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.

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 9	99.70 19	97.98 47	97.18 2	95.96 85	99.33 19	92.62 26	100.00 1	98.99 20	99.93 1	99.98 6

NCCC		98.12 5	98.11 3	98.13 23	99.76 6	94.46 47	99.81 7	97.88 49	96.54 9	98.84 19	99.46 10	92.55 27	99.98 9	98.25 37	99.93 1	99.94 18

DVP-MVS++		98.18 2	98.09 5	98.44 15	99.61 24	95.38 21	99.55 37	97.68 80	93.01 60	99.23 8	99.45 14	95.12 8	99.98 9	99.25 15	99.92 3	99.97 7

PC_three_1452									94.60 27	99.41 2	99.12 42	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 10				99.19 28	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

MSLP-MVS++		97.50 14	97.45 15	97.63 37	99.65 16	93.21 71	99.70 19	98.13 39	94.61 26	97.78 47	99.46 10	89.85 49	99.81 70	97.97 40	99.91 6	99.88 26

DPE-MVS		98.11 6	98.00 6	98.44 15	99.50 42	95.39 20	99.29 72	97.72 71	94.50 28	98.64 22	99.54 3	93.32 19	99.97 21	99.58 9	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CNVR-MVS		98.46 1	98.38 1	98.72 8	99.80 4	96.19 14	99.80 9	97.99 46	97.05 5	99.41 2	99.59 2	92.89 25	100.00 1	98.99 20	99.90 7	99.96 10

test9_res														98.60 25	99.87 9	99.90 22

agg_prior2														97.84 44	99.87 9	99.91 21

HPM-MVS++		97.72 10	97.59 11	98.14 22	99.53 40	94.76 41	99.19 76	97.75 66	95.66 17	98.21 32	99.29 20	91.10 33	99.99 5	97.68 45	99.87 9	99.68 54

MG-MVS		97.24 17	96.83 27	98.47 14	99.79 5	95.71 17	99.07 98	99.06 9	94.45 30	96.42 79	98.70 87	88.81 59	99.74 78	95.35 91	99.86 12	99.97 7

MSP-MVS		97.77 9	98.18 2	96.53 88	99.54 36	90.14 132	99.41 59	97.70 76	95.46 21	98.60 23	99.19 28	95.71 4	99.49 102	98.15 38	99.85 13	99.95 15
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
train_agg		97.20 20	97.08 20	97.57 41	99.57 33	93.17 72	99.38 62	97.66 83	90.18 124	98.39 28	99.18 31	90.94 35	99.66 84	98.58 28	99.85 13	99.88 26

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 78					99.98 9	99.55 10	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 78					99.98 9	99.55 10	99.83 15	99.96 10

SMA-MVS		97.24 17	96.99 21	98.00 28	99.30 54	94.20 54	99.16 82	97.65 88	89.55 144	99.22 10	99.52 8	90.34 46	99.99 5	98.32 35	99.83 15	99.82 31
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
TSAR-MVS + MP.		97.44 15	97.46 14	97.39 45	99.12 65	93.49 68	98.52 156	97.50 121	94.46 29	98.99 14	98.64 90	91.58 30	99.08 138	98.49 29	99.83 15	99.60 65
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test_241102_TWO								97.72 71	94.17 33	99.23 8	99.54 3	93.14 24	99.98 9	99.70 3	99.82 19	99.99 1

DVP-MVS		98.07 7	98.00 6	98.29 18	99.66 12	95.20 29	99.72 16	97.47 126	93.95 38	99.07 12	99.46 10	93.18 22	99.97 21	99.64 6	99.82 19	99.69 53
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									93.01 60	99.07 12	99.46 10	94.66 14	99.97 21	99.25 15	99.82 19	99.95 15

test_0728_SECOND				98.77 7	99.66 12	96.37 13	99.72 16	97.68 80					99.98 9	99.64 6	99.82 19	99.96 10

SED-MVS		98.18 2	98.10 4	98.41 17	99.63 18	95.24 24	99.77 10	97.72 71	94.17 33	99.30 6	99.54 3	93.32 19	99.98 9	99.70 3	99.81 23	99.99 1

IU-MVS					99.63 18	95.38 21		97.73 70	95.54 19	99.54 1				99.69 5	99.81 23	99.99 1

test_prior2							99.57 35		91.43 95	98.12 36	98.97 56	90.43 43		98.33 34	99.81 23

DPM-MVS		97.86 8	97.25 18	99.68 1	98.25 93	99.10 1	99.76 13	97.78 63	96.61 8	98.15 33	99.53 7	93.62 17	100.00 1	91.79 147	99.80 26	99.94 18

APDe-MVS		97.53 11	97.47 13	97.70 35	99.58 30	93.63 63	99.56 36	97.52 116	93.59 53	98.01 42	99.12 42	90.80 39	99.55 96	99.26 14	99.79 27	99.93 20

CDPH-MVS		96.56 35	96.18 39	97.70 35	99.59 28	93.92 59	99.13 93	97.44 132	89.02 156	97.90 45	99.22 25	88.90 58	99.49 102	94.63 109	99.79 27	99.68 54

region2R		96.30 42	96.17 42	96.70 78	99.70 7	90.31 127	99.46 50	97.66 83	90.55 114	97.07 62	99.07 47	86.85 95	99.97 21	95.43 89	99.74 29	99.81 32

SD-MVS		97.51 13	97.40 16	97.81 33	99.01 72	93.79 62	99.33 69	97.38 139	93.73 49	98.83 20	99.02 53	90.87 38	99.88 49	98.69 23	99.74 29	99.77 42
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
HFP-MVS		96.42 38	96.26 37	96.90 66	99.69 8	90.96 114	99.47 46	97.81 58	90.54 115	96.88 64	99.05 50	87.57 76	99.96 28	95.65 82	99.72 31	99.78 37

ACMMPR		96.28 43	96.14 46	96.73 75	99.68 9	90.47 125	99.47 46	97.80 60	90.54 115	96.83 69	99.03 52	86.51 106	99.95 31	95.65 82	99.72 31	99.75 45

CP-MVS		96.22 44	96.15 45	96.42 93	99.67 10	89.62 149	99.70 19	97.61 96	90.07 130	96.00 84	99.16 34	87.43 79	99.92 39	96.03 78	99.72 31	99.70 51

test12				97.83 32	99.33 53	94.45 48		97.55 109		97.56 48		88.60 61	99.50 101		99.71 34	99.55 70

ZD-MVS					99.67 10	93.28 70		97.61 96	87.78 198	97.41 52	99.16 34	90.15 47	99.56 95	98.35 33	99.70 35

DeepC-MVS_fast	93.52 2	97.16 21	96.84 26	98.13 23	99.61 24	94.45 48	98.85 120	97.64 89	96.51 11	95.88 88	99.39 18	87.35 85	99.99 5	96.61 67	99.69 36	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APD-MVS		96.95 26	96.72 28	97.63 37	99.51 41	93.58 64	99.16 82	97.44 132	90.08 129	98.59 24	99.07 47	89.06 55	99.42 113	97.92 41	99.66 37	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SF-MVS		97.22 19	96.92 22	98.12 25	99.11 66	94.88 34	99.44 53	97.45 129	89.60 140	98.70 21	99.42 17	90.42 44	99.72 79	98.47 30	99.65 38	99.77 42

HPM-MVS		95.41 68	95.22 67	95.99 109	99.29 55	89.14 154	99.17 81	97.09 167	87.28 211	95.40 98	98.48 102	84.93 129	99.38 118	95.64 86	99.65 38	99.47 77
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test222					98.32 92	91.21 102	98.08 205	97.58 104	83.74 269	95.87 89	99.02 53	86.74 98			99.64 40	99.81 32

mPP-MVS		95.90 54	95.75 56	96.38 95	99.58 30	89.41 153	99.26 73	97.41 136	90.66 109	94.82 107	98.95 62	86.15 113	99.98 9	95.24 94	99.64 40	99.74 46

SteuartSystems-ACMMP		97.25 16	97.34 17	97.01 57	97.38 120	91.46 99	99.75 14	97.66 83	94.14 37	98.13 34	99.26 21	92.16 29	99.66 84	97.91 42	99.64 40	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS_fast		94.89 77	94.62 76	95.70 118	99.11 66	88.44 174	99.14 90	97.11 163	85.82 235	95.69 94	98.47 103	83.46 147	99.32 125	93.16 133	99.63 43	99.35 85

9.14			96.87 24		99.34 50		99.50 43	97.49 123	89.41 147	98.59 24	99.43 16	89.78 50	99.69 81	98.69 23	99.62 44

新几何1				97.40 44	98.92 77	92.51 87		97.77 65	85.52 240	96.69 74	99.06 49	88.08 70	99.89 48	84.88 225	99.62 44	99.79 35

原ACMM1				96.18 100	99.03 71	90.08 135		97.63 93	88.98 157	97.00 63	98.97 56	88.14 69	99.71 80	88.23 187	99.62 44	98.76 141

PHI-MVS		96.65 33	96.46 33	97.21 51	99.34 50	91.77 92	99.70 19	98.05 42	86.48 228	98.05 39	99.20 27	89.33 53	99.96 28	98.38 31	99.62 44	99.90 22

DELS-MVS		97.12 22	96.60 31	98.68 9	98.03 102	96.57 10	99.84 4	97.84 52	96.36 13	95.20 102	98.24 111	88.17 66	99.83 64	96.11 76	99.60 48	99.64 60
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
MP-MVS		96.00 48	95.82 52	96.54 87	99.47 46	90.13 134	99.36 66	97.41 136	90.64 112	95.49 97	98.95 62	85.51 121	99.98 9	96.00 79	99.59 49	99.52 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.09 46	95.81 54	96.95 65	99.42 47	91.19 103	99.55 37	97.53 113	89.72 135	95.86 90	98.94 65	86.59 102	99.97 21	95.13 95	99.56 50	99.68 54

MVS_111021_HR		96.69 31	96.69 29	96.72 77	98.58 88	91.00 113	99.14 90	99.45 1	93.86 44	95.15 103	98.73 81	88.48 62	99.76 76	97.23 53	99.56 50	99.40 81

DeepPCF-MVS	93.56 1	96.55 36	97.84 10	92.68 210	98.71 85	78.11 329	99.70 19	97.71 75	98.18 1	97.36 54	99.76 1	90.37 45	99.94 34	99.27 13	99.54 52	99.99 1

CPTT-MVS		94.60 89	94.43 79	95.09 136	99.66 12	86.85 209	99.44 53	97.47 126	83.22 278	94.34 115	98.96 60	82.50 167	99.55 96	94.81 103	99.50 53	98.88 127

MP-MVS-pluss		95.80 57	95.30 64	97.29 47	98.95 76	92.66 82	98.59 151	97.14 159	88.95 159	93.12 132	99.25 22	85.62 118	99.94 34	96.56 69	99.48 54	99.28 92
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		96.59 34	96.18 39	97.81 33	98.82 81	93.55 65	98.88 119	97.59 102	90.66 109	97.98 43	99.14 38	86.59 102	100.00 1	96.47 71	99.46 55	99.89 25

PGM-MVS		95.85 55	95.65 60	96.45 91	99.50 42	89.77 146	98.22 190	98.90 12	89.19 151	96.74 72	98.95 62	85.91 117	99.92 39	93.94 118	99.46 55	99.66 58

testdata				95.26 133	98.20 95	87.28 201		97.60 98	85.21 244	98.48 27	99.15 36	88.15 68	98.72 152	90.29 163	99.45 57	99.78 37

SR-MVS		96.13 45	96.16 44	96.07 105	99.42 47	89.04 156	98.59 151	97.33 143	90.44 118	96.84 67	99.12 42	86.75 97	99.41 116	97.47 48	99.44 58	99.76 44

XVS		96.47 37	96.37 35	96.77 71	99.62 22	90.66 122	99.43 56	97.58 104	92.41 75	96.86 65	98.96 60	87.37 81	99.87 52	95.65 82	99.43 59	99.78 37

X-MVStestdata		90.69 179	88.66 201	96.77 71	99.62 22	90.66 122	99.43 56	97.58 104	92.41 75	96.86 65	29.59 385	87.37 81	99.87 52	95.65 82	99.43 59	99.78 37

MVS		93.92 102	92.28 131	98.83 6	95.69 186	96.82 7	96.22 284	98.17 34	84.89 253	84.34 230	98.61 94	79.32 198	99.83 64	93.88 120	99.43 59	99.86 29

MTAPA		96.09 46	95.80 55	96.96 64	99.29 55	91.19 103	97.23 247	97.45 129	92.58 69	94.39 114	99.24 24	86.43 108	99.99 5	96.22 73	99.40 62	99.71 50

旧先验1					98.97 73	92.90 81		97.74 67			99.15 36	91.05 34			99.33 63	99.60 65

PAPM_NR		95.43 66	95.05 72	96.57 86	99.42 47	90.14 132	98.58 153	97.51 118	90.65 111	92.44 140	98.90 68	87.77 75	99.90 46	90.88 155	99.32 64	99.68 54

SR-MVS-dyc-post		95.75 61	95.86 51	95.41 128	99.22 59	87.26 204	98.40 174	97.21 151	89.63 138	96.67 75	98.97 56	86.73 99	99.36 120	96.62 65	99.31 65	99.60 65

RE-MVS-def			95.70 57		99.22 59	87.26 204	98.40 174	97.21 151	89.63 138	96.67 75	98.97 56	85.24 127		96.62 65	99.31 65	99.60 65

PAPM		96.35 39	95.94 48	97.58 39	94.10 239	95.25 23	98.93 114	98.17 34	94.26 32	93.94 121	98.72 83	89.68 51	97.88 187	96.36 72	99.29 67	99.62 64

APD-MVS_3200maxsize		95.64 64	95.65 60	95.62 122	99.24 58	87.80 184	98.42 169	97.22 150	88.93 161	96.64 77	98.98 55	85.49 122	99.36 120	96.68 64	99.27 68	99.70 51

3Dnovator	87.35 11	93.17 130	91.77 144	97.37 46	95.41 196	93.07 75	98.82 123	97.85 51	91.53 91	82.56 249	97.58 136	71.97 249	99.82 67	91.01 153	99.23 69	99.22 98

patch_mono-2		97.10 23	97.97 8	94.49 158	99.21 61	83.73 274	99.62 30	98.25 29	95.28 22	99.38 4	98.91 67	92.28 28	99.94 34	99.61 8	99.22 70	99.78 37

dcpmvs_2		95.67 63	96.18 39	94.12 175	98.82 81	84.22 267	97.37 239	95.45 273	90.70 108	95.77 92	98.63 92	90.47 42	98.68 154	99.20 17	99.22 70	99.45 78

GST-MVS		95.97 51	95.66 58	96.90 66	99.49 45	91.22 101	99.45 52	97.48 124	89.69 136	95.89 87	98.72 83	86.37 109	99.95 31	94.62 110	99.22 70	99.52 72

PS-MVSNAJ		96.87 28	96.40 34	98.29 18	97.35 121	97.29 5	99.03 104	97.11 163	95.83 15	98.97 15	99.14 38	82.48 169	99.60 93	98.60 25	99.08 73	98.00 174

test_fmvsm_n_1920		97.08 24	97.55 12	95.67 120	97.94 104	89.61 150	99.93 1	98.48 23	97.08 4	99.08 11	99.13 40	88.17 66	99.93 37	99.11 18	99.06 74	97.47 187

MVS_111021_LR		95.78 58	95.94 48	95.28 132	98.19 97	87.69 185	98.80 125	99.26 7	93.39 55	95.04 105	98.69 88	84.09 139	99.76 76	96.96 59	99.06 74	98.38 159

PAPR		96.35 39	95.82 52	97.94 30	99.63 18	94.19 55	99.42 58	97.55 109	92.43 72	93.82 125	99.12 42	87.30 86	99.91 42	94.02 116	99.06 74	99.74 46

114514_t		94.06 97	93.05 115	97.06 55	99.08 69	92.26 88	98.97 112	97.01 175	82.58 291	92.57 138	98.22 112	80.68 189	99.30 126	89.34 176	99.02 77	99.63 62

API-MVS		94.78 81	94.18 86	96.59 83	99.21 61	90.06 139	98.80 125	97.78 63	83.59 273	93.85 123	99.21 26	83.79 142	99.97 21	92.37 143	99.00 78	99.74 46

MVSFormer		94.71 86	94.08 89	96.61 82	95.05 216	94.87 35	97.77 223	96.17 219	86.84 219	98.04 40	98.52 97	85.52 119	95.99 290	89.83 166	98.97 79	98.96 117

lupinMVS		96.32 41	95.94 48	97.44 43	95.05 216	94.87 35	99.86 3	96.50 197	93.82 47	98.04 40	98.77 77	85.52 119	98.09 175	96.98 58	98.97 79	99.37 83

3Dnovator+	87.72 8	93.43 119	91.84 142	98.17 21	95.73 185	95.08 31	98.92 116	97.04 170	91.42 96	81.48 274	97.60 134	74.60 223	99.79 73	90.84 156	98.97 79	99.64 60

GG-mvs-BLEND				96.98 62	96.53 152	94.81 40	87.20 354	97.74 67		93.91 122	96.40 183	96.56 2	96.94 237	95.08 96	98.95 82	99.20 99

test_cas_vis1_n_1920		93.86 106	93.74 100	94.22 171	95.39 198	86.08 231	99.73 15	96.07 226	96.38 12	97.19 60	97.78 124	65.46 299	99.86 57	96.71 62	98.92 83	96.73 205

MVS_0304		97.53 11	97.15 19	98.67 10	97.30 123	96.52 11	99.60 31	98.88 13	97.14 3	97.21 57	98.94 65	86.89 94	99.91 42	99.43 12	98.91 84	99.59 69

CS-MVS-test		95.98 50	96.34 36	94.90 143	98.06 101	87.66 188	99.69 26	96.10 223	93.66 50	98.35 31	99.05 50	86.28 110	97.66 205	96.96 59	98.90 85	99.37 83

gg-mvs-nofinetune		90.00 193	87.71 217	96.89 70	96.15 171	94.69 44	85.15 360	97.74 67	68.32 360	92.97 135	60.16 373	96.10 3	96.84 240	93.89 119	98.87 86	99.14 102

MAR-MVS		94.43 93	94.09 88	95.45 126	99.10 68	87.47 194	98.39 178	97.79 62	88.37 178	94.02 120	99.17 33	78.64 205	99.91 42	92.48 142	98.85 87	98.96 117
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
CSCG		94.87 78	94.71 75	95.36 129	99.54 36	86.49 214	99.34 68	98.15 37	82.71 289	90.15 177	99.25 22	89.48 52	99.86 57	94.97 101	98.82 88	99.72 49

CHOSEN 280x420		96.80 30	96.85 25	96.66 81	97.85 107	94.42 50	94.76 308	98.36 26	92.50 71	95.62 96	97.52 138	97.92 1	97.38 223	98.31 36	98.80 89	98.20 170

CANet		97.00 25	96.49 32	98.55 11	98.86 80	96.10 15	99.83 5	97.52 116	95.90 14	97.21 57	98.90 68	82.66 166	99.93 37	98.71 22	98.80 89	99.63 62

test_vis1_n_1920		93.08 132	93.42 105	92.04 222	96.31 162	79.36 317	99.83 5	96.06 227	96.72 7	98.53 26	98.10 117	58.57 322	99.91 42	97.86 43	98.79 91	96.85 204

MVP-Stereo		86.61 251	85.83 245	88.93 299	88.70 330	83.85 273	96.07 288	94.41 313	82.15 300	75.64 320	91.96 268	67.65 279	96.45 263	77.20 293	98.72 92	86.51 351
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
QAPM		91.41 163	89.49 183	97.17 53	95.66 188	93.42 69	98.60 149	97.51 118	80.92 314	81.39 275	97.41 144	72.89 242	99.87 52	82.33 256	98.68 93	98.21 169

1314		93.44 118	91.98 139	97.84 31	95.24 200	94.38 51	96.22 284	97.92 48	90.18 124	82.28 257	97.71 129	77.63 210	99.80 72	91.94 146	98.67 94	99.34 87

CS-MVS		95.75 61	96.19 38	94.40 162	97.88 106	86.22 225	99.66 27	96.12 222	92.69 68	98.07 38	98.89 70	87.09 88	97.59 211	96.71 62	98.62 95	99.39 82

EC-MVSNet		95.09 74	95.17 68	94.84 146	95.42 195	88.17 176	99.48 44	95.92 239	91.47 93	97.34 55	98.36 106	82.77 162	97.41 222	97.24 52	98.58 96	98.94 122

DeepC-MVS	91.02 4	94.56 92	93.92 96	96.46 90	97.16 129	90.76 118	98.39 178	97.11 163	93.92 40	88.66 190	98.33 107	78.14 207	99.85 60	95.02 98	98.57 97	98.78 139
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OpenMVS	85.28 14	90.75 177	88.84 196	96.48 89	93.58 258	93.51 67	98.80 125	97.41 136	82.59 290	78.62 302	97.49 140	68.00 276	99.82 67	84.52 231	98.55 98	96.11 219

EIA-MVS		95.11 73	95.27 66	94.64 155	96.34 161	86.51 213	99.59 33	96.62 186	92.51 70	94.08 119	98.64 90	86.05 114	98.24 169	95.07 97	98.50 99	99.18 100

jason		95.40 69	94.86 74	97.03 56	92.91 271	94.23 53	99.70 19	96.30 208	93.56 54	96.73 73	98.52 97	81.46 185	97.91 184	96.08 77	98.47 100	98.96 117
jason: jason.
MS-PatchMatch		86.75 247	85.92 244	89.22 292	91.97 281	82.47 292	96.91 258	96.14 221	83.74 269	77.73 309	93.53 242	58.19 324	97.37 225	76.75 297	98.35 101	87.84 340

test_fmvsmvis_n_1920		95.47 65	95.40 63	95.70 118	94.33 234	90.22 130	99.70 19	96.98 177	96.80 6	92.75 136	98.89 70	82.46 172	99.92 39	98.36 32	98.33 102	96.97 202

DP-MVS Recon		95.85 55	95.15 69	97.95 29	99.87 2	94.38 51	99.60 31	97.48 124	86.58 225	94.42 113	99.13 40	87.36 84	99.98 9	93.64 125	98.33 102	99.48 76

test_fmvs1		92.35 145	92.94 120	90.57 256	97.19 127	75.43 337	99.55 37	94.97 293	95.20 23	96.82 70	97.57 137	59.59 320	99.84 61	97.30 51	98.29 104	96.46 213

xiu_mvs_v2_base		96.66 32	96.17 42	98.11 26	97.11 134	96.96 6	99.01 107	97.04 170	95.51 20	98.86 18	99.11 46	82.19 176	99.36 120	98.59 27	98.14 105	98.00 174

BH-w/o		92.32 146	91.79 143	93.91 184	96.85 141	86.18 227	99.11 95	95.74 256	88.13 187	84.81 223	97.00 163	77.26 212	97.91 184	89.16 181	98.03 106	97.64 181

test_fmvs1_n		91.07 170	91.41 151	90.06 270	94.10 239	74.31 341	99.18 78	94.84 297	94.81 25	96.37 80	97.46 141	50.86 350	99.82 67	97.14 54	97.90 107	96.04 220

TAPA-MVS	87.50 9	90.35 183	89.05 192	94.25 170	98.48 91	85.17 254	98.42 169	96.58 192	82.44 296	87.24 202	98.53 96	82.77 162	98.84 145	59.09 362	97.88 108	98.72 142
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CHOSEN 1792x2688		94.35 94	93.82 98	95.95 111	97.40 119	88.74 168	98.41 171	98.27 28	92.18 81	91.43 155	96.40 183	78.88 200	99.81 70	93.59 126	97.81 109	99.30 90

BH-untuned		91.46 162	90.84 163	93.33 195	96.51 154	84.83 260	98.84 122	95.50 270	86.44 230	83.50 235	96.70 176	75.49 219	97.77 195	86.78 205	97.81 109	97.40 188

Vis-MVSNet		92.64 138	91.85 141	95.03 140	95.12 209	88.23 175	98.48 164	96.81 181	91.61 89	92.16 144	97.22 152	71.58 255	98.00 183	85.85 216	97.81 109	98.88 127
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPNet		96.82 29	96.68 30	97.25 50	98.65 86	93.10 74	99.48 44	98.76 14	96.54 9	97.84 46	98.22 112	87.49 78	99.66 84	95.35 91	97.78 112	99.00 113
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended		95.94 53	95.66 58	96.75 73	98.77 83	91.61 96	99.88 2	98.04 43	93.64 52	94.21 116	97.76 125	83.50 145	99.87 52	97.41 49	97.75 113	98.79 137

test_vis1_n		90.40 182	90.27 173	90.79 251	91.55 290	76.48 333	99.12 94	94.44 309	94.31 31	97.34 55	96.95 165	43.60 361	99.42 113	97.57 47	97.60 114	96.47 212

ETV-MVS		96.00 48	96.00 47	96.00 108	96.56 151	91.05 111	99.63 29	96.61 187	93.26 58	97.39 53	98.30 109	86.62 101	98.13 172	98.07 39	97.57 115	98.82 134

PLC	91.07 3	94.23 96	94.01 90	94.87 144	99.17 63	87.49 193	99.25 74	96.55 194	88.43 176	91.26 159	98.21 114	85.92 115	99.86 57	89.77 170	97.57 115	97.24 193
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LS3D		90.19 188	88.72 199	94.59 157	98.97 73	86.33 222	96.90 259	96.60 188	74.96 341	84.06 233	98.74 80	75.78 217	99.83 64	74.93 308	97.57 115	97.62 184

AdaColmap		93.82 107	93.06 114	96.10 104	99.88 1	89.07 155	98.33 182	97.55 109	86.81 221	90.39 174	98.65 89	75.09 220	99.98 9	93.32 131	97.53 118	99.26 94

BH-RMVSNet		91.25 167	89.99 176	95.03 140	96.75 147	88.55 171	98.65 141	94.95 294	87.74 201	87.74 196	97.80 122	68.27 273	98.14 171	80.53 272	97.49 119	98.41 156

CANet_DTU		94.31 95	93.35 106	97.20 52	97.03 138	94.71 43	98.62 145	95.54 268	95.61 18	97.21 57	98.47 103	71.88 250	99.84 61	88.38 185	97.46 120	97.04 200

PatchMatch-RL		91.47 161	90.54 170	94.26 169	98.20 95	86.36 220	96.94 257	97.14 159	87.75 200	88.98 188	95.75 198	71.80 252	99.40 117	80.92 267	97.39 121	97.02 201

UGNet		91.91 156	90.85 162	95.10 135	97.06 136	88.69 169	98.01 209	98.24 31	92.41 75	92.39 141	93.61 239	60.52 317	99.68 82	88.14 188	97.25 122	96.92 203
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
PVSNet	87.13 12	93.69 110	92.83 122	96.28 98	97.99 103	90.22 130	99.38 62	98.93 11	91.42 96	93.66 126	97.68 130	71.29 257	99.64 90	87.94 192	97.20 123	98.98 115

test2506		94.80 80	94.21 83	96.58 84	96.41 157	92.18 90	98.01 209	98.96 10	90.82 106	93.46 128	97.28 147	85.92 115	98.45 159	89.82 168	97.19 124	99.12 105

ECVR-MVS		92.29 147	91.33 152	95.15 134	96.41 157	87.84 183	98.10 202	94.84 297	90.82 106	91.42 157	97.28 147	65.61 296	98.49 158	90.33 162	97.19 124	99.12 105

EI-MVSNet-Vis-set		95.76 60	95.63 62	96.17 102	99.14 64	90.33 126	98.49 162	97.82 55	91.92 85	94.75 108	98.88 72	87.06 90	99.48 106	95.40 90	97.17 126	98.70 144

test1111		92.12 152	91.19 155	94.94 142	96.15 171	87.36 198	98.12 199	94.84 297	90.85 105	90.97 162	97.26 149	65.60 297	98.37 161	89.74 171	97.14 127	99.07 111

CNLPA		93.64 114	92.74 123	96.36 96	98.96 75	90.01 142	99.19 76	95.89 247	86.22 231	89.40 185	98.85 73	80.66 190	99.84 61	88.57 183	96.92 128	99.24 95

xiu_mvs_v1_base_debu		94.73 83	93.98 91	96.99 59	95.19 204	95.24 24	98.62 145	96.50 197	92.99 62	97.52 49	98.83 74	72.37 245	99.15 131	97.03 55	96.74 129	96.58 208

xiu_mvs_v1_base		94.73 83	93.98 91	96.99 59	95.19 204	95.24 24	98.62 145	96.50 197	92.99 62	97.52 49	98.83 74	72.37 245	99.15 131	97.03 55	96.74 129	96.58 208

xiu_mvs_v1_base_debi		94.73 83	93.98 91	96.99 59	95.19 204	95.24 24	98.62 145	96.50 197	92.99 62	97.52 49	98.83 74	72.37 245	99.15 131	97.03 55	96.74 129	96.58 208

MVS_Test		93.67 113	92.67 125	96.69 79	96.72 148	92.66 82	97.22 248	96.03 228	87.69 204	95.12 104	94.03 226	81.55 182	98.28 166	89.17 180	96.46 132	99.14 102

EI-MVSNet-UG-set		95.43 66	95.29 65	95.86 113	99.07 70	89.87 143	98.43 168	97.80 60	91.78 87	94.11 118	98.77 77	86.25 112	99.48 106	94.95 102	96.45 133	98.22 168

TSAR-MVS + GP.		96.95 26	96.91 23	97.07 54	98.88 79	91.62 95	99.58 34	96.54 195	95.09 24	96.84 67	98.63 92	91.16 31	99.77 75	99.04 19	96.42 134	99.81 32

PVSNet_Blended_VisFu		94.67 87	94.11 87	96.34 97	97.14 131	91.10 108	99.32 70	97.43 134	92.10 84	91.53 154	96.38 186	83.29 151	99.68 82	93.42 130	96.37 135	98.25 166

Vis-MVSNet (Re-imp)		93.26 127	93.00 119	94.06 178	96.14 173	86.71 212	98.68 137	96.70 184	88.30 182	89.71 184	97.64 133	85.43 125	96.39 265	88.06 190	96.32 136	99.08 109

EPMVS		92.59 141	91.59 147	95.59 124	97.22 126	90.03 140	91.78 334	98.04 43	90.42 119	91.66 149	90.65 296	86.49 107	97.46 218	81.78 262	96.31 137	99.28 92

PMMVS		93.62 115	93.90 97	92.79 205	96.79 146	81.40 302	98.85 120	96.81 181	91.25 99	96.82 70	98.15 116	77.02 213	98.13 172	93.15 134	96.30 138	98.83 133

TESTMET0.1,1		93.82 107	93.26 110	95.49 125	95.21 203	90.25 128	99.15 87	97.54 112	89.18 152	91.79 146	94.87 214	89.13 54	97.63 208	86.21 209	96.29 139	98.60 149

test-LLR		93.11 131	92.68 124	94.40 162	94.94 221	87.27 202	99.15 87	97.25 145	90.21 122	91.57 150	94.04 224	84.89 130	97.58 212	85.94 213	96.13 140	98.36 162

test-mter		93.27 126	92.89 121	94.40 162	94.94 221	87.27 202	99.15 87	97.25 145	88.95 159	91.57 150	94.04 224	88.03 71	97.58 212	85.94 213	96.13 140	98.36 162

Effi-MVS+		93.87 105	93.15 113	96.02 107	95.79 182	90.76 118	96.70 269	95.78 253	86.98 216	95.71 93	97.17 156	79.58 194	98.01 182	94.57 111	96.09 142	99.31 89

mvs_anonymous		92.50 143	91.65 146	95.06 137	96.60 150	89.64 148	97.06 253	96.44 201	86.64 224	84.14 231	93.93 230	82.49 168	96.17 283	91.47 148	96.08 143	99.35 85

IS-MVSNet		93.00 133	92.51 128	94.49 158	96.14 173	87.36 198	98.31 185	95.70 258	88.58 169	90.17 176	97.50 139	83.02 158	97.22 226	87.06 197	96.07 144	98.90 126

PatchmatchNet		92.05 155	91.04 158	95.06 137	96.17 170	89.04 156	91.26 342	97.26 144	89.56 143	90.64 168	90.56 302	88.35 64	97.11 229	79.53 275	96.07 144	99.03 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
F-COLMAP		92.07 154	91.75 145	93.02 200	98.16 98	82.89 285	98.79 129	95.97 231	86.54 227	87.92 195	97.80 122	78.69 204	99.65 88	85.97 211	95.93 146	96.53 211

diffmvs		94.59 90	94.19 84	95.81 114	95.54 191	90.69 120	98.70 135	95.68 260	91.61 89	95.96 85	97.81 121	80.11 191	98.06 177	96.52 70	95.76 147	98.67 146
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMMP		94.67 87	94.30 80	95.79 115	99.25 57	88.13 178	98.41 171	98.67 21	90.38 120	91.43 155	98.72 83	82.22 175	99.95 31	93.83 122	95.76 147	99.29 91
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
LCM-MVSNet-Re		88.59 221	88.61 202	88.51 302	95.53 192	72.68 349	96.85 261	88.43 368	88.45 173	73.14 333	90.63 297	75.82 216	94.38 331	92.95 135	95.71 149	98.48 154

PCF-MVS	89.78 5	91.26 165	89.63 180	96.16 103	95.44 194	91.58 98	95.29 304	96.10 223	85.07 248	82.75 245	97.45 142	78.28 206	99.78 74	80.60 271	95.65 150	97.12 195
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
FE-MVS		91.38 164	90.16 175	95.05 139	96.46 155	87.53 192	89.69 351	97.84 52	82.97 283	92.18 143	92.00 267	84.07 140	98.93 143	80.71 269	95.52 151	98.68 145

mvsany_test1		94.57 91	95.09 71	92.98 201	95.84 181	82.07 295	98.76 131	95.24 286	92.87 67	96.45 78	98.71 86	84.81 132	99.15 131	97.68 45	95.49 152	97.73 179

casdiffmvs		93.98 101	93.43 104	95.61 123	95.07 215	89.86 144	98.80 125	95.84 252	90.98 103	92.74 137	97.66 132	79.71 193	98.10 174	94.72 106	95.37 153	98.87 129
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs_mvg		94.00 99	93.33 107	96.03 106	95.22 202	90.90 116	99.09 96	95.99 229	90.58 113	91.55 153	97.37 145	79.91 192	98.06 177	95.01 99	95.22 154	99.13 104
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		93.91 103	93.30 108	95.72 117	95.10 213	90.07 136	97.48 235	95.91 244	91.03 101	93.54 127	97.68 130	79.58 194	98.02 181	94.27 114	95.14 155	99.08 109

Fast-Effi-MVS+		91.72 158	90.79 166	94.49 158	95.89 179	87.40 197	99.54 42	95.70 258	85.01 251	89.28 187	95.68 199	77.75 209	97.57 215	83.22 246	95.06 156	98.51 152

EPNet_dtu		92.28 148	92.15 135	92.70 209	97.29 124	84.84 259	98.64 143	97.82 55	92.91 65	93.02 134	97.02 162	85.48 124	95.70 304	72.25 327	94.89 157	97.55 186
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UA-Net		93.30 124	92.62 126	95.34 130	96.27 164	88.53 173	95.88 294	96.97 178	90.90 104	95.37 99	97.07 160	82.38 173	99.10 137	83.91 241	94.86 158	98.38 159

baseline2		94.04 98	93.80 99	94.74 150	93.07 270	90.25 128	98.12 199	98.16 36	89.86 132	86.53 212	96.95 165	95.56 6	98.05 179	91.44 149	94.53 159	95.93 221

MVS-HIRNet		79.01 313	75.13 325	90.66 254	93.82 254	81.69 298	85.16 359	93.75 323	54.54 369	74.17 326	59.15 375	57.46 326	96.58 252	63.74 351	94.38 160	93.72 232

SCA		90.64 180	89.25 189	94.83 147	94.95 220	88.83 164	96.26 281	97.21 151	90.06 131	90.03 178	90.62 298	66.61 287	96.81 242	83.16 247	94.36 161	98.84 130

OMC-MVS		93.90 104	93.62 102	94.73 151	98.63 87	87.00 207	98.04 208	96.56 193	92.19 80	92.46 139	98.73 81	79.49 197	99.14 135	92.16 145	94.34 162	98.03 173

DP-MVS		88.75 218	86.56 235	95.34 130	98.92 77	87.45 195	97.64 231	93.52 328	70.55 352	81.49 273	97.25 150	74.43 226	99.88 49	71.14 330	94.09 163	98.67 146

sss		94.85 79	93.94 95	97.58 39	96.43 156	94.09 58	98.93 114	99.16 8	89.50 145	95.27 100	97.85 119	81.50 183	99.65 88	92.79 140	94.02 164	98.99 114

FA-MVS(test-final)		92.22 151	91.08 157	95.64 121	96.05 177	88.98 158	91.60 337	97.25 145	86.99 213	91.84 145	92.12 261	83.03 157	99.00 140	86.91 202	93.91 165	98.93 123

EPP-MVSNet		93.75 109	93.67 101	94.01 181	95.86 180	85.70 242	98.67 139	97.66 83	84.46 258	91.36 158	97.18 155	91.16 31	97.79 193	92.93 136	93.75 166	98.53 151

GeoE		90.60 181	89.56 181	93.72 191	95.10 213	85.43 247	99.41 59	94.94 295	83.96 266	87.21 203	96.83 172	74.37 227	97.05 233	80.50 273	93.73 167	98.67 146

CVMVSNet		90.30 185	90.91 161	88.46 303	94.32 235	73.58 345	97.61 232	97.59 102	90.16 127	88.43 193	97.10 158	76.83 214	92.86 342	82.64 253	93.54 168	98.93 123

thisisatest0515		94.75 82	94.19 84	96.43 92	96.13 176	92.64 85	99.47 46	97.60 98	87.55 207	93.17 131	97.59 135	94.71 13	98.42 160	88.28 186	93.20 169	98.24 167

JIA-IIPM		85.97 261	84.85 261	89.33 291	93.23 267	73.68 344	85.05 361	97.13 161	69.62 356	91.56 152	68.03 371	88.03 71	96.96 235	77.89 289	93.12 170	97.34 190

Effi-MVS+-dtu		89.97 195	90.68 168	87.81 307	95.15 208	71.98 351	97.87 217	95.40 277	91.92 85	87.57 197	91.44 277	74.27 229	96.84 240	89.45 173	93.10 171	94.60 229

HY-MVS	88.56 7	95.29 70	94.23 82	98.48 13	97.72 109	96.41 12	94.03 316	98.74 15	92.42 74	95.65 95	94.76 217	86.52 105	99.49 102	95.29 93	92.97 172	99.53 71

LFMVS		92.23 150	90.84 163	96.42 93	98.24 94	91.08 110	98.24 189	96.22 214	83.39 276	94.74 109	98.31 108	61.12 315	98.85 144	94.45 112	92.82 173	99.32 88

HyFIR lowres test		93.68 112	93.29 109	94.87 144	97.57 117	88.04 180	98.18 194	98.47 24	87.57 206	91.24 160	95.05 211	85.49 122	97.46 218	93.22 132	92.82 173	99.10 107

CDS-MVSNet		93.47 117	93.04 116	94.76 148	94.75 227	89.45 152	98.82 123	97.03 172	87.91 195	90.97 162	96.48 181	89.06 55	96.36 267	89.50 172	92.81 175	98.49 153
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		95.97 51	95.11 70	98.54 12	97.62 113	96.65 8	99.44 53	98.74 15	92.25 79	95.21 101	98.46 105	86.56 104	99.46 108	95.00 100	92.69 176	99.50 75

test_yl		95.27 71	94.60 77	97.28 48	98.53 89	92.98 78	99.05 101	98.70 18	86.76 222	94.65 111	97.74 127	87.78 73	99.44 109	95.57 87	92.61 177	99.44 79

DCV-MVSNet		95.27 71	94.60 77	97.28 48	98.53 89	92.98 78	99.05 101	98.70 18	86.76 222	94.65 111	97.74 127	87.78 73	99.44 109	95.57 87	92.61 177	99.44 79

MSDG		88.29 225	86.37 237	94.04 180	96.90 140	86.15 229	96.52 272	94.36 314	77.89 331	79.22 297	96.95 165	69.72 263	99.59 94	73.20 323	92.58 179	96.37 216

thisisatest0530		94.00 99	93.52 103	95.43 127	95.76 184	90.02 141	98.99 109	97.60 98	86.58 225	91.74 147	97.36 146	94.78 12	98.34 162	86.37 208	92.48 180	97.94 176

TR-MVS		90.77 176	89.44 184	94.76 148	96.31 162	88.02 181	97.92 213	95.96 233	85.52 240	88.22 194	97.23 151	66.80 286	98.09 175	84.58 229	92.38 181	98.17 171

MDTV_nov1_ep13			90.47 172		96.14 173	88.55 171	91.34 341	97.51 118	89.58 141	92.24 142	90.50 306	86.99 93	97.61 210	77.64 290	92.34 182

TAMVS		92.62 139	92.09 137	94.20 172	94.10 239	87.68 186	98.41 171	96.97 178	87.53 208	89.74 182	96.04 193	84.77 134	96.49 260	88.97 182	92.31 183	98.42 155

ADS-MVSNet2		87.62 237	86.88 230	89.86 277	96.21 167	79.14 319	87.15 355	92.99 332	83.01 281	89.91 180	87.27 337	78.87 201	92.80 345	74.20 315	92.27 184	97.64 181

ADS-MVSNet		88.99 206	87.30 223	94.07 177	96.21 167	87.56 191	87.15 355	96.78 183	83.01 281	89.91 180	87.27 337	78.87 201	97.01 234	74.20 315	92.27 184	97.64 181

cascas		90.93 174	89.33 188	95.76 116	95.69 186	93.03 77	98.99 109	96.59 189	80.49 316	86.79 210	94.45 221	65.23 300	98.60 157	93.52 127	92.18 186	95.66 223

CR-MVSNet		88.83 214	87.38 222	93.16 198	93.47 260	86.24 223	84.97 362	94.20 317	88.92 162	90.76 166	86.88 341	84.43 135	94.82 324	70.64 331	92.17 187	98.41 156

RPMNet		85.07 275	81.88 291	94.64 155	93.47 260	86.24 223	84.97 362	97.21 151	64.85 367	90.76 166	78.80 364	80.95 188	99.27 127	53.76 368	92.17 187	98.41 156

DSMNet-mixed		81.60 302	81.43 296	82.10 338	84.36 355	60.79 366	93.63 320	86.74 371	79.00 321	79.32 296	87.15 339	63.87 305	89.78 362	66.89 344	91.92 189	95.73 222

tttt0517		93.30 124	93.01 118	94.17 173	95.57 189	86.47 215	98.51 159	97.60 98	85.99 233	90.55 169	97.19 154	94.80 11	98.31 163	85.06 222	91.86 190	97.74 178

VNet		95.08 75	94.26 81	97.55 42	98.07 100	93.88 60	98.68 137	98.73 17	90.33 121	97.16 61	97.43 143	79.19 199	99.53 99	96.91 61	91.85 191	99.24 95

tpmrst		92.78 135	92.16 134	94.65 153	96.27 164	87.45 195	91.83 333	97.10 166	89.10 155	94.68 110	90.69 293	88.22 65	97.73 203	89.78 169	91.80 192	98.77 140

alignmvs		95.77 59	95.00 73	98.06 27	97.35 121	95.68 18	99.71 18	97.50 121	91.50 92	96.16 83	98.61 94	86.28 110	99.00 140	96.19 74	91.74 193	99.51 74

CostFormer		92.89 134	92.48 129	94.12 175	94.99 218	85.89 237	92.89 325	97.00 176	86.98 216	95.00 106	90.78 289	90.05 48	97.51 216	92.92 137	91.73 194	98.96 117

Fast-Effi-MVS+-dtu		88.84 212	88.59 204	89.58 285	93.44 263	78.18 327	98.65 141	94.62 306	88.46 172	84.12 232	95.37 207	68.91 267	96.52 256	82.06 259	91.70 195	94.06 230

PatchT		85.44 271	83.19 279	92.22 215	93.13 269	83.00 281	83.80 368	96.37 204	70.62 351	90.55 169	79.63 363	84.81 132	94.87 322	58.18 364	91.59 196	98.79 137

tpm2		91.77 157	91.09 156	93.82 187	94.83 225	85.56 246	92.51 330	97.16 158	84.00 264	93.83 124	90.66 295	87.54 77	97.17 227	87.73 194	91.55 197	98.72 142

tpm cat1		88.89 210	87.27 224	93.76 188	95.79 182	85.32 251	90.76 347	97.09 167	76.14 337	85.72 217	88.59 327	82.92 159	98.04 180	76.96 294	91.43 198	97.90 177

canonicalmvs		95.02 76	93.96 94	98.20 20	97.53 118	95.92 16	98.71 133	96.19 217	91.78 87	95.86 90	98.49 101	79.53 196	99.03 139	96.12 75	91.42 199	99.66 58

Patchmatch-test		86.25 258	84.06 274	92.82 204	94.42 232	82.88 286	82.88 369	94.23 316	71.58 349	79.39 295	90.62 298	89.00 57	96.42 264	63.03 354	91.37 200	99.16 101

dp		90.16 190	88.83 197	94.14 174	96.38 160	86.42 216	91.57 338	97.06 169	84.76 255	88.81 189	90.19 314	84.29 137	97.43 221	75.05 307	91.35 201	98.56 150

VDDNet		90.08 192	88.54 207	94.69 152	94.41 233	87.68 186	98.21 192	96.40 202	76.21 336	93.33 130	97.75 126	54.93 337	98.77 147	94.71 107	90.96 202	97.61 185

thres200		93.69 110	92.59 127	96.97 63	97.76 108	94.74 42	99.35 67	99.36 2	89.23 150	91.21 161	96.97 164	83.42 148	98.77 147	85.08 221	90.96 202	97.39 189

thres100view900		93.34 123	92.15 135	96.90 66	97.62 113	94.84 37	99.06 100	99.36 2	87.96 193	90.47 172	96.78 173	83.29 151	98.75 149	84.11 237	90.69 204	97.12 195

tfpn200view9		93.43 119	92.27 132	96.90 66	97.68 111	94.84 37	99.18 78	99.36 2	88.45 173	90.79 164	96.90 168	83.31 149	98.75 149	84.11 237	90.69 204	97.12 195

thres400		93.39 121	92.27 132	96.73 75	97.68 111	94.84 37	99.18 78	99.36 2	88.45 173	90.79 164	96.90 168	83.31 149	98.75 149	84.11 237	90.69 204	96.61 206

VDD-MVS		91.24 168	90.18 174	94.45 161	97.08 135	85.84 240	98.40 174	96.10 223	86.99 213	93.36 129	98.16 115	54.27 339	99.20 128	96.59 68	90.63 207	98.31 165

thres600view7		93.18 129	92.00 138	96.75 73	97.62 113	94.92 32	99.07 98	99.36 2	87.96 193	90.47 172	96.78 173	83.29 151	98.71 153	82.93 251	90.47 208	96.61 206

GA-MVS		90.10 191	88.69 200	94.33 166	92.44 275	87.97 182	99.08 97	96.26 212	89.65 137	86.92 207	93.11 251	68.09 274	96.96 235	82.54 255	90.15 209	98.05 172

tpmvs		89.16 204	87.76 215	93.35 194	97.19 127	84.75 261	90.58 349	97.36 141	81.99 301	84.56 226	89.31 324	83.98 141	98.17 170	74.85 310	90.00 210	97.12 195

1112_ss		92.71 136	91.55 148	96.20 99	95.56 190	91.12 106	98.48 164	94.69 304	88.29 183	86.89 208	98.50 99	87.02 91	98.66 155	84.75 226	89.77 211	98.81 135

Test_1112_low_res		92.27 149	90.97 159	96.18 100	95.53 192	91.10 108	98.47 166	94.66 305	88.28 184	86.83 209	93.50 243	87.00 92	98.65 156	84.69 227	89.74 212	98.80 136

XVG-OURS-SEG-HR		90.95 173	90.66 169	91.83 225	95.18 207	81.14 309	95.92 291	95.92 239	88.40 177	90.33 175	97.85 119	70.66 260	99.38 118	92.83 138	88.83 213	94.98 227

COLMAP_ROB	82.69 18	84.54 282	82.82 282	89.70 282	96.72 148	78.85 320	95.89 292	92.83 336	71.55 350	77.54 311	95.89 196	59.40 321	99.14 135	67.26 342	88.26 214	91.11 291
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet		84.48 283	81.83 292	92.42 213	91.73 288	87.36 198	85.52 358	94.42 312	81.40 307	81.91 266	87.58 331	51.92 345	92.81 344	73.84 318	88.15 215	97.08 199

ab-mvs		91.05 172	89.17 190	96.69 79	95.96 178	91.72 94	92.62 329	97.23 149	85.61 239	89.74 182	93.89 232	68.55 270	99.42 113	91.09 151	87.84 216	98.92 125

XVG-OURS		90.83 175	90.49 171	91.86 224	95.23 201	81.25 306	95.79 299	95.92 239	88.96 158	90.02 179	98.03 118	71.60 254	99.35 123	91.06 152	87.78 217	94.98 227

AllTest		84.97 276	83.12 280	90.52 259	96.82 142	78.84 321	95.89 292	92.17 344	77.96 329	75.94 316	95.50 201	55.48 332	99.18 129	71.15 328	87.14 218	93.55 233

TestCases				90.52 259	96.82 142	78.84 321		92.17 344	77.96 329	75.94 316	95.50 201	55.48 332	99.18 129	71.15 328	87.14 218	93.55 233

Anonymous202405211		88.84 212	87.03 228	94.27 168	98.14 99	84.18 268	98.44 167	95.58 266	76.79 335	89.34 186	96.88 170	53.42 342	99.54 98	87.53 196	87.12 220	99.09 108

SDMVSNet		91.09 169	89.91 177	94.65 153	96.80 144	90.54 124	97.78 221	97.81 58	88.34 180	85.73 215	95.26 208	66.44 290	98.26 167	94.25 115	86.75 221	95.14 224

sd_testset		89.23 203	88.05 214	92.74 208	96.80 144	85.33 250	95.85 297	97.03 172	88.34 180	85.73 215	95.26 208	61.12 315	97.76 200	85.61 217	86.75 221	95.14 224

test_vis1_rt		81.31 303	80.05 306	85.11 323	91.29 295	70.66 355	98.98 111	77.39 381	85.76 237	68.80 347	82.40 354	36.56 368	99.44 109	92.67 141	86.55 223	85.24 358

HQP3-MVS								96.37 204							86.29 224

HQP-MVS		91.50 160	91.23 154	92.29 214	93.95 244	86.39 218	99.16 82	96.37 204	93.92 40	87.57 197	96.67 177	73.34 235	97.77 195	93.82 123	86.29 224	92.72 236

plane_prior						86.07 233	99.14 90		93.81 48						86.26 226

HQP_MVS		91.26 165	90.95 160	92.16 218	93.84 251	86.07 233	99.02 105	96.30 208	93.38 56	86.99 204	96.52 179	72.92 240	97.75 201	93.46 128	86.17 227	92.67 238

plane_prior5								96.30 208					97.75 201	93.46 128	86.17 227	92.67 238

OPM-MVS		89.76 197	89.15 191	91.57 234	90.53 304	85.58 245	98.11 201	95.93 238	92.88 66	86.05 213	96.47 182	67.06 285	97.87 188	89.29 179	86.08 229	91.26 287
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
RPSCF		85.33 272	85.55 250	84.67 328	94.63 230	62.28 365	93.73 318	93.76 322	74.38 344	85.23 222	97.06 161	64.09 303	98.31 163	80.98 265	86.08 229	93.41 235

CLD-MVS		91.06 171	90.71 167	92.10 220	94.05 243	86.10 230	99.55 37	96.29 211	94.16 35	84.70 225	97.17 156	69.62 265	97.82 191	94.74 105	86.08 229	92.39 242
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test0.0.03 1		88.96 207	88.61 202	90.03 274	91.09 297	84.43 264	98.97 112	97.02 174	90.21 122	80.29 283	96.31 188	84.89 130	91.93 356	72.98 324	85.70 232	93.73 231

dmvs_re		88.69 220	88.06 213	90.59 255	93.83 253	78.68 323	95.75 300	96.18 218	87.99 192	84.48 229	96.32 187	67.52 280	96.94 237	84.98 224	85.49 233	96.14 218

LPG-MVS_test		88.86 211	88.47 208	90.06 270	93.35 265	80.95 311	98.22 190	95.94 236	87.73 202	83.17 241	96.11 191	66.28 291	97.77 195	90.19 164	85.19 234	91.46 277

LGP-MVS_train				90.06 270	93.35 265	80.95 311		95.94 236	87.73 202	83.17 241	96.11 191	66.28 291	97.77 195	90.19 164	85.19 234	91.46 277

ACMM	86.95 13	88.77 217	88.22 211	90.43 261	93.61 257	81.34 304	98.50 160	95.92 239	87.88 196	83.85 234	95.20 210	67.20 283	97.89 186	86.90 203	84.90 236	92.06 259
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CMPMVS	58.40 21	80.48 306	80.11 305	81.59 341	85.10 353	59.56 368	94.14 315	95.95 235	68.54 359	60.71 365	93.31 245	55.35 335	97.87 188	83.06 250	84.85 237	87.33 345
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ACMP	87.39 10	88.71 219	88.24 210	90.12 269	93.91 249	81.06 310	98.50 160	95.67 261	89.43 146	80.37 282	95.55 200	65.67 294	97.83 190	90.55 160	84.51 238	91.47 276
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		88.26 226	87.73 216	89.84 278	88.05 337	82.21 293	97.77 223	96.17 219	86.84 219	82.41 254	91.95 269	72.07 248	95.99 290	89.83 166	84.50 239	91.32 284

iter_conf_final		93.22 128	93.04 116	93.76 188	97.03 138	92.22 89	99.05 101	93.31 330	92.11 83	86.93 206	95.42 204	95.01 10	96.59 249	93.98 117	84.48 240	92.46 241

jajsoiax		87.35 239	86.51 236	89.87 276	87.75 342	81.74 297	97.03 254	95.98 230	88.47 170	80.15 285	93.80 234	61.47 312	96.36 267	89.44 174	84.47 241	91.50 275

mvs_tets		87.09 242	86.22 239	89.71 281	87.87 338	81.39 303	96.73 268	95.90 245	88.19 186	79.99 287	93.61 239	59.96 319	96.31 275	89.40 175	84.34 242	91.43 279

iter_conf05		93.48 116	93.18 112	94.39 165	97.15 130	94.17 56	99.30 71	92.97 333	92.38 78	86.70 211	95.42 204	95.67 5	96.59 249	94.67 108	84.32 243	92.39 242

test_fmvs2		85.10 274	85.45 252	84.02 331	89.85 313	65.63 363	98.49 162	92.59 338	90.45 117	85.43 221	93.32 244	43.94 359	96.59 249	90.81 157	84.19 244	89.85 322

Anonymous20240529		87.66 236	85.58 249	93.92 183	97.59 116	85.01 257	98.13 197	97.13 161	66.69 365	88.47 192	96.01 194	55.09 336	99.51 100	87.00 199	84.12 245	97.23 194

anonymousdsp		86.69 248	85.75 247	89.53 286	86.46 349	82.94 282	96.39 275	95.71 257	83.97 265	79.63 292	90.70 292	68.85 268	95.94 293	86.01 210	84.02 246	89.72 324

mvsmamba		89.99 194	89.42 185	91.69 232	90.64 303	86.34 221	98.40 174	92.27 342	91.01 102	84.80 224	94.93 212	76.12 215	96.51 257	92.81 139	83.84 247	92.21 251

XVG-ACMP-BASELINE		85.86 263	84.95 259	88.57 301	89.90 311	77.12 332	94.30 312	95.60 265	87.40 210	82.12 260	92.99 254	53.42 342	97.66 205	85.02 223	83.83 248	90.92 295

ACMMP++															83.83 248

ET-MVSNet_ETH3D		92.56 142	91.45 150	95.88 112	96.39 159	94.13 57	99.46 50	96.97 178	92.18 81	66.94 356	98.29 110	94.65 15	94.28 332	94.34 113	83.82 250	99.24 95

EG-PatchMatch MVS		79.92 308	77.59 313	86.90 314	87.06 347	77.90 331	96.20 286	94.06 319	74.61 342	66.53 358	88.76 326	40.40 366	96.20 280	67.02 343	83.66 251	86.61 349

D2MVS		87.96 228	87.39 221	89.70 282	91.84 286	83.40 277	98.31 185	98.49 22	88.04 190	78.23 308	90.26 308	73.57 233	96.79 244	84.21 234	83.53 252	88.90 334

UniMVSNet_ETH3D		85.65 270	83.79 277	91.21 238	90.41 306	80.75 313	95.36 303	95.78 253	78.76 325	81.83 271	94.33 222	49.86 352	96.66 246	84.30 232	83.52 253	96.22 217

bld_raw_dy_0_64		87.82 229	86.71 233	91.15 240	89.54 319	85.61 243	97.37 239	89.16 366	89.26 149	83.42 237	94.50 220	65.79 293	96.18 281	88.00 191	83.37 254	91.67 265

PVSNet_BlendedMVS		93.36 122	93.20 111	93.84 186	98.77 83	91.61 96	99.47 46	98.04 43	91.44 94	94.21 116	92.63 258	83.50 145	99.87 52	97.41 49	83.37 254	90.05 318

PS-MVSNAJss		89.54 201	89.05 192	91.00 244	88.77 328	84.36 265	97.39 236	95.97 231	88.47 170	81.88 267	93.80 234	82.48 169	96.50 258	89.34 176	83.34 256	92.15 254

EI-MVSNet		89.87 196	89.38 187	91.36 237	94.32 235	85.87 238	97.61 232	96.59 189	85.10 246	85.51 219	97.10 158	81.30 187	96.56 253	83.85 243	83.03 257	91.64 266

MVSTER		92.71 136	92.32 130	93.86 185	97.29 124	92.95 80	99.01 107	96.59 189	90.09 128	85.51 219	94.00 228	94.61 16	96.56 253	90.77 159	83.03 257	92.08 258

FIs		90.70 178	89.87 178	93.18 197	92.29 276	91.12 106	98.17 196	98.25 29	89.11 154	83.44 236	94.82 216	82.26 174	96.17 283	87.76 193	82.76 259	92.25 247

tpm		89.67 198	88.95 194	91.82 226	92.54 274	81.43 301	92.95 324	95.92 239	87.81 197	90.50 171	89.44 321	84.99 128	95.65 305	83.67 244	82.71 260	98.38 159

ACMMP++_ref															82.64 261

FC-MVSNet-test		90.22 187	89.40 186	92.67 211	91.78 287	89.86 144	97.89 214	98.22 32	88.81 164	82.96 244	94.66 218	81.90 180	95.96 292	85.89 215	82.52 262	92.20 253

ITE_SJBPF				87.93 305	92.26 277	76.44 334		93.47 329	87.67 205	79.95 288	95.49 203	56.50 329	97.38 223	75.24 306	82.33 263	89.98 320

RRT_MVS		88.91 209	88.56 205	89.93 275	90.31 307	81.61 299	98.08 205	96.38 203	89.30 148	82.41 254	94.84 215	73.15 238	96.04 289	90.38 161	82.23 264	92.15 254

OpenMVS_ROB	73.86 20	77.99 320	75.06 326	86.77 315	83.81 358	77.94 330	96.38 276	91.53 354	67.54 362	68.38 349	87.13 340	43.94 359	96.08 287	55.03 367	81.83 265	86.29 352

LTVRE_ROB	81.71 19	84.59 281	82.72 287	90.18 267	92.89 272	83.18 280	93.15 323	94.74 301	78.99 322	75.14 323	92.69 256	65.64 295	97.63 208	69.46 335	81.82 266	89.74 323
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
USDC		84.74 277	82.93 281	90.16 268	91.73 288	83.54 276	95.00 306	93.30 331	88.77 165	73.19 332	93.30 246	53.62 341	97.65 207	75.88 303	81.54 267	89.30 329

ACMH	83.09 17	84.60 280	82.61 289	90.57 256	93.18 268	82.94 282	96.27 279	94.92 296	81.01 312	72.61 339	93.61 239	56.54 328	97.79 193	74.31 313	81.07 268	90.99 293
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		86.50 254	84.79 263	91.63 233	91.97 281	81.49 300	96.49 273	97.38 139	82.24 298	82.44 251	95.82 197	51.22 347	98.25 168	84.55 230	80.96 269	95.13 226

GBi-Net		86.67 249	84.96 257	91.80 227	95.11 210	88.81 165	96.77 263	95.25 283	82.94 284	82.12 260	90.25 309	62.89 307	94.97 319	79.04 279	80.24 270	91.62 268

test1		86.67 249	84.96 257	91.80 227	95.11 210	88.81 165	96.77 263	95.25 283	82.94 284	82.12 260	90.25 309	62.89 307	94.97 319	79.04 279	80.24 270	91.62 268

FMVSNet3		88.81 216	87.08 227	93.99 182	96.52 153	94.59 46	98.08 205	96.20 215	85.85 234	82.12 260	91.60 274	74.05 231	95.40 312	79.04 279	80.24 270	91.99 261

baseline1		92.61 140	91.28 153	96.58 84	97.05 137	94.63 45	97.72 227	96.20 215	89.82 133	88.56 191	96.85 171	86.85 95	97.82 191	88.42 184	80.10 273	97.30 191

testgi		82.29 297	81.00 300	86.17 318	87.24 345	74.84 340	97.39 236	91.62 352	88.63 166	75.85 319	95.42 204	46.07 358	91.55 357	66.87 345	79.94 274	92.12 256

test_0402		78.81 315	76.33 320	86.26 317	91.18 296	78.44 326	95.88 294	91.34 355	68.55 358	70.51 343	89.91 316	52.65 344	94.99 318	47.14 372	79.78 275	85.34 357

FMVSNet2		86.90 244	84.79 263	93.24 196	95.11 210	92.54 86	97.67 230	95.86 251	82.94 284	80.55 280	91.17 283	62.89 307	95.29 314	77.23 291	79.71 276	91.90 262

pmmvs4		87.58 238	86.17 241	91.80 227	89.58 317	88.92 163	97.25 245	95.28 282	82.54 292	80.49 281	93.17 250	75.62 218	96.05 288	82.75 252	78.90 277	90.42 309

ACMH+	83.78 15	84.21 286	82.56 290	89.15 294	93.73 256	79.16 318	96.43 274	94.28 315	81.09 311	74.00 327	94.03 226	54.58 338	97.67 204	76.10 301	78.81 278	90.63 306

XXY-MVS		87.75 233	86.02 242	92.95 203	90.46 305	89.70 147	97.71 229	95.90 245	84.02 263	80.95 276	94.05 223	67.51 281	97.10 231	85.16 220	78.41 279	92.04 260

pmmvs5		85.87 262	84.40 272	90.30 266	88.53 332	84.23 266	98.60 149	93.71 324	81.53 306	80.29 283	92.02 264	64.51 302	95.52 308	82.04 260	78.34 280	91.15 289

LF4IMVS		81.94 300	81.17 299	84.25 330	87.23 346	68.87 361	93.35 322	91.93 349	83.35 277	75.40 321	93.00 253	49.25 355	96.65 247	78.88 282	78.11 281	87.22 347

cl22		89.57 200	88.79 198	91.91 223	97.94 104	87.62 189	97.98 211	96.51 196	85.03 249	82.37 256	91.79 270	83.65 143	96.50 258	85.96 212	77.89 282	91.61 271

miper_ehance_all_eth		88.94 208	88.12 212	91.40 235	95.32 199	86.93 208	97.85 218	95.55 267	84.19 261	81.97 265	91.50 276	84.16 138	95.91 297	84.69 227	77.89 282	91.36 282

miper_enhance_ethall		90.33 184	89.70 179	92.22 215	97.12 133	88.93 162	98.35 181	95.96 233	88.60 168	83.14 243	92.33 260	87.38 80	96.18 281	86.49 207	77.89 282	91.55 274

TinyColmap		80.42 307	77.94 312	87.85 306	92.09 280	78.58 324	93.74 317	89.94 361	74.99 340	69.77 344	91.78 271	46.09 357	97.58 212	65.17 350	77.89 282	87.38 343

FMVSNet1		83.94 290	81.32 298	91.80 227	91.94 284	88.81 165	96.77 263	95.25 283	77.98 327	78.25 307	90.25 309	50.37 351	94.97 319	73.27 322	77.81 286	91.62 268

OurMVSNet-221017-0		84.13 289	83.59 278	85.77 321	87.81 339	70.24 356	94.89 307	93.65 326	86.08 232	76.53 312	93.28 247	61.41 313	96.14 285	80.95 266	77.69 287	90.93 294

IterMVS		85.81 265	84.67 266	89.22 292	93.51 259	83.67 275	96.32 278	94.80 300	85.09 247	78.69 300	90.17 315	66.57 289	93.17 341	79.48 277	77.42 288	90.81 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		85.73 268	84.64 267	89.00 297	93.46 262	82.90 284	96.27 279	94.70 303	85.02 250	78.62 302	90.35 307	66.61 287	93.33 338	79.38 278	77.36 289	90.76 301

our_test_3		84.47 284	82.80 283	89.50 287	89.01 325	83.90 272	97.03 254	94.56 307	81.33 308	75.36 322	90.52 304	71.69 253	94.54 330	68.81 337	76.84 290	90.07 316

dmvs_testset		77.17 323	78.99 310	71.71 351	87.25 344	38.55 385	91.44 339	81.76 377	85.77 236	69.49 345	95.94 195	69.71 264	84.37 371	52.71 370	76.82 291	92.21 251

EU-MVSNet		84.19 287	84.42 271	83.52 334	88.64 331	67.37 362	96.04 289	95.76 255	85.29 243	78.44 305	93.18 249	70.67 259	91.48 358	75.79 304	75.98 292	91.70 264

Anonymous20231206		80.76 305	79.42 309	84.79 327	84.78 354	72.98 346	96.53 271	92.97 333	79.56 320	74.33 324	88.83 325	61.27 314	92.15 353	60.59 359	75.92 293	89.24 331

IterMVS-LS		88.34 223	87.44 220	91.04 243	94.10 239	85.85 239	98.10 202	95.48 271	85.12 245	82.03 264	91.21 282	81.35 186	95.63 306	83.86 242	75.73 294	91.63 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VPA-MVSNet		89.10 205	87.66 218	93.45 193	92.56 273	91.02 112	97.97 212	98.32 27	86.92 218	86.03 214	92.01 265	68.84 269	97.10 231	90.92 154	75.34 295	92.23 249

nrg030		90.23 186	88.87 195	94.32 167	91.53 291	93.54 66	98.79 129	95.89 247	88.12 188	84.55 227	94.61 219	78.80 203	96.88 239	92.35 144	75.21 296	92.53 240

cl____		87.82 229	86.79 232	90.89 248	94.88 223	85.43 247	97.81 219	95.24 286	82.91 288	80.71 279	91.22 281	81.97 179	95.84 299	81.34 264	75.06 297	91.40 281

DIV-MVS_self_test		87.82 229	86.81 231	90.87 249	94.87 224	85.39 249	97.81 219	95.22 291	82.92 287	80.76 278	91.31 280	81.99 177	95.81 301	81.36 263	75.04 298	91.42 280

v1192		86.32 257	84.71 265	91.17 239	89.53 320	86.40 217	98.13 197	95.44 275	82.52 293	82.42 253	90.62 298	71.58 255	96.33 274	77.23 291	74.88 299	90.79 299

v1240		85.77 267	84.11 273	90.73 253	89.26 324	85.15 255	97.88 216	95.23 290	81.89 304	82.16 259	90.55 303	69.60 266	96.31 275	75.59 305	74.87 300	90.72 303

FMVSNet5		82.29 297	80.54 301	87.52 309	93.79 255	84.01 270	93.73 318	92.47 340	76.92 334	74.27 325	86.15 345	63.69 306	89.24 364	69.07 336	74.79 301	89.29 330

v1144		86.83 246	85.31 254	91.40 235	89.75 314	87.21 206	98.31 185	95.45 273	83.22 278	82.70 247	90.78 289	73.36 234	96.36 267	79.49 276	74.69 302	90.63 306

Anonymous20240521		78.63 317	76.90 318	83.82 332	82.82 360	72.86 347	95.72 301	93.57 327	73.55 347	72.17 340	84.79 348	49.69 353	92.51 349	65.29 349	74.50 303	86.09 353

v1921920		86.02 260	84.44 270	90.77 252	89.32 323	85.20 252	98.10 202	95.35 281	82.19 299	82.25 258	90.71 291	70.73 258	96.30 278	76.85 296	74.49 304	90.80 298

WR-MVS		88.54 222	87.22 226	92.52 212	91.93 285	89.50 151	98.56 154	97.84 52	86.99 213	81.87 268	93.81 233	74.25 230	95.92 296	85.29 219	74.43 305	92.12 256

ppachtmachnet_test		83.63 292	81.57 295	89.80 279	89.01 325	85.09 256	97.13 251	94.50 308	78.84 323	76.14 314	91.00 285	69.78 262	94.61 329	63.40 352	74.36 306	89.71 325

Patchmtry		83.61 293	81.64 293	89.50 287	93.36 264	82.84 287	84.10 365	94.20 317	69.47 357	79.57 293	86.88 341	84.43 135	94.78 325	68.48 339	74.30 307	90.88 296

V42		87.00 243	85.68 248	90.98 245	89.91 310	86.08 231	98.32 184	95.61 264	83.67 272	82.72 246	90.67 294	74.00 232	96.53 255	81.94 261	74.28 308	90.32 311

Anonymous20231211		84.72 278	82.65 288	90.91 246	97.71 110	84.55 263	97.28 243	96.67 185	66.88 364	79.18 298	90.87 288	58.47 323	96.60 248	82.61 254	74.20 309	91.59 273

SixPastTwentyTwo		82.63 296	81.58 294	85.79 320	88.12 336	71.01 354	95.17 305	92.54 339	84.33 260	72.93 337	92.08 262	60.41 318	95.61 307	74.47 312	74.15 310	90.75 302

v2v482		87.27 241	85.76 246	91.78 231	89.59 316	87.58 190	98.56 154	95.54 268	84.53 257	82.51 250	91.78 271	73.11 239	96.47 261	82.07 258	74.14 311	91.30 285

v144192		86.40 255	84.89 260	90.91 246	89.48 321	85.59 244	98.21 192	95.43 276	82.45 295	82.62 248	90.58 301	72.79 243	96.36 267	78.45 286	74.04 312	90.79 299

c3_l		88.19 227	87.23 225	91.06 242	94.97 219	86.17 228	97.72 227	95.38 278	83.43 275	81.68 272	91.37 278	82.81 161	95.72 303	84.04 240	73.70 313	91.29 286

eth_miper_zixun_eth		87.76 232	87.00 229	90.06 270	94.67 229	82.65 290	97.02 256	95.37 279	84.19 261	81.86 270	91.58 275	81.47 184	95.90 298	83.24 245	73.61 314	91.61 271

miper_lstm_enhance		86.90 244	86.20 240	89.00 297	94.53 231	81.19 307	96.74 267	95.24 286	82.33 297	80.15 285	90.51 305	81.99 177	94.68 328	80.71 269	73.58 315	91.12 290

tfpnnormal		83.65 291	81.35 297	90.56 258	91.37 294	88.06 179	97.29 242	97.87 50	78.51 326	76.20 313	90.91 286	64.78 301	96.47 261	61.71 357	73.50 316	87.13 348

N_pmnet		70.19 333	69.87 335	71.12 353	88.24 334	30.63 389	95.85 297	28.70 389	70.18 354	68.73 348	86.55 343	64.04 304	93.81 334	53.12 369	73.46 317	88.94 333

EGC-MVSNET		60.70 338	55.37 342	76.72 345	86.35 350	71.08 352	89.96 350	84.44 376	0.38 386	1.50 387	84.09 350	37.30 367	88.10 367	40.85 376	73.44 318	70.97 371

CP-MVSNet		86.54 252	85.45 252	89.79 280	91.02 299	82.78 288	97.38 238	97.56 108	85.37 242	79.53 294	93.03 252	71.86 251	95.25 315	79.92 274	73.43 319	91.34 283

PS-CasMVS		85.81 265	84.58 268	89.49 289	90.77 301	82.11 294	97.20 249	97.36 141	84.83 254	79.12 299	92.84 255	67.42 282	95.16 317	78.39 287	73.25 320	91.21 288

WR-MVS_H		86.53 253	85.49 251	89.66 284	91.04 298	83.31 279	97.53 234	98.20 33	84.95 252	79.64 291	90.90 287	78.01 208	95.33 313	76.29 300	72.81 321	90.35 310

FPMVS		61.57 336	60.32 339	65.34 356	60.14 383	42.44 383	91.02 345	89.72 363	44.15 372	42.63 375	80.93 359	19.02 377	80.59 377	42.50 373	72.76 322	73.00 369

v10		85.73 268	84.01 275	90.87 249	90.03 308	86.73 211	97.20 249	95.22 291	81.25 309	79.85 290	89.75 318	73.30 237	96.28 279	76.87 295	72.64 323	89.61 326

UniMVSNet (Re)		89.50 202	88.32 209	93.03 199	92.21 278	90.96 114	98.90 118	98.39 25	89.13 153	83.22 238	92.03 263	81.69 181	96.34 273	86.79 204	72.53 324	91.81 263

UniMVSNet_NR-MVSNet		89.60 199	88.55 206	92.75 207	92.17 279	90.07 136	98.74 132	98.15 37	88.37 178	83.21 239	93.98 229	82.86 160	95.93 294	86.95 200	72.47 325	92.25 247

DU-MVS		88.83 214	87.51 219	92.79 205	91.46 292	90.07 136	98.71 133	97.62 95	88.87 163	83.21 239	93.68 236	74.63 221	95.93 294	86.95 200	72.47 325	92.36 244

v8		86.11 259	84.45 269	91.10 241	89.99 309	86.85 209	97.24 246	95.36 280	81.99 301	79.89 289	89.86 317	74.53 225	96.39 265	78.83 283	72.32 327	90.05 318

VPNet		88.30 224	86.57 234	93.49 192	91.95 283	91.35 100	98.18 194	97.20 155	88.61 167	84.52 228	94.89 213	62.21 310	96.76 245	89.34 176	72.26 328	92.36 244

v7n		84.42 285	82.75 286	89.43 290	88.15 335	81.86 296	96.75 266	95.67 261	80.53 315	78.38 306	89.43 322	69.89 261	96.35 272	73.83 319	72.13 329	90.07 316

new_pmnet		76.02 324	73.71 329	82.95 335	83.88 357	72.85 348	91.26 342	92.26 343	70.44 353	62.60 363	81.37 357	47.64 356	92.32 351	61.85 356	72.10 330	83.68 363

IB-MVS	89.43 6	92.12 152	90.83 165	95.98 110	95.40 197	90.78 117	99.81 7	98.06 41	91.23 100	85.63 218	93.66 238	90.63 40	98.78 146	91.22 150	71.85 331	98.36 162
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
NR-MVSNet		87.74 235	86.00 243	92.96 202	91.46 292	90.68 121	96.65 270	97.42 135	88.02 191	73.42 330	93.68 236	77.31 211	95.83 300	84.26 233	71.82 332	92.36 244

v148		86.38 256	85.06 256	90.37 265	89.47 322	84.10 269	98.52 156	95.48 271	83.80 268	80.93 277	90.22 312	74.60 223	96.31 275	80.92 267	71.55 333	90.69 304

Baseline_NR-MVSNet		85.83 264	84.82 262	88.87 300	88.73 329	83.34 278	98.63 144	91.66 351	80.41 319	82.44 251	91.35 279	74.63 221	95.42 311	84.13 236	71.39 334	87.84 340

TranMVSNet+NR-MVSNet		87.75 233	86.31 238	92.07 221	90.81 300	88.56 170	98.33 182	97.18 156	87.76 199	81.87 268	93.90 231	72.45 244	95.43 310	83.13 249	71.30 335	92.23 249

PEN-MVS		85.21 273	83.93 276	89.07 296	89.89 312	81.31 305	97.09 252	97.24 148	84.45 259	78.66 301	92.68 257	68.44 272	94.87 322	75.98 302	70.92 336	91.04 292

MIMVSNet1		75.92 325	73.30 330	83.81 333	81.29 364	75.57 336	92.26 331	92.05 347	73.09 348	67.48 355	86.18 344	40.87 365	87.64 368	55.78 366	70.68 337	88.21 338

pm-mvs1		84.68 279	82.78 285	90.40 262	89.58 317	85.18 253	97.31 241	94.73 302	81.93 303	76.05 315	92.01 265	65.48 298	96.11 286	78.75 284	69.14 338	89.91 321

DTE-MVSNet		84.14 288	82.80 283	88.14 304	88.95 327	79.87 316	96.81 262	96.24 213	83.50 274	77.60 310	92.52 259	67.89 278	94.24 333	72.64 326	69.05 339	90.32 311

test20.03		78.51 318	77.48 314	81.62 340	83.07 359	71.03 353	96.11 287	92.83 336	81.66 305	69.31 346	89.68 319	57.53 325	87.29 369	58.65 363	68.47 340	86.53 350

h-mvs33		92.47 144	91.95 140	94.05 179	97.13 132	85.01 257	98.36 180	98.08 40	93.85 45	96.27 81	96.73 175	83.19 154	99.43 112	95.81 80	68.09 341	97.70 180

K. test v3		81.04 304	79.77 307	84.83 326	87.41 343	70.23 357	95.60 302	93.93 321	83.70 271	67.51 354	89.35 323	55.76 330	93.58 337	76.67 298	68.03 342	90.67 305

test_fmvs3		75.09 327	75.19 324	74.81 348	77.45 371	54.08 373	95.93 290	90.64 358	82.51 294	73.29 331	81.19 358	22.29 375	86.29 370	85.50 218	67.89 343	84.06 361

MDA-MVSNet_test_wron		79.65 311	77.05 316	87.45 310	87.79 341	80.13 314	96.25 282	94.44 309	73.87 345	51.80 369	87.47 336	68.04 275	92.12 354	66.02 346	67.79 344	90.09 314

YYNet1		79.64 312	77.04 317	87.43 311	87.80 340	79.98 315	96.23 283	94.44 309	73.83 346	51.83 368	87.53 332	67.96 277	92.07 355	66.00 347	67.75 345	90.23 313

APD_test1		68.93 335	66.98 338	74.77 349	80.62 366	53.15 375	87.97 353	85.01 374	53.76 370	59.26 366	87.52 333	25.19 373	89.95 361	56.20 365	67.33 346	81.19 367

AUN-MVS		90.17 189	89.50 182	92.19 217	96.21 167	82.67 289	97.76 225	97.53 113	88.05 189	91.67 148	96.15 189	83.10 156	97.47 217	88.11 189	66.91 347	96.43 214

hse-mvs2		91.67 159	91.51 149	92.15 219	96.22 166	82.61 291	97.74 226	97.53 113	93.85 45	96.27 81	96.15 189	83.19 154	97.44 220	95.81 80	66.86 348	96.40 215

pmmvs6		79.90 309	77.31 315	87.67 308	84.17 356	78.13 328	95.86 296	93.68 325	67.94 361	72.67 338	89.62 320	50.98 349	95.75 302	74.80 311	66.04 349	89.14 332

test_f		71.94 332	70.82 333	75.30 347	72.77 374	53.28 374	91.62 336	89.66 364	75.44 339	64.47 361	78.31 365	20.48 376	89.56 363	78.63 285	66.02 350	83.05 366

Gipuma		54.77 343	52.22 347	62.40 360	86.50 348	59.37 369	50.20 378	90.35 360	36.52 376	41.20 377	49.49 378	18.33 379	81.29 373	32.10 378	65.34 351	46.54 378
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX				76.08 346	90.74 302	51.65 378		90.84 357	86.47 229	57.89 367	87.98 328	35.88 369	92.60 346	65.77 348	65.06 352	83.97 362

MDA-MVSNet-bldmvs		77.82 321	74.75 327	87.03 313	88.33 333	78.52 325	96.34 277	92.85 335	75.57 338	48.87 371	87.89 329	57.32 327	92.49 350	60.79 358	64.80 353	90.08 315

mvsany_test3		75.85 326	74.52 328	79.83 343	73.53 373	60.64 367	91.73 335	87.87 370	83.91 267	70.55 342	82.52 353	31.12 370	93.66 335	86.66 206	62.83 354	85.19 359

Patchmatch-RL test		81.90 301	80.13 304	87.23 312	80.71 365	70.12 358	84.07 366	88.19 369	83.16 280	70.57 341	82.18 356	87.18 87	92.59 347	82.28 257	62.78 355	98.98 115

lessismore_v0				85.08 324	85.59 352	69.28 359		90.56 359		67.68 353	90.21 313	54.21 340	95.46 309	73.88 317	62.64 356	90.50 308

PM-MVS		74.88 328	72.85 331	80.98 342	78.98 369	64.75 364	90.81 346	85.77 372	80.95 313	68.23 351	82.81 352	29.08 372	92.84 343	76.54 299	62.46 357	85.36 356

pmmvs-eth3d		78.71 316	76.16 321	86.38 316	80.25 367	81.19 307	94.17 314	92.13 346	77.97 328	66.90 357	82.31 355	55.76 330	92.56 348	73.63 321	62.31 358	85.38 355

ambc				79.60 344	72.76 375	56.61 370	76.20 373	92.01 348		68.25 350	80.23 361	23.34 374	94.73 326	73.78 320	60.81 359	87.48 342

test_method		70.10 334	68.66 337	74.41 350	86.30 351	55.84 371	94.47 309	89.82 362	35.18 377	66.15 359	84.75 349	30.54 371	77.96 378	70.40 334	60.33 360	89.44 328

TDRefinement		78.01 319	75.31 323	86.10 319	70.06 376	73.84 343	93.59 321	91.58 353	74.51 343	73.08 335	91.04 284	49.63 354	97.12 228	74.88 309	59.47 361	87.33 345

TransMVSNet (Re)		81.97 299	79.61 308	89.08 295	89.70 315	84.01 270	97.26 244	91.85 350	78.84 323	73.07 336	91.62 273	67.17 284	95.21 316	67.50 341	59.46 362	88.02 339

PMVS	41.42 23	45.67 346	42.50 349	55.17 362	34.28 388	32.37 387	66.24 376	78.71 380	30.72 378	22.04 383	59.59 374	4.59 387	77.85 379	27.49 379	58.84 363	55.29 376
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		61.29 337	58.75 340	68.92 355	67.41 377	52.84 376	91.18 344	59.23 388	66.96 363	41.96 376	58.44 376	11.37 384	94.72 327	74.25 314	57.97 364	59.20 375

KD-MVS_self_test		77.47 322	75.88 322	82.24 336	81.59 362	68.93 360	92.83 328	94.02 320	77.03 333	73.14 333	83.39 351	55.44 334	90.42 359	67.95 340	57.53 365	87.38 343

CL-MVSNet_self_test		79.89 310	78.34 311	84.54 329	81.56 363	75.01 338	96.88 260	95.62 263	81.10 310	75.86 318	85.81 346	68.49 271	90.26 360	63.21 353	56.51 366	88.35 337

UnsupCasMVSNet_eth		78.90 314	76.67 319	85.58 322	82.81 361	74.94 339	91.98 332	96.31 207	84.64 256	65.84 360	87.71 330	51.33 346	92.23 352	72.89 325	56.50 367	89.56 327

PVSNet_0	83.28 16	87.31 240	85.16 255	93.74 190	94.78 226	84.59 262	98.91 117	98.69 20	89.81 134	78.59 304	93.23 248	61.95 311	99.34 124	94.75 104	55.72 368	97.30 191

new-patchmatchnet		74.80 329	72.40 332	81.99 339	78.36 370	72.20 350	94.44 310	92.36 341	77.06 332	63.47 362	79.98 362	51.04 348	88.85 365	60.53 360	54.35 369	84.92 360

pmmvs3		72.86 331	69.76 336	82.17 337	73.86 372	74.19 342	94.20 313	89.01 367	64.23 368	67.72 352	80.91 360	41.48 363	88.65 366	62.40 355	54.02 370	83.68 363

testf1		56.38 341	53.73 344	64.31 358	64.84 378	45.11 380	80.50 371	75.94 383	38.87 373	42.74 373	75.07 366	11.26 385	81.19 374	41.11 374	53.27 371	66.63 372

APD_test2		56.38 341	53.73 344	64.31 358	64.84 378	45.11 380	80.50 371	75.94 383	38.87 373	42.74 373	75.07 366	11.26 385	81.19 374	41.11 374	53.27 371	66.63 372

LCM-MVSNet		60.07 339	56.37 341	71.18 352	54.81 385	48.67 379	82.17 370	89.48 365	37.95 375	49.13 370	69.12 369	13.75 383	81.76 372	59.28 361	51.63 373	83.10 365

UnsupCasMVSNet_bld		73.85 330	70.14 334	84.99 325	79.44 368	75.73 335	88.53 352	95.24 286	70.12 355	61.94 364	74.81 368	41.41 364	93.62 336	68.65 338	51.13 374	85.62 354

KD-MVS_2432*1600		82.98 294	80.52 302	90.38 263	94.32 235	88.98 158	92.87 326	95.87 249	80.46 317	73.79 328	87.49 334	82.76 164	93.29 339	70.56 332	46.53 375	88.87 335

miper_refine_blended		82.98 294	80.52 302	90.38 263	94.32 235	88.98 158	92.87 326	95.87 249	80.46 317	73.79 328	87.49 334	82.76 164	93.29 339	70.56 332	46.53 375	88.87 335

PMMVS2		58.97 340	55.07 343	70.69 354	62.72 380	55.37 372	85.97 357	80.52 378	49.48 371	45.94 372	68.31 370	15.73 381	80.78 376	49.79 371	37.12 377	75.91 368

MVE	44.00 22	41.70 347	37.64 352	53.90 363	49.46 386	43.37 382	65.09 377	66.66 385	26.19 381	25.77 382	48.53 379	3.58 389	63.35 382	26.15 380	27.28 378	54.97 377
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		41.02 348	40.93 350	41.29 364	61.97 381	33.83 386	84.00 367	65.17 386	27.17 379	27.56 379	46.72 380	17.63 380	60.41 383	19.32 381	18.82 379	29.61 379

ANet_high		50.71 345	46.17 348	64.33 357	44.27 387	52.30 377	76.13 374	78.73 379	64.95 366	27.37 380	55.23 377	14.61 382	67.74 380	36.01 377	18.23 380	72.95 370

EMVS		39.96 349	39.88 351	40.18 365	59.57 384	32.12 388	84.79 364	64.57 387	26.27 380	26.14 381	44.18 383	18.73 378	59.29 384	17.03 382	17.67 381	29.12 380

tmp_tt		53.66 344	52.86 346	56.05 361	32.75 389	41.97 384	73.42 375	76.12 382	21.91 382	39.68 378	96.39 185	42.59 362	65.10 381	78.00 288	14.92 382	61.08 374

wuyk23d		16.71 352	16.73 356	16.65 366	60.15 382	25.22 390	41.24 379	5.17 390	6.56 383	5.48 386	3.61 386	3.64 388	22.72 385	15.20 383	9.52 383	1.99 383

testmvs		18.81 351	23.05 354	6.10 368	4.48 390	2.29 392	97.78 221	3.00 391	3.27 384	18.60 384	62.71 372	1.53 391	2.49 387	14.26 384	1.80 384	13.50 382

test123		16.58 353	19.47 355	7.91 367	3.59 391	5.37 391	94.32 311	1.39 392	2.49 385	13.98 385	44.60 382	2.91 390	2.65 386	11.35 385	0.57 385	15.70 381

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

cdsmvs_eth3d_5k		22.52 350	30.03 353	0.00 369	0.00 392	0.00 393	0.00 380	97.17 157	0.00 387	0.00 388	98.77 77	74.35 228	0.00 388	0.00 386	0.00 386	0.00 384

pcd_1.5k_mvsjas		6.87 355	9.16 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	82.48 169	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

ab-mvs-re		8.21 354	10.94 357	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	98.50 99	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

FOURS1					99.50 42	88.94 161	99.55 37	97.47 126	91.32 98	98.12 36

test_one_0601					99.59 28	94.89 33		97.64 89	93.14 59	98.93 17	99.45 14	93.45 18

eth-test2					0.00 392

eth-test					0.00 392

test_241102_ONE					99.63 18	95.24 24		97.72 71	94.16 35	99.30 6	99.49 9	93.32 19	99.98 9

save fliter					99.34 50	93.85 61	99.65 28	97.63 93	95.69 16

test0726					99.66 12	95.20 29	99.77 10	97.70 76	93.95 38	99.35 5	99.54 3	93.18 22

GSMVS																98.84 130

test_part2					99.54 36	95.42 19				98.13 34

sam_mvs1												88.39 63				98.84 130

sam_mvs												87.08 89

MTGPA								97.45 129

test_post1							90.74 348				41.37 384	85.38 126	96.36 267	83.16 247

test_post											46.00 381	87.37 81	97.11 229

patchmatchnet-post											84.86 347	88.73 60	96.81 242

MTMP							99.21 75	91.09 356

gm-plane-assit					94.69 228	88.14 177			88.22 185		97.20 153		98.29 165	90.79 158

TEST9					99.57 33	93.17 72	99.38 62	97.66 83	89.57 142	98.39 28	99.18 31	90.88 37	99.66 84

test_8					99.55 35	93.07 75	99.37 65	97.64 89	90.18 124	98.36 30	99.19 28	90.94 35	99.64 90

agg_prior					99.54 36	92.66 82		97.64 89		97.98 43			99.61 92

test_prior4						92.00 91	99.41 59

test_prior				97.01 57	99.58 30	91.77 92		97.57 107					99.49 102			99.79 35

旧先验2							98.67 139		85.75 238	98.96 16			98.97 142	93.84 121

新几何2							98.26 188

无先验							98.52 156	97.82 55	87.20 212				99.90 46	87.64 195		99.85 30

原ACMM2							98.69 136

testdata2													99.88 49	84.16 235

segment_acmp												90.56 41

testdata1							97.89 214		92.43 72

plane_prior7					93.84 251	85.73 241

plane_prior6					93.92 248	86.02 235						72.92 240

plane_prior4											96.52 179

plane_prior3						85.91 236			93.65 51	86.99 204

plane_prior2							99.02 105		93.38 56

plane_prior1					93.90 250

n2								0.00 393

nn								0.00 393

door-mid								84.90 375

test11								97.68 80

door								85.30 373

HQP5-MVS						86.39 218

HQP-NCC					93.95 244		99.16 82		93.92 40	87.57 197

ACMP_Plane					93.95 244		99.16 82		93.92 40	87.57 197

BP-MVS														93.82 123

HQP4-MVS										87.57 197			97.77 195			92.72 236

HQP2-MVS												73.34 235

NP-MVS					93.94 247	86.22 225					96.67 177

MDTV_nov1_ep13_2view						91.17 105	91.38 340		87.45 209	93.08 133		86.67 100		87.02 198		98.95 121

Test By Simon												83.62 144

High-resolution multi-view benchmark