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.

MM		97.29 22	96.98 29	98.23 11	98.01 111	95.03 26	98.07 55	95.76 294	97.78 1	97.52 44	98.80 25	88.09 107	99.86 9	99.44 1	99.37 61	99.80 1

fmvsm_l_conf0.5_n_a		97.63 8	97.76 5	97.26 62	98.25 89	92.59 89	97.81 91	98.68 13	94.93 33	99.24 3	98.87 18	93.52 20	99.79 36	99.32 2	99.21 74	99.40 57

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 55	98.21 95	92.75 83	97.83 87	98.73 9	95.04 31	99.30 1	98.84 23	93.34 22	99.78 38	99.32 2	99.13 83	99.50 43

test_fmvsm_n_1920		97.55 11	97.89 3	96.53 88	98.41 77	91.73 116	98.01 60	99.02 1	96.37 4	99.30 1	98.92 13	92.39 41	99.79 36	99.16 4	99.46 41	98.08 179

test_fmvsmconf_n		97.49 15	97.56 9	97.29 58	97.44 147	92.37 95	97.91 76	98.88 4	95.83 8	98.92 12	99.05 5	91.45 57	99.80 33	99.12 5	99.46 41	99.69 12

fmvsm_s_conf0.5_n		96.85 41	97.13 19	96.04 128	98.07 108	90.28 175	97.97 69	98.76 8	94.93 33	98.84 16	99.06 4	88.80 97	99.65 61	99.06 6	98.63 106	98.18 168

test_fmvsmconf0.1_n		97.09 27	97.06 22	97.19 67	95.67 253	92.21 102	97.95 72	98.27 39	95.78 12	98.40 25	99.00 7	89.99 84	99.78 38	99.06 6	99.41 53	99.59 24

MVS_0304		96.74 50	96.31 64	98.02 19	96.87 174	94.65 30	97.58 121	94.39 354	96.47 3	97.16 56	98.39 50	87.53 121	99.87 7	98.97 8	99.41 53	99.55 34

fmvsm_s_conf0.5_n_a		96.75 49	96.93 32	96.20 120	97.64 134	90.72 163	98.00 61	98.73 9	94.55 55	98.91 13	99.08 3	88.22 106	99.63 70	98.91 9	98.37 118	98.25 163

test_fmvsmvis_n_1920		96.70 51	96.84 37	96.31 109	96.62 194	91.73 116	97.98 63	98.30 32	96.19 5	96.10 102	98.95 11	89.42 88	99.76 41	98.90 10	99.08 87	97.43 213

fmvsm_s_conf0.1_n		96.58 58	96.77 44	96.01 132	96.67 192	90.25 176	97.91 76	98.38 23	94.48 59	98.84 16	99.14 1	88.06 108	99.62 71	98.82 11	98.60 108	98.15 172

test_fmvsmconf0.01_n		96.15 70	95.85 74	97.03 74	92.66 369	91.83 115	97.97 69	97.84 123	95.57 15	97.53 43	99.00 7	84.20 169	99.76 41	98.82 11	99.08 87	99.48 47

fmvsm_s_conf0.1_n_a		96.40 63	96.47 57	96.16 122	95.48 261	90.69 164	97.91 76	98.33 29	94.07 71	98.93 9	99.14 1	87.44 125	99.61 72	98.63 13	98.32 120	98.18 168

mamv4		94.66 116	96.10 69	90.37 352	98.01 111	73.41 400	96.82 198	97.78 128	89.95 216	94.52 143	97.43 133	92.91 27	99.09 152	98.28 14	99.16 80	98.60 133

MVSMamba_PlusPlus		96.51 59	96.48 56	96.59 85	98.07 108	91.97 111	98.14 49	97.79 127	90.43 205	97.34 52	97.52 129	91.29 63	99.19 133	98.12 15	99.64 14	98.60 133

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 32	94.76 46	98.30 26	98.90 15	93.77 17	99.68 57	97.93 16	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_vis1_n_1920		94.17 126	94.58 107	92.91 287	97.42 148	82.02 354	97.83 87	97.85 119	94.68 49	98.10 30	98.49 40	70.15 348	99.32 120	97.91 17	98.82 98	97.40 215

reproduce_model		97.51 14	97.51 13	97.50 49	98.99 46	93.01 77	97.79 93	98.21 51	95.73 13	97.99 33	99.03 6	92.63 36	99.82 28	97.80 18	99.42 50	99.67 13

balanced_conf03		96.84 43	96.89 34	96.68 79	97.63 136	92.22 101	98.17 48	97.82 125	94.44 61	98.23 28	97.36 136	90.97 71	99.22 130	97.74 19	99.66 10	98.61 132

reproduce-ours		97.53 12	97.51 13	97.60 46	98.97 47	93.31 68	97.71 104	98.20 53	95.80 10	97.88 37	98.98 9	92.91 27	99.81 30	97.68 20	99.43 48	99.67 13

our_new_method		97.53 12	97.51 13	97.60 46	98.97 47	93.31 68	97.71 104	98.20 53	95.80 10	97.88 37	98.98 9	92.91 27	99.81 30	97.68 20	99.43 48	99.67 13

MSC_two_6792asdad				98.86 1	98.67 61	96.94 1		97.93 108					99.86 9	97.68 20	99.67 6	99.77 2

No_MVS				98.86 1	98.67 61	96.94 1		97.93 108					99.86 9	97.68 20	99.67 6	99.77 2

patch_mono-2		96.83 44	97.44 16	95.01 181	99.05 39	85.39 308	96.98 185	98.77 7	94.70 48	97.99 33	98.66 29	93.61 19	99.91 1	97.67 24	99.50 35	99.72 11

test_vis1_n		92.37 198	92.26 183	92.72 295	94.75 309	82.64 344	98.02 59	96.80 242	91.18 174	97.77 41	97.93 91	58.02 396	98.29 236	97.63 25	98.21 124	97.23 224

test_fmvs1_n		92.73 188	92.88 157	92.29 306	96.08 239	81.05 362	97.98 63	97.08 212	90.72 189	96.79 69	98.18 73	63.07 387	98.45 221	97.62 26	98.42 117	97.36 216

test_fmvs1		93.21 163	93.53 135	92.25 308	96.55 203	81.20 361	97.40 145	96.96 225	90.68 191	96.80 67	98.04 82	69.25 354	98.40 224	97.58 27	98.50 111	97.16 225

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 35	98.27 39	95.13 26	99.19 4	98.89 16	95.54 5	99.85 18	97.52 28	99.66 10	99.56 31

test_241102_TWO								98.27 39	95.13 26	98.93 9	98.89 16	94.99 11	99.85 18	97.52 28	99.65 13	99.74 8

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 42	97.85 119	94.92 35	98.73 18	98.87 18	95.08 8	99.84 23	97.52 28	99.67 6	99.48 47
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_SECOND				98.51 4	99.45 3	95.93 5	98.21 42	98.28 36					99.86 9	97.52 28	99.67 6	99.75 6

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 61	95.39 11	99.29 1	98.28 36	94.78 44	98.93 9	98.87 18	96.04 2	99.86 9	97.45 32	99.58 23	99.59 24

test_0728_THIRD									94.78 44	98.73 18	98.87 18	95.87 4	99.84 23	97.45 32	99.72 2	99.77 2

EC-MVSNet		96.42 62	96.47 57	96.26 115	97.01 169	91.52 128	98.89 5	97.75 130	94.42 62	96.64 78	97.68 112	89.32 89	98.60 209	97.45 32	99.11 86	98.67 130

IU-MVS					99.42 7	95.39 11		97.94 107	90.40 207	98.94 8				97.41 35	99.66 10	99.74 8

mmtdpeth		89.70 305	88.96 303	91.90 316	95.84 248	84.42 324	97.46 139	95.53 310	90.27 208	94.46 146	90.50 377	69.74 353	98.95 169	97.39 36	69.48 402	92.34 379

dcpmvs_2		96.37 65	97.05 25	94.31 223	98.96 49	84.11 329	97.56 124	97.51 162	93.92 76	97.43 49	98.52 37	92.75 32	99.32 120	97.32 37	99.50 35	99.51 40

CS-MVS		96.86 39	97.06 22	96.26 115	98.16 101	91.16 148	99.09 3	97.87 114	95.30 21	97.06 62	98.03 83	91.72 50	98.71 199	97.10 38	99.17 78	98.90 108

TSAR-MVS + MP.		97.42 16	97.33 18	97.69 41	99.25 27	94.24 41	98.07 55	97.85 119	93.72 82	98.57 21	98.35 54	93.69 18	99.40 113	97.06 39	99.46 41	99.44 52
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		97.68 6	97.44 16	98.37 7	98.90 53	95.86 6	97.27 158	98.08 77	95.81 9	97.87 40	98.31 63	94.26 13	99.68 57	97.02 40	99.49 38	99.57 28

SD-MVS		97.41 17	97.53 11	97.06 73	98.57 72	94.46 34	97.92 75	98.14 67	94.82 41	99.01 6	98.55 35	94.18 14	97.41 337	96.94 41	99.64 14	99.32 65
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
SPE-MVS-test		96.89 37	97.04 26	96.45 99	98.29 85	91.66 122	99.03 4	97.85 119	95.84 7	96.90 65	97.97 89	91.24 64	98.75 192	96.92 42	99.33 63	98.94 101

CANet		96.39 64	96.02 70	97.50 49	97.62 137	93.38 63	97.02 179	97.96 105	95.42 18	94.86 135	97.81 104	87.38 127	99.82 28	96.88 43	99.20 76	99.29 66

TSAR-MVS + GP.		96.69 53	96.49 55	97.27 61	98.31 84	93.39 62	96.79 200	96.72 245	94.17 69	97.44 47	97.66 115	92.76 31	99.33 118	96.86 44	97.76 140	99.08 87

DeepPCF-MVS	93.97 1	96.61 56	97.09 21	95.15 173	98.09 104	86.63 284	96.00 263	98.15 65	95.43 17	97.95 35	98.56 33	93.40 21	99.36 117	96.77 45	99.48 39	99.45 50

BP-MVS1		95.89 79	95.49 79	97.08 72	96.67 192	93.20 72	98.08 53	96.32 269	94.56 54	96.32 92	97.84 101	84.07 172	99.15 142	96.75 46	98.78 100	98.90 108

test_cas_vis1_n_1920		94.48 120	94.55 111	94.28 225	96.78 185	86.45 289	97.63 117	97.64 145	93.32 101	97.68 42	98.36 53	73.75 325	99.08 155	96.73 47	99.05 89	97.31 220

SMA-MVS		97.35 19	97.03 27	98.30 8	99.06 38	95.42 10	97.94 73	98.18 60	90.57 201	98.85 15	98.94 12	93.33 23	99.83 26	96.72 48	99.68 4	99.63 19
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
DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 166	98.35 27	95.16 25	98.71 20	98.80 25	95.05 10	99.89 3	96.70 49	99.73 1	99.73 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.59 10	97.54 10	97.73 37	99.40 11	93.77 56	98.53 14	98.29 34	95.55 16	98.56 22	97.81 104	93.90 15	99.65 61	96.62 50	99.21 74	99.77 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
MSLP-MVS++		96.94 35	97.06 22	96.59 85	98.72 58	91.86 114	97.67 108	98.49 19	94.66 51	97.24 54	98.41 49	92.31 44	98.94 171	96.61 51	99.46 41	98.96 98

MP-MVS-pluss		96.70 51	96.27 66	97.98 22	99.23 30	94.71 29	96.96 187	98.06 85	90.67 192	95.55 122	98.78 27	91.07 68	99.86 9	96.58 52	99.55 26	99.38 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SteuartSystems-ACMMP		97.62 9	97.53 11	97.87 24	98.39 80	94.25 40	98.43 22	98.27 39	95.34 20	98.11 29	98.56 33	94.53 12	99.71 49	96.57 53	99.62 17	99.65 17
Skip Steuart: Steuart Systems R&D Blog.
MCST-MVS		97.18 24	96.84 37	98.20 14	99.30 24	95.35 15	97.12 173	98.07 82	93.54 91	96.08 103	97.69 111	93.86 16	99.71 49	96.50 54	99.39 57	99.55 34

SF-MVS		97.39 18	97.13 19	98.17 15	99.02 42	95.28 19	98.23 39	98.27 39	92.37 135	98.27 27	98.65 31	93.33 23	99.72 48	96.49 55	99.52 30	99.51 40

EI-MVSNet-Vis-set		96.51 59	96.47 57	96.63 82	98.24 90	91.20 143	96.89 191	97.73 133	94.74 47	96.49 85	98.49 40	90.88 74	99.58 80	96.44 56	98.32 120	99.13 80

VDD-MVS		93.82 144	93.08 150	96.02 130	97.88 121	89.96 186	97.72 102	95.85 290	92.43 133	95.86 111	98.44 46	68.42 362	99.39 114	96.31 57	94.85 203	98.71 127

ACMMP_NAP		97.20 23	96.86 35	98.23 11	99.09 34	95.16 22	97.60 120	98.19 58	92.82 126	97.93 36	98.74 28	91.60 55	99.86 9	96.26 58	99.52 30	99.67 13

diffmvs		95.25 96	95.13 94	95.63 151	96.43 217	89.34 208	95.99 264	97.35 193	92.83 125	96.31 93	97.37 135	86.44 138	98.67 202	96.26 58	97.19 159	98.87 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet-UG-set		96.34 66	96.30 65	96.47 96	98.20 96	90.93 155	96.86 193	97.72 135	94.67 50	96.16 100	98.46 44	90.43 79	99.58 80	96.23 60	97.96 133	98.90 108

SR-MVS		97.01 32	96.86 35	97.47 51	99.09 34	93.27 70	97.98 63	98.07 82	93.75 81	97.45 46	98.48 43	91.43 59	99.59 77	96.22 61	99.27 67	99.54 36

xiu_mvs_v1_base_debu		95.01 102	94.76 101	95.75 143	96.58 198	91.71 118	96.25 249	97.35 193	92.99 115	96.70 73	96.63 179	82.67 200	99.44 109	96.22 61	97.46 144	96.11 256

xiu_mvs_v1_base		95.01 102	94.76 101	95.75 143	96.58 198	91.71 118	96.25 249	97.35 193	92.99 115	96.70 73	96.63 179	82.67 200	99.44 109	96.22 61	97.46 144	96.11 256

xiu_mvs_v1_base_debi		95.01 102	94.76 101	95.75 143	96.58 198	91.71 118	96.25 249	97.35 193	92.99 115	96.70 73	96.63 179	82.67 200	99.44 109	96.22 61	97.46 144	96.11 256

alignmvs		95.87 81	95.23 91	97.78 31	97.56 145	95.19 21	97.86 81	97.17 204	94.39 65	96.47 87	96.40 192	85.89 146	99.20 132	96.21 65	95.11 201	98.95 100

sasdasda		96.02 73	95.45 82	97.75 35	97.59 140	95.15 23	98.28 30	97.60 149	94.52 57	96.27 95	96.12 206	87.65 116	99.18 136	96.20 66	94.82 205	98.91 105

canonicalmvs		96.02 73	95.45 82	97.75 35	97.59 140	95.15 23	98.28 30	97.60 149	94.52 57	96.27 95	96.12 206	87.65 116	99.18 136	96.20 66	94.82 205	98.91 105

MGCFI-Net		95.94 78	95.40 86	97.56 48	97.59 140	94.62 31	98.21 42	97.57 154	94.41 63	96.17 99	96.16 204	87.54 120	99.17 138	96.19 68	94.73 210	98.91 105

RRT-MVS		94.51 118	94.35 118	94.98 184	96.40 218	86.55 287	97.56 124	97.41 185	93.19 106	94.93 133	97.04 154	79.12 265	99.30 124	96.19 68	97.32 154	99.09 86

MTAPA		97.08 28	96.78 43	97.97 23	99.37 16	94.42 36	97.24 160	98.08 77	95.07 30	96.11 101	98.59 32	90.88 74	99.90 2	96.18 70	99.50 35	99.58 27

APD-MVS_3200maxsize		96.81 45	96.71 47	97.12 69	99.01 45	92.31 98	97.98 63	98.06 85	93.11 112	97.44 47	98.55 35	90.93 72	99.55 90	96.06 71	99.25 71	99.51 40

SR-MVS-dyc-post		96.88 38	96.80 42	97.11 70	99.02 42	92.34 96	97.98 63	98.03 94	93.52 93	97.43 49	98.51 38	91.40 60	99.56 88	96.05 72	99.26 69	99.43 54

RE-MVS-def			96.72 46		99.02 42	92.34 96	97.98 63	98.03 94	93.52 93	97.43 49	98.51 38	90.71 76		96.05 72	99.26 69	99.43 54

MVS_111021_HR		96.68 55	96.58 52	96.99 75	98.46 73	92.31 98	96.20 254	98.90 3	94.30 68	95.86 111	97.74 109	92.33 42	99.38 116	96.04 74	99.42 50	99.28 68

PHI-MVS		96.77 47	96.46 60	97.71 40	98.40 78	94.07 48	98.21 42	98.45 22	89.86 218	97.11 60	98.01 86	92.52 39	99.69 55	96.03 75	99.53 29	99.36 63

casdiffmvs_mvg		95.81 82	95.57 77	96.51 92	96.87 174	91.49 129	97.50 131	97.56 158	93.99 74	95.13 131	97.92 92	87.89 112	98.78 187	95.97 76	97.33 152	99.26 70
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++		97.34 20	96.97 30	98.47 5	99.08 36	96.16 4	97.55 128	97.97 104	95.59 14	96.61 79	97.89 93	92.57 38	99.84 23	95.95 77	99.51 33	99.40 57

DELS-MVS		96.61 56	96.38 63	97.30 57	97.79 125	93.19 73	95.96 265	98.18 60	95.23 22	95.87 110	97.65 116	91.45 57	99.70 54	95.87 78	99.44 47	99.00 96
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
MVS_111021_LR		96.24 69	96.19 68	96.39 104	98.23 94	91.35 136	96.24 252	98.79 6	93.99 74	95.80 113	97.65 116	89.92 86	99.24 128	95.87 78	99.20 76	98.58 135

h-mvs33		94.15 128	93.52 137	96.04 128	97.81 124	90.22 177	97.62 119	97.58 153	95.19 23	96.74 71	97.45 130	83.67 177	99.61 72	95.85 80	79.73 376	98.29 162

hse-mvs2		93.45 156	92.99 152	94.81 194	97.02 168	88.59 230	96.69 211	96.47 263	95.19 23	96.74 71	96.16 204	83.67 177	98.48 220	95.85 80	79.13 380	97.35 218

NCCC		97.30 21	97.03 27	98.11 17	98.77 56	95.06 25	97.34 151	98.04 92	95.96 6	97.09 61	97.88 95	93.18 25	99.71 49	95.84 82	99.17 78	99.56 31

VNet		95.89 79	95.45 82	97.21 65	98.07 108	92.94 80	97.50 131	98.15 65	93.87 78	97.52 44	97.61 122	85.29 153	99.53 94	95.81 83	95.27 196	99.16 76

PC_three_1452									90.77 186	98.89 14	98.28 68	96.24 1	98.35 231	95.76 84	99.58 23	99.59 24

9.14			96.75 45		98.93 50		97.73 99	98.23 50	91.28 170	97.88 37	98.44 46	93.00 26	99.65 61	95.76 84	99.47 40

XVS		97.18 24	96.96 31	97.81 28	99.38 14	94.03 50	98.59 12	98.20 53	94.85 37	96.59 81	98.29 66	91.70 52	99.80 33	95.66 86	99.40 55	99.62 20

X-MVStestdata		91.71 223	89.67 287	97.81 28	99.38 14	94.03 50	98.59 12	98.20 53	94.85 37	96.59 81	32.69 420	91.70 52	99.80 33	95.66 86	99.40 55	99.62 20

baseline		95.58 88	95.42 85	96.08 124	96.78 185	90.41 173	97.16 170	97.45 176	93.69 85	95.65 120	97.85 99	87.29 128	98.68 201	95.66 86	97.25 157	99.13 80

ETV-MVS		96.02 73	95.89 73	96.40 102	97.16 155	92.44 93	97.47 137	97.77 129	94.55 55	96.48 86	94.51 285	91.23 66	98.92 173	95.65 89	98.19 125	97.82 194

casdiffmvs		95.64 85	95.49 79	96.08 124	96.76 190	90.45 171	97.29 157	97.44 180	94.00 73	95.46 126	97.98 88	87.52 123	98.73 195	95.64 90	97.33 152	99.08 87
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HFP-MVS		97.14 26	96.92 33	97.83 26	99.42 7	94.12 46	98.52 15	98.32 30	93.21 103	97.18 55	98.29 66	92.08 46	99.83 26	95.63 91	99.59 19	99.54 36

ACMMPR		97.07 29	96.84 37	97.79 30	99.44 6	93.88 52	98.52 15	98.31 31	93.21 103	97.15 57	98.33 60	91.35 61	99.86 9	95.63 91	99.59 19	99.62 20

HPM-MVS		96.69 53	96.45 61	97.40 53	99.36 18	93.11 75	98.87 6	98.06 85	91.17 175	96.40 90	97.99 87	90.99 70	99.58 80	95.61 93	99.61 18	99.49 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		97.02 31	96.81 41	97.64 44	99.33 21	93.54 59	98.80 8	98.28 36	92.99 115	96.45 89	98.30 65	91.90 49	99.85 18	95.61 93	99.68 4	99.54 36

DeepC-MVS	93.07 3	96.06 71	95.66 76	97.29 58	97.96 114	93.17 74	97.30 156	98.06 85	93.92 76	93.38 171	98.66 29	86.83 133	99.73 45	95.60 95	99.22 73	98.96 98
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		96.96 33	96.67 48	97.85 25	99.37 16	94.12 46	98.49 19	98.18 60	92.64 131	96.39 91	98.18 73	91.61 54	99.88 4	95.59 96	99.55 26	99.57 28

region2R		97.07 29	96.84 37	97.77 33	99.46 2	93.79 54	98.52 15	98.24 47	93.19 106	97.14 58	98.34 57	91.59 56	99.87 7	95.46 97	99.59 19	99.64 18

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 69	96.04 2	99.24 128	95.36 98	99.59 19	99.56 31

lupinMVS		94.99 106	94.56 108	96.29 113	96.34 222	91.21 141	95.83 272	96.27 273	88.93 251	96.22 97	96.88 162	86.20 143	98.85 180	95.27 99	99.05 89	98.82 120

reproduce_monomvs		91.30 250	91.10 224	91.92 314	96.82 181	82.48 348	97.01 182	97.49 165	94.64 53	88.35 300	95.27 250	70.53 343	98.10 253	95.20 100	84.60 344	95.19 307

mPP-MVS		96.86 39	96.60 50	97.64 44	99.40 11	93.44 61	98.50 18	98.09 76	93.27 102	95.95 109	98.33 60	91.04 69	99.88 4	95.20 100	99.57 25	99.60 23

DeepC-MVS_fast	93.89 2	96.93 36	96.64 49	97.78 31	98.64 67	94.30 37	97.41 141	98.04 92	94.81 42	96.59 81	98.37 52	91.24 64	99.64 69	95.16 102	99.52 30	99.42 56
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
jason		94.84 111	94.39 117	96.18 121	95.52 259	90.93 155	96.09 258	96.52 260	89.28 237	96.01 107	97.32 137	84.70 160	98.77 190	95.15 103	98.91 97	98.85 116
jason: jason.
train_agg		96.30 67	95.83 75	97.72 38	98.70 59	94.19 42	96.41 233	98.02 97	88.58 263	96.03 104	97.56 126	92.73 34	99.59 77	95.04 104	99.37 61	99.39 59

mvsany_test1		93.93 140	93.98 123	93.78 253	94.94 299	86.80 277	94.62 320	92.55 385	88.77 260	96.85 66	98.49 40	88.98 93	98.08 258	95.03 105	95.62 190	96.46 245

test_prior2							96.35 241		92.80 127	96.03 104	97.59 123	92.01 47		95.01 106	99.38 58

nrg030		94.05 135	93.31 146	96.27 114	95.22 283	94.59 32	98.34 25	97.46 171	92.93 122	91.21 229	96.64 175	87.23 130	98.22 240	94.99 107	85.80 324	95.98 260

VDDNet		93.05 172	92.07 186	96.02 130	96.84 177	90.39 174	98.08 53	95.85 290	86.22 323	95.79 114	98.46 44	67.59 365	99.19 133	94.92 108	94.85 203	98.47 147

mvsmamba		94.57 117	94.14 121	95.87 136	97.03 167	89.93 187	97.84 85	95.85 290	91.34 166	94.79 137	96.80 164	80.67 236	98.81 184	94.85 109	98.12 129	98.85 116

APD-MVS		96.95 34	96.60 50	98.01 20	99.03 41	94.93 27	97.72 102	98.10 75	91.50 159	98.01 32	98.32 62	92.33 42	99.58 80	94.85 109	99.51 33	99.53 39
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
GST-MVS		96.85 41	96.52 54	97.82 27	99.36 18	94.14 45	98.29 29	98.13 68	92.72 128	96.70 73	98.06 80	91.35 61	99.86 9	94.83 111	99.28 66	99.47 49

MP-MVS		96.77 47	96.45 61	97.72 38	99.39 13	93.80 53	98.41 23	98.06 85	93.37 98	95.54 124	98.34 57	90.59 78	99.88 4	94.83 111	99.54 28	99.49 45
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test9_res														94.81 113	99.38 58	99.45 50

PS-MVSNAJ		95.37 92	95.33 89	95.49 161	97.35 149	90.66 166	95.31 299	97.48 166	93.85 79	96.51 84	95.70 231	88.65 100	99.65 61	94.80 114	98.27 122	96.17 251

HPM-MVS_fast		96.51 59	96.27 66	97.22 64	99.32 22	92.74 84	98.74 9	98.06 85	90.57 201	96.77 70	98.35 54	90.21 81	99.53 94	94.80 114	99.63 16	99.38 61

xiu_mvs_v2_base		95.32 94	95.29 90	95.40 166	97.22 151	90.50 169	95.44 293	97.44 180	93.70 84	96.46 88	96.18 201	88.59 103	99.53 94	94.79 116	97.81 137	96.17 251

CSCG		96.05 72	95.91 72	96.46 98	99.24 28	90.47 170	98.30 28	98.57 18	89.01 246	93.97 158	97.57 124	92.62 37	99.76 41	94.66 117	99.27 67	99.15 78

test_fmvs2		89.77 304	89.93 276	89.31 366	93.68 345	76.37 393	97.64 115	95.90 287	89.84 221	91.49 216	96.26 199	58.77 395	97.10 347	94.65 118	91.13 269	94.46 343

EIA-MVS		95.53 90	95.47 81	95.71 148	97.06 163	89.63 192	97.82 89	97.87 114	93.57 87	93.92 159	95.04 259	90.61 77	98.95 169	94.62 119	98.68 104	98.54 137

SDMVSNet		94.17 126	93.61 131	95.86 138	98.09 104	91.37 135	97.35 150	98.20 53	93.18 108	91.79 209	97.28 139	79.13 264	98.93 172	94.61 120	92.84 240	97.28 221

ZD-MVS					99.05 39	94.59 32		98.08 77	89.22 239	97.03 63	98.10 76	92.52 39	99.65 61	94.58 121	99.31 65

ACMMP		96.27 68	95.93 71	97.28 60	99.24 28	92.62 87	98.25 35	98.81 5	92.99 115	94.56 142	98.39 50	88.96 94	99.85 18	94.57 122	97.63 141	99.36 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
GDP-MVS		95.62 86	95.13 94	97.09 71	96.79 184	93.26 71	97.89 79	97.83 124	93.58 86	96.80 67	97.82 103	83.06 191	99.16 140	94.40 123	97.95 134	98.87 114

PGM-MVS		96.81 45	96.53 53	97.65 42	99.35 20	93.53 60	97.65 111	98.98 2	92.22 137	97.14 58	98.44 46	91.17 67	99.85 18	94.35 124	99.46 41	99.57 28

ET-MVSNet_ETH3D		91.49 238	90.11 267	95.63 151	96.40 218	91.57 127	95.34 296	93.48 373	90.60 200	75.58 396	95.49 242	80.08 248	96.79 359	94.25 125	89.76 287	98.52 139

LFMVS		93.60 150	92.63 168	96.52 89	98.13 103	91.27 138	97.94 73	93.39 374	90.57 201	96.29 94	98.31 63	69.00 355	99.16 140	94.18 126	95.87 183	99.12 83

MVSFormer		95.37 92	95.16 93	95.99 133	96.34 222	91.21 141	98.22 40	97.57 154	91.42 163	96.22 97	97.32 137	86.20 143	97.92 289	94.07 127	99.05 89	98.85 116

test_djsdf		93.07 171	92.76 161	94.00 237	93.49 351	88.70 228	98.22 40	97.57 154	91.42 163	90.08 254	95.55 239	82.85 197	97.92 289	94.07 127	91.58 261	95.40 289

mvs_anonymous		93.82 144	93.74 127	94.06 233	96.44 216	85.41 306	95.81 273	97.05 217	89.85 220	90.09 253	96.36 194	87.44 125	97.75 307	93.97 129	96.69 170	99.02 90

VPA-MVSNet		93.24 162	92.48 177	95.51 159	95.70 251	92.39 94	97.86 81	98.66 16	92.30 136	92.09 202	95.37 245	80.49 240	98.40 224	93.95 130	85.86 323	95.75 273

agg_prior2														93.94 131	99.38 58	99.50 43

mvs_tets		92.31 201	91.76 197	93.94 244	93.41 354	88.29 239	97.63 117	97.53 160	92.04 146	88.76 292	96.45 189	74.62 317	98.09 257	93.91 132	91.48 263	95.45 285

Effi-MVS+		94.93 107	94.45 115	96.36 107	96.61 195	91.47 131	96.41 233	97.41 185	91.02 181	94.50 144	95.92 215	87.53 121	98.78 187	93.89 133	96.81 165	98.84 119

jajsoiax		92.42 195	91.89 194	94.03 236	93.33 357	88.50 235	97.73 99	97.53 160	92.00 148	88.85 289	96.50 187	75.62 309	98.11 252	93.88 134	91.56 262	95.48 281

XVG-OURS-SEG-HR		93.86 143	93.55 133	94.81 194	97.06 163	88.53 234	95.28 300	97.45 176	91.68 155	94.08 155	97.68 112	82.41 208	98.90 176	93.84 135	92.47 246	96.98 228

PS-MVSNAJss		93.74 147	93.51 138	94.44 214	93.91 337	89.28 213	97.75 96	97.56 158	92.50 132	89.94 256	96.54 185	88.65 100	98.18 245	93.83 136	90.90 275	95.86 261

EPNet		95.20 99	94.56 108	97.14 68	92.80 366	92.68 86	97.85 84	94.87 342	96.64 2	92.46 187	97.80 106	86.23 140	99.65 61	93.72 137	98.62 107	99.10 85
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		95.27 95	94.91 99	96.38 105	98.20 96	90.86 157	97.27 158	98.25 45	90.21 209	94.18 152	97.27 141	87.48 124	99.73 45	93.53 138	97.77 139	98.55 136

CPTT-MVS		95.57 89	95.19 92	96.70 78	99.27 26	91.48 130	98.33 26	98.11 73	87.79 289	95.17 130	98.03 83	87.09 131	99.61 72	93.51 139	99.42 50	99.02 90

MVSTER		93.20 164	92.81 160	94.37 217	96.56 201	89.59 195	97.06 176	97.12 207	91.24 171	91.30 223	95.96 213	82.02 215	98.05 265	93.48 140	90.55 279	95.47 283

PVSNet_BlendedMVS		94.06 134	93.92 124	94.47 212	98.27 86	89.46 203	96.73 205	98.36 24	90.17 210	94.36 147	95.24 253	88.02 109	99.58 80	93.44 141	90.72 277	94.36 347

PVSNet_Blended		94.87 110	94.56 108	95.81 140	98.27 86	89.46 203	95.47 292	98.36 24	88.84 254	94.36 147	96.09 211	88.02 109	99.58 80	93.44 141	98.18 126	98.40 155

3Dnovator	91.36 5	95.19 100	94.44 116	97.44 52	96.56 201	93.36 65	98.65 11	98.36 24	94.12 70	89.25 281	98.06 80	82.20 212	99.77 40	93.41 143	99.32 64	99.18 75

EPP-MVSNet		95.22 98	95.04 97	95.76 141	97.49 146	89.56 196	98.67 10	97.00 223	90.69 190	94.24 150	97.62 121	89.79 87	98.81 184	93.39 144	96.49 174	98.92 104

CHOSEN 280x420		93.12 168	92.72 166	94.34 220	96.71 191	87.27 265	90.29 394	97.72 135	86.61 315	91.34 220	95.29 247	84.29 168	98.41 223	93.25 145	98.94 95	97.35 218

3Dnovator+	91.43 4	95.40 91	94.48 114	98.16 16	96.90 173	95.34 16	98.48 20	97.87 114	94.65 52	88.53 297	98.02 85	83.69 176	99.71 49	93.18 146	98.96 94	99.44 52

test_yl		94.78 113	94.23 119	96.43 100	97.74 127	91.22 139	96.85 194	97.10 209	91.23 172	95.71 116	96.93 157	84.30 166	99.31 122	93.10 147	95.12 199	98.75 122

DCV-MVSNet		94.78 113	94.23 119	96.43 100	97.74 127	91.22 139	96.85 194	97.10 209	91.23 172	95.71 116	96.93 157	84.30 166	99.31 122	93.10 147	95.12 199	98.75 122

test_vis1_rt		86.16 343	85.06 344	89.46 362	93.47 353	80.46 369	96.41 233	86.61 412	85.22 337	79.15 389	88.64 391	52.41 404	97.06 348	93.08 149	90.57 278	90.87 395

test1111		93.19 165	92.82 159	94.30 224	97.58 144	84.56 323	98.21 42	89.02 404	93.53 92	94.58 141	98.21 70	72.69 328	99.05 162	93.06 150	98.48 114	99.28 68

ECVR-MVS		93.19 165	92.73 165	94.57 209	97.66 132	85.41 306	98.21 42	88.23 406	93.43 96	94.70 139	98.21 70	72.57 329	99.07 159	93.05 151	98.49 112	99.25 71

HQP_MVS		93.78 146	93.43 142	94.82 192	96.21 226	89.99 182	97.74 97	97.51 162	94.85 37	91.34 220	96.64 175	81.32 226	98.60 209	93.02 152	92.23 249	95.86 261

plane_prior5								97.51 162					98.60 209	93.02 152	92.23 249	95.86 261

MonoMVSNet		91.92 216	91.77 196	92.37 302	92.94 363	83.11 340	97.09 175	95.55 307	92.91 123	90.85 233	94.55 282	81.27 228	96.52 362	93.01 154	87.76 305	97.47 212

test2506		91.60 229	90.78 236	94.04 235	97.66 132	83.81 332	98.27 32	75.53 421	93.43 96	95.23 128	98.21 70	67.21 368	99.07 159	93.01 154	98.49 112	99.25 71

MVS_Test		94.89 109	94.62 105	95.68 149	96.83 179	89.55 197	96.70 209	97.17 204	91.17 175	95.60 121	96.11 210	87.87 113	98.76 191	93.01 154	97.17 160	98.72 125

CLD-MVS		92.98 175	92.53 174	94.32 221	96.12 236	89.20 216	95.28 300	97.47 169	92.66 129	89.90 257	95.62 235	80.58 238	98.40 224	92.73 157	92.40 247	95.38 291
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XVG-OURS		93.72 148	93.35 145	94.80 197	97.07 160	88.61 229	94.79 317	97.46 171	91.97 149	93.99 156	97.86 98	81.74 221	98.88 177	92.64 158	92.67 245	96.92 232

旧先验2							95.94 266		81.66 376	97.34 52			98.82 182	92.26 159

CDPH-MVS		95.97 76	95.38 87	97.77 33	98.93 50	94.44 35	96.35 241	97.88 112	86.98 308	96.65 77	97.89 93	91.99 48	99.47 105	92.26 159	99.46 41	99.39 59

FIs		94.09 133	93.70 128	95.27 169	95.70 251	92.03 109	98.10 51	98.68 13	93.36 100	90.39 240	96.70 170	87.63 118	97.94 286	92.25 161	90.50 281	95.84 264

LPG-MVS_test		92.94 178	92.56 171	94.10 231	96.16 231	88.26 241	97.65 111	97.46 171	91.29 167	90.12 250	97.16 147	79.05 267	98.73 195	92.25 161	91.89 257	95.31 296

LGP-MVS_train				94.10 231	96.16 231	88.26 241		97.46 171	91.29 167	90.12 250	97.16 147	79.05 267	98.73 195	92.25 161	91.89 257	95.31 296

cascas		91.20 255	90.08 268	94.58 208	94.97 295	89.16 219	93.65 359	97.59 152	79.90 387	89.40 273	92.92 347	75.36 310	98.36 230	92.14 164	94.75 208	96.23 247

OPM-MVS		93.28 161	92.76 161	94.82 192	94.63 315	90.77 161	96.65 215	97.18 202	93.72 82	91.68 213	97.26 142	79.33 262	98.63 206	92.13 165	92.28 248	95.07 310
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BP-MVS														92.13 165

HQP-MVS		93.19 165	92.74 164	94.54 210	95.86 243	89.33 209	96.65 215	97.39 187	93.55 88	90.14 244	95.87 217	80.95 230	98.50 217	92.13 165	92.10 254	95.78 269

DP-MVS Recon		95.68 84	95.12 96	97.37 54	99.19 31	94.19 42	97.03 177	98.08 77	88.35 272	95.09 132	97.65 116	89.97 85	99.48 104	92.08 168	98.59 109	98.44 152

VPNet		92.23 207	91.31 214	94.99 182	95.56 257	90.96 153	97.22 165	97.86 118	92.96 121	90.96 231	96.62 182	75.06 312	98.20 242	91.90 169	83.65 358	95.80 267

sss		94.51 118	93.80 126	96.64 80	97.07 160	91.97 111	96.32 244	98.06 85	88.94 250	94.50 144	96.78 165	84.60 161	99.27 126	91.90 169	96.02 179	98.68 129

anonymousdsp		92.16 209	91.55 205	93.97 240	92.58 371	89.55 197	97.51 130	97.42 184	89.42 234	88.40 299	94.84 268	80.66 237	97.88 294	91.87 171	91.28 267	94.48 342

test_fmvs3		83.21 359	83.02 356	83.78 382	86.77 406	68.34 408	96.76 203	94.91 337	86.49 316	84.14 362	89.48 387	36.04 414	91.73 404	91.86 172	80.77 373	91.26 394

ACMP	89.59 10	92.62 190	92.14 185	94.05 234	96.40 218	88.20 244	97.36 149	97.25 201	91.52 158	88.30 303	96.64 175	78.46 279	98.72 198	91.86 172	91.48 263	95.23 303
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HyFIR lowres test		93.66 149	92.92 155	95.87 136	98.24 90	89.88 188	94.58 322	98.49 19	85.06 341	93.78 161	95.78 226	82.86 196	98.67 202	91.77 174	95.71 188	99.07 89

UGNet		94.04 136	93.28 147	96.31 109	96.85 176	91.19 144	97.88 80	97.68 140	94.40 64	93.00 179	96.18 201	73.39 327	99.61 72	91.72 175	98.46 115	98.13 173
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
UniMVSNet_NR-MVSNet		93.37 158	92.67 167	95.47 164	95.34 272	92.83 81	97.17 169	98.58 17	92.98 120	90.13 248	95.80 222	88.37 105	97.85 295	91.71 176	83.93 353	95.73 275

DU-MVS		92.90 180	92.04 187	95.49 161	94.95 297	92.83 81	97.16 170	98.24 47	93.02 114	90.13 248	95.71 229	83.47 180	97.85 295	91.71 176	83.93 353	95.78 269

Effi-MVS+-dtu		93.08 170	93.21 149	92.68 298	96.02 240	83.25 339	97.14 172	96.72 245	93.85 79	91.20 230	93.44 339	83.08 189	98.30 235	91.69 178	95.73 187	96.50 242

UniMVSNet (Re)		93.31 160	92.55 172	95.61 153	95.39 266	93.34 66	97.39 146	98.71 11	93.14 111	90.10 252	94.83 269	87.71 114	98.03 269	91.67 179	83.99 352	95.46 284

LCM-MVSNet-Re		92.50 191	92.52 175	92.44 300	96.82 181	81.89 355	96.92 189	93.71 371	92.41 134	84.30 358	94.60 280	85.08 156	97.03 350	91.51 180	97.36 150	98.40 155

FC-MVSNet-test		93.94 139	93.57 132	95.04 179	95.48 261	91.45 133	98.12 50	98.71 11	93.37 98	90.23 243	96.70 170	87.66 115	97.85 295	91.49 181	90.39 282	95.83 265

PMMVS		92.86 182	92.34 180	94.42 216	94.92 300	86.73 280	94.53 324	96.38 267	84.78 346	94.27 149	95.12 258	83.13 188	98.40 224	91.47 182	96.49 174	98.12 174

Vis-MVSNet		95.23 97	94.81 100	96.51 92	97.18 154	91.58 126	98.26 34	98.12 70	94.38 66	94.90 134	98.15 75	82.28 210	98.92 173	91.45 183	98.58 110	99.01 93
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		94.15 128	93.51 138	96.06 126	98.27 86	89.38 206	95.18 308	98.48 21	85.60 331	93.76 162	97.11 150	83.15 187	99.61 72	91.33 184	98.72 103	99.19 74

OMC-MVS		95.09 101	94.70 104	96.25 118	98.46 73	91.28 137	96.43 231	97.57 154	92.04 146	94.77 138	97.96 90	87.01 132	99.09 152	91.31 185	96.77 166	98.36 159

MG-MVS		95.61 87	95.38 87	96.31 109	98.42 76	90.53 168	96.04 260	97.48 166	93.47 95	95.67 119	98.10 76	89.17 91	99.25 127	91.27 186	98.77 101	99.13 80

ACMM	89.79 8	92.96 176	92.50 176	94.35 218	96.30 224	88.71 227	97.58 121	97.36 192	91.40 165	90.53 237	96.65 174	79.77 254	98.75 192	91.24 187	91.64 259	95.59 279
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WTY-MVS		94.71 115	94.02 122	96.79 77	97.71 129	92.05 108	96.59 224	97.35 193	90.61 198	94.64 140	96.93 157	86.41 139	99.39 114	91.20 188	94.71 211	98.94 101

testing11		91.68 226	90.75 239	94.47 212	96.53 206	86.56 286	95.76 277	94.51 351	91.10 179	91.24 228	93.59 333	68.59 359	98.86 178	91.10 189	94.29 215	98.00 183

tt0805		91.09 259	90.07 271	94.16 229	95.61 254	88.31 238	97.56 124	96.51 261	89.56 227	89.17 282	95.64 234	67.08 372	98.38 229	91.07 190	88.44 300	95.80 267

Anonymous20240529		91.98 215	90.73 241	95.73 146	98.14 102	89.40 205	97.99 62	97.72 135	79.63 388	93.54 166	97.41 134	69.94 350	99.56 88	91.04 191	91.11 270	98.22 165

AUN-MVS		91.76 222	90.75 239	94.81 194	97.00 170	88.57 231	96.65 215	96.49 262	89.63 225	92.15 198	96.12 206	78.66 276	98.50 217	90.83 192	79.18 379	97.36 216

mvsany_test3		83.59 357	82.44 361	87.03 376	83.80 409	73.82 398	93.70 355	90.92 398	86.42 317	82.51 374	90.26 380	46.76 409	95.71 374	90.82 193	76.76 386	91.57 389

CANet_DTU		94.37 121	93.65 130	96.55 87	96.46 215	92.13 106	96.21 253	96.67 252	94.38 66	93.53 167	97.03 155	79.34 261	99.71 49	90.76 194	98.45 116	97.82 194

ab-mvs		93.57 152	92.55 172	96.64 80	97.28 150	91.96 113	95.40 294	97.45 176	89.81 222	93.22 177	96.28 197	79.62 258	99.46 106	90.74 195	93.11 237	98.50 142

CostFormer		91.18 258	90.70 243	92.62 299	94.84 305	81.76 356	94.09 343	94.43 352	84.15 352	92.72 186	93.77 324	79.43 260	98.20 242	90.70 196	92.18 252	97.90 187

Anonymous202405211		92.07 212	90.83 235	95.76 141	98.19 98	88.75 226	97.58 121	95.00 332	86.00 326	93.64 163	97.45 130	66.24 377	99.53 94	90.68 197	92.71 243	99.01 93

testing99		91.62 228	90.72 242	94.32 221	96.48 212	86.11 298	95.81 273	94.76 343	91.55 157	91.75 211	93.44 339	68.55 360	98.82 182	90.43 198	93.69 230	98.04 181

tpmrst		91.44 240	91.32 213	91.79 322	95.15 288	79.20 385	93.42 364	95.37 314	88.55 266	93.49 168	93.67 330	82.49 206	98.27 237	90.41 199	89.34 291	97.90 187

thisisatest0530		93.03 173	92.21 184	95.49 161	97.07 160	89.11 220	97.49 136	92.19 387	90.16 211	94.09 154	96.41 191	76.43 302	99.05 162	90.38 200	95.68 189	98.31 161

UA-Net		95.95 77	95.53 78	97.20 66	97.67 130	92.98 79	97.65 111	98.13 68	94.81 42	96.61 79	98.35 54	88.87 95	99.51 99	90.36 201	97.35 151	99.11 84

UniMVSNet_ETH3D		91.34 248	90.22 264	94.68 202	94.86 304	87.86 255	97.23 164	97.46 171	87.99 280	89.90 257	96.92 160	66.35 375	98.23 239	90.30 202	90.99 273	97.96 184

tttt0517		92.96 176	92.33 181	94.87 191	97.11 158	87.16 271	97.97 69	92.09 388	90.63 196	93.88 160	97.01 156	76.50 299	99.06 161	90.29 203	95.45 193	98.38 157

testing91		91.90 218	91.02 226	94.53 211	96.54 204	86.55 287	95.86 270	95.64 303	91.77 152	91.89 206	93.47 338	69.94 350	98.86 178	90.23 204	93.86 229	98.18 168

FA-MVS(test-final)		93.52 154	92.92 155	95.31 168	96.77 187	88.54 233	94.82 316	96.21 278	89.61 226	94.20 151	95.25 252	83.24 184	99.14 145	90.01 205	96.16 178	98.25 163

IS-MVSNet		94.90 108	94.52 112	96.05 127	97.67 130	90.56 167	98.44 21	96.22 276	93.21 103	93.99 156	97.74 109	85.55 151	98.45 221	89.98 206	97.86 135	99.14 79

miper_enhance_ethall		91.54 236	91.01 227	93.15 279	95.35 271	87.07 273	93.97 345	96.90 233	86.79 312	89.17 282	93.43 342	86.55 136	97.64 315	89.97 207	86.93 314	94.74 336

EI-MVSNet		93.03 173	92.88 157	93.48 267	95.77 249	86.98 274	96.44 229	97.12 207	90.66 194	91.30 223	97.64 119	86.56 135	98.05 265	89.91 208	90.55 279	95.41 286

IterMVS-LS		92.29 203	91.94 192	93.34 272	96.25 225	86.97 275	96.57 227	97.05 217	90.67 192	89.50 272	94.80 271	86.59 134	97.64 315	89.91 208	86.11 322	95.40 289
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		91.21 254	90.56 249	93.14 280	96.09 238	86.80 277	94.41 330	96.58 259	87.80 288	88.58 296	93.99 317	80.85 235	97.62 318	89.87 210	86.93 314	94.99 313

CDS-MVSNet		94.14 131	93.54 134	95.93 134	96.18 229	91.46 132	96.33 243	97.04 219	88.97 249	93.56 164	96.51 186	87.55 119	97.89 293	89.80 211	95.95 181	98.44 152
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WR-MVS		92.34 199	91.53 206	94.77 199	95.13 290	90.83 158	96.40 237	97.98 103	91.88 150	89.29 278	95.54 240	82.50 205	97.80 301	89.79 212	85.27 332	95.69 276

NR-MVSNet		92.34 199	91.27 217	95.53 158	94.95 297	93.05 76	97.39 146	98.07 82	92.65 130	84.46 356	95.71 229	85.00 157	97.77 305	89.71 213	83.52 359	95.78 269

Anonymous20231211		90.63 279	89.42 294	94.27 226	98.24 90	89.19 218	98.05 57	97.89 110	79.95 386	88.25 306	94.96 261	72.56 330	98.13 248	89.70 214	85.14 334	95.49 280

testdata				95.46 165	98.18 100	88.90 224		97.66 141	82.73 368	97.03 63	98.07 79	90.06 82	98.85 180	89.67 215	98.98 93	98.64 131

Baseline_NR-MVSNet		91.20 255	90.62 245	92.95 286	93.83 340	88.03 249	97.01 182	95.12 328	88.42 270	89.70 263	95.13 257	83.47 180	97.44 334	89.66 216	83.24 361	93.37 364

DPM-MVS		95.69 83	94.92 98	98.01 20	98.08 107	95.71 9	95.27 302	97.62 148	90.43 205	95.55 122	97.07 152	91.72 50	99.50 102	89.62 217	98.94 95	98.82 120

XXY-MVS		92.16 209	91.23 219	94.95 188	94.75 309	90.94 154	97.47 137	97.43 183	89.14 241	88.90 286	96.43 190	79.71 255	98.24 238	89.56 218	87.68 306	95.67 277

miper_ehance_all_eth		91.59 230	91.13 223	92.97 285	95.55 258	86.57 285	94.47 326	96.88 236	87.77 290	88.88 288	94.01 315	86.22 141	97.54 324	89.49 219	86.93 314	94.79 332

WBMVS		90.69 278	89.99 274	92.81 292	96.48 212	85.00 316	95.21 307	96.30 271	89.46 232	89.04 285	94.05 314	72.45 331	97.82 299	89.46 220	87.41 311	95.61 278

XVG-ACMP-BASELINE		90.93 268	90.21 265	93.09 281	94.31 328	85.89 299	95.33 297	97.26 199	91.06 180	89.38 274	95.44 244	68.61 358	98.60 209	89.46 220	91.05 271	94.79 332

thisisatest0515		92.29 203	91.30 215	95.25 170	96.60 196	88.90 224	94.36 332	92.32 386	87.92 282	93.43 170	94.57 281	77.28 294	99.00 166	89.42 222	95.86 184	97.86 190

c3_l		91.38 243	90.89 229	92.88 289	95.58 256	86.30 292	94.68 319	96.84 240	88.17 276	88.83 291	94.23 305	85.65 150	97.47 331	89.36 223	84.63 342	94.89 322

AdaColmap		94.34 122	93.68 129	96.31 109	98.59 69	91.68 121	96.59 224	97.81 126	89.87 217	92.15 198	97.06 153	83.62 179	99.54 92	89.34 224	98.07 130	97.70 199

TranMVSNet+NR-MVSNet		92.50 191	91.63 202	95.14 174	94.76 308	92.07 107	97.53 129	98.11 73	92.90 124	89.56 269	96.12 206	83.16 186	97.60 320	89.30 225	83.20 362	95.75 273

D2MVS		91.30 250	90.95 228	92.35 303	94.71 312	85.52 304	96.18 255	98.21 51	88.89 252	86.60 339	93.82 322	79.92 252	97.95 285	89.29 226	90.95 274	93.56 360

1314		92.81 186	92.03 188	95.14 174	95.33 275	89.52 200	96.04 260	97.44 180	87.72 293	86.25 342	95.33 246	83.84 174	98.79 186	89.26 227	97.05 162	97.11 226

v2v482		91.59 230	90.85 233	93.80 251	93.87 339	88.17 246	96.94 188	96.88 236	89.54 228	89.53 270	94.90 265	81.70 222	98.02 270	89.25 228	85.04 338	95.20 304

114514_t		93.95 138	93.06 151	96.63 82	99.07 37	91.61 123	97.46 139	97.96 105	77.99 394	93.00 179	97.57 124	86.14 145	99.33 118	89.22 229	99.15 81	98.94 101

PAPM_NR		95.01 102	94.59 106	96.26 115	98.89 54	90.68 165	97.24 160	97.73 133	91.80 151	92.93 184	96.62 182	89.13 92	99.14 145	89.21 230	97.78 138	98.97 97

baseline1		92.82 185	91.90 193	95.55 157	97.20 153	90.77 161	97.19 167	94.58 348	92.20 139	92.36 191	96.34 195	84.16 170	98.21 241	89.20 231	83.90 356	97.68 200

IB-MVS	87.33 17	89.91 297	88.28 313	94.79 198	95.26 282	87.70 259	95.12 310	93.95 366	89.35 236	87.03 331	92.49 354	70.74 342	99.19 133	89.18 232	81.37 370	97.49 210
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
HY-MVS	89.66 9	93.87 142	92.95 154	96.63 82	97.10 159	92.49 92	95.64 285	96.64 253	89.05 245	93.00 179	95.79 225	85.77 149	99.45 108	89.16 233	94.35 213	97.96 184

V42		91.58 232	90.87 230	93.73 254	94.05 334	88.50 235	97.32 154	96.97 224	88.80 259	89.71 262	94.33 297	82.54 204	98.05 265	89.01 234	85.07 336	94.64 340

sd_testset		93.10 169	92.45 178	95.05 178	98.09 104	89.21 215	96.89 191	97.64 145	93.18 108	91.79 209	97.28 139	75.35 311	98.65 204	88.99 235	92.84 240	97.28 221

OurMVSNet-221017-0		90.51 283	90.19 266	91.44 331	93.41 354	81.25 359	96.98 185	96.28 272	91.68 155	86.55 340	96.30 196	74.20 320	97.98 274	88.96 236	87.40 312	95.09 309

API-MVS		94.84 111	94.49 113	95.90 135	97.90 120	92.00 110	97.80 92	97.48 166	89.19 240	94.81 136	96.71 168	88.84 96	99.17 138	88.91 237	98.76 102	96.53 240

test-LLR		91.42 241	91.19 221	92.12 310	94.59 316	80.66 365	94.29 337	92.98 378	91.11 177	90.76 235	92.37 357	79.02 269	98.07 262	88.81 238	96.74 167	97.63 201

test-mter		90.19 293	89.54 291	92.12 310	94.59 316	80.66 365	94.29 337	92.98 378	87.68 294	90.76 235	92.37 357	67.67 364	98.07 262	88.81 238	96.74 167	97.63 201

eth_miper_zixun_eth		91.02 263	90.59 247	92.34 305	95.33 275	84.35 325	94.10 342	96.90 233	88.56 265	88.84 290	94.33 297	84.08 171	97.60 320	88.77 240	84.37 349	95.06 311

TAMVS		94.01 137	93.46 140	95.64 150	96.16 231	90.45 171	96.71 208	96.89 235	89.27 238	93.46 169	96.92 160	87.29 128	97.94 286	88.70 241	95.74 186	98.53 138

Patchmatch-RL test		87.38 329	86.24 332	90.81 344	88.74 399	78.40 389	88.12 407	93.17 376	87.11 307	82.17 376	89.29 388	81.95 217	95.60 378	88.64 242	77.02 384	98.41 154

baseline2		91.63 227	90.86 231	93.94 244	94.33 326	86.32 291	95.92 267	91.64 392	89.37 235	86.94 335	94.69 275	81.62 223	98.69 200	88.64 242	94.57 212	96.81 235

TESTMET0.1,1		90.06 295	89.42 294	91.97 313	94.41 324	80.62 367	94.29 337	91.97 390	87.28 304	90.44 239	92.47 356	68.79 356	97.67 312	88.50 244	96.60 172	97.61 205

Vis-MVSNet (Re-imp)		94.15 128	93.88 125	94.95 188	97.61 138	87.92 252	98.10 51	95.80 293	92.22 137	93.02 178	97.45 130	84.53 163	97.91 292	88.24 245	97.97 132	99.02 90

1112_ss		93.37 158	92.42 179	96.21 119	97.05 165	90.99 151	96.31 245	96.72 245	86.87 311	89.83 260	96.69 172	86.51 137	99.14 145	88.12 246	93.67 231	98.50 142

UBG		91.55 234	90.76 237	93.94 244	96.52 208	85.06 315	95.22 305	94.54 349	90.47 204	91.98 204	92.71 349	72.02 332	98.74 194	88.10 247	95.26 197	98.01 182

CVMVSNet		91.23 253	91.75 198	89.67 360	95.77 249	74.69 396	96.44 229	94.88 339	85.81 328	92.18 197	97.64 119	79.07 266	95.58 379	88.06 248	95.86 184	98.74 124

MAR-MVS		94.22 124	93.46 140	96.51 92	98.00 113	92.19 105	97.67 108	97.47 169	88.13 279	93.00 179	95.84 219	84.86 159	99.51 99	87.99 249	98.17 127	97.83 193
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
原ACMM1				96.38 105	98.59 69	91.09 150		97.89 110	87.41 300	95.22 129	97.68 112	90.25 80	99.54 92	87.95 250	99.12 85	98.49 144

CP-MVSNet		91.89 219	91.24 218	93.82 250	95.05 293	88.57 231	97.82 89	98.19 58	91.70 154	88.21 307	95.76 227	81.96 216	97.52 328	87.86 251	84.65 341	95.37 292

v148		90.99 264	90.38 253	92.81 292	93.83 340	85.80 300	96.78 202	96.68 250	89.45 233	88.75 293	93.93 319	82.96 195	97.82 299	87.83 252	83.25 360	94.80 330

v1144		91.37 245	90.60 246	93.68 259	93.89 338	88.23 243	96.84 196	97.03 221	88.37 271	89.69 264	94.39 292	82.04 214	97.98 274	87.80 253	85.37 329	94.84 324

DIV-MVS_self_test		90.97 266	90.33 254	92.88 289	95.36 270	86.19 296	94.46 328	96.63 256	87.82 286	88.18 308	94.23 305	82.99 192	97.53 326	87.72 254	85.57 326	94.93 318

gm-plane-assit					93.22 358	78.89 388			84.82 345		93.52 335		98.64 205	87.72 254

GeoE		93.89 141	93.28 147	95.72 147	96.96 172	89.75 191	98.24 38	96.92 232	89.47 231	92.12 200	97.21 145	84.42 164	98.39 228	87.71 256	96.50 173	99.01 93

cl____		90.96 267	90.32 255	92.89 288	95.37 269	86.21 295	94.46 328	96.64 253	87.82 286	88.15 309	94.18 308	82.98 193	97.54 324	87.70 257	85.59 325	94.92 320

pmmvs4		90.93 268	89.85 279	94.17 228	93.34 356	90.79 160	94.60 321	96.02 283	84.62 347	87.45 320	95.15 255	81.88 219	97.45 333	87.70 257	87.87 304	94.27 352

Test_1112_low_res		92.84 184	91.84 195	95.85 139	97.04 166	89.97 185	95.53 289	96.64 253	85.38 334	89.65 266	95.18 254	85.86 147	99.10 149	87.70 257	93.58 236	98.49 144

无先验							95.79 275	97.87 114	83.87 357				99.65 61	87.68 260		98.89 112

Fast-Effi-MVS+		93.46 155	92.75 163	95.59 154	96.77 187	90.03 179	96.81 199	97.13 206	88.19 275	91.30 223	94.27 302	86.21 142	98.63 206	87.66 261	96.46 176	98.12 174

CNLPA		94.28 123	93.53 135	96.52 89	98.38 81	92.55 90	96.59 224	96.88 236	90.13 213	91.91 205	97.24 143	85.21 154	99.09 152	87.64 262	97.83 136	97.92 186

v8		91.29 252	90.53 250	93.57 264	94.15 330	88.12 248	97.34 151	97.06 216	88.99 247	88.32 302	94.26 304	83.08 189	98.01 271	87.62 263	83.92 355	94.57 341

pmmvs5		89.86 302	88.87 306	92.82 291	92.86 364	86.23 294	96.26 248	95.39 312	84.24 351	87.12 327	94.51 285	74.27 319	97.36 340	87.61 264	87.57 307	94.86 323

Fast-Effi-MVS+-dtu		92.29 203	91.99 190	93.21 278	95.27 279	85.52 304	97.03 177	96.63 256	92.09 144	89.11 284	95.14 256	80.33 244	98.08 258	87.54 265	94.74 209	96.03 259

OpenMVS	89.19 12	92.86 182	91.68 201	96.40 102	95.34 272	92.73 85	98.27 32	98.12 70	84.86 344	85.78 345	97.75 108	78.89 274	99.74 44	87.50 266	98.65 105	96.73 237

miper_lstm_enhance		90.50 284	90.06 272	91.83 319	95.33 275	83.74 333	93.86 351	96.70 249	87.56 297	87.79 314	93.81 323	83.45 182	96.92 355	87.39 267	84.62 343	94.82 327

IterMVS-SCA-FT		90.31 286	89.81 281	91.82 320	95.52 259	84.20 328	94.30 336	96.15 280	90.61 198	87.39 323	94.27 302	75.80 306	96.44 363	87.34 268	86.88 318	94.82 327

PLC	91.00 6	94.11 132	93.43 142	96.13 123	98.58 71	91.15 149	96.69 211	97.39 187	87.29 303	91.37 219	96.71 168	88.39 104	99.52 98	87.33 269	97.13 161	97.73 197
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		90.25 289	89.74 286	91.76 325	93.92 336	79.73 379	93.98 344	93.54 372	88.28 273	91.99 203	93.25 343	77.51 293	97.44 334	87.30 270	87.94 303	98.12 174

GA-MVS		91.38 243	90.31 256	94.59 204	94.65 314	87.62 260	94.34 333	96.19 279	90.73 188	90.35 241	93.83 320	71.84 334	97.96 281	87.22 271	93.61 234	98.21 166

BH-untuned		92.94 178	92.62 169	93.92 247	97.22 151	86.16 297	96.40 237	96.25 275	90.06 214	89.79 261	96.17 203	83.19 185	98.35 231	87.19 272	97.27 156	97.24 223

v144192		91.06 261	90.28 258	93.39 270	93.66 346	87.23 268	96.83 197	97.07 214	87.43 299	89.69 264	94.28 301	81.48 224	98.00 272	87.18 273	84.92 340	94.93 318

RPSCF		90.75 273	90.86 231	90.42 351	96.84 177	76.29 394	95.61 286	96.34 268	83.89 355	91.38 218	97.87 96	76.45 300	98.78 187	87.16 274	92.23 249	96.20 249

test_f		80.57 366	79.62 368	83.41 383	83.38 412	67.80 410	93.57 362	93.72 370	80.80 383	77.91 393	87.63 399	33.40 415	92.08 403	87.14 275	79.04 381	90.34 398

PS-CasMVS		91.55 234	90.84 234	93.69 258	94.96 296	88.28 240	97.84 85	98.24 47	91.46 161	88.04 311	95.80 222	79.67 256	97.48 330	87.02 276	84.54 347	95.31 296

pm-mvs1		90.72 275	89.65 289	93.96 241	94.29 329	89.63 192	97.79 93	96.82 241	89.07 243	86.12 344	95.48 243	78.61 277	97.78 303	86.97 277	81.67 368	94.46 343

IterMVS		90.15 294	89.67 287	91.61 327	95.48 261	83.72 334	94.33 334	96.12 281	89.99 215	87.31 326	94.15 310	75.78 308	96.27 366	86.97 277	86.89 317	94.83 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		93.58 151	92.98 153	95.37 167	98.40 78	88.98 222	97.18 168	97.29 198	87.75 292	90.49 238	97.10 151	85.21 154	99.50 102	86.70 279	96.72 169	97.63 201

PVSNet	86.66 18	92.24 206	91.74 200	93.73 254	97.77 126	83.69 336	92.88 374	96.72 245	87.91 283	93.00 179	94.86 267	78.51 278	99.05 162	86.53 280	97.45 148	98.47 147

v1192		91.07 260	90.23 262	93.58 263	93.70 343	87.82 257	96.73 205	97.07 214	87.77 290	89.58 267	94.32 299	80.90 234	97.97 277	86.52 281	85.48 327	94.95 314

新几何1				97.32 56	98.60 68	93.59 58		97.75 130	81.58 377	95.75 115	97.85 99	90.04 83	99.67 59	86.50 282	99.13 83	98.69 128

v10		91.04 262	90.23 262	93.49 266	94.12 331	88.16 247	97.32 154	97.08 212	88.26 274	88.29 304	94.22 307	82.17 213	97.97 277	86.45 283	84.12 351	94.33 348

v1921920		90.85 270	90.03 273	93.29 274	93.55 347	86.96 276	96.74 204	97.04 219	87.36 301	89.52 271	94.34 296	80.23 246	97.97 277	86.27 284	85.21 333	94.94 316

MDTV_nov1_ep13_2view						70.35 404	93.10 371		83.88 356	93.55 165		82.47 207		86.25 285		98.38 157

test_post1							92.81 376				16.58 424	80.53 239	97.68 311	86.20 286

SCA		91.84 220	91.18 222	93.83 249	95.59 255	84.95 319	94.72 318	95.58 306	90.82 184	92.25 196	93.69 327	75.80 306	98.10 253	86.20 286	95.98 180	98.45 149

PAPR		94.18 125	93.42 144	96.48 95	97.64 134	91.42 134	95.55 287	97.71 139	88.99 247	92.34 194	95.82 221	89.19 90	99.11 148	86.14 288	97.38 149	98.90 108

GBi-Net		91.35 246	90.27 259	94.59 204	96.51 209	91.18 145	97.50 131	96.93 228	88.82 256	89.35 275	94.51 285	73.87 321	97.29 343	86.12 289	88.82 294	95.31 296

test1		91.35 246	90.27 259	94.59 204	96.51 209	91.18 145	97.50 131	96.93 228	88.82 256	89.35 275	94.51 285	73.87 321	97.29 343	86.12 289	88.82 294	95.31 296

FMVSNet3		91.78 221	90.69 244	95.03 180	96.53 206	92.27 100	97.02 179	96.93 228	89.79 223	89.35 275	94.65 278	77.01 295	97.47 331	86.12 289	88.82 294	95.35 293

EPMVS		90.70 276	89.81 281	93.37 271	94.73 311	84.21 327	93.67 358	88.02 407	89.50 230	92.38 190	93.49 336	77.82 291	97.78 303	86.03 292	92.68 244	98.11 177

MVS		91.71 223	90.44 251	95.51 159	95.20 285	91.59 125	96.04 260	97.45 176	73.44 404	87.36 324	95.60 236	85.42 152	99.10 149	85.97 293	97.46 144	95.83 265

testdata2													99.67 59	85.96 294

K. test v3		87.64 328	86.75 330	90.32 353	93.02 362	79.48 383	96.61 221	92.08 389	90.66 194	80.25 385	94.09 312	67.21 368	96.65 361	85.96 294	80.83 372	94.83 325

WR-MVS_H		92.00 214	91.35 211	93.95 242	95.09 292	89.47 201	98.04 58	98.68 13	91.46 161	88.34 301	94.68 276	85.86 147	97.56 322	85.77 296	84.24 350	94.82 327

gg-mvs-nofinetune		87.82 325	85.61 337	94.44 214	94.46 321	89.27 214	91.21 389	84.61 415	80.88 380	89.89 259	74.98 411	71.50 336	97.53 326	85.75 297	97.21 158	96.51 241

tpm2		89.96 296	89.21 298	92.23 309	94.91 302	81.25 359	93.78 353	94.42 353	80.62 384	91.56 214	93.44 339	76.44 301	97.94 286	85.60 298	92.08 256	97.49 210

v1240		90.70 276	89.85 279	93.23 276	93.51 350	86.80 277	96.61 221	97.02 222	87.16 306	89.58 267	94.31 300	79.55 259	97.98 274	85.52 299	85.44 328	94.90 321

PEN-MVS		91.20 255	90.44 251	93.48 267	94.49 320	87.91 254	97.76 95	98.18 60	91.29 167	87.78 315	95.74 228	80.35 243	97.33 341	85.46 300	82.96 363	95.19 307

QAPM		93.45 156	92.27 182	96.98 76	96.77 187	92.62 87	98.39 24	98.12 70	84.50 349	88.27 305	97.77 107	82.39 209	99.81 30	85.40 301	98.81 99	98.51 141

EU-MVSNet		88.72 317	88.90 305	88.20 370	93.15 360	74.21 397	96.63 220	94.22 361	85.18 338	87.32 325	95.97 212	76.16 303	94.98 385	85.27 302	86.17 320	95.41 286

BH-w/o		92.14 211	91.75 198	93.31 273	96.99 171	85.73 301	95.67 280	95.69 299	88.73 261	89.26 280	94.82 270	82.97 194	98.07 262	85.26 303	96.32 177	96.13 255

FMVSNet2		91.31 249	90.08 268	94.99 182	96.51 209	92.21 102	97.41 141	96.95 226	88.82 256	88.62 294	94.75 273	73.87 321	97.42 336	85.20 304	88.55 299	95.35 293

PM-MVS		83.48 358	81.86 364	88.31 369	87.83 403	77.59 391	93.43 363	91.75 391	86.91 309	80.63 381	89.91 384	44.42 410	95.84 372	85.17 305	76.73 387	91.50 391

LF4IMVS		87.94 324	87.25 321	89.98 357	92.38 376	80.05 377	94.38 331	95.25 322	87.59 296	84.34 357	94.74 274	64.31 384	97.66 314	84.83 306	87.45 308	92.23 382

PatchmatchNet		91.91 217	91.35 211	93.59 262	95.38 267	84.11 329	93.15 369	95.39 312	89.54 228	92.10 201	93.68 329	82.82 198	98.13 248	84.81 307	95.32 195	98.52 139
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs6		87.81 326	86.19 333	92.69 297	91.32 381	86.30 292	97.34 151	96.41 266	80.59 385	84.05 365	94.37 294	67.37 367	97.67 312	84.75 308	79.51 378	94.09 355

v7n		90.76 272	89.86 278	93.45 269	93.54 348	87.60 261	97.70 107	97.37 190	88.85 253	87.65 317	94.08 313	81.08 229	98.10 253	84.68 309	83.79 357	94.66 339

SixPastTwentyTwo		89.15 310	88.54 310	90.98 339	93.49 351	80.28 373	96.70 209	94.70 344	90.78 185	84.15 361	95.57 237	71.78 335	97.71 310	84.63 310	85.07 336	94.94 316

TDRefinement		86.53 336	84.76 348	91.85 318	82.23 414	84.25 326	96.38 239	95.35 315	84.97 343	84.09 363	94.94 262	65.76 381	98.34 234	84.60 311	74.52 392	92.97 367

ACMH	87.59 16	90.53 281	89.42 294	93.87 248	96.21 226	87.92 252	97.24 160	96.94 227	88.45 269	83.91 366	96.27 198	71.92 333	98.62 208	84.43 312	89.43 290	95.05 312
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	87.92 14	90.20 292	89.18 299	93.25 275	96.48 212	86.45 289	96.99 184	96.68 250	88.83 255	84.79 355	96.22 200	70.16 347	98.53 215	84.42 313	88.04 302	94.77 335

test_vis3_rt		72.73 372	70.55 375	79.27 386	80.02 415	68.13 409	93.92 349	74.30 423	76.90 397	58.99 414	73.58 414	20.29 423	95.37 382	84.16 314	72.80 397	74.31 411

FE-MVS		92.05 213	91.05 225	95.08 177	96.83 179	87.93 251	93.91 350	95.70 297	86.30 320	94.15 153	94.97 260	76.59 298	99.21 131	84.10 315	96.86 163	98.09 178

MS-PatchMatch		90.27 288	89.77 283	91.78 323	94.33 326	84.72 322	95.55 287	96.73 244	86.17 324	86.36 341	95.28 249	71.28 338	97.80 301	84.09 316	98.14 128	92.81 370

PatchMatch-RL		92.90 180	92.02 189	95.56 155	98.19 98	90.80 159	95.27 302	97.18 202	87.96 281	91.86 208	95.68 232	80.44 241	98.99 167	84.01 317	97.54 143	96.89 233

lessismore_v0				90.45 350	91.96 379	79.09 387		87.19 410		80.32 384	94.39 292	66.31 376	97.55 323	84.00 318	76.84 385	94.70 337

UWE-MVS		89.91 297	89.48 293	91.21 335	95.88 242	78.23 390	94.91 315	90.26 400	89.11 242	92.35 193	94.52 284	68.76 357	97.96 281	83.95 319	95.59 191	97.42 214

CMPMVS	62.92 21	85.62 350	84.92 346	87.74 372	89.14 394	73.12 402	94.17 340	96.80 242	73.98 401	73.65 400	94.93 263	66.36 374	97.61 319	83.95 319	91.28 267	92.48 378
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVP-Stereo		90.74 274	90.08 268	92.71 296	93.19 359	88.20 244	95.86 270	96.27 273	86.07 325	84.86 354	94.76 272	77.84 290	97.75 307	83.88 321	98.01 131	92.17 385
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LS3D		93.57 152	92.61 170	96.47 96	97.59 140	91.61 123	97.67 108	97.72 135	85.17 339	90.29 242	98.34 57	84.60 161	99.73 45	83.85 322	98.27 122	98.06 180

DTE-MVSNet		90.56 280	89.75 285	93.01 283	93.95 335	87.25 266	97.64 115	97.65 143	90.74 187	87.12 327	95.68 232	79.97 251	97.00 353	83.33 323	81.66 369	94.78 334

BH-RMVSNet		92.72 189	91.97 191	94.97 186	97.16 155	87.99 250	96.15 256	95.60 304	90.62 197	91.87 207	97.15 149	78.41 280	98.57 213	83.16 324	97.60 142	98.36 159

pmmvs-eth3d		86.22 342	84.45 350	91.53 328	88.34 401	87.25 266	94.47 326	95.01 331	83.47 363	79.51 388	89.61 386	69.75 352	95.71 374	83.13 325	76.73 387	91.64 387

FMVSNet1		89.88 300	88.31 312	94.59 204	95.41 265	91.18 145	97.50 131	96.93 228	86.62 314	87.41 322	94.51 285	65.94 380	97.29 343	83.04 326	87.43 309	95.31 296

testing222		90.31 286	88.96 303	94.35 218	96.54 204	87.29 263	95.50 290	93.84 369	90.97 182	91.75 211	92.96 346	62.18 392	98.00 272	82.86 327	94.08 222	97.76 196

MDTV_nov1_ep13			90.76 237		95.22 283	80.33 371	93.03 372	95.28 319	88.14 278	92.84 185	93.83 320	81.34 225	98.08 258	82.86 327	94.34 214

TR-MVS		91.48 239	90.59 247	94.16 229	96.40 218	87.33 262	95.67 280	95.34 318	87.68 294	91.46 217	95.52 241	76.77 297	98.35 231	82.85 329	93.61 234	96.79 236

dmvs_re		90.21 291	89.50 292	92.35 303	95.47 264	85.15 312	95.70 279	94.37 356	90.94 183	88.42 298	93.57 334	74.63 316	95.67 376	82.80 330	89.57 289	96.22 248

JIA-IIPM		88.26 322	87.04 326	91.91 315	93.52 349	81.42 358	89.38 401	94.38 355	80.84 381	90.93 232	80.74 408	79.22 263	97.92 289	82.76 331	91.62 260	96.38 246

PVSNet_0	82.17 19	85.46 351	83.64 354	90.92 340	95.27 279	79.49 382	90.55 393	95.60 304	83.76 359	83.00 373	89.95 383	71.09 339	97.97 277	82.75 332	60.79 413	95.31 296

ambc				86.56 378	83.60 411	70.00 405	85.69 409	94.97 334		80.60 382	88.45 392	37.42 413	96.84 358	82.69 333	75.44 391	92.86 369

USDC		88.94 312	87.83 317	92.27 307	94.66 313	84.96 318	93.86 351	95.90 287	87.34 302	83.40 368	95.56 238	67.43 366	98.19 244	82.64 334	89.67 288	93.66 359

ITE_SJBPF				92.43 301	95.34 272	85.37 309		95.92 285	91.47 160	87.75 316	96.39 193	71.00 340	97.96 281	82.36 335	89.86 286	93.97 356

UnsupCasMVSNet_eth		85.99 345	84.45 350	90.62 348	89.97 389	82.40 351	93.62 360	97.37 190	89.86 218	78.59 391	92.37 357	65.25 383	95.35 383	82.27 336	70.75 399	94.10 353

GG-mvs-BLEND				93.62 260	93.69 344	89.20 216	92.39 381	83.33 417		87.98 313	89.84 385	71.00 340	96.87 357	82.08 337	95.40 194	94.80 330

thres600view7		92.49 193	91.60 203	95.18 172	97.91 119	89.47 201	97.65 111	94.66 345	92.18 143	93.33 172	94.91 264	78.06 287	99.10 149	81.61 338	94.06 226	96.98 228

LTVRE_ROB	88.41 13	90.99 264	89.92 277	94.19 227	96.18 229	89.55 197	96.31 245	97.09 211	87.88 284	85.67 346	95.91 216	78.79 275	98.57 213	81.50 339	89.98 284	94.44 345
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
tpmvs		89.83 303	89.15 300	91.89 317	94.92 300	80.30 372	93.11 370	95.46 311	86.28 321	88.08 310	92.65 350	80.44 241	98.52 216	81.47 340	89.92 285	96.84 234

thres100view900		92.43 194	91.58 204	94.98 184	97.92 118	89.37 207	97.71 104	94.66 345	92.20 139	93.31 173	94.90 265	78.06 287	99.08 155	81.40 341	94.08 222	96.48 243

tfpn200view9		92.38 197	91.52 207	94.95 188	97.85 122	89.29 211	97.41 141	94.88 339	92.19 141	93.27 175	94.46 290	78.17 283	99.08 155	81.40 341	94.08 222	96.48 243

thres400		92.42 195	91.52 207	95.12 176	97.85 122	89.29 211	97.41 141	94.88 339	92.19 141	93.27 175	94.46 290	78.17 283	99.08 155	81.40 341	94.08 222	96.98 228

mvs5depth		86.53 336	85.08 343	90.87 341	88.74 399	82.52 347	91.91 383	94.23 360	86.35 319	87.11 329	93.70 326	66.52 373	97.76 306	81.37 344	75.80 389	92.31 381

ETVMVS		90.52 282	89.14 301	94.67 203	96.81 183	87.85 256	95.91 268	93.97 365	89.71 224	92.34 194	92.48 355	65.41 382	97.96 281	81.37 344	94.27 216	98.21 166

DP-MVS		92.76 187	91.51 209	96.52 89	98.77 56	90.99 151	97.38 148	96.08 282	82.38 370	89.29 278	97.87 96	83.77 175	99.69 55	81.37 344	96.69 170	98.89 112

thres200		92.23 207	91.39 210	94.75 201	97.61 138	89.03 221	96.60 223	95.09 329	92.08 145	93.28 174	94.00 316	78.39 281	99.04 165	81.26 347	94.18 218	96.19 250

CR-MVSNet		90.82 271	89.77 283	93.95 242	94.45 322	87.19 269	90.23 395	95.68 301	86.89 310	92.40 188	92.36 360	80.91 232	97.05 349	81.09 348	93.95 227	97.60 206

ttmdpeth		85.91 347	84.76 348	89.36 364	89.14 394	80.25 374	95.66 283	93.16 377	83.77 358	83.39 369	95.26 251	66.24 377	95.26 384	80.65 349	75.57 390	92.57 374

MSDG		91.42 241	90.24 261	94.96 187	97.15 157	88.91 223	93.69 357	96.32 269	85.72 330	86.93 336	96.47 188	80.24 245	98.98 168	80.57 350	95.05 202	96.98 228

dp		88.90 314	88.26 314	90.81 344	94.58 318	76.62 392	92.85 375	94.93 336	85.12 340	90.07 255	93.07 344	75.81 305	98.12 251	80.53 351	87.42 310	97.71 198

tpm cat1		88.36 320	87.21 323	91.81 321	95.13 290	80.55 368	92.58 378	95.70 297	74.97 400	87.45 320	91.96 367	78.01 289	98.17 246	80.39 352	88.74 297	96.72 238

KD-MVS_self_test		85.95 346	84.95 345	88.96 367	89.55 393	79.11 386	95.13 309	96.42 265	85.91 327	84.07 364	90.48 378	70.03 349	94.82 386	80.04 353	72.94 396	92.94 368

AllTest		90.23 290	88.98 302	93.98 238	97.94 116	86.64 281	96.51 228	95.54 308	85.38 334	85.49 348	96.77 166	70.28 345	99.15 142	80.02 354	92.87 238	96.15 253

TestCases				93.98 238	97.94 116	86.64 281		95.54 308	85.38 334	85.49 348	96.77 166	70.28 345	99.15 142	80.02 354	92.87 238	96.15 253

ADS-MVSNet2		89.45 307	88.59 309	92.03 312	95.86 243	82.26 352	90.93 390	94.32 359	83.23 365	91.28 226	91.81 369	79.01 271	95.99 368	79.52 356	91.39 265	97.84 191

ADS-MVSNet		89.89 299	88.68 308	93.53 265	95.86 243	84.89 320	90.93 390	95.07 330	83.23 365	91.28 226	91.81 369	79.01 271	97.85 295	79.52 356	91.39 265	97.84 191

our_test_3		88.78 316	87.98 316	91.20 337	92.45 374	82.53 346	93.61 361	95.69 299	85.77 329	84.88 353	93.71 325	79.99 250	96.78 360	79.47 358	86.24 319	94.28 351

EPNet_dtu		91.71 223	91.28 216	92.99 284	93.76 342	83.71 335	96.69 211	95.28 319	93.15 110	87.02 332	95.95 214	83.37 183	97.38 339	79.46 359	96.84 164	97.88 189
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		88.94 312	87.56 318	93.08 282	94.35 325	88.45 237	97.73 99	95.23 323	87.47 298	84.26 359	95.29 247	79.86 253	97.33 341	79.44 360	74.44 393	93.45 363

EG-PatchMatch MVS		87.02 334	85.44 338	91.76 325	92.67 368	85.00 316	96.08 259	96.45 264	83.41 364	79.52 387	93.49 336	57.10 398	97.72 309	79.34 361	90.87 276	92.56 375

Patchmtry		88.64 318	87.25 321	92.78 294	94.09 332	86.64 281	89.82 399	95.68 301	80.81 382	87.63 318	92.36 360	80.91 232	97.03 350	78.86 362	85.12 335	94.67 338

FMVSNet5		87.29 330	85.79 336	91.78 323	94.80 307	87.28 264	95.49 291	95.28 319	84.09 353	83.85 367	91.82 368	62.95 388	94.17 391	78.48 363	85.34 331	93.91 357

COLMAP_ROB	87.81 15	90.40 285	89.28 297	93.79 252	97.95 115	87.13 272	96.92 189	95.89 289	82.83 367	86.88 338	97.18 146	73.77 324	99.29 125	78.44 364	93.62 233	94.95 314
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240521		86.42 339	85.44 338	89.34 365	90.33 386	79.79 378	96.73 205	95.92 285	83.71 360	83.25 370	91.36 373	63.92 385	96.01 367	78.39 365	85.36 330	92.22 383

test0.0.03 1		89.37 309	88.70 307	91.41 332	92.47 373	85.63 302	95.22 305	92.70 383	91.11 177	86.91 337	93.65 331	79.02 269	93.19 401	78.00 366	89.18 292	95.41 286

MIMVSNet		88.50 319	86.76 329	93.72 256	94.84 305	87.77 258	91.39 385	94.05 362	86.41 318	87.99 312	92.59 353	63.27 386	95.82 373	77.44 367	92.84 240	97.57 208

MDA-MVSNet_test_wron		85.87 348	84.23 352	90.80 346	92.38 376	82.57 345	93.17 367	95.15 326	82.15 371	67.65 406	92.33 363	78.20 282	95.51 380	77.33 368	79.74 375	94.31 350

YYNet1		85.87 348	84.23 352	90.78 347	92.38 376	82.46 350	93.17 367	95.14 327	82.12 372	67.69 404	92.36 360	78.16 285	95.50 381	77.31 369	79.73 376	94.39 346

UnsupCasMVSNet_bld		82.13 364	79.46 369	90.14 355	88.00 402	82.47 349	90.89 392	96.62 258	78.94 391	75.61 395	84.40 406	56.63 399	96.31 365	77.30 370	66.77 407	91.63 388

KD-MVS_2432*1600		84.81 354	82.64 358	91.31 333	91.07 383	85.34 310	91.22 387	95.75 295	85.56 332	83.09 371	90.21 381	67.21 368	95.89 369	77.18 371	62.48 411	92.69 371

miper_refine_blended		84.81 354	82.64 358	91.31 333	91.07 383	85.34 310	91.22 387	95.75 295	85.56 332	83.09 371	90.21 381	67.21 368	95.89 369	77.18 371	62.48 411	92.69 371

PCF-MVS	89.48 11	91.56 233	89.95 275	96.36 107	96.60 196	92.52 91	92.51 379	97.26 199	79.41 389	88.90 286	96.56 184	84.04 173	99.55 90	77.01 373	97.30 155	97.01 227
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		89.88 300	89.56 290	90.82 343	94.57 319	83.06 341	95.65 284	92.85 380	87.86 285	90.83 234	94.10 311	79.66 257	96.88 356	76.34 374	94.19 217	92.54 376

testgi		87.97 323	87.21 323	90.24 354	92.86 364	80.76 363	96.67 214	94.97 334	91.74 153	85.52 347	95.83 220	62.66 390	94.47 389	76.25 375	88.36 301	95.48 281

TinyColmap		86.82 335	85.35 341	91.21 335	94.91 302	82.99 342	93.94 347	94.02 364	83.58 361	81.56 377	94.68 276	62.34 391	98.13 248	75.78 376	87.35 313	92.52 377

ppachtmachnet_test		88.35 321	87.29 320	91.53 328	92.45 374	83.57 337	93.75 354	95.97 284	84.28 350	85.32 351	94.18 308	79.00 273	96.93 354	75.71 377	84.99 339	94.10 353

PAPM		91.52 237	90.30 257	95.20 171	95.30 278	89.83 189	93.38 365	96.85 239	86.26 322	88.59 295	95.80 222	84.88 158	98.15 247	75.67 378	95.93 182	97.63 201

WAC-MVS						79.53 380								75.56 379

myMVS_eth3d		87.18 331	86.38 331	89.58 361	95.16 286	79.53 380	95.00 312	93.93 367	88.55 266	86.96 333	91.99 365	56.23 400	94.00 393	75.47 380	94.11 219	95.20 304

CL-MVSNet_self_test		86.31 341	85.15 342	89.80 359	88.83 397	81.74 357	93.93 348	96.22 276	86.67 313	85.03 352	90.80 376	78.09 286	94.50 387	74.92 381	71.86 398	93.15 366

tfpnnormal		89.70 305	88.40 311	93.60 261	95.15 288	90.10 178	97.56 124	98.16 64	87.28 304	86.16 343	94.63 279	77.57 292	98.05 265	74.48 382	84.59 345	92.65 373

DSMNet-mixed		86.34 340	86.12 335	87.00 377	89.88 390	70.43 403	94.93 314	90.08 401	77.97 395	85.42 350	92.78 348	74.44 318	93.96 395	74.43 383	95.14 198	96.62 239

Patchmatch-test		89.42 308	87.99 315	93.70 257	95.27 279	85.11 313	88.98 402	94.37 356	81.11 378	87.10 330	93.69 327	82.28 210	97.50 329	74.37 384	94.76 207	98.48 146

LCM-MVSNet		72.55 373	69.39 377	82.03 384	70.81 424	65.42 413	90.12 397	94.36 358	55.02 414	65.88 408	81.72 407	24.16 422	89.96 405	74.32 385	68.10 405	90.71 397

new-patchmatchnet		83.18 360	81.87 363	87.11 375	86.88 405	75.99 395	93.70 355	95.18 325	85.02 342	77.30 394	88.40 393	65.99 379	93.88 396	74.19 386	70.18 400	91.47 392

MVStest1		82.38 363	80.04 367	89.37 363	87.63 404	82.83 343	95.03 311	93.37 375	73.90 402	73.50 401	94.35 295	62.89 389	93.25 400	73.80 387	65.92 408	92.04 386

testing3		87.67 327	86.88 328	90.05 356	96.14 234	80.71 364	97.10 174	92.85 380	90.15 212	87.54 319	94.55 282	55.70 401	94.10 392	73.77 388	94.10 221	95.35 293

MDA-MVSNet-bldmvs		85.00 352	82.95 357	91.17 338	93.13 361	83.33 338	94.56 323	95.00 332	84.57 348	65.13 410	92.65 350	70.45 344	95.85 371	73.57 389	77.49 383	94.33 348

pmmvs3		79.97 367	77.50 372	87.39 374	82.80 413	79.38 384	92.70 377	90.75 399	70.69 405	78.66 390	87.47 401	51.34 405	93.40 398	73.39 390	69.65 401	89.38 400

test_method		66.11 381	64.89 383	69.79 398	72.62 422	35.23 430	65.19 417	92.83 382	20.35 420	65.20 409	88.08 397	43.14 411	82.70 415	73.12 391	63.46 410	91.45 393

PatchT		88.87 315	87.42 319	93.22 277	94.08 333	85.10 314	89.51 400	94.64 347	81.92 373	92.36 191	88.15 396	80.05 249	97.01 352	72.43 392	93.65 232	97.54 209

Anonymous20231206		87.09 333	86.14 334	89.93 358	91.22 382	80.35 370	96.11 257	95.35 315	83.57 362	84.16 360	93.02 345	73.54 326	95.61 377	72.16 393	86.14 321	93.84 358

MVS-HIRNet		82.47 362	81.21 365	86.26 379	95.38 267	69.21 406	88.96 403	89.49 402	66.28 408	80.79 380	74.08 413	68.48 361	97.39 338	71.93 394	95.47 192	92.18 384

new_pmnet		82.89 361	81.12 366	88.18 371	89.63 391	80.18 375	91.77 384	92.57 384	76.79 398	75.56 397	88.23 395	61.22 393	94.48 388	71.43 395	82.92 364	89.87 399

TAPA-MVS	90.10 7	92.30 202	91.22 220	95.56 155	98.33 83	89.60 194	96.79 200	97.65 143	81.83 374	91.52 215	97.23 144	87.94 111	98.91 175	71.31 396	98.37 118	98.17 171
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test20.03		86.14 344	85.40 340	88.35 368	90.12 387	80.06 376	95.90 269	95.20 324	88.59 262	81.29 378	93.62 332	71.43 337	92.65 402	71.26 397	81.17 371	92.34 379

tmp_tt		51.94 388	53.82 388	46.29 404	33.73 428	45.30 428	78.32 414	67.24 425	18.02 421	50.93 417	87.05 402	52.99 403	53.11 423	70.76 398	25.29 421	40.46 419

MIMVSNet1		84.93 353	83.05 355	90.56 349	89.56 392	84.84 321	95.40 294	95.35 315	83.91 354	80.38 383	92.21 364	57.23 397	93.34 399	70.69 399	82.75 366	93.50 361

APD_test1		79.31 368	77.70 371	84.14 381	89.11 396	69.07 407	92.36 382	91.50 393	69.07 406	73.87 399	92.63 352	39.93 412	94.32 390	70.54 400	80.25 374	89.02 401

RPMNet		88.98 311	87.05 325	94.77 199	94.45 322	87.19 269	90.23 395	98.03 94	77.87 396	92.40 188	87.55 400	80.17 247	99.51 99	68.84 401	93.95 227	97.60 206

N_pmnet		78.73 369	78.71 370	78.79 387	92.80 366	46.50 426	94.14 341	43.71 428	78.61 392	80.83 379	91.66 371	74.94 314	96.36 364	67.24 402	84.45 348	93.50 361

OpenMVS_ROB	81.14 20	84.42 356	82.28 362	90.83 342	90.06 388	84.05 331	95.73 278	94.04 363	73.89 403	80.17 386	91.53 372	59.15 394	97.64 315	66.92 403	89.05 293	90.80 396

PMMVS2		70.19 375	66.92 379	80.01 385	76.35 418	65.67 412	86.22 408	87.58 409	64.83 410	62.38 411	80.29 410	26.78 420	88.49 412	63.79 404	54.07 415	85.88 402

test_0402		86.46 338	84.79 347	91.45 330	95.02 294	85.55 303	96.29 247	94.89 338	80.90 379	82.21 375	93.97 318	68.21 363	97.29 343	62.98 405	88.68 298	91.51 390

DeepMVS_CX				74.68 396	90.84 385	64.34 414		81.61 419	65.34 409	67.47 407	88.01 398	48.60 408	80.13 418	62.33 406	73.68 395	79.58 408

Syy-MVS		87.13 332	87.02 327	87.47 373	95.16 286	73.21 401	95.00 312	93.93 367	88.55 266	86.96 333	91.99 365	75.90 304	94.00 393	61.59 407	94.11 219	95.20 304

testf1		69.31 377	66.76 380	76.94 391	78.61 416	61.93 415	88.27 405	86.11 413	55.62 412	59.69 412	85.31 404	20.19 424	89.32 406	57.62 408	69.44 403	79.58 408

APD_test2		69.31 377	66.76 380	76.94 391	78.61 416	61.93 415	88.27 405	86.11 413	55.62 412	59.69 412	85.31 404	20.19 424	89.32 406	57.62 408	69.44 403	79.58 408

EGC-MVSNET		68.77 379	63.01 385	86.07 380	92.49 372	82.24 353	93.96 346	90.96 397	0.71 425	2.62 426	90.89 375	53.66 402	93.46 397	57.25 410	84.55 346	82.51 406

dmvs_testset		81.38 365	82.60 360	77.73 388	91.74 380	51.49 423	93.03 372	84.21 416	89.07 243	78.28 392	91.25 374	76.97 296	88.53 411	56.57 411	82.24 367	93.16 365

FPMVS		71.27 374	69.85 376	75.50 394	74.64 419	59.03 419	91.30 386	91.50 393	58.80 411	57.92 415	88.28 394	29.98 418	85.53 414	53.43 412	82.84 365	81.95 407

ANet_high		63.94 383	59.58 386	77.02 390	61.24 426	66.06 411	85.66 410	87.93 408	78.53 393	42.94 418	71.04 415	25.42 421	80.71 417	52.60 413	30.83 419	84.28 405

Gipuma		67.86 380	65.41 382	75.18 395	92.66 369	73.45 399	66.50 416	94.52 350	53.33 415	57.80 416	66.07 416	30.81 416	89.20 408	48.15 414	78.88 382	62.90 416
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
dongtai		69.99 376	69.33 378	71.98 397	88.78 398	61.64 417	89.86 398	59.93 427	75.67 399	74.96 398	85.45 403	50.19 406	81.66 416	43.86 415	55.27 414	72.63 412

PMVS	53.92 22	58.58 384	55.40 387	68.12 399	51.00 427	48.64 424	78.86 413	87.10 411	46.77 416	35.84 422	74.28 412	8.76 426	86.34 413	42.07 416	73.91 394	69.38 413
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	50.73 23	53.25 386	48.81 391	66.58 401	65.34 425	57.50 420	72.49 415	70.94 424	40.15 419	39.28 421	63.51 417	6.89 428	73.48 421	38.29 417	42.38 417	68.76 415
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		76.77 370	76.63 373	77.18 389	85.32 407	56.82 421	94.53 324	89.39 403	82.66 369	71.35 402	89.18 389	75.03 313	88.88 409	35.42 418	66.79 406	85.84 403

SSC-MVS		76.05 371	75.83 374	76.72 393	84.77 408	56.22 422	94.32 335	88.96 405	81.82 375	70.52 403	88.91 390	74.79 315	88.71 410	33.69 419	64.71 409	85.23 404

E-PMN		53.28 385	52.56 389	55.43 402	74.43 420	47.13 425	83.63 412	76.30 420	42.23 417	42.59 419	62.22 418	28.57 419	74.40 419	31.53 420	31.51 418	44.78 417

kuosan		65.27 382	64.66 384	67.11 400	83.80 409	61.32 418	88.53 404	60.77 426	68.22 407	67.67 405	80.52 409	49.12 407	70.76 422	29.67 421	53.64 416	69.26 414

EMVS		52.08 387	51.31 390	54.39 403	72.62 422	45.39 427	83.84 411	75.51 422	41.13 418	40.77 420	59.65 419	30.08 417	73.60 420	28.31 422	29.90 420	44.18 418

wuyk23d		25.11 389	24.57 393	26.74 405	73.98 421	39.89 429	57.88 418	9.80 429	12.27 422	10.39 423	6.97 425	7.03 427	36.44 424	25.43 423	17.39 422	3.89 422

testmvs		13.36 391	16.33 394	4.48 407	5.04 429	2.26 432	93.18 366	3.28 430	2.70 423	8.24 424	21.66 421	2.29 430	2.19 425	7.58 424	2.96 423	9.00 421

test123		13.04 392	15.66 395	5.18 406	4.51 430	3.45 431	92.50 380	1.81 431	2.50 424	7.58 425	20.15 422	3.67 429	2.18 426	7.13 425	1.07 424	9.90 420

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		23.24 390	30.99 392	0.00 408	0.00 431	0.00 433	0.00 419	97.63 147	0.00 426	0.00 427	96.88 162	84.38 165	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		7.39 394	9.85 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	88.65 100	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		8.06 393	10.74 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	96.69 172	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

FOURS1					99.55 1	93.34 66	99.29 1	98.35 27	94.98 32	98.49 23

test_one_0601					99.32 22	95.20 20		98.25 45	95.13 26	98.48 24	98.87 18	95.16 7

eth-test2					0.00 431

eth-test					0.00 431

test_241102_ONE					99.42 7	95.30 17		98.27 39	95.09 29	99.19 4	98.81 24	95.54 5	99.65 61

save fliter					98.91 52	94.28 38	97.02 179	98.02 97	95.35 19

test0726					99.45 3	95.36 13	98.31 27	98.29 34	94.92 35	98.99 7	98.92 13	95.08 8

GSMVS																98.45 149

test_part2					99.28 25	95.74 8				98.10 30

sam_mvs1												82.76 199				98.45 149

sam_mvs												81.94 218

MTGPA								98.08 77

test_post											17.58 423	81.76 220	98.08 258

patchmatchnet-post											90.45 379	82.65 203	98.10 253

MTMP							97.86 81	82.03 418

TEST9					98.70 59	94.19 42	96.41 233	98.02 97	88.17 276	96.03 104	97.56 126	92.74 33	99.59 77

test_8					98.67 61	94.06 49	96.37 240	98.01 100	88.58 263	95.98 108	97.55 128	92.73 34	99.58 80

agg_prior					98.67 61	93.79 54		98.00 101		95.68 118			99.57 87

test_prior4						93.66 57	96.42 232

test_prior				97.23 63	98.67 61	92.99 78		98.00 101					99.41 112			99.29 66

新几何2							95.79 275

旧先验1					98.38 81	93.38 63		97.75 130			98.09 78	92.30 45			99.01 92	99.16 76

原ACMM2							95.67 280

test222					98.24 90	92.21 102	95.33 297	97.60 149	79.22 390	95.25 127	97.84 101	88.80 97			99.15 81	98.72 125

segment_acmp												92.89 30

testdata1							95.26 304		93.10 113

test12				97.65 42	98.46 73	94.26 39		97.66 141		95.52 125		90.89 73	99.46 106		99.25 71	99.22 73

plane_prior7					96.21 226	89.98 184

plane_prior6					96.10 237	90.00 180						81.32 226

plane_prior4											96.64 175

plane_prior3						90.00 180			94.46 60	91.34 220

plane_prior2							97.74 97		94.85 37

plane_prior1					96.14 234

plane_prior						89.99 182	97.24 160		94.06 72						92.16 253

n2								0.00 432

nn								0.00 432

door-mid								91.06 396

test11								97.88 112

door								91.13 395

HQP5-MVS						89.33 209

HQP-NCC					95.86 243		96.65 215		93.55 88	90.14 244

ACMP_Plane					95.86 243		96.65 215		93.55 88	90.14 244

HQP4-MVS										90.14 244			98.50 217			95.78 269

HQP3-MVS								97.39 187							92.10 254

HQP2-MVS												80.95 230

NP-MVS					95.99 241	89.81 190					95.87 217

ACMMP++_ref															90.30 283

ACMMP++															91.02 272

Test By Simon												88.73 99

High-resolution multi-view benchmark