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.

TestfortrainingZip				99.33 5	99.87 2	97.98 5	99.65 52	98.06 53	92.29 115	99.91 1	99.64 2	95.49 8	100.00 1		98.29 133	100.00 1

SED-MVS		98.18 2	98.10 4	98.41 20	99.63 23	95.24 29	99.77 29	97.72 98	94.17 59	99.30 17	99.54 4	93.32 23	99.98 13	99.70 5	99.81 23	99.99 2

IU-MVS					99.63 23	95.38 26		97.73 97	95.54 37	99.54 9				99.69 7	99.81 23	99.99 2

OPU-MVS				99.49 4	99.64 22	98.51 4	99.77 29				99.19 45	95.12 9	99.97 25	99.90 1	99.92 3	99.99 2

test_241102_TWO								97.72 98	94.17 59	99.23 20	99.54 4	93.14 28	99.98 13	99.70 5	99.82 19	99.99 2

DeepPCF-MVS	93.56 1	96.55 57	97.84 11	92.68 301	98.71 96	78.11 433	99.70 41	97.71 102	98.18 1	97.36 84	99.76 1	90.37 58	99.94 40	99.27 25	99.54 58	99.99 2

MCST-MVS		98.18 2	97.95 9	98.86 6	99.85 4	96.60 11	99.70 41	97.98 62	97.18 11	95.96 123	99.33 27	92.62 30	100.00 1	98.99 41	99.93 1	99.98 7

DVP-MVS++		98.18 2	98.09 5	98.44 18	99.61 29	95.38 26	99.55 66	97.68 109	93.01 91	99.23 20	99.45 19	95.12 9	99.98 13	99.25 28	99.92 3	99.97 8

PC_three_1452									94.60 51	99.41 11	99.12 63	95.50 7	99.96 33	99.84 2	99.92 3	99.97 8

MG-MVS		97.24 24	96.83 39	98.47 17	99.79 6	95.71 21	99.07 141	99.06 10	94.45 56	96.42 114	98.70 117	88.81 78	99.74 110	95.35 137	99.86 12	99.97 8

MSC_two_6792asdad				99.51 2	99.61 29	98.60 2		97.69 107					99.98 13	99.55 16	99.83 15	99.96 11

No_MVS				99.51 2	99.61 29	98.60 2		97.69 107					99.98 13	99.55 16	99.83 15	99.96 11

test_0728_SECOND				98.77 10	99.66 17	96.37 16	99.72 38	97.68 109					99.98 13	99.64 8	99.82 19	99.96 11

CNVR-MVS		98.46 1	98.38 1	98.72 12	99.80 5	96.19 17	99.80 26	97.99 61	97.05 13	99.41 11	99.59 3	92.89 29	100.00 1	98.99 41	99.90 7	99.96 11

DeepC-MVS_fast	93.52 2	97.16 28	96.84 37	98.13 27	99.61 29	94.45 56	98.85 164	97.64 124	96.51 25	95.88 126	99.39 23	87.35 106	99.99 9	96.61 103	99.69 38	99.96 11
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TestfortrainingZip a		97.86 9	97.55 15	98.78 9	99.75 8	96.39 15	99.65 52	98.11 47	92.89 98	98.58 48	99.53 8	93.98 18	100.00 1	95.87 124	99.64 42	99.95 16

test_0728_THIRD									93.01 91	99.07 26	99.46 15	94.66 14	99.97 25	99.25 28	99.82 19	99.95 16

DPE-MVS		98.11 6	98.00 6	98.44 18	99.50 47	95.39 25	99.29 105	97.72 98	94.50 52	98.64 43	99.54 4	93.32 23	99.97 25	99.58 12	99.90 7	99.95 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.77 12	98.18 2	96.53 113	99.54 41	90.14 180	99.41 92	97.70 103	95.46 39	98.60 45	99.19 45	95.71 5	99.49 134	98.15 69	99.85 13	99.95 16
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
DPM-MVS		97.86 9	97.25 26	99.68 1	98.25 105	99.10 1	99.76 32	97.78 90	96.61 21	98.15 62	99.53 8	93.62 20	100.00 1	91.79 220	99.80 26	99.94 20

NCCC		98.12 5	98.11 3	98.13 27	99.76 7	94.46 55	99.81 20	97.88 69	96.54 22	98.84 35	99.46 15	92.55 31	99.98 13	98.25 67	99.93 1	99.94 20

APDe-MVS		97.53 18	97.47 19	97.70 45	99.58 35	93.63 75	99.56 65	97.52 153	93.59 81	98.01 71	99.12 63	90.80 49	99.55 128	99.26 26	99.79 27	99.93 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
agg_prior2														97.84 76	99.87 9	99.91 23

test9_res														98.60 50	99.87 9	99.90 24

SteuartSystems-ACMMP		97.25 23	97.34 24	97.01 77	97.38 147	91.46 139	99.75 35	97.66 115	94.14 63	98.13 63	99.26 30	92.16 35	99.66 116	97.91 73	99.64 42	99.90 24
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		96.65 51	96.46 55	97.21 69	99.34 55	91.77 129	99.70 41	98.05 55	86.48 313	98.05 68	99.20 41	89.33 70	99.96 33	98.38 60	99.62 50	99.90 24

ACMMP_NAP		96.59 52	96.18 65	97.81 41	98.82 92	93.55 80	98.88 163	97.59 137	90.66 155	97.98 72	99.14 58	86.59 125	100.00 1	96.47 107	99.46 61	99.89 27

train_agg		97.20 27	97.08 27	97.57 51	99.57 38	93.17 90	99.38 95	97.66 115	90.18 176	98.39 55	99.18 48	90.94 42	99.66 116	98.58 53	99.85 13	99.88 28

MSLP-MVS++		97.50 20	97.45 21	97.63 47	99.65 21	93.21 88	99.70 41	98.13 45	94.61 50	97.78 77	99.46 15	89.85 64	99.81 97	97.97 71	99.91 6	99.88 28

APD-MVS		96.95 35	96.72 45	97.63 47	99.51 46	93.58 78	99.16 122	97.44 170	90.08 182	98.59 46	99.07 70	89.06 72	99.42 145	97.92 72	99.66 39	99.88 28
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MED-MVS test				97.84 36	99.75 8	93.67 72	99.65 52	98.11 47	92.89 98	98.58 48	99.53 8		100.00 1	99.53 19	99.64 42	99.87 31

MED-MVS		97.89 8	97.91 10	97.84 36	99.75 8	93.67 72	99.65 52	98.11 47	92.38 113	98.58 48	99.53 8	93.98 18	100.00 1	99.53 19	99.64 42	99.87 31

ME-MVS		97.59 17	97.51 17	97.84 36	99.73 11	93.67 72	99.52 72	98.07 51	92.38 113	98.32 59	99.53 8	90.83 48	99.97 25	99.53 19	99.64 42	99.87 31

MVS		93.92 154	92.28 193	98.83 8	95.69 233	96.82 9	96.22 381	98.17 39	84.89 343	84.34 318	98.61 125	79.32 254	99.83 91	93.88 175	99.43 65	99.86 34

MM		97.76 13	97.39 23	98.86 6	98.30 104	96.83 8	99.81 20	99.13 9	97.66 2	98.29 60	98.96 88	85.84 143	99.90 61	99.72 3	98.80 105	99.85 35

无先验							98.52 219	97.82 79	87.20 292				99.90 61	87.64 271		99.85 35

reproduce-ours		96.66 48	96.80 41	96.22 132	98.95 84	89.03 223	98.62 201	97.38 178	93.42 83	96.80 105	99.36 24	88.92 75	99.80 99	98.51 55	99.26 75	99.82 37

our_new_method		96.66 48	96.80 41	96.22 132	98.95 84	89.03 223	98.62 201	97.38 178	93.42 83	96.80 105	99.36 24	88.92 75	99.80 99	98.51 55	99.26 75	99.82 37

SMA-MVS		97.24 24	96.99 28	98.00 33	99.30 59	94.20 63	99.16 122	97.65 122	89.55 204	99.22 22	99.52 13	90.34 59	99.99 9	98.32 64	99.83 15	99.82 37
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
region2R		96.30 64	96.17 68	96.70 100	99.70 12	90.31 173	99.46 82	97.66 115	90.55 163	97.07 92	99.07 70	86.85 116	99.97 25	95.43 135	99.74 29	99.81 40

test222					98.32 103	91.21 143	98.08 284	97.58 139	83.74 364	95.87 127	99.02 79	86.74 119			99.64 42	99.81 40

TSAR-MVS + GP.		96.95 35	96.91 33	97.07 74	98.88 90	91.62 134	99.58 63	96.54 254	95.09 44	96.84 99	98.63 123	91.16 37	99.77 107	99.04 38	96.42 174	99.81 40

reproduce_model		96.57 55	96.75 44	96.02 148	98.93 87	88.46 249	98.56 215	97.34 185	93.18 89	96.96 95	99.35 26	88.69 80	99.80 99	98.53 54	99.21 81	99.79 43

test_prior				97.01 77	99.58 35	91.77 129		97.57 142					99.49 134			99.79 43

新几何1				97.40 58	98.92 88	92.51 113		97.77 92	85.52 330	96.69 109	99.06 73	88.08 91	99.89 69	84.88 310	99.62 50	99.79 43

patch_mono-2		97.10 31	97.97 8	94.49 236	99.21 68	83.73 369	99.62 60	98.25 34	95.28 41	99.38 14	98.91 96	92.28 34	99.94 40	99.61 11	99.22 78	99.78 46

HFP-MVS		96.42 60	96.26 60	96.90 87	99.69 13	90.96 155	99.47 78	97.81 83	90.54 164	96.88 96	99.05 75	87.57 97	99.96 33	95.65 127	99.72 32	99.78 46

XVS		96.47 58	96.37 57	96.77 93	99.62 27	90.66 164	99.43 89	97.58 139	92.41 110	96.86 97	98.96 88	87.37 102	99.87 75	95.65 127	99.43 65	99.78 46

X-MVStestdata		90.69 259	88.66 289	96.77 93	99.62 27	90.66 164	99.43 89	97.58 139	92.41 110	96.86 97	29.59 502	87.37 102	99.87 75	95.65 127	99.43 65	99.78 46

testdata				95.26 196	98.20 108	87.28 289		97.60 133	85.21 334	98.48 52	99.15 55	88.15 89	98.72 194	90.29 237	99.45 63	99.78 46

SF-MVS		97.22 26	96.92 31	98.12 29	99.11 73	94.88 40	99.44 85	97.45 166	89.60 200	98.70 40	99.42 22	90.42 56	99.72 111	98.47 58	99.65 40	99.77 51

SD-MVS		97.51 19	97.40 22	97.81 41	99.01 79	93.79 71	99.33 103	97.38 178	93.73 76	98.83 36	99.02 79	90.87 47	99.88 71	98.69 46	99.74 29	99.77 51
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
SR-MVS		96.13 69	96.16 70	96.07 145	99.42 52	89.04 221	98.59 210	97.33 188	90.44 167	96.84 99	99.12 63	86.75 118	99.41 148	97.47 81	99.44 64	99.76 53

ACMMPR		96.28 65	96.14 72	96.73 97	99.68 14	90.47 169	99.47 78	97.80 85	90.54 164	96.83 101	99.03 77	86.51 130	99.95 37	95.65 127	99.72 32	99.75 54

mPP-MVS		95.90 81	95.75 85	96.38 122	99.58 35	89.41 210	99.26 111	97.41 174	90.66 155	94.82 149	98.95 91	86.15 138	99.98 13	95.24 142	99.64 42	99.74 55

PAPR		96.35 61	95.82 80	97.94 35	99.63 23	94.19 64	99.42 91	97.55 144	92.43 107	93.82 175	99.12 63	87.30 107	99.91 56	94.02 172	99.06 86	99.74 55

API-MVS		94.78 125	94.18 128	96.59 108	99.21 68	90.06 187	98.80 170	97.78 90	83.59 368	93.85 172	99.21 40	83.79 178	99.97 25	92.37 211	99.00 90	99.74 55

fmvsm_l_conf0.5_n_9		97.33 22	97.32 25	97.37 60	97.64 130	92.45 114	99.93 1	97.85 72	97.39 6	99.84 2	99.09 69	85.42 152	99.92 49	99.52 22	99.20 82	99.73 58

CSCG		94.87 122	94.71 114	95.36 185	99.54 41	86.49 304	99.34 102	98.15 43	82.71 386	90.15 257	99.25 32	89.48 69	99.86 81	94.97 150	98.82 102	99.72 59

fmvsm_s_conf0.5_n_9		96.76 45	96.92 31	96.29 129	97.95 118	89.21 214	99.81 20	97.55 144	97.04 14	99.68 5	99.22 37	82.84 199	99.94 40	99.56 15	98.61 117	99.71 60

MTAPA		96.09 70	95.80 83	96.96 84	99.29 60	91.19 144	97.23 339	97.45 166	92.58 104	94.39 159	99.24 34	86.43 132	99.99 9	96.22 110	99.40 68	99.71 60

test_fmvsmconf_n		96.78 43	96.84 37	96.61 106	95.99 222	90.25 174	99.90 4	98.13 45	96.68 20	98.42 54	98.92 95	85.34 154	99.88 71	99.12 35	99.08 83	99.70 62

APD-MVS_3200maxsize		95.64 97	95.65 90	95.62 174	99.24 65	87.80 266	98.42 235	97.22 196	88.93 229	96.64 112	98.98 82	85.49 148	99.36 152	96.68 100	99.27 74	99.70 62

CP-MVS		96.22 66	96.15 71	96.42 118	99.67 15	89.62 204	99.70 41	97.61 131	90.07 183	96.00 122	99.16 51	87.43 100	99.92 49	96.03 120	99.72 32	99.70 62

DVP-MVS		98.07 7	98.00 6	98.29 21	99.66 17	95.20 34	99.72 38	97.47 163	93.95 64	99.07 26	99.46 15	93.18 26	99.97 25	99.64 8	99.82 19	99.69 65
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
MGCNet		97.81 11	97.51 17	98.74 11	98.97 80	96.57 12	99.91 3	98.17 39	97.45 5	98.76 38	98.97 83	86.69 122	99.96 33	99.72 3	98.92 96	99.69 65

ZNCC-MVS		96.09 70	95.81 82	96.95 85	99.42 52	91.19 144	99.55 66	97.53 149	89.72 194	95.86 128	98.94 94	86.59 125	99.97 25	95.13 143	99.56 56	99.68 67

HPM-MVS++		97.72 14	97.59 14	98.14 26	99.53 45	94.76 47	99.19 116	97.75 93	95.66 35	98.21 61	99.29 29	91.10 39	99.99 9	97.68 78	99.87 9	99.68 67

CDPH-MVS		96.56 56	96.18 65	97.70 45	99.59 33	93.92 67	99.13 135	97.44 170	89.02 224	97.90 74	99.22 37	88.90 77	99.49 134	94.63 159	99.79 27	99.68 67

PAPM_NR		95.43 101	95.05 108	96.57 111	99.42 52	90.14 180	98.58 213	97.51 155	90.65 157	92.44 208	98.90 98	87.77 96	99.90 61	90.88 229	99.32 70	99.68 67

lecture		96.67 47	96.77 43	96.39 121	99.27 62	89.71 201	99.65 52	98.62 22	92.28 116	98.62 44	99.07 70	86.74 119	99.79 103	97.83 77	98.82 102	99.66 71

sasdasda		95.02 115	93.96 137	98.20 23	97.53 139	95.92 19	98.71 182	96.19 283	91.78 125	95.86 128	98.49 134	79.53 251	99.03 173	96.12 115	91.42 283	99.66 71

canonicalmvs		95.02 115	93.96 137	98.20 23	97.53 139	95.92 19	98.71 182	96.19 283	91.78 125	95.86 128	98.49 134	79.53 251	99.03 173	96.12 115	91.42 283	99.66 71

PGM-MVS		95.85 84	95.65 90	96.45 116	99.50 47	89.77 199	98.22 265	98.90 13	89.19 215	96.74 107	98.95 91	85.91 142	99.92 49	93.94 173	99.46 61	99.66 71

MGCFI-Net		94.89 118	93.84 145	98.06 31	97.49 142	95.55 23	98.64 196	96.10 292	91.60 130	95.75 133	98.46 140	79.31 255	98.98 177	95.95 122	91.24 288	99.65 75

fmvsm_s_conf0.5_n_8		97.06 33	96.94 30	97.44 53	97.78 123	92.77 105	99.83 15	97.83 78	97.58 3	99.25 19	99.20 41	82.71 205	99.92 49	99.64 8	98.61 117	99.64 76

DELS-MVS		97.12 29	96.60 49	98.68 13	98.03 116	96.57 12	99.84 14	97.84 74	96.36 27	95.20 144	98.24 147	88.17 87	99.83 91	96.11 117	99.60 54	99.64 76
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
3Dnovator+	87.72 8	93.43 175	91.84 211	98.17 25	95.73 232	95.08 37	98.92 159	97.04 217	91.42 136	81.48 368	97.60 177	74.60 309	99.79 103	90.84 230	98.97 92	99.64 76

CANet		97.00 34	96.49 52	98.55 14	98.86 91	96.10 18	99.83 15	97.52 153	95.90 29	97.21 88	98.90 98	82.66 207	99.93 46	98.71 45	98.80 105	99.63 79

114514_t		94.06 148	93.05 170	97.06 75	99.08 76	92.26 118	98.97 155	97.01 222	82.58 388	92.57 203	98.22 148	80.68 240	99.30 158	89.34 250	99.02 89	99.63 79

PAPM		96.35 61	95.94 74	97.58 49	94.10 323	95.25 28	98.93 157	98.17 39	94.26 58	93.94 169	98.72 113	89.68 67	97.88 263	96.36 108	99.29 73	99.62 81

SR-MVS-dyc-post		95.75 91	95.86 77	95.41 184	99.22 66	87.26 292	98.40 241	97.21 197	89.63 197	96.67 110	98.97 83	86.73 121	99.36 152	96.62 101	99.31 71	99.60 82

RE-MVS-def			95.70 86		99.22 66	87.26 292	98.40 241	97.21 197	89.63 197	96.67 110	98.97 83	85.24 158		96.62 101	99.31 71	99.60 82

TSAR-MVS + MP.		97.44 21	97.46 20	97.39 59	99.12 72	93.49 83	98.52 219	97.50 158	94.46 54	98.99 28	98.64 121	91.58 36	99.08 172	98.49 57	99.83 15	99.60 82
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
旧先验1					98.97 80	92.90 102		97.74 94			99.15 55	91.05 41			99.33 69	99.60 82

fmvsm_l_conf0.5_n_3		97.12 29	96.89 34	97.79 44	97.39 146	93.84 70	99.87 6	97.70 103	97.34 8	99.39 13	99.20 41	82.86 197	99.94 40	99.21 31	99.07 85	99.58 86

fmvsm_l_conf0.5_n		97.65 16	97.72 13	97.41 57	97.51 141	92.78 104	99.85 12	98.05 55	96.78 17	99.60 7	99.23 35	90.42 56	99.92 49	99.55 16	98.50 124	99.55 87

test12				97.83 40	99.33 58	94.45 56		97.55 144		97.56 78		88.60 81	99.50 133		99.71 36	99.55 87

HY-MVS	88.56 7	95.29 106	94.23 124	98.48 16	97.72 126	96.41 14	94.03 424	98.74 15	92.42 109	95.65 136	94.76 304	86.52 129	99.49 134	95.29 140	92.97 241	99.53 89

GST-MVS		95.97 76	95.66 88	96.90 87	99.49 50	91.22 142	99.45 84	97.48 161	89.69 195	95.89 125	98.72 113	86.37 133	99.95 37	94.62 160	99.22 78	99.52 90

balanced_ft_v1		94.96 117	94.35 121	96.78 92	97.54 138	92.05 121	98.03 291	96.20 280	90.90 148	96.83 101	95.51 289	76.75 286	98.77 186	98.68 48	98.70 112	99.52 90

MP-MVS		96.00 73	95.82 80	96.54 112	99.47 51	90.13 182	99.36 99	97.41 174	90.64 158	95.49 139	98.95 91	85.51 147	99.98 13	96.00 121	99.59 55	99.52 90
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
balanced_conf03		96.83 39	96.51 51	97.81 41	97.60 134	95.15 36	98.40 241	96.77 235	93.00 93	98.69 41	96.19 270	89.75 66	98.76 189	98.45 59	99.72 32	99.51 93

alignmvs		95.77 89	95.00 110	98.06 31	97.35 149	95.68 22	99.71 40	97.50 158	91.50 132	96.16 121	98.61 125	86.28 134	99.00 175	96.19 111	91.74 271	99.51 93

WTY-MVS		95.97 76	95.11 106	98.54 15	97.62 131	96.65 10	99.44 85	98.74 15	92.25 117	95.21 143	98.46 140	86.56 127	99.46 140	95.00 148	92.69 245	99.50 95

MVSMamba_PlusPlus		95.73 94	95.15 103	97.44 53	97.28 155	94.35 61	98.26 261	96.75 236	83.09 376	97.84 75	95.97 278	89.59 68	98.48 207	97.86 74	99.73 31	99.49 96

mvsmamba		94.27 143	93.91 142	95.35 187	96.42 196	88.61 243	97.77 307	96.38 267	91.17 144	94.05 166	95.27 296	78.41 271	97.96 257	97.36 84	98.40 127	99.48 97

DP-MVS Recon		95.85 84	95.15 103	97.95 34	99.87 2	94.38 59	99.60 61	97.48 161	86.58 308	94.42 157	99.13 60	87.36 105	99.98 13	93.64 180	98.33 130	99.48 97

HPM-MVS		95.41 103	95.22 101	95.99 152	99.29 60	89.14 218	99.17 121	97.09 214	87.28 291	95.40 140	98.48 137	84.93 161	99.38 150	95.64 131	99.65 40	99.47 99
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
dcpmvs_2		95.67 96	96.18 65	94.12 256	98.82 92	84.22 362	97.37 332	95.45 375	90.70 154	95.77 132	98.63 123	90.47 54	98.68 196	99.20 32	99.22 78	99.45 100

test_yl		95.27 107	94.60 116	97.28 66	98.53 100	92.98 97	99.05 145	98.70 18	86.76 305	94.65 154	97.74 168	87.78 94	99.44 141	95.57 133	92.61 246	99.44 101

DCV-MVSNet		95.27 107	94.60 116	97.28 66	98.53 100	92.98 97	99.05 145	98.70 18	86.76 305	94.65 154	97.74 168	87.78 94	99.44 141	95.57 133	92.61 246	99.44 101

test_fmvsmconf0.1_n		95.94 79	95.79 84	96.40 120	92.42 370	89.92 191	99.79 27	96.85 229	96.53 24	97.22 87	98.67 119	82.71 205	99.84 87	98.92 43	98.98 91	99.43 103

fmvsm_l_conf0.5_n_a		97.70 15	97.80 12	97.42 56	97.59 135	92.91 101	99.86 9	98.04 57	96.70 19	99.58 8	99.26 30	90.90 44	99.94 40	99.57 13	98.66 115	99.40 104

MVS_111021_HR		96.69 46	96.69 46	96.72 99	98.58 99	91.00 154	99.14 130	99.45 1	93.86 71	95.15 145	98.73 111	88.48 82	99.76 108	97.23 87	99.56 56	99.40 104

CS-MVS		95.75 91	96.19 63	94.40 240	97.88 121	86.22 315	99.66 50	96.12 290	92.69 103	98.07 67	98.89 100	87.09 110	97.59 294	96.71 98	98.62 116	99.39 106

SPE-MVS-test		95.98 75	96.34 59	94.90 215	98.06 115	87.66 271	99.69 48	96.10 292	93.66 78	98.35 58	99.05 75	86.28 134	97.66 288	96.96 93	98.90 98	99.37 107

RRT-MVS		93.39 177	92.64 183	95.64 170	96.11 219	88.75 240	97.40 328	95.77 340	89.46 208	92.70 201	95.42 293	72.98 329	98.81 184	96.91 95	96.97 163	99.37 107

lupinMVS		96.32 63	95.94 74	97.44 53	95.05 278	94.87 41	99.86 9	96.50 256	93.82 74	98.04 69	98.77 107	85.52 145	98.09 236	96.98 92	98.97 92	99.37 107

mvs_anonymous		92.50 211	91.65 216	95.06 209	96.60 187	89.64 203	97.06 347	96.44 261	86.64 307	84.14 319	93.93 317	82.49 210	96.17 369	91.47 222	96.08 186	99.35 110

HPM-MVS_fast		94.89 118	94.62 115	95.70 166	99.11 73	88.44 250	99.14 130	97.11 210	85.82 325	95.69 135	98.47 138	83.46 183	99.32 157	93.16 198	99.63 49	99.35 110

1314		93.44 174	91.98 206	97.84 36	95.24 255	94.38 59	96.22 381	97.92 67	90.18 176	82.28 348	97.71 171	77.63 278	99.80 99	91.94 218	98.67 114	99.34 112

LFMVS		92.23 219	90.84 238	96.42 118	98.24 107	91.08 151	98.24 264	96.22 278	83.39 371	94.74 152	98.31 144	61.12 421	98.85 182	94.45 162	92.82 242	99.32 113

Effi-MVS+		93.87 158	93.15 166	96.02 148	95.79 229	90.76 160	96.70 363	95.78 338	86.98 298	95.71 134	97.17 211	79.58 248	98.01 254	94.57 161	96.09 185	99.31 114

CHOSEN 1792x2688		94.35 140	93.82 146	95.95 155	97.40 145	88.74 241	98.41 238	98.27 33	92.18 119	91.43 230	96.40 263	78.88 258	99.81 97	93.59 181	97.81 140	99.30 115

ACMMP		94.67 131	94.30 122	95.79 162	99.25 64	88.13 258	98.41 238	98.67 21	90.38 169	91.43 230	98.72 113	82.22 218	99.95 37	93.83 177	95.76 190	99.29 116
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
MP-MVS-pluss		95.80 87	95.30 97	97.29 64	98.95 84	92.66 106	98.59 210	97.14 206	88.95 227	93.12 187	99.25 32	85.62 144	99.94 40	96.56 105	99.48 60	99.28 117
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
EPMVS		92.59 209	91.59 217	95.59 176	97.22 157	90.03 188	91.78 448	98.04 57	90.42 168	91.66 224	90.65 395	86.49 131	97.46 301	81.78 359	96.31 177	99.28 117

AdaColmap		93.82 160	93.06 169	96.10 144	99.88 1	89.07 220	98.33 252	97.55 144	86.81 303	90.39 252	98.65 120	75.09 306	99.98 13	93.32 190	97.53 150	99.26 119

ET-MVSNet_ETH3D		92.56 210	91.45 220	95.88 158	96.39 200	94.13 65	99.46 82	96.97 225	92.18 119	66.94 467	98.29 146	94.65 15	94.28 432	94.34 166	83.82 336	99.24 120

VNet		95.08 114	94.26 123	97.55 52	98.07 114	93.88 68	98.68 189	98.73 17	90.33 170	97.16 91	97.43 188	79.19 256	99.53 131	96.91 95	91.85 269	99.24 120

CNLPA		93.64 167	92.74 180	96.36 124	98.96 83	90.01 190	99.19 116	95.89 329	86.22 316	89.40 273	98.85 103	80.66 241	99.84 87	88.57 260	96.92 165	99.24 120

3Dnovator	87.35 11	93.17 188	91.77 214	97.37 60	95.41 248	93.07 93	98.82 167	97.85 72	91.53 131	82.56 341	97.58 179	71.97 339	99.82 94	91.01 227	99.23 77	99.22 123

GG-mvs-BLEND				96.98 82	96.53 190	94.81 46	87.20 468	97.74 94		93.91 170	96.40 263	96.56 2	96.94 323	95.08 144	98.95 95	99.20 124

EIA-MVS		95.11 112	95.27 99	94.64 228	96.34 202	86.51 303	99.59 62	96.62 243	92.51 105	94.08 165	98.64 121	86.05 139	98.24 218	95.07 145	98.50 124	99.18 125

Patchmatch-test		86.25 350	84.06 368	92.82 293	94.42 307	82.88 382	82.88 486	94.23 424	71.58 458	79.39 393	90.62 397	89.00 74	96.42 348	63.03 463	91.37 285	99.16 126

test_fmvsmconf0.01_n		94.14 147	93.51 154	96.04 146	86.79 449	89.19 215	99.28 108	95.94 315	95.70 32	95.50 138	98.49 134	73.27 326	99.79 103	98.28 66	98.32 132	99.15 127

gg-mvs-nofinetune		90.00 281	87.71 307	96.89 91	96.15 213	94.69 51	85.15 475	97.74 94	68.32 471	92.97 194	60.16 490	96.10 4	96.84 326	93.89 174	98.87 100	99.14 128

MVS_Test		93.67 166	92.67 182	96.69 101	96.72 185	92.66 106	97.22 340	96.03 301	87.69 283	95.12 146	94.03 312	81.55 226	98.28 215	89.17 256	96.46 172	99.14 128

casdiffmvs_mvg		94.00 150	93.33 161	96.03 147	95.22 257	90.90 158	99.09 139	95.99 303	90.58 161	91.55 228	97.37 192	79.91 246	98.06 245	95.01 147	95.22 201	99.13 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test2506		94.80 124	94.21 125	96.58 109	96.41 198	92.18 120	98.01 292	98.96 11	90.82 152	93.46 182	97.28 199	85.92 140	98.45 208	89.82 242	97.19 158	99.12 131

ECVR-MVS		92.29 216	91.33 222	95.15 203	96.41 198	87.84 265	98.10 278	94.84 404	90.82 152	91.42 232	97.28 199	65.61 396	98.49 206	90.33 236	97.19 158	99.12 131

MonoMVSNet		90.69 259	89.78 256	93.45 279	91.78 385	84.97 353	96.51 368	94.44 416	90.56 162	85.96 303	90.97 384	78.61 269	96.27 364	95.35 137	83.79 337	99.11 133

HyFIR lowres test		93.68 165	93.29 163	94.87 216	97.57 137	88.04 260	98.18 269	98.47 26	87.57 285	91.24 235	95.05 300	85.49 148	97.46 301	93.22 197	92.82 242	99.10 134

0.3-1-1-0.015		91.27 241	89.64 260	96.15 143	92.69 365	91.62 134	99.74 36	97.35 184	84.68 349	92.71 200	93.18 336	85.31 157	97.75 280	92.11 214	68.98 436	99.09 135

0.4-1-1-0.2		91.19 246	89.53 263	96.20 135	92.78 364	91.76 131	99.76 32	97.34 185	84.77 345	92.54 204	93.05 340	84.51 169	97.74 283	92.01 215	68.98 436	99.09 135

fmvsm_s_conf0.5_n_10		96.95 35	96.82 40	97.33 62	97.76 124	93.00 96	99.87 6	97.95 63	97.32 9	99.71 4	99.20 41	81.48 229	99.90 61	99.32 23	98.78 109	99.09 135

Anonymous202405211		88.84 301	87.03 321	94.27 247	98.14 112	84.18 363	98.44 231	95.58 361	76.79 434	89.34 274	96.88 241	53.42 451	99.54 130	87.53 272	87.12 309	99.09 135

0.4-1-1-0.1		91.07 248	89.43 267	96.01 150	92.48 368	91.23 141	99.69 48	97.34 185	84.50 352	92.49 206	92.98 344	84.53 167	97.72 285	91.87 219	68.97 438	99.08 139

baseline		93.91 155	93.30 162	95.72 165	95.10 275	90.07 184	97.48 326	95.91 326	91.03 145	93.54 180	97.68 172	79.58 248	98.02 253	94.27 167	95.14 203	99.08 139

Vis-MVSNet (Re-imp)		93.26 185	93.00 174	94.06 259	96.14 215	86.71 300	98.68 189	96.70 238	88.30 256	89.71 269	97.64 175	85.43 151	96.39 349	88.06 267	96.32 176	99.08 139

test1111		92.12 221	91.19 226	94.94 214	96.15 213	87.36 286	98.12 275	94.84 404	90.85 151	90.97 237	97.26 201	65.60 397	98.37 210	89.74 245	97.14 161	99.07 142

PatchmatchNet		92.05 225	91.04 230	95.06 209	96.17 212	89.04 221	91.26 456	97.26 190	89.56 203	90.64 244	90.56 401	88.35 84	97.11 315	79.53 372	96.07 187	99.03 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPNet		96.82 40	96.68 47	97.25 68	98.65 97	93.10 92	99.48 76	98.76 14	96.54 22	97.84 75	98.22 148	87.49 99	99.66 116	95.35 137	97.78 143	99.00 144
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		94.85 123	93.94 139	97.58 49	96.43 195	94.09 66	98.93 157	99.16 8	89.50 206	95.27 142	97.85 157	81.50 228	99.65 120	92.79 206	94.02 222	98.99 145

Patchmatch-RL test		81.90 404	80.13 407	87.23 414	80.71 476	70.12 471	84.07 481	88.19 483	83.16 375	70.57 450	82.18 468	87.18 108	92.59 451	82.28 353	62.78 457	98.98 146

PVSNet	87.13 12	93.69 163	92.83 179	96.28 130	97.99 117	90.22 177	99.38 95	98.93 12	91.42 136	93.66 177	97.68 172	71.29 347	99.64 122	87.94 268	97.20 157	98.98 146

MVSFormer		94.71 130	94.08 131	96.61 106	95.05 278	94.87 41	97.77 307	96.17 287	86.84 301	98.04 69	98.52 129	85.52 145	95.99 377	89.83 240	98.97 92	98.96 148

jason		95.40 104	94.86 112	97.03 76	92.91 361	94.23 62	99.70 41	96.30 272	93.56 82	96.73 108	98.52 129	81.46 231	97.91 259	96.08 118	98.47 126	98.96 148
jason: jason.
CostFormer		92.89 197	92.48 189	94.12 256	94.99 282	85.89 332	92.89 437	97.00 223	86.98 298	95.00 148	90.78 388	90.05 63	97.51 299	92.92 204	91.73 272	98.96 148

MAR-MVS		94.43 139	94.09 130	95.45 179	99.10 75	87.47 282	98.39 246	97.79 87	88.37 252	94.02 167	99.17 50	78.64 268	99.91 56	92.48 208	98.85 101	98.96 148
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
MDTV_nov1_ep13_2view						91.17 146	91.38 454		87.45 288	93.08 188		86.67 123		87.02 276		98.95 152

EC-MVSNet		95.09 113	95.17 102	94.84 218	95.42 247	88.17 256	99.48 76	95.92 320	91.47 133	97.34 85	98.36 142	82.77 201	97.41 305	97.24 86	98.58 120	98.94 153

FA-MVS(test-final)		92.22 220	91.08 229	95.64 170	96.05 220	88.98 228	91.60 451	97.25 191	86.99 295	91.84 219	92.12 353	83.03 194	99.00 175	86.91 280	93.91 223	98.93 154

CVMVSNet		90.30 272	90.91 235	88.46 402	94.32 315	73.58 457	97.61 322	97.59 137	90.16 179	88.43 282	97.10 216	76.83 285	92.86 446	82.64 345	93.54 232	98.93 154

SymmetryMVS		95.49 99	95.27 99	96.17 139	97.13 166	90.37 170	99.14 130	98.59 23	94.92 45	96.30 117	97.98 155	85.33 155	99.23 160	94.35 164	93.67 231	98.92 156

ab-mvs		91.05 251	89.17 273	96.69 101	95.96 223	91.72 132	92.62 441	97.23 195	85.61 329	89.74 267	93.89 319	68.55 365	99.42 145	91.09 225	87.84 305	98.92 156

IS-MVSNet		93.00 196	92.51 187	94.49 236	96.14 215	87.36 286	98.31 255	95.70 349	88.58 243	90.17 256	97.50 183	83.02 195	97.22 311	87.06 275	96.07 187	98.90 158

viewmanbaseed2359cas		93.90 156	93.34 160	95.56 177	95.39 250	89.72 200	98.58 213	96.00 302	90.32 171	93.58 179	97.78 162	78.71 266	98.07 243	94.43 163	95.29 199	98.88 159

CPTT-MVS		94.60 133	94.43 120	95.09 206	99.66 17	86.85 297	99.44 85	97.47 163	83.22 373	94.34 161	98.96 88	82.50 209	99.55 128	94.81 153	99.50 59	98.88 159

Vis-MVSNet		92.64 206	91.85 210	95.03 212	95.12 267	88.23 255	98.48 227	96.81 231	91.61 128	92.16 214	97.22 206	71.58 345	98.00 255	85.85 301	97.81 140	98.88 159
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
casdiffmvs		93.98 152	93.43 156	95.61 175	95.07 277	89.86 194	98.80 170	95.84 335	90.98 146	92.74 199	97.66 174	79.71 247	98.10 234	94.72 156	95.37 198	98.87 162
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GSMVS																98.84 163

sam_mvs1												88.39 83				98.84 163

SCA		90.64 262	89.25 272	94.83 219	94.95 286	88.83 236	96.26 378	97.21 197	90.06 184	90.03 260	90.62 397	66.61 388	96.81 328	83.16 337	94.36 216	98.84 163

PMMVS		93.62 168	93.90 143	92.79 294	96.79 183	81.40 400	98.85 164	96.81 231	91.25 141	96.82 103	98.15 152	77.02 284	98.13 230	93.15 200	96.30 178	98.83 166

ETV-MVS		96.00 73	96.00 73	96.00 151	96.56 188	91.05 152	99.63 59	96.61 244	93.26 88	97.39 83	98.30 145	86.62 124	98.13 230	98.07 70	97.57 147	98.82 167

viewdifsd2359ckpt09		93.54 171	92.91 176	95.44 181	95.57 238	89.48 207	98.68 189	95.66 357	89.52 205	92.50 205	97.75 165	78.46 270	98.03 251	93.32 190	94.69 209	98.81 168

1112_ss		92.71 203	91.55 218	96.20 135	95.56 240	91.12 147	98.48 227	94.69 411	88.29 257	86.89 297	98.50 131	87.02 113	98.66 197	84.75 311	89.77 300	98.81 168

Test_1112_low_res		92.27 218	90.97 233	96.18 137	95.53 242	91.10 149	98.47 230	94.66 412	88.28 258	86.83 298	93.50 330	87.00 114	98.65 198	84.69 312	89.74 301	98.80 170

PatchT		85.44 364	83.19 375	92.22 307	93.13 357	83.00 377	83.80 483	96.37 268	70.62 461	90.55 247	79.63 479	84.81 164	94.87 422	58.18 475	91.59 274	98.79 171

PVSNet_Blended		95.94 79	95.66 88	96.75 95	98.77 94	91.61 136	99.88 5	98.04 57	93.64 80	94.21 162	97.76 164	83.50 181	99.87 75	97.41 82	97.75 144	98.79 171

GDP-MVS		96.05 72	95.63 92	97.31 63	95.37 252	94.65 52	99.36 99	96.42 262	92.14 121	97.07 92	98.53 127	93.33 22	98.50 202	91.76 221	96.66 171	98.78 173

DeepC-MVS	91.02 4	94.56 136	93.92 140	96.46 115	97.16 164	90.76 160	98.39 246	97.11 210	93.92 66	88.66 279	98.33 143	78.14 273	99.85 85	95.02 146	98.57 121	98.78 173
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
guyue		94.21 145	93.72 150	95.66 169	95.22 257	90.17 179	98.74 178	96.85 229	93.67 77	93.01 192	96.72 252	78.83 262	98.06 245	96.04 119	94.44 214	98.77 175

tpmrst		92.78 202	92.16 201	94.65 226	96.27 205	87.45 283	91.83 447	97.10 213	89.10 223	94.68 153	90.69 392	88.22 86	97.73 284	89.78 243	91.80 270	98.77 175

原ACMM1				96.18 137	99.03 78	90.08 183		97.63 128	88.98 225	97.00 94	98.97 83	88.14 90	99.71 112	88.23 264	99.62 50	98.76 177

viewmacassd2359aftdt		93.16 189	92.44 190	95.31 191	94.34 311	89.19 215	98.40 241	95.84 335	89.62 199	92.87 196	97.31 198	76.07 294	98.00 255	92.93 202	94.58 212	98.75 178

icg_test_0407_2		91.56 234	90.90 236	93.54 276	94.61 301	86.22 315	95.72 399	95.72 344	88.78 233	89.76 265	96.93 234	77.24 282	95.65 401	86.73 285	92.59 248	98.74 179

IMVS_0407		91.79 230	90.98 232	94.24 251	94.61 301	86.22 315	96.45 370	95.72 344	88.78 233	89.76 265	96.93 234	77.24 282	97.77 273	86.73 285	92.59 248	98.74 179

IMVS_0404		89.79 284	88.57 293	93.47 278	94.61 301	86.22 315	94.45 413	95.72 344	88.78 233	81.88 360	96.93 234	65.39 400	95.47 407	86.73 285	92.59 248	98.74 179

IMVS_0403		91.93 227	91.13 227	94.34 243	94.61 301	86.22 315	96.70 363	95.72 344	88.78 233	90.00 262	96.93 234	78.07 274	98.07 243	86.73 285	92.59 248	98.74 179

fmvsm_s_conf0.5_n_5		96.46 59	96.23 62	97.15 73	96.42 196	92.80 103	99.83 15	97.39 177	94.50 52	98.71 39	99.13 60	82.52 208	99.90 61	99.24 30	98.38 128	98.74 179

AstraMVS		93.38 179	93.01 172	94.50 235	93.94 331	86.55 301	98.91 160	95.86 333	93.88 70	92.88 195	97.49 184	75.61 304	98.21 221	96.15 114	92.39 255	98.73 184

E3new		94.19 146	93.78 148	95.43 182	95.81 228	89.44 209	98.80 170	96.11 291	90.24 173	93.85 172	97.75 165	80.94 239	98.14 227	95.00 148	95.48 197	98.72 185

tpm2		91.77 231	91.09 228	93.82 269	94.83 293	85.56 340	92.51 442	97.16 205	84.00 359	93.83 174	90.66 394	87.54 98	97.17 312	87.73 270	91.55 276	98.72 185

TAPA-MVS	87.50 9	90.35 269	89.05 278	94.25 249	98.48 102	85.17 348	98.42 235	96.58 251	82.44 393	87.24 292	98.53 127	82.77 201	98.84 183	59.09 473	97.88 139	98.72 185
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
EI-MVSNet-Vis-set		95.76 90	95.63 92	96.17 139	99.14 71	90.33 172	98.49 225	97.82 79	91.92 123	94.75 151	98.88 102	87.06 112	99.48 138	95.40 136	97.17 160	98.70 188

viewdifsd2359ckpt13		93.45 173	92.86 178	95.21 199	95.45 245	88.91 235	98.59 210	95.92 320	89.39 212	92.67 202	97.33 197	78.02 275	98.03 251	93.27 192	95.12 204	98.69 189

viewcassd2359sk11		93.95 153	93.48 155	95.36 185	95.48 244	89.25 213	98.74 178	96.10 292	90.10 180	93.48 181	97.55 181	80.05 244	98.14 227	94.66 158	95.16 202	98.69 189

FE-MVS		91.38 239	90.16 252	95.05 211	96.46 194	87.53 280	89.69 465	97.84 74	82.97 379	92.18 213	92.00 359	84.07 176	98.93 179	80.71 366	95.52 195	98.68 191

E2		93.62 168	93.07 167	95.26 196	95.00 281	88.99 227	98.63 198	96.09 297	89.84 188	93.02 190	97.36 193	78.88 258	98.11 232	94.23 169	94.60 210	98.67 192

E3		93.62 168	93.07 167	95.26 196	94.98 283	89.00 226	98.63 198	96.09 297	89.83 189	93.01 192	97.35 195	78.90 257	98.11 232	94.23 169	94.60 210	98.67 192

GeoE		90.60 265	89.56 262	93.72 275	95.10 275	85.43 341	99.41 92	94.94 402	83.96 361	87.21 293	96.83 247	74.37 313	97.05 319	80.50 370	93.73 230	98.67 192

diffmvs		94.59 134	94.19 126	95.81 161	95.54 241	90.69 162	98.70 185	95.68 352	91.61 128	95.96 123	97.81 159	80.11 243	98.06 245	96.52 106	95.76 190	98.67 192
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DP-MVS		88.75 307	86.56 327	95.34 188	98.92 88	87.45 283	97.64 321	93.52 437	70.55 462	81.49 367	97.25 203	74.43 312	99.88 71	71.14 433	94.09 220	98.67 192

BP-MVS1		96.59 52	96.36 58	97.29 64	95.05 278	94.72 49	99.44 85	97.45 166	92.71 102	96.41 115	98.50 131	94.11 17	98.50 202	95.61 132	97.97 137	98.66 197

ETVMVS		94.50 137	93.90 143	96.31 128	97.48 143	92.98 97	99.07 141	97.86 71	88.09 263	94.40 158	96.90 238	88.35 84	97.28 310	90.72 234	92.25 262	98.66 197

TESTMET0.1,1		93.82 160	93.26 164	95.49 178	95.21 259	90.25 174	99.15 127	97.54 148	89.18 216	91.79 220	94.87 302	89.13 71	97.63 291	86.21 294	96.29 180	98.60 199

casdiffseed414692147		91.84 229	90.69 243	95.28 194	94.50 306	89.32 211	98.31 255	95.67 354	87.82 275	90.22 255	96.63 257	74.27 315	97.94 258	86.37 291	92.43 254	98.59 200

E4		93.15 191	92.50 188	95.09 206	94.41 308	88.61 243	98.48 227	95.99 303	89.40 211	92.22 212	97.13 213	77.43 279	98.10 234	93.58 182	93.90 224	98.56 201

dp		90.16 278	88.83 285	94.14 255	96.38 201	86.42 306	91.57 452	97.06 216	84.76 346	88.81 277	90.19 413	84.29 173	97.43 304	75.05 405	91.35 286	98.56 201

EPP-MVSNet		93.75 162	93.67 151	94.01 262	95.86 226	85.70 337	98.67 192	97.66 115	84.46 353	91.36 233	97.18 210	91.16 37	97.79 271	92.93 202	93.75 229	98.53 203

Fast-Effi-MVS+		91.72 232	90.79 241	94.49 236	95.89 224	87.40 285	99.54 71	95.70 349	85.01 341	89.28 275	95.68 286	77.75 277	97.57 298	83.22 336	95.06 205	98.51 204

fmvsm_s_conf0.5_n_6		96.78 43	96.64 48	97.20 70	96.03 221	93.20 89	99.82 19	97.68 109	95.20 42	99.61 6	99.11 67	84.52 168	99.90 61	99.04 38	98.77 110	98.50 205

CDS-MVSNet		93.47 172	93.04 171	94.76 220	94.75 296	89.45 208	98.82 167	97.03 219	87.91 270	90.97 237	96.48 261	89.06 72	96.36 351	89.50 246	92.81 244	98.49 206
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
LCM-MVSNet-Re		88.59 312	88.61 290	88.51 401	95.53 242	72.68 462	96.85 355	88.43 482	88.45 247	73.14 441	90.63 396	75.82 299	94.38 431	92.95 201	95.71 192	98.48 207

myMVS_eth3d28		95.74 93	95.34 96	96.92 86	97.41 144	93.58 78	99.28 108	97.70 103	90.97 147	93.91 170	97.25 203	90.59 52	98.75 190	96.85 97	94.14 219	98.44 208

TAMVS		92.62 207	92.09 204	94.20 253	94.10 323	87.68 269	98.41 238	96.97 225	87.53 287	89.74 267	96.04 276	84.77 166	96.49 344	88.97 258	92.31 259	98.42 209

CR-MVSNet		88.83 303	87.38 314	93.16 285	93.47 348	86.24 313	84.97 477	94.20 425	88.92 230	90.76 242	86.88 444	84.43 171	94.82 424	70.64 434	92.17 264	98.41 210

RPMNet		85.07 369	81.88 388	94.64 228	93.47 348	86.24 313	84.97 477	97.21 197	64.85 479	90.76 242	78.80 481	80.95 238	99.27 159	53.76 481	92.17 264	98.41 210

BH-RMVSNet		91.25 244	89.99 253	95.03 212	96.75 184	88.55 246	98.65 194	94.95 401	87.74 280	87.74 286	97.80 160	68.27 368	98.14 227	80.53 369	97.49 151	98.41 210

viewdifsd2359ckpt07		92.71 203	92.19 196	94.28 246	94.96 285	86.26 312	98.29 259	95.80 337	88.71 239	90.81 239	97.34 196	76.57 287	98.19 223	93.16 198	94.05 221	98.39 213

UA-Net		93.30 182	92.62 185	95.34 188	96.27 205	88.53 248	95.88 392	96.97 225	90.90 148	95.37 141	97.07 223	82.38 216	99.10 171	83.91 329	94.86 207	98.38 214

tpm		89.67 286	88.95 280	91.82 319	92.54 367	81.43 399	92.95 436	95.92 320	87.81 276	90.50 249	89.44 422	84.99 160	95.65 401	83.67 334	82.71 346	98.38 214

MVS_111021_LR		95.78 88	95.94 74	95.28 194	98.19 110	87.69 268	98.80 170	99.26 7	93.39 85	95.04 147	98.69 118	84.09 175	99.76 108	96.96 93	99.06 86	98.38 214

diffmvs_AUTHOR		94.30 142	93.92 140	95.45 179	94.77 295	89.92 191	98.55 218	95.68 352	91.33 138	95.83 131	97.64 175	79.58 248	98.05 248	96.19 111	95.66 193	98.37 217

NormalMVS		95.87 82	95.83 78	95.99 152	99.27 62	90.37 170	99.14 130	96.39 264	94.92 45	96.30 117	97.98 155	85.33 155	99.23 160	94.35 164	98.82 102	98.37 217

KinetiMVS		93.07 194	91.98 206	96.34 125	94.84 292	91.78 128	98.73 181	97.18 202	91.25 141	94.01 168	97.09 220	71.02 348	98.86 181	86.77 284	96.89 166	98.37 217

test-LLR		93.11 192	92.68 181	94.40 240	94.94 287	87.27 290	99.15 127	97.25 191	90.21 174	91.57 225	94.04 310	84.89 162	97.58 295	85.94 298	96.13 183	98.36 220

test-mter		93.27 184	92.89 177	94.40 240	94.94 287	87.27 290	99.15 127	97.25 191	88.95 227	91.57 225	94.04 310	88.03 92	97.58 295	85.94 298	96.13 183	98.36 220

IB-MVS	89.43 6	92.12 221	90.83 240	95.98 154	95.40 249	90.78 159	99.81 20	98.06 53	91.23 143	85.63 307	93.66 325	90.63 51	98.78 185	91.22 224	71.85 425	98.36 220
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
VDD-MVS		91.24 245	90.18 251	94.45 239	97.08 170	85.84 335	98.40 241	96.10 292	86.99 295	93.36 184	98.16 151	54.27 447	99.20 162	96.59 104	90.63 294	98.31 223

UBG		95.73 94	95.41 94	96.69 101	96.97 175	93.23 87	99.13 135	97.79 87	91.28 140	94.38 160	96.78 248	92.37 33	98.56 201	96.17 113	93.84 225	98.26 224

testing91		94.88 120	94.44 119	96.21 134	97.19 160	91.90 126	99.23 113	97.66 115	89.91 186	93.66 177	97.05 226	90.21 61	98.50 202	93.52 183	91.53 280	98.25 225

testing222		94.48 138	94.00 133	95.95 155	97.30 152	92.27 117	98.82 167	97.92 67	89.20 214	94.82 149	97.26 201	87.13 109	97.32 309	91.95 217	91.56 275	98.25 225

PVSNet_Blended_VisFu		94.67 131	94.11 129	96.34 125	97.14 165	91.10 149	99.32 104	97.43 172	92.10 122	91.53 229	96.38 266	83.29 187	99.68 114	93.42 189	96.37 175	98.25 225

thisisatest0515		94.75 126	94.19 126	96.43 117	96.13 218	92.64 109	99.47 78	97.60 133	87.55 286	93.17 186	97.59 178	94.71 13	98.42 209	88.28 263	93.20 238	98.24 228

EI-MVSNet-UG-set		95.43 101	95.29 98	95.86 159	99.07 77	89.87 193	98.43 232	97.80 85	91.78 125	94.11 164	98.77 107	86.25 136	99.48 138	94.95 151	96.45 173	98.22 229

QAPM		91.41 238	89.49 265	97.17 72	95.66 235	93.42 84	98.60 208	97.51 155	80.92 412	81.39 369	97.41 189	72.89 332	99.87 75	82.33 351	98.68 113	98.21 230

CHOSEN 280x420		96.80 41	96.85 36	96.66 104	97.85 122	94.42 58	94.76 411	98.36 31	92.50 106	95.62 137	97.52 182	97.92 1	97.38 306	98.31 65	98.80 105	98.20 231

testing11		95.33 105	94.98 111	96.37 123	97.20 158	92.31 116	99.29 105	97.68 109	90.59 160	94.43 156	97.20 207	90.79 50	98.60 199	95.25 141	92.38 256	98.18 232

TR-MVS		90.77 256	89.44 266	94.76 220	96.31 203	88.02 261	97.92 296	95.96 312	85.52 330	88.22 283	97.23 205	66.80 385	98.09 236	84.58 315	92.38 256	98.17 233

E5new		92.80 198	92.19 196	94.62 230	94.34 311	87.64 272	98.08 284	95.97 306	89.15 217	92.01 215	97.08 221	76.37 290	98.08 238	93.25 193	93.46 233	98.15 234

E6new		92.80 198	92.19 196	94.62 230	94.31 319	87.64 272	98.08 284	95.97 306	89.15 217	92.01 215	97.10 216	76.38 288	98.08 238	93.25 193	93.45 235	98.15 234

E6		92.80 198	92.19 196	94.62 230	94.31 319	87.64 272	98.08 284	95.97 306	89.15 217	92.01 215	97.10 216	76.38 288	98.08 238	93.25 193	93.45 235	98.15 234

E5		92.80 198	92.19 196	94.62 230	94.34 311	87.64 272	98.08 284	95.97 306	89.15 217	92.01 215	97.08 221	76.37 290	98.08 238	93.25 193	93.46 233	98.15 234

viewmambaseed2359dif		93.05 195	92.64 183	94.25 249	94.94 287	86.53 302	98.38 248	95.69 351	87.03 294	93.38 183	97.74 168	78.79 264	98.08 238	93.49 186	94.35 217	98.15 234

testing99		94.88 120	94.45 118	96.17 139	97.20 158	91.91 125	99.20 115	97.66 115	89.95 185	93.68 176	97.06 224	90.28 60	98.50 202	93.52 183	91.54 277	98.12 239

GA-MVS		90.10 279	88.69 288	94.33 244	92.44 369	87.97 263	99.08 140	96.26 276	89.65 196	86.92 296	93.11 339	68.09 370	96.96 321	82.54 347	90.15 296	98.05 240

OMC-MVS		93.90 156	93.62 152	94.73 223	98.63 98	87.00 295	98.04 290	96.56 252	92.19 118	92.46 207	98.73 111	79.49 253	99.14 169	92.16 213	94.34 218	98.03 241

xiu_mvs_v2_base		96.66 48	96.17 68	98.11 30	97.11 169	96.96 7	99.01 150	97.04 217	95.51 38	98.86 34	99.11 67	82.19 219	99.36 152	98.59 52	98.14 135	98.00 242

PS-MVSNAJ		96.87 38	96.40 56	98.29 21	97.35 149	97.29 6	99.03 147	97.11 210	95.83 30	98.97 30	99.14 58	82.48 211	99.60 125	98.60 50	99.08 83	98.00 242

SD_0403		86.82 338	87.08 319	86.04 427	93.55 346	69.09 473	94.11 423	95.02 399	87.84 274	80.48 377	95.86 283	73.05 328	91.04 465	72.53 427	91.26 287	97.99 244

thisisatest0530		94.00 150	93.52 153	95.43 182	95.76 231	90.02 189	98.99 152	97.60 133	86.58 308	91.74 221	97.36 193	94.78 12	98.34 211	86.37 291	92.48 253	97.94 245

tpm cat1		88.89 299	87.27 316	93.76 272	95.79 229	85.32 345	90.76 461	97.09 214	76.14 437	85.72 306	88.59 428	82.92 196	98.04 250	76.96 391	91.43 282	97.90 246

testing3-2		95.17 110	94.78 113	96.33 127	97.35 149	92.35 115	99.85 12	98.43 28	90.60 159	92.84 197	97.00 228	90.89 45	98.89 180	95.95 122	90.12 297	97.76 247

tttt0517		93.30 182	93.01 172	94.17 254	95.57 238	86.47 305	98.51 222	97.60 133	85.99 321	90.55 247	97.19 209	94.80 11	98.31 212	85.06 307	91.86 268	97.74 248

mamba_0408		90.65 261	89.16 274	95.12 204	95.12 267	89.81 196	83.02 484	95.17 397	85.95 322	89.50 270	96.85 242	75.85 297	97.82 267	87.19 273	93.79 226	97.73 249

SSM_04072		90.31 271	89.16 274	93.74 273	95.12 267	89.81 196	83.02 484	95.17 397	85.95 322	89.50 270	96.85 242	75.85 297	93.69 438	87.19 273	93.79 226	97.73 249

SSM_0407		92.04 226	91.03 231	95.07 208	95.12 267	89.81 196	97.18 343	95.49 370	86.17 317	89.50 270	97.13 213	75.65 301	97.68 286	89.26 254	93.79 226	97.73 249

mvsany_test1		94.57 135	95.09 107	92.98 288	95.84 227	82.07 393	98.76 177	95.24 390	92.87 101	96.45 113	98.71 116	84.81 164	99.15 165	97.68 78	95.49 196	97.73 249

h-mvs33		92.47 212	91.95 208	94.05 260	97.13 166	85.01 351	98.36 250	98.08 50	93.85 72	96.27 119	96.73 251	83.19 191	99.43 144	95.81 125	68.09 440	97.70 253

ADS-MVSNet2		87.62 328	86.88 323	89.86 373	96.21 208	79.14 422	87.15 469	92.99 440	83.01 377	89.91 263	87.27 440	78.87 260	92.80 449	74.20 413	92.27 260	97.64 254

ADS-MVSNet		88.99 296	87.30 315	94.07 258	96.21 208	87.56 279	87.15 469	96.78 234	83.01 377	89.91 263	87.27 440	78.87 260	97.01 320	74.20 413	92.27 260	97.64 254

BH-w/o		92.32 215	91.79 213	93.91 266	96.85 178	86.18 321	99.11 138	95.74 343	88.13 261	84.81 312	97.00 228	77.26 281	97.91 259	89.16 257	98.03 136	97.64 254

SSM_0404		92.33 214	91.33 222	95.33 190	95.35 253	90.54 167	97.45 327	95.49 370	86.17 317	90.26 254	97.13 213	75.65 301	97.82 267	89.26 254	95.26 200	97.63 257

LS3D		90.19 275	88.72 287	94.59 234	98.97 80	86.33 311	96.90 353	96.60 245	74.96 449	84.06 321	98.74 110	75.78 300	99.83 91	74.93 406	97.57 147	97.62 258

VDDNet		90.08 280	88.54 295	94.69 225	94.41 308	87.68 269	98.21 267	96.40 263	76.21 436	93.33 185	97.75 165	54.93 445	98.77 186	94.71 157	90.96 289	97.61 259

EPNet_dtu		92.28 217	92.15 202	92.70 300	97.29 153	84.84 354	98.64 196	97.82 79	92.91 97	93.02 190	97.02 227	85.48 150	95.70 399	72.25 429	94.89 206	97.55 260
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsm_n_1920		97.08 32	97.55 15	95.67 168	97.94 119	89.61 205	99.93 1	98.48 25	97.08 12	99.08 25	99.13 60	88.17 87	99.93 46	99.11 36	99.06 86	97.47 261

fmvsm_s_conf0.5_n_3		96.58 54	96.55 50	96.66 104	97.23 156	92.59 111	99.81 20	97.82 79	97.35 7	99.42 10	99.16 51	80.27 242	99.93 46	99.26 26	98.60 119	97.45 262

BH-untuned		91.46 237	90.84 238	93.33 282	96.51 192	84.83 355	98.84 166	95.50 369	86.44 315	83.50 323	96.70 253	75.49 305	97.77 273	86.78 283	97.81 140	97.40 263

thres200		93.69 163	92.59 186	96.97 83	97.76 124	94.74 48	99.35 101	99.36 2	89.23 213	91.21 236	96.97 230	83.42 184	98.77 186	85.08 306	90.96 289	97.39 264

viewdifsd2359ckpt11		90.42 267	89.65 258	92.73 299	93.71 343	82.67 385	98.09 281	95.27 385	89.80 192	90.10 259	97.40 190	69.43 359	98.18 225	92.46 209	80.61 358	97.34 265

viewmsd2359difaftdt		90.43 266	89.65 258	92.74 297	93.72 342	82.67 385	98.09 281	95.27 385	89.80 192	90.12 258	97.40 190	69.43 359	98.20 222	92.45 210	80.62 357	97.34 265

JIA-IIPM		85.97 354	84.85 353	89.33 389	93.23 355	73.68 456	85.05 476	97.13 208	69.62 467	91.56 227	68.03 488	88.03 92	96.96 321	77.89 386	93.12 239	97.34 265

baseline1		92.61 208	91.28 224	96.58 109	97.05 173	94.63 53	97.72 312	96.20 280	89.82 190	88.56 280	96.85 242	86.85 116	97.82 267	88.42 261	80.10 362	97.30 268

PVSNet_0	83.28 16	87.31 331	85.16 347	93.74 273	94.78 294	84.59 357	98.91 160	98.69 20	89.81 191	78.59 407	93.23 335	61.95 417	99.34 156	94.75 154	55.72 480	97.30 268

UWE-MVS		93.18 186	93.40 158	92.50 304	96.56 188	83.55 371	98.09 281	97.84 74	89.50 206	91.72 222	96.23 269	91.08 40	96.70 332	86.28 293	93.33 237	97.26 270

PLC	91.07 3	94.23 144	94.01 132	94.87 216	99.17 70	87.49 281	99.25 112	96.55 253	88.43 250	91.26 234	98.21 150	85.92 140	99.86 81	89.77 244	97.57 147	97.24 271
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Anonymous20240529		87.66 327	85.58 341	93.92 265	97.59 135	85.01 351	98.13 273	97.13 208	66.69 476	88.47 281	96.01 277	55.09 443	99.51 132	87.00 277	84.12 332	97.23 272

thres100view900		93.34 181	92.15 202	96.90 87	97.62 131	94.84 43	99.06 144	99.36 2	87.96 268	90.47 250	96.78 248	83.29 187	98.75 190	84.11 323	90.69 291	97.12 273

tfpn200view9		93.43 175	92.27 194	96.90 87	97.68 128	94.84 43	99.18 118	99.36 2	88.45 247	90.79 240	96.90 238	83.31 185	98.75 190	84.11 323	90.69 291	97.12 273

tpmvs		89.16 292	87.76 305	93.35 281	97.19 160	84.75 356	90.58 463	97.36 182	81.99 398	84.56 314	89.31 425	83.98 177	98.17 226	74.85 408	90.00 299	97.12 273

PCF-MVS	89.78 5	91.26 242	89.63 261	96.16 142	95.44 246	91.58 138	95.29 405	96.10 292	85.07 338	82.75 335	97.45 187	78.28 272	99.78 106	80.60 368	95.65 194	97.12 273
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MIMVSNet		84.48 377	81.83 389	92.42 305	91.73 387	87.36 286	85.52 472	94.42 420	81.40 404	81.91 359	87.58 434	51.92 454	92.81 448	73.84 417	88.15 304	97.08 277

CANet_DTU		94.31 141	93.35 159	97.20 70	97.03 174	94.71 50	98.62 201	95.54 363	95.61 36	97.21 88	98.47 138	71.88 340	99.84 87	88.38 262	97.46 152	97.04 278

PatchMatch-RL		91.47 236	90.54 246	94.26 248	98.20 108	86.36 310	96.94 351	97.14 206	87.75 279	88.98 276	95.75 285	71.80 342	99.40 149	80.92 364	97.39 154	97.02 279

fmvsm_s_conf0.5_n_a		95.97 76	96.19 63	95.31 191	96.51 192	89.01 225	99.81 20	98.39 29	95.46 39	99.19 24	99.16 51	81.44 232	99.91 56	98.83 44	96.97 163	97.01 280

test_fmvsmvis_n_1920		95.47 100	95.40 95	95.70 166	94.33 314	90.22 177	99.70 41	96.98 224	96.80 16	92.75 198	98.89 100	82.46 214	99.92 49	98.36 61	98.33 130	96.97 281

UGNet		91.91 228	90.85 237	95.10 205	97.06 171	88.69 242	98.01 292	98.24 36	92.41 110	92.39 210	93.61 326	60.52 423	99.68 114	88.14 265	97.25 156	96.92 282
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
test_vis1_n_1920		93.08 193	93.42 157	92.04 314	96.31 203	79.36 419	99.83 15	96.06 300	96.72 18	98.53 51	98.10 153	58.57 428	99.91 56	97.86 74	98.79 108	96.85 283

fmvsm_s_conf0.5_n		96.19 67	96.49 52	95.30 193	97.37 148	89.16 217	99.86 9	98.47 26	95.68 34	98.87 33	99.15 55	82.44 215	99.92 49	99.14 34	97.43 153	96.83 284

LuminaMVS		93.16 189	92.30 192	95.76 163	92.26 372	92.64 109	97.60 324	96.21 279	90.30 172	93.06 189	95.59 287	76.00 295	97.89 261	94.93 152	94.70 208	96.76 285

Elysia		90.62 263	88.95 280	95.64 170	93.08 358	91.94 123	97.65 319	96.39 264	84.72 347	90.59 245	95.95 279	62.22 414	98.23 219	83.69 332	96.23 181	96.74 286

StellarMVS		90.62 263	88.95 280	95.64 170	93.08 358	91.94 123	97.65 319	96.39 264	84.72 347	90.59 245	95.95 279	62.22 414	98.23 219	83.69 332	96.23 181	96.74 286

fmvsm_s_conf0.1_n_a		95.16 111	95.15 103	95.18 202	92.06 377	88.94 231	99.29 105	97.53 149	94.46 54	98.98 29	98.99 81	79.99 245	99.85 85	98.24 68	96.86 167	96.73 288

test_cas_vis1_n_1920		93.86 159	93.74 149	94.22 252	95.39 250	86.08 325	99.73 37	96.07 299	96.38 26	97.19 90	97.78 162	65.46 399	99.86 81	96.71 98	98.92 96	96.73 288

fmvsm_s_conf0.5_n_11		96.80 41	96.97 29	96.28 130	98.09 113	92.26 118	99.87 6	96.49 260	97.55 4	99.75 3	99.32 28	83.20 190	99.91 56	99.57 13	98.88 99	96.67 290

fmvsm_s_conf0.1_n		95.56 98	95.68 87	95.20 201	94.35 310	89.10 219	99.50 74	97.67 114	94.76 49	98.68 42	99.03 77	81.13 236	99.86 81	98.63 49	97.36 155	96.63 291

thres600view7		93.18 186	92.00 205	96.75 95	97.62 131	94.92 38	99.07 141	99.36 2	87.96 268	90.47 250	96.78 248	83.29 187	98.71 195	82.93 341	90.47 295	96.61 292

thres400		93.39 177	92.27 194	96.73 97	97.68 128	94.84 43	99.18 118	99.36 2	88.45 247	90.79 240	96.90 238	83.31 185	98.75 190	84.11 323	90.69 291	96.61 292

xiu_mvs_v1_base_debu		94.73 127	93.98 134	96.99 79	95.19 260	95.24 29	98.62 201	96.50 256	92.99 94	97.52 79	98.83 104	72.37 335	99.15 165	97.03 89	96.74 168	96.58 294

xiu_mvs_v1_base		94.73 127	93.98 134	96.99 79	95.19 260	95.24 29	98.62 201	96.50 256	92.99 94	97.52 79	98.83 104	72.37 335	99.15 165	97.03 89	96.74 168	96.58 294

xiu_mvs_v1_base_debi		94.73 127	93.98 134	96.99 79	95.19 260	95.24 29	98.62 201	96.50 256	92.99 94	97.52 79	98.83 104	72.37 335	99.15 165	97.03 89	96.74 168	96.58 294

F-COLMAP		92.07 224	91.75 215	93.02 287	98.16 111	82.89 381	98.79 175	95.97 306	86.54 310	87.92 284	97.80 160	78.69 267	99.65 120	85.97 296	95.93 189	96.53 297

fmvsm_s_conf0.5_n_7		95.87 82	96.25 61	94.72 224	96.19 211	87.74 267	99.66 50	97.94 65	95.78 31	98.44 53	99.23 35	81.26 235	99.90 61	99.17 33	98.57 121	96.52 298

fmvsm_s_conf0.5_n_4		96.17 68	96.49 52	95.21 199	97.06 171	89.26 212	99.76 32	98.07 51	95.99 28	99.35 15	99.22 37	82.19 219	99.89 69	99.06 37	97.68 145	96.49 299

test_vis1_n		90.40 268	90.27 250	90.79 348	91.55 389	76.48 443	99.12 137	94.44 416	94.31 57	97.34 85	96.95 231	43.60 473	99.42 145	97.57 80	97.60 146	96.47 300

test_fmvs1		92.35 213	92.94 175	90.57 353	97.19 160	75.43 449	99.55 66	94.97 400	95.20 42	96.82 103	97.57 180	59.59 426	99.84 87	97.30 85	98.29 133	96.46 301

AUN-MVS		90.17 277	89.50 264	92.19 309	96.21 208	82.67 385	97.76 310	97.53 149	88.05 264	91.67 223	96.15 271	83.10 193	97.47 300	88.11 266	66.91 446	96.43 302

hse-mvs2		91.67 233	91.51 219	92.15 311	96.22 207	82.61 389	97.74 311	97.53 149	93.85 72	96.27 119	96.15 271	83.19 191	97.44 303	95.81 125	66.86 447	96.40 303

MSDG		88.29 316	86.37 329	94.04 261	96.90 177	86.15 323	96.52 367	94.36 422	77.89 429	79.22 396	96.95 231	69.72 355	99.59 126	73.20 422	92.58 252	96.37 304

UniMVSNet_ETH3D		85.65 363	83.79 372	91.21 336	90.41 404	80.75 412	95.36 403	95.78 338	78.76 423	81.83 365	94.33 308	49.86 463	96.66 333	84.30 318	83.52 340	96.22 305

dmvs_re		88.69 309	88.06 303	90.59 352	93.83 338	78.68 426	95.75 398	96.18 285	87.99 267	84.48 317	96.32 267	67.52 376	96.94 323	84.98 309	85.49 322	96.14 306

OpenMVS	85.28 14	90.75 257	88.84 284	96.48 114	93.58 345	93.51 82	98.80 170	97.41 174	82.59 387	78.62 402	97.49 184	68.00 372	99.82 94	84.52 317	98.55 123	96.11 307

test_fmvs1_n		91.07 248	91.41 221	90.06 367	94.10 323	74.31 453	99.18 118	94.84 404	94.81 47	96.37 116	97.46 186	50.86 460	99.82 94	97.14 88	97.90 138	96.04 308

fmvsm_s_conf0.5_n_2		95.85 84	95.83 78	95.91 157	97.19 160	91.79 127	99.78 28	97.65 122	97.23 10	99.22 22	99.06 73	75.93 296	99.90 61	99.30 24	97.09 162	96.02 309

baseline2		94.04 149	93.80 147	94.74 222	93.07 360	90.25 174	98.12 275	98.16 42	89.86 187	86.53 300	96.95 231	95.56 6	98.05 248	91.44 223	94.53 213	95.93 310

fmvsm_s_conf0.1_n_2		95.24 109	95.04 109	95.83 160	95.60 236	91.71 133	99.65 52	96.18 285	96.99 15	98.79 37	98.91 96	73.91 320	99.87 75	99.00 40	96.30 178	95.91 311

UWE-MVS-28		90.99 252	91.93 209	88.15 403	95.12 267	77.87 436	97.18 343	97.79 87	88.72 238	88.69 278	96.52 258	86.54 128	90.75 466	84.64 314	92.16 266	95.83 312

DSMNet-mixed		81.60 405	81.43 393	82.10 453	84.36 458	60.79 482	93.63 428	86.74 486	79.00 419	79.32 395	87.15 442	63.87 407	89.78 473	66.89 452	91.92 267	95.73 313

cascas		90.93 254	89.33 270	95.76 163	95.69 233	93.03 95	98.99 152	96.59 248	80.49 414	86.79 299	94.45 307	65.23 401	98.60 199	93.52 183	92.18 263	95.66 314

SDMVSNet		91.09 247	89.91 254	94.65 226	96.80 181	90.54 167	97.78 305	97.81 83	88.34 254	85.73 304	95.26 297	66.44 391	98.26 216	94.25 168	86.75 310	95.14 315

sd_testset		89.23 291	88.05 304	92.74 297	96.80 181	85.33 344	95.85 395	97.03 219	88.34 254	85.73 304	95.26 297	61.12 421	97.76 279	85.61 302	86.75 310	95.14 315

tt0805		86.50 346	84.79 355	91.63 330	91.97 378	81.49 398	96.49 369	97.38 178	82.24 395	82.44 343	95.82 284	51.22 457	98.25 217	84.55 316	80.96 356	95.13 317

XVG-OURS-SEG-HR		90.95 253	90.66 245	91.83 317	95.18 263	81.14 407	95.92 389	95.92 320	88.40 251	90.33 253	97.85 157	70.66 351	99.38 150	92.83 205	88.83 302	94.98 318

XVG-OURS		90.83 255	90.49 247	91.86 316	95.23 256	81.25 404	95.79 397	95.92 320	88.96 226	90.02 261	98.03 154	71.60 344	99.35 155	91.06 226	87.78 306	94.98 318

sc_t1		78.53 423	74.87 434	89.48 387	87.92 438	77.36 439	94.80 410	90.61 471	57.65 483	76.28 418	89.59 421	38.25 480	96.18 367	74.04 415	64.72 453	94.91 320

Effi-MVS+-dtu		89.97 282	90.68 244	87.81 407	95.15 264	71.98 464	97.87 300	95.40 379	91.92 123	87.57 287	91.44 374	74.27 315	96.84 326	89.45 247	93.10 240	94.60 321

Fast-Effi-MVS+-dtu		88.84 301	88.59 292	89.58 382	93.44 351	78.18 430	98.65 194	94.62 413	88.46 246	84.12 320	95.37 295	68.91 362	96.52 341	82.06 355	91.70 273	94.06 322

test0.0.03 1		88.96 297	88.61 290	90.03 371	91.09 396	84.43 359	98.97 155	97.02 221	90.21 174	80.29 380	96.31 268	84.89 162	91.93 460	72.98 423	85.70 321	93.73 323

MVS-HIRNet		79.01 418	75.13 432	90.66 351	93.82 339	81.69 397	85.16 474	93.75 432	54.54 486	74.17 433	59.15 492	57.46 432	96.58 337	63.74 460	94.38 215	93.72 324

AllTest		84.97 370	83.12 376	90.52 356	96.82 179	78.84 424	95.89 390	92.17 451	77.96 427	75.94 422	95.50 290	55.48 439	99.18 163	71.15 431	87.14 307	93.55 325

TestCases				90.52 356	96.82 179	78.84 424		92.17 451	77.96 427	75.94 422	95.50 290	55.48 439	99.18 163	71.15 431	87.14 307	93.55 325

RPSCF		85.33 365	85.55 342	84.67 439	94.63 300	62.28 481	93.73 426	93.76 431	74.38 452	85.23 311	97.06 224	64.09 404	98.31 212	80.98 362	86.08 318	93.41 327

kuosan		84.40 380	83.34 374	87.60 409	95.87 225	79.21 420	92.39 443	96.87 228	76.12 438	73.79 435	93.98 315	81.51 227	90.63 467	64.13 459	75.42 387	92.95 328

Syy-MVS		84.10 385	84.53 361	82.83 449	95.14 265	65.71 478	97.68 315	96.66 240	86.52 311	82.63 338	96.84 245	68.15 369	89.89 471	45.62 487	91.54 277	92.87 329

myMVS_eth3d		88.68 311	89.07 277	87.50 411	95.14 265	79.74 417	97.68 315	96.66 240	86.52 311	82.63 338	96.84 245	85.22 159	89.89 471	69.43 440	91.54 277	92.87 329

HQP4-MVS										87.57 287			97.77 273			92.72 331

HQP-MVS		91.50 235	91.23 225	92.29 306	93.95 328	86.39 308	99.16 122	96.37 268	93.92 66	87.57 287	96.67 255	73.34 323	97.77 273	93.82 178	86.29 313	92.72 331

HQP_MVS		91.26 242	90.95 234	92.16 310	93.84 336	86.07 327	99.02 148	96.30 272	93.38 86	86.99 294	96.52 258	72.92 330	97.75 280	93.46 187	86.17 316	92.67 333

plane_prior5								96.30 272					97.75 280	93.46 187	86.17 316	92.67 333

nrg030		90.23 273	88.87 283	94.32 245	91.53 390	93.54 81	98.79 175	95.89 329	88.12 262	84.55 315	94.61 306	78.80 263	96.88 325	92.35 212	75.21 389	92.53 335

CLD-MVS		91.06 250	90.71 242	92.10 312	94.05 327	86.10 324	99.55 66	96.29 275	94.16 61	84.70 313	97.17 211	69.62 357	97.82 267	94.74 155	86.08 318	92.39 336
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
VPNet		88.30 315	86.57 326	93.49 277	91.95 380	91.35 140	98.18 269	97.20 201	88.61 241	84.52 316	94.89 301	62.21 416	96.76 331	89.34 250	72.26 422	92.36 337

DU-MVS		88.83 303	87.51 311	92.79 294	91.46 391	90.07 184	98.71 182	97.62 130	88.87 231	83.21 328	93.68 323	74.63 307	95.93 381	86.95 278	72.47 419	92.36 337

NR-MVSNet		87.74 326	86.00 335	92.96 290	91.46 391	90.68 163	96.65 365	97.42 173	88.02 266	73.42 438	93.68 323	77.31 280	95.83 389	84.26 319	71.82 426	92.36 337

testing3		87.75 323	88.22 300	86.36 423	94.66 299	77.41 438	99.52 72	97.95 63	86.05 320	81.12 370	96.69 254	86.18 137	89.31 476	61.65 467	90.12 297	92.35 340

FIs		90.70 258	89.87 255	93.18 284	92.29 371	91.12 147	98.17 271	98.25 34	89.11 222	83.44 324	94.82 303	82.26 217	96.17 369	87.76 269	82.76 345	92.25 341

UniMVSNet_NR-MVSNet		89.60 287	88.55 294	92.75 296	92.17 375	90.07 184	98.74 178	98.15 43	88.37 252	83.21 328	93.98 315	82.86 197	95.93 381	86.95 278	72.47 419	92.25 341

VPA-MVSNet		89.10 295	87.66 308	93.45 279	92.56 366	91.02 153	97.97 295	98.32 32	86.92 300	86.03 302	92.01 357	68.84 364	97.10 317	90.92 228	75.34 388	92.23 343

TranMVSNet+NR-MVSNet		87.75 323	86.31 330	92.07 313	90.81 399	88.56 245	98.33 252	97.18 202	87.76 278	81.87 362	93.90 318	72.45 334	95.43 409	83.13 339	71.30 429	92.23 343

dmvs_testset		77.17 431	78.99 413	71.71 466	87.25 445	38.55 503	91.44 453	81.76 494	85.77 326	69.49 456	95.94 281	69.71 356	84.37 486	52.71 483	76.82 382	92.21 345

FC-MVSNet-test		90.22 274	89.40 268	92.67 302	91.78 385	89.86 194	97.89 297	98.22 37	88.81 232	82.96 334	94.66 305	81.90 224	95.96 379	85.89 300	82.52 348	92.20 346

WBMVS		91.35 240	90.49 247	93.94 264	96.97 175	93.40 85	99.27 110	96.71 237	87.40 289	83.10 333	91.76 365	92.38 32	96.23 365	88.95 259	77.89 372	92.17 347

PS-MVSNAJss		89.54 289	89.05 278	91.00 341	88.77 426	84.36 360	97.39 329	95.97 306	88.47 244	81.88 360	93.80 321	82.48 211	96.50 342	89.34 250	83.34 342	92.15 348

testgi		82.29 399	81.00 397	86.17 425	87.24 446	74.84 452	97.39 329	91.62 461	88.63 240	75.85 425	95.42 293	46.07 470	91.55 462	66.87 453	79.94 363	92.12 349

WR-MVS		88.54 313	87.22 318	92.52 303	91.93 382	89.50 206	98.56 215	97.84 74	86.99 295	81.87 362	93.81 320	74.25 317	95.92 383	85.29 304	74.43 398	92.12 349

MVSTER		92.71 203	92.32 191	93.86 267	97.29 153	92.95 100	99.01 150	96.59 248	90.09 181	85.51 308	94.00 314	94.61 16	96.56 338	90.77 233	83.03 343	92.08 351

ACMM	86.95 13	88.77 306	88.22 300	90.43 358	93.61 344	81.34 402	98.50 223	95.92 320	87.88 271	83.85 322	95.20 299	67.20 379	97.89 261	86.90 281	84.90 325	92.06 352
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		87.75 323	86.02 334	92.95 291	90.46 403	89.70 202	97.71 314	95.90 327	84.02 358	80.95 371	94.05 309	67.51 377	97.10 317	85.16 305	78.41 369	92.04 353

FMVSNet3		88.81 305	87.08 319	93.99 263	96.52 191	94.59 54	98.08 284	96.20 280	85.85 324	82.12 351	91.60 368	74.05 318	95.40 411	79.04 376	80.24 359	91.99 354

FMVSNet2		86.90 335	84.79 355	93.24 283	95.11 272	92.54 112	97.67 317	95.86 333	82.94 380	80.55 375	91.17 381	62.89 411	95.29 414	77.23 388	79.71 365	91.90 355

usedtu_dtu_shiyan1		89.12 293	87.56 309	93.78 270	89.74 412	93.60 76	98.70 185	96.60 245	87.85 272	83.43 325	91.56 370	76.34 292	95.92 383	82.75 342	81.08 353	91.82 356

FE-MVSNET3		89.12 293	87.56 309	93.78 270	89.74 412	93.60 76	98.70 185	96.60 245	87.85 272	83.43 325	91.56 370	76.34 292	95.92 383	82.75 342	81.08 353	91.82 356

UniMVSNet (Re)		89.50 290	88.32 298	93.03 286	92.21 374	90.96 155	98.90 162	98.39 29	89.13 221	83.22 327	92.03 355	81.69 225	96.34 357	86.79 282	72.53 418	91.81 358

EU-MVSNet		84.19 382	84.42 364	83.52 447	88.64 429	67.37 477	96.04 387	95.76 342	85.29 333	78.44 409	93.18 336	70.67 350	91.48 463	75.79 402	75.98 384	91.70 359

SSC-MVS3.2		85.22 366	83.90 371	89.17 392	91.87 383	79.84 416	97.66 318	96.63 242	86.81 303	81.99 357	91.35 376	55.80 436	96.00 376	76.52 397	76.53 383	91.67 360

VortexMVS		90.18 276	89.28 271	92.89 292	95.58 237	90.94 157	97.82 302	95.94 315	90.90 148	82.11 355	91.48 373	78.75 265	96.08 373	91.99 216	78.97 366	91.65 361

EI-MVSNet		89.87 283	89.38 269	91.36 335	94.32 315	85.87 333	97.61 322	96.59 248	85.10 336	85.51 308	97.10 216	81.30 234	96.56 338	83.85 331	83.03 343	91.64 362

IterMVS-LS		88.34 314	87.44 312	91.04 340	94.10 323	85.85 334	98.10 278	95.48 373	85.12 335	82.03 356	91.21 380	81.35 233	95.63 403	83.86 330	75.73 386	91.63 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		86.67 341	84.96 349	91.80 320	95.11 272	88.81 237	96.77 357	95.25 387	82.94 380	82.12 351	90.25 408	62.89 411	94.97 419	79.04 376	80.24 359	91.62 364

test1		86.67 341	84.96 349	91.80 320	95.11 272	88.81 237	96.77 357	95.25 387	82.94 380	82.12 351	90.25 408	62.89 411	94.97 419	79.04 376	80.24 359	91.62 364

FMVSNet1		83.94 386	81.32 395	91.80 320	91.94 381	88.81 237	96.77 357	95.25 387	77.98 425	78.25 411	90.25 408	50.37 462	94.97 419	73.27 421	77.81 377	91.62 364

cl22		89.57 288	88.79 286	91.91 315	97.94 119	87.62 276	97.98 294	96.51 255	85.03 339	82.37 347	91.79 362	83.65 179	96.50 342	85.96 297	77.89 372	91.61 367

eth_miper_zixun_eth		87.76 322	87.00 322	90.06 367	94.67 298	82.65 388	97.02 350	95.37 381	84.19 356	81.86 364	91.58 369	81.47 230	95.90 387	83.24 335	73.61 407	91.61 367

Anonymous20231211		84.72 372	82.65 384	90.91 343	97.71 127	84.55 358	97.28 335	96.67 239	66.88 475	79.18 397	90.87 387	58.47 429	96.60 335	82.61 346	74.20 402	91.59 369

miper_enhance_ethall		90.33 270	89.70 257	92.22 307	97.12 168	88.93 233	98.35 251	95.96 312	88.60 242	83.14 332	92.33 352	87.38 101	96.18 367	86.49 290	77.89 372	91.55 370

jajsoiax		87.35 330	86.51 328	89.87 372	87.75 443	81.74 396	97.03 348	95.98 305	88.47 244	80.15 382	93.80 321	61.47 418	96.36 351	89.44 248	84.47 329	91.50 371

blend_shiyan4		86.02 352	84.08 367	91.83 317	83.24 464	88.24 251	98.42 235	95.51 365	75.55 446	79.43 392	86.84 446	84.51 169	95.77 391	83.97 327	69.26 433	91.48 372

ACMP	87.39 10	88.71 308	88.24 299	90.12 366	93.91 334	81.06 408	98.50 223	95.67 354	89.43 209	80.37 379	95.55 288	65.67 394	97.83 266	90.55 235	84.51 327	91.47 373
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LPG-MVS_test		88.86 300	88.47 296	90.06 367	93.35 353	80.95 409	98.22 265	95.94 315	87.73 281	83.17 330	96.11 273	66.28 392	97.77 273	90.19 238	85.19 323	91.46 374

LGP-MVS_train				90.06 367	93.35 353	80.95 409		95.94 315	87.73 281	83.17 330	96.11 273	66.28 392	97.77 273	90.19 238	85.19 323	91.46 374

mvs_tets		87.09 333	86.22 331	89.71 378	87.87 439	81.39 401	96.73 362	95.90 327	88.19 260	79.99 384	93.61 326	59.96 425	96.31 359	89.40 249	84.34 330	91.43 376

DIV-MVS_self_test		87.82 320	86.81 324	90.87 346	94.87 291	85.39 343	97.81 303	95.22 395	82.92 383	80.76 373	91.31 378	81.99 221	95.81 390	81.36 360	75.04 391	91.42 377

cl____		87.82 320	86.79 325	90.89 345	94.88 290	85.43 341	97.81 303	95.24 390	82.91 384	80.71 374	91.22 379	81.97 223	95.84 388	81.34 361	75.06 390	91.40 378

wanda-best-256-512		83.28 391	80.44 402	91.78 325	82.91 466	88.24 251	98.43 232	95.51 365	75.76 440	78.60 404	86.54 449	66.95 382	95.71 397	82.44 349	56.84 473	91.38 379

FE-blended-shiyan7		83.27 392	80.44 402	91.78 325	82.91 466	88.24 251	98.43 232	95.51 365	75.76 440	78.60 404	86.54 449	66.93 383	95.71 397	82.44 349	56.84 473	91.38 379

usedtu_blend_shiyan5		82.04 401	78.78 414	91.80 320	82.91 466	88.24 251	94.33 416	92.37 448	66.55 477	78.60 404	86.54 449	66.93 383	95.77 391	83.97 327	56.84 473	91.38 379

blended_shiyan6		83.17 394	80.34 406	91.67 329	82.80 471	87.93 264	98.29 259	95.51 365	75.63 444	78.46 408	86.48 452	66.74 387	95.70 399	82.33 351	56.84 473	91.37 382

blended_shiyan8		83.22 393	80.40 405	91.71 328	82.77 472	88.01 262	98.25 263	95.49 370	75.64 443	78.68 400	86.55 447	66.76 386	95.75 393	82.50 348	56.93 472	91.36 383

miper_ehance_all_eth		88.94 298	88.12 302	91.40 332	95.32 254	86.93 296	97.85 301	95.55 362	84.19 356	81.97 358	91.50 372	84.16 174	95.91 386	84.69 312	77.89 372	91.36 383

CP-MVSNet		86.54 344	85.45 344	89.79 376	91.02 398	82.78 384	97.38 331	97.56 143	85.37 332	79.53 391	93.03 341	71.86 341	95.25 415	79.92 371	73.43 413	91.34 385

test_djsdf		88.26 317	87.73 306	89.84 374	88.05 436	82.21 391	97.77 307	96.17 287	86.84 301	82.41 346	91.95 361	72.07 338	95.99 377	89.83 240	84.50 328	91.32 386

v2v482		87.27 332	85.76 338	91.78 325	89.59 415	87.58 278	98.56 215	95.54 363	84.53 351	82.51 342	91.78 363	73.11 327	96.47 345	82.07 354	74.14 404	91.30 387

c3_l		88.19 318	87.23 317	91.06 339	94.97 284	86.17 322	97.72 312	95.38 380	83.43 370	81.68 366	91.37 375	82.81 200	95.72 396	84.04 326	73.70 406	91.29 388

OPM-MVS		89.76 285	89.15 276	91.57 331	90.53 402	85.58 339	98.11 277	95.93 319	92.88 100	86.05 301	96.47 262	67.06 381	97.87 264	89.29 253	86.08 318	91.26 389
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
gbinet_0.2-2-1-0.02		83.16 395	80.42 404	91.39 334	83.70 462	87.60 277	98.62 201	95.77 340	75.83 439	79.33 394	87.92 431	64.07 405	95.34 412	81.87 358	56.67 477	91.25 390

reproduce_monomvs		92.11 223	91.82 212	92.98 288	98.25 105	90.55 166	98.38 248	97.93 66	94.81 47	80.46 378	92.37 351	96.46 3	97.17 312	94.06 171	73.61 407	91.23 391

PS-CasMVS		85.81 358	84.58 360	89.49 386	90.77 400	82.11 392	97.20 341	97.36 182	84.83 344	79.12 398	92.84 345	67.42 378	95.16 417	78.39 384	73.25 414	91.21 392

pmmvs5		85.87 355	84.40 365	90.30 363	88.53 430	84.23 361	98.60 208	93.71 433	81.53 403	80.29 380	92.02 356	64.51 403	95.52 405	82.04 356	78.34 370	91.15 393

miper_lstm_enhance		86.90 335	86.20 332	89.00 396	94.53 305	81.19 405	96.74 361	95.24 390	82.33 394	80.15 382	90.51 404	81.99 221	94.68 428	80.71 366	73.58 409	91.12 394

COLMAP_ROB	82.69 18	84.54 376	82.82 378	89.70 379	96.72 185	78.85 423	95.89 390	92.83 443	71.55 459	77.54 416	95.89 282	59.40 427	99.14 169	67.26 450	88.26 303	91.11 395
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PEN-MVS		85.21 367	83.93 370	89.07 395	89.89 409	81.31 403	97.09 346	97.24 194	84.45 354	78.66 401	92.68 348	68.44 367	94.87 422	75.98 400	70.92 430	91.04 396

ACMH	83.09 17	84.60 374	82.61 385	90.57 353	93.18 356	82.94 378	96.27 376	94.92 403	81.01 410	72.61 447	93.61 326	56.54 434	97.79 271	74.31 411	81.07 355	90.99 397
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		84.13 384	83.59 373	85.77 431	87.81 440	70.24 469	94.89 409	93.65 435	86.08 319	76.53 417	93.28 334	61.41 419	96.14 371	80.95 363	77.69 378	90.93 398

XVG-ACMP-BASELINE		85.86 356	84.95 351	88.57 400	89.90 408	77.12 440	94.30 418	95.60 360	87.40 289	82.12 351	92.99 343	53.42 451	97.66 288	85.02 308	83.83 334	90.92 399

Patchmtry		83.61 390	81.64 390	89.50 384	93.36 352	82.84 383	84.10 480	94.20 425	69.47 468	79.57 390	86.88 444	84.43 171	94.78 425	68.48 446	74.30 400	90.88 400

IterMVS		85.81 358	84.67 358	89.22 390	93.51 347	83.67 370	96.32 375	94.80 407	85.09 337	78.69 399	90.17 414	66.57 390	93.17 445	79.48 374	77.42 379	90.81 401
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		86.02 352	84.44 363	90.77 349	89.32 421	85.20 346	98.10 278	95.35 383	82.19 396	82.25 349	90.71 390	70.73 349	96.30 362	76.85 393	74.49 397	90.80 402

v144192		86.40 347	84.89 352	90.91 343	89.48 419	85.59 338	98.21 267	95.43 378	82.45 392	82.62 340	90.58 400	72.79 333	96.36 351	78.45 383	74.04 405	90.79 403

v1192		86.32 349	84.71 357	91.17 337	89.53 418	86.40 307	98.13 273	95.44 377	82.52 390	82.42 345	90.62 397	71.58 345	96.33 358	77.23 388	74.88 392	90.79 403

IterMVS-SCA-FT		85.73 361	84.64 359	89.00 396	93.46 350	82.90 380	96.27 376	94.70 410	85.02 340	78.62 402	90.35 406	66.61 388	93.33 442	79.38 375	77.36 380	90.76 405

dongtai		81.36 406	80.61 398	83.62 445	94.25 322	73.32 458	95.15 407	96.81 231	73.56 455	69.79 453	92.81 346	81.00 237	86.80 484	52.08 484	70.06 432	90.75 406

SixPastTwentyTwo		82.63 398	81.58 391	85.79 430	88.12 435	71.01 467	95.17 406	92.54 446	84.33 355	72.93 445	92.08 354	60.41 424	95.61 404	74.47 410	74.15 403	90.75 406

v1240		85.77 360	84.11 366	90.73 350	89.26 422	85.15 349	97.88 299	95.23 394	81.89 401	82.16 350	90.55 402	69.60 358	96.31 359	75.59 403	74.87 393	90.72 408

v148		86.38 348	85.06 348	90.37 362	89.47 420	84.10 364	98.52 219	95.48 373	83.80 363	80.93 372	90.22 411	74.60 309	96.31 359	80.92 364	71.55 427	90.69 409

K. test v3		81.04 408	79.77 410	84.83 437	87.41 444	70.23 470	95.60 401	93.93 429	83.70 366	67.51 465	89.35 424	55.76 437	93.58 441	76.67 395	68.03 441	90.67 410

v1144		86.83 337	85.31 346	91.40 332	89.75 411	87.21 294	98.31 255	95.45 375	83.22 373	82.70 337	90.78 388	73.36 322	96.36 351	79.49 373	74.69 395	90.63 411

ACMH+	83.78 15	84.21 381	82.56 387	89.15 393	93.73 341	79.16 421	96.43 371	94.28 423	81.09 409	74.00 434	94.03 312	54.58 446	97.67 287	76.10 399	78.81 368	90.63 411

lessismore_v0				85.08 435	85.59 455	69.28 472		90.56 472		67.68 464	90.21 412	54.21 448	95.46 408	73.88 416	62.64 458	90.50 413

pmmvs4		87.58 329	86.17 333	91.80 320	89.58 416	88.92 234	97.25 337	95.28 384	82.54 389	80.49 376	93.17 338	75.62 303	96.05 375	82.75 342	78.90 367	90.42 414

WR-MVS_H		86.53 345	85.49 343	89.66 381	91.04 397	83.31 375	97.53 325	98.20 38	84.95 342	79.64 388	90.90 386	78.01 276	95.33 413	76.29 398	72.81 415	90.35 415

V42		87.00 334	85.68 340	90.98 342	89.91 407	86.08 325	98.32 254	95.61 359	83.67 367	82.72 336	90.67 393	74.00 319	96.53 340	81.94 357	74.28 401	90.32 416

DTE-MVSNet		84.14 383	82.80 379	88.14 404	88.95 425	79.87 415	96.81 356	96.24 277	83.50 369	77.60 415	92.52 350	67.89 374	94.24 433	72.64 426	69.05 435	90.32 416

YYNet1		79.64 417	77.04 422	87.43 413	87.80 441	79.98 414	96.23 380	94.44 416	73.83 454	51.83 485	87.53 435	67.96 373	92.07 459	66.00 455	67.75 444	90.23 418

MDA-MVSNet_test_wron		79.65 416	77.05 421	87.45 412	87.79 442	80.13 413	96.25 379	94.44 416	73.87 453	51.80 486	87.47 439	68.04 371	92.12 458	66.02 454	67.79 443	90.09 419

MDA-MVSNet-bldmvs		77.82 429	74.75 435	87.03 415	88.33 432	78.52 428	96.34 374	92.85 442	75.57 445	48.87 488	87.89 432	57.32 433	92.49 454	60.79 468	64.80 452	90.08 420

our_test_3		84.47 378	82.80 379	89.50 384	89.01 423	83.90 367	97.03 348	94.56 414	81.33 405	75.36 428	90.52 403	71.69 343	94.54 430	68.81 444	76.84 381	90.07 421

v7n		84.42 379	82.75 382	89.43 388	88.15 434	81.86 395	96.75 360	95.67 354	80.53 413	78.38 410	89.43 423	69.89 353	96.35 356	73.83 418	72.13 423	90.07 421

v8		86.11 351	84.45 362	91.10 338	89.99 406	86.85 297	97.24 338	95.36 382	81.99 398	79.89 386	89.86 417	74.53 311	96.39 349	78.83 380	72.32 421	90.05 423

PVSNet_BlendedMVS		93.36 180	93.20 165	93.84 268	98.77 94	91.61 136	99.47 78	98.04 57	91.44 134	94.21 162	92.63 349	83.50 181	99.87 75	97.41 82	83.37 341	90.05 423

ITE_SJBPF				87.93 405	92.26 372	76.44 444		93.47 438	87.67 284	79.95 385	95.49 292	56.50 435	97.38 306	75.24 404	82.33 349	89.98 425

pm-mvs1		84.68 373	82.78 381	90.40 359	89.58 416	85.18 347	97.31 333	94.73 409	81.93 400	76.05 421	92.01 357	65.48 398	96.11 372	78.75 381	69.14 434	89.91 426

test_fmvs2		85.10 368	85.45 344	84.02 442	89.85 410	65.63 479	98.49 225	92.59 445	90.45 166	85.43 310	93.32 331	43.94 471	96.59 336	90.81 231	84.19 331	89.85 427

LTVRE_ROB	81.71 19	84.59 375	82.72 383	90.18 364	92.89 362	83.18 376	93.15 433	94.74 408	78.99 420	75.14 429	92.69 347	65.64 395	97.63 291	69.46 439	81.82 351	89.74 428
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
anonymousdsp		86.69 340	85.75 339	89.53 383	86.46 451	82.94 378	96.39 372	95.71 348	83.97 360	79.63 389	90.70 391	68.85 363	95.94 380	86.01 295	84.02 333	89.72 429

ppachtmachnet_test		83.63 389	81.57 392	89.80 375	89.01 423	85.09 350	97.13 345	94.50 415	78.84 421	76.14 420	91.00 383	69.78 354	94.61 429	63.40 461	74.36 399	89.71 430

v10		85.73 361	84.01 369	90.87 346	90.03 405	86.73 299	97.20 341	95.22 395	81.25 406	79.85 387	89.75 418	73.30 325	96.28 363	76.87 392	72.64 417	89.61 431

UnsupCasMVSNet_eth		78.90 419	76.67 424	85.58 432	82.81 470	74.94 451	91.98 446	96.31 271	84.64 350	65.84 473	87.71 433	51.33 456	92.23 456	72.89 424	56.50 479	89.56 432

test_method		70.10 446	68.66 449	74.41 465	86.30 453	55.84 487	94.47 412	89.82 475	35.18 494	66.15 471	84.75 460	30.54 486	77.96 495	70.40 437	60.33 465	89.44 433

USDC		84.74 371	82.93 377	90.16 365	91.73 387	83.54 372	95.00 408	93.30 439	88.77 237	73.19 440	93.30 333	53.62 450	97.65 290	75.88 401	81.54 352	89.30 434

FMVSNet5		82.29 399	80.54 399	87.52 410	93.79 340	84.01 365	93.73 426	92.47 447	76.92 432	74.27 432	86.15 454	63.69 409	89.24 477	69.07 442	74.79 394	89.29 435

Anonymous20231206		80.76 409	79.42 412	84.79 438	84.78 457	72.98 459	96.53 366	92.97 441	79.56 418	74.33 431	88.83 426	61.27 420	92.15 457	60.59 469	75.92 385	89.24 436

pmmvs6		79.90 413	77.31 420	87.67 408	84.17 459	78.13 432	95.86 394	93.68 434	67.94 472	72.67 446	89.62 420	50.98 459	95.75 393	74.80 409	66.04 448	89.14 437

tt0320-xc		75.92 435	72.23 444	87.01 416	88.40 431	78.15 431	93.57 430	89.15 480	55.46 484	69.66 455	85.79 456	38.20 481	93.85 436	69.72 438	60.08 466	89.03 438

tt0320		76.58 432	73.16 440	86.86 419	88.03 437	77.60 437	93.55 431	90.63 469	55.37 485	70.93 449	84.98 457	41.57 475	94.01 435	69.02 443	64.32 454	88.97 439

N_pmnet		70.19 445	69.87 447	71.12 468	88.24 433	30.63 507	95.85 395	28.70 506	70.18 464	68.73 459	86.55 447	64.04 406	93.81 437	53.12 482	73.46 411	88.94 440

usedtu_dtu_shiyan2		69.89 447	65.80 452	82.15 452	69.90 493	68.09 476	93.09 434	90.63 469	58.33 482	61.56 478	79.31 480	28.96 488	89.43 475	57.76 476	52.68 486	88.92 441

D2MVS		87.96 319	87.39 313	89.70 379	91.84 384	83.40 373	98.31 255	98.49 24	88.04 265	78.23 412	90.26 407	73.57 321	96.79 330	84.21 320	83.53 339	88.90 442

KD-MVS_2432*1600		82.98 396	80.52 400	90.38 360	94.32 315	88.98 228	92.87 438	95.87 331	80.46 415	73.79 435	87.49 437	82.76 203	93.29 443	70.56 435	46.53 492	88.87 443

miper_refine_blended		82.98 396	80.52 400	90.38 360	94.32 315	88.98 228	92.87 438	95.87 331	80.46 415	73.79 435	87.49 437	82.76 203	93.29 443	70.56 435	46.53 492	88.87 443

CL-MVSNet_self_test		79.89 414	78.34 415	84.54 440	81.56 474	75.01 450	96.88 354	95.62 358	81.10 408	75.86 424	85.81 455	68.49 366	90.26 469	63.21 462	56.51 478	88.35 445

MIMVSNet1		75.92 435	73.30 439	83.81 444	81.29 475	75.57 448	92.26 444	92.05 454	73.09 457	67.48 466	86.18 453	40.87 478	87.64 482	55.78 478	70.68 431	88.21 446

TransMVSNet (Re)		81.97 402	79.61 411	89.08 394	89.70 414	84.01 365	97.26 336	91.85 457	78.84 421	73.07 444	91.62 367	67.17 380	95.21 416	67.50 449	59.46 468	88.02 447

MS-PatchMatch		86.75 339	85.92 336	89.22 390	91.97 378	82.47 390	96.91 352	96.14 289	83.74 364	77.73 414	93.53 329	58.19 430	97.37 308	76.75 394	98.35 129	87.84 448

Baseline_NR-MVSNet		85.83 357	84.82 354	88.87 399	88.73 427	83.34 374	98.63 198	91.66 459	80.41 417	82.44 343	91.35 376	74.63 307	95.42 410	84.13 322	71.39 428	87.84 448

WB-MVSnew		88.69 309	88.34 297	89.77 377	94.30 321	85.99 330	98.14 272	97.31 189	87.15 293	87.85 285	96.07 275	69.91 352	95.52 405	72.83 425	91.47 281	87.80 450

ambc				79.60 459	72.76 491	56.61 486	76.20 490	92.01 455		68.25 461	80.23 477	23.34 490	94.73 426	73.78 419	60.81 464	87.48 451

KD-MVS_self_test		77.47 430	75.88 427	82.24 450	81.59 473	68.93 474	92.83 440	94.02 428	77.03 431	73.14 441	83.39 462	55.44 441	90.42 468	67.95 447	57.53 471	87.38 452

TinyColmap		80.42 411	77.94 416	87.85 406	92.09 376	78.58 427	93.74 425	89.94 474	74.99 448	69.77 454	91.78 363	46.09 469	97.58 295	65.17 458	77.89 372	87.38 452

TDRefinement		78.01 427	75.31 430	86.10 426	70.06 492	73.84 455	93.59 429	91.58 462	74.51 451	73.08 443	91.04 382	49.63 465	97.12 314	74.88 407	59.47 467	87.33 454

CMPMVS	58.40 21	80.48 410	80.11 408	81.59 456	85.10 456	59.56 484	94.14 422	95.95 314	68.54 470	60.71 479	93.31 332	55.35 442	97.87 264	83.06 340	84.85 326	87.33 454
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LF4IMVS		81.94 403	81.17 396	84.25 441	87.23 447	68.87 475	93.35 432	91.93 456	83.35 372	75.40 427	93.00 342	49.25 467	96.65 334	78.88 379	78.11 371	87.22 456

tfpnnormal		83.65 388	81.35 394	90.56 355	91.37 393	88.06 259	97.29 334	97.87 70	78.51 424	76.20 419	90.91 385	64.78 402	96.47 345	61.71 466	73.50 410	87.13 457

EG-PatchMatch MVS		79.92 412	77.59 418	86.90 418	87.06 448	77.90 435	96.20 383	94.06 427	74.61 450	66.53 469	88.76 427	40.40 479	96.20 366	67.02 451	83.66 338	86.61 458

test20.03		78.51 424	77.48 419	81.62 455	83.07 465	71.03 466	96.11 385	92.83 443	81.66 402	69.31 457	89.68 419	57.53 431	87.29 483	58.65 474	68.47 439	86.53 459

ttmdpeth		79.80 415	77.91 417	85.47 433	83.34 463	75.75 446	95.32 404	91.45 464	76.84 433	74.81 430	91.71 366	53.98 449	94.13 434	72.42 428	61.29 461	86.51 460

MVP-Stereo		86.61 343	85.83 337	88.93 398	88.70 428	83.85 368	96.07 386	94.41 421	82.15 397	75.64 426	91.96 360	67.65 375	96.45 347	77.20 390	98.72 111	86.51 460
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
OpenMVS_ROB	73.86 20	77.99 428	75.06 433	86.77 420	83.81 461	77.94 434	96.38 373	91.53 463	67.54 473	68.38 460	87.13 443	43.94 471	96.08 373	55.03 480	81.83 350	86.29 462

Anonymous20240521		78.63 422	76.90 423	83.82 443	82.82 469	72.86 460	95.72 399	93.57 436	73.55 456	72.17 448	84.79 459	49.69 464	92.51 453	65.29 457	74.50 396	86.09 463

FE-MVSNET2		78.42 425	75.71 428	86.55 421	78.55 482	81.99 394	95.40 402	93.86 430	81.11 407	66.27 470	81.89 469	49.29 466	91.80 461	72.03 430	63.02 455	85.86 464

mmtdpeth		83.69 387	82.59 386	86.99 417	92.82 363	76.98 441	96.16 384	91.63 460	82.89 385	92.41 209	82.90 463	54.95 444	98.19 223	96.27 109	53.27 483	85.81 465

mvs5depth		78.17 426	75.56 429	85.97 428	80.43 478	76.44 444	85.46 473	89.24 479	76.39 435	78.17 413	88.26 429	51.73 455	95.73 395	69.31 441	61.09 462	85.73 466

UnsupCasMVSNet_bld		73.85 442	70.14 446	84.99 436	79.44 480	75.73 447	88.53 466	95.24 390	70.12 465	61.94 477	74.81 485	41.41 477	93.62 440	68.65 445	51.13 488	85.62 467

MVStest1		76.56 433	73.43 438	85.96 429	86.30 453	80.88 411	94.26 419	91.74 458	61.98 481	58.53 481	89.96 415	69.30 361	91.47 464	59.26 472	49.56 490	85.52 468

pmmvs-eth3d		78.71 421	76.16 426	86.38 422	80.25 479	81.19 405	94.17 421	92.13 453	77.97 426	66.90 468	82.31 467	55.76 437	92.56 452	73.63 420	62.31 460	85.38 469

PM-MVS		74.88 440	72.85 441	80.98 457	78.98 481	64.75 480	90.81 460	85.77 487	80.95 411	68.23 462	82.81 464	29.08 487	92.84 447	76.54 396	62.46 459	85.36 470

test_0402		78.81 420	76.33 425	86.26 424	91.18 395	78.44 429	95.88 392	91.34 465	68.55 469	70.51 452	89.91 416	52.65 453	94.99 418	47.14 486	79.78 364	85.34 471

test_vis1_rt		81.31 407	80.05 409	85.11 434	91.29 394	70.66 468	98.98 154	77.39 498	85.76 327	68.80 458	82.40 466	36.56 483	99.44 141	92.67 207	86.55 312	85.24 472

mvsany_test3		75.85 437	74.52 436	79.83 458	73.53 489	60.64 483	91.73 449	87.87 485	83.91 362	70.55 451	82.52 465	31.12 485	93.66 439	86.66 289	62.83 456	85.19 473

new-patchmatchnet		74.80 441	72.40 442	81.99 454	78.36 483	72.20 463	94.44 414	92.36 449	77.06 430	63.47 475	79.98 478	51.04 458	88.85 478	60.53 470	54.35 481	84.92 474

FE-MVSNET		75.08 439	72.25 443	83.56 446	77.93 484	76.96 442	94.36 415	87.96 484	75.72 442	66.01 472	81.60 471	50.48 461	88.85 478	55.38 479	60.82 463	84.86 475

test_fmvs3		75.09 438	75.19 431	74.81 463	77.45 485	54.08 489	95.93 388	90.64 468	82.51 391	73.29 439	81.19 473	22.29 491	86.29 485	85.50 303	67.89 442	84.06 476

DeepMVS_CX				76.08 461	90.74 401	51.65 494		90.84 467	86.47 314	57.89 482	87.98 430	35.88 484	92.60 450	65.77 456	65.06 451	83.97 477

pmmvs3		72.86 443	69.76 448	82.17 451	73.86 488	74.19 454	94.20 420	89.01 481	64.23 480	67.72 463	80.91 476	41.48 476	88.65 480	62.40 464	54.02 482	83.68 478

new_pmnet		76.02 434	73.71 437	82.95 448	83.88 460	72.85 461	91.26 456	92.26 450	70.44 463	62.60 476	81.37 472	47.64 468	92.32 455	61.85 465	72.10 424	83.68 478

LCM-MVSNet		60.07 454	56.37 456	71.18 467	54.81 502	48.67 495	82.17 487	89.48 478	37.95 492	49.13 487	69.12 486	13.75 499	81.76 487	59.28 471	51.63 487	83.10 480

test_f		71.94 444	70.82 445	75.30 462	72.77 490	53.28 490	91.62 450	89.66 477	75.44 447	64.47 474	78.31 482	20.48 492	89.56 474	78.63 382	66.02 449	83.05 481

APD_test1		68.93 448	66.98 450	74.77 464	80.62 477	53.15 491	87.97 467	85.01 489	53.76 487	59.26 480	87.52 436	25.19 489	89.95 470	56.20 477	67.33 445	81.19 482

PMMVS2		58.97 455	55.07 458	70.69 469	62.72 497	55.37 488	85.97 471	80.52 495	49.48 488	45.94 489	68.31 487	15.73 497	80.78 491	49.79 485	37.12 494	75.91 483

WB-MVS		66.44 449	66.29 451	66.89 471	74.84 486	44.93 498	93.00 435	84.09 492	71.15 460	55.82 483	81.63 470	63.79 408	80.31 493	21.85 496	50.47 489	75.43 484

SSC-MVS		65.42 450	65.20 453	66.06 472	73.96 487	43.83 499	92.08 445	83.54 493	69.77 466	54.73 484	80.92 475	63.30 410	79.92 494	20.48 497	48.02 491	74.44 485

FPMVS		61.57 451	60.32 454	65.34 473	60.14 500	42.44 501	91.02 459	89.72 476	44.15 489	42.63 492	80.93 474	19.02 493	80.59 492	42.50 488	72.76 416	73.00 486

ANet_high		50.71 460	46.17 463	64.33 474	44.27 504	52.30 493	76.13 491	78.73 496	64.95 478	27.37 497	55.23 494	14.61 498	67.74 497	36.01 492	18.23 497	72.95 487

EGC-MVSNET		60.70 453	55.37 457	76.72 460	86.35 452	71.08 465	89.96 464	84.44 491	0.38 503	1.50 504	84.09 461	37.30 482	88.10 481	40.85 491	73.44 412	70.97 488

testf1		56.38 456	53.73 459	64.31 475	64.84 495	45.11 496	80.50 488	75.94 500	38.87 490	42.74 490	75.07 483	11.26 501	81.19 489	41.11 489	53.27 483	66.63 489

APD_test2		56.38 456	53.73 459	64.31 475	64.84 495	45.11 496	80.50 488	75.94 500	38.87 490	42.74 490	75.07 483	11.26 501	81.19 489	41.11 489	53.27 483	66.63 489

tmp_tt		53.66 459	52.86 461	56.05 478	32.75 506	41.97 502	73.42 492	76.12 499	21.91 499	39.68 495	96.39 265	42.59 474	65.10 498	78.00 385	14.92 499	61.08 491

test_vis3_rt		61.29 452	58.75 455	68.92 470	67.41 494	52.84 492	91.18 458	59.23 505	66.96 474	41.96 493	58.44 493	11.37 500	94.72 427	74.25 412	57.97 470	59.20 492

PMVS	41.42 23	45.67 461	42.50 464	55.17 479	34.28 505	32.37 505	66.24 493	78.71 497	30.72 495	22.04 500	59.59 491	4.59 503	77.85 496	27.49 494	58.84 469	55.29 493
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	44.00 22	41.70 462	37.64 467	53.90 480	49.46 503	43.37 500	65.09 494	66.66 502	26.19 498	25.77 499	48.53 496	3.58 505	63.35 499	26.15 495	27.28 495	54.97 494
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		54.77 458	52.22 462	62.40 477	86.50 450	59.37 485	50.20 495	90.35 473	36.52 493	41.20 494	49.49 495	18.33 495	81.29 488	32.10 493	65.34 450	46.54 495
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		41.02 463	40.93 465	41.29 481	61.97 498	33.83 504	84.00 482	65.17 503	27.17 496	27.56 496	46.72 497	17.63 496	60.41 500	19.32 498	18.82 496	29.61 496

EMVS		39.96 464	39.88 466	40.18 482	59.57 501	32.12 506	84.79 479	64.57 504	26.27 497	26.14 498	44.18 500	18.73 494	59.29 501	17.03 499	17.67 498	29.12 497

test123		16.58 468	19.47 470	7.91 484	3.59 508	5.37 509	94.32 417	1.39 509	2.49 502	13.98 502	44.60 499	2.91 506	2.65 503	11.35 502	0.57 502	15.70 498

testmvs		18.81 466	23.05 469	6.10 485	4.48 507	2.29 510	97.78 305	3.00 508	3.27 501	18.60 501	62.71 489	1.53 507	2.49 504	14.26 501	1.80 501	13.50 499

wuyk23d		16.71 467	16.73 471	16.65 483	60.15 499	25.22 508	41.24 496	5.17 507	6.56 500	5.48 503	3.61 503	3.64 504	22.72 502	15.20 500	9.52 500	1.99 500

mmdepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

cdsmvs_eth3d_5k		22.52 465	30.03 468	0.00 486	0.00 509	0.00 511	0.00 497	97.17 204	0.00 504	0.00 505	98.77 107	74.35 314	0.00 505	0.00 503	0.00 503	0.00 501

pcd_1.5k_mvsjas		6.87 470	9.16 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	82.48 211	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		8.21 469	10.94 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	98.50 131	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

WAC-MVS						79.74 417								67.75 448

FOURS1					99.50 47	88.94 231	99.55 66	97.47 163	91.32 139	98.12 65

test_one_0601					99.59 33	94.89 39		97.64 124	93.14 90	98.93 32	99.45 19	93.45 21

eth-test2					0.00 509

eth-test					0.00 509

ZD-MVS					99.67 15	93.28 86		97.61 131	87.78 277	97.41 82	99.16 51	90.15 62	99.56 127	98.35 62	99.70 37

test_241102_ONE					99.63 23	95.24 29		97.72 98	94.16 61	99.30 17	99.49 14	93.32 23	99.98 13

9.14			96.87 35		99.34 55		99.50 74	97.49 160	89.41 210	98.59 46	99.43 21	89.78 65	99.69 113	98.69 46	99.62 50

save fliter					99.34 55	93.85 69	99.65 52	97.63 128	95.69 33

test0726					99.66 17	95.20 34	99.77 29	97.70 103	93.95 64	99.35 15	99.54 4	93.18 26

test_part2					99.54 41	95.42 24				98.13 63

sam_mvs												87.08 111

MTGPA								97.45 166

test_post1							90.74 462				41.37 501	85.38 153	96.36 351	83.16 337

test_post											46.00 498	87.37 102	97.11 315

patchmatchnet-post											84.86 458	88.73 79	96.81 328

MTMP							99.21 114	91.09 466

gm-plane-assit					94.69 297	88.14 257			88.22 259		97.20 207		98.29 214	90.79 232

TEST9					99.57 38	93.17 90	99.38 95	97.66 115	89.57 202	98.39 55	99.18 48	90.88 46	99.66 116

test_8					99.55 40	93.07 93	99.37 98	97.64 124	90.18 176	98.36 57	99.19 45	90.94 42	99.64 122

agg_prior					99.54 41	92.66 106		97.64 124		97.98 72			99.61 124

test_prior4						92.00 122	99.41 92

test_prior2							99.57 64		91.43 135	98.12 65	98.97 83	90.43 55		98.33 63	99.81 23

旧先验2							98.67 192		85.75 328	98.96 31			98.97 178	93.84 176

新几何2							98.26 261

原ACMM2							98.69 188

testdata2													99.88 71	84.16 321

segment_acmp												90.56 53

testdata1							97.89 297		92.43 107

plane_prior7					93.84 336	85.73 336

plane_prior6					93.92 333	86.02 329						72.92 330

plane_prior4											96.52 258

plane_prior3						85.91 331			93.65 79	86.99 294

plane_prior2							99.02 148		93.38 86

plane_prior1					93.90 335

plane_prior						86.07 327	99.14 130		93.81 75						86.26 315

n2								0.00 510

nn								0.00 510

door-mid								84.90 490

test11								97.68 109

door								85.30 488

HQP5-MVS						86.39 308

HQP-NCC					93.95 328		99.16 122		93.92 66	87.57 287

ACMP_Plane					93.95 328		99.16 122		93.92 66	87.57 287

BP-MVS														93.82 178

HQP3-MVS								96.37 268							86.29 313

HQP2-MVS												73.34 323

NP-MVS					93.94 331	86.22 315					96.67 255

MDTV_nov1_ep13			90.47 249		96.14 215	88.55 246	91.34 455	97.51 155	89.58 201	92.24 211	90.50 405	86.99 115	97.61 293	77.64 387	92.34 258

ACMMP++_ref															82.64 347

ACMMP++															83.83 334

Test By Simon												83.62 180

High-resolution multi-view benchmark