.20 318	95.98 204	98.45 167

MonoMVSNet		91.92 247	91.77 227	92.37 334	92.94 400	83.11 374	97.09 194	95.55 338	92.91 140	90.85 263	94.55 315	81.27 255	96.52 397	93.01 174	87.76 339	97.47 244

AllTest		90.23 322	88.98 336	93.98 266	97.94 123	86.64 307	96.51 253	95.54 339	85.38 369	85.49 384	96.77 195	70.28 377	99.15 156	80.02 390	92.87 271	96.15 287

TestCases				93.98 266	97.94 123	86.64 307		95.54 339	85.38 369	85.49 384	96.77 195	70.28 377	99.15 156	80.02 390	92.87 271	96.15 287

mmtdpeth		89.70 339	88.96 337	91.90 351	95.84 279	84.42 357	97.46 156	95.53 341	90.27 241	94.46 167	90.50 415	69.74 386	98.95 186	97.39 47	69.48 440	92.34 417

tpmvs		89.83 336	89.15 334	91.89 352	94.92 334	80.30 406	93.11 406	95.46 342	86.28 356	88.08 343	92.65 386	80.44 269	98.52 243	81.47 375	89.92 318	96.84 267

pmmvs5		89.86 335	88.87 340	92.82 323	92.86 402	86.23 320	96.26 275	95.39 343	84.24 386	87.12 361	94.51 318	74.27 350	97.36 371	87.61 296	87.57 341	94.86 359

PatchmatchNet		91.91 248	91.35 242	93.59 292	95.38 300	84.11 362	93.15 405	95.39 343	89.54 261	92.10 230	93.68 364	82.82 221	98.13 276	84.81 340	95.32 225	98.52 157
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 272	91.32 244	91.79 357	95.15 322	79.20 421	93.42 400	95.37 345	88.55 300	93.49 196	93.67 365	82.49 230	98.27 265	90.41 230	89.34 324	97.90 216

Anonymous20231206		87.09 367	86.14 369	89.93 395	91.22 420	80.35 404	96.11 286	95.35 346	83.57 397	84.16 396	93.02 381	73.54 357	95.61 413	72.16 430	86.14 356	93.84 396

MIMVSNet1		84.93 390	83.05 392	90.56 385	89.56 430	84.84 354	95.40 326	95.35 346	83.91 389	80.38 421	92.21 401	57.23 433	93.34 436	70.69 436	82.75 401	93.50 399

TDRefinement		86.53 371	84.76 383	91.85 353	82.23 452	84.25 359	96.38 264	95.35 346	84.97 378	84.09 399	94.94 294	65.76 416	98.34 262	84.60 344	74.52 430	92.97 405

TR-MVS		91.48 271	90.59 279	94.16 256	96.40 241	87.33 287	95.67 311	95.34 349	87.68 329	91.46 247	95.52 271	76.77 326	98.35 259	82.85 363	93.61 267	96.79 269

EPNet_dtu		91.71 254	91.28 247	92.99 316	93.76 376	83.71 368	96.69 236	95.28 350	93.15 127	87.02 366	95.95 244	83.37 204	97.38 370	79.46 395	96.84 183	97.88 218
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 364	85.79 371	91.78 358	94.80 341	87.28 289	95.49 323	95.28 350	84.09 388	83.85 403	91.82 405	62.95 423	94.17 428	78.48 399	85.34 366	93.91 395

MDTV_nov1_ep13			90.76 269		95.22 316	80.33 405	93.03 408	95.28 350	88.14 313	92.84 214	93.83 355	81.34 252	98.08 286	82.86 361	94.34 244

LF4IMVS		87.94 358	87.25 355	89.98 393	92.38 414	80.05 412	94.38 365	95.25 353	87.59 331	84.34 393	94.74 306	64.31 419	97.66 345	84.83 339	87.45 342	92.23 420

TransMVSNet (Re)		88.94 346	87.56 352	93.08 314	94.35 359	88.45 259	97.73 108	95.23 354	87.47 333	84.26 395	95.29 278	79.86 281	97.33 372	79.44 396	74.44 431	93.45 401

test20.03		86.14 380	85.40 375	88.35 405	90.12 425	80.06 411	95.90 299	95.20 355	88.59 296	81.29 416	93.62 367	71.43 368	92.65 440	71.26 434	81.17 406	92.34 417

new-patchmatchnet		83.18 398	81.87 401	87.11 413	86.88 443	75.99 432	93.70 391	95.18 356	85.02 377	77.30 432	88.40 431	65.99 414	93.88 433	74.19 422	70.18 438	91.47 430

MDA-MVSNet_test_wron		85.87 384	84.23 387	90.80 382	92.38 414	82.57 379	93.17 403	95.15 357	82.15 406	67.65 444	92.33 399	78.20 310	95.51 416	77.33 404	79.74 410	94.31 386

YYNet1		85.87 384	84.23 387	90.78 383	92.38 414	82.46 384	93.17 403	95.14 358	82.12 407	67.69 442	92.36 396	78.16 313	95.50 417	77.31 405	79.73 411	94.39 382

Baseline_NR-MVSNet		91.20 287	90.62 277	92.95 318	93.83 374	88.03 273	97.01 201	95.12 359	88.42 304	89.70 294	95.13 288	83.47 201	97.44 365	89.66 247	83.24 396	93.37 402

thres200		92.23 237	91.39 241	94.75 225	97.61 148	89.03 243	96.60 248	95.09 360	92.08 166	93.28 202	94.00 351	78.39 309	99.04 182	81.26 382	94.18 250	96.19 283

ADS-MVSNet		89.89 332	88.68 342	93.53 296	95.86 274	84.89 353	90.93 426	95.07 361	83.23 400	91.28 256	91.81 406	79.01 299	97.85 324	79.52 392	91.39 298	97.84 223

pmmvs-eth3d		86.22 378	84.45 385	91.53 363	88.34 439	87.25 291	94.47 360	95.01 362	83.47 398	79.51 426	89.61 424	69.75 385	95.71 410	83.13 359	76.73 424	91.64 425

Anonymous202405211		92.07 243	90.83 267	95.76 162	98.19 102	88.75 248	97.58 132	95.00 363	86.00 361	93.64 188	97.45 149	66.24 412	99.53 105	90.68 224	92.71 276	99.01 99

MDA-MVSNet-bldmvs		85.00 389	82.95 394	91.17 374	93.13 398	83.33 371	94.56 356	95.00 363	84.57 383	65.13 448	92.65 386	70.45 376	95.85 407	73.57 425	77.49 420	94.33 384

ambc				86.56 416	83.60 449	70.00 443	85.69 447	94.97 365		80.60 420	88.45 430	37.42 451	96.84 391	82.69 367	75.44 428	92.86 407

testgi		87.97 357	87.21 357	90.24 390	92.86 402	80.76 397	96.67 239	94.97 365	91.74 175	85.52 383	95.83 250	62.66 425	94.47 426	76.25 411	88.36 334	95.48 315

myMVS_eth3d28		91.52 268	90.97 259	93.17 310	96.91 190	83.24 373	95.61 317	94.96 367	92.24 157	91.98 233	93.28 378	69.31 387	98.40 251	88.71 272	95.68 214	97.88 218

dp		88.90 348	88.26 348	90.81 380	94.58 352	76.62 429	92.85 411	94.93 368	85.12 375	90.07 285	93.07 380	75.81 334	98.12 279	80.53 387	87.42 344	97.71 230

test_fmvs3		83.21 397	83.02 393	83.78 420	86.77 444	68.34 446	96.76 228	94.91 369	86.49 351	84.14 398	89.48 425	36.04 452	91.73 442	91.86 195	80.77 408	91.26 432

test_0402		86.46 374	84.79 382	91.45 365	95.02 328	85.55 336	96.29 274	94.89 370	80.90 414	82.21 412	93.97 353	68.21 398	97.29 374	62.98 443	88.68 331	91.51 428

tfpn200view9		92.38 227	91.52 238	94.95 212	97.85 129	89.29 233	97.41 159	94.88 371	92.19 162	93.27 203	94.46 323	78.17 311	99.08 170	81.40 376	94.08 254	96.48 276

CVMVSNet		91.23 285	91.75 229	89.67 397	95.77 280	74.69 433	96.44 254	94.88 371	85.81 363	92.18 226	97.64 136	79.07 294	95.58 415	88.06 280	95.86 209	98.74 140

thres400		92.42 225	91.52 238	95.12 199	97.85 129	89.29 233	97.41 159	94.88 371	92.19 162	93.27 203	94.46 323	78.17 311	99.08 170	81.40 376	94.08 254	96.98 261

tt0320		85.39 388	83.12 391	92.19 344	93.44 390	85.79 332	96.19 282	94.87 374	71.19 442	82.92 410	91.76 408	58.43 431	96.81 392	81.03 384	78.26 419	93.98 393

EPNet		95.20 114	94.56 125	97.14 71	92.80 404	92.68 93	97.85 88	94.87 374	96.64 6	92.46 216	97.80 121	86.23 150	99.65 72	93.72 155	98.62 117	99.10 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 259	90.72 274	94.32 248	96.48 235	86.11 329	95.81 303	94.76 376	91.55 179	91.75 241	93.44 374	68.55 395	98.82 202	90.43 229	93.69 263	98.04 208

sc_t1		86.48 373	84.10 389	93.63 289	93.45 389	85.76 333	96.79 223	94.71 377	73.06 440	86.45 376	94.35 328	55.13 438	97.95 313	84.38 347	78.55 418	97.18 257

SixPastTwentyTwo		89.15 344	88.54 344	90.98 375	93.49 386	80.28 408	96.70 234	94.70 378	90.78 217	84.15 397	95.57 267	71.78 366	97.71 341	84.63 343	85.07 371	94.94 352

thres100view900		92.43 224	91.58 235	94.98 208	97.92 125	89.37 229	97.71 113	94.66 379	92.20 160	93.31 201	94.90 297	78.06 315	99.08 170	81.40 376	94.08 254	96.48 276

thres600view7		92.49 222	91.60 234	95.18 195	97.91 126	89.47 223	97.65 122	94.66 379	92.18 164	93.33 200	94.91 296	78.06 315	99.10 164	81.61 372	94.06 258	96.98 261

PatchT		88.87 349	87.42 353	93.22 308	94.08 367	85.10 347	89.51 436	94.64 381	81.92 408	92.36 220	88.15 434	80.05 277	97.01 384	72.43 429	93.65 265	97.54 241

baseline1		92.82 214	91.90 224	95.55 178	97.20 167	90.77 174	97.19 186	94.58 382	92.20 160	92.36 220	96.34 224	84.16 191	98.21 269	89.20 262	83.90 391	97.68 232

AstraMVS		94.82 130	94.64 121	95.34 190	96.36 245	88.09 272	97.58 132	94.56 383	94.98 43	95.70 134	97.92 105	81.93 244	98.93 189	96.87 55	95.88 207	98.99 103

UBG		91.55 265	90.76 269	93.94 272	96.52 231	85.06 348	95.22 338	94.54 384	90.47 237	91.98 233	92.71 385	72.02 363	98.74 216	88.10 279	95.26 227	98.01 210

Gipuma		67.86 418	65.41 420	75.18 433	92.66 407	73.45 437	66.50 454	94.52 385	53.33 453	57.80 454	66.07 454	30.81 454	89.20 446	48.15 452	78.88 417	62.90 454
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 257	90.75 271	94.47 239	96.53 229	86.56 312	95.76 307	94.51 386	91.10 209	91.24 258	93.59 368	68.59 394	98.86 196	91.10 212	94.29 246	98.00 211

CostFormer		91.18 290	90.70 275	92.62 331	94.84 339	81.76 390	94.09 377	94.43 387	84.15 387	92.72 215	93.77 359	79.43 288	98.20 270	90.70 223	92.18 285	97.90 216

tpm2		89.96 329	89.21 332	92.23 343	94.91 336	81.25 393	93.78 388	94.42 388	80.62 419	91.56 244	93.44 374	76.44 330	97.94 315	85.60 330	92.08 289	97.49 242

testing3-2		92.10 242	92.05 216	92.27 340	97.71 138	79.56 415	97.42 158	94.41 389	93.53 108	93.22 205	95.49 272	69.16 389	99.11 162	93.25 164	94.22 248	98.13 196

MVS_0304		96.74 58	96.31 75	98.02 19	96.87 192	94.65 30	97.58 132	94.39 390	96.47 9	97.16 67	98.39 61	87.53 130	99.87 7	98.97 17	99.41 54	99.55 38

JIA-IIPM		88.26 356	87.04 360	91.91 350	93.52 384	81.42 392	89.38 437	94.38 391	80.84 416	90.93 262	80.74 446	79.22 291	97.92 318	82.76 365	91.62 293	96.38 279

dmvs_re		90.21 323	89.50 325	92.35 335	95.47 297	85.15 345	95.70 310	94.37 392	90.94 215	88.42 330	93.57 369	74.63 347	95.67 412	82.80 364	89.57 322	96.22 281

Patchmatch-test		89.42 342	87.99 349	93.70 286	95.27 312	85.11 346	88.98 438	94.37 392	81.11 413	87.10 364	93.69 362	82.28 234	97.50 360	74.37 420	94.76 237	98.48 164

LCM-MVSNet		72.55 411	69.39 415	82.03 422	70.81 462	65.42 451	90.12 433	94.36 394	55.02 452	65.88 446	81.72 445	24.16 460	89.96 443	74.32 421	68.10 443	90.71 435

ADS-MVSNet2		89.45 341	88.59 343	92.03 347	95.86 274	82.26 386	90.93 426	94.32 395	83.23 400	91.28 256	91.81 406	79.01 299	95.99 404	79.52 392	91.39 298	97.84 223

mvs5depth		86.53 371	85.08 378	90.87 377	88.74 437	82.52 381	91.91 419	94.23 396	86.35 354	87.11 363	93.70 361	66.52 408	97.76 336	81.37 379	75.80 426	92.31 419

EU-MVSNet		88.72 351	88.90 339	88.20 407	93.15 397	74.21 435	96.63 245	94.22 397	85.18 373	87.32 358	95.97 242	76.16 332	94.98 421	85.27 335	86.17 355	95.41 322

tt0320-xc		84.83 391	82.33 399	92.31 338	93.66 380	86.20 322	96.17 284	94.06 398	71.26 441	82.04 414	92.22 400	55.07 439	96.72 395	81.49 374	75.04 429	94.02 392

MIMVSNet		88.50 353	86.76 363	93.72 285	94.84 339	87.77 282	91.39 421	94.05 399	86.41 353	87.99 345	92.59 389	63.27 421	95.82 409	77.44 403	92.84 273	97.57 240

OpenMVS_ROB	81.14 20	84.42 394	82.28 400	90.83 378	90.06 426	84.05 364	95.73 309	94.04 400	73.89 438	80.17 424	91.53 410	59.15 429	97.64 346	66.92 441	89.05 326	90.80 434

TinyColmap		86.82 369	85.35 376	91.21 370	94.91 336	82.99 376	93.94 381	94.02 401	83.58 396	81.56 415	94.68 308	62.34 426	98.13 276	75.78 412	87.35 347	92.52 415

ETVMVS		90.52 314	89.14 335	94.67 228	96.81 202	87.85 280	95.91 298	93.97 402	89.71 257	92.34 223	92.48 391	65.41 417	97.96 309	81.37 379	94.27 247	98.21 189

IB-MVS	87.33 17	89.91 330	88.28 347	94.79 222	95.26 315	87.70 283	95.12 343	93.95 403	89.35 269	87.03 365	92.49 390	70.74 374	99.19 147	89.18 263	81.37 405	97.49 242
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		87.13 366	87.02 361	87.47 411	95.16 319	73.21 439	95.00 345	93.93 404	88.55 300	86.96 367	91.99 402	75.90 333	94.00 430	61.59 445	94.11 251	95.20 340

myMVS_eth3d		87.18 365	86.38 366	89.58 398	95.16 319	79.53 416	95.00 345	93.93 404	88.55 300	86.96 367	91.99 402	56.23 436	94.00 430	75.47 416	94.11 251	95.20 340

testing222		90.31 318	88.96 337	94.35 245	96.54 227	87.29 288	95.50 322	93.84 406	90.97 212	91.75 241	92.96 382	62.18 427	98.00 300	82.86 361	94.08 254	97.76 228

test_f		80.57 404	79.62 406	83.41 421	83.38 450	67.80 448	93.57 398	93.72 407	80.80 418	77.91 431	87.63 437	33.40 453	92.08 441	87.14 307	79.04 416	90.34 436

LCM-MVSNet-Re		92.50 220	92.52 204	92.44 332	96.82 200	81.89 389	96.92 210	93.71 408	92.41 153	84.30 394	94.60 313	85.08 172	97.03 382	91.51 203	97.36 165	98.40 173

tpm		90.25 321	89.74 319	91.76 360	93.92 370	79.73 414	93.98 378	93.54 409	88.28 307	91.99 232	93.25 379	77.51 321	97.44 365	87.30 302	87.94 337	98.12 198

ET-MVSNet_ETH3D		91.49 270	90.11 299	95.63 172	96.40 241	91.57 137	95.34 329	93.48 410	90.60 232	75.58 434	95.49 272	80.08 276	96.79 393	94.25 143	89.76 320	98.52 157

LFMVS		93.60 176	92.63 197	96.52 101	98.13 108	91.27 148	97.94 76	93.39 411	90.57 234	96.29 108	98.31 74	69.00 390	99.16 154	94.18 144	95.87 208	99.12 87

MVStest1		82.38 401	80.04 405	89.37 400	87.63 442	82.83 377	95.03 344	93.37 412	73.90 437	73.50 439	94.35 328	62.89 424	93.25 438	73.80 423	65.92 446	92.04 424

Patchmatch-RL test		87.38 363	86.24 367	90.81 380	88.74 437	78.40 425	88.12 445	93.17 413	87.11 342	82.17 413	89.29 426	81.95 242	95.60 414	88.64 274	77.02 421	98.41 172

ttmdpeth		85.91 383	84.76 383	89.36 401	89.14 432	80.25 409	95.66 314	93.16 414	83.77 393	83.39 405	95.26 282	66.24 412	95.26 420	80.65 385	75.57 427	92.57 412

test-LLR		91.42 273	91.19 252	92.12 345	94.59 350	80.66 399	94.29 371	92.98 415	91.11 207	90.76 265	92.37 393	79.02 297	98.07 290	88.81 269	96.74 186	97.63 233

test-mter		90.19 325	89.54 324	92.12 345	94.59 350	80.66 399	94.29 371	92.98 415	87.68 329	90.76 265	92.37 393	67.67 399	98.07 290	88.81 269	96.74 186	97.63 233

WB-MVSnew		89.88 333	89.56 323	90.82 379	94.57 353	83.06 375	95.65 315	92.85 417	87.86 320	90.83 264	94.10 345	79.66 285	96.88 389	76.34 410	94.19 249	92.54 414

testing3		87.67 361	86.88 362	90.05 392	96.14 263	80.71 398	97.10 193	92.85 417	90.15 245	87.54 352	94.55 315	55.70 437	94.10 429	73.77 424	94.10 253	95.35 329

test_method		66.11 419	64.89 421	69.79 436	72.62 460	35.23 468	65.19 455	92.83 419	20.35 458	65.20 447	88.08 435	43.14 449	82.70 453	73.12 427	63.46 448	91.45 431

test0.0.03 1		89.37 343	88.70 341	91.41 367	92.47 411	85.63 335	95.22 338	92.70 420	91.11 207	86.91 371	93.65 366	79.02 297	93.19 439	78.00 402	89.18 325	95.41 322

new_pmnet		82.89 399	81.12 404	88.18 408	89.63 429	80.18 410	91.77 420	92.57 421	76.79 433	75.56 435	88.23 433	61.22 428	94.48 425	71.43 432	82.92 399	89.87 437

mvsany_test1		93.93 165	93.98 144	93.78 282	94.94 333	86.80 303	94.62 353	92.55 422	88.77 294	96.85 77	98.49 51	88.98 96	98.08 286	95.03 119	95.62 216	96.46 278

thisisatest0515		92.29 233	91.30 246	95.25 193	96.60 218	88.90 246	94.36 366	92.32 423	87.92 317	93.43 198	94.57 314	77.28 322	99.00 183	89.42 253	95.86 209	97.86 222

thisisatest0530		93.03 201	92.21 213	95.49 182	97.07 174	89.11 242	97.49 153	92.19 424	90.16 244	94.09 176	96.41 220	76.43 331	99.05 179	90.38 231	95.68 214	98.31 183

tttt0517		92.96 204	92.33 210	94.87 215	97.11 172	87.16 296	97.97 72	92.09 425	90.63 228	93.88 182	97.01 184	76.50 328	99.06 176	90.29 234	95.45 223	98.38 175

K. test v3		87.64 362	86.75 364	90.32 389	93.02 399	79.48 419	96.61 246	92.08 426	90.66 226	80.25 423	94.09 347	67.21 403	96.65 396	85.96 326	80.83 407	94.83 361

TESTMET0.1,1		90.06 327	89.42 327	91.97 348	94.41 358	80.62 401	94.29 371	91.97 427	87.28 339	90.44 269	92.47 392	68.79 391	97.67 343	88.50 276	96.60 191	97.61 237

PM-MVS		83.48 396	81.86 402	88.31 406	87.83 441	77.59 427	93.43 399	91.75 428	86.91 344	80.63 419	89.91 422	44.42 448	95.84 408	85.17 338	76.73 424	91.50 429

baseline2		91.63 258	90.86 263	93.94 272	94.33 360	86.32 317	95.92 297	91.64 429	89.37 268	86.94 369	94.69 307	81.62 249	98.69 223	88.64 274	94.57 242	96.81 268

APD_test1		79.31 406	77.70 409	84.14 419	89.11 434	69.07 445	92.36 418	91.50 430	69.07 444	73.87 437	92.63 388	39.93 450	94.32 427	70.54 437	80.25 409	89.02 439

FPMVS		71.27 412	69.85 414	75.50 432	74.64 457	59.03 457	91.30 422	91.50 430	58.80 449	57.92 453	88.28 432	29.98 456	85.53 452	53.43 450	82.84 400	81.95 445

door								91.13 432

door-mid								91.06 433

EGC-MVSNET		68.77 417	63.01 423	86.07 418	92.49 410	82.24 387	93.96 380	90.96 434	0.71 463	2.62 464	90.89 413	53.66 440	93.46 434	57.25 448	84.55 381	82.51 444

mvsany_test3		83.59 395	82.44 398	87.03 414	83.80 447	73.82 436	93.70 391	90.92 435	86.42 352	82.51 411	90.26 418	46.76 447	95.71 410	90.82 218	76.76 423	91.57 427

pmmvs3		79.97 405	77.50 410	87.39 412	82.80 451	79.38 420	92.70 413	90.75 436	70.69 443	78.66 428	87.47 439	51.34 443	93.40 435	73.39 426	69.65 439	89.38 438

UWE-MVS		89.91 330	89.48 326	91.21 370	95.88 273	78.23 426	94.91 348	90.26 437	89.11 275	92.35 222	94.52 317	68.76 392	97.96 309	83.95 353	95.59 217	97.42 246

DSMNet-mixed		86.34 376	86.12 370	87.00 415	89.88 428	70.43 441	94.93 347	90.08 438	77.97 430	85.42 386	92.78 384	74.44 349	93.96 432	74.43 419	95.14 228	96.62 272

MVS-HIRNet		82.47 400	81.21 403	86.26 417	95.38 300	69.21 444	88.96 439	89.49 439	66.28 446	80.79 418	74.08 451	68.48 396	97.39 369	71.93 431	95.47 222	92.18 422

WB-MVS		76.77 408	76.63 411	77.18 427	85.32 445	56.82 459	94.53 357	89.39 440	82.66 404	71.35 440	89.18 427	75.03 342	88.88 447	35.42 456	66.79 444	85.84 441

test1111		93.19 193	92.82 187	94.30 251	97.58 154	84.56 356	98.21 43	89.02 441	93.53 108	94.58 162	98.21 81	72.69 359	99.05 179	93.06 170	98.48 124	99.28 72

SSC-MVS		76.05 409	75.83 412	76.72 431	84.77 446	56.22 460	94.32 369	88.96 442	81.82 410	70.52 441	88.91 428	74.79 346	88.71 448	33.69 457	64.71 447	85.23 442

ECVR-MVS		93.19 193	92.73 193	94.57 234	97.66 142	85.41 339	98.21 43	88.23 443	93.43 113	94.70 160	98.21 81	72.57 360	99.07 174	93.05 171	98.49 122	99.25 75

EPMVS		90.70 308	89.81 314	93.37 302	94.73 345	84.21 360	93.67 394	88.02 444	89.50 263	92.38 219	93.49 371	77.82 319	97.78 333	86.03 324	92.68 277	98.11 203

ANet_high		63.94 421	59.58 424	77.02 428	61.24 464	66.06 449	85.66 448	87.93 445	78.53 428	42.94 456	71.04 453	25.42 459	80.71 455	52.60 451	30.83 457	84.28 443

PMMVS2		70.19 413	66.92 417	80.01 423	76.35 456	65.67 450	86.22 446	87.58 446	64.83 448	62.38 449	80.29 448	26.78 458	88.49 450	63.79 442	54.07 453	85.88 440

lessismore_v0				90.45 386	91.96 417	79.09 423		87.19 447		80.32 422	94.39 325	66.31 411	97.55 354	84.00 352	76.84 422	94.70 373

PMVS	53.92 22	58.58 422	55.40 425	68.12 437	51.00 465	48.64 462	78.86 451	87.10 448	46.77 454	35.84 460	74.28 450	8.76 464	86.34 451	42.07 454	73.91 432	69.38 451
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 370	86.41 365	88.02 409	92.87 401	74.60 434	95.38 328	86.70 449	88.17 310	87.28 360	94.67 310	70.83 373	93.30 437	67.45 439	94.31 245	96.17 284

test_vis1_rt		86.16 379	85.06 379	89.46 399	93.47 388	80.46 403	96.41 258	86.61 450	85.22 372	79.15 427	88.64 429	52.41 442	97.06 380	93.08 169	90.57 311	90.87 433

testf1		69.31 415	66.76 418	76.94 429	78.61 454	61.93 453	88.27 443	86.11 451	55.62 450	59.69 450	85.31 442	20.19 462	89.32 444	57.62 446	69.44 441	79.58 446

APD_test2		69.31 415	66.76 418	76.94 429	78.61 454	61.93 453	88.27 443	86.11 451	55.62 450	59.69 450	85.31 442	20.19 462	89.32 444	57.62 446	69.44 441	79.58 446

gg-mvs-nofinetune		87.82 359	85.61 372	94.44 241	94.46 355	89.27 236	91.21 425	84.61 453	80.88 415	89.89 289	74.98 449	71.50 367	97.53 357	85.75 329	97.21 174	96.51 274

dmvs_testset		81.38 403	82.60 397	77.73 426	91.74 418	51.49 461	93.03 408	84.21 454	89.07 276	78.28 430	91.25 412	76.97 324	88.53 449	56.57 449	82.24 402	93.16 403

GG-mvs-BLEND				93.62 290	93.69 378	89.20 238	92.39 417	83.33 455		87.98 346	89.84 423	71.00 371	96.87 390	82.08 371	95.40 224	94.80 366

MTMP							97.86 85	82.03 456

DeepMVS_CX				74.68 434	90.84 423	64.34 452		81.61 457	65.34 447	67.47 445	88.01 436	48.60 446	80.13 456	62.33 444	73.68 433	79.58 446

E-PMN		53.28 423	52.56 427	55.43 440	74.43 458	47.13 463	83.63 450	76.30 458	42.23 455	42.59 457	62.22 456	28.57 457	74.40 457	31.53 458	31.51 456	44.78 455

test2506		91.60 260	90.78 268	94.04 262	97.66 142	83.81 365	98.27 33	75.53 459	93.43 113	95.23 146	98.21 81	67.21 403	99.07 174	93.01 174	98.49 122	99.25 75

EMVS		52.08 425	51.31 428	54.39 441	72.62 460	45.39 465	83.84 449	75.51 460	41.13 456	40.77 458	59.65 457	30.08 455	73.60 458	28.31 460	29.90 458	44.18 456

test_vis3_rt		72.73 410	70.55 413	79.27 424	80.02 453	68.13 447	93.92 383	74.30 461	76.90 432	58.99 452	73.58 452	20.29 461	95.37 418	84.16 348	72.80 435	74.31 449

MVE	50.73 23	53.25 424	48.81 429	66.58 439	65.34 463	57.50 458	72.49 453	70.94 462	40.15 457	39.28 459	63.51 455	6.89 466	73.48 459	38.29 455	42.38 455	68.76 453
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 426	53.82 426	46.29 442	33.73 466	45.30 466	78.32 452	67.24 463	18.02 459	50.93 455	87.05 440	52.99 441	53.11 461	70.76 435	25.29 459	40.46 457

kuosan		65.27 420	64.66 422	67.11 438	83.80 447	61.32 456	88.53 442	60.77 464	68.22 445	67.67 443	80.52 447	49.12 445	70.76 460	29.67 459	53.64 454	69.26 452

dongtai		69.99 414	69.33 416	71.98 435	88.78 436	61.64 455	89.86 434	59.93 465	75.67 434	74.96 436	85.45 441	50.19 444	81.66 454	43.86 453	55.27 452	72.63 450

N_pmnet		78.73 407	78.71 408	78.79 425	92.80 404	46.50 464	94.14 375	43.71 466	78.61 427	80.83 417	91.66 409	74.94 345	96.36 400	67.24 440	84.45 383	93.50 399

wuyk23d		25.11 427	24.57 431	26.74 443	73.98 459	39.89 467	57.88 456	9.80 467	12.27 460	10.39 461	6.97 463	7.03 465	36.44 462	25.43 461	17.39 460	3.89 460

testmvs		13.36 429	16.33 432	4.48 445	5.04 467	2.26 470	93.18 402	3.28 468	2.70 461	8.24 462	21.66 459	2.29 468	2.19 463	7.58 462	2.96 461	9.00 459

test123		13.04 430	15.66 433	5.18 444	4.51 468	3.45 469	92.50 416	1.81 469	2.50 462	7.58 463	20.15 460	3.67 467	2.18 464	7.13 463	1.07 462	9.90 458

mmdepth		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

monomultidepth		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

test_blank		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

uanet_test		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

DCPMVS		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

pcd_1.5k_mvsjas		7.39 432	9.85 435	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	88.65 104	0.00 465	0.00 464	0.00 463	0.00 461

sosnet-low-res		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

sosnet		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

uncertanet		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

Regformer		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

n2								0.00 470

nn								0.00 470

ab-mvs-re		8.06 431	10.74 434	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	96.69 201	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

uanet		0.00 433	0.00 436	0.00 446	0.00 469	0.00 471	0.00 457	0.00 470	0.00 464	0.00 465	0.00 464	0.00 469	0.00 465	0.00 464	0.00 463	0.00 461

WAC-MVS						79.53 416								75.56 415

PC_three_1452									90.77 218	98.89 23	98.28 79	96.24 1	98.35 259	95.76 98	99.58 23	99.59 27

eth-test2					0.00 469

eth-test					0.00 469

OPU-MVS				98.55 3	98.82 57	96.86 3	98.25 36				98.26 80	96.04 2	99.24 142	95.36 112	99.59 19	99.56 35

test_0728_THIRD									94.78 58	98.73 27	98.87 28	95.87 4	99.84 23	97.45 43	99.72 2	99.77 2

GSMVS																98.45 167

test_part2					99.28 27	95.74 8				98.10 41

sam_mvs1												82.76 222				98.45 167

sam_mvs												81.94 243

test_post1							92.81 412				16.58 462	80.53 267	97.68 342	86.20 318

test_post											17.58 461	81.76 246	98.08 286

patchmatchnet-post											90.45 417	82.65 227	98.10 281

gm-plane-assit					93.22 395	78.89 424			84.82 380		93.52 370		98.64 230	87.72 286

test9_res														94.81 129	99.38 59	99.45 54

agg_prior2														93.94 149	99.38 59	99.50 47

test_prior4						93.66 58	96.42 257

test_prior2							96.35 266		92.80 145	96.03 118	97.59 142	92.01 47		95.01 120	99.38 59

旧先验2							95.94 295		81.66 411	97.34 63			98.82 202	92.26 180

新几何2							95.79 305

原ACMM2							95.67 311

testdata2													99.67 70	85.96 326

segment_acmp												92.89 30

testdata1							95.26 337		93.10 130

plane_prior7					96.21 250	89.98 203

plane_prior6					96.10 266	90.00 199						81.32 253

plane_prior4											96.64 204

plane_prior3						90.00 199			94.46 75	91.34 250

plane_prior2							97.74 106		94.85 50

plane_prior1					96.14 263

plane_prior						89.99 201	97.24 178		94.06 87						92.16 286

HQP5-MVS						89.33 231

HQP-NCC					95.86 274		96.65 240		93.55 104	90.14 274

ACMP_Plane					95.86 274		96.65 240		93.55 104	90.14 274

BP-MVS														92.13 188

HQP4-MVS										90.14 274			98.50 244			95.78 303

HQP2-MVS												80.95 257

NP-MVS					95.99 272	89.81 210					95.87 247

MDTV_nov1_ep13_2view						70.35 442	93.10 407		83.88 391	93.55 191		82.47 231		86.25 317		98.38 175

ACMMP++_ref															90.30 316

ACMMP++															91.02 305

Test By Simon												88.73 103

High-resolution multi-view benchmark