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	98.08 204

PGM-MVS		96.81 52	96.53 63	97.65 43	99.35 22	93.53 61	97.65 122	98.98 2	92.22 157	97.14 69	98.44 57	91.17 68	99.85 18	94.35 141	99.46 41	99.57 31

MVS_111021_HR		96.68 63	96.58 62	96.99 80	98.46 75	92.31 106	96.20 280	98.90 3	94.30 83	95.86 126	97.74 123	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	94.56 162	98.39 61	88.96 97	99.85 18	94.57 139	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	96.24 278	98.79 7	93.99 90	95.80 128	97.65 132	89.92 87	99.24 142	95.87 92	99.20 81	98.58 151

patch_mono-2		96.83 51	97.44 20	95.01 204	99.05 41	85.39 340	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	98.18 190

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	98.25 185

FC-MVSNet-test		93.94 162	93.57 154	95.04 202	95.48 292	91.45 143	98.12 51	98.71 12	93.37 115	90.23 272	96.70 198	87.66 123	97.85 323	91.49 203	90.39 314	95.83 298

UniMVSNet (Re)		93.31 187	92.55 200	95.61 173	95.39 298	93.34 67	97.39 164	98.71 12	93.14 128	90.10 281	94.83 300	87.71 122	98.03 296	91.67 201	83.99 386	95.46 317

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		94.09 153	93.70 150	95.27 191	95.70 281	92.03 118	98.10 52	98.68 14	93.36 117	90.39 269	96.70 198	87.63 126	97.94 314	92.25 181	90.50 313	95.84 297

WR-MVS_H		92.00 244	91.35 241	93.95 269	95.09 325	89.47 222	98.04 59	98.68 14	91.46 186	88.34 332	94.68 307	85.86 157	97.56 352	85.77 327	84.24 384	94.82 362

fmvsm_s_conf0.5_n_4		96.75 56	97.07 28	95.79 160	97.76 135	89.57 216	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	98.08 204

VPA-MVSNet		93.24 189	92.48 205	95.51 179	95.70 281	92.39 102	97.86 85	98.66 17	92.30 155	92.09 230	95.37 275	80.49 267	98.40 250	93.95 147	85.86 357	95.75 306

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	98.59 150

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	84.47 183	99.75 51	99.37 4	98.45 126	97.88 217

UniMVSNet_NR-MVSNet		93.37 185	92.67 194	95.47 184	95.34 304	92.83 85	97.17 188	98.58 23	92.98 137	90.13 277	95.80 251	88.37 111	97.85 323	91.71 198	83.93 387	95.73 308

CSCG		96.05 84	95.91 84	96.46 111	99.24 30	90.47 183	98.30 29	98.57 24	89.01 278	93.97 179	97.57 142	92.62 37	99.76 47	94.66 133	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	98.94 110

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	98.96 106

HyFIR lowres test		93.66 174	92.92 182	95.87 152	98.24 94	89.88 207	94.58 354	98.49 27	85.06 375	93.78 182	95.78 255	82.86 218	98.67 225	91.77 196	95.71 212	99.07 93

CHOSEN 1792x2688		94.15 148	93.51 160	96.06 139	98.27 90	89.38 227	95.18 340	98.48 29	85.60 365	93.76 183	97.11 173	83.15 208	99.61 83	91.33 206	98.72 112	99.19 78

fmvsm_s_conf0.5_n_7		96.45 71	96.80 51	95.37 187	97.29 162	88.38 259	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	98.02 208

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	98.93 114

PHI-MVS		96.77 54	96.46 70	97.71 41	98.40 81	94.07 48	98.21 43	98.45 32	89.86 250	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	96.67 213	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	98.15 194

PVSNet_BlendedMVS		94.06 154	93.92 144	94.47 238	98.27 90	89.46 224	96.73 229	98.36 34	90.17 242	94.36 167	95.24 283	88.02 116	99.58 91	93.44 159	90.72 309	94.36 382

PVSNet_Blended		94.87 126	94.56 124	95.81 158	98.27 90	89.46 224	95.47 323	98.36 34	88.84 287	94.36 167	96.09 240	88.02 116	99.58 91	93.44 159	98.18 138	98.40 172

3Dnovator	91.36 5	95.19 114	94.44 132	97.44 53	96.56 223	93.36 66	98.65 12	98.36 34	94.12 85	89.25 311	98.06 91	82.20 235	99.77 46	93.41 161	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	95.48 292	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	98.18 190

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	96.62 215	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	97.43 244

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	97.81 118	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	95.67 283	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	94.91 113	96.38 118	98.20 100	90.86 170	97.27 176	98.25 55	90.21 241	94.18 172	97.27 162	87.48 133	99.73 54	93.53 156	97.77 154	98.55 153

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		91.55 264	90.84 265	93.69 286	94.96 329	88.28 262	97.84 89	98.24 57	91.46 186	88.04 343	95.80 251	79.67 283	97.48 360	87.02 307	84.54 381	95.31 331

DU-MVS		92.90 207	92.04 216	95.49 181	94.95 330	92.83 85	97.16 189	98.24 57	93.02 131	90.13 277	95.71 258	83.47 200	97.85 323	91.71 198	83.93 387	95.78 302

9.14			96.75 55		98.93 52		97.73 108	98.23 60	91.28 195	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		91.30 281	90.95 259	92.35 334	94.71 345	85.52 336	96.18 282	98.21 61	88.89 285	86.60 372	93.82 356	79.92 279	97.95 312	89.29 256	90.95 306	93.56 397

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		94.17 146	93.61 153	95.86 154	98.09 109	91.37 145	97.35 168	98.20 63	93.18 125	91.79 238	97.28 160	79.13 291	98.93 189	94.61 136	92.84 272	97.28 252

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		91.71 253	89.67 319	97.81 28	99.38 14	94.03 50	98.59 13	98.20 63	94.85 50	96.59 92	32.69 457	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		91.89 249	91.24 248	93.82 278	95.05 326	88.57 252	97.82 94	98.19 68	91.70 175	88.21 338	95.76 256	81.96 240	97.52 358	87.86 282	84.65 375	95.37 327

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	90.57 233	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		91.20 286	90.44 282	93.48 297	94.49 353	87.91 277	97.76 102	98.18 70	91.29 192	87.78 347	95.74 257	80.35 270	97.33 371	85.46 331	82.96 397	95.19 342

DELS-MVS		96.61 65	96.38 74	97.30 59	97.79 133	93.19 74	95.96 293	98.18 70	95.23 32	95.87 125	97.65 132	91.45 58	99.70 65	95.87 92	99.44 47	99.00 101
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		89.70 338	88.40 344	93.60 290	95.15 321	90.10 197	97.56 136	98.16 74	87.28 338	86.16 378	94.63 311	77.57 319	98.05 292	74.48 417	84.59 379	92.65 410

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	97.61 138	85.29 168	99.53 105	95.81 97	95.27 225	99.16 80

DeepPCF-MVS	93.97 1	96.61 65	97.09 27	95.15 195	98.09 109	86.63 309	96.00 291	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	97.41 367	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	90.36 231	97.35 166	99.11 88

QAPM		93.45 183	92.27 210	96.98 81	96.77 208	92.62 94	98.39 25	98.12 80	84.50 383	88.27 336	97.77 121	82.39 232	99.81 30	85.40 332	98.81 108	98.51 158

Vis-MVSNet		95.23 111	94.81 114	96.51 105	97.18 168	91.58 136	98.26 35	98.12 80	94.38 81	94.90 152	98.15 86	82.28 233	98.92 191	91.45 205	98.58 120	99.01 98
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 210	91.68 231	96.40 115	95.34 304	92.73 90	98.27 33	98.12 80	84.86 378	85.78 380	97.75 122	78.89 301	99.74 52	87.50 297	98.65 115	96.73 269

TranMVSNet+NR-MVSNet		92.50 219	91.63 232	95.14 196	94.76 341	92.07 115	97.53 142	98.11 83	92.90 141	89.56 299	96.12 235	83.16 207	97.60 350	89.30 255	83.20 396	95.75 306

CPTT-MVS		95.57 102	95.19 105	96.70 86	99.27 28	91.48 140	98.33 27	98.11 83	87.79 323	95.17 147	98.03 94	87.09 140	99.61 83	93.51 157	99.42 51	99.02 95

APD-MVS		96.95 41	96.60 60	98.01 20	99.03 43	94.93 27	97.72 111	98.10 85	91.50 184	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	89.22 271	97.03 74	98.10 87	92.52 39	99.65 72	94.58 138	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	88.35 305	95.09 149	97.65 132	89.97 86	99.48 117	92.08 190	98.59 119	98.44 169

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	97.69 127	93.86 16	99.71 60	96.50 67	99.39 58	99.55 38

NR-MVSNet		92.34 228	91.27 247	95.53 178	94.95 330	93.05 77	97.39 164	98.07 92	92.65 149	84.46 391	95.71 258	85.00 174	97.77 334	89.71 243	83.52 393	95.78 302

MP-MVS-pluss		96.70 59	96.27 77	97.98 22	99.23 32	94.71 29	96.96 207	98.06 95	90.67 223	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	90.57 233	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	91.17 202	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		94.51 137	93.80 146	96.64 88	97.07 174	91.97 120	96.32 270	98.06 95	88.94 283	94.50 164	96.78 193	84.60 180	99.27 140	91.90 191	96.02 202	98.68 144

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	93.38 198	98.66 40	86.83 142	99.73 54	95.60 109	99.22 75	98.96 106
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		88.98 344	87.05 358	94.77 222	94.45 355	87.19 293	90.23 430	98.03 104	77.87 430	92.40 216	87.55 437	80.17 274	99.51 110	68.84 437	93.95 258	97.60 237

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

TEST9					98.70 61	94.19 42	96.41 257	98.02 107	88.17 309	96.03 118	97.56 144	92.74 33	99.59 88

train_agg		96.30 79	95.83 87	97.72 39	98.70 61	94.19 42	96.41 257	98.02 107	88.58 296	96.03 118	97.56 144	92.73 34	99.59 88	95.04 118	99.37 62	99.39 63

test_8					98.67 63	94.06 49	96.37 264	98.01 110	88.58 296	95.98 122	97.55 146	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		92.34 228	91.53 236	94.77 222	95.13 323	90.83 171	96.40 261	97.98 113	91.88 170	89.29 308	95.54 269	82.50 228	97.80 330	89.79 242	85.27 366	95.69 309

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	94.86 153	97.81 118	87.38 136	99.82 28	96.88 54	99.20 81	99.29 70

114514_t		93.95 161	93.06 176	96.63 92	99.07 39	91.61 133	97.46 156	97.96 115	77.99 428	93.00 207	97.57 142	86.14 154	99.33 132	89.22 259	99.15 88	98.94 110

IU-MVS					99.42 7	95.39 11		97.94 117	90.40 239	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	83.21 205	99.74 52	99.22 8	98.06 143	97.88 217

Anonymous20231211		90.63 310	89.42 326	94.27 252	98.24 94	89.19 239	98.05 58	97.89 121	79.95 420	88.25 337	94.96 292	72.56 360	98.13 275	89.70 244	85.14 368	95.49 313

原ACMM1				96.38 118	98.59 71	91.09 161		97.89 121	87.41 334	95.22 146	97.68 128	90.25 81	99.54 103	87.95 281	99.12 93	98.49 161

CDPH-MVS		95.97 88	95.38 100	97.77 34	98.93 52	94.44 35	96.35 265	97.88 123	86.98 342	96.65 88	97.89 107	91.99 48	99.47 118	92.26 179	99.46 41	99.39 63

test11								97.88 123

EIA-MVS		95.53 103	95.47 94	95.71 168	97.06 177	89.63 212	97.82 94	97.87 125	93.57 103	93.92 180	95.04 289	90.61 78	98.95 186	94.62 135	98.68 113	98.54 154

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	98.90 119

无先验							95.79 304	97.87 125	83.87 391				99.65 72	87.68 291		98.89 123

3Dnovator+	91.43 4	95.40 104	94.48 130	98.16 16	96.90 191	95.34 16	98.48 21	97.87 125	94.65 67	88.53 328	98.02 96	83.69 196	99.71 60	93.18 165	98.96 103	99.44 56

VPNet		92.23 236	91.31 244	94.99 205	95.56 288	90.96 165	97.22 184	97.86 129	92.96 138	90.96 260	96.62 210	75.06 340	98.20 269	91.90 191	83.65 392	95.80 300

test_vis1_n_1920		94.17 146	94.58 123	92.91 318	97.42 159	82.02 387	97.83 92	97.85 130	94.68 64	98.10 41	98.49 51	70.15 379	99.32 134	97.91 27	98.82 107	97.40 246

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	98.94 110

test_fmvsmconf0.01_n		96.15 82	95.85 86	97.03 79	92.66 406	91.83 124	97.97 72	97.84 134	95.57 23	97.53 54	99.00 14	84.20 189	99.76 47	98.82 20	99.08 95	99.48 51

GDP-MVS		95.62 99	95.13 107	97.09 75	96.79 202	93.26 72	97.89 83	97.83 135	93.58 102	96.80 78	97.82 117	83.06 212	99.16 154	94.40 140	97.95 149	98.87 125

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	97.36 155	90.97 72	99.22 144	97.74 29	99.66 10	98.61 147

AdaColmap		94.34 141	93.68 151	96.31 122	98.59 71	91.68 131	96.59 248	97.81 137	89.87 249	92.15 226	97.06 176	83.62 199	99.54 103	89.34 254	98.07 142	97.70 230

MVSMamba_PlusPlus		96.51 68	96.48 66	96.59 96	98.07 113	91.97 120	98.14 50	97.79 138	90.43 237	97.34 63	97.52 147	91.29 64	99.19 147	98.12 25	99.64 14	98.60 148

KinetiMVS		95.26 109	94.75 118	96.79 84	96.99 186	92.05 116	97.82 94	97.78 139	94.77 60	96.46 101	97.70 125	80.62 264	99.34 131	92.37 178	98.28 133	98.97 103

mamv4		94.66 134	96.10 81	90.37 387	98.01 116	73.41 437	96.82 220	97.78 139	89.95 248	94.52 163	97.43 151	92.91 27	99.09 167	98.28 24	99.16 87	98.60 148

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	94.51 317	91.23 67	98.92 191	95.65 103	98.19 137	97.82 225

新几何1				97.32 58	98.60 70	93.59 59		97.75 142	81.58 411	95.75 130	97.85 113	90.04 84	99.67 70	86.50 313	99.13 91	98.69 143

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	97.68 128	89.32 92	98.60 233	97.45 43	99.11 94	98.67 145

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		95.01 117	94.59 122	96.26 128	98.89 56	90.68 178	97.24 178	97.73 145	91.80 171	92.93 212	96.62 210	89.13 95	99.14 159	89.21 260	97.78 153	98.97 103

Anonymous20240529		91.98 245	90.73 272	95.73 166	98.14 106	89.40 226	97.99 63	97.72 147	79.63 422	93.54 191	97.41 153	69.94 381	99.56 99	91.04 213	91.11 302	98.22 187

CHOSEN 280x420		93.12 195	92.72 193	94.34 246	96.71 212	87.27 289	90.29 429	97.72 147	86.61 349	91.34 249	95.29 277	84.29 188	98.41 249	93.25 163	98.94 104	97.35 249

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	98.90 119

LS3D		93.57 178	92.61 198	96.47 109	97.59 150	91.61 133	97.67 118	97.72 147	85.17 373	90.29 271	98.34 68	84.60 180	99.73 54	83.85 355	98.27 134	98.06 206

PAPR		94.18 145	93.42 167	96.48 108	97.64 144	91.42 144	95.55 318	97.71 151	88.99 280	92.34 222	95.82 250	89.19 93	99.11 162	86.14 319	97.38 164	98.90 119

UGNet		94.04 156	93.28 170	96.31 122	96.85 194	91.19 154	97.88 84	97.68 152	94.40 79	93.00 207	96.18 230	73.39 357	99.61 83	91.72 197	98.46 125	98.13 195
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				95.46 185	98.18 104	88.90 245		97.66 153	82.73 402	97.03 74	98.07 90	90.06 83	98.85 198	89.67 245	98.98 102	98.64 146

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		90.56 311	89.75 317	93.01 314	93.95 368	87.25 290	97.64 126	97.65 155	90.74 218	87.12 360	95.68 261	79.97 278	97.00 384	83.33 356	81.66 403	94.78 369

TAPA-MVS	90.10 7	92.30 231	91.22 250	95.56 175	98.33 86	89.60 214	96.79 222	97.65 155	81.83 408	91.52 244	97.23 165	87.94 118	98.91 193	71.31 432	98.37 129	98.17 193
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 196	92.45 206	95.05 200	98.09 109	89.21 236	96.89 212	97.64 157	93.18 125	91.79 238	97.28 160	75.35 339	98.65 228	88.99 265	92.84 272	97.28 252

test_cas_vis1_n_1920		94.48 139	94.55 127	94.28 251	96.78 206	86.45 314	97.63 128	97.64 157	93.32 118	97.68 53	98.36 64	73.75 355	99.08 170	96.73 59	99.05 97	97.31 251

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	85.34 166	99.50 113	94.99 121	99.21 76	98.97 103

Elysia		94.00 158	93.12 173	96.64 88	96.08 267	92.72 91	97.50 145	97.63 159	91.15 204	94.82 154	97.12 171	74.98 342	99.06 176	90.78 218	98.02 144	98.12 197

StellarMVS		94.00 158	93.12 173	96.64 88	96.08 267	92.72 91	97.50 145	97.63 159	91.15 204	94.82 154	97.12 171	74.98 342	99.06 176	90.78 218	98.02 144	98.12 197

cdsmvs_eth3d_5k		23.24 427	30.99 429	0.00 445	0.00 468	0.00 470	0.00 456	97.63 159	0.00 463	0.00 464	96.88 189	84.38 185	0.00 464	0.00 463	0.00 462	0.00 460

DPM-MVS		95.69 96	94.92 112	98.01 20	98.08 112	95.71 9	95.27 334	97.62 163	90.43 237	95.55 139	97.07 175	91.72 51	99.50 113	89.62 247	98.94 104	98.82 131

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	96.12 235	87.65 124	99.18 150	96.20 80	94.82 234	98.91 116

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	96.12 235	87.65 124	99.18 150	96.20 80	94.82 234	98.91 116

test222					98.24 94	92.21 110	95.33 329	97.60 164	79.22 424	95.25 144	97.84 115	88.80 101			99.15 88	98.72 140

cascas		91.20 286	90.08 299	94.58 232	94.97 328	89.16 240	93.65 394	97.59 167	79.90 421	89.40 303	92.92 382	75.36 338	98.36 257	92.14 184	94.75 237	96.23 279

h-mvs33		94.15 148	93.52 159	96.04 141	97.81 132	90.22 196	97.62 130	97.58 168	95.19 33	96.74 82	97.45 148	83.67 197	99.61 83	95.85 94	79.73 410	98.29 183

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	96.16 233	87.54 129	99.17 152	96.19 82	94.73 239	98.91 116

MVSFormer		95.37 105	95.16 106	95.99 148	96.34 245	91.21 151	98.22 41	97.57 169	91.42 188	96.22 111	97.32 156	86.20 152	97.92 317	94.07 144	99.05 97	98.85 127

test_djsdf		93.07 198	92.76 188	94.00 263	93.49 385	88.70 249	98.22 41	97.57 169	91.42 188	90.08 283	95.55 268	82.85 219	97.92 317	94.07 144	91.58 293	95.40 324

OMC-MVS		95.09 116	94.70 119	96.25 131	98.46 75	91.28 147	96.43 255	97.57 169	92.04 166	94.77 158	97.96 101	87.01 141	99.09 167	91.31 207	96.77 184	98.36 176

PS-MVSNAJss		93.74 171	93.51 160	94.44 240	93.91 370	89.28 234	97.75 104	97.56 173	92.50 151	89.94 285	96.54 213	88.65 104	98.18 272	93.83 153	90.90 307	95.86 294

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	95.13 148	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		92.42 224	91.89 224	94.03 262	93.33 393	88.50 256	97.73 108	97.53 175	92.00 168	88.85 320	96.50 215	75.62 337	98.11 279	93.88 151	91.56 294	95.48 314

mvs_tets		92.31 230	91.76 227	93.94 271	93.41 390	88.29 261	97.63 128	97.53 175	92.04 166	88.76 323	96.45 217	74.62 347	98.09 284	93.91 149	91.48 295	95.45 319

dcpmvs_2		96.37 75	97.05 32	94.31 249	98.96 51	84.11 361	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		93.78 170	93.43 165	94.82 215	96.21 249	89.99 201	97.74 106	97.51 177	94.85 50	91.34 249	96.64 203	81.32 252	98.60 233	93.02 171	92.23 281	95.86 294

plane_prior5								97.51 177					98.60 233	93.02 171	92.23 281	95.86 294

reproduce_monomvs		91.30 281	91.10 254	91.92 348	96.82 199	82.48 381	97.01 201	97.49 180	94.64 68	88.35 331	95.27 280	70.53 374	98.10 280	95.20 114	84.60 378	95.19 342

PS-MVSNAJ		95.37 105	95.33 102	95.49 181	97.35 160	90.66 179	95.31 331	97.48 181	93.85 95	96.51 97	95.70 260	88.65 104	99.65 72	94.80 130	98.27 134	96.17 283

API-MVS		94.84 127	94.49 129	95.90 151	97.90 127	92.00 119	97.80 98	97.48 181	89.19 272	94.81 156	96.71 196	88.84 100	99.17 152	88.91 267	98.76 111	96.53 272

MG-MVS		95.61 100	95.38 100	96.31 122	98.42 79	90.53 181	96.04 288	97.48 181	93.47 112	95.67 136	98.10 87	89.17 94	99.25 141	91.27 208	98.77 110	99.13 84

MAR-MVS		94.22 144	93.46 162	96.51 105	98.00 118	92.19 113	97.67 118	97.47 184	88.13 313	93.00 207	95.84 248	84.86 178	99.51 110	87.99 280	98.17 139	97.83 224
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		92.98 202	92.53 202	94.32 247	96.12 264	89.20 237	95.28 332	97.47 184	92.66 148	89.90 286	95.62 264	80.58 265	98.40 250	92.73 176	92.40 279	95.38 326
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 279	90.22 295	94.68 226	94.86 337	87.86 278	97.23 182	97.46 186	87.99 314	89.90 286	96.92 187	66.35 409	98.23 266	90.30 232	90.99 305	97.96 211

nrg030		94.05 155	93.31 169	96.27 127	95.22 315	94.59 32	98.34 26	97.46 186	92.93 139	91.21 258	96.64 203	87.23 139	98.22 267	94.99 121	85.80 358	95.98 293

XVG-OURS		93.72 172	93.35 168	94.80 220	97.07 174	88.61 250	94.79 349	97.46 186	91.97 169	93.99 177	97.86 112	81.74 246	98.88 195	92.64 177	92.67 277	96.92 264

LPG-MVS_test		92.94 205	92.56 199	94.10 257	96.16 259	88.26 263	97.65 122	97.46 186	91.29 192	90.12 279	97.16 168	79.05 294	98.73 217	92.25 181	91.89 289	95.31 331

LGP-MVS_train				94.10 257	96.16 259	88.26 263		97.46 186	91.29 192	90.12 279	97.16 168	79.05 294	98.73 217	92.25 181	91.89 289	95.31 331

MVS		91.71 253	90.44 282	95.51 179	95.20 317	91.59 135	96.04 288	97.45 191	73.44 438	87.36 356	95.60 265	85.42 165	99.10 164	85.97 324	97.46 159	95.83 298

XVG-OURS-SEG-HR		93.86 167	93.55 155	94.81 217	97.06 177	88.53 255	95.28 332	97.45 191	91.68 176	94.08 176	97.68 128	82.41 231	98.90 194	93.84 152	92.47 278	96.98 260

baseline		95.58 101	95.42 98	96.08 137	96.78 206	90.41 187	97.16 189	97.45 191	93.69 101	95.65 137	97.85 113	87.29 137	98.68 224	95.66 100	97.25 173	99.13 84

ab-mvs		93.57 178	92.55 200	96.64 88	97.28 163	91.96 122	95.40 325	97.45 191	89.81 254	93.22 204	96.28 226	79.62 285	99.46 119	90.74 221	93.11 269	98.50 159

xiu_mvs_v2_base		95.32 107	95.29 103	95.40 186	97.22 165	90.50 182	95.44 324	97.44 195	93.70 100	96.46 101	96.18 230	88.59 108	99.53 105	94.79 132	97.81 152	96.17 283

1314		92.81 214	92.03 217	95.14 196	95.33 307	89.52 221	96.04 288	97.44 195	87.72 327	86.25 377	95.33 276	83.84 194	98.79 206	89.26 257	97.05 179	97.11 258

casdiffmvs		95.64 98	95.49 92	96.08 137	96.76 211	90.45 184	97.29 175	97.44 195	94.00 89	95.46 143	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		92.16 238	91.23 249	94.95 211	94.75 342	90.94 166	97.47 154	97.43 198	89.14 273	88.90 316	96.43 218	79.71 282	98.24 265	89.56 248	87.68 339	95.67 310

anonymousdsp		92.16 238	91.55 235	93.97 267	92.58 408	89.55 218	97.51 144	97.42 199	89.42 266	88.40 330	94.84 299	80.66 263	97.88 322	91.87 193	91.28 299	94.48 377

Effi-MVS+		94.93 122	94.45 131	96.36 120	96.61 216	91.47 141	96.41 257	97.41 200	91.02 210	94.50 164	95.92 244	87.53 130	98.78 207	93.89 150	96.81 183	98.84 130

RRT-MVS		94.51 137	94.35 134	94.98 207	96.40 240	86.55 312	97.56 136	97.41 200	93.19 123	94.93 151	97.04 177	79.12 292	99.30 138	96.19 82	97.32 169	99.09 90

HQP3-MVS								97.39 202							92.10 286

HQP-MVS		93.19 192	92.74 191	94.54 235	95.86 273	89.33 230	96.65 239	97.39 202	93.55 104	90.14 273	95.87 246	80.95 256	98.50 243	92.13 187	92.10 286	95.78 302

PLC	91.00 6	94.11 152	93.43 165	96.13 136	98.58 73	91.15 160	96.69 235	97.39 202	87.29 337	91.37 248	96.71 196	88.39 109	99.52 109	87.33 300	97.13 177	97.73 228
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 303	89.86 310	93.45 299	93.54 382	87.60 284	97.70 116	97.37 205	88.85 286	87.65 349	94.08 347	81.08 255	98.10 280	84.68 341	83.79 391	94.66 374

UnsupCasMVSNet_eth		85.99 380	84.45 384	90.62 383	89.97 426	82.40 384	93.62 395	97.37 205	89.86 250	78.59 428	92.37 392	65.25 417	95.35 418	82.27 369	70.75 436	94.10 388

ACMM	89.79 8	92.96 203	92.50 204	94.35 244	96.30 247	88.71 248	97.58 132	97.36 207	91.40 190	90.53 266	96.65 202	79.77 281	98.75 214	91.24 209	91.64 291	95.59 312
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 117	94.76 115	95.75 163	96.58 219	91.71 128	96.25 275	97.35 208	92.99 132	96.70 84	96.63 207	82.67 223	99.44 122	96.22 75	97.46 159	96.11 289

xiu_mvs_v1_base		95.01 117	94.76 115	95.75 163	96.58 219	91.71 128	96.25 275	97.35 208	92.99 132	96.70 84	96.63 207	82.67 223	99.44 122	96.22 75	97.46 159	96.11 289

xiu_mvs_v1_base_debi		95.01 117	94.76 115	95.75 163	96.58 219	91.71 128	96.25 275	97.35 208	92.99 132	96.70 84	96.63 207	82.67 223	99.44 122	96.22 75	97.46 159	96.11 289

diffmvs		95.25 110	95.13 107	95.63 171	96.43 239	89.34 229	95.99 292	97.35 208	92.83 143	96.31 107	97.37 154	86.44 147	98.67 225	96.26 72	97.19 175	98.87 125
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		94.71 133	94.02 142	96.79 84	97.71 138	92.05 116	96.59 248	97.35 208	90.61 229	94.64 160	96.93 184	86.41 148	99.39 127	91.20 210	94.71 240	98.94 110

mamba_test_0407		94.54 136	94.12 141	95.80 159	96.79 202	90.38 189	96.79 222	97.29 213	91.24 196	93.68 184	97.60 139	85.03 172	98.67 225	92.14 184	96.51 192	98.35 178

mamba_0404		94.73 132	94.31 136	95.98 149	97.05 179	90.90 169	97.01 201	97.29 213	91.24 196	94.17 173	97.60 139	85.03 172	98.76 211	92.14 184	97.30 170	98.29 183

F-COLMAP		93.58 176	92.98 180	95.37 187	98.40 81	88.98 243	97.18 187	97.29 213	87.75 326	90.49 267	97.10 174	85.21 169	99.50 113	86.70 310	96.72 187	97.63 232

VortexMVS		92.88 209	92.64 195	93.58 292	96.58 219	87.53 285	96.93 209	97.28 216	92.78 146	89.75 291	94.99 290	82.73 222	97.76 335	94.60 137	88.16 334	95.46 317

XVG-ACMP-BASELINE		90.93 299	90.21 296	93.09 312	94.31 361	85.89 329	95.33 329	97.26 217	91.06 209	89.38 304	95.44 274	68.61 392	98.60 233	89.46 250	91.05 303	94.79 367

PCF-MVS	89.48 11	91.56 263	89.95 307	96.36 120	96.60 217	92.52 99	92.51 414	97.26 217	79.41 423	88.90 316	96.56 212	84.04 193	99.55 101	77.01 408	97.30 170	97.01 259
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 218	92.14 213	94.05 260	96.40 240	88.20 266	97.36 167	97.25 219	91.52 183	88.30 334	96.64 203	78.46 306	98.72 221	91.86 194	91.48 295	95.23 338
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 176	93.46 162	93.94 271	96.19 253	86.16 323	93.73 389	97.24 220	91.54 179	93.50 193	97.04 177	85.64 162	96.91 387	90.68 223	95.59 216	98.76 133

icg_test_0407		93.94 162	93.75 148	94.49 237	96.19 253	86.16 323	96.35 265	97.24 220	91.54 179	93.50 193	97.04 177	85.64 162	98.54 240	90.68 223	95.59 216	98.76 133

ICG_test_0404		92.44 222	91.92 222	94.00 263	96.19 253	86.16 323	93.84 386	97.24 220	91.54 179	88.17 340	97.04 177	76.96 324	97.09 378	90.68 223	95.59 216	98.76 133

icg_test_0403		93.98 160	93.79 147	94.55 234	96.19 253	86.16 323	96.35 265	97.24 220	91.54 179	93.59 188	97.04 177	85.86 157	98.73 217	90.68 223	95.59 216	98.76 133

OPM-MVS		93.28 188	92.76 188	94.82 215	94.63 348	90.77 174	96.65 239	97.18 224	93.72 98	91.68 242	97.26 163	79.33 289	98.63 230	92.13 187	92.28 280	95.07 345
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 207	92.02 218	95.56 175	98.19 102	90.80 172	95.27 334	97.18 224	87.96 315	91.86 237	95.68 261	80.44 268	98.99 184	84.01 350	97.54 158	96.89 265

alignmvs		95.87 94	95.23 104	97.78 32	97.56 156	95.19 21	97.86 85	97.17 226	94.39 80	96.47 100	96.40 220	85.89 156	99.20 146	96.21 79	95.11 230	98.95 109

MVS_Test		94.89 124	94.62 121	95.68 169	96.83 197	89.55 218	96.70 233	97.17 226	91.17 202	95.60 138	96.11 239	87.87 121	98.76 211	93.01 173	97.17 176	98.72 140

Fast-Effi-MVS+		93.46 182	92.75 190	95.59 174	96.77 208	90.03 198	96.81 221	97.13 228	88.19 308	91.30 252	94.27 335	86.21 151	98.63 230	87.66 292	96.46 198	98.12 197

EI-MVSNet		93.03 200	92.88 184	93.48 297	95.77 279	86.98 298	96.44 253	97.12 229	90.66 225	91.30 252	97.64 135	86.56 144	98.05 292	89.91 238	90.55 311	95.41 321

MVSTER		93.20 191	92.81 187	94.37 243	96.56 223	89.59 215	97.06 195	97.12 229	91.24 196	91.30 252	95.96 242	82.02 239	98.05 292	93.48 158	90.55 311	95.47 316

viewmambaseed2359dif		94.28 142	94.14 139	94.71 225	96.21 249	86.97 299	95.93 295	97.11 231	89.00 279	95.00 150	97.70 125	86.02 155	98.59 237	93.71 155	96.59 191	98.57 152

test_yl		94.78 130	94.23 137	96.43 113	97.74 136	91.22 149	96.85 216	97.10 232	91.23 199	95.71 132	96.93 184	84.30 186	99.31 136	93.10 166	95.12 228	98.75 137

DCV-MVSNet		94.78 130	94.23 137	96.43 113	97.74 136	91.22 149	96.85 216	97.10 232	91.23 199	95.71 132	96.93 184	84.30 186	99.31 136	93.10 166	95.12 228	98.75 137

LTVRE_ROB	88.41 13	90.99 295	89.92 309	94.19 253	96.18 257	89.55 218	96.31 271	97.09 234	87.88 318	85.67 381	95.91 245	78.79 302	98.57 238	81.50 372	89.98 316	94.44 380
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		92.73 216	92.88 184	92.29 338	96.08 267	81.05 395	97.98 66	97.08 235	90.72 220	96.79 80	98.18 84	63.07 421	98.45 247	97.62 37	98.42 128	97.36 247

v10		91.04 293	90.23 293	93.49 296	94.12 364	88.16 269	97.32 172	97.08 235	88.26 307	88.29 335	94.22 340	82.17 236	97.97 304	86.45 314	84.12 385	94.33 383

mamba_0408		93.70 173	92.99 177	95.83 156	96.79 202	90.38 189	88.69 439	97.07 237	90.96 212	93.68 184	97.31 158	84.97 175	98.76 211	90.95 214	96.51 192	98.35 178

mamba_test_0407_2		93.51 181	92.99 177	95.05 200	96.79 202	90.38 189	88.69 439	97.07 237	90.96 212	93.68 184	97.31 158	84.97 175	96.42 398	90.95 214	96.51 192	98.35 178

v144192		91.06 292	90.28 289	93.39 300	93.66 379	87.23 292	96.83 219	97.07 237	87.43 333	89.69 294	94.28 334	81.48 249	98.00 299	87.18 304	84.92 374	94.93 353

v1192		91.07 291	90.23 293	93.58 292	93.70 376	87.82 280	96.73 229	97.07 237	87.77 324	89.58 297	94.32 332	80.90 260	97.97 304	86.52 312	85.48 361	94.95 349

v8		91.29 283	90.53 281	93.57 294	94.15 363	88.12 270	97.34 169	97.06 241	88.99 280	88.32 333	94.26 337	83.08 210	98.01 298	87.62 294	83.92 389	94.57 376

mvs_anonymous		93.82 168	93.74 149	94.06 259	96.44 238	85.41 338	95.81 302	97.05 242	89.85 252	90.09 282	96.36 222	87.44 134	97.75 337	93.97 146	96.69 188	99.02 95

IterMVS-LS		92.29 232	91.94 221	93.34 302	96.25 248	86.97 299	96.57 251	97.05 242	90.67 223	89.50 302	94.80 302	86.59 143	97.64 345	89.91 238	86.11 356	95.40 324
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 301	90.03 304	93.29 304	93.55 381	86.96 301	96.74 228	97.04 244	87.36 335	89.52 301	94.34 329	80.23 273	97.97 304	86.27 315	85.21 367	94.94 351

CDS-MVSNet		94.14 151	93.54 156	95.93 150	96.18 257	91.46 142	96.33 269	97.04 244	88.97 282	93.56 189	96.51 214	87.55 128	97.89 321	89.80 241	95.95 204	98.44 169
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 337	89.26 330	91.19 372	95.16 318	80.29 406	94.53 356	97.03 246	91.79 172	88.86 319	94.10 344	69.94 381	97.82 327	85.29 333	86.66 352	95.45 319

v1144		91.37 276	90.60 277	93.68 287	93.89 371	88.23 265	96.84 218	97.03 246	88.37 304	89.69 294	94.39 324	82.04 238	97.98 301	87.80 284	85.37 363	94.84 359

v1240		90.70 307	89.85 311	93.23 306	93.51 384	86.80 302	96.61 245	97.02 248	87.16 340	89.58 297	94.31 333	79.55 286	97.98 301	85.52 330	85.44 362	94.90 356

EPP-MVSNet		95.22 112	95.04 110	95.76 161	97.49 157	89.56 217	98.67 11	97.00 249	90.69 221	94.24 170	97.62 137	89.79 89	98.81 204	93.39 162	96.49 196	98.92 115

V42		91.58 262	90.87 261	93.73 282	94.05 367	88.50 256	97.32 172	96.97 250	88.80 292	89.71 292	94.33 330	82.54 227	98.05 292	89.01 264	85.07 370	94.64 375

test_fmvs1		93.21 190	93.53 157	92.25 341	96.55 225	81.20 394	97.40 163	96.96 251	90.68 222	96.80 78	98.04 93	69.25 387	98.40 250	97.58 38	98.50 121	97.16 257

FMVSNet2		91.31 280	90.08 299	94.99 205	96.51 231	92.21 110	97.41 159	96.95 252	88.82 289	88.62 325	94.75 304	73.87 351	97.42 366	85.20 336	88.55 331	95.35 328

ACMH	87.59 16	90.53 312	89.42 326	93.87 276	96.21 249	87.92 275	97.24 178	96.94 253	88.45 302	83.91 401	96.27 227	71.92 363	98.62 232	84.43 344	89.43 322	95.05 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 277	90.27 290	94.59 228	96.51 231	91.18 156	97.50 145	96.93 254	88.82 289	89.35 305	94.51 317	73.87 351	97.29 373	86.12 320	88.82 326	95.31 331

test1		91.35 277	90.27 290	94.59 228	96.51 231	91.18 156	97.50 145	96.93 254	88.82 289	89.35 305	94.51 317	73.87 351	97.29 373	86.12 320	88.82 326	95.31 331

FMVSNet3		91.78 251	90.69 275	95.03 203	96.53 228	92.27 108	97.02 198	96.93 254	89.79 255	89.35 305	94.65 310	77.01 322	97.47 361	86.12 320	88.82 326	95.35 328

FMVSNet1		89.88 332	88.31 345	94.59 228	95.41 297	91.18 156	97.50 145	96.93 254	86.62 348	87.41 354	94.51 317	65.94 414	97.29 373	83.04 359	87.43 342	95.31 331

GeoE		93.89 165	93.28 170	95.72 167	96.96 189	89.75 210	98.24 39	96.92 258	89.47 263	92.12 228	97.21 166	84.42 184	98.39 255	87.71 287	96.50 195	99.01 98

SymmetryMVS		95.94 90	95.54 90	97.15 70	97.85 129	92.90 83	97.99 63	96.91 259	95.92 13	96.57 95	97.93 102	85.34 166	99.50 113	94.99 121	96.39 199	99.05 94

miper_enhance_ethall		91.54 266	91.01 257	93.15 310	95.35 303	87.07 297	93.97 378	96.90 260	86.79 346	89.17 312	93.43 376	86.55 145	97.64 345	89.97 237	86.93 347	94.74 371

eth_miper_zixun_eth		91.02 294	90.59 278	92.34 336	95.33 307	84.35 357	94.10 375	96.90 260	88.56 298	88.84 321	94.33 330	84.08 191	97.60 350	88.77 270	84.37 383	95.06 346

TAMVS		94.01 157	93.46 162	95.64 170	96.16 259	90.45 184	96.71 232	96.89 262	89.27 270	93.46 196	96.92 187	87.29 137	97.94 314	88.70 272	95.74 210	98.53 155

miper_ehance_all_eth		91.59 260	91.13 253	92.97 316	95.55 289	86.57 310	94.47 359	96.88 263	87.77 324	88.88 318	94.01 349	86.22 150	97.54 354	89.49 249	86.93 347	94.79 367

v2v482		91.59 260	90.85 264	93.80 279	93.87 372	88.17 268	96.94 208	96.88 263	89.54 260	89.53 300	94.90 296	81.70 247	98.02 297	89.25 258	85.04 372	95.20 339

CNLPA		94.28 142	93.53 157	96.52 101	98.38 84	92.55 98	96.59 248	96.88 263	90.13 245	91.91 234	97.24 164	85.21 169	99.09 167	87.64 293	97.83 151	97.92 214

PAPM		91.52 267	90.30 288	95.20 193	95.30 310	89.83 208	93.38 400	96.85 266	86.26 356	88.59 326	95.80 251	84.88 177	98.15 274	75.67 413	95.93 205	97.63 232

c3_l		91.38 274	90.89 260	92.88 320	95.58 287	86.30 317	94.68 351	96.84 267	88.17 309	88.83 322	94.23 338	85.65 161	97.47 361	89.36 253	84.63 376	94.89 357

pm-mvs1		90.72 306	89.65 321	93.96 268	94.29 362	89.63 212	97.79 100	96.82 268	89.07 275	86.12 379	95.48 273	78.61 304	97.78 332	86.97 308	81.67 402	94.46 378

test_vis1_n		92.37 227	92.26 211	92.72 326	94.75 342	82.64 377	98.02 60	96.80 269	91.18 201	97.77 52	97.93 102	58.02 431	98.29 263	97.63 35	98.21 136	97.23 255

CMPMVS	62.92 21	85.62 385	84.92 380	87.74 409	89.14 431	73.12 439	94.17 373	96.80 269	73.98 435	73.65 437	94.93 294	66.36 408	97.61 349	83.95 352	91.28 299	92.48 415
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 319	89.77 315	91.78 357	94.33 359	84.72 354	95.55 318	96.73 271	86.17 358	86.36 376	95.28 279	71.28 368	97.80 330	84.09 349	98.14 140	92.81 407

Effi-MVS+-dtu		93.08 197	93.21 172	92.68 329	96.02 270	83.25 371	97.14 191	96.72 272	93.85 95	91.20 259	93.44 373	83.08 210	98.30 262	91.69 200	95.73 211	96.50 274

TSAR-MVS + GP.		96.69 61	96.49 65	97.27 63	98.31 87	93.39 63	96.79 222	96.72 272	94.17 84	97.44 58	97.66 131	92.76 31	99.33 132	96.86 56	97.76 155	99.08 91

1112_ss		93.37 185	92.42 207	96.21 132	97.05 179	90.99 163	96.31 271	96.72 272	86.87 345	89.83 289	96.69 200	86.51 146	99.14 159	88.12 277	93.67 263	98.50 159

PVSNet	86.66 18	92.24 235	91.74 230	93.73 282	97.77 134	83.69 368	92.88 409	96.72 272	87.91 317	93.00 207	94.86 298	78.51 305	99.05 179	86.53 311	97.45 163	98.47 164

miper_lstm_enhance		90.50 315	90.06 303	91.83 353	95.33 307	83.74 365	93.86 384	96.70 276	87.56 331	87.79 346	93.81 357	83.45 202	96.92 386	87.39 298	84.62 377	94.82 362

v148		90.99 295	90.38 284	92.81 323	93.83 373	85.80 330	96.78 226	96.68 277	89.45 265	88.75 324	93.93 353	82.96 216	97.82 327	87.83 283	83.25 394	94.80 365

ACMH+	87.92 14	90.20 323	89.18 332	93.25 305	96.48 234	86.45 314	96.99 204	96.68 277	88.83 288	84.79 390	96.22 229	70.16 378	98.53 241	84.42 345	88.04 335	94.77 370

CANet_DTU		94.37 140	93.65 152	96.55 98	96.46 237	92.13 114	96.21 279	96.67 279	94.38 81	93.53 192	97.03 182	79.34 288	99.71 60	90.76 220	98.45 126	97.82 225

cl____		90.96 298	90.32 286	92.89 319	95.37 301	86.21 320	94.46 361	96.64 280	87.82 320	88.15 341	94.18 341	82.98 214	97.54 354	87.70 288	85.59 359	94.92 355

HY-MVS	89.66 9	93.87 166	92.95 181	96.63 92	97.10 173	92.49 100	95.64 315	96.64 280	89.05 277	93.00 207	95.79 254	85.77 160	99.45 121	89.16 263	94.35 242	97.96 211

Test_1112_low_res		92.84 212	91.84 225	95.85 155	97.04 181	89.97 204	95.53 320	96.64 280	85.38 368	89.65 296	95.18 284	85.86 157	99.10 164	87.70 288	93.58 268	98.49 161

DIV-MVS_self_test		90.97 297	90.33 285	92.88 320	95.36 302	86.19 322	94.46 361	96.63 283	87.82 320	88.18 339	94.23 338	82.99 213	97.53 356	87.72 285	85.57 360	94.93 353

Fast-Effi-MVS+-dtu		92.29 232	91.99 219	93.21 308	95.27 311	85.52 336	97.03 196	96.63 283	92.09 164	89.11 314	95.14 286	80.33 271	98.08 285	87.54 296	94.74 238	96.03 292

UnsupCasMVSNet_bld		82.13 401	79.46 406	90.14 390	88.00 439	82.47 382	90.89 427	96.62 285	78.94 425	75.61 432	84.40 443	56.63 434	96.31 400	77.30 405	66.77 444	91.63 425

cl22		91.21 285	90.56 280	93.14 311	96.09 266	86.80 302	94.41 363	96.58 286	87.80 322	88.58 327	93.99 351	80.85 261	97.62 348	89.87 240	86.93 347	94.99 348

jason		94.84 127	94.39 133	96.18 134	95.52 290	90.93 167	96.09 286	96.52 287	89.28 269	96.01 121	97.32 156	84.70 179	98.77 210	95.15 117	98.91 106	98.85 127
jason: jason.
tt0805		91.09 290	90.07 302	94.16 255	95.61 285	88.31 260	97.56 136	96.51 288	89.56 259	89.17 312	95.64 263	67.08 406	98.38 256	91.07 212	88.44 332	95.80 300

AUN-MVS		91.76 252	90.75 270	94.81 217	97.00 185	88.57 252	96.65 239	96.49 289	89.63 257	92.15 226	96.12 235	78.66 303	98.50 243	90.83 216	79.18 413	97.36 247

hse-mvs2		93.45 183	92.99 177	94.81 217	97.02 183	88.59 251	96.69 235	96.47 290	95.19 33	96.74 82	96.16 233	83.67 197	98.48 246	95.85 94	79.13 414	97.35 249

SD_0403		90.01 327	90.02 305	89.96 393	95.65 284	76.76 427	95.76 306	96.46 291	90.58 232	86.59 373	96.29 225	82.12 237	94.78 422	73.00 427	93.76 261	98.35 178

EG-PatchMatch MVS		87.02 367	85.44 372	91.76 359	92.67 405	85.00 348	96.08 287	96.45 292	83.41 398	79.52 424	93.49 370	57.10 433	97.72 339	79.34 396	90.87 308	92.56 412

KD-MVS_self_test		85.95 381	84.95 379	88.96 403	89.55 430	79.11 421	95.13 341	96.42 293	85.91 361	84.07 399	90.48 415	70.03 380	94.82 421	80.04 388	72.94 433	92.94 405

pmmvs6		87.81 359	86.19 367	92.69 328	91.32 418	86.30 317	97.34 169	96.41 294	80.59 419	84.05 400	94.37 326	67.37 401	97.67 342	84.75 340	79.51 412	94.09 390

PMMVS		92.86 210	92.34 208	94.42 242	94.92 333	86.73 305	94.53 356	96.38 295	84.78 380	94.27 169	95.12 288	83.13 209	98.40 250	91.47 204	96.49 196	98.12 197

RPSCF		90.75 304	90.86 262	90.42 386	96.84 195	76.29 430	95.61 316	96.34 296	83.89 389	91.38 247	97.87 110	76.45 328	98.78 207	87.16 305	92.23 281	96.20 281

BP-MVS1		95.89 92	95.49 92	97.08 77	96.67 213	93.20 73	98.08 54	96.32 297	94.56 69	96.32 106	97.84 115	84.07 192	99.15 156	96.75 58	98.78 109	98.90 119

MSDG		91.42 272	90.24 292	94.96 210	97.15 171	88.91 244	93.69 392	96.32 297	85.72 364	86.93 369	96.47 216	80.24 272	98.98 185	80.57 385	95.05 231	96.98 260

WBMVS		90.69 309	89.99 306	92.81 323	96.48 234	85.00 348	95.21 339	96.30 299	89.46 264	89.04 315	94.05 348	72.45 361	97.82 327	89.46 250	87.41 344	95.61 311

OurMVSNet-221017-0		90.51 314	90.19 297	91.44 365	93.41 390	81.25 392	96.98 205	96.28 300	91.68 176	86.55 374	96.30 224	74.20 350	97.98 301	88.96 266	87.40 345	95.09 344

MVP-Stereo		90.74 305	90.08 299	92.71 327	93.19 395	88.20 266	95.86 299	96.27 301	86.07 359	84.86 389	94.76 303	77.84 317	97.75 337	83.88 354	98.01 146	92.17 422
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 121	94.56 124	96.29 126	96.34 245	91.21 151	95.83 301	96.27 301	88.93 284	96.22 111	96.88 189	86.20 152	98.85 198	95.27 113	99.05 97	98.82 131

BH-untuned		92.94 205	92.62 197	93.92 275	97.22 165	86.16 323	96.40 261	96.25 303	90.06 246	89.79 290	96.17 232	83.19 206	98.35 258	87.19 303	97.27 172	97.24 254

CL-MVSNet_self_test		86.31 376	85.15 376	89.80 395	88.83 434	81.74 390	93.93 381	96.22 304	86.67 347	85.03 387	90.80 413	78.09 313	94.50 423	74.92 416	71.86 435	93.15 403

IS-MVSNet		94.90 123	94.52 128	96.05 140	97.67 140	90.56 180	98.44 22	96.22 304	93.21 120	93.99 177	97.74 123	85.55 164	98.45 247	89.98 236	97.86 150	99.14 83

FA-MVS(test-final)		93.52 180	92.92 182	95.31 190	96.77 208	88.54 254	94.82 348	96.21 306	89.61 258	94.20 171	95.25 282	83.24 204	99.14 159	90.01 235	96.16 201	98.25 185

GA-MVS		91.38 274	90.31 287	94.59 228	94.65 347	87.62 283	94.34 366	96.19 307	90.73 219	90.35 270	93.83 354	71.84 364	97.96 308	87.22 302	93.61 266	98.21 188

LuminaMVS		94.89 124	94.35 134	96.53 99	95.48 292	92.80 87	96.88 214	96.18 308	92.85 142	95.92 124	96.87 191	81.44 250	98.83 201	96.43 70	97.10 178	97.94 213

IterMVS-SCA-FT		90.31 317	89.81 313	91.82 354	95.52 290	84.20 360	94.30 369	96.15 309	90.61 229	87.39 355	94.27 335	75.80 334	96.44 397	87.34 299	86.88 351	94.82 362

IterMVS		90.15 325	89.67 319	91.61 361	95.48 292	83.72 366	94.33 367	96.12 310	89.99 247	87.31 358	94.15 343	75.78 336	96.27 401	86.97 308	86.89 350	94.83 360
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 215	91.51 239	96.52 101	98.77 58	90.99 163	97.38 166	96.08 311	82.38 404	89.29 308	97.87 110	83.77 195	99.69 66	81.37 378	96.69 188	98.89 123

pmmvs4		90.93 299	89.85 311	94.17 254	93.34 392	90.79 173	94.60 353	96.02 312	84.62 381	87.45 352	95.15 285	81.88 244	97.45 363	87.70 288	87.87 337	94.27 387

ppachtmachnet_test		88.35 354	87.29 353	91.53 362	92.45 411	83.57 369	93.75 388	95.97 313	84.28 384	85.32 386	94.18 341	79.00 300	96.93 385	75.71 412	84.99 373	94.10 388

Anonymous20240521		86.42 374	85.44 372	89.34 401	90.33 423	79.79 412	96.73 229	95.92 314	83.71 394	83.25 405	91.36 410	63.92 419	96.01 402	78.39 400	85.36 364	92.22 420

ITE_SJBPF				92.43 332	95.34 304	85.37 341		95.92 314	91.47 185	87.75 348	96.39 221	71.00 370	97.96 308	82.36 368	89.86 318	93.97 393

test_fmvs2		89.77 336	89.93 308	89.31 402	93.68 378	76.37 429	97.64 126	95.90 316	89.84 253	91.49 245	96.26 228	58.77 429	97.10 377	94.65 134	91.13 301	94.46 378

USDC		88.94 345	87.83 350	92.27 339	94.66 346	84.96 350	93.86 384	95.90 316	87.34 336	83.40 403	95.56 267	67.43 400	98.19 271	82.64 367	89.67 320	93.66 396

COLMAP_ROB	87.81 15	90.40 316	89.28 329	93.79 280	97.95 122	87.13 296	96.92 210	95.89 318	82.83 401	86.88 371	97.18 167	73.77 354	99.29 139	78.44 399	93.62 265	94.95 349
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 168	93.08 175	96.02 143	97.88 128	89.96 205	97.72 111	95.85 319	92.43 152	95.86 126	98.44 57	68.42 396	99.39 127	96.31 71	94.85 232	98.71 142

VDDNet		93.05 199	92.07 214	96.02 143	96.84 195	90.39 188	98.08 54	95.85 319	86.22 357	95.79 129	98.46 55	67.59 399	99.19 147	94.92 124	94.85 232	98.47 164

mvsmamba		94.57 135	94.14 139	95.87 152	97.03 182	89.93 206	97.84 89	95.85 319	91.34 191	94.79 157	96.80 192	80.67 262	98.81 204	94.85 125	98.12 141	98.85 127

Vis-MVSNet (Re-imp)		94.15 148	93.88 145	94.95 211	97.61 148	87.92 275	98.10 52	95.80 322	92.22 157	93.02 206	97.45 148	84.53 182	97.91 320	88.24 276	97.97 147	99.02 95

MM		97.29 26	96.98 36	98.23 11	98.01 116	95.03 26	98.07 56	95.76 323	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		84.81 391	82.64 394	91.31 367	91.07 420	85.34 342	91.22 422	95.75 324	85.56 366	83.09 406	90.21 418	67.21 402	95.89 404	77.18 406	62.48 448	92.69 408

miper_refine_blended		84.81 391	82.64 394	91.31 367	91.07 420	85.34 342	91.22 422	95.75 324	85.56 366	83.09 406	90.21 418	67.21 402	95.89 404	77.18 406	62.48 448	92.69 408

FE-MVS		92.05 243	91.05 255	95.08 199	96.83 197	87.93 274	93.91 383	95.70 326	86.30 354	94.15 174	94.97 291	76.59 326	99.21 145	84.10 348	96.86 181	98.09 203

tpm cat1		88.36 353	87.21 356	91.81 355	95.13 323	80.55 401	92.58 413	95.70 326	74.97 434	87.45 352	91.96 403	78.01 316	98.17 273	80.39 387	88.74 329	96.72 270

our_test_3		88.78 349	87.98 349	91.20 371	92.45 411	82.53 379	93.61 396	95.69 328	85.77 363	84.88 388	93.71 359	79.99 277	96.78 393	79.47 393	86.24 353	94.28 386

BH-w/o		92.14 240	91.75 228	93.31 303	96.99 186	85.73 333	95.67 310	95.69 328	88.73 294	89.26 310	94.82 301	82.97 215	98.07 289	85.26 335	96.32 200	96.13 288

CR-MVSNet		90.82 302	89.77 315	93.95 269	94.45 355	87.19 293	90.23 430	95.68 330	86.89 344	92.40 216	92.36 395	80.91 258	97.05 380	81.09 382	93.95 258	97.60 237

Patchmtry		88.64 351	87.25 354	92.78 325	94.09 365	86.64 306	89.82 434	95.68 330	80.81 416	87.63 350	92.36 395	80.91 258	97.03 381	78.86 397	85.12 369	94.67 373

testing91		91.90 248	91.02 256	94.53 236	96.54 226	86.55 312	95.86 299	95.64 332	91.77 173	91.89 235	93.47 372	69.94 381	98.86 196	90.23 234	93.86 260	98.18 190

BH-RMVSNet		92.72 217	91.97 220	94.97 209	97.16 169	87.99 273	96.15 284	95.60 333	90.62 228	91.87 236	97.15 170	78.41 307	98.57 238	83.16 357	97.60 157	98.36 176

PVSNet_0	82.17 19	85.46 386	83.64 389	90.92 375	95.27 311	79.49 417	90.55 428	95.60 333	83.76 393	83.00 408	89.95 420	71.09 369	97.97 304	82.75 365	60.79 450	95.31 331

guyue		95.17 115	94.96 111	95.82 157	96.97 188	89.65 211	97.56 136	95.58 335	94.82 54	95.72 131	97.42 152	82.90 217	98.84 200	96.71 61	96.93 180	98.96 106

SCA		91.84 250	91.18 252	93.83 277	95.59 286	84.95 351	94.72 350	95.58 335	90.82 215	92.25 224	93.69 361	75.80 334	98.10 280	86.20 317	95.98 203	98.45 166

MonoMVSNet		91.92 246	91.77 226	92.37 333	92.94 399	83.11 373	97.09 194	95.55 337	92.91 140	90.85 262	94.55 314	81.27 254	96.52 396	93.01 173	87.76 338	97.47 243

AllTest		90.23 321	88.98 335	93.98 265	97.94 123	86.64 306	96.51 252	95.54 338	85.38 368	85.49 383	96.77 194	70.28 376	99.15 156	80.02 389	92.87 270	96.15 286

TestCases				93.98 265	97.94 123	86.64 306		95.54 338	85.38 368	85.49 383	96.77 194	70.28 376	99.15 156	80.02 389	92.87 270	96.15 286

mmtdpeth		89.70 338	88.96 336	91.90 350	95.84 278	84.42 356	97.46 156	95.53 340	90.27 240	94.46 166	90.50 414	69.74 385	98.95 186	97.39 47	69.48 439	92.34 416

tpmvs		89.83 335	89.15 333	91.89 351	94.92 333	80.30 405	93.11 405	95.46 341	86.28 355	88.08 342	92.65 385	80.44 268	98.52 242	81.47 374	89.92 317	96.84 266

pmmvs5		89.86 334	88.87 339	92.82 322	92.86 401	86.23 319	96.26 274	95.39 342	84.24 385	87.12 360	94.51 317	74.27 349	97.36 370	87.61 295	87.57 340	94.86 358

PatchmatchNet		91.91 247	91.35 241	93.59 291	95.38 299	84.11 361	93.15 404	95.39 342	89.54 260	92.10 229	93.68 363	82.82 220	98.13 275	84.81 339	95.32 224	98.52 156
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 271	91.32 243	91.79 356	95.15 321	79.20 420	93.42 399	95.37 344	88.55 299	93.49 195	93.67 364	82.49 229	98.27 264	90.41 229	89.34 323	97.90 215

Anonymous20231206		87.09 366	86.14 368	89.93 394	91.22 419	80.35 403	96.11 285	95.35 345	83.57 396	84.16 395	93.02 380	73.54 356	95.61 412	72.16 429	86.14 355	93.84 395

MIMVSNet1		84.93 389	83.05 391	90.56 384	89.56 429	84.84 353	95.40 325	95.35 345	83.91 388	80.38 420	92.21 400	57.23 432	93.34 435	70.69 435	82.75 400	93.50 398

TDRefinement		86.53 370	84.76 382	91.85 352	82.23 451	84.25 358	96.38 263	95.35 345	84.97 377	84.09 398	94.94 293	65.76 415	98.34 261	84.60 343	74.52 429	92.97 404

TR-MVS		91.48 270	90.59 278	94.16 255	96.40 240	87.33 286	95.67 310	95.34 348	87.68 328	91.46 246	95.52 270	76.77 325	98.35 258	82.85 362	93.61 266	96.79 268

EPNet_dtu		91.71 253	91.28 246	92.99 315	93.76 375	83.71 367	96.69 235	95.28 349	93.15 127	87.02 365	95.95 243	83.37 203	97.38 369	79.46 394	96.84 182	97.88 217
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 363	85.79 370	91.78 357	94.80 340	87.28 288	95.49 322	95.28 349	84.09 387	83.85 402	91.82 404	62.95 422	94.17 427	78.48 398	85.34 365	93.91 394

MDTV_nov1_ep13			90.76 268		95.22 315	80.33 404	93.03 407	95.28 349	88.14 312	92.84 213	93.83 354	81.34 251	98.08 285	82.86 360	94.34 243

LF4IMVS		87.94 357	87.25 354	89.98 392	92.38 413	80.05 411	94.38 364	95.25 352	87.59 330	84.34 392	94.74 305	64.31 418	97.66 344	84.83 338	87.45 341	92.23 419

TransMVSNet (Re)		88.94 345	87.56 351	93.08 313	94.35 358	88.45 258	97.73 108	95.23 353	87.47 332	84.26 394	95.29 277	79.86 280	97.33 371	79.44 395	74.44 430	93.45 400

test20.03		86.14 379	85.40 374	88.35 404	90.12 424	80.06 410	95.90 298	95.20 354	88.59 295	81.29 415	93.62 366	71.43 367	92.65 439	71.26 433	81.17 405	92.34 416

new-patchmatchnet		83.18 397	81.87 400	87.11 412	86.88 442	75.99 431	93.70 390	95.18 355	85.02 376	77.30 431	88.40 430	65.99 413	93.88 432	74.19 421	70.18 437	91.47 429

MDA-MVSNet_test_wron		85.87 383	84.23 386	90.80 381	92.38 413	82.57 378	93.17 402	95.15 356	82.15 405	67.65 443	92.33 398	78.20 309	95.51 415	77.33 403	79.74 409	94.31 385

YYNet1		85.87 383	84.23 386	90.78 382	92.38 413	82.46 383	93.17 402	95.14 357	82.12 406	67.69 441	92.36 395	78.16 312	95.50 416	77.31 404	79.73 410	94.39 381

Baseline_NR-MVSNet		91.20 286	90.62 276	92.95 317	93.83 373	88.03 272	97.01 201	95.12 358	88.42 303	89.70 293	95.13 287	83.47 200	97.44 364	89.66 246	83.24 395	93.37 401

thres200		92.23 236	91.39 240	94.75 224	97.61 148	89.03 242	96.60 247	95.09 359	92.08 165	93.28 201	94.00 350	78.39 308	99.04 182	81.26 381	94.18 249	96.19 282

ADS-MVSNet		89.89 331	88.68 341	93.53 295	95.86 273	84.89 352	90.93 425	95.07 360	83.23 399	91.28 255	91.81 405	79.01 298	97.85 323	79.52 391	91.39 297	97.84 222

pmmvs-eth3d		86.22 377	84.45 384	91.53 362	88.34 438	87.25 290	94.47 359	95.01 361	83.47 397	79.51 425	89.61 423	69.75 384	95.71 409	83.13 358	76.73 423	91.64 424

Anonymous202405211		92.07 242	90.83 266	95.76 161	98.19 102	88.75 247	97.58 132	95.00 362	86.00 360	93.64 187	97.45 148	66.24 411	99.53 105	90.68 223	92.71 275	99.01 98

MDA-MVSNet-bldmvs		85.00 388	82.95 393	91.17 373	93.13 397	83.33 370	94.56 355	95.00 362	84.57 382	65.13 447	92.65 385	70.45 375	95.85 406	73.57 424	77.49 419	94.33 383

ambc				86.56 415	83.60 448	70.00 442	85.69 446	94.97 364		80.60 419	88.45 429	37.42 450	96.84 390	82.69 366	75.44 427	92.86 406

testgi		87.97 356	87.21 356	90.24 389	92.86 401	80.76 396	96.67 238	94.97 364	91.74 174	85.52 382	95.83 249	62.66 424	94.47 425	76.25 410	88.36 333	95.48 314

myMVS_eth3d28		91.52 267	90.97 258	93.17 309	96.91 190	83.24 372	95.61 316	94.96 366	92.24 156	91.98 232	93.28 377	69.31 386	98.40 250	88.71 271	95.68 213	97.88 217

dp		88.90 347	88.26 347	90.81 379	94.58 351	76.62 428	92.85 410	94.93 367	85.12 374	90.07 284	93.07 379	75.81 333	98.12 278	80.53 386	87.42 343	97.71 229

test_fmvs3		83.21 396	83.02 392	83.78 419	86.77 443	68.34 445	96.76 227	94.91 368	86.49 350	84.14 397	89.48 424	36.04 451	91.73 441	91.86 194	80.77 407	91.26 431

test_0402		86.46 373	84.79 381	91.45 364	95.02 327	85.55 335	96.29 273	94.89 369	80.90 413	82.21 411	93.97 352	68.21 397	97.29 373	62.98 442	88.68 330	91.51 427

tfpn200view9		92.38 226	91.52 237	94.95 211	97.85 129	89.29 232	97.41 159	94.88 370	92.19 161	93.27 202	94.46 322	78.17 310	99.08 170	81.40 375	94.08 253	96.48 275

CVMVSNet		91.23 284	91.75 228	89.67 396	95.77 279	74.69 432	96.44 253	94.88 370	85.81 362	92.18 225	97.64 135	79.07 293	95.58 414	88.06 279	95.86 208	98.74 139

thres400		92.42 224	91.52 237	95.12 198	97.85 129	89.29 232	97.41 159	94.88 370	92.19 161	93.27 202	94.46 322	78.17 310	99.08 170	81.40 375	94.08 253	96.98 260

tt0320		85.39 387	83.12 390	92.19 343	93.44 389	85.79 331	96.19 281	94.87 373	71.19 441	82.92 409	91.76 407	58.43 430	96.81 391	81.03 383	78.26 418	93.98 392

EPNet		95.20 113	94.56 124	97.14 71	92.80 403	92.68 93	97.85 88	94.87 373	96.64 6	92.46 215	97.80 120	86.23 149	99.65 72	93.72 154	98.62 117	99.10 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 258	90.72 273	94.32 247	96.48 234	86.11 328	95.81 302	94.76 375	91.55 178	91.75 240	93.44 373	68.55 394	98.82 202	90.43 228	93.69 262	98.04 207

sc_t1		86.48 372	84.10 388	93.63 288	93.45 388	85.76 332	96.79 222	94.71 376	73.06 439	86.45 375	94.35 327	55.13 437	97.95 312	84.38 346	78.55 417	97.18 256

SixPastTwentyTwo		89.15 343	88.54 343	90.98 374	93.49 385	80.28 407	96.70 233	94.70 377	90.78 216	84.15 396	95.57 266	71.78 365	97.71 340	84.63 342	85.07 370	94.94 351

thres100view900		92.43 223	91.58 234	94.98 207	97.92 125	89.37 228	97.71 113	94.66 378	92.20 159	93.31 200	94.90 296	78.06 314	99.08 170	81.40 375	94.08 253	96.48 275

thres600view7		92.49 221	91.60 233	95.18 194	97.91 126	89.47 222	97.65 122	94.66 378	92.18 163	93.33 199	94.91 295	78.06 314	99.10 164	81.61 371	94.06 257	96.98 260

PatchT		88.87 348	87.42 352	93.22 307	94.08 366	85.10 346	89.51 435	94.64 380	81.92 407	92.36 219	88.15 433	80.05 276	97.01 383	72.43 428	93.65 264	97.54 240

baseline1		92.82 213	91.90 223	95.55 177	97.20 167	90.77 174	97.19 186	94.58 381	92.20 159	92.36 219	96.34 223	84.16 190	98.21 268	89.20 261	83.90 390	97.68 231

AstraMVS		94.82 129	94.64 120	95.34 189	96.36 244	88.09 271	97.58 132	94.56 382	94.98 43	95.70 134	97.92 105	81.93 243	98.93 189	96.87 55	95.88 206	98.99 102

UBG		91.55 264	90.76 268	93.94 271	96.52 230	85.06 347	95.22 337	94.54 383	90.47 236	91.98 232	92.71 384	72.02 362	98.74 216	88.10 278	95.26 226	98.01 209

Gipuma		67.86 417	65.41 419	75.18 432	92.66 406	73.45 436	66.50 453	94.52 384	53.33 452	57.80 453	66.07 453	30.81 453	89.20 445	48.15 451	78.88 416	62.90 453
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 256	90.75 270	94.47 238	96.53 228	86.56 311	95.76 306	94.51 385	91.10 208	91.24 257	93.59 367	68.59 393	98.86 196	91.10 211	94.29 245	98.00 210

CostFormer		91.18 289	90.70 274	92.62 330	94.84 338	81.76 389	94.09 376	94.43 386	84.15 386	92.72 214	93.77 358	79.43 287	98.20 269	90.70 222	92.18 284	97.90 215

tpm2		89.96 328	89.21 331	92.23 342	94.91 335	81.25 392	93.78 387	94.42 387	80.62 418	91.56 243	93.44 373	76.44 329	97.94 314	85.60 329	92.08 288	97.49 241

testing3-2		92.10 241	92.05 215	92.27 339	97.71 138	79.56 414	97.42 158	94.41 388	93.53 108	93.22 204	95.49 271	69.16 388	99.11 162	93.25 163	94.22 247	98.13 195

MVS_0304		96.74 58	96.31 75	98.02 19	96.87 192	94.65 30	97.58 132	94.39 389	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		88.26 355	87.04 359	91.91 349	93.52 383	81.42 391	89.38 436	94.38 390	80.84 415	90.93 261	80.74 445	79.22 290	97.92 317	82.76 364	91.62 292	96.38 278

dmvs_re		90.21 322	89.50 324	92.35 334	95.47 296	85.15 344	95.70 309	94.37 391	90.94 214	88.42 329	93.57 368	74.63 346	95.67 411	82.80 363	89.57 321	96.22 280

Patchmatch-test		89.42 341	87.99 348	93.70 285	95.27 311	85.11 345	88.98 437	94.37 391	81.11 412	87.10 363	93.69 361	82.28 233	97.50 359	74.37 419	94.76 236	98.48 163

LCM-MVSNet		72.55 410	69.39 414	82.03 421	70.81 461	65.42 450	90.12 432	94.36 393	55.02 451	65.88 445	81.72 444	24.16 459	89.96 442	74.32 420	68.10 442	90.71 434

ADS-MVSNet2		89.45 340	88.59 342	92.03 346	95.86 273	82.26 385	90.93 425	94.32 394	83.23 399	91.28 255	91.81 405	79.01 298	95.99 403	79.52 391	91.39 297	97.84 222

mvs5depth		86.53 370	85.08 377	90.87 376	88.74 436	82.52 380	91.91 418	94.23 395	86.35 353	87.11 362	93.70 360	66.52 407	97.76 335	81.37 378	75.80 425	92.31 418

EU-MVSNet		88.72 350	88.90 338	88.20 406	93.15 396	74.21 434	96.63 244	94.22 396	85.18 372	87.32 357	95.97 241	76.16 331	94.98 420	85.27 334	86.17 354	95.41 321

tt0320-xc		84.83 390	82.33 398	92.31 337	93.66 379	86.20 321	96.17 283	94.06 397	71.26 440	82.04 413	92.22 399	55.07 438	96.72 394	81.49 373	75.04 428	94.02 391

MIMVSNet		88.50 352	86.76 362	93.72 284	94.84 338	87.77 281	91.39 420	94.05 398	86.41 352	87.99 344	92.59 388	63.27 420	95.82 408	77.44 402	92.84 272	97.57 239

OpenMVS_ROB	81.14 20	84.42 393	82.28 399	90.83 377	90.06 425	84.05 363	95.73 308	94.04 399	73.89 437	80.17 423	91.53 409	59.15 428	97.64 345	66.92 440	89.05 325	90.80 433

TinyColmap		86.82 368	85.35 375	91.21 369	94.91 335	82.99 375	93.94 380	94.02 400	83.58 395	81.56 414	94.68 307	62.34 425	98.13 275	75.78 411	87.35 346	92.52 414

ETVMVS		90.52 313	89.14 334	94.67 227	96.81 201	87.85 279	95.91 297	93.97 401	89.71 256	92.34 222	92.48 390	65.41 416	97.96 308	81.37 378	94.27 246	98.21 188

IB-MVS	87.33 17	89.91 329	88.28 346	94.79 221	95.26 314	87.70 282	95.12 342	93.95 402	89.35 268	87.03 364	92.49 389	70.74 373	99.19 147	89.18 262	81.37 404	97.49 241
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		87.13 365	87.02 360	87.47 410	95.16 318	73.21 438	95.00 344	93.93 403	88.55 299	86.96 366	91.99 401	75.90 332	94.00 429	61.59 444	94.11 250	95.20 339

myMVS_eth3d		87.18 364	86.38 365	89.58 397	95.16 318	79.53 415	95.00 344	93.93 403	88.55 299	86.96 366	91.99 401	56.23 435	94.00 429	75.47 415	94.11 250	95.20 339

testing222		90.31 317	88.96 336	94.35 244	96.54 226	87.29 287	95.50 321	93.84 405	90.97 211	91.75 240	92.96 381	62.18 426	98.00 299	82.86 360	94.08 253	97.76 227

test_f		80.57 403	79.62 405	83.41 420	83.38 449	67.80 447	93.57 397	93.72 406	80.80 417	77.91 430	87.63 436	33.40 452	92.08 440	87.14 306	79.04 415	90.34 435

LCM-MVSNet-Re		92.50 219	92.52 203	92.44 331	96.82 199	81.89 388	96.92 210	93.71 407	92.41 153	84.30 393	94.60 312	85.08 171	97.03 381	91.51 202	97.36 165	98.40 172

tpm		90.25 320	89.74 318	91.76 359	93.92 369	79.73 413	93.98 377	93.54 408	88.28 306	91.99 231	93.25 378	77.51 320	97.44 364	87.30 301	87.94 336	98.12 197

ET-MVSNet_ETH3D		91.49 269	90.11 298	95.63 171	96.40 240	91.57 137	95.34 328	93.48 409	90.60 231	75.58 433	95.49 271	80.08 275	96.79 392	94.25 142	89.76 319	98.52 156

LFMVS		93.60 175	92.63 196	96.52 101	98.13 108	91.27 148	97.94 76	93.39 410	90.57 233	96.29 108	98.31 74	69.00 389	99.16 154	94.18 143	95.87 207	99.12 87

MVStest1		82.38 400	80.04 404	89.37 399	87.63 441	82.83 376	95.03 343	93.37 411	73.90 436	73.50 438	94.35 327	62.89 423	93.25 437	73.80 422	65.92 445	92.04 423

Patchmatch-RL test		87.38 362	86.24 366	90.81 379	88.74 436	78.40 424	88.12 444	93.17 412	87.11 341	82.17 412	89.29 425	81.95 241	95.60 413	88.64 273	77.02 420	98.41 171

ttmdpeth		85.91 382	84.76 382	89.36 400	89.14 431	80.25 408	95.66 313	93.16 413	83.77 392	83.39 404	95.26 281	66.24 411	95.26 419	80.65 384	75.57 426	92.57 411

test-LLR		91.42 272	91.19 251	92.12 344	94.59 349	80.66 398	94.29 370	92.98 414	91.11 206	90.76 264	92.37 392	79.02 296	98.07 289	88.81 268	96.74 185	97.63 232

test-mter		90.19 324	89.54 323	92.12 344	94.59 349	80.66 398	94.29 370	92.98 414	87.68 328	90.76 264	92.37 392	67.67 398	98.07 289	88.81 268	96.74 185	97.63 232

WB-MVSnew		89.88 332	89.56 322	90.82 378	94.57 352	83.06 374	95.65 314	92.85 416	87.86 319	90.83 263	94.10 344	79.66 284	96.88 388	76.34 409	94.19 248	92.54 413

testing3		87.67 360	86.88 361	90.05 391	96.14 262	80.71 397	97.10 193	92.85 416	90.15 244	87.54 351	94.55 314	55.70 436	94.10 428	73.77 423	94.10 252	95.35 328

test_method		66.11 418	64.89 420	69.79 435	72.62 459	35.23 467	65.19 454	92.83 418	20.35 457	65.20 446	88.08 434	43.14 448	82.70 452	73.12 426	63.46 447	91.45 430

test0.0.03 1		89.37 342	88.70 340	91.41 366	92.47 410	85.63 334	95.22 337	92.70 419	91.11 206	86.91 370	93.65 365	79.02 296	93.19 438	78.00 401	89.18 324	95.41 321

new_pmnet		82.89 398	81.12 403	88.18 407	89.63 428	80.18 409	91.77 419	92.57 420	76.79 432	75.56 434	88.23 432	61.22 427	94.48 424	71.43 431	82.92 398	89.87 436

mvsany_test1		93.93 164	93.98 143	93.78 281	94.94 332	86.80 302	94.62 352	92.55 421	88.77 293	96.85 77	98.49 51	88.98 96	98.08 285	95.03 119	95.62 215	96.46 277

thisisatest0515		92.29 232	91.30 245	95.25 192	96.60 217	88.90 245	94.36 365	92.32 422	87.92 316	93.43 197	94.57 313	77.28 321	99.00 183	89.42 252	95.86 208	97.86 221

thisisatest0530		93.03 200	92.21 212	95.49 181	97.07 174	89.11 241	97.49 153	92.19 423	90.16 243	94.09 175	96.41 219	76.43 330	99.05 179	90.38 230	95.68 213	98.31 182

tttt0517		92.96 203	92.33 209	94.87 214	97.11 172	87.16 295	97.97 72	92.09 424	90.63 227	93.88 181	97.01 183	76.50 327	99.06 176	90.29 233	95.45 222	98.38 174

K. test v3		87.64 361	86.75 363	90.32 388	93.02 398	79.48 418	96.61 245	92.08 425	90.66 225	80.25 422	94.09 346	67.21 402	96.65 395	85.96 325	80.83 406	94.83 360

TESTMET0.1,1		90.06 326	89.42 326	91.97 347	94.41 357	80.62 400	94.29 370	91.97 426	87.28 338	90.44 268	92.47 391	68.79 390	97.67 342	88.50 275	96.60 190	97.61 236

PM-MVS		83.48 395	81.86 401	88.31 405	87.83 440	77.59 426	93.43 398	91.75 427	86.91 343	80.63 418	89.91 421	44.42 447	95.84 407	85.17 337	76.73 423	91.50 428

baseline2		91.63 257	90.86 262	93.94 271	94.33 359	86.32 316	95.92 296	91.64 428	89.37 267	86.94 368	94.69 306	81.62 248	98.69 223	88.64 273	94.57 241	96.81 267

APD_test1		79.31 405	77.70 408	84.14 418	89.11 433	69.07 444	92.36 417	91.50 429	69.07 443	73.87 436	92.63 387	39.93 449	94.32 426	70.54 436	80.25 408	89.02 438

FPMVS		71.27 411	69.85 413	75.50 431	74.64 456	59.03 456	91.30 421	91.50 429	58.80 448	57.92 452	88.28 431	29.98 455	85.53 451	53.43 449	82.84 399	81.95 444

door								91.13 431

door-mid								91.06 432

EGC-MVSNET		68.77 416	63.01 422	86.07 417	92.49 409	82.24 386	93.96 379	90.96 433	0.71 462	2.62 463	90.89 412	53.66 439	93.46 433	57.25 447	84.55 380	82.51 443

mvsany_test3		83.59 394	82.44 397	87.03 413	83.80 446	73.82 435	93.70 390	90.92 434	86.42 351	82.51 410	90.26 417	46.76 446	95.71 409	90.82 217	76.76 422	91.57 426

pmmvs3		79.97 404	77.50 409	87.39 411	82.80 450	79.38 419	92.70 412	90.75 435	70.69 442	78.66 427	87.47 438	51.34 442	93.40 434	73.39 425	69.65 438	89.38 437

UWE-MVS		89.91 329	89.48 325	91.21 369	95.88 272	78.23 425	94.91 347	90.26 436	89.11 274	92.35 221	94.52 316	68.76 391	97.96 308	83.95 352	95.59 216	97.42 245

DSMNet-mixed		86.34 375	86.12 369	87.00 414	89.88 427	70.43 440	94.93 346	90.08 437	77.97 429	85.42 385	92.78 383	74.44 348	93.96 431	74.43 418	95.14 227	96.62 271

MVS-HIRNet		82.47 399	81.21 402	86.26 416	95.38 299	69.21 443	88.96 438	89.49 438	66.28 445	80.79 417	74.08 450	68.48 395	97.39 368	71.93 430	95.47 221	92.18 421

WB-MVS		76.77 407	76.63 410	77.18 426	85.32 444	56.82 458	94.53 356	89.39 439	82.66 403	71.35 439	89.18 426	75.03 341	88.88 446	35.42 455	66.79 443	85.84 440

test1111		93.19 192	92.82 186	94.30 250	97.58 154	84.56 355	98.21 43	89.02 440	93.53 108	94.58 161	98.21 81	72.69 358	99.05 179	93.06 169	98.48 124	99.28 72

SSC-MVS		76.05 408	75.83 411	76.72 430	84.77 445	56.22 459	94.32 368	88.96 441	81.82 409	70.52 440	88.91 427	74.79 345	88.71 447	33.69 456	64.71 446	85.23 441

ECVR-MVS		93.19 192	92.73 192	94.57 233	97.66 142	85.41 338	98.21 43	88.23 442	93.43 113	94.70 159	98.21 81	72.57 359	99.07 174	93.05 170	98.49 122	99.25 75

EPMVS		90.70 307	89.81 313	93.37 301	94.73 344	84.21 359	93.67 393	88.02 443	89.50 262	92.38 218	93.49 370	77.82 318	97.78 332	86.03 323	92.68 276	98.11 202

ANet_high		63.94 420	59.58 423	77.02 427	61.24 463	66.06 448	85.66 447	87.93 444	78.53 427	42.94 455	71.04 452	25.42 458	80.71 454	52.60 450	30.83 456	84.28 442

PMMVS2		70.19 412	66.92 416	80.01 422	76.35 455	65.67 449	86.22 445	87.58 445	64.83 447	62.38 448	80.29 447	26.78 457	88.49 449	63.79 441	54.07 452	85.88 439

lessismore_v0				90.45 385	91.96 416	79.09 422		87.19 446		80.32 421	94.39 324	66.31 410	97.55 353	84.00 351	76.84 421	94.70 372

PMVS	53.92 22	58.58 421	55.40 424	68.12 436	51.00 464	48.64 461	78.86 450	87.10 447	46.77 453	35.84 459	74.28 449	8.76 463	86.34 450	42.07 453	73.91 431	69.38 450
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 369	86.41 364	88.02 408	92.87 400	74.60 433	95.38 327	86.70 448	88.17 309	87.28 359	94.67 309	70.83 372	93.30 436	67.45 438	94.31 244	96.17 283

test_vis1_rt		86.16 378	85.06 378	89.46 398	93.47 387	80.46 402	96.41 257	86.61 449	85.22 371	79.15 426	88.64 428	52.41 441	97.06 379	93.08 168	90.57 310	90.87 432

testf1		69.31 414	66.76 417	76.94 428	78.61 453	61.93 452	88.27 442	86.11 450	55.62 449	59.69 449	85.31 441	20.19 461	89.32 443	57.62 445	69.44 440	79.58 445

APD_test2		69.31 414	66.76 417	76.94 428	78.61 453	61.93 452	88.27 442	86.11 450	55.62 449	59.69 449	85.31 441	20.19 461	89.32 443	57.62 445	69.44 440	79.58 445

gg-mvs-nofinetune		87.82 358	85.61 371	94.44 240	94.46 354	89.27 235	91.21 424	84.61 452	80.88 414	89.89 288	74.98 448	71.50 366	97.53 356	85.75 328	97.21 174	96.51 273

dmvs_testset		81.38 402	82.60 396	77.73 425	91.74 417	51.49 460	93.03 407	84.21 453	89.07 275	78.28 429	91.25 411	76.97 323	88.53 448	56.57 448	82.24 401	93.16 402

GG-mvs-BLEND				93.62 289	93.69 377	89.20 237	92.39 416	83.33 454		87.98 345	89.84 422	71.00 370	96.87 389	82.08 370	95.40 223	94.80 365

MTMP							97.86 85	82.03 455

DeepMVS_CX				74.68 433	90.84 422	64.34 451		81.61 456	65.34 446	67.47 444	88.01 435	48.60 445	80.13 455	62.33 443	73.68 432	79.58 445

E-PMN		53.28 422	52.56 426	55.43 439	74.43 457	47.13 462	83.63 449	76.30 457	42.23 454	42.59 456	62.22 455	28.57 456	74.40 456	31.53 457	31.51 455	44.78 454

test2506		91.60 259	90.78 267	94.04 261	97.66 142	83.81 364	98.27 33	75.53 458	93.43 113	95.23 145	98.21 81	67.21 402	99.07 174	93.01 173	98.49 122	99.25 75

EMVS		52.08 424	51.31 427	54.39 440	72.62 459	45.39 464	83.84 448	75.51 459	41.13 455	40.77 457	59.65 456	30.08 454	73.60 457	28.31 459	29.90 457	44.18 455

test_vis3_rt		72.73 409	70.55 412	79.27 423	80.02 452	68.13 446	93.92 382	74.30 460	76.90 431	58.99 451	73.58 451	20.29 460	95.37 417	84.16 347	72.80 434	74.31 448

MVE	50.73 23	53.25 423	48.81 428	66.58 438	65.34 462	57.50 457	72.49 452	70.94 461	40.15 456	39.28 458	63.51 454	6.89 465	73.48 458	38.29 454	42.38 454	68.76 452
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 425	53.82 425	46.29 441	33.73 465	45.30 465	78.32 451	67.24 462	18.02 458	50.93 454	87.05 439	52.99 440	53.11 460	70.76 434	25.29 458	40.46 456

kuosan		65.27 419	64.66 421	67.11 437	83.80 446	61.32 455	88.53 441	60.77 463	68.22 444	67.67 442	80.52 446	49.12 444	70.76 459	29.67 458	53.64 453	69.26 451

dongtai		69.99 413	69.33 415	71.98 434	88.78 435	61.64 454	89.86 433	59.93 464	75.67 433	74.96 435	85.45 440	50.19 443	81.66 453	43.86 452	55.27 451	72.63 449

N_pmnet		78.73 406	78.71 407	78.79 424	92.80 403	46.50 463	94.14 374	43.71 465	78.61 426	80.83 416	91.66 408	74.94 344	96.36 399	67.24 439	84.45 382	93.50 398

wuyk23d		25.11 426	24.57 430	26.74 442	73.98 458	39.89 466	57.88 455	9.80 466	12.27 459	10.39 460	6.97 462	7.03 464	36.44 461	25.43 460	17.39 459	3.89 459

testmvs		13.36 428	16.33 431	4.48 444	5.04 466	2.26 469	93.18 401	3.28 467	2.70 460	8.24 461	21.66 458	2.29 467	2.19 462	7.58 461	2.96 460	9.00 458

test123		13.04 429	15.66 432	5.18 443	4.51 467	3.45 468	92.50 415	1.81 468	2.50 461	7.58 462	20.15 459	3.67 466	2.18 463	7.13 462	1.07 461	9.90 457

mmdepth		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

monomultidepth		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

test_blank		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uanet_test		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

DCPMVS		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

pcd_1.5k_mvsjas		7.39 431	9.85 434	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	88.65 104	0.00 464	0.00 463	0.00 462	0.00 460

sosnet-low-res		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

sosnet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uncertanet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

Regformer		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

n2								0.00 469

nn								0.00 469

ab-mvs-re		8.06 430	10.74 433	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	96.69 200	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uanet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

WAC-MVS						79.53 415								75.56 414

PC_three_1452									90.77 217	98.89 23	98.28 79	96.24 1	98.35 258	95.76 98	99.58 23	99.59 27

eth-test2					0.00 468

eth-test					0.00 468

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																98.45 166

test_part2					99.28 27	95.74 8				98.10 41

sam_mvs1												82.76 221				98.45 166

sam_mvs												81.94 242

test_post1							92.81 411				16.58 461	80.53 266	97.68 341	86.20 317

test_post											17.58 460	81.76 245	98.08 285

patchmatchnet-post											90.45 416	82.65 226	98.10 280

gm-plane-assit					93.22 394	78.89 423			84.82 379		93.52 369		98.64 229	87.72 285

test9_res														94.81 129	99.38 59	99.45 54

agg_prior2														93.94 148	99.38 59	99.50 47

test_prior4						93.66 58	96.42 256

test_prior2							96.35 265		92.80 145	96.03 118	97.59 141	92.01 47		95.01 120	99.38 59

旧先验2							95.94 294		81.66 410	97.34 63			98.82 202	92.26 179

新几何2							95.79 304

原ACMM2							95.67 310

testdata2													99.67 70	85.96 325

segment_acmp												92.89 30

testdata1							95.26 336		93.10 130

plane_prior7					96.21 249	89.98 203

plane_prior6					96.10 265	90.00 199						81.32 252

plane_prior4											96.64 203

plane_prior3						90.00 199			94.46 75	91.34 249

plane_prior2							97.74 106		94.85 50

plane_prior1					96.14 262

plane_prior						89.99 201	97.24 178		94.06 87						92.16 285

HQP5-MVS						89.33 230

HQP-NCC					95.86 273		96.65 239		93.55 104	90.14 273

ACMP_Plane					95.86 273		96.65 239		93.55 104	90.14 273

BP-MVS														92.13 187

HQP4-MVS										90.14 273			98.50 243			95.78 302

HQP2-MVS												80.95 256

NP-MVS					95.99 271	89.81 209					95.87 246

MDTV_nov1_ep13_2view						70.35 441	93.10 406		83.88 390	93.55 190		82.47 230		86.25 316		98.38 174

ACMMP++_ref															90.30 315

ACMMP++															91.02 304

Test By Simon												88.73 103

High-resolution multi-view benchmark