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		95.10 11	94.91 18	95.68 5	96.09 106	88.34 9	96.68 33	94.37 248	95.08 1	94.68 44	97.72 30	82.94 90	99.64 1	97.85 2	98.76 29	99.06 7

fmvsm_s_conf0.5_n_3		94.49 24	95.13 10	92.56 121	95.49 137	81.10 195	95.93 77	97.16 42	92.96 2	97.39 7	98.13 4	83.63 81	98.80 96	97.89 1	97.61 86	97.78 95

EPNet		91.79 95	91.02 106	94.10 58	90.10 352	85.25 73	96.03 68	92.05 314	92.83 3	87.39 188	95.78 116	79.39 136	99.01 66	88.13 140	97.48 87	98.05 76
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVS_0304		94.18 41	93.80 52	95.34 9	94.91 166	87.62 14	95.97 73	93.01 288	92.58 4	94.22 49	97.20 50	80.56 120	99.59 8	97.04 12	98.68 37	98.81 17

NCCC		94.81 17	94.69 23	95.17 14	97.83 51	87.46 17	95.66 95	96.93 61	92.34 5	93.94 58	96.58 83	87.74 27	99.44 29	92.83 61	98.40 54	98.62 22

SPE-MVS-test		94.02 44	94.29 33	93.24 82	96.69 81	83.24 128	97.49 5	96.92 62	92.14 6	92.90 79	95.77 117	85.02 63	98.33 145	93.03 58	98.62 46	98.13 69

CNVR-MVS		95.40 7	95.37 7	95.50 8	98.11 36	88.51 7	95.29 113	96.96 57	92.09 7	95.32 36	97.08 56	89.49 15	99.33 40	95.10 32	98.85 20	98.66 21

UA-Net		92.83 80	92.54 83	93.68 74	96.10 105	84.71 83	95.66 95	96.39 110	91.92 8	93.22 72	96.49 86	83.16 86	98.87 88	84.47 188	95.47 131	97.45 112

CANet		93.54 57	93.20 70	94.55 43	95.65 128	85.73 65	94.94 137	96.69 89	91.89 9	90.69 131	95.88 111	81.99 111	99.54 20	93.14 56	97.95 74	98.39 40

HPM-MVS++		95.14 10	94.91 18	95.83 4	98.25 29	89.65 4	95.92 78	96.96 57	91.75 10	94.02 57	96.83 68	88.12 24	99.55 16	93.41 52	98.94 16	98.28 55

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 25	97.47 11	91.73 11	96.10 24	96.69 73	89.90 12	99.30 43	94.70 35	98.04 71	99.13 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
CS-MVS		94.12 42	94.44 27	93.17 85	96.55 88	83.08 138	97.63 3	96.95 59	91.71 12	93.50 69	96.21 93	85.61 52	98.24 150	93.64 47	98.17 62	98.19 65

SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 25	96.99 75	86.33 42	97.33 7	97.30 30	91.38 13	95.39 35	97.46 36	88.98 19	99.40 30	94.12 41	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
MTAPA		94.42 30	94.22 37	95.00 18	98.42 21	86.95 21	94.36 181	96.97 55	91.07 14	93.14 74	97.56 33	84.30 74	99.56 12	93.43 50	98.75 30	98.47 33

test_one_0601					98.58 11	85.83 61		97.44 15	91.05 15	96.78 18	98.06 16	91.45 11

fmvsm_l_conf0.5_n_3		94.80 18	95.01 13	94.15 57	95.64 129	85.08 75	96.09 60	97.36 22	90.98 16	97.09 12	98.12 7	84.98 67	98.94 83	97.07 10	97.80 79	98.43 38

EI-MVSNet-Vis-set		93.01 78	92.92 75	93.29 79	95.01 157	83.51 121	94.48 165	95.77 165	90.87 17	92.52 95	96.67 75	84.50 72	99.00 71	91.99 88	94.44 158	97.36 113

3Dnovator+	87.14 4	92.42 88	91.37 98	95.55 7	95.63 130	88.73 6	97.07 18	96.77 79	90.84 18	84.02 281	96.62 81	75.95 175	99.34 37	87.77 144	97.68 84	98.59 24

HQP_MVS		90.60 124	90.19 118	91.82 161	94.70 178	82.73 151	95.85 83	96.22 126	90.81 19	86.91 194	94.86 153	74.23 200	98.12 158	88.15 138	89.99 226	94.63 234

plane_prior2							95.85 83		90.81 19

DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 54	86.00 50	98.29 1	97.49 6	90.75 21	97.62 5	98.06 16	92.59 2	99.61 4	95.64 23	99.02 12	98.86 11

test_0728_THIRD									90.75 21	97.04 14	98.05 18	92.09 6	99.55 16	95.64 23	99.13 3	99.13 2

DELS-MVS		93.43 66	93.25 68	93.97 60	95.42 139	85.04 76	93.06 250	97.13 45	90.74 23	91.84 113	95.09 145	86.32 45	99.21 48	91.22 103	98.45 52	97.65 102
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
ETV-MVS		92.74 82	92.66 80	92.97 98	95.20 150	84.04 106	95.07 130	96.51 102	90.73 24	92.96 78	91.19 286	84.06 76	98.34 143	91.72 97	96.54 110	96.54 159

EI-MVSNet-UG-set		92.74 82	92.62 82	93.12 88	94.86 169	83.20 130	94.40 173	95.74 168	90.71 25	92.05 104	96.60 82	84.00 77	98.99 73	91.55 99	93.63 168	97.17 122

XVS		94.45 26	94.32 30	94.85 25	98.54 13	86.60 34	96.93 22	97.19 36	90.66 26	92.85 81	97.16 54	85.02 63	99.49 26	91.99 88	98.56 50	98.47 33

X-MVStestdata		88.31 186	86.13 233	94.85 25	98.54 13	86.60 34	96.93 22	97.19 36	90.66 26	92.85 81	23.41 426	85.02 63	99.49 26	91.99 88	98.56 50	98.47 33

EC-MVSNet		93.44 62	93.71 58	92.63 117	95.21 149	82.43 159	97.27 9	96.71 87	90.57 28	92.88 80	95.80 115	83.16 86	98.16 156	93.68 46	98.14 65	97.31 114

SD-MVS		94.96 13	95.33 8	93.88 63	97.25 72	86.69 28	96.19 49	97.11 48	90.42 29	96.95 16	97.27 44	89.53 14	96.91 265	94.38 39	98.85 20	98.03 78
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
BP-MVS1		92.48 86	92.07 89	93.72 72	94.50 192	84.39 99	95.90 79	94.30 251	90.39 30	92.67 91	95.94 107	74.46 196	98.65 110	93.14 56	97.35 91	98.13 69

fmvsm_s_conf0.5_n_2		93.47 59	93.83 50	92.39 131	95.36 140	81.19 191	95.20 123	96.56 98	90.37 31	97.13 11	98.03 22	77.47 158	98.96 80	97.79 3	96.58 109	97.03 132

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 52	97.13 14	97.44 15	90.31 32	97.71 1	98.07 14	92.31 4	99.58 10	95.66 21	99.13 3	98.84 14

test_241102_TWO								97.44 15	90.31 32	97.62 5	98.07 14	91.46 10	99.58 10	95.66 21	99.12 6	98.98 10

fmvsm_s_conf0.1_n_2		93.16 75	93.42 64	92.37 132	94.62 182	81.13 193	95.23 118	95.89 157	90.30 34	96.74 20	98.02 23	76.14 170	98.95 82	97.64 4	96.21 117	97.03 132

casdiffmvs_mvg		92.96 79	92.83 77	93.35 78	94.59 184	83.40 124	95.00 134	96.34 113	90.30 34	92.05 104	96.05 102	83.43 82	98.15 157	92.07 84	95.67 125	98.49 29
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 55	97.09 16	96.73 84	90.27 36	97.04 14	98.05 18	91.47 8	99.55 16	95.62 25	99.08 7	98.45 36
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
test0726					98.78 3	85.93 55	97.19 11	97.47 11	90.27 36	97.64 4	98.13 4	91.47 8

test_241102_ONE					98.77 5	85.99 52		97.44 15	90.26 38	97.71 1	97.96 24	92.31 4	99.38 31

plane_prior3						82.75 148			90.26 38	86.91 194

DeepPCF-MVS	89.96 1	94.20 38	94.77 22	92.49 125	96.52 91	80.00 229	94.00 206	97.08 49	90.05 40	95.65 33	97.29 43	89.66 13	98.97 78	93.95 43	98.71 32	98.50 27

MSLP-MVS++		93.72 54	94.08 43	92.65 116	97.31 68	83.43 122	95.79 87	97.33 26	90.03 41	93.58 65	96.96 62	84.87 68	97.76 188	92.19 80	98.66 41	96.76 148

sasdasda		93.27 69	92.75 78	94.85 25	95.70 125	87.66 12	96.33 39	96.41 108	90.00 42	94.09 53	94.60 166	82.33 99	98.62 115	92.40 71	92.86 188	98.27 57

canonicalmvs		93.27 69	92.75 78	94.85 25	95.70 125	87.66 12	96.33 39	96.41 108	90.00 42	94.09 53	94.60 166	82.33 99	98.62 115	92.40 71	92.86 188	98.27 57

Vis-MVSNet		91.75 97	91.23 101	93.29 79	95.32 142	83.78 111	96.14 56	95.98 147	89.89 44	90.45 133	96.58 83	75.09 187	98.31 148	84.75 184	96.90 100	97.78 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TranMVSNet+NR-MVSNet		88.84 171	87.95 177	91.49 173	92.68 267	83.01 142	94.92 139	96.31 115	89.88 45	85.53 231	93.85 198	76.63 168	96.96 261	81.91 231	79.87 358	94.50 245

MGCFI-Net		93.03 77	92.63 81	94.23 56	95.62 131	85.92 57	96.08 61	96.33 114	89.86 46	93.89 60	94.66 163	82.11 106	98.50 123	92.33 76	92.82 191	98.27 57

test_fmvsm_n_1920		94.71 21	95.11 11	93.50 77	95.79 120	84.62 85	96.15 54	97.64 2	89.85 47	97.19 9	97.89 26	86.28 46	98.71 106	97.11 9	98.08 70	97.17 122

reproduce-ours		94.82 15	94.97 14	94.38 50	97.91 47	85.46 68	95.86 81	97.15 43	89.82 48	95.23 39	98.10 10	87.09 37	99.37 33	95.30 29	98.25 60	98.30 50

our_new_method		94.82 15	94.97 14	94.38 50	97.91 47	85.46 68	95.86 81	97.15 43	89.82 48	95.23 39	98.10 10	87.09 37	99.37 33	95.30 29	98.25 60	98.30 50

balanced_conf03		93.98 47	94.22 37	93.26 81	96.13 101	83.29 127	96.27 45	96.52 101	89.82 48	95.56 34	95.51 126	84.50 72	98.79 98	94.83 34	98.86 19	97.72 98

h-mvs33		90.80 114	90.15 120	92.75 110	96.01 110	82.66 155	95.43 105	95.53 186	89.80 51	93.08 75	95.64 122	75.77 176	99.00 71	92.07 84	78.05 368	96.60 154

hse-mvs2		89.88 141	89.34 140	91.51 172	94.83 171	81.12 194	93.94 209	93.91 268	89.80 51	93.08 75	93.60 205	75.77 176	97.66 195	92.07 84	77.07 375	95.74 194

UniMVSNet_NR-MVSNet		89.92 139	89.29 142	91.81 163	93.39 245	83.72 112	94.43 171	97.12 46	89.80 51	86.46 205	93.32 211	83.16 86	97.23 241	84.92 180	81.02 341	94.49 247

FOURS1					98.86 1	85.54 67	98.29 1	97.49 6	89.79 54	96.29 22

alignmvs		93.08 76	92.50 84	94.81 32	95.62 131	87.61 15	95.99 71	96.07 140	89.77 55	94.12 52	94.87 152	80.56 120	98.66 108	92.42 70	93.10 184	98.15 68

TSAR-MVS + GP.		93.66 55	93.41 65	94.41 49	96.59 85	86.78 26	94.40 173	93.93 265	89.77 55	94.21 50	95.59 124	87.35 34	98.61 117	92.72 64	96.15 119	97.83 92

IS-MVSNet		91.43 102	91.09 105	92.46 126	95.87 119	81.38 185	96.95 19	93.69 275	89.72 57	89.50 149	95.98 105	78.57 147	97.77 187	83.02 206	96.50 112	98.22 64

reproduce_model		94.76 19	94.92 17	94.29 54	97.92 43	85.18 74	95.95 76	97.19 36	89.67 58	95.27 38	98.16 3	86.53 43	99.36 35	95.42 28	98.15 64	98.33 45

plane_prior						82.73 151	95.21 121		89.66 59						89.88 231

casdiffmvs		92.51 85	92.43 85	92.74 111	94.41 199	81.98 169	94.54 163	96.23 125	89.57 60	91.96 108	96.17 98	82.58 95	98.01 175	90.95 109	95.45 133	98.23 63
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DU-MVS		89.34 159	88.50 162	91.85 160	93.04 257	83.72 112	94.47 168	96.59 95	89.50 61	86.46 205	93.29 214	77.25 160	97.23 241	84.92 180	81.02 341	94.59 237

save fliter					97.85 49	85.63 66	95.21 121	96.82 73	89.44 62

CANet_DTU		90.26 129	89.41 138	92.81 106	93.46 243	83.01 142	93.48 227	94.47 244	89.43 63	87.76 180	94.23 181	70.54 252	99.03 61	84.97 179	96.39 114	96.38 162

DeepC-MVS_fast	89.43 2	94.04 43	93.79 53	94.80 33	97.48 64	86.78 26	95.65 97	96.89 65	89.40 64	92.81 84	96.97 61	85.37 57	99.24 46	90.87 111	98.69 35	98.38 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf_n		94.60 22	94.81 21	93.98 59	94.62 182	84.96 78	96.15 54	97.35 23	89.37 65	96.03 27	98.11 8	86.36 44	99.01 66	97.45 5	97.83 78	97.96 81

UGNet		89.95 137	88.95 149	92.95 100	94.51 191	83.31 126	95.70 91	95.23 205	89.37 65	87.58 182	93.94 191	64.00 319	98.78 99	83.92 195	96.31 115	96.74 150
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
FC-MVSNet-test		90.27 128	90.18 119	90.53 210	93.71 233	79.85 234	95.77 88	97.59 3	89.31 67	86.27 212	94.67 162	81.93 112	97.01 258	84.26 190	88.09 262	94.71 233

test_fmvsmconf0.1_n		94.20 38	94.31 32	93.88 63	92.46 271	84.80 81	96.18 51	96.82 73	89.29 68	95.68 32	98.11 8	85.10 60	98.99 73	97.38 6	97.75 83	97.86 89

UniMVSNet (Re)		89.80 142	89.07 146	92.01 144	93.60 239	84.52 90	94.78 149	97.47 11	89.26 69	86.44 208	92.32 245	82.10 107	97.39 229	84.81 183	80.84 345	94.12 260

baseline		92.39 89	92.29 87	92.69 115	94.46 195	81.77 173	94.14 190	96.27 120	89.22 70	91.88 111	96.00 103	82.35 98	97.99 177	91.05 105	95.27 139	98.30 50

3Dnovator	86.66 5	91.73 98	90.82 110	94.44 45	94.59 184	86.37 41	97.18 12	97.02 52	89.20 71	84.31 276	96.66 76	73.74 212	99.17 50	86.74 159	97.96 73	97.79 94

VNet		92.24 90	91.91 91	93.24 82	96.59 85	83.43 122	94.84 145	96.44 105	89.19 72	94.08 56	95.90 109	77.85 157	98.17 155	88.90 131	93.38 177	98.13 69

FIs		90.51 125	90.35 115	90.99 198	93.99 222	80.98 198	95.73 89	97.54 4	89.15 73	86.72 201	94.68 161	81.83 113	97.24 240	85.18 177	88.31 259	94.76 232

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 25	87.28 18	95.56 103	97.51 5	89.13 74	97.14 10	97.91 25	91.64 7	99.62 2	94.61 37	99.17 2	98.86 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_fmvsmconf0.01_n		93.19 73	93.02 73	93.71 73	89.25 365	84.42 98	96.06 65	96.29 116	89.06 75	94.68 44	98.13 4	79.22 138	98.98 77	97.22 7	97.24 92	97.74 97

NR-MVSNet		88.58 181	87.47 188	91.93 152	93.04 257	84.16 103	94.77 150	96.25 123	89.05 76	80.04 341	93.29 214	79.02 140	97.05 256	81.71 238	80.05 355	94.59 237

RRT-MVS		90.85 113	90.70 112	91.30 181	94.25 206	76.83 298	94.85 144	96.13 134	89.04 77	90.23 137	94.88 151	70.15 257	98.72 104	91.86 95	94.88 144	98.34 43

MP-MVS		94.25 33	94.07 44	94.77 35	98.47 18	86.31 44	96.71 31	96.98 54	89.04 77	91.98 106	97.19 51	85.43 56	99.56 12	92.06 87	98.79 24	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 28	86.29 46	97.46 6	97.40 20	89.03 79	96.20 23	98.10 10	89.39 16	99.34 37	95.88 20	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DeepC-MVS	88.79 3	93.31 68	92.99 74	94.26 55	96.07 108	85.83 61	94.89 140	96.99 53	89.02 80	89.56 146	97.37 41	82.51 96	99.38 31	92.20 79	98.30 57	97.57 107
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmvis_n_1920		93.44 62	93.55 62	93.10 89	93.67 236	84.26 101	95.83 85	96.14 131	89.00 81	92.43 98	97.50 34	83.37 85	98.72 104	96.61 16	97.44 88	96.32 164

OPM-MVS		90.12 131	89.56 134	91.82 161	93.14 250	83.90 108	94.16 189	95.74 168	88.96 82	87.86 175	95.43 130	72.48 228	97.91 183	88.10 142	90.18 225	93.65 290
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP-NCC					94.17 210		94.39 175		88.81 83	85.43 240

ACMP_Plane					94.17 210		94.39 175		88.81 83	85.43 240

HQP-MVS		89.80 142	89.28 143	91.34 180	94.17 210	81.56 176	94.39 175	96.04 143	88.81 83	85.43 240	93.97 190	73.83 210	97.96 179	87.11 156	89.77 235	94.50 245

MVS_111021_HR		93.45 61	93.31 66	93.84 65	96.99 75	84.84 79	93.24 243	97.24 33	88.76 86	91.60 120	95.85 112	86.07 49	98.66 108	91.91 92	98.16 63	98.03 78

SDMVSNet		90.19 130	89.61 133	91.93 152	96.00 111	83.09 137	92.89 256	95.98 147	88.73 87	86.85 198	95.20 140	72.09 232	97.08 251	88.90 131	89.85 232	95.63 199

sd_testset		88.59 180	87.85 180	90.83 202	96.00 111	80.42 214	92.35 272	94.71 238	88.73 87	86.85 198	95.20 140	67.31 288	96.43 295	79.64 268	89.85 232	95.63 199

mPP-MVS		93.99 46	93.78 54	94.63 40	98.50 16	85.90 60	96.87 26	96.91 63	88.70 89	91.83 115	97.17 53	83.96 78	99.55 16	91.44 101	98.64 45	98.43 38

VPNet		88.20 189	87.47 188	90.39 220	93.56 240	79.46 240	94.04 201	95.54 185	88.67 90	86.96 191	94.58 169	69.33 268	97.15 245	84.05 193	80.53 350	94.56 240

HFP-MVS		94.52 23	94.40 28	94.86 24	98.61 10	86.81 25	96.94 20	97.34 24	88.63 91	93.65 63	97.21 48	86.10 48	99.49 26	92.35 74	98.77 28	98.30 50

ACMMPR		94.43 28	94.28 34	94.91 21	98.63 9	86.69 28	96.94 20	97.32 28	88.63 91	93.53 68	97.26 46	85.04 62	99.54 20	92.35 74	98.78 26	98.50 27

reproduce_monomvs		86.37 262	85.87 246	87.87 305	93.66 237	73.71 336	93.44 230	95.02 215	88.61 93	82.64 307	91.94 263	57.88 366	96.68 273	89.96 120	79.71 360	93.22 306

region2R		94.43 28	94.27 36	94.92 20	98.65 8	86.67 30	96.92 24	97.23 35	88.60 94	93.58 65	97.27 44	85.22 58	99.54 20	92.21 78	98.74 31	98.56 25

WR-MVS		88.38 183	87.67 183	90.52 212	93.30 247	80.18 218	93.26 241	95.96 150	88.57 95	85.47 236	92.81 231	76.12 171	96.91 265	81.24 243	82.29 321	94.47 250

CP-MVS		94.34 31	94.21 39	94.74 37	98.39 23	86.64 32	97.60 4	97.24 33	88.53 96	92.73 89	97.23 47	85.20 59	99.32 41	92.15 81	98.83 22	98.25 62

EIA-MVS		91.95 93	91.94 90	91.98 148	95.16 152	80.01 228	95.36 106	96.73 84	88.44 97	89.34 151	92.16 250	83.82 80	98.45 133	89.35 125	97.06 95	97.48 110

CP-MVSNet		87.63 207	87.26 195	88.74 281	93.12 251	76.59 303	95.29 113	96.58 96	88.43 98	83.49 295	92.98 225	75.28 185	95.83 324	78.97 276	81.15 337	93.79 279

VDD-MVS		90.74 116	89.92 128	93.20 84	96.27 97	83.02 141	95.73 89	93.86 269	88.42 99	92.53 94	96.84 67	62.09 330	98.64 112	90.95 109	92.62 193	97.93 84

dcpmvs_2		93.49 58	94.19 41	91.38 178	97.69 57	76.78 299	94.25 184	96.29 116	88.33 100	94.46 46	96.88 65	88.07 25	98.64 112	93.62 48	98.09 68	98.73 18

ACMMP		93.24 71	92.88 76	94.30 53	98.09 38	85.33 72	96.86 27	97.45 14	88.33 100	90.15 141	97.03 60	81.44 114	99.51 24	90.85 112	95.74 124	98.04 77
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
nrg030		91.08 110	90.39 114	93.17 85	93.07 254	86.91 22	96.41 37	96.26 121	88.30 102	88.37 167	94.85 155	82.19 105	97.64 198	91.09 104	82.95 311	94.96 222

ACMMP_NAP		94.74 20	94.56 24	95.28 10	98.02 41	87.70 11	95.68 92	97.34 24	88.28 103	95.30 37	97.67 32	85.90 50	99.54 20	93.91 44	98.95 15	98.60 23

ZNCC-MVS		94.47 25	94.28 34	95.03 16	98.52 15	86.96 20	96.85 28	97.32 28	88.24 104	93.15 73	97.04 59	86.17 47	99.62 2	92.40 71	98.81 23	98.52 26

GST-MVS		94.21 36	93.97 48	94.90 23	98.41 22	86.82 24	96.54 36	97.19 36	88.24 104	93.26 70	96.83 68	85.48 55	99.59 8	91.43 102	98.40 54	98.30 50

PS-CasMVS		87.32 223	86.88 201	88.63 284	92.99 260	76.33 308	95.33 108	96.61 94	88.22 106	83.30 300	93.07 223	73.03 222	95.79 328	78.36 281	81.00 343	93.75 286

SR-MVS		94.23 35	94.17 42	94.43 47	98.21 32	85.78 63	96.40 38	96.90 64	88.20 107	94.33 48	97.40 39	84.75 70	99.03 61	93.35 53	97.99 72	98.48 30

MVS_111021_LR		92.47 87	92.29 87	92.98 97	95.99 114	84.43 96	93.08 248	96.09 138	88.20 107	91.12 127	95.72 120	81.33 116	97.76 188	91.74 96	97.37 90	96.75 149

TSAR-MVS + MP.		94.85 14	94.94 16	94.58 42	98.25 29	86.33 42	96.11 59	96.62 93	88.14 109	96.10 24	96.96 62	89.09 18	98.94 83	94.48 38	98.68 37	98.48 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.5_n		93.76 52	94.06 46	92.86 104	95.62 131	83.17 131	96.14 56	96.12 135	88.13 110	95.82 30	98.04 21	83.43 82	98.48 125	96.97 13	96.23 116	96.92 141

test1111		89.10 162	88.64 157	90.48 215	95.53 136	74.97 322	96.08 61	84.89 399	88.13 110	90.16 140	96.65 77	63.29 324	98.10 160	86.14 165	96.90 100	98.39 40

patch_mono-2		93.74 53	94.32 30	92.01 144	97.54 60	78.37 266	93.40 231	97.19 36	88.02 112	94.99 43	97.21 48	88.35 21	98.44 135	94.07 42	98.09 68	99.23 1

PEN-MVS		86.80 244	86.27 229	88.40 287	92.32 275	75.71 316	95.18 124	96.38 111	87.97 113	82.82 304	93.15 219	73.39 218	95.92 319	76.15 307	79.03 366	93.59 291

testdata1							92.15 280		87.94 114

VPA-MVSNet		89.62 145	88.96 148	91.60 169	93.86 226	82.89 146	95.46 104	97.33 26	87.91 115	88.43 166	93.31 212	74.17 203	97.40 226	87.32 152	82.86 316	94.52 242

WR-MVS_H		87.80 199	87.37 190	89.10 270	93.23 248	78.12 272	95.61 99	97.30 30	87.90 116	83.72 287	92.01 261	79.65 135	96.01 315	76.36 303	80.54 349	93.16 310

CLD-MVS		89.47 151	88.90 152	91.18 186	94.22 208	82.07 167	92.13 281	96.09 138	87.90 116	85.37 246	92.45 241	74.38 198	97.56 203	87.15 154	90.43 220	93.93 269
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test2506		87.21 230	86.28 228	90.02 237	95.62 131	73.64 338	96.25 47	71.38 424	87.89 118	90.45 133	96.65 77	55.29 378	98.09 168	86.03 169	96.94 98	98.33 45

ECVR-MVS		89.09 164	88.53 160	90.77 205	95.62 131	75.89 312	96.16 52	84.22 401	87.89 118	90.20 138	96.65 77	63.19 326	98.10 160	85.90 170	96.94 98	98.33 45

MG-MVS		91.77 96	91.70 95	92.00 147	97.08 74	80.03 227	93.60 224	95.18 208	87.85 120	90.89 129	96.47 87	82.06 109	98.36 140	85.07 178	97.04 96	97.62 103

GDP-MVS		92.04 91	91.46 97	93.75 71	94.55 189	84.69 84	95.60 102	96.56 98	87.83 121	93.07 77	95.89 110	73.44 216	98.65 110	90.22 119	96.03 121	97.91 86

MonoMVSNet		86.89 242	86.55 217	87.92 304	89.46 364	73.75 335	94.12 191	93.10 284	87.82 122	85.10 251	90.76 304	69.59 264	94.94 350	86.47 163	82.50 318	95.07 216

LCM-MVSNet-Re		88.30 187	88.32 169	88.27 293	94.71 177	72.41 357	93.15 244	90.98 345	87.77 123	79.25 350	91.96 262	78.35 150	95.75 329	83.04 205	95.62 126	96.65 153

SF-MVS		94.97 12	94.90 20	95.20 12	97.84 50	87.76 10	96.65 34	97.48 10	87.76 124	95.71 31	97.70 31	88.28 23	99.35 36	93.89 45	98.78 26	98.48 30

Effi-MVS+-dtu		88.65 177	88.35 166	89.54 258	93.33 246	76.39 306	94.47 168	94.36 249	87.70 125	85.43 240	89.56 337	73.45 215	97.26 238	85.57 175	91.28 207	94.97 219

fmvsm_s_conf0.1_n		93.46 60	93.66 60	92.85 105	93.75 232	83.13 133	96.02 69	95.74 168	87.68 126	95.89 29	98.17 2	82.78 93	98.46 129	96.71 14	96.17 118	96.98 137

test_prior2							94.12 191		87.67 127	92.63 92	96.39 89	86.62 40		91.50 100	98.67 40

Vis-MVSNet (Re-imp)		89.59 147	89.44 136	90.03 235	95.74 122	75.85 313	95.61 99	90.80 352	87.66 128	87.83 177	95.40 131	76.79 164	96.46 293	78.37 280	96.73 105	97.80 93

SR-MVS-dyc-post		93.82 50	93.82 51	93.82 66	97.92 43	84.57 87	96.28 43	96.76 80	87.46 129	93.75 61	97.43 37	84.24 75	99.01 66	92.73 62	97.80 79	97.88 87

RE-MVS-def			93.68 59		97.92 43	84.57 87	96.28 43	96.76 80	87.46 129	93.75 61	97.43 37	82.94 90		92.73 62	97.80 79	97.88 87

PGM-MVS		93.96 48	93.72 57	94.68 38	98.43 20	86.22 47	95.30 111	97.78 1	87.45 131	93.26 70	97.33 42	84.62 71	99.51 24	90.75 113	98.57 49	98.32 49

DTE-MVSNet		86.11 265	85.48 258	87.98 301	91.65 301	74.92 323	94.93 138	95.75 167	87.36 132	82.26 310	93.04 224	72.85 223	95.82 325	74.04 324	77.46 372	93.20 308

fmvsm_s_conf0.5_n_a		93.57 56	93.76 56	93.00 96	95.02 156	83.67 114	96.19 49	96.10 137	87.27 133	95.98 28	98.05 18	83.07 89	98.45 133	96.68 15	95.51 128	96.88 144

myMVS_eth3d28		85.80 272	85.26 266	87.42 317	94.73 174	69.92 382	90.60 318	90.95 347	87.21 134	86.06 218	90.04 325	59.47 355	96.02 313	74.89 319	93.35 180	96.33 163

thres100view900		87.63 207	86.71 208	90.38 222	96.12 102	78.55 259	95.03 133	91.58 329	87.15 135	88.06 172	92.29 247	68.91 278	98.10 160	70.13 350	91.10 208	94.48 248

MCST-MVS		94.45 26	94.20 40	95.19 13	98.46 19	87.50 16	95.00 134	97.12 46	87.13 136	92.51 96	96.30 90	89.24 17	99.34 37	93.46 49	98.62 46	98.73 18

Effi-MVS+		91.59 101	91.11 103	93.01 95	94.35 204	83.39 125	94.60 159	95.10 212	87.10 137	90.57 132	93.10 222	81.43 115	98.07 171	89.29 127	94.48 156	97.59 106

thres600view7		87.65 204	86.67 210	90.59 207	96.08 107	78.72 255	94.88 141	91.58 329	87.06 138	88.08 171	92.30 246	68.91 278	98.10 160	70.05 353	91.10 208	94.96 222

diffmvs		91.37 104	91.23 101	91.77 164	93.09 253	80.27 216	92.36 271	95.52 187	87.03 139	91.40 124	94.93 148	80.08 125	97.44 216	92.13 83	94.56 153	97.61 104
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
APD-MVS_3200maxsize		93.78 51	93.77 55	93.80 68	97.92 43	84.19 102	96.30 41	96.87 67	86.96 140	93.92 59	97.47 35	83.88 79	98.96 80	92.71 65	97.87 76	98.26 61

OMC-MVS		91.23 106	90.62 113	93.08 91	96.27 97	84.07 104	93.52 226	95.93 151	86.95 141	89.51 147	96.13 100	78.50 148	98.35 142	85.84 172	92.90 187	96.83 147

tfpn200view9		87.58 211	86.64 211	90.41 219	95.99 114	78.64 257	94.58 160	91.98 318	86.94 142	88.09 169	91.77 267	69.18 274	98.10 160	70.13 350	91.10 208	94.48 248

thres400		87.62 209	86.64 211	90.57 208	95.99 114	78.64 257	94.58 160	91.98 318	86.94 142	88.09 169	91.77 267	69.18 274	98.10 160	70.13 350	91.10 208	94.96 222

HPM-MVS		94.02 44	93.88 49	94.43 47	98.39 23	85.78 63	97.25 10	97.07 50	86.90 144	92.62 93	96.80 72	84.85 69	99.17 50	92.43 69	98.65 44	98.33 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
LFMVS		90.08 132	89.13 145	92.95 100	96.71 80	82.32 164	96.08 61	89.91 368	86.79 145	92.15 103	96.81 70	62.60 328	98.34 143	87.18 153	93.90 164	98.19 65

fmvsm_s_conf0.1_n_a		93.19 73	93.26 67	92.97 98	92.49 269	83.62 117	96.02 69	95.72 171	86.78 146	96.04 26	98.19 1	82.30 101	98.43 137	96.38 17	95.42 134	96.86 145

baseline1		88.10 191	87.28 193	90.57 208	94.96 161	80.07 223	94.27 183	91.29 338	86.74 147	87.41 185	94.00 188	76.77 165	96.20 306	80.77 251	79.31 364	95.44 203

LPG-MVS_test		89.45 152	88.90 152	91.12 187	94.47 193	81.49 180	95.30 111	96.14 131	86.73 148	85.45 237	95.16 142	69.89 259	98.10 160	87.70 145	89.23 244	93.77 284

LGP-MVS_train				91.12 187	94.47 193	81.49 180		96.14 131	86.73 148	85.45 237	95.16 142	69.89 259	98.10 160	87.70 145	89.23 244	93.77 284

EPNet_dtu		86.49 259	85.94 244	88.14 298	90.24 350	72.82 347	94.11 193	92.20 310	86.66 150	79.42 349	92.36 244	73.52 213	95.81 326	71.26 338	93.66 167	95.80 192
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_l_conf0.5_n		94.29 32	94.46 26	93.79 69	95.28 144	85.43 70	95.68 92	96.43 106	86.56 151	96.84 17	97.81 29	87.56 32	98.77 100	97.14 8	96.82 104	97.16 126

testing91		87.11 235	86.18 231	89.92 241	94.43 198	75.38 321	91.53 296	92.27 308	86.48 152	86.50 203	90.24 316	61.19 344	97.53 205	82.10 225	90.88 216	96.84 146

ACMP	84.23 8	89.01 169	88.35 166	90.99 198	94.73 174	81.27 186	95.07 130	95.89 157	86.48 152	83.67 289	94.30 175	69.33 268	97.99 177	87.10 158	88.55 251	93.72 288
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS_Test		91.31 105	91.11 103	91.93 152	94.37 200	80.14 220	93.46 229	95.80 163	86.46 154	91.35 125	93.77 201	82.21 104	98.09 168	87.57 147	94.95 143	97.55 109

thres200		87.21 230	86.24 230	90.12 231	95.36 140	78.53 260	93.26 241	92.10 312	86.42 155	88.00 174	91.11 292	69.24 273	98.00 176	69.58 354	91.04 214	93.83 278

PAPM_NR		91.22 107	90.78 111	92.52 124	97.60 59	81.46 182	94.37 179	96.24 124	86.39 156	87.41 185	94.80 157	82.06 109	98.48 125	82.80 212	95.37 135	97.61 104

fmvsm_l_conf0.5_n_a		94.20 38	94.40 28	93.60 75	95.29 143	84.98 77	95.61 99	96.28 119	86.31 157	96.75 19	97.86 28	87.40 33	98.74 103	97.07 10	97.02 97	97.07 128

PS-MVSNAJ		91.18 108	90.92 107	91.96 150	95.26 147	82.60 158	92.09 283	95.70 172	86.27 158	91.84 113	92.46 240	79.70 131	98.99 73	89.08 129	95.86 123	94.29 254

MP-MVS-pluss		94.21 36	94.00 47	94.85 25	98.17 33	86.65 31	94.82 146	97.17 41	86.26 159	92.83 83	97.87 27	85.57 54	99.56 12	94.37 40	98.92 17	98.34 43
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PS-MVSNAJss		89.97 136	89.62 132	91.02 195	91.90 289	80.85 203	95.26 117	95.98 147	86.26 159	86.21 214	94.29 176	79.70 131	97.65 196	88.87 133	88.10 260	94.57 239

test_vis1_n_1920		89.39 157	89.84 129	88.04 300	92.97 261	72.64 352	94.71 154	96.03 145	86.18 161	91.94 110	96.56 85	61.63 334	95.74 330	93.42 51	95.11 141	95.74 194

EPP-MVSNet		91.70 99	91.56 96	92.13 143	95.88 117	80.50 212	97.33 7	95.25 204	86.15 162	89.76 145	95.60 123	83.42 84	98.32 147	87.37 151	93.25 181	97.56 108

testing99		86.72 249	85.73 255	89.69 253	94.23 207	74.91 324	91.35 300	90.97 346	86.14 163	86.36 209	90.22 317	59.41 357	97.48 209	82.24 222	90.66 217	96.69 152

XVG-OURS		89.40 156	88.70 156	91.52 171	94.06 215	81.46 182	91.27 303	96.07 140	86.14 163	88.89 159	95.77 117	68.73 281	97.26 238	87.39 150	89.96 228	95.83 190

9.14			94.47 25		97.79 52		96.08 61	97.44 15	86.13 165	95.10 41	97.40 39	88.34 22	99.22 47	93.25 54	98.70 34

xiu_mvs_v2_base		91.13 109	90.89 109	91.86 158	94.97 160	82.42 160	92.24 277	95.64 179	86.11 166	91.74 118	93.14 220	79.67 134	98.89 87	89.06 130	95.46 132	94.28 255

SMA-MVS		95.20 8	95.07 12	95.59 6	98.14 35	88.48 8	96.26 46	97.28 32	85.90 167	97.67 3	98.10 10	88.41 20	99.56 12	94.66 36	99.19 1	98.71 20
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
Fast-Effi-MVS+-dtu		87.44 217	86.72 207	89.63 256	92.04 283	77.68 287	94.03 202	93.94 264	85.81 168	82.42 308	91.32 283	70.33 254	97.06 254	80.33 260	90.23 224	94.14 259

XVG-OURS-SEG-HR		89.95 137	89.45 135	91.47 175	94.00 221	81.21 190	91.87 287	96.06 142	85.78 169	88.55 163	95.73 119	74.67 195	97.27 236	88.71 134	89.64 237	95.91 185

HPM-MVS_fast		93.40 67	93.22 69	93.94 62	98.36 25	84.83 80	97.15 13	96.80 76	85.77 170	92.47 97	97.13 55	82.38 97	99.07 56	90.51 116	98.40 54	97.92 85

EI-MVSNet		89.10 162	88.86 154	89.80 248	91.84 291	78.30 268	93.70 221	95.01 216	85.73 171	87.15 189	95.28 134	79.87 128	97.21 243	83.81 197	87.36 274	93.88 273

IterMVS-LS		88.36 185	87.91 179	89.70 252	93.80 229	78.29 269	93.73 218	95.08 214	85.73 171	84.75 258	91.90 265	79.88 127	96.92 264	83.83 196	82.51 317	93.89 270
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
APD-MVS		94.24 34	94.07 44	94.75 36	98.06 39	86.90 23	95.88 80	96.94 60	85.68 173	95.05 42	97.18 52	87.31 35	99.07 56	91.90 94	98.61 48	98.28 55
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_yl		90.69 118	90.02 126	92.71 112	95.72 123	82.41 162	94.11 193	95.12 210	85.63 174	91.49 121	94.70 159	74.75 191	98.42 138	86.13 167	92.53 195	97.31 114

DCV-MVSNet		90.69 118	90.02 126	92.71 112	95.72 123	82.41 162	94.11 193	95.12 210	85.63 174	91.49 121	94.70 159	74.75 191	98.42 138	86.13 167	92.53 195	97.31 114

K. test v3		81.59 328	80.15 330	85.91 348	89.89 358	69.42 384	92.57 265	87.71 385	85.56 176	73.44 388	89.71 334	55.58 373	95.52 336	77.17 295	69.76 391	92.78 324

SixPastTwentyTwo		83.91 307	82.90 309	86.92 332	90.99 324	70.67 376	93.48 227	91.99 317	85.54 177	77.62 363	92.11 255	60.59 348	96.87 267	76.05 308	77.75 369	93.20 308

ITE_SJBPF				88.24 295	91.88 290	77.05 295		92.92 289	85.54 177	80.13 339	93.30 213	57.29 368	96.20 306	72.46 334	84.71 293	91.49 355

BH-RMVSNet		88.37 184	87.48 187	91.02 195	95.28 144	79.45 241	92.89 256	93.07 286	85.45 179	86.91 194	94.84 156	70.35 253	97.76 188	73.97 325	94.59 152	95.85 188

IterMVS-SCA-FT		85.45 277	84.53 283	88.18 297	91.71 297	76.87 297	90.19 330	92.65 299	85.40 180	81.44 321	90.54 309	66.79 297	95.00 349	81.04 245	81.05 339	92.66 327

GA-MVS		86.61 251	85.27 265	90.66 206	91.33 312	78.71 256	90.40 321	93.81 272	85.34 181	85.12 250	89.57 336	61.25 341	97.11 250	80.99 248	89.59 238	96.15 172

ACMM	84.12 9	89.14 161	88.48 165	91.12 187	94.65 181	81.22 189	95.31 109	96.12 135	85.31 182	85.92 220	94.34 172	70.19 256	98.06 172	85.65 173	88.86 249	94.08 264
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		90.64 121	90.05 123	92.40 128	93.97 223	84.46 93	93.32 234	95.46 189	85.17 183	92.25 99	94.03 183	70.59 248	98.57 120	90.97 106	94.67 148	94.18 256

xiu_mvs_v1_base		90.64 121	90.05 123	92.40 128	93.97 223	84.46 93	93.32 234	95.46 189	85.17 183	92.25 99	94.03 183	70.59 248	98.57 120	90.97 106	94.67 148	94.18 256

xiu_mvs_v1_base_debi		90.64 121	90.05 123	92.40 128	93.97 223	84.46 93	93.32 234	95.46 189	85.17 183	92.25 99	94.03 183	70.59 248	98.57 120	90.97 106	94.67 148	94.18 256

PHI-MVS		93.89 49	93.65 61	94.62 41	96.84 78	86.43 39	96.69 32	97.49 6	85.15 186	93.56 67	96.28 91	85.60 53	99.31 42	92.45 68	98.79 24	98.12 72

mvs_tets		88.06 194	87.28 193	90.38 222	90.94 328	79.88 232	95.22 120	95.66 176	85.10 187	84.21 278	93.94 191	63.53 322	97.40 226	88.50 136	88.40 257	93.87 274

tttt0517		88.61 178	87.78 181	91.11 190	94.96 161	77.81 281	95.35 107	89.69 372	85.09 188	88.05 173	94.59 168	66.93 294	98.48 125	83.27 203	92.13 200	97.03 132

XVG-ACMP-BASELINE		86.00 266	84.84 276	89.45 262	91.20 314	78.00 274	91.70 292	95.55 183	85.05 189	82.97 302	92.25 249	54.49 382	97.48 209	82.93 207	87.45 273	92.89 320

mmtdpeth		85.04 290	84.15 287	87.72 308	93.11 252	75.74 315	94.37 179	92.83 292	84.98 190	89.31 152	86.41 379	61.61 336	97.14 248	92.63 67	62.11 407	90.29 375

jajsoiax		88.24 188	87.50 186	90.48 215	90.89 332	80.14 220	95.31 109	95.65 178	84.97 191	84.24 277	94.02 186	65.31 312	97.42 218	88.56 135	88.52 253	93.89 270

testing222		84.84 294	83.32 299	89.43 263	94.15 213	75.94 311	91.09 308	89.41 377	84.90 192	85.78 223	89.44 338	52.70 389	96.28 304	70.80 345	91.57 204	96.07 179

mvsmamba		90.33 126	89.69 131	92.25 141	95.17 151	81.64 175	95.27 116	93.36 280	84.88 193	89.51 147	94.27 179	69.29 272	97.42 218	89.34 126	96.12 120	97.68 100

FA-MVS(test-final)		89.66 144	88.91 151	91.93 152	94.57 187	80.27 216	91.36 299	94.74 237	84.87 194	89.82 144	92.61 237	74.72 194	98.47 128	83.97 194	93.53 171	97.04 131

v2v482		87.84 197	87.06 197	90.17 227	90.99 324	79.23 252	94.00 206	95.13 209	84.87 194	85.53 231	92.07 259	74.45 197	97.45 213	84.71 185	81.75 329	93.85 277

v148		87.04 237	86.32 226	89.21 266	90.94 328	77.26 292	93.71 220	94.43 245	84.84 196	84.36 272	90.80 302	76.04 173	97.05 256	82.12 224	79.60 361	93.31 301

v8		87.50 216	86.71 208	89.89 242	91.37 309	79.40 242	94.50 164	95.38 198	84.81 197	83.60 292	91.33 281	76.05 172	97.42 218	82.84 210	80.51 352	92.84 322

testing11		86.44 260	85.35 263	89.69 253	94.29 205	75.40 320	91.30 301	90.53 355	84.76 198	85.06 252	90.13 322	58.95 362	97.45 213	82.08 226	91.09 212	96.21 171

BH-untuned		88.60 179	88.13 174	90.01 238	95.24 148	78.50 262	93.29 239	94.15 258	84.75 199	84.46 266	93.40 208	75.76 178	97.40 226	77.59 290	94.52 155	94.12 260

OurMVSNet-221017-0		85.35 281	84.64 280	87.49 314	90.77 336	72.59 354	94.01 204	94.40 247	84.72 200	79.62 348	93.17 218	61.91 332	96.72 270	81.99 229	81.16 335	93.16 310

dmvs_re		84.20 302	83.22 303	87.14 328	91.83 293	77.81 281	90.04 334	90.19 360	84.70 201	81.49 319	89.17 341	64.37 318	91.13 393	71.58 337	85.65 287	92.46 333

MVSFormer		91.68 100	91.30 99	92.80 107	93.86 226	83.88 109	95.96 74	95.90 155	84.66 202	91.76 116	94.91 149	77.92 154	97.30 232	89.64 123	97.11 93	97.24 118

test_djsdf		89.03 167	88.64 157	90.21 226	90.74 338	79.28 249	95.96 74	95.90 155	84.66 202	85.33 248	92.94 226	74.02 206	97.30 232	89.64 123	88.53 252	94.05 266

MVSTER		88.84 171	88.29 170	90.51 213	92.95 262	80.44 213	93.73 218	95.01 216	84.66 202	87.15 189	93.12 221	72.79 224	97.21 243	87.86 143	87.36 274	93.87 274

v7n		86.81 243	85.76 252	89.95 240	90.72 339	79.25 251	95.07 130	95.92 152	84.45 205	82.29 309	90.86 298	72.60 227	97.53 205	79.42 273	80.52 351	93.08 314

MVSMamba_PlusPlus		93.44 62	93.54 63	93.14 87	96.58 87	83.05 139	96.06 65	96.50 103	84.42 206	94.09 53	95.56 125	85.01 66	98.69 107	94.96 33	98.66 41	97.67 101

testing3		80.46 341	79.59 338	83.06 370	93.44 244	64.64 401	93.33 233	85.47 396	84.34 207	79.93 343	90.84 300	44.35 407	92.39 381	57.06 404	87.56 270	92.16 343

ET-MVSNet_ETH3D		87.51 214	85.91 245	92.32 135	93.70 235	83.93 107	92.33 274	90.94 348	84.16 208	72.09 392	92.52 239	69.90 258	95.85 323	89.20 128	88.36 258	97.17 122

CSCG		93.23 72	93.05 72	93.76 70	98.04 40	84.07 104	96.22 48	97.37 21	84.15 209	90.05 142	95.66 121	87.77 26	99.15 53	89.91 121	98.27 58	98.07 74

Baseline_NR-MVSNet		87.07 236	86.63 213	88.40 287	91.44 304	77.87 279	94.23 187	92.57 300	84.12 210	85.74 225	92.08 257	77.25 160	96.04 311	82.29 221	79.94 356	91.30 359

UniMVSNet_ETH3D		87.53 213	86.37 223	91.00 197	92.44 272	78.96 254	94.74 151	95.61 180	84.07 211	85.36 247	94.52 170	59.78 354	97.34 231	82.93 207	87.88 265	96.71 151

thisisatest0530		88.67 176	87.61 184	91.86 158	94.87 168	80.07 223	94.63 158	89.90 369	84.00 212	88.46 165	93.78 200	66.88 296	98.46 129	83.30 202	92.65 192	97.06 129

ab-mvs		89.41 154	88.35 166	92.60 118	95.15 154	82.65 156	92.20 279	95.60 181	83.97 213	88.55 163	93.70 204	74.16 204	98.21 154	82.46 217	89.37 240	96.94 139

GeoE		90.05 133	89.43 137	91.90 157	95.16 152	80.37 215	95.80 86	94.65 241	83.90 214	87.55 184	94.75 158	78.18 152	97.62 200	81.28 242	93.63 168	97.71 99

FMVSNet3		87.40 219	86.11 235	91.30 181	93.79 231	83.64 116	94.20 188	94.81 233	83.89 215	84.37 269	91.87 266	68.45 284	96.56 284	78.23 284	85.36 288	93.70 289

pm-mvs1		86.61 251	85.54 256	89.82 245	91.44 304	80.18 218	95.28 115	94.85 229	83.84 216	81.66 318	92.62 236	72.45 230	96.48 290	79.67 267	78.06 367	92.82 323

tt0805		86.92 240	85.74 254	90.48 215	92.22 276	79.98 230	95.63 98	94.88 227	83.83 217	84.74 259	92.80 232	57.61 367	97.67 193	85.48 176	84.42 295	93.79 279

v10		87.25 226	86.38 222	89.85 243	91.19 315	79.50 239	94.48 165	95.45 192	83.79 218	83.62 291	91.19 286	75.13 186	97.42 218	81.94 230	80.60 347	92.63 328

testgi		80.94 339	80.20 329	83.18 368	87.96 382	66.29 394	91.28 302	90.70 354	83.70 219	78.12 357	92.84 228	51.37 391	90.82 395	63.34 386	82.46 319	92.43 334

V42		87.68 202	86.86 202	90.15 229	90.58 343	80.14 220	94.24 186	95.28 203	83.66 220	85.67 226	91.33 281	74.73 193	97.41 224	84.43 189	81.83 327	92.89 320

ZD-MVS					98.15 34	86.62 33		97.07 50	83.63 221	94.19 51	96.91 64	87.57 31	99.26 45	91.99 88	98.44 53

GBi-Net		87.26 224	85.98 241	91.08 191	94.01 218	83.10 134	95.14 127	94.94 219	83.57 222	84.37 269	91.64 271	66.59 301	96.34 301	78.23 284	85.36 288	93.79 279

test1		87.26 224	85.98 241	91.08 191	94.01 218	83.10 134	95.14 127	94.94 219	83.57 222	84.37 269	91.64 271	66.59 301	96.34 301	78.23 284	85.36 288	93.79 279

FMVSNet2		87.19 232	85.82 248	91.30 181	94.01 218	83.67 114	94.79 148	94.94 219	83.57 222	83.88 284	92.05 260	66.59 301	96.51 288	77.56 291	85.01 291	93.73 287

SCA		86.32 263	85.18 267	89.73 251	92.15 278	76.60 302	91.12 307	91.69 325	83.53 225	85.50 234	88.81 348	66.79 297	96.48 290	76.65 299	90.35 222	96.12 175

PVSNet_BlendedMVS		89.98 135	89.70 130	90.82 203	96.12 102	81.25 187	93.92 211	96.83 71	83.49 226	89.10 155	92.26 248	81.04 118	98.85 92	86.72 161	87.86 266	92.35 338

DPM-MVS		92.58 84	91.74 94	95.08 15	96.19 99	89.31 5	92.66 262	96.56 98	83.44 227	91.68 119	95.04 146	86.60 42	98.99 73	85.60 174	97.92 75	96.93 140

test-LLR		85.87 269	85.41 259	87.25 322	90.95 326	71.67 364	89.55 342	89.88 370	83.41 228	84.54 263	87.95 362	67.25 290	95.11 346	81.82 233	93.37 178	94.97 219

test0.0.03 1		82.41 319	81.69 315	84.59 360	88.23 377	72.89 346	90.24 326	87.83 384	83.41 228	79.86 344	89.78 332	67.25 290	88.99 405	65.18 379	83.42 309	91.90 347

ETVMVS		84.43 299	82.92 308	88.97 275	94.37 200	74.67 325	91.23 305	88.35 381	83.37 230	86.06 218	89.04 343	55.38 376	95.67 332	67.12 368	91.34 206	96.58 156

v1144		87.61 210	86.79 206	90.06 234	91.01 323	79.34 245	93.95 208	95.42 197	83.36 231	85.66 227	91.31 284	74.98 189	97.42 218	83.37 201	82.06 323	93.42 299

PVSNet_Blended_VisFu		91.38 103	90.91 108	92.80 107	96.39 94	83.17 131	94.87 142	96.66 90	83.29 232	89.27 153	94.46 171	80.29 123	99.17 50	87.57 147	95.37 135	96.05 182

IB-MVS	80.51 15	85.24 285	83.26 301	91.19 185	92.13 280	79.86 233	91.75 290	91.29 338	83.28 233	80.66 331	88.49 354	61.28 340	98.46 129	80.99 248	79.46 362	95.25 211
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
IterMVS		84.88 292	83.98 292	87.60 310	91.44 304	76.03 310	90.18 331	92.41 302	83.24 234	81.06 327	90.42 314	66.60 300	94.28 358	79.46 269	80.98 344	92.48 331
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_cas_vis1_n_1920		88.83 174	88.85 155	88.78 277	91.15 319	76.72 300	93.85 214	94.93 223	83.23 235	92.81 84	96.00 103	61.17 345	94.45 352	91.67 98	94.84 145	95.17 213

Fast-Effi-MVS+		89.41 154	88.64 157	91.71 166	94.74 173	80.81 204	93.54 225	95.10 212	83.11 236	86.82 200	90.67 308	79.74 130	97.75 191	80.51 257	93.55 170	96.57 157

WTY-MVS		89.60 146	88.92 150	91.67 167	95.47 138	81.15 192	92.38 270	94.78 235	83.11 236	89.06 157	94.32 174	78.67 145	96.61 279	81.57 239	90.89 215	97.24 118

LTVRE_ROB	82.13 13	86.26 264	84.90 274	90.34 224	94.44 197	81.50 178	92.31 276	94.89 225	83.03 238	79.63 347	92.67 234	69.69 262	97.79 186	71.20 339	86.26 283	91.72 349
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
AUN-MVS		87.78 200	86.54 218	91.48 174	94.82 172	81.05 196	93.91 213	93.93 265	83.00 239	86.93 192	93.53 206	69.50 266	97.67 193	86.14 165	77.12 374	95.73 196

UnsupCasMVSNet_eth		80.07 345	78.27 352	85.46 352	85.24 398	72.63 353	88.45 362	94.87 228	82.99 240	71.64 395	88.07 361	56.34 371	91.75 388	73.48 330	63.36 405	92.01 345

XXY-MVS		87.65 204	86.85 203	90.03 235	92.14 279	80.60 210	93.76 217	95.23 205	82.94 241	84.60 261	94.02 186	74.27 199	95.49 340	81.04 245	83.68 304	94.01 268

mvs_anonymous		89.37 158	89.32 141	89.51 261	93.47 242	74.22 331	91.65 294	94.83 231	82.91 242	85.45 237	93.79 199	81.23 117	96.36 300	86.47 163	94.09 161	97.94 82

BH-w/o		87.57 212	87.05 198	89.12 269	94.90 167	77.90 277	92.41 268	93.51 277	82.89 243	83.70 288	91.34 280	75.75 179	97.07 253	75.49 310	93.49 173	92.39 336

AdaColmap		89.89 140	89.07 146	92.37 132	97.41 65	83.03 140	94.42 172	95.92 152	82.81 244	86.34 211	94.65 164	73.89 208	99.02 64	80.69 253	95.51 128	95.05 217

dmvs_testset		74.57 368	75.81 366	70.86 394	87.72 385	40.47 429	87.05 380	77.90 419	82.75 245	71.15 397	85.47 387	67.98 287	84.12 416	45.26 413	76.98 376	88.00 397

TransMVSNet (Re)		84.43 299	83.06 306	88.54 285	91.72 296	78.44 263	95.18 124	92.82 294	82.73 246	79.67 346	92.12 253	73.49 214	95.96 317	71.10 343	68.73 397	91.21 361

DP-MVS Recon		91.95 93	91.28 100	93.96 61	98.33 27	85.92 57	94.66 157	96.66 90	82.69 247	90.03 143	95.82 114	82.30 101	99.03 61	84.57 186	96.48 113	96.91 142

v1192		87.25 226	86.33 225	90.00 239	90.76 337	79.04 253	93.80 215	95.48 188	82.57 248	85.48 235	91.18 288	73.38 219	97.42 218	82.30 220	82.06 323	93.53 293

PC_three_1452									82.47 249	97.09 12	97.07 58	92.72 1	98.04 173	92.70 66	99.02 12	98.86 11

API-MVS		90.66 120	90.07 122	92.45 127	96.36 95	84.57 87	96.06 65	95.22 207	82.39 250	89.13 154	94.27 179	80.32 122	98.46 129	80.16 262	96.71 106	94.33 253

tfpnnormal		84.72 296	83.23 302	89.20 267	92.79 265	80.05 225	94.48 165	95.81 162	82.38 251	81.08 326	91.21 285	69.01 277	96.95 262	61.69 391	80.59 348	90.58 374

MAR-MVS		90.30 127	89.37 139	93.07 93	96.61 84	84.48 92	95.68 92	95.67 174	82.36 252	87.85 176	92.85 227	76.63 168	98.80 96	80.01 263	96.68 107	95.91 185
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
baseline2		86.50 257	85.39 260	89.84 244	91.12 320	76.70 301	91.88 286	88.58 379	82.35 253	79.95 342	90.95 296	73.42 217	97.63 199	80.27 261	89.95 229	95.19 212

UBG		85.51 276	84.57 282	88.35 289	94.21 209	71.78 362	90.07 333	89.66 374	82.28 254	85.91 221	89.01 344	61.30 339	97.06 254	76.58 302	92.06 201	96.22 169

TAMVS		89.21 160	88.29 170	91.96 150	93.71 233	82.62 157	93.30 238	94.19 256	82.22 255	87.78 179	93.94 191	78.83 141	96.95 262	77.70 289	92.98 186	96.32 164

ACMH+	81.04 14	85.05 288	83.46 298	89.82 245	94.66 180	79.37 243	94.44 170	94.12 261	82.19 256	78.04 358	92.82 230	58.23 364	97.54 204	73.77 328	82.90 315	92.54 329

ACMH	80.38 17	85.36 280	83.68 295	90.39 220	94.45 196	80.63 208	94.73 152	94.85 229	82.09 257	77.24 364	92.65 235	60.01 352	97.58 201	72.25 335	84.87 292	92.96 317
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
eth_miper_zixun_eth		86.50 257	85.77 251	88.68 282	91.94 286	75.81 314	90.47 320	94.89 225	82.05 258	84.05 280	90.46 312	75.96 174	96.77 269	82.76 213	79.36 363	93.46 298

anonymousdsp		87.84 197	87.09 196	90.12 231	89.13 366	80.54 211	94.67 156	95.55 183	82.05 258	83.82 285	92.12 253	71.47 237	97.15 245	87.15 154	87.80 269	92.67 326

PVSNet_Blended		90.73 117	90.32 116	91.98 148	96.12 102	81.25 187	92.55 266	96.83 71	82.04 260	89.10 155	92.56 238	81.04 118	98.85 92	86.72 161	95.91 122	95.84 189

c3_l		87.14 234	86.50 220	89.04 272	92.20 277	77.26 292	91.22 306	94.70 239	82.01 261	84.34 273	90.43 313	78.81 142	96.61 279	83.70 199	81.09 338	93.25 304

CDS-MVSNet		89.45 152	88.51 161	92.29 138	93.62 238	83.61 119	93.01 251	94.68 240	81.95 262	87.82 178	93.24 216	78.69 144	96.99 259	80.34 259	93.23 182	96.28 167
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v144192		87.19 232	86.35 224	89.74 249	90.64 341	78.24 270	93.92 211	95.43 195	81.93 263	85.51 233	91.05 294	74.21 202	97.45 213	82.86 209	81.56 331	93.53 293

PAPR		90.02 134	89.27 144	92.29 138	95.78 121	80.95 200	92.68 261	96.22 126	81.91 264	86.66 202	93.75 203	82.23 103	98.44 135	79.40 274	94.79 146	97.48 110

v1921920		86.97 239	86.06 238	89.69 253	90.53 346	78.11 273	93.80 215	95.43 195	81.90 265	85.33 248	91.05 294	72.66 225	97.41 224	82.05 228	81.80 328	93.53 293

mamv4		90.92 111	91.78 93	88.33 292	95.67 127	70.75 375	92.92 255	96.02 146	81.90 265	88.11 168	95.34 132	85.88 51	96.97 260	95.22 31	95.01 142	97.26 117

CPTT-MVS		91.99 92	91.80 92	92.55 122	98.24 31	81.98 169	96.76 30	96.49 104	81.89 267	90.24 136	96.44 88	78.59 146	98.61 117	89.68 122	97.85 77	97.06 129

train_agg		93.44 62	93.08 71	94.52 44	97.53 61	86.49 37	94.07 198	96.78 77	81.86 268	92.77 86	96.20 94	87.63 29	99.12 54	92.14 82	98.69 35	97.94 82

test_8					97.49 63	86.30 45	94.02 203	96.76 80	81.86 268	92.70 90	96.20 94	87.63 29	99.02 64

cl____		86.52 256	85.78 249	88.75 279	92.03 284	76.46 304	90.74 314	94.30 251	81.83 270	83.34 298	90.78 303	75.74 181	96.57 282	81.74 236	81.54 332	93.22 306

DIV-MVS_self_test		86.53 255	85.78 249	88.75 279	92.02 285	76.45 305	90.74 314	94.30 251	81.83 270	83.34 298	90.82 301	75.75 179	96.57 282	81.73 237	81.52 333	93.24 305

Syy-MVS		80.07 345	79.78 333	80.94 379	91.92 287	59.93 411	89.75 340	87.40 388	81.72 272	78.82 352	87.20 372	66.29 305	91.29 391	47.06 412	87.84 267	91.60 352

myMVS_eth3d		79.67 350	78.79 349	82.32 376	91.92 287	64.08 402	89.75 340	87.40 388	81.72 272	78.82 352	87.20 372	45.33 405	91.29 391	59.09 399	87.84 267	91.60 352

v1240		86.78 245	85.85 247	89.56 257	90.45 347	77.79 283	93.61 223	95.37 200	81.65 274	85.43 240	91.15 290	71.50 236	97.43 217	81.47 241	82.05 325	93.47 297

FMVSNet1		85.85 270	84.11 288	91.08 191	92.81 264	83.10 134	95.14 127	94.94 219	81.64 275	82.68 305	91.64 271	59.01 361	96.34 301	75.37 312	83.78 301	93.79 279

PatchmatchNet		85.85 270	84.70 278	89.29 265	91.76 295	75.54 317	88.49 360	91.30 337	81.63 276	85.05 253	88.70 352	71.71 233	96.24 305	74.61 322	89.05 247	96.08 178
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WBMVS		84.97 291	84.18 285	87.34 318	94.14 214	71.62 366	90.20 329	92.35 303	81.61 277	84.06 279	90.76 304	61.82 333	96.52 287	78.93 277	83.81 300	93.89 270

TEST9					97.53 61	86.49 37	94.07 198	96.78 77	81.61 277	92.77 86	96.20 94	87.71 28	99.12 54

sss		88.93 170	88.26 172	90.94 201	94.05 216	80.78 205	91.71 291	95.38 198	81.55 279	88.63 162	93.91 195	75.04 188	95.47 341	82.47 216	91.61 203	96.57 157

HY-MVS	83.01 12	89.03 167	87.94 178	92.29 138	94.86 169	82.77 147	92.08 284	94.49 243	81.52 280	86.93 192	92.79 233	78.32 151	98.23 151	79.93 264	90.55 218	95.88 187

CNLPA		89.07 165	87.98 176	92.34 134	96.87 77	84.78 82	94.08 197	93.24 281	81.41 281	84.46 266	95.13 144	75.57 183	96.62 276	77.21 294	93.84 166	95.61 201

EPMVS		83.90 308	82.70 312	87.51 312	90.23 351	72.67 350	88.62 359	81.96 407	81.37 282	85.01 254	88.34 356	66.31 304	94.45 352	75.30 313	87.12 277	95.43 204

cl22		86.78 245	85.98 241	89.18 268	92.34 274	77.62 288	90.84 313	94.13 260	81.33 283	83.97 283	90.15 321	73.96 207	96.60 281	84.19 191	82.94 312	93.33 300

miper_ehance_all_eth		87.22 229	86.62 214	89.02 273	92.13 280	77.40 291	90.91 312	94.81 233	81.28 284	84.32 274	90.08 324	79.26 137	96.62 276	83.81 197	82.94 312	93.04 315

IU-MVS					98.77 5	86.00 50		96.84 70	81.26 285	97.26 8				95.50 27	99.13 3	99.03 8

CL-MVSNet_self_test		81.74 325	80.53 323	85.36 353	85.96 392	72.45 356	90.25 324	93.07 286	81.24 286	79.85 345	87.29 371	70.93 243	92.52 380	66.95 369	69.23 393	91.11 365

test20.03		79.95 347	79.08 346	82.55 372	85.79 394	67.74 391	91.09 308	91.08 341	81.23 287	74.48 384	89.96 329	61.63 334	90.15 397	60.08 395	76.38 377	89.76 379

miper_lstm_enhance		85.27 284	84.59 281	87.31 319	91.28 313	74.63 326	87.69 373	94.09 262	81.20 288	81.36 323	89.85 331	74.97 190	94.30 357	81.03 247	79.84 359	93.01 316

TR-MVS		86.78 245	85.76 252	89.82 245	94.37 200	78.41 264	92.47 267	92.83 292	81.11 289	86.36 209	92.40 242	68.73 281	97.48 209	73.75 329	89.85 232	93.57 292

VDDNet		89.56 148	88.49 164	92.76 109	95.07 155	82.09 166	96.30 41	93.19 283	81.05 290	91.88 111	96.86 66	61.16 346	98.33 145	88.43 137	92.49 197	97.84 91

tpm		84.73 295	84.02 290	86.87 335	90.33 348	68.90 385	89.06 353	89.94 367	80.85 291	85.75 224	89.86 330	68.54 283	95.97 316	77.76 288	84.05 299	95.75 193

D2MVS		85.90 268	85.09 269	88.35 289	90.79 335	77.42 290	91.83 288	95.70 172	80.77 292	80.08 340	90.02 326	66.74 299	96.37 298	81.88 232	87.97 264	91.26 360

FE-MVS		87.40 219	86.02 239	91.57 170	94.56 188	79.69 237	90.27 322	93.72 274	80.57 293	88.80 160	91.62 275	65.32 311	98.59 119	74.97 318	94.33 160	96.44 160

mvs5depth		80.98 337	79.15 345	86.45 340	84.57 400	73.29 342	87.79 369	91.67 326	80.52 294	82.20 313	89.72 333	55.14 379	95.93 318	73.93 327	66.83 399	90.12 377

Anonymous202405211		87.68 202	86.13 233	92.31 136	96.66 82	80.74 206	94.87 142	91.49 333	80.47 295	89.46 150	95.44 128	54.72 381	98.23 151	82.19 223	89.89 230	97.97 80

jason		90.80 114	90.10 121	92.90 102	93.04 257	83.53 120	93.08 248	94.15 258	80.22 296	91.41 123	94.91 149	76.87 162	97.93 182	90.28 118	96.90 100	97.24 118
jason: jason.
thisisatest0515		87.33 222	85.99 240	91.37 179	93.49 241	79.55 238	90.63 317	89.56 376	80.17 297	87.56 183	90.86 298	67.07 293	98.28 149	81.50 240	93.02 185	96.29 166

tpmrst		85.35 281	84.99 270	86.43 341	90.88 333	67.88 389	88.71 357	91.43 335	80.13 298	86.08 217	88.80 350	73.05 221	96.02 313	82.48 215	83.40 310	95.40 205

CDPH-MVS		92.83 80	92.30 86	94.44 45	97.79 52	86.11 49	94.06 200	96.66 90	80.09 299	92.77 86	96.63 80	86.62 40	99.04 60	87.40 149	98.66 41	98.17 67

PM-MVS		78.11 359	76.12 363	84.09 366	83.54 403	70.08 380	88.97 355	85.27 398	79.93 300	74.73 382	86.43 378	34.70 415	93.48 370	79.43 272	72.06 387	88.72 392

UWE-MVS		83.69 311	83.09 304	85.48 351	93.06 255	65.27 399	90.92 311	86.14 391	79.90 301	86.26 213	90.72 307	57.17 369	95.81 326	71.03 344	92.62 193	95.35 208

lupinMVS		90.92 111	90.21 117	93.03 94	93.86 226	83.88 109	92.81 259	93.86 269	79.84 302	91.76 116	94.29 176	77.92 154	98.04 173	90.48 117	97.11 93	97.17 122

PatchMatch-RL		86.77 248	85.54 256	90.47 218	95.88 117	82.71 153	90.54 319	92.31 306	79.82 303	84.32 274	91.57 279	68.77 280	96.39 297	73.16 331	93.48 175	92.32 339

PLC	84.53 7	89.06 166	88.03 175	92.15 142	97.27 71	82.69 154	94.29 182	95.44 194	79.71 304	84.01 282	94.18 182	76.68 167	98.75 101	77.28 293	93.41 176	95.02 218
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
F-COLMAP		87.95 195	86.80 205	91.40 177	96.35 96	80.88 202	94.73 152	95.45 192	79.65 305	82.04 315	94.61 165	71.13 239	98.50 123	76.24 306	91.05 213	94.80 231

test_vis1_n		86.56 254	86.49 221	86.78 337	88.51 371	72.69 349	94.68 155	93.78 273	79.55 306	90.70 130	95.31 133	48.75 397	93.28 373	93.15 55	93.99 162	94.38 252

MIMVSNet		82.59 318	80.53 323	88.76 278	91.51 302	78.32 267	86.57 383	90.13 362	79.32 307	80.70 330	88.69 353	52.98 388	93.07 377	66.03 376	88.86 249	94.90 226

KD-MVS_2432*1600		78.50 357	76.02 364	85.93 346	86.22 390	74.47 328	84.80 395	92.33 304	79.29 308	76.98 366	85.92 383	53.81 386	93.97 362	67.39 366	57.42 412	89.36 382

miper_refine_blended		78.50 357	76.02 364	85.93 346	86.22 390	74.47 328	84.80 395	92.33 304	79.29 308	76.98 366	85.92 383	53.81 386	93.97 362	67.39 366	57.42 412	89.36 382

test-mter		84.54 298	83.64 296	87.25 322	90.95 326	71.67 364	89.55 342	89.88 370	79.17 310	84.54 263	87.95 362	55.56 374	95.11 346	81.82 233	93.37 178	94.97 219

miper_enhance_ethall		86.90 241	86.18 231	89.06 271	91.66 300	77.58 289	90.22 328	94.82 232	79.16 311	84.48 265	89.10 342	79.19 139	96.66 274	84.06 192	82.94 312	92.94 318

MDA-MVSNet-bldmvs		78.85 356	76.31 361	86.46 339	89.76 359	73.88 334	88.79 356	90.42 356	79.16 311	59.18 411	88.33 357	60.20 350	94.04 360	62.00 390	68.96 395	91.48 356

WB-MVSnew		83.77 309	83.28 300	85.26 356	91.48 303	71.03 371	91.89 285	87.98 382	78.91 313	84.78 257	90.22 317	69.11 276	94.02 361	64.70 382	90.44 219	90.71 369

tpmvs		83.35 314	82.07 313	87.20 326	91.07 322	71.00 373	88.31 363	91.70 324	78.91 313	80.49 334	87.18 374	69.30 271	97.08 251	68.12 364	83.56 306	93.51 296

原ACMM1				92.01 144	97.34 67	81.05 196		96.81 75	78.89 315	90.45 133	95.92 108	82.65 94	98.84 94	80.68 254	98.26 59	96.14 173

MSDG		84.86 293	83.09 304	90.14 230	93.80 229	80.05 225	89.18 351	93.09 285	78.89 315	78.19 356	91.91 264	65.86 310	97.27 236	68.47 359	88.45 255	93.11 312

UWE-MVS-28		78.98 355	78.38 351	80.80 380	88.18 380	60.66 410	90.65 316	78.51 414	78.84 317	77.93 360	90.93 297	59.08 360	89.02 404	50.96 409	90.33 223	92.72 325

PAPM		86.68 250	85.39 260	90.53 210	93.05 256	79.33 248	89.79 338	94.77 236	78.82 318	81.95 316	93.24 216	76.81 163	97.30 232	66.94 370	93.16 183	94.95 225

PVSNet	78.82 18	85.55 275	84.65 279	88.23 296	94.72 176	71.93 358	87.12 379	92.75 296	78.80 319	84.95 255	90.53 310	64.43 317	96.71 272	74.74 320	93.86 165	96.06 181

MVP-Stereo		85.97 267	84.86 275	89.32 264	90.92 330	82.19 165	92.11 282	94.19 256	78.76 320	78.77 355	91.63 274	68.38 285	96.56 284	75.01 317	93.95 163	89.20 387
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
OpenMVS	83.78 11	88.74 175	87.29 192	93.08 91	92.70 266	85.39 71	96.57 35	96.43 106	78.74 321	80.85 328	96.07 101	69.64 263	99.01 66	78.01 287	96.65 108	94.83 229

KD-MVS_self_test		80.20 344	79.24 341	83.07 369	85.64 396	65.29 398	91.01 310	93.93 265	78.71 322	76.32 370	86.40 380	59.20 359	92.93 378	72.59 333	69.35 392	91.00 368

MDTV_nov1_ep13			83.56 297		91.69 299	69.93 381	87.75 372	91.54 331	78.60 323	84.86 256	88.90 347	69.54 265	96.03 312	70.25 347	88.93 248

test_fmvs1_n		87.03 238	87.04 199	86.97 330	89.74 360	71.86 359	94.55 162	94.43 245	78.47 324	91.95 109	95.50 127	51.16 392	93.81 365	93.02 59	94.56 153	95.26 210

Patchmatch-RL test		81.67 326	79.96 332	86.81 336	85.42 397	71.23 368	82.17 407	87.50 387	78.47 324	77.19 365	82.50 401	70.81 245	93.48 370	82.66 214	72.89 385	95.71 197

QAPM		89.51 149	88.15 173	93.59 76	94.92 164	84.58 86	96.82 29	96.70 88	78.43 326	83.41 296	96.19 97	73.18 220	99.30 43	77.11 296	96.54 110	96.89 143

1314		87.51 214	86.57 216	90.34 224	92.42 273	79.74 236	92.63 263	95.35 202	78.35 327	80.14 338	91.62 275	74.05 205	97.15 245	81.05 244	93.53 171	94.12 260

test_fmvs1		87.34 221	87.56 185	86.68 338	90.59 342	71.80 361	94.01 204	94.04 263	78.30 328	91.97 107	95.22 137	56.28 372	93.71 367	92.89 60	94.71 147	94.52 242

CR-MVSNet		85.35 281	83.76 294	90.12 231	90.58 343	79.34 245	85.24 392	91.96 320	78.27 329	85.55 229	87.87 365	71.03 241	95.61 333	73.96 326	89.36 241	95.40 205

USDC		82.76 315	81.26 320	87.26 321	91.17 316	74.55 327	89.27 348	93.39 279	78.26 330	75.30 378	92.08 257	54.43 383	96.63 275	71.64 336	85.79 286	90.61 371

new-patchmatchnet		76.41 365	75.17 367	80.13 381	82.65 407	59.61 412	87.66 374	91.08 341	78.23 331	69.85 399	83.22 395	54.76 380	91.63 390	64.14 385	64.89 403	89.16 388

1112_ss		88.42 182	87.33 191	91.72 165	94.92 164	80.98 198	92.97 253	94.54 242	78.16 332	83.82 285	93.88 196	78.78 143	97.91 183	79.45 270	89.41 239	96.26 168

MIMVSNet1		79.38 352	77.28 355	85.69 350	86.35 389	73.67 337	91.61 295	92.75 296	78.11 333	72.64 391	88.12 360	48.16 398	91.97 387	60.32 394	77.49 371	91.43 357

test_fmvs2		83.98 304	84.03 289	83.83 367	87.16 386	67.53 393	93.93 210	92.89 290	77.62 334	86.89 197	93.53 206	47.18 401	92.02 385	90.54 114	86.51 281	91.93 346

MS-PatchMatch		85.05 288	84.16 286	87.73 307	91.42 307	78.51 261	91.25 304	93.53 276	77.50 335	80.15 337	91.58 277	61.99 331	95.51 337	75.69 309	94.35 159	89.16 388

AllTest		83.42 312	81.39 318	89.52 259	95.01 157	77.79 283	93.12 245	90.89 350	77.41 336	76.12 372	93.34 209	54.08 384	97.51 207	68.31 361	84.27 297	93.26 302

TestCases				89.52 259	95.01 157	77.79 283		90.89 350	77.41 336	76.12 372	93.34 209	54.08 384	97.51 207	68.31 361	84.27 297	93.26 302

TESTMET0.1,1		83.74 310	82.85 310	86.42 342	89.96 356	71.21 369	89.55 342	87.88 383	77.41 336	83.37 297	87.31 370	56.71 370	93.65 369	80.62 255	92.85 190	94.40 251

gm-plane-assit					89.60 363	68.00 387			77.28 339		88.99 345		97.57 202	79.44 271

EG-PatchMatch MVS		82.37 320	80.34 326	88.46 286	90.27 349	79.35 244	92.80 260	94.33 250	77.14 340	73.26 389	90.18 320	47.47 400	96.72 270	70.25 347	87.32 276	89.30 384

FMVSNet5		81.52 330	79.60 337	87.27 320	91.17 316	77.95 275	91.49 297	92.26 309	76.87 341	76.16 371	87.91 364	51.67 390	92.34 382	67.74 365	81.16 335	91.52 354

mvsany_test1		85.42 279	85.30 264	85.77 349	87.95 383	75.41 319	87.61 376	80.97 409	76.82 342	88.68 161	95.83 113	77.44 159	90.82 395	85.90 170	86.51 281	91.08 367

our_test_3		81.93 322	80.46 325	86.33 343	88.46 374	73.48 340	88.46 361	91.11 340	76.46 343	76.69 368	88.25 358	66.89 295	94.36 355	68.75 357	79.08 365	91.14 363

TDRefinement		79.81 348	77.34 354	87.22 325	79.24 414	75.48 318	93.12 245	92.03 315	76.45 344	75.01 379	91.58 277	49.19 396	96.44 294	70.22 349	69.18 394	89.75 380

LF4IMVS		80.37 343	79.07 347	84.27 364	86.64 388	69.87 383	89.39 347	91.05 343	76.38 345	74.97 380	90.00 327	47.85 399	94.25 359	74.55 323	80.82 346	88.69 393

TAPA-MVS	84.62 6	88.16 190	87.01 200	91.62 168	96.64 83	80.65 207	94.39 175	96.21 129	76.38 345	86.19 215	95.44 128	79.75 129	98.08 170	62.75 389	95.29 137	96.13 174
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dp		81.47 331	80.23 328	85.17 357	89.92 357	65.49 397	86.74 381	90.10 363	76.30 347	81.10 325	87.12 375	62.81 327	95.92 319	68.13 363	79.88 357	94.09 263

CostFormer		85.77 273	84.94 273	88.26 294	91.16 318	72.58 355	89.47 346	91.04 344	76.26 348	86.45 207	89.97 328	70.74 246	96.86 268	82.35 219	87.07 279	95.34 209

RPSCF		85.07 287	84.27 284	87.48 315	92.91 263	70.62 377	91.69 293	92.46 301	76.20 349	82.67 306	95.22 137	63.94 320	97.29 235	77.51 292	85.80 285	94.53 241

Test_1112_low_res		87.65 204	86.51 219	91.08 191	94.94 163	79.28 249	91.77 289	94.30 251	76.04 350	83.51 294	92.37 243	77.86 156	97.73 192	78.69 279	89.13 246	96.22 169

pmmvs4		85.43 278	83.86 293	90.16 228	90.02 355	82.97 144	90.27 322	92.67 298	75.93 351	80.73 329	91.74 269	71.05 240	95.73 331	78.85 278	83.46 308	91.78 348

LS3D		87.89 196	86.32 226	92.59 119	96.07 108	82.92 145	95.23 118	94.92 224	75.66 352	82.89 303	95.98 105	72.48 228	99.21 48	68.43 360	95.23 140	95.64 198

pmmvs5		84.21 301	82.84 311	88.34 291	88.95 368	76.94 296	92.41 268	91.91 322	75.63 353	80.28 335	91.18 288	64.59 316	95.57 334	77.09 297	83.47 307	92.53 330

Anonymous20240521		80.44 342	79.21 342	84.11 365	85.75 395	67.89 388	92.86 258	93.23 282	75.61 354	75.59 377	87.47 369	50.03 393	94.33 356	71.14 342	81.21 334	90.12 377

pmmvs-eth3d		80.97 338	78.72 350	87.74 306	84.99 399	79.97 231	90.11 332	91.65 327	75.36 355	73.51 387	86.03 382	59.45 356	93.96 364	75.17 314	72.21 386	89.29 386

ppachtmachnet_test		81.84 323	80.07 331	87.15 327	88.46 374	74.43 330	89.04 354	92.16 311	75.33 356	77.75 361	88.99 345	66.20 306	95.37 342	65.12 380	77.60 370	91.65 350

test_0402		81.30 334	79.17 344	87.67 309	93.19 249	78.17 271	92.98 252	91.71 323	75.25 357	76.02 374	90.31 315	59.23 358	96.37 298	50.22 410	83.63 305	88.47 395

COLMAP_ROB	80.39 16	83.96 305	82.04 314	89.74 249	95.28 144	79.75 235	94.25 184	92.28 307	75.17 358	78.02 359	93.77 201	58.60 363	97.84 185	65.06 381	85.92 284	91.63 351
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TinyColmap		79.76 349	77.69 353	85.97 345	91.71 297	73.12 343	89.55 342	90.36 358	75.03 359	72.03 393	90.19 319	46.22 404	96.19 308	63.11 387	81.03 340	88.59 394

DP-MVS		87.25 226	85.36 262	92.90 102	97.65 58	83.24 128	94.81 147	92.00 316	74.99 360	81.92 317	95.00 147	72.66 225	99.05 58	66.92 372	92.33 198	96.40 161

PatchT		82.68 317	81.27 319	86.89 334	90.09 353	70.94 374	84.06 399	90.15 361	74.91 361	85.63 228	83.57 394	69.37 267	94.87 351	65.19 378	88.50 254	94.84 228

CHOSEN 280x420		85.15 286	83.99 291	88.65 283	92.47 270	78.40 265	79.68 414	92.76 295	74.90 362	81.41 322	89.59 335	69.85 261	95.51 337	79.92 265	95.29 137	92.03 344

gg-mvs-nofinetune		81.77 324	79.37 339	88.99 274	90.85 334	77.73 286	86.29 384	79.63 412	74.88 363	83.19 301	69.05 415	60.34 349	96.11 310	75.46 311	94.64 151	93.11 312

pmmvs6		83.42 312	81.60 316	88.87 276	88.01 381	77.87 279	94.96 136	94.24 255	74.67 364	78.80 354	91.09 293	60.17 351	96.49 289	77.06 298	75.40 381	92.23 341

CHOSEN 1792x2688		88.84 171	87.69 182	92.30 137	96.14 100	81.42 184	90.01 335	95.86 160	74.52 365	87.41 185	93.94 191	75.46 184	98.36 140	80.36 258	95.53 127	97.12 127

MDA-MVSNet_test_wron		79.21 354	77.19 357	85.29 354	88.22 378	72.77 348	85.87 386	90.06 364	74.34 366	62.62 408	87.56 368	66.14 307	91.99 386	66.90 373	73.01 383	91.10 366

YYNet1		79.22 353	77.20 356	85.28 355	88.20 379	72.66 351	85.87 386	90.05 366	74.33 367	62.70 406	87.61 367	66.09 308	92.03 384	66.94 370	72.97 384	91.15 362

mvsany_test3		74.95 367	73.26 371	80.02 382	74.61 418	63.16 406	85.53 390	78.42 415	74.16 368	74.89 381	86.46 377	36.02 414	89.09 403	82.39 218	66.91 398	87.82 399

Anonymous20240529		88.09 192	86.59 215	92.58 120	96.53 90	81.92 171	95.99 71	95.84 161	74.11 369	89.06 157	95.21 139	61.44 338	98.81 95	83.67 200	87.47 271	97.01 135

test_fmvs3		77.67 361	77.16 358	79.22 383	79.52 413	61.14 408	92.34 273	91.64 328	73.98 370	78.86 351	86.59 376	27.38 419	87.03 407	88.12 141	75.97 379	89.50 381

无先验							93.28 240	96.26 121	73.95 371				99.05 58	80.56 256		96.59 155

Anonymous20231211		86.59 253	85.13 268	90.98 200	96.52 91	81.50 178	96.14 56	96.16 130	73.78 372	83.65 290	92.15 251	63.26 325	97.37 230	82.82 211	81.74 330	94.06 265

Anonymous20231206		81.03 336	79.77 335	84.82 359	87.85 384	70.26 379	91.42 298	92.08 313	73.67 373	77.75 361	89.25 340	62.43 329	93.08 376	61.50 392	82.00 326	91.12 364

PCF-MVS	84.11 10	87.74 201	86.08 237	92.70 114	94.02 217	84.43 96	89.27 348	95.87 159	73.62 374	84.43 268	94.33 173	78.48 149	98.86 90	70.27 346	94.45 157	94.81 230
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVS		67.92 376	67.49 378	69.21 398	81.09 409	41.17 428	88.03 366	78.00 418	73.50 375	62.63 407	83.11 398	63.94 320	86.52 409	25.66 424	51.45 416	79.94 409

HyFIR lowres test		88.09 192	86.81 204	91.93 152	96.00 111	80.63 208	90.01 335	95.79 164	73.42 376	87.68 181	92.10 256	73.86 209	97.96 179	80.75 252	91.70 202	97.19 121

MDTV_nov1_ep13_2view						55.91 421	87.62 375		73.32 377	84.59 262		70.33 254		74.65 321		95.50 202

JIA-IIPM		81.04 335	78.98 348	87.25 322	88.64 370	73.48 340	81.75 408	89.61 375	73.19 378	82.05 314	73.71 411	66.07 309	95.87 322	71.18 341	84.60 294	92.41 335

cascas		86.43 261	84.98 271	90.80 204	92.10 282	80.92 201	90.24 326	95.91 154	73.10 379	83.57 293	88.39 355	65.15 313	97.46 212	84.90 182	91.43 205	94.03 267

ANet_high		58.88 385	54.22 390	72.86 391	56.50 431	56.67 416	80.75 410	86.00 392	73.09 380	37.39 423	64.63 419	22.17 423	79.49 421	43.51 415	23.96 425	82.43 407

ADS-MVSNet2		81.66 327	79.71 336	87.50 313	91.35 310	74.19 332	83.33 402	88.48 380	72.90 381	82.24 311	85.77 385	64.98 314	93.20 375	64.57 383	83.74 302	95.12 214

ADS-MVSNet		81.56 329	79.78 333	86.90 333	91.35 310	71.82 360	83.33 402	89.16 378	72.90 381	82.24 311	85.77 385	64.98 314	93.76 366	64.57 383	83.74 302	95.12 214

PVSNet_0	73.20 20	77.22 362	74.83 368	84.37 362	90.70 340	71.10 370	83.09 404	89.67 373	72.81 383	73.93 386	83.13 396	60.79 347	93.70 368	68.54 358	50.84 417	88.30 396

testdata				90.49 214	96.40 93	77.89 278		95.37 200	72.51 384	93.63 64	96.69 73	82.08 108	97.65 196	83.08 204	97.39 89	95.94 184

SSC-MVS		67.06 377	66.56 379	68.56 400	80.54 410	40.06 430	87.77 371	77.37 421	72.38 385	61.75 409	82.66 400	63.37 323	86.45 410	24.48 425	48.69 419	79.16 411

PMMVS		85.71 274	84.96 272	87.95 302	88.90 369	77.09 294	88.68 358	90.06 364	72.32 386	86.47 204	90.76 304	72.15 231	94.40 354	81.78 235	93.49 173	92.36 337

Patchmtry		82.71 316	80.93 322	88.06 299	90.05 354	76.37 307	84.74 397	91.96 320	72.28 387	81.32 324	87.87 365	71.03 241	95.50 339	68.97 356	80.15 354	92.32 339

tpm2		84.08 303	82.94 307	87.48 315	91.39 308	71.27 367	89.23 350	90.37 357	71.95 388	84.64 260	89.33 339	67.30 289	96.55 286	75.17 314	87.09 278	94.63 234

UnsupCasMVSNet_bld		76.23 366	73.27 370	85.09 358	83.79 402	72.92 345	85.65 389	93.47 278	71.52 389	68.84 401	79.08 406	49.77 394	93.21 374	66.81 374	60.52 409	89.13 390

RPMNet		83.95 306	81.53 317	91.21 184	90.58 343	79.34 245	85.24 392	96.76 80	71.44 390	85.55 229	82.97 399	70.87 244	98.91 86	61.01 393	89.36 241	95.40 205

旧先验2							93.36 232		71.25 391	94.37 47			97.13 249	86.74 159

新几何1				93.10 89	97.30 69	84.35 100		95.56 182	71.09 392	91.26 126	96.24 92	82.87 92	98.86 90	79.19 275	98.10 67	96.07 179

test_vis1_rt		77.96 360	76.46 360	82.48 374	85.89 393	71.74 363	90.25 324	78.89 413	71.03 393	71.30 396	81.35 403	42.49 409	91.05 394	84.55 187	82.37 320	84.65 401

Patchmatch-test		81.37 332	79.30 340	87.58 311	90.92 330	74.16 333	80.99 409	87.68 386	70.52 394	76.63 369	88.81 348	71.21 238	92.76 379	60.01 397	86.93 280	95.83 190

ttmdpeth		76.55 364	74.64 369	82.29 377	82.25 408	67.81 390	89.76 339	85.69 394	70.35 395	75.76 375	91.69 270	46.88 402	89.77 399	66.16 375	63.23 406	89.30 384

114514_t		89.51 149	88.50 162	92.54 123	98.11 36	81.99 168	95.16 126	96.36 112	70.19 396	85.81 222	95.25 136	76.70 166	98.63 114	82.07 227	96.86 103	97.00 136

N_pmnet		68.89 375	68.44 377	70.23 395	89.07 367	28.79 434	88.06 365	19.50 434	69.47 397	71.86 394	84.93 388	61.24 342	91.75 388	54.70 406	77.15 373	90.15 376

OpenMVS_ROB	74.94 19	79.51 351	77.03 359	86.93 331	87.00 387	76.23 309	92.33 274	90.74 353	68.93 398	74.52 383	88.23 359	49.58 395	96.62 276	57.64 402	84.29 296	87.94 398

test222					96.55 88	81.70 174	92.22 278	95.01 216	68.36 399	90.20 138	96.14 99	80.26 124			97.80 79	96.05 182

dongtai		58.82 386	58.24 384	60.56 403	83.13 404	45.09 427	82.32 406	48.22 433	67.61 400	61.70 410	69.15 414	38.75 411	76.05 422	32.01 421	41.31 421	60.55 418

MVS		87.44 217	86.10 236	91.44 176	92.61 268	83.62 117	92.63 263	95.66 176	67.26 401	81.47 320	92.15 251	77.95 153	98.22 153	79.71 266	95.48 130	92.47 332

tpm cat1		81.96 321	80.27 327	87.01 329	91.09 321	71.02 372	87.38 377	91.53 332	66.25 402	80.17 336	86.35 381	68.22 286	96.15 309	69.16 355	82.29 321	93.86 276

CVMVSNet		84.69 297	84.79 277	84.37 362	91.84 291	64.92 400	93.70 221	91.47 334	66.19 403	86.16 216	95.28 134	67.18 292	93.33 372	80.89 250	90.42 221	94.88 227

test_f		71.95 372	70.87 373	75.21 390	74.21 420	59.37 413	85.07 394	85.82 393	65.25 404	70.42 398	83.13 396	23.62 420	82.93 418	78.32 282	71.94 388	83.33 403

CMPMVS	59.16 21	80.52 340	79.20 343	84.48 361	83.98 401	67.63 392	89.95 337	93.84 271	64.79 405	66.81 403	91.14 291	57.93 365	95.17 344	76.25 305	88.10 260	90.65 370
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		81.32 333	80.95 321	82.42 375	88.50 373	63.67 404	93.32 234	91.33 336	64.02 406	80.57 333	92.83 229	61.21 343	92.27 383	76.34 304	80.38 353	91.32 358

test_vis3_rt		65.12 379	62.60 381	72.69 392	71.44 421	60.71 409	87.17 378	65.55 425	63.80 407	53.22 415	65.65 418	14.54 429	89.44 402	76.65 299	65.38 401	67.91 416

new_pmnet		72.15 371	70.13 374	78.20 386	82.95 406	65.68 395	83.91 400	82.40 406	62.94 408	64.47 405	79.82 405	42.85 408	86.26 411	57.41 403	74.44 382	82.65 406

MVStest1		72.91 370	69.70 375	82.54 373	78.14 415	73.05 344	88.21 364	86.21 390	60.69 409	64.70 404	90.53 310	46.44 403	85.70 412	58.78 400	53.62 414	88.87 391

DSMNet-mixed		76.94 363	76.29 362	78.89 384	83.10 405	56.11 420	87.78 370	79.77 411	60.65 410	75.64 376	88.71 351	61.56 337	88.34 406	60.07 396	89.29 243	92.21 342

kuosan		53.51 388	53.30 391	54.13 407	76.06 416	45.36 426	80.11 413	48.36 432	59.63 411	54.84 413	63.43 420	37.41 412	62.07 427	20.73 427	39.10 422	54.96 421

pmmvs3		71.81 373	68.71 376	81.11 378	75.86 417	70.42 378	86.74 381	83.66 402	58.95 412	68.64 402	80.89 404	36.93 413	89.52 401	63.10 388	63.59 404	83.39 402

MVS-HIRNet		73.70 369	72.20 372	78.18 387	91.81 294	56.42 419	82.94 405	82.58 405	55.24 413	68.88 400	66.48 416	55.32 377	95.13 345	58.12 401	88.42 256	83.01 404

PMMVS2		59.60 382	56.40 385	69.21 398	68.83 425	46.58 424	73.02 419	77.48 420	55.07 414	49.21 417	72.95 413	17.43 427	80.04 420	49.32 411	44.33 420	80.99 408

APD_test1		69.04 374	66.26 380	77.36 389	80.51 411	62.79 407	85.46 391	83.51 403	54.11 415	59.14 412	84.79 390	23.40 422	89.61 400	55.22 405	70.24 390	79.68 410

FPMVS		64.63 380	62.55 382	70.88 393	70.80 422	56.71 415	84.42 398	84.42 400	51.78 416	49.57 416	81.61 402	23.49 421	81.48 419	40.61 419	76.25 378	74.46 412

LCM-MVSNet		66.00 378	62.16 383	77.51 388	64.51 428	58.29 414	83.87 401	90.90 349	48.17 417	54.69 414	73.31 412	16.83 428	86.75 408	65.47 377	61.67 408	87.48 400

DeepMVS_CX				56.31 406	74.23 419	51.81 422		56.67 430	44.85 418	48.54 418	75.16 409	27.87 418	58.74 428	40.92 418	52.22 415	58.39 420

Gipuma		57.99 387	54.91 389	67.24 401	88.51 371	65.59 396	52.21 422	90.33 359	43.58 419	42.84 422	51.18 423	20.29 425	85.07 413	34.77 420	70.45 389	51.05 422
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testf1		59.54 383	56.11 387	69.85 396	69.28 423	56.61 417	80.37 411	76.55 422	42.58 420	45.68 419	75.61 407	11.26 430	84.18 414	43.20 416	60.44 410	68.75 414

APD_test2		59.54 383	56.11 387	69.85 396	69.28 423	56.61 417	80.37 411	76.55 422	42.58 420	45.68 419	75.61 407	11.26 430	84.18 414	43.20 416	60.44 410	68.75 414

PMVS	47.18 22	52.22 389	48.46 393	63.48 402	45.72 433	46.20 425	73.41 418	78.31 416	41.03 422	30.06 425	65.68 417	6.05 432	83.43 417	30.04 422	65.86 400	60.80 417
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		43.23 392	42.29 394	46.03 408	65.58 427	37.41 431	73.51 417	64.62 426	33.99 423	28.47 427	47.87 424	19.90 426	67.91 424	22.23 426	24.45 424	32.77 423

EMVS		42.07 393	41.12 395	44.92 409	63.45 429	35.56 433	73.65 416	63.48 427	33.05 424	26.88 428	45.45 425	21.27 424	67.14 425	19.80 428	23.02 426	32.06 424

MVE	39.65 23	43.39 391	38.59 397	57.77 404	56.52 430	48.77 423	55.38 421	58.64 429	29.33 425	28.96 426	52.65 422	4.68 433	64.62 426	28.11 423	33.07 423	59.93 419
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.52 390	48.47 392	56.66 405	52.26 432	18.98 436	41.51 424	81.40 408	10.10 426	44.59 421	75.01 410	28.51 417	68.16 423	53.54 407	49.31 418	82.83 405

wuyk23d		21.27 396	20.48 399	23.63 411	68.59 426	36.41 432	49.57 423	6.85 435	9.37 427	7.89 429	4.46 431	4.03 434	31.37 429	17.47 429	16.07 428	3.12 426

tmp_tt		35.64 394	39.24 396	24.84 410	14.87 434	23.90 435	62.71 420	51.51 431	6.58 428	36.66 424	62.08 421	44.37 406	30.34 430	52.40 408	22.00 427	20.27 425

testmvs		8.92 397	11.52 400	1.12 413	1.06 435	0.46 438	86.02 385	0.65 436	0.62 429	2.74 430	9.52 429	0.31 436	0.45 432	2.38 430	0.39 429	2.46 428

test123		8.76 398	11.22 401	1.39 412	0.85 436	0.97 437	85.76 388	0.35 437	0.54 430	2.45 431	8.14 430	0.60 435	0.48 431	2.16 431	0.17 430	2.71 427

EGC-MVSNET		61.97 381	56.37 386	78.77 385	89.63 362	73.50 339	89.12 352	82.79 404	0.21 431	1.24 432	84.80 389	39.48 410	90.04 398	44.13 414	75.94 380	72.79 413

mmdepth		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

monomultidepth		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

test_blank		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

uanet_test		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

DCPMVS		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

cdsmvs_eth3d_5k		22.14 395	29.52 398	0.00 414	0.00 437	0.00 439	0.00 425	95.76 166	0.00 432	0.00 433	94.29 176	75.66 182	0.00 433	0.00 432	0.00 431	0.00 429

pcd_1.5k_mvsjas		6.64 400	8.86 403	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	79.70 131	0.00 433	0.00 432	0.00 431	0.00 429

sosnet-low-res		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

sosnet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

uncertanet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

Regformer		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

ab-mvs-re		7.82 399	10.43 402	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	93.88 196	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

uanet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 439	0.00 425	0.00 438	0.00 432	0.00 433	0.00 432	0.00 437	0.00 433	0.00 432	0.00 431	0.00 429

WAC-MVS						64.08 402								59.14 398

MSC_two_6792asdad				96.52 1	97.78 54	90.86 1		96.85 68					99.61 4	96.03 18	99.06 9	99.07 5

No_MVS				96.52 1	97.78 54	90.86 1		96.85 68					99.61 4	96.03 18	99.06 9	99.07 5

eth-test2					0.00 437

eth-test					0.00 437

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 56	92.59 2	98.94 83	92.25 77	98.99 14	98.84 14

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 16	97.49 6					99.61 4	95.62 25	99.08 7	98.99 9

GSMVS																96.12 175

test_part2					98.55 12	87.22 19				96.40 21

sam_mvs1												71.70 234				96.12 175

sam_mvs												70.60 247

ambc				83.06 370	79.99 412	63.51 405	77.47 415	92.86 291		74.34 385	84.45 391	28.74 416	95.06 348	73.06 332	68.89 396	90.61 371

MTGPA								96.97 55

test_post1							88.00 367				9.81 428	69.31 270	95.53 335	76.65 299

test_post											10.29 427	70.57 251	95.91 321

patchmatchnet-post											83.76 393	71.53 235	96.48 290

GG-mvs-BLEND				87.94 303	89.73 361	77.91 276	87.80 368	78.23 417		80.58 332	83.86 392	59.88 353	95.33 343	71.20 339	92.22 199	90.60 373

MTMP							96.16 52	60.64 428

test9_res														91.91 92	98.71 32	98.07 74

agg_prior2														90.54 114	98.68 37	98.27 57

agg_prior					97.38 66	85.92 57		96.72 86		92.16 102			98.97 78

test_prior4						85.96 54	94.11 193

test_prior				93.82 66	97.29 70	84.49 91		96.88 66					98.87 88			98.11 73

新几何2							93.11 247

旧先验1					96.79 79	81.81 172		95.67 174			96.81 70	86.69 39			97.66 85	96.97 138

原ACMM2							92.94 254

testdata2													98.75 101	78.30 283

segment_acmp												87.16 36

test12				94.34 52	97.13 73	86.15 48		96.29 116		91.04 128		85.08 61	99.01 66		98.13 66	97.86 89

plane_prior7					94.70 178	82.74 150

plane_prior6					94.52 190	82.75 148						74.23 200

plane_prior5								96.22 126					98.12 158	88.15 138	89.99 226	94.63 234

plane_prior4											94.86 153

plane_prior1					94.59 184

n2								0.00 438

nn								0.00 438

door-mid								85.49 395

lessismore_v0				86.04 344	88.46 374	68.78 386		80.59 410		73.01 390	90.11 323	55.39 375	96.43 295	75.06 316	65.06 402	92.90 319

test11								96.57 97

door								85.33 397

HQP5-MVS						81.56 176

BP-MVS														87.11 156

HQP4-MVS										85.43 240			97.96 179			94.51 244

HQP3-MVS								96.04 143							89.77 235

HQP2-MVS												73.83 210

NP-MVS					94.37 200	82.42 160					93.98 189

ACMMP++_ref															87.47 271

ACMMP++															88.01 263

Test By Simon												80.02 126

High-resolution multi-view benchmark