High-res multi-view results

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

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

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

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

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

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

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

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 2

sc_t1		97.21 9	97.71 4	95.71 78	99.06 10	88.89 142	96.72 31	97.79 139	98.34 2	98.97 2	99.40 5	96.81 9	98.79 160	92.58 130	99.72 15	99.45 23

fmvsm_l_mol_unc0.5_1		94.01 173	95.09 124	90.74 363	96.48 234	76.52 448	89.38 392	97.59 160	89.00 219	98.96 3	98.98 12	91.62 164	97.76 327	94.82 52	99.01 131	97.93 228

UniMVSNet_ETH3D		97.13 10	97.72 3	95.35 97	99.51 2	87.38 181	97.70 8	97.54 166	98.16 5	98.94 4	99.33 6	97.84 4	99.08 111	90.73 190	99.73 14	99.59 15

OurMVSNet-221017-0		96.80 19	96.75 25	96.96 38	99.03 12	91.85 82	97.98 7	98.01 102	94.15 64	98.93 5	99.07 10	88.07 252	99.57 14	95.86 27	99.69 17	99.46 22

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 29	98.81 32	93.86 40	99.07 2	98.98 8	97.01 17	98.92 6	98.78 20	95.22 47	98.61 196	96.85 11	99.77 9	99.31 33
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
tt0320		96.97 13	97.64 6	94.96 120	98.89 23	86.86 197	96.85 23	98.45 25	98.29 3	98.88 7	99.45 3	96.48 13	98.54 214	91.73 156	99.72 15	99.47 21

tt0320-xc		97.00 12	97.67 5	94.98 117	98.89 23	86.94 195	96.72 31	98.46 24	98.28 4	98.86 8	99.43 4	96.80 10	98.51 222	91.79 153	99.76 10	99.50 19

LCM-MVSNet-Re		94.20 163	94.58 151	93.04 224	95.91 296	83.13 285	93.79 179	99.19 5	92.00 117	98.84 9	98.04 53	93.64 101	99.02 123	81.28 406	98.54 222	96.96 325

PS-MVSNAJss		96.01 59	96.04 63	95.89 71	98.82 30	88.51 154	95.57 97	97.88 123	88.72 228	98.81 10	98.86 16	90.77 197	99.60 9	95.43 40	99.53 39	99.57 16

mvs_tets		96.83 15	96.71 26	97.17 30	98.83 29	92.51 70	96.58 38	97.61 156	87.57 270	98.80 11	98.90 15	96.50 12	99.59 13	96.15 22	99.47 44	99.40 27

Anonymous20231211		96.60 32	97.13 19	95.00 116	97.46 145	86.35 214	97.11 18	98.24 54	97.58 11	98.72 12	98.97 13	93.15 120	99.15 99	93.18 107	99.74 13	99.50 19

ACMH	88.36 12	96.59 34	97.43 9	94.07 169	98.56 49	85.33 243	96.33 54	98.30 41	94.66 54	98.72 12	98.30 41	97.51 5	98.00 298	94.87 50	99.59 29	98.86 94
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
jajsoiax		96.59 34	96.42 38	97.12 32	98.76 35	92.49 71	96.44 48	97.42 178	86.96 289	98.71 14	98.72 23	95.36 38	99.56 17	95.92 25	99.45 48	99.32 32

wuyk23d		87.83 395	90.79 302	78.96 525	90.46 497	88.63 147	92.72 232	90.67 441	91.65 140	98.68 15	97.64 90	96.06 19	77.53 548	59.84 541	99.41 60	70.73 546

DTE-MVSNet		96.74 24	97.43 9	94.67 139	99.13 6	84.68 251	96.51 41	97.94 115	98.14 6	98.67 16	98.32 40	95.04 56	99.69 3	93.27 104	99.82 7	99.62 13

PS-CasMVS		96.69 27	97.43 9	94.49 153	99.13 6	84.09 264	96.61 37	97.97 107	97.91 8	98.64 17	98.13 46	95.24 45	99.65 4	93.39 98	99.84 3	99.72 4

PEN-MVS		96.69 27	97.39 12	94.61 142	99.16 4	84.50 253	96.54 39	98.05 92	98.06 7	98.64 17	98.25 43	95.01 59	99.65 4	92.95 116	99.83 5	99.68 7

SixPastTwentyTwo		94.91 113	95.21 112	93.98 172	98.52 57	83.19 282	95.93 79	94.84 340	94.86 53	98.49 19	98.74 22	81.45 346	99.60 9	94.69 53	99.39 62	99.15 48

WR-MVS_H		96.60 32	97.05 20	95.24 106	99.02 13	86.44 210	96.78 28	98.08 83	97.42 12	98.48 20	97.86 74	91.76 162	99.63 7	94.23 64	99.84 3	99.66 9

v7n		96.82 16	97.31 14	95.33 99	98.54 55	86.81 198	96.83 24	98.07 86	96.59 25	98.46 21	98.43 38	92.91 131	99.52 19	96.25 21	99.76 10	99.65 11

anonymousdsp		96.74 24	96.42 38	97.68 7	98.00 102	94.03 29	96.97 19	97.61 156	87.68 267	98.45 22	98.77 21	94.20 90	99.50 23	96.70 13	99.40 61	99.53 17

CP-MVSNet		96.19 54	96.80 23	94.38 158	98.99 19	83.82 267	96.31 61	97.53 169	97.60 10	98.34 23	97.52 101	91.98 156	99.63 7	93.08 112	99.81 8	99.70 5

reproduce_model		97.35 4	97.24 15	97.70 4	98.44 67	95.08 12	95.88 82	98.50 21	96.62 24	98.27 24	97.93 63	94.57 79	99.50 23	95.57 35	99.35 67	98.52 151

test_fmvsmvis_n_1920		95.08 108	95.40 101	94.13 167	96.66 208	87.75 176	93.44 196	98.49 23	85.57 330	98.27 24	97.11 153	94.11 93	97.75 329	96.26 20	98.72 197	96.89 330

FOURS1					99.21 3	94.68 16	98.45 4	98.81 10	97.73 9	98.27 24

test_djsdf		96.62 30	96.49 35	97.01 35	98.55 53	91.77 85	97.15 15	97.37 181	88.98 220	98.26 27	98.86 16	93.35 112	99.60 9	96.41 18	99.45 48	99.66 9

reproduce-ours		97.28 7	97.19 17	97.57 11	98.37 72	94.84 13	95.57 97	98.40 30	96.36 31	98.18 28	97.78 76	95.47 32	99.50 23	95.26 46	99.33 73	98.36 171

our_new_method		97.28 7	97.19 17	97.57 11	98.37 72	94.84 13	95.57 97	98.40 30	96.36 31	98.18 28	97.78 76	95.47 32	99.50 23	95.26 46	99.33 73	98.36 171

ACMH+	88.43 11	96.48 38	96.82 22	95.47 92	98.54 55	89.06 138	95.65 91	98.61 15	96.10 36	98.16 30	97.52 101	96.90 7	98.62 195	90.30 210	99.60 27	98.72 121

Elysia		96.00 60	96.36 43	94.91 122	98.01 100	85.96 227	95.29 110	97.90 118	95.31 45	98.14 31	97.28 132	88.82 235	99.51 20	97.08 7	99.38 63	99.26 37

StellarMVS		96.00 60	96.36 43	94.91 122	98.01 100	85.96 227	95.29 110	97.90 118	95.31 45	98.14 31	97.28 132	88.82 235	99.51 20	97.08 7	99.38 63	99.26 37

pmmvs6		96.80 19	97.36 13	95.15 112	99.12 8	87.82 175	96.68 33	97.86 126	96.10 36	98.14 31	99.28 8	97.94 3	98.21 263	91.38 169	99.69 17	99.42 24

ANet_high		94.83 118	96.28 48	90.47 374	96.65 209	73.16 483	94.33 150	98.74 13	96.39 30	98.09 34	98.93 14	93.37 111	98.70 182	90.38 202	99.68 20	99.53 17

nrg030		96.32 49	96.55 34	95.62 84	97.83 114	88.55 153	95.77 86	98.29 44	92.68 94	98.03 35	97.91 71	95.13 50	98.95 135	93.85 75	99.49 43	99.36 30

MIMVSNet1		95.52 82	95.45 95	95.72 77	99.14 5	89.02 139	96.23 68	96.87 234	93.73 76	97.87 36	98.49 34	90.73 201	99.05 118	86.43 329	99.60 27	99.10 57

dcpmvs_2		93.96 176	95.01 127	90.82 359	97.60 134	74.04 477	93.68 184	98.85 9	89.80 199	97.82 37	97.01 164	91.14 187	99.21 92	90.56 194	98.59 215	99.19 45

test_vis3_rt		90.40 313	90.03 326	91.52 313	92.58 426	88.95 140	90.38 346	97.72 146	73.30 493	97.79 38	97.51 105	77.05 407	87.10 530	89.03 259	94.89 453	98.50 153

TransMVSNet (Re)		95.27 101	96.04 63	92.97 227	98.37 72	81.92 311	95.07 121	96.76 246	93.97 70	97.77 39	98.57 29	95.72 24	97.90 305	88.89 264	99.23 95	99.08 58

RoMa-HiRes		94.64 129	94.29 166	95.68 81	97.47 144	93.88 37	93.83 178	96.23 282	88.05 254	97.75 40	96.20 239	88.58 241	94.93 459	91.33 170	99.17 109	98.22 188

DPE-MVS		95.89 66	95.88 75	95.92 68	97.93 108	89.83 121	93.46 194	98.30 41	92.37 102	97.75 40	96.95 167	95.14 49	99.51 20	91.74 155	99.28 88	98.41 164
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
lecture		97.32 6	97.64 6	96.33 54	99.01 15	90.77 107	96.90 21	98.60 16	96.30 33	97.74 42	98.00 56	96.87 8	99.39 54	95.95 24	99.42 54	98.84 98

test_0402		95.73 73	96.22 51	94.26 161	98.19 85	85.77 233	93.24 203	97.24 199	96.88 20	97.69 43	97.77 80	94.12 92	99.13 104	91.54 165	99.29 83	97.88 240

TestfortrainingZip a		96.50 36	96.80 23	95.62 84	98.69 37	88.28 158	96.32 56	98.06 90	94.10 65	97.65 44	97.37 116	94.54 82	99.28 85	95.41 42	99.04 127	99.30 34

NR-MVSNet		95.28 98	95.28 110	95.26 104	97.75 120	87.21 185	95.08 120	97.37 181	93.92 74	97.65 44	95.90 260	90.10 218	99.33 76	90.11 221	99.66 23	99.26 37

SED-MVS		96.00 60	96.41 41	94.76 132	98.51 58	86.97 192	95.21 114	98.10 80	91.95 118	97.63 46	97.25 135	96.48 13	99.35 67	93.29 102	99.29 83	97.95 223

test_241102_ONE					98.51 58	86.97 192		98.10 80	91.85 125	97.63 46	97.03 161	96.48 13	98.95 135

test0726					98.51 58	86.69 202	95.34 105	98.18 63	91.85 125	97.63 46	97.37 116	95.58 28

Anonymous20240529		95.50 83	95.83 79	94.50 151	97.33 153	85.93 229	95.19 118	96.77 245	96.64 23	97.61 49	98.05 51	93.23 117	98.79 160	88.60 276	99.04 127	98.78 111

test_fmvsmconf0.01_n		95.90 65	96.09 58	95.31 102	97.30 155	89.21 133	94.24 155	98.76 12	86.25 305	97.56 50	98.66 24	95.73 23	98.44 236	97.35 3	98.99 134	98.27 183

DVP-MVS++		95.93 63	96.34 45	94.70 135	96.54 225	86.66 204	98.45 4	98.22 58	93.26 87	97.54 51	97.36 121	93.12 121	99.38 63	93.88 73	98.68 204	98.04 208

test_241102_TWO								98.10 80	91.95 118	97.54 51	97.25 135	95.37 36	99.35 67	93.29 102	99.25 91	98.49 155

FC-MVSNet-test		95.32 94	95.88 75	93.62 193	98.49 65	81.77 312	95.90 81	98.32 38	93.93 72	97.53 53	97.56 96	88.48 243	99.40 51	92.91 117	99.83 5	99.68 7

fmvsm_s_conf0.5_n_9		95.58 80	95.91 73	94.59 146	97.25 156	86.26 216	92.96 216	97.86 126	91.88 123	97.52 54	98.13 46	91.45 174	98.54 214	97.17 4	98.99 134	98.98 70

K. test v3		93.37 199	93.27 212	93.66 191	98.05 94	82.62 300	94.35 149	86.62 476	96.05 38	97.51 55	98.85 18	76.59 420	99.65 4	93.21 106	98.20 272	98.73 120

casdiffmvs_mvg		95.10 106	95.62 89	93.53 201	96.25 265	83.23 279	92.66 237	98.19 61	93.06 90	97.49 56	97.15 148	94.78 72	98.71 181	92.27 138	98.72 197	98.65 132
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TranMVSNet+NR-MVSNet		96.07 58	96.26 49	95.50 90	98.26 80	87.69 177	93.75 180	97.86 126	95.96 41	97.48 57	97.14 149	95.33 40	99.44 33	90.79 188	99.76 10	99.38 28

v8		94.65 128	95.29 109	92.74 244	96.65 209	79.77 362	94.59 139	97.17 203	91.86 124	97.47 58	97.93 63	88.16 250	99.08 111	94.32 61	99.47 44	99.38 28

fmvsm_s_conf0.5_n_10		94.63 130	95.11 121	93.18 221	96.28 259	83.51 271	93.00 213	98.25 46	88.37 244	97.43 59	97.70 83	88.90 233	98.63 194	97.15 5	98.90 155	97.41 292

v10		94.68 127	95.27 111	92.90 234	96.57 222	80.15 345	94.65 138	97.57 163	90.68 173	97.43 59	98.00 56	88.18 249	99.15 99	94.84 51	99.55 37	99.41 26

APDe-MVS		96.46 39	96.64 29	95.93 66	97.68 129	89.38 131	96.90 21	98.41 29	92.52 98	97.43 59	97.92 68	95.11 52	99.50 23	94.45 58	99.30 80	98.92 87
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsmconf0.1_n		95.61 77	95.72 85	95.26 104	96.85 190	89.20 134	93.51 192	98.60 16	85.68 326	97.42 62	98.30 41	95.34 39	98.39 237	96.85 11	98.98 136	98.19 193

SMA-MVS		95.77 71	95.54 92	96.47 52	98.27 79	91.19 95	95.09 119	97.79 139	86.48 297	97.42 62	97.51 105	94.47 86	99.29 81	93.55 85	99.29 83	98.93 83
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
DVP-MVS		95.82 69	96.18 53	94.72 134	98.51 58	86.69 202	95.20 116	97.00 216	91.85 125	97.40 64	97.35 124	95.58 28	99.34 70	93.44 94	99.31 78	98.13 201
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									93.26 87	97.40 64	97.35 124	94.69 74	99.34 70	93.88 73	99.42 54	98.89 91

aaatest				95.52 89	98.69 37	88.21 161	96.32 56	98.58 18	88.79 226	97.38 66	96.22 236		99.39 54	92.89 118	99.10 115	98.96 77

MED-MVS		96.38 47	96.63 30	95.63 83	98.69 37	88.21 161	96.32 56	98.58 18	94.10 65	97.38 66	97.37 116	95.11 52	99.39 54	92.89 118	99.19 102	99.30 34

fmvsm_s_conf0.1_n_2		94.38 148	94.78 137	93.19 220	97.07 171	81.72 315	91.97 275	97.51 172	87.05 288	97.31 68	97.92 68	88.29 247	98.15 273	97.10 6	98.81 173	99.70 5

fmvsm_l_conf0.5_n_9		94.51 137	95.11 121	92.72 245	96.70 205	83.14 284	91.91 281	97.89 122	88.44 240	97.30 69	97.57 94	91.60 165	97.54 345	95.82 28	98.74 191	97.47 286

testf1		96.77 21	96.49 35	97.60 9	99.01 15	96.70 3	96.31 61	98.33 36	94.96 50	97.30 69	97.93 63	96.05 20	97.90 305	89.32 243	99.23 95	98.19 193

APD_test2		96.77 21	96.49 35	97.60 9	99.01 15	96.70 3	96.31 61	98.33 36	94.96 50	97.30 69	97.93 63	96.05 20	97.90 305	89.32 243	99.23 95	98.19 193

RoMa-SfM		93.45 195	92.92 224	95.03 115	96.77 199	94.01 31	93.01 211	95.19 329	83.99 370	97.28 72	95.33 301	87.17 273	93.66 475	88.55 279	99.00 133	97.42 291

pm-mvs1		95.43 87	95.94 69	93.93 177	98.38 70	85.08 247	95.46 102	97.12 209	91.84 128	97.28 72	98.46 36	95.30 42	97.71 333	90.17 219	99.42 54	98.99 66

TDRefinement		97.68 3	97.60 8	97.93 2	99.02 13	95.95 8	98.61 3	98.81 10	97.41 13	97.28 72	98.46 36	94.62 77	98.84 149	94.64 54	99.53 39	98.99 66

SD-MVS		95.19 103	95.73 84	93.55 197	96.62 218	88.88 144	94.67 136	98.05 92	91.26 156	97.25 75	96.40 216	95.42 34	94.36 468	92.72 125	99.19 102	97.40 296
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
fmvsm_s_conf0.5_n_8		94.70 125	95.34 105	92.78 243	96.77 199	81.50 320	92.64 239	98.50 21	91.51 148	97.22 76	97.93 63	88.07 252	98.45 234	96.62 16	98.80 177	98.39 169

fmvsm_s_conf0.5_n_2		94.25 160	94.63 149	93.10 223	96.65 209	81.75 314	91.72 293	97.25 197	86.93 292	97.20 77	97.67 87	88.44 245	98.14 276	97.06 9	98.77 183	99.42 24

fmvsm_s_conf0.5_n_3		95.20 102	95.95 68	92.94 231	96.60 219	82.18 308	93.13 207	98.39 32	91.44 151	97.16 78	97.68 85	93.03 128	97.82 316	97.54 2	98.63 209	98.81 102

ACMM	88.83 9	96.30 51	96.07 61	96.97 37	98.39 69	92.95 61	94.74 131	98.03 99	90.82 168	97.15 79	96.85 177	96.25 18	99.00 125	93.10 110	99.33 73	98.95 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LoFTR		90.05 333	89.57 338	91.50 314	93.73 398	91.47 90	90.72 330	89.37 450	81.71 411	97.13 80	96.40 216	74.09 434	92.38 487	84.18 368	98.79 180	90.63 506

lessismore_v0				93.87 180	98.05 94	83.77 268		80.32 538		97.13 80	97.91 71	77.49 397	99.11 109	92.62 127	98.08 284	98.74 119

LuminaMVS		93.43 197	93.18 214	94.16 163	97.32 154	85.29 244	93.36 199	93.94 372	88.09 253	97.12 82	96.43 212	80.11 358	98.98 127	93.53 86	98.76 185	98.21 189

test_fmvsm_n_1920		94.72 123	94.74 140	94.67 139	96.30 258	88.62 148	93.19 205	98.07 86	85.63 328	97.08 83	97.35 124	90.86 194	97.66 336	95.70 30	98.48 231	97.74 264

FIs		94.90 115	95.35 104	93.55 197	98.28 78	81.76 313	95.33 106	98.14 72	93.05 91	97.07 84	97.18 144	87.65 263	99.29 81	91.72 157	99.69 17	99.61 14

LPG-MVS_test		96.38 47	96.23 50	96.84 41	98.36 75	92.13 77	95.33 106	98.25 46	91.78 132	97.07 84	97.22 140	96.38 16	99.28 85	92.07 143	99.59 29	99.11 54

LGP-MVS_train				96.84 41	98.36 75	92.13 77		98.25 46	91.78 132	97.07 84	97.22 140	96.38 16	99.28 85	92.07 143	99.59 29	99.11 54

VPA-MVSNet		95.14 105	95.67 87	93.58 196	97.76 119	83.15 283	94.58 141	97.58 162	93.39 84	97.05 87	98.04 53	93.25 115	98.51 222	89.75 233	99.59 29	99.08 58

FMVSNet1		94.84 117	95.13 119	93.97 173	97.60 134	84.29 257	95.99 75	96.56 263	92.38 101	97.03 88	98.53 31	90.12 216	98.98 127	88.78 269	99.16 110	98.65 132

SR-MVS-dyc-post		96.84 14	96.60 33	97.56 13	98.07 92	95.27 9	96.37 51	98.12 76	95.66 42	97.00 89	97.03 161	94.85 69	99.42 37	93.49 88	98.84 165	98.00 213

RE-MVS-def			96.66 27		98.07 92	95.27 9	96.37 51	98.12 76	95.66 42	97.00 89	97.03 161	95.40 35		93.49 88	98.84 165	98.00 213

test_one_0601					98.26 80	87.14 187		98.18 63	94.25 61	96.99 91	97.36 121	95.13 50

APD-MVS_3200maxsize		96.82 16	96.65 28	97.32 28	97.95 106	93.82 42	96.31 61	98.25 46	95.51 44	96.99 91	97.05 160	95.63 27	99.39 54	93.31 100	98.88 160	98.75 115

EG-PatchMatch MVS		94.54 136	94.67 147	94.14 166	97.87 113	86.50 206	92.00 274	96.74 247	88.16 252	96.93 93	97.61 92	93.04 127	97.90 305	91.60 161	98.12 279	98.03 211

test_fmvsmconf_n		95.43 87	95.50 93	95.22 109	96.48 234	89.19 135	93.23 204	98.36 35	85.61 329	96.92 94	98.02 55	95.23 46	98.38 241	96.69 14	98.95 146	98.09 203

KD-MVS_self_test		94.10 167	94.73 141	92.19 277	97.66 131	79.49 375	94.86 128	97.12 209	89.59 205	96.87 95	97.65 89	90.40 209	98.34 248	89.08 258	99.35 67	98.75 115

MVStest1		84.79 448	84.06 452	86.98 466	77.73 554	74.76 464	91.08 315	85.63 488	77.70 458	96.86 96	97.97 60	41.05 550	88.24 520	92.22 139	96.28 398	97.94 225

MP-MVS-pluss		96.08 57	95.92 72	96.57 47	99.06 10	91.21 94	93.25 202	98.32 38	87.89 259	96.86 96	97.38 115	95.55 30	99.39 54	95.47 38	99.47 44	99.11 54
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
COLMAP_ROB	91.06 5	96.75 23	96.62 31	97.13 31	98.38 70	94.31 21	96.79 27	98.32 38	96.69 21	96.86 96	97.56 96	95.48 31	98.77 167	90.11 221	99.44 51	98.31 178
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_s_conf0.5_n_5		94.50 138	94.80 134	93.60 194	96.80 195	84.93 248	92.81 228	97.59 160	85.27 338	96.85 99	97.29 130	91.48 173	98.05 289	96.67 15	98.47 232	97.83 248

SR-MVS		96.70 26	96.42 38	97.54 14	98.05 94	94.69 15	96.13 71	98.07 86	95.17 48	96.82 100	96.73 190	95.09 55	99.43 36	92.99 115	98.71 199	98.50 153

UniMVSNet_NR-MVSNet		95.35 92	95.21 112	95.76 75	97.69 128	88.59 151	92.26 265	97.84 130	94.91 52	96.80 101	95.78 271	90.42 207	99.41 43	91.60 161	99.58 33	99.29 36

DU-MVS		95.28 98	95.12 120	95.75 76	97.75 120	88.59 151	92.58 242	97.81 135	93.99 68	96.80 101	95.90 260	90.10 218	99.41 43	91.60 161	99.58 33	99.26 37

hybridcas		94.81 120	95.45 95	92.88 236	96.74 201	81.36 323	93.32 201	98.13 73	92.16 113	96.79 103	96.98 166	94.91 65	98.53 218	91.16 174	98.90 155	98.75 115

OPM-MVS		95.61 77	95.45 95	96.08 58	98.49 65	91.00 98	92.65 238	97.33 189	90.05 194	96.77 104	96.85 177	95.04 56	98.56 211	92.77 121	99.06 119	98.70 125
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Casviewmamba		95.48 85	95.97 67	94.04 170	96.94 181	84.57 252	93.96 171	98.29 44	93.94 71	96.76 105	97.14 149	95.27 43	98.72 174	92.37 137	99.02 130	98.82 99

test_part2					98.21 84	89.41 129				96.72 106

PMatch-Up-SfM		92.38 250	91.36 280	95.46 93	96.22 268	92.32 73	89.61 380	95.31 323	85.08 347	96.71 107	96.12 247	75.90 423	97.27 368	89.73 234	97.54 333	96.78 337

SSC-MVS		90.16 325	92.96 220	81.78 517	97.88 111	48.48 554	90.75 328	87.69 467	96.02 40	96.70 108	97.63 91	85.60 303	97.80 319	85.73 339	98.60 214	99.06 60

v1240		93.29 203	93.71 193	92.06 285	96.01 290	77.89 414	91.81 289	97.37 181	85.12 345	96.69 109	96.40 216	86.67 287	99.07 117	94.51 55	98.76 185	99.22 42

KinetiMVS		95.09 107	95.40 101	94.15 164	97.42 148	84.35 256	93.91 174	96.69 251	94.41 60	96.67 110	97.25 135	87.67 261	99.14 101	95.78 29	98.81 173	98.97 73

tfpnnormal		94.27 155	94.87 132	92.48 265	97.71 125	80.88 334	94.55 145	95.41 319	93.70 77	96.67 110	97.72 82	91.40 176	98.18 267	87.45 307	99.18 106	98.36 171

VortexMVS		92.13 262	92.56 240	90.85 356	94.54 371	76.17 452	92.30 262	96.63 258	86.20 307	96.66 112	96.79 182	79.87 361	98.16 271	91.27 172	98.76 185	98.24 185

SteuartSystems-ACMMP		96.40 45	96.30 47	96.71 43	98.63 42	91.96 80	95.70 88	98.01 102	93.34 86	96.64 113	96.57 203	94.99 60	99.36 66	93.48 90	99.34 71	98.82 99
Skip Steuart: Steuart Systems R&D Blog.
WR-MVS		93.49 193	93.72 190	92.80 241	97.57 137	80.03 351	90.14 359	95.68 303	93.70 77	96.62 114	95.39 298	87.21 272	99.04 121	87.50 306	99.64 25	99.33 31

ACMP	88.15 13	95.71 74	95.43 99	96.54 48	98.17 86	91.73 86	94.24 155	98.08 83	89.46 207	96.61 115	96.47 209	95.85 22	99.12 105	90.45 199	99.56 36	98.77 114
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
fmvsm_l_conf0.5_n_3		95.19 103	95.36 103	94.68 137	96.79 197	87.49 179	93.05 210	98.38 33	87.21 279	96.59 116	97.76 81	94.20 90	98.11 277	95.90 26	98.40 239	98.42 161

DP-MVS		95.62 76	95.84 78	94.97 118	97.16 163	88.62 148	94.54 146	97.64 152	96.94 19	96.58 117	97.32 128	93.07 125	98.72 174	90.45 199	98.84 165	97.57 278

IterMVS-LS		93.78 182	94.28 168	92.27 270	96.27 262	79.21 386	91.87 285	96.78 242	91.77 134	96.57 118	97.07 157	87.15 274	98.74 171	91.99 146	99.03 129	98.86 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AstraMVS		92.75 233	92.73 231	92.79 242	97.02 176	81.48 321	92.88 225	90.62 442	87.99 256	96.48 119	96.71 192	82.02 341	98.48 229	92.44 134	98.46 233	98.40 168

HPM-MVS_fast		97.01 11	96.89 21	97.39 24	99.12 8	93.92 36	97.16 14	98.17 67	93.11 89	96.48 119	97.36 121	96.92 6	99.34 70	94.31 62	99.38 63	98.92 87

FE-MVSNET2		94.07 170	94.47 157	92.90 234	97.45 147	81.26 325	93.58 188	97.54 166	88.28 246	96.46 121	97.92 68	91.41 175	98.74 171	88.12 292	99.44 51	98.69 128

fmvsm_s_conf0.5_n_6		94.14 166	94.54 154	92.95 229	96.51 230	82.74 298	92.71 234	98.13 73	86.56 295	96.44 122	96.85 177	88.51 242	98.05 289	96.03 23	99.09 117	98.06 204

mvsany_test3		89.11 356	88.21 375	91.83 295	91.30 471	90.25 115	88.09 426	78.76 542	76.37 470	96.43 123	98.39 39	83.79 318	90.43 503	86.57 323	94.20 473	94.80 435

DKM		92.97 221	92.35 249	94.81 129	96.53 228	93.72 46	90.94 319	94.88 338	85.21 340	96.42 124	95.18 306	83.11 324	93.06 482	89.66 237	99.24 93	97.64 271

ambc				92.98 226	96.88 187	83.01 289	95.92 80	96.38 274		96.41 125	97.48 107	88.26 248	97.80 319	89.96 227	98.93 149	98.12 202

aaEdge-Enhanced		95.61 77	95.65 88	95.49 91	97.62 133	88.21 161	94.21 158	97.87 125	92.48 99	96.38 126	96.22 236	94.06 94	99.32 77	92.89 118	99.10 115	98.96 77

guyue		92.60 240	92.62 237	92.52 264	96.73 202	81.00 330	93.00 213	91.83 427	88.28 246	96.38 126	96.23 235	80.71 354	98.37 245	92.06 145	98.37 249	98.20 191

test-260524					97.94 107	87.97 171		97.94 115		96.37 128		93.24 116	99.34 70	94.10 67	99.19 102

ACMMP_NAP		96.21 53	96.12 57	96.49 51	98.90 22	91.42 92	94.57 142	98.03 99	90.42 184	96.37 128	97.35 124	95.68 25	99.25 89	94.44 59	99.34 71	98.80 104

SF-MVS		95.88 67	95.88 75	95.87 72	98.12 88	89.65 123	95.58 96	98.56 20	91.84 128	96.36 130	96.68 194	94.37 87	99.32 77	92.41 135	99.05 122	98.64 138

fmvsm_s_conf0.5_n_4		94.26 156	94.58 151	93.31 213	96.40 242	82.73 299	92.59 241	97.41 179	86.60 293	96.33 131	97.07 157	89.91 222	98.07 286	96.88 10	98.01 294	99.13 50

ACMMP		96.61 31	96.34 45	97.43 21	98.61 45	93.88 37	96.95 20	98.18 63	92.26 107	96.33 131	96.84 180	95.10 54	99.40 51	93.47 91	99.33 73	99.02 63
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
VDDNet		94.03 171	94.27 170	93.31 213	98.87 26	82.36 304	95.51 101	91.78 428	97.19 15	96.32 133	98.60 28	84.24 313	98.75 168	87.09 314	98.83 170	98.81 102

PMatch-SfM		91.76 272	90.58 311	95.30 103	95.64 319	91.67 88	89.49 386	94.79 345	84.45 361	96.31 134	96.02 254	71.68 453	97.26 370	89.13 256	97.75 315	96.98 322

UniMVSNet (Re)		95.32 94	95.15 114	95.80 74	97.79 118	88.91 141	92.91 223	98.07 86	93.46 83	96.31 134	95.97 259	90.14 215	99.34 70	92.11 140	99.64 25	99.16 47

XVG-ACMP-BASELINE		95.68 75	95.34 105	96.69 44	98.40 68	93.04 58	94.54 146	98.05 92	90.45 183	96.31 134	96.76 185	92.91 131	98.72 174	91.19 173	99.42 54	98.32 176

MTAPA		96.65 29	96.38 42	97.47 18	98.95 21	94.05 27	95.88 82	97.62 154	94.46 59	96.29 137	96.94 168	93.56 102	99.37 65	94.29 63	99.42 54	98.99 66

Baseline_NR-MVSNet		94.47 144	95.09 124	92.60 256	98.50 64	80.82 335	92.08 270	96.68 254	93.82 75	96.29 137	98.56 30	90.10 218	97.75 329	90.10 223	99.66 23	99.24 41

IS-MVSNet		94.49 143	94.35 164	94.92 121	98.25 82	86.46 209	97.13 17	94.31 357	96.24 34	96.28 139	96.36 224	82.88 328	99.35 67	88.19 288	99.52 41	98.96 77

test_fmvs3		92.42 248	92.40 246	92.46 267	93.80 397	87.28 183	93.86 176	97.05 213	76.86 466	96.25 140	98.66 24	82.87 329	91.26 497	95.44 39	96.83 375	98.82 99

VDD-MVS		94.37 150	94.37 161	94.40 157	97.49 141	86.07 223	93.97 170	93.28 392	94.49 57	96.24 141	97.78 76	87.99 256	98.79 160	88.92 262	99.14 112	98.34 175

DeepPCF-MVS	90.46 6	94.20 163	93.56 201	96.14 56	95.96 292	92.96 60	89.48 387	97.46 176	85.14 344	96.23 142	95.42 293	93.19 118	98.08 282	90.37 205	98.76 185	97.38 299

PM-MVS		93.33 202	92.67 236	95.33 99	96.58 221	94.06 25	92.26 265	92.18 416	85.92 316	96.22 143	96.61 200	85.64 302	95.99 431	90.35 206	98.23 265	95.93 387

DeepC-MVS	91.39 4	95.43 87	95.33 107	95.71 78	97.67 130	90.17 117	93.86 176	98.02 101	87.35 274	96.22 143	97.99 59	94.48 85	99.05 118	92.73 124	99.68 20	97.93 228
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
mvs5depth		95.28 98	95.82 81	93.66 191	96.42 240	83.08 287	97.35 12	99.28 2	96.44 28	96.20 145	99.65 2	84.10 315	98.01 296	94.06 68	98.93 149	99.87 1

V42		93.43 197	93.58 199	92.97 227	95.34 337	81.22 327	92.67 236	96.49 268	87.25 277	96.20 145	96.37 223	87.32 269	98.85 148	92.39 136	98.21 270	98.85 97

CSCG		94.69 126	94.75 138	94.52 150	97.55 138	87.87 173	95.01 124	97.57 163	92.68 94	96.20 145	93.44 387	91.92 157	98.78 164	89.11 257	99.24 93	96.92 327

v1921920		93.26 205	93.61 198	92.19 277	96.04 289	78.31 407	91.88 284	97.24 199	85.17 342	96.19 148	96.19 240	86.76 285	99.05 118	94.18 65	98.84 165	99.22 42

EI-MVSNet-UG-set		94.35 152	94.27 170	94.59 146	92.46 431	85.87 231	92.42 252	94.69 348	93.67 80	96.13 149	95.84 264	91.20 183	98.86 146	93.78 77	98.23 265	99.03 62

EI-MVSNet-Vis-set		94.36 151	94.28 168	94.61 142	92.55 428	85.98 226	92.44 250	94.69 348	93.70 77	96.12 150	95.81 266	91.24 180	98.86 146	93.76 80	98.22 269	98.98 70

viewdifsd2359ckpt07		93.63 185	94.33 165	91.55 310	96.19 271	77.86 415	90.11 362	97.74 143	90.76 170	96.11 151	96.61 200	94.37 87	98.27 255	88.82 267	98.23 265	98.51 152

v1192		93.49 193	93.78 188	92.62 254	96.16 273	79.62 366	91.83 288	97.22 201	86.07 311	96.10 152	96.38 222	87.22 271	99.02 123	94.14 66	98.88 160	99.22 42

WB-MVS		89.44 348	92.15 256	81.32 518	97.73 123	48.22 555	89.73 377	87.98 464	95.24 47	96.05 153	96.99 165	85.18 306	96.95 392	82.45 390	97.97 300	98.78 111

FMVSNet2		92.78 231	92.73 231	92.95 229	95.40 333	81.98 310	94.18 159	95.53 314	88.63 230	96.05 153	97.37 116	81.31 348	98.81 156	87.38 310	98.67 206	98.06 204

viewdifsd2359ckpt11		93.36 200	93.99 178	91.48 315	95.50 329	78.39 403	90.47 340	96.69 251	88.59 233	96.03 155	96.88 174	93.48 105	97.63 340	90.20 217	98.07 286	98.41 164

viewmsd2359difaftdt		93.36 200	93.99 178	91.48 315	95.50 329	78.39 403	90.47 340	96.69 251	88.59 233	96.03 155	96.88 174	93.48 105	97.63 340	90.20 217	98.07 286	98.41 164

v144192		93.20 212	93.54 202	92.16 281	96.05 285	78.26 408	91.95 276	97.14 205	84.98 351	95.96 157	96.11 249	87.08 277	99.04 121	93.79 76	98.84 165	99.17 46

HPM-MVS		96.81 18	96.62 31	97.36 26	98.89 23	93.53 51	97.51 10	98.44 26	92.35 104	95.95 158	96.41 215	96.71 11	99.42 37	93.99 71	99.36 66	99.13 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test1111		90.39 315	90.61 308	89.74 400	98.04 97	71.50 497	95.59 93	79.72 540	89.41 208	95.94 159	98.14 45	70.79 457	98.81 156	88.52 280	99.32 77	98.90 90

v148		92.87 226	93.29 209	91.62 307	96.25 265	77.72 420	91.28 306	95.05 332	89.69 201	95.93 160	96.04 252	87.34 268	98.38 241	90.05 224	97.99 298	98.78 111

v1144		93.50 192	93.81 185	92.57 257	96.28 259	79.61 367	91.86 287	96.96 220	86.95 290	95.91 161	96.32 226	87.65 263	98.96 133	93.51 87	98.88 160	99.13 50

Anonymous20240521		92.86 228	93.57 200	90.74 363	96.57 222	75.50 461	94.15 160	95.60 305	89.38 209	95.90 162	97.90 73	80.39 357	97.96 302	92.60 129	99.68 20	98.75 115

APD_test1		95.91 64	95.42 100	97.36 26	98.82 30	96.62 6	95.64 92	97.64 152	93.38 85	95.89 163	97.23 138	93.35 112	97.66 336	88.20 287	98.66 208	97.79 254

PC_three_1452									75.31 479	95.87 164	95.75 273	92.93 130	96.34 423	87.18 312	98.68 204	98.04 208

ELoFTR		89.04 359	88.72 355	89.99 393	94.38 377	89.08 137	90.15 358	89.10 451	75.60 474	95.85 165	96.52 207	75.00 428	89.26 513	83.82 374	98.08 284	91.61 496

IU-MVS					98.51 58	86.66 204		96.83 239	72.74 499	95.83 166				93.00 114	99.29 83	98.64 138

Patchmatch-RL test		88.81 368	88.52 360	89.69 402	95.33 338	79.94 355	86.22 472	92.71 404	78.46 454	95.80 167	94.18 359	66.25 481	95.33 448	89.22 251	98.53 223	93.78 463

E5new		94.50 138	95.15 114	92.55 258	97.04 172	80.27 341	92.96 216	98.25 46	90.18 188	95.77 168	97.45 109	94.85 69	98.59 201	91.16 174	98.73 193	98.79 106

E5		94.50 138	95.15 114	92.55 258	97.04 172	80.27 341	92.96 216	98.25 46	90.18 188	95.77 168	97.45 109	94.85 69	98.59 201	91.16 174	98.73 193	98.79 106

fmvsm_l_conf0.5_n		93.79 181	93.81 185	93.73 188	96.16 273	86.26 216	92.46 248	96.72 248	81.69 412	95.77 168	97.11 153	90.83 196	97.82 316	95.58 34	97.99 298	97.11 310

E6new		94.50 138	95.15 114	92.55 258	97.04 172	80.28 339	92.96 216	98.25 46	90.18 188	95.76 171	97.45 109	94.86 67	98.59 201	91.16 174	98.73 193	98.79 106

E6		94.50 138	95.15 114	92.55 258	97.04 172	80.28 339	92.96 216	98.25 46	90.18 188	95.76 171	97.45 109	94.86 67	98.59 201	91.16 174	98.73 193	98.79 106

fmvsm_s_conf0.1_n		94.19 165	94.41 158	93.52 203	97.22 160	84.37 254	93.73 181	95.26 325	84.45 361	95.76 171	98.00 56	91.85 158	97.21 375	95.62 31	97.82 311	98.98 70

PGM-MVS		96.32 49	95.94 69	97.43 21	98.59 48	93.84 41	95.33 106	98.30 41	91.40 153	95.76 171	96.87 176	95.26 44	99.45 32	92.77 121	99.21 99	99.00 64

casdiffmvs		94.32 154	94.80 134	92.85 238	96.05 285	81.44 322	92.35 256	98.05 92	91.53 145	95.75 175	96.80 181	93.35 112	98.49 224	91.01 183	98.32 253	98.64 138
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GST-MVS		96.24 52	95.99 66	97.00 36	98.65 41	92.71 66	95.69 90	98.01 102	92.08 116	95.74 176	96.28 230	95.22 47	99.42 37	93.17 108	99.06 119	98.88 93

VPNet		93.08 215	93.76 189	91.03 343	98.60 46	75.83 459	91.51 298	95.62 304	91.84 128	95.74 176	97.10 155	89.31 229	98.32 249	85.07 354	99.06 119	98.93 83

test_f		86.65 429	87.13 402	85.19 491	90.28 500	86.11 222	86.52 465	91.66 429	69.76 521	95.73 178	97.21 142	69.51 463	81.28 546	89.15 255	94.40 465	88.17 518

EU-MVSNet		87.39 411	86.71 415	89.44 407	93.40 407	76.11 453	94.93 127	90.00 445	57.17 546	95.71 179	97.37 116	64.77 490	97.68 335	92.67 126	94.37 468	94.52 443

fmvsm_s_conf0.5_n_11		94.91 113	95.44 98	93.33 212	96.45 236	83.11 286	93.56 190	98.64 14	89.76 200	95.70 180	97.97 60	92.32 146	98.08 282	95.62 31	98.95 146	98.79 106

SSM_0404		94.38 148	94.69 142	93.43 207	97.16 163	83.23 279	93.95 172	97.84 130	91.46 149	95.70 180	96.56 205	92.50 144	99.08 111	88.83 265	98.23 265	97.98 217

v2v482		93.29 203	93.63 196	92.29 269	96.35 251	78.82 395	91.77 292	96.28 278	88.45 239	95.70 180	96.26 233	86.02 296	98.90 139	93.02 113	98.81 173	99.14 49

MatchFormer		85.84 439	85.60 436	86.56 474	90.63 490	87.98 170	89.85 371	83.79 509	72.98 497	95.69 183	94.88 323	69.40 464	87.92 521	74.60 480	98.55 219	83.77 538

DenseAffine		91.92 268	90.90 294	94.97 118	96.37 245	93.07 56	90.35 348	93.65 380	84.62 358	95.66 184	94.39 349	78.19 386	94.97 458	86.02 335	98.90 155	96.87 333

fmvsm_l_conf0.5_n_a		93.59 189	93.63 196	93.49 205	96.10 280	85.66 237	92.32 259	96.57 262	81.32 420	95.63 185	97.14 149	90.19 212	97.73 332	95.37 44	98.03 291	97.07 315

HFP-MVS		96.39 46	96.17 55	97.04 34	98.51 58	93.37 52	96.30 65	97.98 105	92.35 104	95.63 185	96.47 209	95.37 36	99.27 88	93.78 77	99.14 112	98.48 156

Anonymous202405211		92.58 242	92.50 242	92.83 239	96.55 224	83.22 281	92.43 251	91.64 430	94.10 65	95.59 187	96.64 196	81.88 345	97.50 348	85.12 351	98.52 226	97.77 258

ACMMPR		96.46 39	96.14 56	97.41 23	98.60 46	93.82 42	96.30 65	97.96 109	92.35 104	95.57 188	96.61 200	94.93 64	99.41 43	93.78 77	99.15 111	99.00 64

XXY-MVS		92.58 242	93.16 216	90.84 357	97.75 120	79.84 357	91.87 285	96.22 285	85.94 315	95.53 189	97.68 85	92.69 137	94.48 464	83.21 378	97.51 334	98.21 189

fmvsm_s_conf0.1_n_a		94.26 156	94.37 161	93.95 176	97.36 151	85.72 235	94.15 160	95.44 316	83.25 382	95.51 190	98.05 51	92.54 140	97.19 378	95.55 36	97.46 339	98.94 81

SDMVSNet		94.43 146	95.02 126	92.69 247	97.93 108	82.88 291	91.92 280	95.99 296	93.65 81	95.51 190	98.63 26	94.60 78	96.48 413	87.57 305	99.35 67	98.70 125

sd_testset		93.94 177	94.39 159	92.61 255	97.93 108	83.24 278	93.17 206	95.04 333	93.65 81	95.51 190	98.63 26	94.49 84	95.89 433	81.72 399	99.35 67	98.70 125

new-patchmatchnet		88.97 364	90.79 302	83.50 509	94.28 379	55.83 549	85.34 489	93.56 385	86.18 309	95.47 193	95.73 274	83.10 325	96.51 412	85.40 343	98.06 288	98.16 196

mPP-MVS		96.46 39	96.05 62	97.69 5	98.62 43	94.65 17	96.45 46	97.74 143	92.59 97	95.47 193	96.68 194	94.50 83	99.42 37	93.10 110	99.26 90	98.99 66

UA-Net		97.35 4	97.24 15	97.69 5	98.22 83	93.87 39	98.42 6	98.19 61	96.95 18	95.46 195	99.23 9	93.45 107	99.57 14	95.34 45	99.89 2	99.63 12

APD-MVS		95.00 110	94.69 142	95.93 66	97.38 149	90.88 102	94.59 139	97.81 135	89.22 214	95.46 195	96.17 244	93.42 110	99.34 70	89.30 245	98.87 163	97.56 280
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
fmvsm_s_conf0.5_n		94.00 174	94.20 172	93.42 208	96.69 206	84.37 254	93.38 198	95.13 331	84.50 360	95.40 197	97.55 100	91.77 160	97.20 376	95.59 33	97.79 312	98.69 128

tt0805		95.42 90	95.93 71	93.86 181	98.75 36	88.47 155	97.68 9	94.29 358	96.48 26	95.38 198	93.63 381	94.89 66	97.94 304	95.38 43	96.92 371	95.17 416

9.14			94.81 133		97.49 141		94.11 163	98.37 34	87.56 271	95.38 198	96.03 253	94.66 75	99.08 111	90.70 191	98.97 142

IterMVS-SCA-FT		91.65 275	91.55 273	91.94 291	93.89 392	79.22 385	87.56 434	93.51 387	91.53 145	95.37 200	96.62 199	78.65 376	98.90 139	91.89 150	94.95 452	97.70 266

ECVR-MVS		90.12 327	90.16 321	90.00 392	97.81 116	72.68 489	95.76 87	78.54 544	89.04 217	95.36 201	98.10 48	70.51 459	98.64 192	87.10 313	99.18 106	98.67 130

ZNCC-MVS		96.42 43	96.20 52	97.07 33	98.80 34	92.79 64	96.08 73	98.16 70	91.74 136	95.34 202	96.36 224	95.68 25	99.44 33	94.41 60	99.28 88	98.97 73

LS3D		96.11 56	95.83 79	96.95 39	94.75 360	94.20 23	97.34 13	97.98 105	97.31 14	95.32 203	96.77 183	93.08 123	99.20 95	91.79 153	98.16 274	97.44 290

tttt0517		89.81 340	88.90 351	92.55 258	97.00 178	79.73 365	95.03 123	83.65 510	89.88 197	95.30 204	94.79 329	53.64 521	99.39 54	91.99 146	98.79 180	98.54 149

XVG-OURS		94.72 123	94.12 175	96.50 50	98.00 102	94.23 22	91.48 300	98.17 67	90.72 171	95.30 204	96.47 209	87.94 257	96.98 390	91.41 168	97.61 328	98.30 180

DKM-HiRes		92.87 226	91.94 263	95.65 82	97.16 163	93.66 47	90.90 321	94.27 360	87.11 286	95.29 206	95.39 298	77.59 396	95.36 445	90.86 186	98.92 153	97.94 225

BridgeMVS		93.45 195	94.17 173	91.28 330	95.81 305	78.40 401	96.20 69	97.48 175	88.56 238	95.29 206	97.20 143	85.56 304	99.21 92	92.52 132	98.91 154	96.24 370

region2R		96.41 44	96.09 58	97.38 25	98.62 43	93.81 44	96.32 56	97.96 109	92.26 107	95.28 208	96.57 203	95.02 58	99.41 43	93.63 81	99.11 114	98.94 81

ArgMatch-SfM		91.28 288	90.08 325	94.88 125	95.22 341	92.66 68	89.81 374	94.51 354	79.15 447	95.27 209	93.71 379	78.33 381	95.52 438	86.11 334	98.63 209	96.46 355

E4		94.00 174	94.53 155	92.42 268	96.78 198	79.99 353	91.33 305	98.16 70	89.69 201	95.27 209	97.16 145	93.94 98	98.64 192	89.99 225	98.42 238	98.61 143

casdiffseed414692147		94.56 134	94.90 129	93.54 199	96.60 219	83.33 275	93.57 189	98.06 90	91.57 142	95.26 211	97.31 129	94.06 94	98.39 237	88.67 272	98.95 146	98.91 89

GeoE		94.55 135	94.68 146	94.15 164	97.23 158	85.11 246	94.14 162	97.34 188	88.71 229	95.26 211	95.50 287	94.65 76	99.12 105	90.94 184	98.40 239	98.23 186

TinyColmap		92.00 267	92.76 228	89.71 401	95.62 321	77.02 432	90.72 330	96.17 288	87.70 266	95.26 211	96.29 228	92.54 140	96.45 416	81.77 397	98.77 183	95.66 402

alignmvs		93.26 205	92.85 225	94.50 151	95.70 312	87.45 180	93.45 195	95.76 300	91.58 141	95.25 214	92.42 426	81.96 343	98.72 174	91.61 160	97.87 309	97.33 301

EI-MVSNet		92.99 219	93.26 213	92.19 277	92.12 445	79.21 386	92.32 259	94.67 350	91.77 134	95.24 215	95.85 262	87.14 275	98.49 224	91.99 146	98.26 260	98.86 94

MVSTER		89.32 350	88.75 354	91.03 343	90.10 504	76.62 446	90.85 323	94.67 350	82.27 402	95.24 215	95.79 267	61.09 507	98.49 224	90.49 198	98.26 260	97.97 221

sasdasda		94.59 131	94.69 142	94.30 159	95.60 322	87.03 190	95.59 93	98.24 54	91.56 143	95.21 217	92.04 439	94.95 61	98.66 188	91.45 166	97.57 331	97.20 307

canonicalmvs		94.59 131	94.69 142	94.30 159	95.60 322	87.03 190	95.59 93	98.24 54	91.56 143	95.21 217	92.04 439	94.95 61	98.66 188	91.45 166	97.57 331	97.20 307

mamba_0408		93.60 188	93.72 190	93.27 216	96.65 209	82.79 294	88.81 411	97.68 148	90.62 177	95.19 219	96.01 255	91.54 171	99.08 111	88.63 274	98.32 253	97.93 228

SSM_04072		93.25 208	93.72 190	91.84 294	96.65 209	82.79 294	88.81 411	97.68 148	90.62 177	95.19 219	96.01 255	91.54 171	94.81 460	88.63 274	98.32 253	97.93 228

SSM_0407		94.23 161	94.56 153	93.24 218	96.65 209	82.79 294	93.66 185	97.84 130	91.46 149	95.19 219	96.56 205	92.50 144	98.99 126	88.83 265	98.32 253	97.93 228

FE-MVSNET		92.02 266	92.22 253	91.41 320	96.63 217	79.08 388	91.53 297	96.84 238	85.52 334	95.16 222	96.14 245	83.97 316	97.50 348	85.48 342	98.75 189	97.64 271

RRT-MVS		92.28 255	93.01 219	90.07 387	94.06 386	73.01 485	95.36 103	97.88 123	92.24 109	95.16 222	97.52 101	78.51 380	99.29 81	90.55 195	95.83 416	97.92 234

fmvsm_s_conf0.5_n_a		94.02 172	94.08 177	93.84 182	96.72 204	85.73 234	93.65 187	95.23 327	83.30 380	95.13 224	97.56 96	92.22 150	97.17 379	95.51 37	97.41 342	98.64 138

MSP-MVS		95.34 93	94.63 149	97.48 17	98.67 40	94.05 27	96.41 50	98.18 63	91.26 156	95.12 225	95.15 307	86.60 289	99.50 23	93.43 97	96.81 376	98.89 91
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
ArgMatch-Sym		90.98 294	89.75 334	94.68 137	95.17 347	92.64 69	89.09 401	93.46 389	78.60 453	95.11 226	92.37 427	80.44 355	95.24 451	85.04 355	98.44 235	96.18 374

GBi-Net		93.21 210	92.96 220	93.97 173	95.40 333	84.29 257	95.99 75	96.56 263	88.63 230	95.10 227	98.53 31	81.31 348	98.98 127	86.74 317	98.38 244	98.65 132

test1		93.21 210	92.96 220	93.97 173	95.40 333	84.29 257	95.99 75	96.56 263	88.63 230	95.10 227	98.53 31	81.31 348	98.98 127	86.74 317	98.38 244	98.65 132

FMVSNet3		90.78 298	90.32 319	92.16 281	93.03 418	79.92 356	92.54 243	94.95 336	86.17 310	95.10 227	96.01 255	69.97 462	98.75 168	86.74 317	98.38 244	97.82 251

CP-MVS		96.44 42	96.08 60	97.54 14	98.29 77	94.62 18	96.80 26	98.08 83	92.67 96	95.08 230	96.39 221	94.77 73	99.42 37	93.17 108	99.44 51	98.58 146

viewmacassd2359aftdt		93.83 180	94.36 163	92.24 273	96.45 236	79.58 371	91.60 295	97.96 109	89.14 216	95.05 231	97.09 156	93.69 100	98.48 229	89.79 230	98.43 236	98.65 132

MGCFI-Net		94.44 145	94.67 147	93.75 186	95.56 325	85.47 240	95.25 113	98.24 54	91.53 145	95.04 232	92.21 433	94.94 63	98.54 214	91.56 164	97.66 325	97.24 305

AllTest		94.88 116	94.51 156	96.00 59	98.02 98	92.17 74	95.26 112	98.43 27	90.48 181	95.04 232	96.74 188	92.54 140	97.86 313	85.11 352	98.98 136	97.98 217

TestCases				96.00 59	98.02 98	92.17 74		98.43 27	90.48 181	95.04 232	96.74 188	92.54 140	97.86 313	85.11 352	98.98 136	97.98 217

YYNet1		88.17 385	88.24 372	87.93 451	92.21 439	73.62 480	80.75 528	88.77 453	82.51 398	94.99 235	95.11 310	82.70 333	93.70 474	83.33 376	93.83 482	96.48 353

EPP-MVSNet		93.91 178	93.68 195	94.59 146	98.08 91	85.55 239	97.44 11	94.03 366	94.22 63	94.94 236	96.19 240	82.07 340	99.57 14	87.28 311	98.89 158	98.65 132

MDA-MVSNet-bldmvs		91.04 292	90.88 296	91.55 310	94.68 367	80.16 344	85.49 486	92.14 419	90.41 185	94.93 237	95.79 267	85.10 307	96.93 395	85.15 349	94.19 475	97.57 278

test_fmvs2		90.62 308	90.40 316	91.29 329	91.93 452	85.46 241	92.70 235	96.48 269	74.44 483	94.91 238	97.59 93	75.52 425	90.57 500	93.44 94	96.56 388	97.84 247

baseline		94.26 156	94.80 134	92.64 249	96.08 282	80.99 331	93.69 183	98.04 98	90.80 169	94.89 239	96.32 226	93.19 118	98.48 229	91.68 159	98.51 228	98.43 160

MDA-MVSNet_test_wron		88.16 386	88.23 373	87.93 451	92.22 438	73.71 479	80.71 529	88.84 452	82.52 397	94.88 240	95.14 308	82.70 333	93.61 476	83.28 377	93.80 483	96.46 355

LFMVS		91.33 285	91.16 288	91.82 296	96.27 262	79.36 380	95.01 124	85.61 491	96.04 39	94.82 241	97.06 159	72.03 452	98.46 233	84.96 356	98.70 202	97.65 270

ITE_SJBPF				95.95 63	97.34 152	93.36 54		96.55 266	91.93 120	94.82 241	95.39 298	91.99 155	97.08 385	85.53 341	97.96 303	97.41 292

ZD-MVS					97.23 158	90.32 113		97.54 166	84.40 363	94.78 243	95.79 267	92.76 136	99.39 54	88.72 271	98.40 239

TSAR-MVS + MP.		94.96 112	94.75 138	95.57 87	98.86 27	88.69 145	96.37 51	96.81 240	85.23 339	94.75 244	97.12 152	91.85 158	99.40 51	93.45 93	98.33 251	98.62 142
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
Patchmtry		90.11 328	89.92 328	90.66 368	90.35 499	77.00 433	92.96 216	92.81 400	90.25 187	94.74 245	96.93 170	67.11 473	97.52 347	85.17 346	98.98 136	97.46 287

3Dnovator+	92.74 2	95.86 68	95.77 83	96.13 57	96.81 194	90.79 106	96.30 65	97.82 134	96.13 35	94.74 245	97.23 138	91.33 177	99.16 98	93.25 105	98.30 257	98.46 157

c3_l		91.32 286	91.42 278	91.00 346	92.29 436	76.79 439	87.52 437	96.42 272	85.76 324	94.72 247	93.89 371	82.73 332	98.16 271	90.93 185	98.55 219	98.04 208

E2		93.53 190	93.96 180	92.25 271	96.39 243	79.76 363	91.06 316	98.05 92	88.58 235	94.71 248	96.64 196	93.08 123	98.57 207	89.16 253	97.97 300	98.42 161

E3		93.53 190	93.96 180	92.25 271	96.39 243	79.76 363	91.06 316	98.05 92	88.58 235	94.71 248	96.64 196	93.07 125	98.57 207	89.16 253	97.97 300	98.42 161

TSAR-MVS + GP.		93.07 218	92.41 245	95.06 114	95.82 303	90.87 103	90.97 318	92.61 409	88.04 255	94.61 250	93.79 376	88.08 251	97.81 318	89.41 242	98.39 243	96.50 351

OMC-MVS		94.22 162	93.69 194	95.81 73	97.25 156	91.27 93	92.27 264	97.40 180	87.10 287	94.56 251	95.42 293	93.74 99	98.11 277	86.62 322	98.85 164	98.06 204

testgi		90.38 316	91.34 282	87.50 458	97.49 141	71.54 496	89.43 389	95.16 330	88.38 242	94.54 252	94.68 334	92.88 133	93.09 481	71.60 509	97.85 310	97.88 240

VNet		92.67 237	92.96 220	91.79 297	96.27 262	80.15 345	91.95 276	94.98 335	92.19 111	94.52 253	96.07 251	87.43 267	97.39 360	84.83 357	98.38 244	97.83 248

dtuonlycased		90.11 328	90.39 317	89.28 414	97.09 170	72.61 490	85.75 479	95.27 324	81.57 415	94.42 254	94.89 320	90.47 206	96.81 402	78.74 436	95.27 441	98.41 164

eth_miper_zixun_eth		90.72 300	90.61 308	91.05 341	92.04 448	76.84 438	86.91 450	96.67 255	85.21 340	94.41 255	93.92 369	79.53 365	98.26 256	89.76 232	97.02 364	98.06 204

test20.03		90.80 297	90.85 298	90.63 370	95.63 320	79.24 384	89.81 374	92.87 399	89.90 196	94.39 256	96.40 216	85.77 297	95.27 450	73.86 494	99.05 122	97.39 297

XVS		96.49 37	96.18 53	97.44 19	98.56 49	93.99 32	96.50 42	97.95 112	94.58 55	94.38 257	96.49 208	94.56 80	99.39 54	93.57 83	99.05 122	98.93 83

X-MVStestdata		90.70 301	88.45 362	97.44 19	98.56 49	93.99 32	96.50 42	97.95 112	94.58 55	94.38 257	26.89 554	94.56 80	99.39 54	93.57 83	99.05 122	98.93 83

3Dnovator	92.54 3	94.80 121	94.90 129	94.47 154	95.47 331	87.06 189	96.63 36	97.28 196	91.82 131	94.34 259	97.41 113	90.60 204	98.65 191	92.47 133	98.11 280	97.70 266

viewcassd2359sk11		93.16 213	93.51 204	92.13 283	96.07 283	79.59 368	90.88 322	97.97 107	87.82 261	94.23 260	96.19 240	92.31 147	98.53 218	88.58 277	97.51 334	98.28 181

MVSMamba_PlusPlus		94.82 119	95.89 74	91.62 307	97.82 115	78.88 393	96.52 40	97.60 158	97.14 16	94.23 260	98.48 35	87.01 278	99.71 2	95.43 40	98.80 177	96.28 367

reproduce_monomvs		87.13 420	86.90 408	87.84 455	90.92 484	68.15 512	91.19 309	93.75 377	85.84 321	94.21 262	95.83 265	42.99 543	97.10 383	89.46 241	97.88 308	98.26 184

viewmanbaseed2359cas		93.08 215	93.43 206	92.01 289	95.69 313	79.29 382	91.15 310	97.70 147	87.45 273	94.18 263	96.12 247	92.31 147	98.37 245	88.58 277	97.73 317	98.38 170

Vis-MVSNet		95.50 83	95.48 94	95.56 88	98.11 89	89.40 130	95.35 104	98.22 58	92.36 103	94.11 264	98.07 50	92.02 154	99.44 33	93.38 99	97.67 324	97.85 246
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
IterMVS		90.18 324	90.16 321	90.21 383	93.15 412	75.98 455	87.56 434	92.97 398	86.43 300	94.09 265	96.40 216	78.32 382	97.43 355	87.87 301	94.69 460	97.23 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSLP-MVS++		93.25 208	93.88 184	91.37 323	96.34 252	82.81 293	93.11 208	97.74 143	89.37 210	94.08 266	95.29 303	90.40 209	96.35 421	90.35 206	98.25 262	94.96 427

BH-untuned		90.68 302	90.90 294	90.05 391	95.98 291	79.57 372	90.04 363	94.94 337	87.91 257	94.07 267	93.00 397	87.76 259	97.78 323	79.19 433	95.17 445	92.80 484

miper_ehance_all_eth		90.48 310	90.42 315	90.69 366	91.62 464	76.57 447	86.83 453	96.18 287	83.38 379	94.06 268	92.66 415	82.20 338	98.04 291	89.79 230	97.02 364	97.45 288

cl____		90.65 305	90.56 312	90.91 354	91.85 454	76.98 435	86.75 455	95.36 321	85.53 331	94.06 268	94.89 320	77.36 403	97.98 301	90.27 212	98.98 136	97.76 259

DIV-MVS_self_test		90.65 305	90.56 312	90.91 354	91.85 454	76.99 434	86.75 455	95.36 321	85.52 334	94.06 268	94.89 320	77.37 402	97.99 300	90.28 211	98.97 142	97.76 259

FA-MVS(test-final)		91.81 270	91.85 267	91.68 305	94.95 351	79.99 353	96.00 74	93.44 390	87.80 262	94.02 271	97.29 130	77.60 395	98.45 234	88.04 297	97.49 336	96.61 342

pmmvs-eth3d		91.54 279	90.73 304	93.99 171	95.76 310	87.86 174	90.83 324	93.98 371	78.23 456	94.02 271	96.22 236	82.62 335	96.83 400	86.57 323	98.33 251	97.29 303

h-mvs33		92.89 223	91.99 261	95.58 86	96.97 179	90.55 110	93.94 173	94.01 370	89.23 212	93.95 273	96.19 240	76.88 415	99.14 101	91.02 181	95.71 419	97.04 319

hse-mvs2		92.24 259	91.20 285	95.38 96	96.16 273	90.65 109	92.52 244	92.01 424	89.23 212	93.95 273	92.99 398	76.88 415	98.69 184	91.02 181	96.03 407	96.81 335

UnsupCasMVSNet_eth		90.33 320	90.34 318	90.28 379	94.64 369	80.24 343	89.69 379	95.88 297	85.77 323	93.94 275	95.69 278	81.99 342	92.98 484	84.21 367	91.30 516	97.62 273

CNVR-MVS		94.58 133	94.29 166	95.46 93	96.94 181	89.35 132	91.81 289	96.80 241	89.66 203	93.90 276	95.44 291	92.80 135	98.72 174	92.74 123	98.52 226	98.32 176

DeepC-MVS_fast	89.96 7	93.73 183	93.44 205	94.60 145	96.14 276	87.90 172	93.36 199	97.14 205	85.53 331	93.90 276	95.45 290	91.30 179	98.59 201	89.51 239	98.62 211	97.31 302
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SP-DiffGlue		90.34 319	90.20 320	90.76 362	90.52 493	90.29 114	90.37 347	94.02 368	87.19 280	93.85 278	92.55 418	78.24 384	87.50 523	89.68 235	95.41 429	94.49 444

E3new		92.83 229	93.10 217	92.04 286	95.78 307	79.45 376	90.76 327	97.90 118	87.23 278	93.79 279	95.70 277	91.55 167	98.49 224	88.17 290	96.99 369	98.16 196

XVG-OURS-SEG-HR		95.38 91	95.00 128	96.51 49	98.10 90	94.07 24	92.46 248	98.13 73	90.69 172	93.75 280	96.25 234	98.03 2	97.02 389	92.08 142	95.55 424	98.45 158

QAPM		92.88 224	92.77 227	93.22 219	95.82 303	83.31 276	96.45 46	97.35 187	83.91 372	93.75 280	96.77 183	89.25 230	98.88 142	84.56 361	97.02 364	97.49 285

MVS_111021_LR		93.66 184	93.28 211	94.80 130	96.25 265	90.95 100	90.21 355	95.43 318	87.91 257	93.74 282	94.40 348	92.88 133	96.38 419	90.39 201	98.28 258	97.07 315

usedtu_dtu_shiyan2		93.15 214	92.40 246	95.41 95	98.56 49	90.53 111	94.71 133	94.14 364	92.10 115	93.73 283	96.94 168	89.66 226	97.77 324	72.97 500	98.81 173	97.92 234

balanced_ft_v1		92.65 239	93.17 215	91.10 340	94.47 373	77.32 427	96.67 34	96.70 250	88.23 248	93.70 284	97.16 145	83.33 321	99.41 43	90.51 197	97.76 314	96.57 343

thisisatest0530		88.69 373	87.52 386	92.20 276	96.33 254	79.36 380	92.81 228	84.01 507	86.44 299	93.67 285	92.68 414	53.62 522	99.25 89	89.65 238	98.45 234	98.00 213

IMVS_0403		92.20 260	92.70 234	90.69 366	95.19 343	76.72 441	92.39 254	96.89 228	85.92 316	93.66 286	94.50 343	90.18 213	98.24 259	88.49 281	97.07 358	97.10 311

PCF-MVS	84.52 17	89.12 355	87.71 383	93.34 211	96.06 284	85.84 232	86.58 463	97.31 191	68.46 526	93.61 287	93.89 371	87.51 266	98.52 221	67.85 525	98.11 280	95.66 402
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS_111021_HR		93.63 185	93.42 207	94.26 161	96.65 209	86.96 194	89.30 395	96.23 282	88.36 245	93.57 288	94.60 338	93.45 107	97.77 324	90.23 215	98.38 244	98.03 211

icg_test_0407_2		91.18 290	91.92 265	88.94 424	95.19 343	76.72 441	84.66 500	96.89 228	85.92 316	93.55 289	94.50 343	91.06 188	92.99 483	88.49 281	97.07 358	97.10 311

IMVS_0407		92.28 255	92.83 226	90.63 370	95.19 343	76.72 441	92.79 231	96.89 228	85.92 316	93.55 289	94.50 343	91.06 188	98.07 286	88.49 281	97.07 358	97.10 311

test2506		85.42 442	84.57 445	87.96 449	97.81 116	66.53 520	96.14 70	56.35 555	89.04 217	93.55 289	98.10 48	42.88 546	98.68 186	88.09 294	99.18 106	98.67 130

MP-MVS		96.14 55	95.68 86	97.51 16	98.81 32	94.06 25	96.10 72	97.78 141	92.73 93	93.48 292	96.72 191	94.23 89	99.42 37	91.99 146	99.29 83	99.05 61
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MonoMVSNet		88.46 376	89.28 341	85.98 483	90.52 493	70.07 506	95.31 109	94.81 343	88.38 242	93.47 293	96.13 246	73.21 439	95.07 453	82.61 386	89.12 525	92.81 483

mmtdpeth		95.82 69	96.02 65	95.23 107	96.91 185	88.62 148	96.49 44	99.26 3	95.07 49	93.41 294	99.29 7	90.25 211	97.27 368	94.49 56	99.01 131	99.80 3

RPSCF		95.58 80	94.89 131	97.62 8	97.58 136	96.30 7	95.97 78	97.53 169	92.42 100	93.41 294	97.78 76	91.21 182	97.77 324	91.06 180	97.06 362	98.80 104

OpenMVS_ROB	85.12 16	89.52 346	89.05 345	90.92 352	94.58 370	81.21 328	91.10 313	93.41 391	77.03 465	93.41 294	93.99 367	83.23 323	97.80 319	79.93 422	94.80 457	93.74 465

PMVS	87.21 14	94.97 111	95.33 107	93.91 178	98.97 20	97.16 2	95.54 100	95.85 299	96.47 27	93.40 297	97.46 108	95.31 41	95.47 442	86.18 333	98.78 182	89.11 512
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
BP-MVS1		91.77 271	91.10 290	93.75 186	96.42 240	83.40 273	94.10 164	91.89 425	91.27 155	93.36 298	94.85 324	64.43 491	99.29 81	94.88 49	98.74 191	98.56 148

SIFT-NCMNet		87.31 413	87.07 406	88.02 448	90.01 506	91.85 82	82.65 520	89.57 448	86.52 296	93.34 299	92.51 420	78.05 391	86.22 537	71.95 505	98.98 136	86.01 534

HQP_MVS		94.26 156	93.93 183	95.23 107	97.71 125	88.12 164	94.56 143	97.81 135	91.74 136	93.31 300	95.59 281	86.93 281	98.95 135	89.26 249	98.51 228	98.60 144

plane_prior3						88.43 157			90.35 186	93.31 300

thres600view7		87.66 400	87.10 405	89.36 411	96.05 285	73.17 482	92.72 232	85.31 495	91.89 122	93.29 302	90.97 461	63.42 498	98.39 237	73.23 497	96.99 369	96.51 348

CPTT-MVS		94.74 122	94.12 175	96.60 46	98.15 87	93.01 59	95.84 84	97.66 151	89.21 215	93.28 303	95.46 289	88.89 234	98.98 127	89.80 229	98.82 171	97.80 253

ALIKED-LG		89.78 342	88.57 359	93.39 209	93.97 388	95.11 11	94.30 153	95.57 312	79.81 433	93.27 304	94.93 319	72.44 444	92.52 486	75.11 476	97.77 313	92.53 488

USDC		89.02 360	89.08 344	88.84 427	95.07 349	74.50 470	88.97 404	96.39 273	73.21 494	93.27 304	96.28 230	82.16 339	96.39 418	77.55 446	98.80 177	95.62 405

thres100view900		87.35 412	86.89 409	88.72 430	96.14 276	73.09 484	93.00 213	85.31 495	92.13 114	93.26 306	90.96 462	63.42 498	98.28 251	71.27 511	96.54 389	94.79 436

N_pmnet		88.90 366	87.25 396	93.83 183	94.40 376	93.81 44	84.73 495	87.09 472	79.36 444	93.26 306	92.43 425	79.29 367	91.68 493	77.50 448	97.22 353	96.00 382

CL-MVSNet_self_test		90.04 335	89.90 329	90.47 374	95.24 340	77.81 416	86.60 462	92.62 408	85.64 327	93.25 308	93.92 369	83.84 317	96.06 428	79.93 422	98.03 291	97.53 282

test_cas_vis1_n_1920		88.25 383	88.27 370	88.20 445	92.19 441	78.92 391	89.45 388	95.44 316	75.29 480	93.23 309	95.65 280	71.58 454	90.23 504	88.05 295	93.55 489	95.44 410

NormalMVS		94.10 167	93.36 208	96.31 55	99.01 15	90.84 104	94.70 134	97.90 118	90.98 162	93.22 310	95.73 274	78.94 370	99.12 105	90.38 202	99.42 54	98.97 73

SymmetryMVS		93.26 205	92.36 248	95.97 61	97.13 167	90.84 104	94.70 134	91.61 431	90.98 162	93.22 310	95.73 274	78.94 370	99.12 105	90.38 202	98.53 223	97.97 221

mvs_anonymous		90.37 317	91.30 283	87.58 457	92.17 443	68.00 513	89.84 372	94.73 347	83.82 374	93.22 310	97.40 114	87.54 265	97.40 359	87.94 300	95.05 449	97.34 300

test_yl		90.11 328	89.73 335	91.26 331	94.09 384	79.82 358	90.44 342	92.65 406	90.90 164	93.19 313	93.30 390	73.90 435	98.03 292	82.23 392	96.87 372	95.93 387

DCV-MVSNet		90.11 328	89.73 335	91.26 331	94.09 384	79.82 358	90.44 342	92.65 406	90.90 164	93.19 313	93.30 390	73.90 435	98.03 292	82.23 392	96.87 372	95.93 387

diffmvs_AUTHOR		92.34 253	92.70 234	91.26 331	94.20 380	78.42 400	89.12 400	97.60 158	87.16 282	93.17 315	95.50 287	88.66 238	97.57 344	91.30 171	97.61 328	97.79 254

viewdifsd2359ckpt13		92.57 244	92.48 244	92.83 239	95.60 322	82.35 306	91.80 291	97.49 174	85.04 349	93.14 316	95.41 296	90.94 193	98.25 257	86.68 320	96.24 402	97.87 243

fmvsm_s_conf0.5_n_7		93.61 187	93.94 182	92.63 252	96.11 279	82.76 297	90.81 325	97.55 165	86.57 294	93.14 316	97.69 84	90.17 214	96.83 400	94.46 57	98.93 149	98.31 178

viewmamba		92.69 236	93.03 218	91.69 304	93.92 391	79.50 374	89.92 367	97.33 189	88.86 225	93.13 318	95.79 267	90.97 192	97.65 338	90.86 186	96.45 393	97.94 225

D2MVS		89.93 336	89.60 337	90.92 352	94.03 387	78.40 401	88.69 418	94.85 339	78.96 450	93.08 319	95.09 312	74.57 430	96.94 393	88.19 288	98.96 144	97.41 292

UnsupCasMVSNet_bld		88.50 375	88.03 378	89.90 394	95.52 327	78.88 393	87.39 440	94.02 368	79.32 445	93.06 320	94.02 365	80.72 353	94.27 469	75.16 475	93.08 500	96.54 344

miper_lstm_enhance		89.90 337	89.80 331	90.19 385	91.37 470	77.50 422	83.82 514	95.00 334	84.84 354	93.05 321	94.96 317	76.53 421	95.20 452	89.96 227	98.67 206	97.86 244

PHI-MVS		94.34 153	93.80 187	95.95 63	95.65 317	91.67 88	94.82 129	97.86 126	87.86 260	93.04 322	94.16 360	91.58 166	98.78 164	90.27 212	98.96 144	97.41 292

TAMVS		90.16 325	89.05 345	93.49 205	96.49 232	86.37 212	90.34 350	92.55 410	80.84 427	92.99 323	94.57 341	81.94 344	98.20 264	73.51 495	98.21 270	95.90 390

Vis-MVSNet (Re-imp)		90.42 312	90.16 321	91.20 336	97.66 131	77.32 427	94.33 150	87.66 468	91.20 158	92.99 323	95.13 309	75.40 426	98.28 251	77.86 442	99.19 102	97.99 216

GDP-MVS		91.56 278	90.83 299	93.77 185	96.34 252	83.65 269	93.66 185	98.12 76	87.32 276	92.98 325	94.71 332	63.58 497	99.30 80	92.61 128	98.14 277	98.35 174

FE-MVS		89.06 358	88.29 368	91.36 324	94.78 358	79.57 372	96.77 29	90.99 435	84.87 353	92.96 326	96.29 228	60.69 509	98.80 159	80.18 417	97.11 357	95.71 398

ab-mvs		92.40 249	92.62 237	91.74 300	97.02 176	81.65 316	95.84 84	95.50 315	86.95 290	92.95 327	97.56 96	90.70 202	97.50 348	79.63 426	97.43 341	96.06 380

viewdifsd2359ckpt09		92.60 240	92.34 250	93.36 210	95.94 295	83.36 274	92.35 256	97.93 117	83.17 386	92.92 328	94.66 335	89.87 223	98.57 207	86.51 327	97.71 321	98.15 198

MCST-MVS		92.91 222	92.51 241	94.10 168	97.52 139	85.72 235	91.36 304	97.13 207	80.33 430	92.91 329	94.24 355	91.23 181	98.72 174	89.99 225	97.93 305	97.86 244

ETV-MVS		92.99 219	92.74 229	93.72 189	95.86 300	86.30 215	92.33 258	97.84 130	91.70 139	92.81 330	86.17 510	92.22 150	99.19 96	88.03 298	97.73 317	95.66 402

MM		94.41 147	94.14 174	95.22 109	95.84 301	87.21 185	94.31 152	90.92 438	94.48 58	92.80 331	97.52 101	85.27 305	99.49 29	96.58 17	99.57 35	98.97 73

TAPA-MVS	88.58 10	92.49 246	91.75 270	94.73 133	96.50 231	89.69 122	92.91 223	97.68 148	78.02 457	92.79 332	94.10 361	90.85 195	97.96 302	84.76 359	98.16 274	96.54 344
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dtuplus		90.63 307	90.59 310	90.74 363	93.85 395	77.43 425	89.01 403	96.16 289	81.42 417	92.77 333	95.54 286	88.59 239	97.28 365	81.99 395	96.00 408	97.50 284

EC-MVSNet		95.44 86	95.62 89	94.89 124	96.93 184	87.69 177	96.48 45	99.14 6	93.93 72	92.77 333	94.52 342	93.95 97	99.49 29	93.62 82	99.22 98	97.51 283

BH-RMVSNet		90.47 311	90.44 314	90.56 373	95.21 342	78.65 399	89.15 399	93.94 372	88.21 249	92.74 335	94.22 356	86.38 290	97.88 309	78.67 438	95.39 431	95.14 419

旧先验2							90.00 365		68.65 525	92.71 336			96.52 411	85.15 349

cl22		89.02 360	88.50 361	90.59 372	89.76 508	76.45 449	86.62 461	94.03 366	82.98 391	92.65 337	92.49 421	72.05 451	97.53 346	88.93 261	97.02 364	97.78 257

tfpn200view9		87.05 422	86.52 421	88.67 431	95.77 308	72.94 486	91.89 282	86.00 483	90.84 166	92.61 338	89.80 473	63.93 494	98.28 251	71.27 511	96.54 389	94.79 436

thres400		87.20 417	86.52 421	89.24 417	95.77 308	72.94 486	91.89 282	86.00 483	90.84 166	92.61 338	89.80 473	63.93 494	98.28 251	71.27 511	96.54 389	96.51 348

test_fmvs1_n		88.73 372	88.38 364	89.76 398	92.06 447	82.53 301	92.30 262	96.59 261	71.14 509	92.58 340	95.41 296	68.55 467	89.57 509	91.12 179	95.66 421	97.18 309

MS-PatchMatch		88.05 388	87.75 382	88.95 423	93.28 409	77.93 412	87.88 429	92.49 411	75.42 476	92.57 341	93.59 384	80.44 355	94.24 471	81.28 406	92.75 503	94.69 441

miper_enhance_ethall		88.42 378	87.87 381	90.07 387	88.67 522	75.52 460	85.10 490	95.59 309	75.68 472	92.49 342	89.45 482	78.96 369	97.88 309	87.86 302	97.02 364	96.81 335

CS-MVS		95.77 71	95.58 91	96.37 53	96.84 191	91.72 87	96.73 30	99.06 7	94.23 62	92.48 343	94.79 329	93.56 102	99.49 29	93.47 91	99.05 122	97.89 239

testdata				91.03 343	96.87 188	82.01 309		94.28 359	71.55 506	92.46 344	95.42 293	85.65 301	97.38 362	82.64 383	97.27 348	93.70 466

patch_mono-2		92.46 247	92.72 233	91.71 302	96.65 209	78.91 392	88.85 408	97.17 203	83.89 373	92.45 345	96.76 185	89.86 224	97.09 384	90.24 214	98.59 215	99.12 53

LF4IMVS		92.72 234	92.02 260	94.84 128	95.65 317	91.99 79	92.92 222	96.60 259	85.08 347	92.44 346	93.62 382	86.80 284	96.35 421	86.81 316	98.25 262	96.18 374

diffmvs		91.74 273	91.93 264	91.15 339	93.06 416	78.17 409	88.77 414	97.51 172	86.28 304	92.42 347	93.96 368	88.04 254	97.46 352	90.69 192	96.67 383	97.82 251
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HPM-MVS++		95.02 109	94.39 159	96.91 40	97.88 111	93.58 50	94.09 165	96.99 218	91.05 161	92.40 348	95.22 305	91.03 191	99.25 89	92.11 140	98.69 203	97.90 237

ppachtmachnet_test		88.61 374	88.64 356	88.50 438	91.76 457	70.99 500	84.59 502	92.98 397	79.30 446	92.38 349	93.53 386	79.57 364	97.45 353	86.50 328	97.17 355	97.07 315

Anonymous20231206		88.77 370	88.29 368	90.20 384	96.31 256	78.81 396	89.56 384	93.49 388	74.26 487	92.38 349	95.58 284	82.21 337	95.43 444	72.07 504	98.75 189	96.34 360

SSC-MVS3.2		89.88 338	91.06 291	86.31 481	95.90 297	63.76 534	82.68 519	92.43 413	91.42 152	92.37 351	94.58 340	86.34 291	96.60 409	84.35 366	99.50 42	98.57 147

MVS_Test		92.57 244	93.29 209	90.40 377	93.53 402	75.85 456	92.52 244	96.96 220	88.73 227	92.35 352	96.70 193	90.77 197	98.37 245	92.53 131	95.49 426	96.99 321

PVSNet_Blended_VisFu		91.63 276	91.20 285	92.94 231	97.73 123	83.95 266	92.14 269	97.46 176	78.85 452	92.35 352	94.98 316	84.16 314	99.08 111	86.36 330	96.77 378	95.79 395

CDPH-MVS		92.67 237	91.83 268	95.18 111	96.94 181	88.46 156	90.70 332	97.07 212	77.38 460	92.34 354	95.08 313	92.67 138	98.88 142	85.74 338	98.57 217	98.20 191

NCCC		94.08 169	93.54 202	95.70 80	96.49 232	89.90 120	92.39 254	96.91 227	90.64 174	92.33 355	94.60 338	90.58 205	98.96 133	90.21 216	97.70 322	98.23 186

XFeat-MNN		80.76 491	79.73 495	83.85 506	79.29 552	82.86 292	76.90 537	83.32 515	69.86 520	92.27 356	87.53 500	57.82 513	84.65 541	74.17 490	96.44 394	84.03 537

CLD-MVS		91.82 269	91.41 279	93.04 224	96.37 245	83.65 269	86.82 454	97.29 194	84.65 357	92.27 356	89.67 479	92.20 152	97.85 315	83.95 372	99.47 44	97.62 273
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MASt3R-SfM		82.76 474	82.17 471	84.53 497	83.29 546	86.01 225	82.08 523	80.49 536	63.10 542	92.22 358	94.20 357	69.18 465	77.62 547	79.63 426	95.37 433	89.94 510

DELS-MVS		92.05 265	92.16 254	91.72 301	94.44 374	80.13 347	87.62 431	97.25 197	87.34 275	92.22 358	93.18 395	89.54 228	98.73 173	89.67 236	98.20 272	96.30 365
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
viewmambaseed2359dif		90.77 299	90.81 300	90.64 369	93.46 405	77.04 431	88.83 409	96.29 277	80.79 428	92.21 360	95.11 310	88.99 232	97.28 365	85.39 345	96.20 405	97.59 276

baseline1		87.62 402	87.31 393	88.54 435	94.71 366	74.27 473	93.10 209	88.20 460	86.20 307	92.18 361	93.04 396	73.21 439	95.52 438	79.32 431	85.82 534	95.83 393

SIFT-ConvMatch		87.94 391	87.21 397	90.11 386	91.67 462	93.60 49	85.55 485	83.12 517	86.48 297	92.15 362	92.98 400	78.11 389	88.58 518	76.60 458	98.25 262	88.14 519

mvsmamba		90.24 323	89.43 340	92.64 249	95.52 327	82.36 304	96.64 35	92.29 414	81.77 409	92.14 363	96.28 230	70.59 458	99.10 110	84.44 363	95.22 444	96.47 354

TestfortrainingZip				93.68 190	95.25 339	86.20 219	96.32 56	96.38 274	92.81 92	92.13 364	93.87 374	87.28 270	98.61 196		95.07 448	96.23 371

API-MVS		91.52 280	91.61 272	91.26 331	94.16 381	86.26 216	94.66 137	94.82 341	91.17 159	92.13 364	91.08 459	90.03 221	97.06 388	79.09 435	97.35 345	90.45 507

DP-MVS Recon		92.31 254	91.88 266	93.60 194	97.18 162	86.87 196	91.10 313	97.37 181	84.92 352	92.08 366	94.08 362	88.59 239	98.20 264	83.50 375	98.14 277	95.73 397

our_test_3		87.55 404	87.59 385	87.44 459	91.76 457	70.48 501	83.83 513	90.55 443	79.79 435	92.06 367	92.17 435	78.63 378	95.63 436	84.77 358	94.73 458	96.22 372

MSDG		90.82 296	90.67 305	91.26 331	94.16 381	83.08 287	86.63 460	96.19 286	90.60 179	91.94 368	91.89 443	89.16 231	95.75 435	80.96 411	94.51 463	94.95 428

Effi-MVS+-dtu		93.90 179	92.60 239	97.77 3	94.74 363	96.67 5	94.00 168	95.41 319	89.94 195	91.93 369	92.13 436	90.12 216	98.97 132	87.68 304	97.48 337	97.67 269

SIFT-UMatch		87.96 390	87.52 386	89.29 412	91.48 467	92.84 63	85.46 487	83.94 508	87.47 272	91.86 370	92.92 402	76.78 418	87.35 526	79.73 425	98.00 297	87.69 521

SIFT-PCN-Cal		87.04 423	86.65 416	88.22 444	90.09 505	90.20 116	83.84 512	85.36 493	85.16 343	91.83 371	91.84 444	78.22 385	87.02 533	74.79 479	98.71 199	87.44 523

Gipuma		95.31 97	95.80 82	93.81 184	97.99 105	90.91 101	96.42 49	97.95 112	96.69 21	91.78 372	98.85 18	91.77 160	95.49 441	91.72 157	99.08 118	95.02 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvs1		87.59 403	87.27 395	88.54 435	88.32 523	81.26 325	90.43 345	95.72 302	70.55 516	91.70 373	94.63 336	68.13 468	89.42 511	90.59 193	95.34 434	94.94 430

onestephybrid01		92.06 264	92.07 258	92.04 286	93.45 406	80.93 333	89.82 373	96.78 242	87.60 269	91.68 374	95.43 292	88.73 237	97.43 355	88.32 285	96.85 374	97.76 259

SIFT-CM-Cal		87.51 407	86.76 414	89.76 398	91.48 467	93.30 55	84.73 495	84.04 506	85.53 331	91.66 375	92.58 417	77.01 412	88.75 517	75.29 471	98.56 218	87.24 526

HyFIR lowres test		87.19 418	85.51 438	92.24 273	97.12 169	80.51 337	85.03 491	96.06 291	66.11 534	91.66 375	92.98 400	70.12 460	99.14 101	75.29 471	95.23 443	97.07 315

hybridnocas07		91.51 281	91.66 271	91.04 342	93.14 414	78.03 410	88.75 416	96.92 224	85.97 314	91.63 377	95.31 302	87.67 261	97.31 363	88.97 260	96.61 387	97.79 254

MGCNet		92.88 224	92.27 251	94.69 136	92.35 434	86.03 224	92.88 225	89.68 446	90.53 180	91.52 378	96.43 212	82.52 336	99.32 77	95.01 48	99.54 38	98.71 124

MVP-Stereo		90.07 332	88.92 349	93.54 199	96.31 256	86.49 207	90.93 320	95.59 309	79.80 434	91.48 379	95.59 281	80.79 352	97.39 360	78.57 440	91.19 517	96.76 339
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
thres200		85.85 438	85.18 440	87.88 454	94.44 374	72.52 492	89.08 402	86.21 479	88.57 237	91.44 380	88.40 492	64.22 492	98.00 298	68.35 523	95.88 415	93.12 476

FMVSNet5		87.82 396	86.56 419	91.62 307	92.31 435	79.81 360	93.49 193	94.81 343	83.26 381	91.36 381	96.93 170	52.77 524	97.49 351	76.07 465	98.03 291	97.55 281

SIFT-PointCN		87.02 424	86.47 424	88.65 433	90.27 501	91.47 90	83.91 510	84.08 505	84.84 354	91.35 382	92.24 431	75.25 427	87.29 528	77.11 454	99.20 101	87.20 528

新几何1				93.17 222	97.16 163	87.29 182		94.43 355	67.95 527	91.29 383	94.94 318	86.97 280	98.23 261	81.06 410	97.75 315	93.98 459

xiu_mvs_v1_base_debu		91.47 282	91.52 274	91.33 326	95.69 313	81.56 317	89.92 367	96.05 293	83.22 383	91.26 384	90.74 464	91.55 167	98.82 151	89.29 246	95.91 412	93.62 469

xiu_mvs_v1_base		91.47 282	91.52 274	91.33 326	95.69 313	81.56 317	89.92 367	96.05 293	83.22 383	91.26 384	90.74 464	91.55 167	98.82 151	89.29 246	95.91 412	93.62 469

xiu_mvs_v1_base_debi		91.47 282	91.52 274	91.33 326	95.69 313	81.56 317	89.92 367	96.05 293	83.22 383	91.26 384	90.74 464	91.55 167	98.82 151	89.29 246	95.91 412	93.62 469

hybrid		91.14 291	91.24 284	90.83 358	93.15 412	77.49 423	88.76 415	96.87 234	84.51 359	91.25 387	95.23 304	87.14 275	97.25 371	88.05 295	96.24 402	97.76 259

blended_shiyan8		88.43 377	87.44 388	91.40 321	92.37 432	79.45 376	87.43 438	93.92 374	82.51 398	91.24 388	85.42 516	74.35 431	98.23 261	84.43 364	95.28 440	96.52 347

SP-SuperGlue		91.30 287	91.15 289	91.75 299	91.06 478	90.99 99	90.32 351	93.55 386	90.63 176	91.17 389	93.82 375	79.84 362	88.92 516	93.30 101	96.63 385	95.34 414

blended_shiyan6		88.42 378	87.43 389	91.40 321	92.37 432	79.43 378	87.41 439	93.91 375	82.51 398	91.17 389	85.44 515	74.34 432	98.24 259	84.38 365	95.32 435	96.53 346

CDS-MVSNet		89.55 344	88.22 374	93.53 201	95.37 336	86.49 207	89.26 396	93.59 383	79.76 436	91.15 391	92.31 429	77.12 405	98.38 241	77.51 447	97.92 306	95.71 398
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OpenMVS	89.45 8	92.27 258	92.13 257	92.68 248	94.53 372	84.10 263	95.70 88	97.03 214	82.44 401	91.14 392	96.42 214	88.47 244	98.38 241	85.95 336	97.47 338	95.55 407

SIFT-NCM-Cal		87.99 389	87.39 392	89.77 397	92.16 444	93.98 34	86.51 466	82.96 519	85.99 313	91.10 393	92.99 398	80.00 360	87.11 529	77.21 451	97.60 330	88.22 517

SPE-MVS-test		95.32 94	95.10 123	95.96 62	96.86 189	90.75 108	96.33 54	99.20 4	93.99 68	91.03 394	93.73 378	93.52 104	99.55 18	91.81 152	99.45 48	97.58 277

SIFT-MNN		87.81 397	87.11 404	89.90 394	92.19 441	93.62 48	86.73 457	84.68 501	87.19 280	90.95 395	92.80 408	73.54 438	87.09 532	78.62 439	97.32 346	88.98 513

usedtu_dtu_shiyan1		89.18 351	88.59 357	90.95 350	94.75 360	77.79 417	86.25 469	94.63 352	81.61 413	90.88 396	92.24 431	77.03 408	98.08 282	82.62 384	97.27 348	96.97 323

FE-MVSNET3		89.18 351	88.59 357	90.95 350	94.75 360	77.79 417	86.25 469	94.63 352	81.61 413	90.88 396	92.25 430	77.03 408	98.08 282	82.62 384	97.27 348	96.97 323

CNLPA		91.72 274	91.20 285	93.26 217	96.17 272	91.02 96	91.14 311	95.55 313	90.16 192	90.87 398	93.56 385	86.31 292	94.40 467	79.92 424	97.12 356	94.37 448

testing3		83.66 462	82.52 466	87.08 463	95.84 301	65.84 525	89.80 376	77.17 548	88.17 251	90.84 399	88.63 489	30.95 555	98.11 277	84.05 369	97.19 354	97.28 304

test_prior2							90.21 355		89.33 211	90.77 400	94.81 326	90.41 208		88.21 286	98.55 219

WBMVS		84.00 458	83.48 457	85.56 486	92.71 424	61.52 538	83.82 514	89.38 449	79.56 440	90.74 401	93.20 394	48.21 529	97.28 365	75.63 469	98.10 282	97.88 240

test222					96.95 180	85.27 245	88.83 409	93.61 382	65.09 537	90.74 401	94.85 324	84.62 312			97.36 344	93.91 460

TR-MVS		87.70 398	87.17 399	89.27 415	94.11 383	79.26 383	88.69 418	91.86 426	81.94 406	90.69 403	89.79 475	82.82 331	97.42 357	72.65 502	91.98 512	91.14 500

CVMVSNet		85.16 444	84.72 442	86.48 475	92.12 445	70.19 502	92.32 259	88.17 461	56.15 547	90.64 404	95.85 262	67.97 471	96.69 406	88.78 269	90.52 521	92.56 486

TEST9					96.45 236	89.46 126	90.60 336	96.92 224	79.09 448	90.49 405	94.39 349	91.31 178	98.88 142

train_agg		92.71 235	91.83 268	95.35 97	96.45 236	89.46 126	90.60 336	96.92 224	79.37 442	90.49 405	94.39 349	91.20 183	98.88 142	88.66 273	98.43 236	97.72 265

test_8					96.37 245	89.14 136	90.51 339	96.89 228	79.37 442	90.42 407	94.36 353	91.20 183	98.82 151

SIFT-UM-Cal		87.93 392	87.42 390	89.44 407	90.95 483	92.71 66	84.33 506	88.32 457	86.32 302	90.41 408	92.73 412	78.78 373	88.31 519	76.83 456	98.16 274	87.31 525

test_vis1_n		89.01 362	89.01 347	89.03 419	92.57 427	82.46 303	92.62 240	96.06 291	73.02 496	90.40 409	95.77 272	74.86 429	89.68 507	90.78 189	94.98 450	94.95 428

gbinet_0.2-2-1-0.02		88.14 387	86.86 410	91.99 290	90.70 488	80.51 337	87.36 441	93.01 396	83.45 378	90.38 410	82.42 535	72.73 442	98.54 214	85.40 343	96.27 399	96.90 328

KD-MVS_2432*1600		82.17 478	80.75 484	86.42 477	82.04 548	70.09 504	81.75 524	90.80 439	82.56 395	90.37 411	89.30 483	42.90 544	96.11 426	74.47 485	92.55 506	93.06 477

miper_refine_blended		82.17 478	80.75 484	86.42 477	82.04 548	70.09 504	81.75 524	90.80 439	82.56 395	90.37 411	89.30 483	42.90 544	96.11 426	74.47 485	92.55 506	93.06 477

SP-LightGlue		90.98 294	90.67 305	91.92 292	91.04 479	91.02 96	90.68 333	94.22 362	89.56 206	90.35 413	92.90 404	77.08 406	89.38 512	93.92 72	96.27 399	95.35 413

test_vis1_n_1920		89.45 347	89.85 330	88.28 442	93.59 401	76.71 445	90.67 334	97.78 141	79.67 438	90.30 414	96.11 249	76.62 419	92.17 489	90.31 209	93.57 487	95.96 385

agg_prior					96.20 269	88.89 142		96.88 233		90.21 415			98.78 164

wanda-best-256-512		87.53 405	86.39 425	90.97 348	91.29 472	78.39 403	85.63 483	93.75 377	81.91 407	90.09 416	83.30 529	72.25 447	98.18 267	83.96 370	95.32 435	96.33 361

FE-blended-shiyan7		87.53 405	86.39 425	90.97 348	91.29 472	78.39 403	85.63 483	93.75 377	81.91 407	90.09 416	83.30 529	72.25 447	98.18 267	83.96 370	95.32 435	96.33 361

usedtu_blend_shiyan5		89.08 357	88.33 365	91.34 325	91.29 472	79.59 368	94.02 166	97.13 207	90.07 193	90.09 416	83.30 529	72.25 447	98.10 280	81.45 403	95.32 435	96.33 361

jason		89.17 354	88.32 366	91.70 303	95.73 311	80.07 348	88.10 425	93.22 393	71.98 503	90.09 416	92.79 409	78.53 379	98.56 211	87.43 308	97.06 362	96.46 355
jason: jason.
Fast-Effi-MVS+-dtu		92.77 232	92.16 254	94.58 149	94.66 368	88.25 159	92.05 271	96.65 256	89.62 204	90.08 420	91.23 455	92.56 139	98.60 199	86.30 331	96.27 399	96.90 328

CHOSEN 1792x2688		87.19 418	85.92 431	91.00 346	97.13 167	79.41 379	84.51 503	95.60 305	64.14 539	90.07 421	94.81 326	78.26 383	97.14 382	73.34 496	95.38 432	96.46 355

PatchMatch-RL		89.18 351	88.02 379	92.64 249	95.90 297	92.87 62	88.67 420	91.06 434	80.34 429	90.03 422	91.67 449	83.34 320	94.42 466	76.35 462	94.84 456	90.64 505

BH-w/o		87.21 416	87.02 407	87.79 456	94.77 359	77.27 429	87.90 428	93.21 395	81.74 410	89.99 423	88.39 493	83.47 319	96.93 395	71.29 510	92.43 508	89.15 511

Fast-Effi-MVS+		91.28 288	90.86 297	92.53 263	95.45 332	82.53 301	89.25 398	96.52 267	85.00 350	89.91 424	88.55 491	92.94 129	98.84 149	84.72 360	95.44 428	96.22 372

AdaColmap		91.63 276	91.36 280	92.47 266	95.56 325	86.36 213	92.24 267	96.27 279	88.88 224	89.90 425	92.69 413	91.65 163	98.32 249	77.38 449	97.64 326	92.72 485

GA-MVS		87.70 398	86.82 411	90.31 378	93.27 410	77.22 430	84.72 498	92.79 402	85.11 346	89.82 426	90.07 470	66.80 476	97.76 327	84.56 361	94.27 471	95.96 385

Patchmatch-test		86.10 436	86.01 429	86.38 479	90.63 490	74.22 475	89.57 383	86.69 475	85.73 325	89.81 427	92.83 406	65.24 488	91.04 498	77.82 445	95.78 417	93.88 462

EIA-MVS		92.35 252	92.03 259	93.30 215	95.81 305	83.97 265	92.80 230	98.17 67	87.71 265	89.79 428	87.56 498	91.17 186	99.18 97	87.97 299	97.27 348	96.77 338

test12				94.43 156	95.95 293	86.75 200		96.24 281		89.76 429		89.79 225	98.79 160		97.95 304	97.75 263

pmmvs4		88.95 365	87.70 384	92.70 246	94.30 378	85.60 238	87.22 443	92.16 418	74.62 482	89.75 430	94.19 358	77.97 392	96.41 417	82.71 382	96.36 395	96.09 378

原ACMM1				92.87 237	96.91 185	84.22 260		97.01 215	76.84 467	89.64 431	94.46 347	88.00 255	98.70 182	81.53 402	98.01 294	95.70 400

blend_shiyan4		83.29 467	80.66 486	91.19 337	91.86 453	79.59 368	87.05 447	93.91 375	82.66 394	89.60 432	83.36 528	42.82 548	98.10 280	81.45 403	73.26 548	95.87 392

SP-MNN		89.68 343	89.55 339	90.06 390	90.43 498	88.06 166	89.60 381	92.13 420	86.42 301	89.57 433	92.55 418	78.14 388	87.91 522	90.35 206	96.74 381	94.22 452

MG-MVS		89.54 345	89.80 331	88.76 428	94.88 352	72.47 493	89.60 381	92.44 412	85.82 322	89.48 434	95.98 258	82.85 330	97.74 331	81.87 396	95.27 441	96.08 379

ttmdpeth		86.91 427	86.57 418	87.91 453	89.68 510	74.24 474	91.49 299	87.09 472	79.84 432	89.46 435	97.86 74	65.42 485	91.04 498	81.57 401	96.74 381	98.44 159

114514_t		90.51 309	89.80 331	92.63 252	98.00 102	82.24 307	93.40 197	97.29 194	65.84 535	89.40 436	94.80 328	86.99 279	98.75 168	83.88 373	98.61 212	96.89 330

Effi-MVS+		92.79 230	92.74 229	92.94 231	95.10 348	83.30 277	94.00 168	97.53 169	91.36 154	89.35 437	90.65 469	94.01 96	98.66 188	87.40 309	95.30 439	96.88 332

PRO-TEST		90.68 302	90.65 307	90.79 361	93.47 403	76.93 437	92.17 268	96.97 219	84.00 369	89.28 438	92.10 438	86.75 286	98.48 229	85.17 346	95.93 411	96.95 326

PDCNetPlus		79.66 500	78.21 504	84.01 504	79.49 551	73.91 478	75.29 539	96.44 271	66.51 531	89.20 439	91.98 442	30.56 556	84.51 543	75.48 470	98.93 149	93.62 469

IMVS_0404		90.67 304	91.06 291	89.50 404	95.19 343	76.72 441	86.58 463	96.89 228	85.92 316	89.17 440	94.50 343	85.77 297	94.67 461	88.49 281	97.07 358	97.10 311

SIFT-NN-CMatch		86.64 430	85.79 432	89.18 418	91.21 475	93.07 56	84.60 501	80.33 537	84.07 368	89.10 441	91.58 452	78.69 375	87.33 527	75.28 473	97.28 347	87.13 529

CR-MVSNet		87.89 393	87.12 403	90.22 382	91.01 481	78.93 389	92.52 244	92.81 400	73.08 495	89.10 441	96.93 170	67.11 473	97.64 339	88.80 268	92.70 504	94.08 454

RPMNet		90.31 322	90.14 324	90.81 360	91.01 481	78.93 389	92.52 244	98.12 76	91.91 121	89.10 441	96.89 173	68.84 466	99.41 43	90.17 219	92.70 504	94.08 454

testing3-2		83.95 459	84.22 449	83.13 511	96.28 259	54.34 553	88.51 422	83.01 518	92.19 111	89.09 444	90.98 460	45.51 535	97.44 354	74.38 487	98.01 294	97.60 275

PatchT		87.51 407	88.17 376	85.55 487	90.64 489	66.91 517	92.02 273	86.09 482	92.20 110	89.05 445	97.16 145	64.15 493	96.37 420	89.21 252	92.98 502	93.37 474

MVSFormer		92.18 261	92.23 252	92.04 286	94.74 363	80.06 349	97.15 15	97.37 181	88.98 220	88.83 446	92.79 409	77.02 410	99.60 9	96.41 18	96.75 379	96.46 355

lupinMVS		88.34 382	87.31 393	91.45 317	94.74 363	80.06 349	87.23 442	92.27 415	71.10 510	88.83 446	91.15 456	77.02 410	98.53 218	86.67 321	96.75 379	95.76 396

HQP-NCC					96.36 248		91.37 301		87.16 282	88.81 448

ACMP_Plane					96.36 248		91.37 301		87.16 282	88.81 448

HQP4-MVS										88.81 448			98.61 196			98.15 198

HQP-MVS		92.09 263	91.49 277	93.88 179	96.36 248	84.89 249	91.37 301	97.31 191	87.16 282	88.81 448	93.40 388	84.76 310	98.60 199	86.55 325	97.73 317	98.14 200

PAPM_NR		91.03 293	90.81 300	91.68 305	96.73 202	81.10 329	93.72 182	96.35 276	88.19 250	88.77 452	92.12 437	85.09 308	97.25 371	82.40 391	93.90 481	96.68 341

SCA		87.43 410	87.21 397	88.10 447	92.01 449	71.98 495	89.43 389	88.11 462	82.26 403	88.71 453	92.83 406	78.65 376	97.59 342	79.61 428	93.30 493	94.75 438

SIFT-NN-PointCN		86.59 431	85.79 432	88.99 420	90.15 502	92.46 72	84.96 493	82.76 521	83.11 387	88.70 454	92.34 428	77.62 394	87.10 530	75.03 477	97.44 340	87.42 524

F-COLMAP		92.28 255	91.06 291	95.95 63	97.52 139	91.90 81	93.53 191	97.18 202	83.98 371	88.70 454	94.04 363	88.41 246	98.55 213	80.17 418	95.99 410	97.39 297

PVSNet_BlendedMVS		90.35 318	89.96 327	91.54 312	94.81 356	78.80 397	90.14 359	96.93 222	79.43 441	88.68 456	95.06 314	86.27 293	98.15 273	80.27 414	98.04 290	97.68 268

PVSNet_Blended		88.74 371	88.16 377	90.46 376	94.81 356	78.80 397	86.64 459	96.93 222	74.67 481	88.68 456	89.18 486	86.27 293	98.15 273	80.27 414	96.00 408	94.44 447

mvsany_test1		83.91 460	82.93 464	86.84 471	86.18 535	85.93 229	81.11 527	75.03 549	70.80 515	88.57 458	94.63 336	83.08 326	87.38 525	80.39 412	86.57 533	87.21 527

AUN-MVS		90.05 333	88.30 367	95.32 101	96.09 281	90.52 112	92.42 252	92.05 423	82.08 405	88.45 459	92.86 405	65.76 483	98.69 184	88.91 263	96.07 406	96.75 340

pmmvs5		87.87 394	87.14 401	90.07 387	93.26 411	76.97 436	88.89 406	92.18 416	73.71 490	88.36 460	93.89 371	76.86 417	96.73 405	80.32 413	96.81 376	96.51 348

WTY-MVS		86.93 426	86.50 423	88.24 443	94.96 350	74.64 466	87.19 444	92.07 422	78.29 455	88.32 461	91.59 451	78.06 390	94.27 469	74.88 478	93.15 497	95.80 394

thisisatest0515		84.72 449	82.99 463	89.90 394	92.96 420	75.33 462	84.36 505	83.42 512	77.37 461	88.27 462	86.65 505	53.94 520	98.72 174	82.56 387	97.40 343	95.67 401

MIMVSNet		87.13 420	86.54 420	88.89 426	96.05 285	76.11 453	94.39 148	88.51 455	81.37 419	88.27 462	96.75 187	72.38 446	95.52 438	65.71 532	95.47 427	95.03 424

SIFT-NN-UMatch		86.43 434	85.66 435	88.76 428	90.73 487	92.76 65	84.99 492	81.25 530	84.13 367	88.17 464	92.04 439	76.90 414	86.62 534	76.34 463	96.36 395	86.91 531

test0.0.03 1		82.48 475	81.47 478	85.48 488	89.70 509	73.57 481	84.73 495	81.64 525	83.07 389	88.13 465	86.61 506	62.86 501	89.10 515	66.24 531	90.29 522	93.77 464

CMPMVS	68.83 22	87.28 414	85.67 434	92.09 284	88.77 521	85.42 242	90.31 353	94.38 356	70.02 519	88.00 466	93.30 390	73.78 437	94.03 473	75.96 467	96.54 389	96.83 334
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WB-MVSnew		84.20 455	83.89 455	85.16 492	91.62 464	66.15 524	88.44 424	81.00 532	76.23 471	87.98 467	87.77 497	84.98 309	93.35 479	62.85 539	94.10 478	95.98 384

PMMVS2		81.31 484	83.44 458	74.92 528	90.52 493	46.49 557	69.19 545	85.23 498	84.30 366	87.95 468	94.71 332	76.95 413	84.36 544	64.07 535	98.09 283	93.89 461

SD_0403		88.79 369	88.88 352	88.51 437	95.89 299	72.58 491	94.27 154	95.24 326	83.77 376	87.92 469	94.38 352	87.70 260	96.47 415	66.36 530	94.40 465	96.49 352

xiu_mvs_v2_base		89.00 363	89.19 342	88.46 440	94.86 354	74.63 467	86.97 448	95.60 305	80.88 425	87.83 470	88.62 490	91.04 190	98.81 156	82.51 389	94.38 467	91.93 492

PS-MVSNAJ		88.86 367	88.99 348	88.48 439	94.88 352	74.71 465	86.69 458	95.60 305	80.88 425	87.83 470	87.37 502	90.77 197	98.82 151	82.52 388	94.37 468	91.93 492

UWE-MVS		80.29 496	79.10 497	83.87 505	91.97 451	59.56 543	86.50 467	77.43 547	75.40 477	87.79 472	88.10 495	44.08 540	96.90 397	64.23 534	96.36 395	95.14 419

test_vis1_rt		85.58 441	84.58 444	88.60 434	87.97 524	86.76 199	85.45 488	93.59 383	66.43 532	87.64 473	89.20 485	79.33 366	85.38 539	81.59 400	89.98 524	93.66 467

ALIKED-MNN		88.42 378	87.16 400	92.21 275	93.47 403	93.93 35	92.87 227	95.20 328	71.10 510	87.62 474	93.76 377	77.41 399	91.34 496	74.50 484	98.53 223	91.36 497

tpm		84.38 452	84.08 451	85.30 490	90.47 496	63.43 535	89.34 393	85.63 488	77.24 464	87.62 474	95.03 315	61.00 508	97.30 364	79.26 432	91.09 519	95.16 417

sss		87.23 415	86.82 411	88.46 440	93.96 389	77.94 411	86.84 452	92.78 403	77.59 459	87.61 476	91.83 445	78.75 374	91.92 491	77.84 443	94.20 473	95.52 409

MAR-MVS		90.32 321	88.87 353	94.66 141	94.82 355	91.85 82	94.22 157	94.75 346	80.91 424	87.52 477	88.07 496	86.63 288	97.87 312	76.67 457	96.21 404	94.25 451
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
DPM-MVS		89.35 349	88.40 363	92.18 280	96.13 278	84.20 261	86.96 449	96.15 290	75.40 477	87.36 478	91.55 453	83.30 322	98.01 296	82.17 394	96.62 386	94.32 450

UGNet		93.08 215	92.50 242	94.79 131	93.87 393	87.99 168	95.07 121	94.26 361	90.64 174	87.33 479	97.67 87	86.89 283	98.49 224	88.10 293	98.71 199	97.91 236
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
PatchmatchNet		85.22 443	84.64 443	86.98 466	89.51 514	69.83 508	90.52 338	87.34 471	78.87 451	87.22 480	92.74 411	66.91 475	96.53 410	81.77 397	86.88 532	94.58 442
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
1112_ss		88.42 378	87.41 391	91.45 317	96.69 206	80.99 331	89.72 378	96.72 248	73.37 492	87.00 481	90.69 467	77.38 401	98.20 264	81.38 405	93.72 484	95.15 418

cascas		87.02 424	86.28 428	89.25 416	91.56 466	76.45 449	84.33 506	96.78 242	71.01 512	86.89 482	85.91 511	81.35 347	96.94 393	83.09 379	95.60 423	94.35 449

CANet		92.38 250	91.99 261	93.52 203	93.82 396	83.46 272	91.14 311	97.00 216	89.81 198	86.47 483	94.04 363	87.90 258	99.21 92	89.50 240	98.27 259	97.90 237

Test_1112_low_res		87.50 409	86.58 417	90.25 381	96.80 195	77.75 419	87.53 436	96.25 280	69.73 522	86.47 483	93.61 383	75.67 424	97.88 309	79.95 420	93.20 495	95.11 422

XFeat-NN		75.97 507	74.88 509	79.25 524	77.98 553	79.81 360	70.81 544	79.50 541	64.75 538	86.32 485	82.83 534	53.44 523	76.70 549	66.89 528	91.40 515	81.23 544

PLC	85.34 15	90.40 313	88.92 349	94.85 127	96.53 228	90.02 118	91.58 296	96.48 269	80.16 431	86.14 486	92.18 434	85.73 299	98.25 257	76.87 455	94.61 462	96.30 365
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SIFT-NN-NCMNet		86.55 432	85.56 437	89.51 403	91.84 456	94.02 30	85.72 480	81.31 529	84.33 365	86.13 487	91.77 446	79.22 368	87.46 524	74.06 492	95.70 420	87.07 530

new_pmnet		81.22 485	81.01 482	81.86 515	90.92 484	70.15 503	84.03 508	80.25 539	70.83 513	85.97 488	89.78 476	67.93 472	84.65 541	67.44 526	91.90 513	90.78 504

EPMVS		81.17 487	80.37 490	83.58 508	85.58 537	65.08 529	90.31 353	71.34 550	77.31 463	85.80 489	91.30 454	59.38 510	92.70 485	79.99 419	82.34 541	92.96 481

dtuonly		84.38 452	85.24 439	81.80 516	87.13 530	58.46 546	81.58 526	92.71 404	74.41 484	85.68 490	92.62 416	78.17 387	92.13 490	79.15 434	95.73 418	94.82 433

dmvs_re		84.69 450	83.94 454	86.95 468	92.24 437	82.93 290	89.51 385	87.37 470	84.38 364	85.37 491	85.08 520	72.44 444	86.59 535	68.05 524	91.03 520	91.33 498

tpmvs		84.22 454	83.97 453	84.94 493	87.09 531	65.18 527	91.21 307	88.35 456	82.87 392	85.21 492	90.96 462	65.24 488	96.75 404	79.60 430	85.25 535	92.90 482

FPMVS		84.50 451	83.28 459	88.16 446	96.32 255	94.49 20	85.76 478	85.47 492	83.09 388	85.20 493	94.26 354	63.79 496	86.58 536	63.72 536	91.88 514	83.40 539

Syy-MVS		84.81 447	84.93 441	84.42 499	91.71 460	63.36 536	85.89 475	81.49 526	81.03 421	85.13 494	81.64 537	77.44 398	95.00 454	85.94 337	94.12 476	94.91 431

myMVS_eth3d		79.62 501	78.26 503	83.72 507	91.71 460	61.25 540	85.89 475	81.49 526	81.03 421	85.13 494	81.64 537	32.12 554	95.00 454	71.17 514	94.12 476	94.91 431

pmmvs3		80.83 490	78.96 499	86.45 476	87.23 529	77.48 424	84.87 494	82.31 523	63.83 540	85.03 496	89.50 481	49.66 526	93.10 480	73.12 499	95.10 446	88.78 516

PAPR		87.65 401	86.77 413	90.27 380	92.85 423	77.38 426	88.56 421	96.23 282	76.82 468	84.98 497	89.75 477	86.08 295	97.16 381	72.33 503	93.35 492	96.26 369

MDTV_nov1_ep13			83.88 456		89.42 515	61.52 538	88.74 417	87.41 469	73.99 488	84.96 498	94.01 366	65.25 487	95.53 437	78.02 441	93.16 496

FBQ-MVS		83.72 461	81.80 472	89.47 405	93.62 400	76.73 440	91.20 308	87.89 466	81.52 416	84.88 499	83.74 525	49.19 527	96.66 408	70.51 518	93.70 485	95.00 426

1314		86.46 433	86.33 427	86.87 470	91.65 463	74.54 468	91.94 278	94.10 365	74.28 486	84.78 500	87.33 503	83.03 327	95.00 454	78.72 437	91.16 518	91.06 501

SP-NN		88.21 384	87.96 380	88.97 422	89.33 516	87.99 168	88.06 427	90.93 437	85.48 336	84.50 501	91.11 458	77.25 404	84.79 540	90.55 195	94.42 464	94.14 453

ADS-MVSNet2		84.01 457	82.20 470	89.41 409	89.04 518	76.37 451	87.57 432	90.98 436	72.71 500	84.46 502	92.45 422	68.08 469	96.48 413	70.58 516	83.97 536	95.38 411

ADS-MVSNet		82.25 476	81.55 476	84.34 500	89.04 518	65.30 526	87.57 432	85.13 499	72.71 500	84.46 502	92.45 422	68.08 469	92.33 488	70.58 516	83.97 536	95.38 411

PVSNet	76.22 20	82.89 472	82.37 468	84.48 498	93.96 389	64.38 532	78.60 534	88.61 454	71.50 507	84.43 504	86.36 509	74.27 433	94.60 463	69.87 519	93.69 486	94.46 446

testing91		83.56 464	82.45 467	86.91 469	92.92 421	67.29 514	86.33 468	88.07 463	86.22 306	84.26 505	85.76 512	48.15 530	97.17 379	76.27 464	94.08 479	96.27 368

MVS		84.98 446	84.30 447	87.01 465	91.03 480	77.69 421	91.94 278	94.16 363	59.36 545	84.23 506	87.50 501	85.66 300	96.80 403	71.79 506	93.05 501	86.54 533

myMVS_eth3d28		80.97 488	80.42 489	82.62 513	93.35 408	58.25 547	84.70 499	85.62 490	86.31 303	84.04 507	85.20 519	46.00 533	94.07 472	62.93 538	95.65 422	95.53 408

testing99		82.94 471	81.72 473	86.59 472	92.55 428	66.53 520	86.08 474	85.70 486	85.47 337	83.95 508	85.70 513	45.87 534	97.07 387	76.58 460	93.56 488	96.17 377

nomal-1		83.48 465	81.65 474	88.98 421	91.07 477	80.73 336	85.66 481	86.34 478	80.98 423	83.93 509	86.95 504	51.44 525	91.71 492	74.53 483	93.93 480	94.49 444

tpmrst		82.85 473	82.93 464	82.64 512	87.65 525	58.99 545	90.14 359	87.90 465	75.54 475	83.93 509	91.63 450	66.79 478	95.36 445	81.21 408	81.54 542	93.57 473

SIFT-NN		84.10 456	83.04 461	87.28 462	90.76 486	92.16 76	84.45 504	81.34 528	83.54 377	83.80 511	89.75 477	70.08 461	82.09 545	68.68 522	94.96 451	87.60 522

ET-MVSNet_ETH3D		86.15 435	84.27 448	91.79 297	93.04 417	81.28 324	87.17 445	86.14 480	79.57 439	83.65 512	88.66 488	57.10 514	98.18 267	87.74 303	95.40 430	95.90 390

HY-MVS	82.50 18	86.81 428	85.93 430	89.47 405	93.63 399	77.93 412	94.02 166	91.58 432	75.68 472	83.64 513	93.64 380	77.40 400	97.42 357	71.70 508	92.07 511	93.05 479

MDTV_nov1_ep13_2view						42.48 558	88.45 423		67.22 530	83.56 514		66.80 476		72.86 501		94.06 456

ETVMVS		79.85 499	77.94 507	85.59 485	92.97 419	66.20 523	86.13 473	80.99 533	81.41 418	83.52 515	83.89 524	41.81 549	94.98 457	56.47 544	94.25 472	95.61 406

CostFormer		83.09 469	82.21 469	85.73 484	89.27 517	67.01 516	90.35 348	86.47 477	70.42 517	83.52 515	93.23 393	61.18 506	96.85 399	77.21 451	88.26 529	93.34 475

DSMNet-mixed		82.21 477	81.56 475	84.16 502	89.57 513	70.00 507	90.65 335	77.66 546	54.99 548	83.30 517	97.57 94	77.89 393	90.50 502	66.86 529	95.54 425	91.97 491

E-PMN		80.72 492	80.86 483	80.29 521	85.11 540	68.77 510	72.96 541	81.97 524	87.76 264	83.25 518	83.01 533	62.22 504	89.17 514	77.15 453	94.31 470	82.93 540

test-LLR		83.58 463	83.17 460	84.79 495	89.68 510	66.86 518	83.08 516	84.52 502	83.07 389	82.85 519	84.78 521	62.86 501	93.49 477	82.85 380	94.86 454	94.03 457

test-mter		81.21 486	80.01 494	84.79 495	89.68 510	66.86 518	83.08 516	84.52 502	73.85 489	82.85 519	84.78 521	43.66 541	93.49 477	82.85 380	94.86 454	94.03 457

UBG		80.28 497	78.94 500	84.31 501	92.86 422	61.77 537	83.87 511	83.31 516	77.33 462	82.78 521	83.72 526	47.60 532	96.06 428	65.47 533	93.48 490	95.11 422

testing222		80.54 494	78.53 502	86.58 473	92.54 430	68.60 511	86.24 471	82.72 522	83.78 375	82.68 522	84.24 523	39.25 552	95.94 432	60.25 540	95.09 447	95.20 415

CANet_DTU		89.85 339	89.17 343	91.87 293	92.20 440	80.02 352	90.79 326	95.87 298	86.02 312	82.53 523	91.77 446	80.01 359	98.57 207	85.66 340	97.70 322	97.01 320

JIA-IIPM		85.08 445	83.04 461	91.19 337	87.56 526	86.14 221	89.40 391	84.44 504	88.98 220	82.20 524	97.95 62	56.82 516	96.15 424	76.55 461	83.45 538	91.30 499

ALIKED-NN		85.96 437	84.14 450	91.44 319	91.73 459	93.37 52	90.32 351	93.65 380	67.84 528	82.08 525	92.92 402	72.88 441	90.01 505	69.17 521	96.64 384	90.93 502

PMMVS		83.00 470	81.11 479	88.66 432	83.81 544	86.44 210	82.24 522	85.65 487	61.75 544	82.07 526	85.64 514	79.75 363	91.59 495	75.99 466	93.09 499	87.94 520

tpm2		81.46 483	80.35 491	84.80 494	89.90 507	65.14 528	90.44 342	85.36 493	65.82 536	82.05 527	92.44 424	57.94 512	96.69 406	70.71 515	88.49 528	92.56 486

IB-MVS	77.21 19	83.11 468	81.05 480	89.29 412	91.15 476	75.85 456	85.66 481	86.00 483	79.70 437	82.02 528	86.61 506	48.26 528	98.39 237	77.84 443	92.22 509	93.63 468
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
tpm cat1		80.61 493	79.46 496	84.07 503	88.78 520	65.06 530	89.26 396	88.23 459	62.27 543	81.90 529	89.66 480	62.70 503	95.29 449	71.72 507	80.60 543	91.86 494

EMVS		80.35 495	80.28 492	80.54 520	84.73 542	69.07 509	72.54 543	80.73 534	87.80 262	81.66 530	81.73 536	62.89 500	89.84 506	75.79 468	94.65 461	82.71 541

dmvs_testset		78.23 505	78.99 498	75.94 527	91.99 450	55.34 551	88.86 407	78.70 543	82.69 393	81.64 531	79.46 539	75.93 422	85.74 538	48.78 548	82.85 540	86.76 532

dp		79.28 502	78.62 501	81.24 519	85.97 536	56.45 548	86.91 450	85.26 497	72.97 498	81.45 532	89.17 487	56.01 518	95.45 443	73.19 498	76.68 547	91.82 495

GLUNet-SfM		58.71 513	56.43 516	65.55 530	45.28 557	59.80 542	54.31 548	55.90 556	37.80 550	81.24 533	73.75 544	38.27 553	70.23 553	34.22 552	87.09 531	66.64 547

testing11		81.98 481	80.52 488	86.38 479	92.69 425	67.13 515	85.79 477	84.80 500	82.16 404	81.19 534	85.41 517	45.24 536	96.88 398	74.14 491	93.24 494	95.14 419

EPNet		89.80 341	88.25 371	94.45 155	83.91 543	86.18 220	93.87 175	87.07 474	91.16 160	80.64 535	94.72 331	78.83 372	98.89 141	85.17 346	98.89 158	98.28 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TESTMET0.1,1		79.09 503	78.04 505	82.25 514	87.52 527	64.03 533	83.08 516	80.62 535	70.28 518	80.16 536	83.22 532	44.13 539	90.56 501	79.95 420	93.36 491	92.15 490

baseline2		83.38 466	81.54 477	88.90 425	91.38 469	72.84 488	88.78 413	81.22 531	78.97 449	79.82 537	87.56 498	61.73 505	97.80 319	74.30 489	90.05 523	96.05 381

gg-mvs-nofinetune		82.10 480	81.02 481	85.34 489	87.46 528	71.04 498	94.74 131	67.56 551	96.44 28	79.43 538	98.99 11	45.24 536	96.15 424	67.18 527	92.17 510	88.85 514

PVSNet_0	70.34 21	74.58 511	72.96 512	79.47 522	90.63 490	66.24 522	73.26 540	83.40 513	63.67 541	78.02 539	78.35 541	72.53 443	89.59 508	56.68 543	60.05 551	82.57 542

MVS-HIRNet		78.83 504	80.60 487	73.51 529	93.07 415	47.37 556	87.10 446	78.00 545	68.94 524	77.53 540	97.26 134	71.45 455	94.62 462	63.28 537	88.74 527	78.55 545

UWE-MVS-28		74.73 510	73.18 511	79.35 523	85.42 539	55.55 550	87.63 430	65.92 552	74.39 485	77.33 541	88.19 494	47.63 531	89.48 510	39.01 550	93.14 498	93.03 480

CHOSEN 280x420		80.04 498	77.97 506	86.23 482	90.13 503	74.53 469	72.87 542	89.59 447	66.38 533	76.29 542	85.32 518	56.96 515	95.36 445	69.49 520	94.72 459	88.79 515

PAPM		81.91 482	80.11 493	87.31 461	93.87 393	72.32 494	84.02 509	93.22 393	69.47 523	76.13 543	89.84 472	72.15 450	97.23 373	53.27 546	89.02 526	92.37 489

GG-mvs-BLEND				83.24 510	85.06 541	71.03 499	94.99 126	65.55 553		74.09 544	75.51 542	44.57 538	94.46 465	59.57 542	87.54 530	84.24 536

0.4-1-1-0.1		77.15 506	73.55 510	87.95 450	85.49 538	75.84 458	80.59 531	82.87 520	73.51 491	73.61 545	68.65 545	42.84 547	97.22 374	75.20 474	79.18 544	90.80 503

EPNet_dtu		85.63 440	84.37 446	89.40 410	86.30 534	74.33 472	91.64 294	88.26 458	84.84 354	72.96 546	89.85 471	71.27 456	97.69 334	76.60 458	97.62 327	96.18 374
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
0.4-1-1-0.2		75.80 508	72.05 514	87.04 464	82.70 547	74.17 476	77.51 535	83.48 511	71.80 504	71.57 547	65.16 547	43.07 542	96.96 391	74.34 488	78.78 545	90.00 509

0.3-1-1-0.015		75.73 509	71.83 515	87.44 459	83.47 545	74.98 463	78.69 533	83.38 514	72.24 502	70.43 548	65.81 546	39.55 551	97.08 385	74.57 481	78.30 546	90.28 508

MVE	59.87 23	73.86 512	72.65 513	77.47 526	87.00 533	74.35 471	61.37 547	60.93 554	67.27 529	69.69 549	86.49 508	81.24 351	72.33 551	56.45 545	83.45 538	85.74 535
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dongtai		53.72 514	53.79 517	53.51 533	79.69 550	36.70 559	77.18 536	32.53 562	71.69 505	68.63 550	60.79 549	26.65 557	73.11 550	30.67 553	36.29 555	50.73 548

DeepMVS_CX				53.83 532	70.38 555	64.56 531		48.52 558	33.01 551	65.50 551	74.21 543	56.19 517	46.64 555	38.45 551	70.07 549	50.30 549

MVS_clip		28.84 518	32.57 521	17.67 537	37.77 559	25.94 561	27.92 550	7.17 563	9.16 553	54.91 552	62.94 548	20.70 559	10.56 558	26.96 554	45.58 553	16.52 551

tmp_tt		37.97 517	44.33 519	18.88 536	11.80 561	21.54 562	63.51 546	45.66 559	4.23 555	51.34 553	50.48 551	59.08 511	22.11 557	44.50 549	68.35 550	13.00 552

kuosan		43.63 516	44.25 520	41.78 534	66.04 556	34.37 560	75.56 538	32.62 561	53.25 549	50.46 554	51.18 550	25.28 558	49.13 554	13.44 556	30.41 556	41.84 550

test_method		50.44 515	48.94 518	54.93 531	39.68 558	12.38 564	28.59 549	90.09 444	6.82 554	41.10 555	78.41 540	54.41 519	70.69 552	50.12 547	51.26 552	81.72 543

VLMVS_CLIP		26.72 519	28.23 523	22.16 535	23.46 560	19.29 563	25.04 551	38.45 560	10.30 552	37.65 556	43.37 552	16.55 560	34.48 556	19.59 555	39.68 554	12.71 553

MVS_baseline		9.63 521	12.05 524	2.37 539	9.15 562	0.73 568	5.23 553	1.75 566	0.31 560	26.23 557	30.60 553	5.95 562	0.00 562	4.43 557	24.78 557	6.38 555

VLMVS		7.75 524	8.50 529	5.52 538	7.85 563	5.47 565	5.34 552	3.06 564	0.41 559	11.88 558	15.91 555	11.95 561	3.89 559	3.42 558	16.65 558	7.20 554

EGC-MVSNET		80.97 488	75.73 508	96.67 45	98.85 28	94.55 19	96.83 24	96.60 259	2.44 556	5.32 559	98.25 43	92.24 149	98.02 295	91.85 151	99.21 99	97.45 288

test123		9.49 522	12.01 525	1.91 540	2.87 564	1.30 566	82.38 521	1.34 567	1.36 557	2.84 560	6.56 557	2.45 563	0.97 560	2.73 559	5.56 559	3.47 556

testmvs		9.02 523	11.42 526	1.81 541	2.77 565	1.13 567	79.44 532	1.90 565	1.18 558	2.65 561	6.80 556	1.95 564	0.87 561	2.62 560	3.45 560	3.44 557

mmdepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet_test		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

cdsmvs_eth3d_5k		23.35 520	31.13 522	0.00 542	0.00 566	0.00 569	0.00 554	95.58 311	0.00 561	0.00 562	91.15 456	93.43 109	0.00 562	0.00 561	0.00 561	0.00 558

pcd_1.5k_mvsjas		7.56 525	10.09 527	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	90.77 197	0.00 562	0.00 561	0.00 561	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

ab-mvs-re		7.56 525	10.08 528	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	90.69 467	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Meshroom													0.00 562
: In preparation.
AliceVision / Meshro													0.00 562
: In preparation.
AliceVision_Meshroom													0.00 562
: In preparation.
PatchmatchNet2					0.00 566	54.43 552	80.66 530	86.13 481	76.71 469
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														77.38 449	97.25 352	96.00 382
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.63 494
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						61.25 540								74.55 482

MSC_two_6792asdad				95.90 69	96.54 225	89.57 124		96.87 234					99.41 43	94.06 68	99.30 80	98.72 121

No_MVS				95.90 69	96.54 225	89.57 124		96.87 234					99.41 43	94.06 68	99.30 80	98.72 121

eth-test2					0.00 566

eth-test					0.00 566

OPU-MVS				95.15 112	96.84 191	89.43 128	95.21 114				95.66 279	93.12 121	98.06 288	86.28 332	98.61 212	97.95 223

save fliter					97.46 145	88.05 167	92.04 272	97.08 211	87.63 268

test_0728_SECOND				94.88 125	98.55 53	86.72 201	95.20 116	98.22 58					99.38 63	93.44 94	99.31 78	98.53 150

GSMVS																94.75 438

sam_mvs1												66.64 479				94.75 438

sam_mvs												66.41 480

MTGPA								97.62 154

test_post1							90.21 355				5.85 559	65.36 486	96.00 430	79.61 428

test_post											6.07 558	65.74 484	95.84 434

patchmatchnet-post											91.71 448	66.22 482	97.59 342

MTMP							94.82 129	54.62 557

gm-plane-assit					87.08 532	59.33 544			71.22 508		83.58 527		97.20 376	73.95 493

test9_res														88.16 291	98.40 239	97.83 248

agg_prior2														87.06 315	98.36 250	97.98 217

test_prior4						89.91 119	90.74 329

test_prior				94.61 142	95.95 293	87.23 184		97.36 186					98.68 186			97.93 228

新几何2							90.02 364

旧先验1					96.20 269	84.17 262		94.82 341			95.57 285	89.57 227			97.89 307	96.32 364

无先验							89.94 366	95.75 301	70.81 514				98.59 201	81.17 409		94.81 434

原ACMM2							89.34 393

testdata2													98.03 292	80.24 416

segment_acmp												92.14 153

testdata1							88.96 405		88.44 240

plane_prior7					97.71 125	88.68 146

plane_prior6					97.21 161	88.23 160						86.93 281

plane_prior5								97.81 135					98.95 135	89.26 249	98.51 228	98.60 144

plane_prior4											95.59 281

plane_prior2							94.56 143		91.74 136

plane_prior1					97.38 149

plane_prior						88.12 164	93.01 211		88.98 220						98.06 288

n2								0.00 568

nn								0.00 568

door-mid								92.13 420

test11								96.65 256

door								91.26 433

HQP5-MVS						84.89 249

BP-MVS														86.55 325

HQP3-MVS								97.31 191							97.73 317

HQP2-MVS												84.76 310

NP-MVS					96.82 193	87.10 188					93.40 388

ACMMP++_ref															98.82 171

ACMMP++															99.25 91

Test By Simon												90.61 203

High-resolution multi-view benchmark