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.

test0726					98.78 3	85.93 53	97.19 11	97.47 11	90.27 30	97.64 4	98.13 1	91.47 8

SMA-MVS		95.20 8	95.07 11	95.59 5	98.14 35	88.48 8	96.26 46	97.28 30	85.90 143	97.67 3	98.10 2	88.41 20	99.56 11	94.66 16	99.19 1	98.71 18
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
APDe-MVS		95.46 5	95.64 5	94.91 20	98.26 28	86.29 44	97.46 6	97.40 20	89.03 63	96.20 17	98.10 2	89.39 16	99.34 33	95.88 6	99.03 11	99.10 4

SED-MVS		95.91 2	96.28 2	94.80 31	98.77 5	85.99 50	97.13 14	97.44 15	90.31 27	97.71 1	98.07 4	92.31 4	99.58 9	95.66 7	99.13 3	98.84 13

test_241102_TWO								97.44 15	90.31 27	97.62 5	98.07 4	91.46 10	99.58 9	95.66 7	99.12 6	98.98 9

DVP-MVS++		95.98 1	96.36 1	94.82 29	97.78 51	86.00 48	98.29 1	97.49 6	90.75 18	97.62 5	98.06 6	92.59 2	99.61 3	95.64 9	99.02 12	98.86 10

test_one_0601					98.58 11	85.83 58		97.44 15	91.05 13	96.78 14	98.06 6	91.45 11

DVP-MVS		95.67 3	96.02 3	94.64 37	98.78 3	85.93 53	97.09 16	96.73 77	90.27 30	97.04 11	98.05 8	91.47 8	99.55 15	95.62 11	99.08 7	98.45 35
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									90.75 18	97.04 11	98.05 8	92.09 6	99.55 15	95.64 9	99.13 3	99.13 2

test_241102_ONE					98.77 5	85.99 50		97.44 15	90.26 32	97.71 1	97.96 10	92.31 4	99.38 30

DPE-MVS		95.57 4	95.67 4	95.25 9	98.36 25	87.28 16	95.56 85	97.51 5	89.13 60	97.14 9	97.91 11	91.64 7	99.62 1	94.61 17	99.17 2	98.86 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_fmvsm_n_1920		94.71 16	95.11 10	93.50 63	95.79 114	84.62 73	96.15 52	97.64 2	89.85 39	97.19 8	97.89 12	86.28 40	98.71 91	97.11 2	98.08 64	97.17 104

MP-MVS-pluss		94.21 29	94.00 36	94.85 24	98.17 33	86.65 29	94.82 126	97.17 38	86.26 135	92.83 61	97.87 13	85.57 47	99.56 11	94.37 20	98.92 17	98.34 41
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MVS_0304		94.60 17	94.38 21	95.23 10	95.41 128	87.49 14	96.53 37	92.75 267	93.82 1	93.07 55	97.84 14	83.66 70	99.59 7	97.61 1	98.76 28	98.61 21

SF-MVS		94.97 11	94.90 14	95.20 11	97.84 47	87.76 9	96.65 34	97.48 10	87.76 106	95.71 20	97.70 15	88.28 23	99.35 32	93.89 25	98.78 25	98.48 29

ACMMP_NAP		94.74 15	94.56 17	95.28 8	98.02 41	87.70 10	95.68 77	97.34 22	88.28 87	95.30 24	97.67 16	85.90 44	99.54 19	93.91 24	98.95 15	98.60 22

MTAPA		94.42 24	94.22 28	95.00 17	98.42 21	86.95 19	94.36 160	96.97 49	91.07 12	93.14 52	97.56 17	84.30 63	99.56 11	93.43 30	98.75 29	98.47 32

test_fmvsmvis_n_1920		93.44 47	93.55 47	93.10 73	93.67 207	84.26 87	95.83 69	96.14 115	89.00 66	92.43 75	97.50 18	83.37 73	98.72 90	96.61 3	97.44 78	96.32 134

APD-MVS_3200maxsize		93.78 40	93.77 42	93.80 59	97.92 43	84.19 88	96.30 42	96.87 61	86.96 120	93.92 38	97.47 19	83.88 68	98.96 73	92.71 44	97.87 70	98.26 53

SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 24	96.99 72	86.33 40	97.33 7	97.30 28	91.38 11	95.39 22	97.46 20	88.98 19	99.40 29	94.12 21	98.89 18	98.82 15
Skip Steuart: Steuart Systems R&D Blog.
SR-MVS-dyc-post		93.82 39	93.82 39	93.82 57	97.92 43	84.57 75	96.28 44	96.76 73	87.46 110	93.75 39	97.43 21	84.24 64	99.01 62	92.73 41	97.80 72	97.88 76

RE-MVS-def			93.68 45		97.92 43	84.57 75	96.28 44	96.76 73	87.46 110	93.75 39	97.43 21	82.94 77		92.73 41	97.80 72	97.88 76

9.14			94.47 18		97.79 49		96.08 56	97.44 15	86.13 141	95.10 25	97.40 23	88.34 22	99.22 43	93.25 34	98.70 33

SR-MVS		94.23 28	94.17 32	94.43 45	98.21 32	85.78 60	96.40 40	96.90 58	88.20 92	94.33 30	97.40 23	84.75 60	99.03 57	93.35 33	97.99 66	98.48 29

DeepC-MVS	88.79 3	93.31 52	92.99 55	94.26 50	96.07 102	85.83 58	94.89 121	96.99 47	89.02 65	89.56 122	97.37 25	82.51 81	99.38 30	92.20 55	98.30 54	97.57 90
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PGM-MVS		93.96 37	93.72 43	94.68 36	98.43 20	86.22 45	95.30 93	97.78 1	87.45 112	93.26 48	97.33 26	84.62 61	99.51 23	90.75 89	98.57 46	98.32 45

DeepPCF-MVS	89.96 1	94.20 31	94.77 15	92.49 104	96.52 87	80.00 209	94.00 184	97.08 43	90.05 34	95.65 21	97.29 27	89.66 13	98.97 71	93.95 23	98.71 31	98.50 26

region2R		94.43 22	94.27 27	94.92 19	98.65 8	86.67 28	96.92 24	97.23 33	88.60 78	93.58 43	97.27 28	85.22 51	99.54 19	92.21 54	98.74 30	98.56 24

SD-MVS		94.96 12	95.33 8	93.88 55	97.25 69	86.69 26	96.19 49	97.11 42	90.42 26	96.95 13	97.27 28	89.53 14	96.91 238	94.38 19	98.85 19	98.03 69
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
ACMMPR		94.43 22	94.28 25	94.91 20	98.63 9	86.69 26	96.94 20	97.32 26	88.63 76	93.53 46	97.26 30	85.04 54	99.54 19	92.35 51	98.78 25	98.50 26

CP-MVS		94.34 25	94.21 29	94.74 35	98.39 23	86.64 30	97.60 4	97.24 31	88.53 80	92.73 67	97.23 31	85.20 52	99.32 37	92.15 57	98.83 21	98.25 54

patch_mono-2		93.74 41	94.32 22	92.01 120	97.54 57	78.37 247	93.40 208	97.19 34	88.02 96	94.99 27	97.21 32	88.35 21	98.44 112	94.07 22	98.09 62	99.23 1

HFP-MVS		94.52 18	94.40 20	94.86 23	98.61 10	86.81 23	96.94 20	97.34 22	88.63 76	93.65 41	97.21 32	86.10 42	99.49 25	92.35 51	98.77 27	98.30 46

MP-MVS		94.25 26	94.07 34	94.77 33	98.47 18	86.31 42	96.71 31	96.98 48	89.04 62	91.98 83	97.19 34	85.43 49	99.56 11	92.06 63	98.79 23	98.44 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APD-MVS		94.24 27	94.07 34	94.75 34	98.06 39	86.90 21	95.88 66	96.94 54	85.68 149	95.05 26	97.18 35	87.31 33	99.07 52	91.90 70	98.61 45	98.28 49
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		93.99 36	93.78 41	94.63 38	98.50 16	85.90 57	96.87 26	96.91 57	88.70 74	91.83 92	97.17 36	83.96 67	99.55 15	91.44 76	98.64 42	98.43 37

XVS		94.45 20	94.32 22	94.85 24	98.54 13	86.60 32	96.93 22	97.19 34	90.66 23	92.85 59	97.16 37	85.02 55	99.49 25	91.99 64	98.56 47	98.47 32

HPM-MVS_fast		93.40 51	93.22 51	93.94 54	98.36 25	84.83 70	97.15 13	96.80 69	85.77 146	92.47 74	97.13 38	82.38 82	99.07 52	90.51 94	98.40 51	97.92 75

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 39	92.59 2	98.94 74	92.25 53	98.99 14	98.84 13

CNVR-MVS		95.40 7	95.37 7	95.50 7	98.11 36	88.51 7	95.29 95	96.96 51	92.09 5	95.32 23	97.08 39	89.49 15	99.33 36	95.10 14	98.85 19	98.66 19

PC_three_1452									82.47 219	97.09 10	97.07 41	92.72 1	98.04 149	92.70 45	99.02 12	98.86 10

ZNCC-MVS		94.47 19	94.28 25	95.03 15	98.52 15	86.96 18	96.85 28	97.32 26	88.24 88	93.15 51	97.04 42	86.17 41	99.62 1	92.40 49	98.81 22	98.52 25

ACMMP		93.24 54	92.88 57	94.30 49	98.09 38	85.33 66	96.86 27	97.45 14	88.33 84	90.15 117	97.03 43	81.44 96	99.51 23	90.85 88	95.74 104	98.04 68
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
DeepC-MVS_fast	89.43 2	94.04 33	93.79 40	94.80 31	97.48 61	86.78 24	95.65 81	96.89 59	89.40 52	92.81 62	96.97 44	85.37 50	99.24 42	90.87 87	98.69 34	98.38 40
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + MP.		94.85 13	94.94 12	94.58 40	98.25 29	86.33 40	96.11 55	96.62 86	88.14 94	96.10 18	96.96 45	89.09 18	98.94 74	94.48 18	98.68 36	98.48 29
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSLP-MVS++		93.72 42	94.08 33	92.65 96	97.31 65	83.43 106	95.79 71	97.33 24	90.03 35	93.58 43	96.96 45	84.87 58	97.76 164	92.19 56	98.66 39	96.76 121

ZD-MVS					98.15 34	86.62 31		97.07 44	83.63 192	94.19 32	96.91 47	87.57 31	99.26 41	91.99 64	98.44 50

dcpmvs_2		93.49 45	94.19 31	91.38 155	97.69 54	76.78 279	94.25 163	96.29 102	88.33 84	94.46 28	96.88 48	88.07 25	98.64 94	93.62 28	98.09 62	98.73 16

VDDNet		89.56 123	88.49 141	92.76 89	95.07 141	82.09 147	96.30 42	93.19 257	81.05 255	91.88 88	96.86 49	61.16 316	98.33 121	88.43 113	92.49 169	97.84 79

VDD-MVS		90.74 91	89.92 103	93.20 69	96.27 93	83.02 121	95.73 74	93.86 244	88.42 83	92.53 71	96.84 50	62.09 304	98.64 94	90.95 85	92.62 166	97.93 74

GST-MVS		94.21 29	93.97 37	94.90 22	98.41 22	86.82 22	96.54 36	97.19 34	88.24 88	93.26 48	96.83 51	85.48 48	99.59 7	91.43 77	98.40 51	98.30 46

HPM-MVS++		95.14 10	94.91 13	95.83 4	98.25 29	89.65 4	95.92 65	96.96 51	91.75 8	94.02 36	96.83 51	88.12 24	99.55 15	93.41 32	98.94 16	98.28 49

旧先验1					96.79 76	81.81 154		95.67 151			96.81 53	86.69 35			97.66 76	96.97 115

LFMVS		90.08 106	89.13 120	92.95 82	96.71 77	82.32 145	96.08 56	89.91 337	86.79 125	92.15 80	96.81 53	62.60 302	98.34 119	87.18 130	93.90 140	98.19 57

HPM-MVS		94.02 34	93.88 38	94.43 45	98.39 23	85.78 60	97.25 10	97.07 44	86.90 124	92.62 70	96.80 55	84.85 59	99.17 46	92.43 47	98.65 41	98.33 42
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MSP-MVS		95.42 6	95.56 6	94.98 18	98.49 17	86.52 34	96.91 25	97.47 11	91.73 9	96.10 18	96.69 56	89.90 12	99.30 39	94.70 15	98.04 65	99.13 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
testdata				90.49 192	96.40 89	77.89 259		95.37 177	72.51 344	93.63 42	96.69 56	82.08 90	97.65 172	83.08 180	97.39 79	95.94 151

EI-MVSNet-Vis-set		93.01 57	92.92 56	93.29 65	95.01 142	83.51 105	94.48 145	95.77 144	90.87 14	92.52 72	96.67 58	84.50 62	99.00 66	91.99 64	94.44 134	97.36 96

3Dnovator	86.66 5	91.73 75	90.82 86	94.44 43	94.59 165	86.37 39	97.18 12	97.02 46	89.20 57	84.31 244	96.66 59	73.74 189	99.17 46	86.74 136	97.96 67	97.79 82

test2506		87.21 209	86.28 206	90.02 217	95.62 122	73.64 310	96.25 47	71.38 381	87.89 102	90.45 110	96.65 60	55.29 341	98.09 144	86.03 145	96.94 85	98.33 42

test1111		89.10 138	88.64 133	90.48 194	95.53 125	74.97 298	96.08 56	84.89 359	88.13 95	90.16 116	96.65 60	63.29 298	98.10 136	86.14 141	96.90 87	98.39 38

ECVR-MVS		89.09 140	88.53 137	90.77 183	95.62 122	75.89 291	96.16 50	84.22 361	87.89 102	90.20 114	96.65 60	63.19 300	98.10 136	85.90 146	96.94 85	98.33 42

CDPH-MVS		92.83 59	92.30 65	94.44 43	97.79 49	86.11 47	94.06 178	96.66 83	80.09 263	92.77 64	96.63 63	86.62 36	99.04 56	87.40 126	98.66 39	98.17 59

3Dnovator+	87.14 4	92.42 66	91.37 74	95.55 6	95.63 121	88.73 6	97.07 18	96.77 72	90.84 15	84.02 248	96.62 64	75.95 153	99.34 33	87.77 120	97.68 75	98.59 23

EI-MVSNet-UG-set		92.74 61	92.62 61	93.12 72	94.86 153	83.20 113	94.40 153	95.74 147	90.71 22	92.05 81	96.60 65	84.00 66	98.99 68	91.55 74	93.63 144	97.17 104

NCCC		94.81 14	94.69 16	95.17 13	97.83 48	87.46 15	95.66 79	96.93 55	92.34 3	93.94 37	96.58 66	87.74 27	99.44 28	92.83 40	98.40 51	98.62 20

Vis-MVSNet		91.75 74	91.23 77	93.29 65	95.32 130	83.78 97	96.14 53	95.98 127	89.89 37	90.45 110	96.58 66	75.09 165	98.31 124	84.75 160	96.90 87	97.78 83
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_vis1_n_1920		89.39 133	89.84 104	88.04 273	92.97 228	72.64 322	94.71 134	96.03 126	86.18 138	91.94 87	96.56 68	61.63 307	95.74 298	93.42 31	95.11 119	95.74 161

UA-Net		92.83 59	92.54 62	93.68 61	96.10 100	84.71 72	95.66 79	96.39 97	91.92 6	93.22 50	96.49 69	83.16 74	98.87 78	84.47 164	95.47 110	97.45 95

MG-MVS		91.77 73	91.70 72	92.00 123	97.08 71	80.03 207	93.60 202	95.18 185	87.85 104	90.89 106	96.47 70	82.06 91	98.36 116	85.07 154	97.04 84	97.62 86

CPTT-MVS		91.99 69	91.80 70	92.55 101	98.24 31	81.98 150	96.76 30	96.49 93	81.89 235	90.24 113	96.44 71	78.59 126	98.61 98	89.68 98	97.85 71	97.06 109

test_prior2							94.12 170		87.67 108	92.63 69	96.39 72	86.62 36		91.50 75	98.67 38

MCST-MVS		94.45 20	94.20 30	95.19 12	98.46 19	87.50 13	95.00 115	97.12 40	87.13 116	92.51 73	96.30 73	89.24 17	99.34 33	93.46 29	98.62 43	98.73 16

PHI-MVS		93.89 38	93.65 46	94.62 39	96.84 75	86.43 37	96.69 32	97.49 6	85.15 163	93.56 45	96.28 74	85.60 46	99.31 38	92.45 46	98.79 23	98.12 63

新几何1				93.10 73	97.30 66	84.35 86		95.56 159	71.09 351	91.26 103	96.24 75	82.87 78	98.86 80	79.19 248	98.10 61	96.07 147

CS-MVS		94.12 32	94.44 19	93.17 70	96.55 84	83.08 119	97.63 3	96.95 53	91.71 10	93.50 47	96.21 76	85.61 45	98.24 126	93.64 27	98.17 57	98.19 57

TEST9					97.53 58	86.49 35	94.07 176	96.78 70	81.61 243	92.77 64	96.20 77	87.71 28	99.12 50

train_agg		93.44 47	93.08 53	94.52 42	97.53 58	86.49 35	94.07 176	96.78 70	81.86 236	92.77 64	96.20 77	87.63 29	99.12 50	92.14 58	98.69 34	97.94 72

test_8					97.49 60	86.30 43	94.02 181	96.76 73	81.86 236	92.70 68	96.20 77	87.63 29	99.02 60

QAPM		89.51 124	88.15 150	93.59 62	94.92 149	84.58 74	96.82 29	96.70 81	78.43 287	83.41 263	96.19 80	73.18 196	99.30 39	77.11 268	96.54 95	96.89 119

casdiffmvs		92.51 64	92.43 64	92.74 91	94.41 177	81.98 150	94.54 143	96.23 109	89.57 48	91.96 85	96.17 81	82.58 80	98.01 151	90.95 85	95.45 112	98.23 55
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test222					96.55 84	81.70 156	92.22 253	95.01 192	68.36 357	90.20 114	96.14 82	80.26 105			97.80 72	96.05 149

OMC-MVS		91.23 83	90.62 88	93.08 75	96.27 93	84.07 90	93.52 204	95.93 131	86.95 121	89.51 123	96.13 83	78.50 128	98.35 118	85.84 148	92.90 162	96.83 120

OpenMVS	83.78 11	88.74 153	87.29 170	93.08 75	92.70 235	85.39 65	96.57 35	96.43 95	78.74 282	80.85 293	96.07 84	69.64 239	99.01 62	78.01 259	96.65 94	94.83 194

casdiffmvs_mvg		92.96 58	92.83 58	93.35 64	94.59 165	83.40 108	95.00 115	96.34 100	90.30 29	92.05 81	96.05 85	83.43 71	98.15 133	92.07 60	95.67 105	98.49 28
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_cas_vis1_n_1920		88.83 152	88.85 130	88.78 252	91.15 284	76.72 280	93.85 192	94.93 199	83.23 205	92.81 62	96.00 86	61.17 315	94.45 318	91.67 73	94.84 121	95.17 179

baseline		92.39 67	92.29 66	92.69 95	94.46 174	81.77 155	94.14 169	96.27 104	89.22 56	91.88 88	96.00 86	82.35 83	97.99 153	91.05 80	95.27 117	98.30 46

IS-MVSNet		91.43 79	91.09 81	92.46 105	95.87 113	81.38 167	96.95 19	93.69 250	89.72 46	89.50 124	95.98 88	78.57 127	97.77 163	83.02 182	96.50 97	98.22 56

LS3D		87.89 174	86.32 204	92.59 99	96.07 102	82.92 126	95.23 99	94.92 200	75.66 313	82.89 270	95.98 88	72.48 205	99.21 44	68.43 327	95.23 118	95.64 165

原ACMM1				92.01 120	97.34 64	81.05 175		96.81 68	78.89 277	90.45 110	95.92 90	82.65 79	98.84 84	80.68 227	98.26 56	96.14 141

VNet		92.24 68	91.91 69	93.24 67	96.59 82	83.43 106	94.84 125	96.44 94	89.19 58	94.08 35	95.90 91	77.85 137	98.17 131	88.90 107	93.38 153	98.13 61

CANet		93.54 44	93.20 52	94.55 41	95.65 120	85.73 62	94.94 118	96.69 82	91.89 7	90.69 108	95.88 92	81.99 93	99.54 19	93.14 36	97.95 68	98.39 38

MVS_111021_HR		93.45 46	93.31 49	93.84 56	96.99 72	84.84 69	93.24 219	97.24 31	88.76 71	91.60 97	95.85 93	86.07 43	98.66 92	91.91 68	98.16 58	98.03 69

mvsany_test1		85.42 251	85.30 238	85.77 316	87.95 345	75.41 297	87.61 333	80.97 369	76.82 303	88.68 135	95.83 94	77.44 138	90.82 357	85.90 146	86.51 247	91.08 331

DP-MVS Recon		91.95 70	91.28 76	93.96 53	98.33 27	85.92 55	94.66 137	96.66 83	82.69 217	90.03 119	95.82 95	82.30 85	99.03 57	84.57 162	96.48 98	96.91 118

EC-MVSNet		93.44 47	93.71 44	92.63 97	95.21 135	82.43 140	97.27 9	96.71 80	90.57 25	92.88 58	95.80 96	83.16 74	98.16 132	93.68 26	98.14 59	97.31 97

EPNet		91.79 72	91.02 82	94.10 51	90.10 317	85.25 67	96.03 60	92.05 287	92.83 2	87.39 161	95.78 97	79.39 117	99.01 62	88.13 116	97.48 77	98.05 67
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CS-MVS-test		94.02 34	94.29 24	93.24 67	96.69 78	83.24 111	97.49 5	96.92 56	92.14 4	92.90 57	95.77 98	85.02 55	98.33 121	93.03 37	98.62 43	98.13 61

XVG-OURS		89.40 132	88.70 131	91.52 148	94.06 187	81.46 164	91.27 274	96.07 121	86.14 140	88.89 133	95.77 98	68.73 255	97.26 214	87.39 127	89.96 192	95.83 157

XVG-OURS-SEG-HR		89.95 112	89.45 110	91.47 152	94.00 193	81.21 172	91.87 261	96.06 123	85.78 145	88.55 137	95.73 100	74.67 173	97.27 212	88.71 110	89.64 201	95.91 152

MVS_111021_LR		92.47 65	92.29 66	92.98 80	95.99 108	84.43 84	93.08 224	96.09 119	88.20 92	91.12 104	95.72 101	81.33 98	97.76 164	91.74 71	97.37 80	96.75 122

CSCG		93.23 55	93.05 54	93.76 60	98.04 40	84.07 90	96.22 48	97.37 21	84.15 180	90.05 118	95.66 102	87.77 26	99.15 49	89.91 97	98.27 55	98.07 65

h-mvs33		90.80 89	90.15 95	92.75 90	96.01 104	82.66 136	95.43 87	95.53 163	89.80 40	93.08 53	95.64 103	75.77 154	99.00 66	92.07 60	78.05 331	96.60 126

EPP-MVSNet		91.70 76	91.56 73	92.13 119	95.88 111	80.50 191	97.33 7	95.25 181	86.15 139	89.76 121	95.60 104	83.42 72	98.32 123	87.37 128	93.25 156	97.56 91

TSAR-MVS + GP.		93.66 43	93.41 48	94.41 47	96.59 82	86.78 24	94.40 153	93.93 240	89.77 44	94.21 31	95.59 105	87.35 32	98.61 98	92.72 43	96.15 101	97.83 80

test_fmvs1_n		87.03 216	87.04 177	86.97 298	89.74 325	71.86 329	94.55 142	94.43 221	78.47 285	91.95 86	95.50 106	51.16 353	93.81 330	93.02 38	94.56 129	95.26 176

Anonymous202405211		87.68 180	86.13 210	92.31 113	96.66 79	80.74 185	94.87 123	91.49 305	80.47 259	89.46 125	95.44 107	54.72 343	98.23 127	82.19 198	89.89 194	97.97 71

TAPA-MVS	84.62 6	88.16 168	87.01 178	91.62 144	96.64 80	80.65 186	94.39 155	96.21 113	76.38 306	86.19 188	95.44 107	79.75 110	98.08 146	62.75 353	95.29 115	96.13 142
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OPM-MVS		90.12 105	89.56 108	91.82 137	93.14 219	83.90 94	94.16 168	95.74 147	88.96 67	87.86 148	95.43 109	72.48 205	97.91 159	88.10 118	90.18 189	93.65 259
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		89.59 122	89.44 111	90.03 215	95.74 116	75.85 292	95.61 83	90.80 322	87.66 109	87.83 150	95.40 110	76.79 143	96.46 265	78.37 252	96.73 91	97.80 81

test_vis1_n		86.56 230	86.49 199	86.78 305	88.51 334	72.69 319	94.68 135	93.78 248	79.55 269	90.70 107	95.31 111	48.75 358	93.28 338	93.15 35	93.99 138	94.38 219

EI-MVSNet		89.10 138	88.86 129	89.80 227	91.84 256	78.30 249	93.70 199	95.01 192	85.73 147	87.15 163	95.28 112	79.87 109	97.21 219	83.81 173	87.36 239	93.88 241

CVMVSNet		84.69 266	84.79 250	84.37 327	91.84 256	64.92 363	93.70 199	91.47 306	66.19 360	86.16 189	95.28 112	67.18 266	93.33 337	80.89 223	90.42 186	94.88 192

114514_t		89.51 124	88.50 139	92.54 102	98.11 36	81.99 149	95.16 106	96.36 99	70.19 354	85.81 192	95.25 114	76.70 145	98.63 96	82.07 200	96.86 90	97.00 114

test_fmvs1		87.34 200	87.56 163	86.68 306	90.59 307	71.80 331	94.01 182	94.04 238	78.30 289	91.97 84	95.22 115	56.28 336	93.71 332	92.89 39	94.71 123	94.52 207

RPSCF		85.07 259	84.27 256	87.48 285	92.91 230	70.62 343	91.69 267	92.46 273	76.20 310	82.67 273	95.22 115	63.94 294	97.29 211	77.51 264	85.80 251	94.53 206

Anonymous20240529		88.09 170	86.59 194	92.58 100	96.53 86	81.92 152	95.99 61	95.84 140	74.11 330	89.06 131	95.21 117	61.44 310	98.81 85	83.67 176	87.47 236	97.01 113

SDMVSNet		90.19 104	89.61 107	91.93 128	96.00 105	83.09 118	92.89 231	95.98 127	88.73 72	86.85 174	95.20 118	72.09 209	97.08 226	88.90 107	89.85 196	95.63 166

sd_testset		88.59 158	87.85 158	90.83 180	96.00 105	80.42 193	92.35 247	94.71 214	88.73 72	86.85 174	95.20 118	67.31 262	96.43 267	79.64 241	89.85 196	95.63 166

LPG-MVS_test		89.45 127	88.90 127	91.12 165	94.47 172	81.49 162	95.30 93	96.14 115	86.73 127	85.45 208	95.16 120	69.89 235	98.10 136	87.70 122	89.23 208	93.77 252

LGP-MVS_train				91.12 165	94.47 172	81.49 162		96.14 115	86.73 127	85.45 208	95.16 120	69.89 235	98.10 136	87.70 122	89.23 208	93.77 252

CNLPA		89.07 142	87.98 154	92.34 111	96.87 74	84.78 71	94.08 175	93.24 255	81.41 246	84.46 234	95.13 122	75.57 161	96.62 249	77.21 266	93.84 142	95.61 168

DELS-MVS		93.43 50	93.25 50	93.97 52	95.42 127	85.04 68	93.06 226	97.13 39	90.74 20	91.84 90	95.09 123	86.32 39	99.21 44	91.22 78	98.45 49	97.65 85
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
DPM-MVS		92.58 63	91.74 71	95.08 14	96.19 95	89.31 5	92.66 237	96.56 91	83.44 198	91.68 96	95.04 124	86.60 38	98.99 68	85.60 150	97.92 69	96.93 117

DP-MVS		87.25 205	85.36 237	92.90 84	97.65 55	83.24 111	94.81 127	92.00 289	74.99 321	81.92 282	95.00 125	72.66 202	99.05 54	66.92 338	92.33 170	96.40 132

diffmvs		91.37 81	91.23 77	91.77 140	93.09 221	80.27 195	92.36 246	95.52 164	87.03 119	91.40 101	94.93 126	80.08 106	97.44 192	92.13 59	94.56 129	97.61 87
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSFormer		91.68 77	91.30 75	92.80 87	93.86 198	83.88 95	95.96 63	95.90 135	84.66 175	91.76 93	94.91 127	77.92 134	97.30 208	89.64 99	97.11 81	97.24 100

jason		90.80 89	90.10 96	92.90 84	93.04 224	83.53 104	93.08 224	94.15 233	80.22 260	91.41 100	94.91 127	76.87 141	97.93 158	90.28 96	96.90 87	97.24 100
jason: jason.
alignmvs		93.08 56	92.50 63	94.81 30	95.62 122	87.61 12	95.99 61	96.07 121	89.77 44	94.12 33	94.87 129	80.56 102	98.66 92	92.42 48	93.10 159	98.15 60

HQP_MVS		90.60 99	90.19 93	91.82 137	94.70 161	82.73 132	95.85 67	96.22 110	90.81 16	86.91 170	94.86 130	74.23 177	98.12 134	88.15 114	89.99 190	94.63 199

plane_prior4											94.86 130

nrg030		91.08 87	90.39 89	93.17 70	93.07 222	86.91 20	96.41 38	96.26 105	88.30 86	88.37 141	94.85 132	82.19 88	97.64 175	91.09 79	82.95 276	94.96 187

mvsmamba		89.96 111	89.50 109	91.33 158	92.90 231	81.82 153	96.68 33	92.37 275	89.03 63	87.00 166	94.85 132	73.05 197	97.65 172	91.03 81	88.63 217	94.51 209

BH-RMVSNet		88.37 162	87.48 165	91.02 173	95.28 131	79.45 222	92.89 231	93.07 259	85.45 156	86.91 170	94.84 134	70.35 230	97.76 164	73.97 295	94.59 128	95.85 155

PAPM_NR		91.22 84	90.78 87	92.52 103	97.60 56	81.46 164	94.37 159	96.24 108	86.39 133	87.41 158	94.80 135	82.06 91	98.48 105	82.80 188	95.37 113	97.61 87

RRT_MVS		89.09 140	88.62 136	90.49 192	92.85 232	79.65 218	96.41 38	94.41 223	88.22 90	85.50 204	94.77 136	69.36 243	97.31 207	89.33 102	86.73 246	94.51 209

GeoE		90.05 107	89.43 112	91.90 133	95.16 137	80.37 194	95.80 70	94.65 217	83.90 185	87.55 157	94.75 137	78.18 132	97.62 177	81.28 215	93.63 144	97.71 84

test_yl		90.69 93	90.02 101	92.71 92	95.72 117	82.41 143	94.11 171	95.12 187	85.63 151	91.49 98	94.70 138	74.75 169	98.42 114	86.13 143	92.53 167	97.31 97

DCV-MVSNet		90.69 93	90.02 101	92.71 92	95.72 117	82.41 143	94.11 171	95.12 187	85.63 151	91.49 98	94.70 138	74.75 169	98.42 114	86.13 143	92.53 167	97.31 97

FIs		90.51 100	90.35 90	90.99 176	93.99 194	80.98 177	95.73 74	97.54 4	89.15 59	86.72 177	94.68 140	81.83 95	97.24 216	85.18 153	88.31 226	94.76 197

FC-MVSNet-test		90.27 102	90.18 94	90.53 188	93.71 204	79.85 214	95.77 72	97.59 3	89.31 54	86.27 186	94.67 141	81.93 94	97.01 232	84.26 166	88.09 229	94.71 198

AdaColmap		89.89 115	89.07 121	92.37 110	97.41 62	83.03 120	94.42 152	95.92 132	82.81 214	86.34 185	94.65 142	73.89 185	99.02 60	80.69 226	95.51 108	95.05 182

F-COLMAP		87.95 173	86.80 183	91.40 154	96.35 92	80.88 181	94.73 132	95.45 169	79.65 268	82.04 280	94.61 143	71.13 216	98.50 104	76.24 277	91.05 181	94.80 196

canonicalmvs		93.27 53	92.75 59	94.85 24	95.70 119	87.66 11	96.33 41	96.41 96	90.00 36	94.09 34	94.60 144	82.33 84	98.62 97	92.40 49	92.86 163	98.27 51

tttt0517		88.61 156	87.78 159	91.11 168	94.96 146	77.81 262	95.35 89	89.69 341	85.09 165	88.05 146	94.59 145	66.93 269	98.48 105	83.27 179	92.13 172	97.03 112

VPNet		88.20 167	87.47 166	90.39 199	93.56 210	79.46 221	94.04 179	95.54 162	88.67 75	86.96 167	94.58 146	69.33 244	97.15 221	84.05 169	80.53 314	94.56 205

UniMVSNet_ETH3D		87.53 192	86.37 201	91.00 175	92.44 239	78.96 235	94.74 131	95.61 157	84.07 182	85.36 218	94.52 147	59.78 324	97.34 206	82.93 183	87.88 232	96.71 124

PVSNet_Blended_VisFu		91.38 80	90.91 84	92.80 87	96.39 90	83.17 114	94.87 123	96.66 83	83.29 202	89.27 127	94.46 148	80.29 104	99.17 46	87.57 124	95.37 113	96.05 149

bld_raw_dy_0_64		87.60 189	86.73 185	90.21 205	91.72 261	80.26 197	95.09 110	88.61 346	85.68 149	85.55 198	94.38 149	63.93 295	96.66 246	87.73 121	87.84 234	93.72 256

ACMM	84.12 9	89.14 137	88.48 142	91.12 165	94.65 164	81.22 171	95.31 91	96.12 118	85.31 159	85.92 191	94.34 150	70.19 233	98.06 148	85.65 149	88.86 215	94.08 233
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PCF-MVS	84.11 10	87.74 179	86.08 214	92.70 94	94.02 189	84.43 84	89.27 309	95.87 138	73.62 335	84.43 236	94.33 151	78.48 129	98.86 80	70.27 313	94.45 133	94.81 195
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WTY-MVS		89.60 121	88.92 125	91.67 143	95.47 126	81.15 173	92.38 245	94.78 211	83.11 206	89.06 131	94.32 152	78.67 125	96.61 252	81.57 212	90.89 183	97.24 100

ACMP	84.23 8	89.01 146	88.35 143	90.99 176	94.73 158	81.27 168	95.07 111	95.89 137	86.48 130	83.67 256	94.30 153	69.33 244	97.99 153	87.10 135	88.55 218	93.72 256
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cdsmvs_eth3d_5k		22.14 350	29.52 353	0.00 369	0.00 392	0.00 393	0.00 380	95.76 145	0.00 387	0.00 388	94.29 154	75.66 160	0.00 388	0.00 386	0.00 386	0.00 384

PS-MVSNAJss		89.97 110	89.62 106	91.02 173	91.90 254	80.85 182	95.26 98	95.98 127	86.26 135	86.21 187	94.29 154	79.70 112	97.65 172	88.87 109	88.10 227	94.57 204

lupinMVS		90.92 88	90.21 92	93.03 78	93.86 198	83.88 95	92.81 234	93.86 244	79.84 265	91.76 93	94.29 154	77.92 134	98.04 149	90.48 95	97.11 81	97.17 104

API-MVS		90.66 95	90.07 97	92.45 106	96.36 91	84.57 75	96.06 59	95.22 184	82.39 220	89.13 128	94.27 157	80.32 103	98.46 108	80.16 235	96.71 92	94.33 220

CANet_DTU		90.26 103	89.41 113	92.81 86	93.46 213	83.01 122	93.48 205	94.47 220	89.43 51	87.76 153	94.23 158	70.54 229	99.03 57	84.97 155	96.39 99	96.38 133

PLC	84.53 7	89.06 143	88.03 153	92.15 118	97.27 68	82.69 135	94.29 161	95.44 171	79.71 267	84.01 249	94.18 159	76.68 146	98.75 88	77.28 265	93.41 152	95.02 183
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
iter_conf_final		89.42 129	88.69 132	91.60 145	95.12 140	82.93 125	95.75 73	92.14 284	87.32 114	87.12 165	94.07 160	67.09 267	97.55 181	90.61 91	89.01 212	94.32 221

iter_conf05		88.85 148	88.08 152	91.17 164	94.27 182	81.64 157	95.18 103	92.15 283	86.23 137	87.28 162	94.07 160	63.89 296	97.55 181	90.63 90	89.00 213	94.32 221

xiu_mvs_v1_base_debu		90.64 96	90.05 98	92.40 107	93.97 195	84.46 81	93.32 210	95.46 166	85.17 160	92.25 76	94.03 162	70.59 225	98.57 101	90.97 82	94.67 124	94.18 225

xiu_mvs_v1_base		90.64 96	90.05 98	92.40 107	93.97 195	84.46 81	93.32 210	95.46 166	85.17 160	92.25 76	94.03 162	70.59 225	98.57 101	90.97 82	94.67 124	94.18 225

xiu_mvs_v1_base_debi		90.64 96	90.05 98	92.40 107	93.97 195	84.46 81	93.32 210	95.46 166	85.17 160	92.25 76	94.03 162	70.59 225	98.57 101	90.97 82	94.67 124	94.18 225

jajsoiax		88.24 166	87.50 164	90.48 194	90.89 297	80.14 200	95.31 91	95.65 155	84.97 167	84.24 245	94.02 165	65.31 286	97.42 194	88.56 111	88.52 220	93.89 239

XXY-MVS		87.65 182	86.85 181	90.03 215	92.14 246	80.60 189	93.76 195	95.23 182	82.94 211	84.60 229	94.02 165	74.27 176	95.49 307	81.04 218	83.68 269	94.01 237

baseline1		88.10 169	87.28 171	90.57 186	94.96 146	80.07 203	94.27 162	91.29 310	86.74 126	87.41 158	94.00 167	76.77 144	96.20 277	80.77 224	79.31 327	95.44 170

NP-MVS					94.37 178	82.42 141					93.98 168

HQP-MVS		89.80 117	89.28 118	91.34 157	94.17 184	81.56 158	94.39 155	96.04 124	88.81 68	85.43 211	93.97 169	73.83 187	97.96 155	87.11 133	89.77 199	94.50 212

mvs_tets		88.06 172	87.28 171	90.38 201	90.94 293	79.88 212	95.22 100	95.66 153	85.10 164	84.21 246	93.94 170	63.53 297	97.40 201	88.50 112	88.40 224	93.87 242

CHOSEN 1792x2688		88.84 149	87.69 160	92.30 114	96.14 96	81.42 166	90.01 299	95.86 139	74.52 326	87.41 158	93.94 170	75.46 162	98.36 116	80.36 231	95.53 107	97.12 108

UGNet		89.95 112	88.95 124	92.95 82	94.51 171	83.31 110	95.70 76	95.23 182	89.37 53	87.58 155	93.94 170	64.00 293	98.78 87	83.92 171	96.31 100	96.74 123
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
TAMVS		89.21 136	88.29 147	91.96 126	93.71 204	82.62 138	93.30 214	94.19 231	82.22 224	87.78 152	93.94 170	78.83 121	96.95 235	77.70 261	92.98 161	96.32 134

sss		88.93 147	88.26 149	90.94 179	94.05 188	80.78 184	91.71 265	95.38 175	81.55 244	88.63 136	93.91 174	75.04 166	95.47 308	82.47 192	91.61 174	96.57 128

1112_ss		88.42 160	87.33 169	91.72 141	94.92 149	80.98 177	92.97 229	94.54 218	78.16 293	83.82 252	93.88 175	78.78 123	97.91 159	79.45 243	89.41 203	96.26 138

ab-mvs-re		7.82 354	10.43 357	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	93.88 175	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

TranMVSNet+NR-MVSNet		88.84 149	87.95 155	91.49 150	92.68 236	83.01 122	94.92 120	96.31 101	89.88 38	85.53 201	93.85 177	76.63 147	96.96 234	81.91 204	79.87 322	94.50 212

mvs_anonymous		89.37 134	89.32 116	89.51 238	93.47 212	74.22 305	91.65 268	94.83 207	82.91 212	85.45 208	93.79 178	81.23 99	96.36 272	86.47 140	94.09 137	97.94 72

thisisatest0530		88.67 154	87.61 162	91.86 134	94.87 152	80.07 203	94.63 138	89.90 338	84.00 183	88.46 139	93.78 179	66.88 271	98.46 108	83.30 178	92.65 165	97.06 109

MVS_Test		91.31 82	91.11 79	91.93 128	94.37 178	80.14 200	93.46 207	95.80 142	86.46 131	91.35 102	93.77 180	82.21 87	98.09 144	87.57 124	94.95 120	97.55 92

COLMAP_ROB	80.39 16	83.96 273	82.04 280	89.74 228	95.28 131	79.75 215	94.25 163	92.28 279	75.17 319	78.02 321	93.77 180	58.60 329	97.84 161	65.06 346	85.92 250	91.63 317
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PAPR		90.02 108	89.27 119	92.29 115	95.78 115	80.95 179	92.68 236	96.22 110	81.91 233	86.66 178	93.75 182	82.23 86	98.44 112	79.40 247	94.79 122	97.48 93

ab-mvs		89.41 130	88.35 143	92.60 98	95.15 139	82.65 137	92.20 254	95.60 158	83.97 184	88.55 137	93.70 183	74.16 181	98.21 130	82.46 193	89.37 204	96.94 116

hse-mvs2		89.88 116	89.34 115	91.51 149	94.83 155	81.12 174	93.94 187	93.91 243	89.80 40	93.08 53	93.60 184	75.77 154	97.66 171	92.07 60	77.07 338	95.74 161

test_fmvs2		83.98 272	84.03 259	83.83 332	87.16 348	67.53 357	93.93 188	92.89 262	77.62 295	86.89 173	93.53 185	47.18 362	92.02 349	90.54 92	86.51 247	91.93 312

AUN-MVS		87.78 178	86.54 196	91.48 151	94.82 156	81.05 175	93.91 191	93.93 240	83.00 209	86.93 168	93.53 185	69.50 241	97.67 169	86.14 141	77.12 337	95.73 163

BH-untuned		88.60 157	88.13 151	90.01 218	95.24 134	78.50 243	93.29 215	94.15 233	84.75 172	84.46 234	93.40 187	75.76 156	97.40 201	77.59 262	94.52 131	94.12 229

AllTest		83.42 278	81.39 284	89.52 236	95.01 142	77.79 264	93.12 221	90.89 320	77.41 297	76.12 333	93.34 188	54.08 346	97.51 185	68.31 328	84.27 263	93.26 271

TestCases				89.52 236	95.01 142	77.79 264		90.89 320	77.41 297	76.12 333	93.34 188	54.08 346	97.51 185	68.31 328	84.27 263	93.26 271

UniMVSNet_NR-MVSNet		89.92 114	89.29 117	91.81 139	93.39 214	83.72 98	94.43 151	97.12 40	89.80 40	86.46 180	93.32 190	83.16 74	97.23 217	84.92 156	81.02 305	94.49 214

VPA-MVSNet		89.62 120	88.96 123	91.60 145	93.86 198	82.89 127	95.46 86	97.33 24	87.91 99	88.43 140	93.31 191	74.17 180	97.40 201	87.32 129	82.86 281	94.52 207

ITE_SJBPF				88.24 268	91.88 255	77.05 276		92.92 261	85.54 154	80.13 304	93.30 192	57.29 333	96.20 277	72.46 303	84.71 259	91.49 319

DU-MVS		89.34 135	88.50 139	91.85 136	93.04 224	83.72 98	94.47 148	96.59 88	89.50 49	86.46 180	93.29 193	77.25 139	97.23 217	84.92 156	81.02 305	94.59 202

NR-MVSNet		88.58 159	87.47 166	91.93 128	93.04 224	84.16 89	94.77 130	96.25 107	89.05 61	80.04 306	93.29 193	79.02 120	97.05 230	81.71 211	80.05 319	94.59 202

CDS-MVSNet		89.45 127	88.51 138	92.29 115	93.62 208	83.61 103	93.01 227	94.68 216	81.95 231	87.82 151	93.24 195	78.69 124	96.99 233	80.34 232	93.23 157	96.28 137
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPM		86.68 226	85.39 235	90.53 188	93.05 223	79.33 229	89.79 302	94.77 212	78.82 279	81.95 281	93.24 195	76.81 142	97.30 208	66.94 336	93.16 158	94.95 190

OurMVSNet-221017-0		85.35 253	84.64 253	87.49 284	90.77 301	72.59 324	94.01 182	94.40 224	84.72 173	79.62 312	93.17 197	61.91 306	96.72 243	81.99 202	81.16 299	93.16 278

PEN-MVS		86.80 221	86.27 207	88.40 262	92.32 242	75.71 294	95.18 103	96.38 98	87.97 97	82.82 271	93.15 198	73.39 194	95.92 288	76.15 278	79.03 329	93.59 260

xiu_mvs_v2_base		91.13 86	90.89 85	91.86 134	94.97 145	82.42 141	92.24 252	95.64 156	86.11 142	91.74 95	93.14 199	79.67 115	98.89 77	89.06 106	95.46 111	94.28 224

MVSTER		88.84 149	88.29 147	90.51 191	92.95 229	80.44 192	93.73 196	95.01 192	84.66 175	87.15 163	93.12 200	72.79 201	97.21 219	87.86 119	87.36 239	93.87 242

Effi-MVS+		91.59 78	91.11 79	93.01 79	94.35 181	83.39 109	94.60 139	95.10 189	87.10 117	90.57 109	93.10 201	81.43 97	98.07 147	89.29 103	94.48 132	97.59 89

PS-CasMVS		87.32 202	86.88 179	88.63 259	92.99 227	76.33 288	95.33 90	96.61 87	88.22 90	83.30 267	93.07 202	73.03 199	95.79 296	78.36 253	81.00 307	93.75 254

DTE-MVSNet		86.11 239	85.48 233	87.98 274	91.65 267	74.92 299	94.93 119	95.75 146	87.36 113	82.26 276	93.04 203	72.85 200	95.82 294	74.04 294	77.46 335	93.20 276

CP-MVSNet		87.63 185	87.26 173	88.74 256	93.12 220	76.59 283	95.29 95	96.58 89	88.43 82	83.49 262	92.98 204	75.28 163	95.83 293	78.97 249	81.15 301	93.79 247

test_djsdf		89.03 144	88.64 133	90.21 205	90.74 303	79.28 230	95.96 63	95.90 135	84.66 175	85.33 219	92.94 205	74.02 183	97.30 208	89.64 99	88.53 219	94.05 235

MAR-MVS		90.30 101	89.37 114	93.07 77	96.61 81	84.48 80	95.68 77	95.67 151	82.36 222	87.85 149	92.85 206	76.63 147	98.80 86	80.01 236	96.68 93	95.91 152
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
testgi		80.94 304	80.20 295	83.18 333	87.96 344	66.29 358	91.28 273	90.70 324	83.70 190	78.12 319	92.84 207	51.37 352	90.82 357	63.34 350	82.46 283	92.43 301

EU-MVSNet		81.32 299	80.95 287	82.42 338	88.50 336	63.67 364	93.32 210	91.33 308	64.02 363	80.57 298	92.83 208	61.21 314	92.27 347	76.34 275	80.38 317	91.32 322

ACMH+	81.04 14	85.05 260	83.46 268	89.82 224	94.66 163	79.37 224	94.44 150	94.12 236	82.19 225	78.04 320	92.82 209	58.23 330	97.54 183	73.77 297	82.90 280	92.54 296

WR-MVS		88.38 161	87.67 161	90.52 190	93.30 216	80.18 198	93.26 217	95.96 130	88.57 79	85.47 207	92.81 210	76.12 149	96.91 238	81.24 216	82.29 285	94.47 217

tt0805		86.92 218	85.74 230	90.48 194	92.22 243	79.98 210	95.63 82	94.88 203	83.83 188	84.74 227	92.80 211	57.61 332	97.67 169	85.48 152	84.42 261	93.79 247

HY-MVS	83.01 12	89.03 144	87.94 156	92.29 115	94.86 153	82.77 128	92.08 259	94.49 219	81.52 245	86.93 168	92.79 212	78.32 131	98.23 127	79.93 237	90.55 184	95.88 154

LTVRE_ROB	82.13 13	86.26 238	84.90 247	90.34 203	94.44 176	81.50 160	92.31 251	94.89 201	83.03 208	79.63 311	92.67 213	69.69 238	97.79 162	71.20 308	86.26 249	91.72 315
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
ACMH	80.38 17	85.36 252	83.68 265	90.39 199	94.45 175	80.63 187	94.73 132	94.85 205	82.09 226	77.24 325	92.65 214	60.01 322	97.58 178	72.25 304	84.87 258	92.96 285
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pm-mvs1		86.61 227	85.54 231	89.82 224	91.44 269	80.18 198	95.28 97	94.85 205	83.84 187	81.66 283	92.62 215	72.45 207	96.48 262	79.67 240	78.06 330	92.82 291

FA-MVS(test-final)		89.66 119	88.91 126	91.93 128	94.57 168	80.27 195	91.36 272	94.74 213	84.87 168	89.82 120	92.61 216	74.72 172	98.47 107	83.97 170	93.53 147	97.04 111

PVSNet_Blended		90.73 92	90.32 91	91.98 124	96.12 97	81.25 169	92.55 241	96.83 65	82.04 229	89.10 129	92.56 217	81.04 100	98.85 82	86.72 138	95.91 102	95.84 156

ET-MVSNet_ETH3D		87.51 193	85.91 222	92.32 112	93.70 206	83.93 93	92.33 249	90.94 318	84.16 179	72.09 352	92.52 218	69.90 234	95.85 292	89.20 104	88.36 225	97.17 104

PS-MVSNAJ		91.18 85	90.92 83	91.96 126	95.26 133	82.60 139	92.09 258	95.70 149	86.27 134	91.84 90	92.46 219	79.70 112	98.99 68	89.08 105	95.86 103	94.29 223

CLD-MVS		89.47 126	88.90 127	91.18 163	94.22 183	82.07 148	92.13 256	96.09 119	87.90 100	85.37 217	92.45 220	74.38 175	97.56 180	87.15 131	90.43 185	93.93 238
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TR-MVS		86.78 222	85.76 228	89.82 224	94.37 178	78.41 245	92.47 242	92.83 264	81.11 254	86.36 184	92.40 221	68.73 255	97.48 187	73.75 298	89.85 196	93.57 261

Test_1112_low_res		87.65 182	86.51 197	91.08 169	94.94 148	79.28 230	91.77 263	94.30 227	76.04 311	83.51 261	92.37 222	77.86 136	97.73 168	78.69 251	89.13 210	96.22 139

EPNet_dtu		86.49 235	85.94 221	88.14 271	90.24 315	72.82 317	94.11 171	92.20 281	86.66 129	79.42 313	92.36 223	73.52 190	95.81 295	71.26 307	93.66 143	95.80 159
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UniMVSNet (Re)		89.80 117	89.07 121	92.01 120	93.60 209	84.52 78	94.78 129	97.47 11	89.26 55	86.44 183	92.32 224	82.10 89	97.39 204	84.81 159	80.84 309	94.12 229

thres600view7		87.65 182	86.67 189	90.59 185	96.08 101	78.72 236	94.88 122	91.58 301	87.06 118	88.08 144	92.30 225	68.91 252	98.10 136	70.05 320	91.10 177	94.96 187

thres100view900		87.63 185	86.71 187	90.38 201	96.12 97	78.55 240	95.03 114	91.58 301	87.15 115	88.06 145	92.29 226	68.91 252	98.10 136	70.13 317	91.10 177	94.48 215

PVSNet_BlendedMVS		89.98 109	89.70 105	90.82 181	96.12 97	81.25 169	93.92 189	96.83 65	83.49 197	89.10 129	92.26 227	81.04 100	98.85 82	86.72 138	87.86 233	92.35 305

XVG-ACMP-BASELINE		86.00 240	84.84 249	89.45 239	91.20 279	78.00 255	91.70 266	95.55 160	85.05 166	82.97 269	92.25 228	54.49 344	97.48 187	82.93 183	87.45 238	92.89 288

EIA-MVS		91.95 70	91.94 68	91.98 124	95.16 137	80.01 208	95.36 88	96.73 77	88.44 81	89.34 126	92.16 229	83.82 69	98.45 111	89.35 101	97.06 83	97.48 93

Anonymous20231211		86.59 229	85.13 241	90.98 178	96.52 87	81.50 160	96.14 53	96.16 114	73.78 333	83.65 257	92.15 230	63.26 299	97.37 205	82.82 187	81.74 294	94.06 234

MVS		87.44 196	86.10 213	91.44 153	92.61 237	83.62 102	92.63 238	95.66 153	67.26 358	81.47 285	92.15 230	77.95 133	98.22 129	79.71 239	95.48 109	92.47 299

anonymousdsp		87.84 175	87.09 174	90.12 211	89.13 329	80.54 190	94.67 136	95.55 160	82.05 227	83.82 252	92.12 232	71.47 214	97.15 221	87.15 131	87.80 235	92.67 293

TransMVSNet (Re)		84.43 268	83.06 273	88.54 260	91.72 261	78.44 244	95.18 103	92.82 265	82.73 216	79.67 310	92.12 232	73.49 191	95.96 287	71.10 312	68.73 360	91.21 325

SixPastTwentyTwo		83.91 275	82.90 275	86.92 300	90.99 289	70.67 342	93.48 205	91.99 290	85.54 154	77.62 324	92.11 234	60.59 318	96.87 240	76.05 279	77.75 332	93.20 276

HyFIR lowres test		88.09 170	86.81 182	91.93 128	96.00 105	80.63 187	90.01 299	95.79 143	73.42 336	87.68 154	92.10 235	73.86 186	97.96 155	80.75 225	91.70 173	97.19 103

Baseline_NR-MVSNet		87.07 214	86.63 192	88.40 262	91.44 269	77.87 260	94.23 166	92.57 272	84.12 181	85.74 194	92.08 236	77.25 139	96.04 282	82.29 197	79.94 320	91.30 323

USDC		82.76 281	81.26 286	87.26 289	91.17 281	74.55 301	89.27 309	93.39 254	78.26 291	75.30 338	92.08 236	54.43 345	96.63 248	71.64 305	85.79 252	90.61 334

v2v482		87.84 175	87.06 175	90.17 207	90.99 289	79.23 233	94.00 184	95.13 186	84.87 168	85.53 201	92.07 238	74.45 174	97.45 190	84.71 161	81.75 293	93.85 245

FMVSNet2		87.19 211	85.82 224	91.30 159	94.01 190	83.67 100	94.79 128	94.94 195	83.57 193	83.88 251	92.05 239	66.59 276	96.51 260	77.56 263	85.01 257	93.73 255

WR-MVS_H		87.80 177	87.37 168	89.10 246	93.23 217	78.12 253	95.61 83	97.30 28	87.90 100	83.72 254	92.01 240	79.65 116	96.01 285	76.36 274	80.54 313	93.16 278

LCM-MVSNet-Re		88.30 165	88.32 146	88.27 266	94.71 160	72.41 327	93.15 220	90.98 317	87.77 105	79.25 314	91.96 241	78.35 130	95.75 297	83.04 181	95.62 106	96.65 125

MSDG		84.86 263	83.09 272	90.14 210	93.80 201	80.05 205	89.18 312	93.09 258	78.89 277	78.19 318	91.91 242	65.86 284	97.27 212	68.47 326	88.45 222	93.11 280

IterMVS-LS		88.36 163	87.91 157	89.70 231	93.80 201	78.29 250	93.73 196	95.08 191	85.73 147	84.75 226	91.90 243	79.88 108	96.92 237	83.83 172	82.51 282	93.89 239
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet3		87.40 198	86.11 212	91.30 159	93.79 203	83.64 101	94.20 167	94.81 209	83.89 186	84.37 237	91.87 244	68.45 258	96.56 257	78.23 256	85.36 254	93.70 258

tfpn200view9		87.58 190	86.64 190	90.41 198	95.99 108	78.64 238	94.58 140	91.98 291	86.94 122	88.09 142	91.77 245	69.18 249	98.10 136	70.13 317	91.10 177	94.48 215

thres400		87.62 187	86.64 190	90.57 186	95.99 108	78.64 238	94.58 140	91.98 291	86.94 122	88.09 142	91.77 245	69.18 249	98.10 136	70.13 317	91.10 177	94.96 187

pmmvs4		85.43 250	83.86 263	90.16 208	90.02 320	82.97 124	90.27 288	92.67 270	75.93 312	80.73 294	91.74 247	71.05 217	95.73 299	78.85 250	83.46 273	91.78 314

GBi-Net		87.26 203	85.98 218	91.08 169	94.01 190	83.10 115	95.14 107	94.94 195	83.57 193	84.37 237	91.64 248	66.59 276	96.34 273	78.23 256	85.36 254	93.79 247

test1		87.26 203	85.98 218	91.08 169	94.01 190	83.10 115	95.14 107	94.94 195	83.57 193	84.37 237	91.64 248	66.59 276	96.34 273	78.23 256	85.36 254	93.79 247

FMVSNet1		85.85 244	84.11 258	91.08 169	92.81 233	83.10 115	95.14 107	94.94 195	81.64 241	82.68 272	91.64 248	59.01 328	96.34 273	75.37 283	83.78 266	93.79 247

MVP-Stereo		85.97 241	84.86 248	89.32 240	90.92 295	82.19 146	92.11 257	94.19 231	78.76 281	78.77 317	91.63 251	68.38 259	96.56 257	75.01 288	93.95 139	89.20 347
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
FE-MVS		87.40 198	86.02 216	91.57 147	94.56 169	79.69 217	90.27 288	93.72 249	80.57 258	88.80 134	91.62 252	65.32 285	98.59 100	74.97 289	94.33 136	96.44 131

1314		87.51 193	86.57 195	90.34 203	92.42 240	79.74 216	92.63 238	95.35 179	78.35 288	80.14 303	91.62 252	74.05 182	97.15 221	81.05 217	93.53 147	94.12 229

MS-PatchMatch		85.05 260	84.16 257	87.73 278	91.42 272	78.51 242	91.25 275	93.53 251	77.50 296	80.15 302	91.58 254	61.99 305	95.51 304	75.69 280	94.35 135	89.16 348

TDRefinement		79.81 311	77.34 315	87.22 293	79.24 371	75.48 296	93.12 221	92.03 288	76.45 305	75.01 339	91.58 254	49.19 357	96.44 266	70.22 316	69.18 357	89.75 341

PatchMatch-RL		86.77 225	85.54 231	90.47 197	95.88 111	82.71 134	90.54 285	92.31 278	79.82 266	84.32 242	91.57 256	68.77 254	96.39 269	73.16 300	93.48 151	92.32 306

BH-w/o		87.57 191	87.05 176	89.12 245	94.90 151	77.90 258	92.41 243	93.51 252	82.89 213	83.70 255	91.34 257	75.75 157	97.07 228	75.49 281	93.49 149	92.39 303

v8		87.50 195	86.71 187	89.89 221	91.37 274	79.40 223	94.50 144	95.38 175	84.81 171	83.60 259	91.33 258	76.05 150	97.42 194	82.84 186	80.51 316	92.84 290

V42		87.68 180	86.86 180	90.15 209	90.58 308	80.14 200	94.24 165	95.28 180	83.66 191	85.67 195	91.33 258	74.73 171	97.41 199	84.43 165	81.83 291	92.89 288

Fast-Effi-MVS+-dtu		87.44 196	86.72 186	89.63 233	92.04 250	77.68 268	94.03 180	93.94 239	85.81 144	82.42 274	91.32 260	70.33 231	97.06 229	80.33 233	90.23 188	94.14 228

v1144		87.61 188	86.79 184	90.06 214	91.01 288	79.34 226	93.95 186	95.42 174	83.36 201	85.66 196	91.31 261	74.98 167	97.42 194	83.37 177	82.06 287	93.42 268

tfpnnormal		84.72 265	83.23 270	89.20 243	92.79 234	80.05 205	94.48 145	95.81 141	82.38 221	81.08 291	91.21 262	69.01 251	96.95 235	61.69 355	80.59 312	90.58 337

ETV-MVS		92.74 61	92.66 60	92.97 81	95.20 136	84.04 92	95.07 111	96.51 92	90.73 21	92.96 56	91.19 263	84.06 65	98.34 119	91.72 72	96.54 95	96.54 130

v10		87.25 205	86.38 200	89.85 222	91.19 280	79.50 220	94.48 145	95.45 169	83.79 189	83.62 258	91.19 263	75.13 164	97.42 194	81.94 203	80.60 311	92.63 295

pmmvs5		84.21 269	82.84 277	88.34 265	88.95 331	76.94 277	92.41 243	91.91 295	75.63 314	80.28 300	91.18 265	64.59 290	95.57 301	77.09 269	83.47 272	92.53 297

v1192		87.25 205	86.33 203	90.00 219	90.76 302	79.04 234	93.80 193	95.48 165	82.57 218	85.48 206	91.18 265	73.38 195	97.42 194	82.30 196	82.06 287	93.53 262

v1240		86.78 222	85.85 223	89.56 234	90.45 312	77.79 264	93.61 201	95.37 177	81.65 240	85.43 211	91.15 267	71.50 213	97.43 193	81.47 214	82.05 289	93.47 266

CMPMVS	59.16 21	80.52 305	79.20 307	84.48 326	83.98 362	67.63 356	89.95 301	93.84 246	64.79 362	66.81 363	91.14 268	57.93 331	95.17 311	76.25 276	88.10 227	90.65 333
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
thres200		87.21 209	86.24 208	90.12 211	95.36 129	78.53 241	93.26 217	92.10 285	86.42 132	88.00 147	91.11 269	69.24 248	98.00 152	69.58 321	91.04 182	93.83 246

pmmvs6		83.42 278	81.60 282	88.87 251	88.01 343	77.87 260	94.96 117	94.24 230	74.67 325	78.80 316	91.09 270	60.17 321	96.49 261	77.06 270	75.40 344	92.23 308

v144192		87.19 211	86.35 202	89.74 228	90.64 306	78.24 251	93.92 189	95.43 172	81.93 232	85.51 203	91.05 271	74.21 179	97.45 190	82.86 185	81.56 295	93.53 262

v1921920		86.97 217	86.06 215	89.69 232	90.53 311	78.11 254	93.80 193	95.43 172	81.90 234	85.33 219	91.05 271	72.66 202	97.41 199	82.05 201	81.80 292	93.53 262

baseline2		86.50 233	85.39 235	89.84 223	91.12 285	76.70 281	91.88 260	88.58 347	82.35 223	79.95 307	90.95 273	73.42 193	97.63 176	80.27 234	89.95 193	95.19 178

thisisatest0515		87.33 201	85.99 217	91.37 156	93.49 211	79.55 219	90.63 284	89.56 344	80.17 261	87.56 156	90.86 274	67.07 268	98.28 125	81.50 213	93.02 160	96.29 136

v7n		86.81 220	85.76 228	89.95 220	90.72 304	79.25 232	95.07 111	95.92 132	84.45 178	82.29 275	90.86 274	72.60 204	97.53 184	79.42 246	80.52 315	93.08 282

DIV-MVS_self_test		86.53 231	85.78 225	88.75 254	92.02 252	76.45 285	90.74 282	94.30 227	81.83 238	83.34 265	90.82 276	75.75 157	96.57 255	81.73 210	81.52 297	93.24 274

v148		87.04 215	86.32 204	89.21 242	90.94 293	77.26 273	93.71 198	94.43 221	84.84 170	84.36 240	90.80 277	76.04 151	97.05 230	82.12 199	79.60 324	93.31 270

cl____		86.52 232	85.78 225	88.75 254	92.03 251	76.46 284	90.74 282	94.30 227	81.83 238	83.34 265	90.78 278	75.74 159	96.57 255	81.74 209	81.54 296	93.22 275

PMMVS		85.71 247	84.96 245	87.95 275	88.90 332	77.09 275	88.68 319	90.06 333	72.32 345	86.47 179	90.76 279	72.15 208	94.40 320	81.78 208	93.49 149	92.36 304

Fast-Effi-MVS+		89.41 130	88.64 133	91.71 142	94.74 157	80.81 183	93.54 203	95.10 189	83.11 206	86.82 176	90.67 280	79.74 111	97.75 167	80.51 230	93.55 146	96.57 128

IterMVS-SCA-FT		85.45 249	84.53 255	88.18 270	91.71 263	76.87 278	90.19 295	92.65 271	85.40 157	81.44 286	90.54 281	66.79 272	95.00 316	81.04 218	81.05 303	92.66 294

PVSNet	78.82 18	85.55 248	84.65 252	88.23 269	94.72 159	71.93 328	87.12 336	92.75 267	78.80 280	84.95 224	90.53 282	64.43 291	96.71 245	74.74 290	93.86 141	96.06 148

eth_miper_zixun_eth		86.50 233	85.77 227	88.68 257	91.94 253	75.81 293	90.47 286	94.89 201	82.05 227	84.05 247	90.46 283	75.96 152	96.77 242	82.76 189	79.36 326	93.46 267

c3_l		87.14 213	86.50 198	89.04 248	92.20 244	77.26 273	91.22 276	94.70 215	82.01 230	84.34 241	90.43 284	78.81 122	96.61 252	83.70 175	81.09 302	93.25 273

IterMVS		84.88 262	83.98 262	87.60 280	91.44 269	76.03 290	90.18 296	92.41 274	83.24 204	81.06 292	90.42 285	66.60 275	94.28 324	79.46 242	80.98 308	92.48 298
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_0402		81.30 300	79.17 308	87.67 279	93.19 218	78.17 252	92.98 228	91.71 296	75.25 318	76.02 335	90.31 286	59.23 326	96.37 270	50.22 369	83.63 270	88.47 354

TinyColmap		79.76 312	77.69 314	85.97 312	91.71 263	73.12 314	89.55 303	90.36 327	75.03 320	72.03 353	90.19 287	46.22 363	96.19 279	63.11 351	81.03 304	88.59 353

EG-PatchMatch MVS		82.37 286	80.34 292	88.46 261	90.27 314	79.35 225	92.80 235	94.33 226	77.14 301	73.26 349	90.18 288	47.47 361	96.72 243	70.25 314	87.32 241	89.30 345

cl22		86.78 222	85.98 218	89.18 244	92.34 241	77.62 269	90.84 281	94.13 235	81.33 248	83.97 250	90.15 289	73.96 184	96.60 254	84.19 167	82.94 277	93.33 269

lessismore_v0				86.04 311	88.46 337	68.78 351		80.59 370		73.01 350	90.11 290	55.39 339	96.43 267	75.06 287	65.06 364	92.90 287

miper_ehance_all_eth		87.22 208	86.62 193	89.02 249	92.13 247	77.40 272	90.91 280	94.81 209	81.28 249	84.32 242	90.08 291	79.26 118	96.62 249	83.81 173	82.94 277	93.04 283

D2MVS		85.90 242	85.09 242	88.35 264	90.79 300	77.42 271	91.83 262	95.70 149	80.77 257	80.08 305	90.02 292	66.74 274	96.37 270	81.88 205	87.97 231	91.26 324

LF4IMVS		80.37 307	79.07 310	84.27 329	86.64 350	69.87 348	89.39 308	91.05 315	76.38 306	74.97 340	90.00 293	47.85 360	94.25 325	74.55 293	80.82 310	88.69 352

CostFormer		85.77 246	84.94 246	88.26 267	91.16 283	72.58 325	89.47 307	91.04 316	76.26 309	86.45 182	89.97 294	70.74 223	96.86 241	82.35 195	87.07 244	95.34 175

test20.03		79.95 310	79.08 309	82.55 336	85.79 356	67.74 355	91.09 278	91.08 313	81.23 252	74.48 344	89.96 295	61.63 307	90.15 359	60.08 359	76.38 340	89.76 340

tpm		84.73 264	84.02 260	86.87 303	90.33 313	68.90 350	89.06 314	89.94 336	80.85 256	85.75 193	89.86 296	68.54 257	95.97 286	77.76 260	84.05 265	95.75 160

miper_lstm_enhance		85.27 256	84.59 254	87.31 287	91.28 278	74.63 300	87.69 330	94.09 237	81.20 253	81.36 288	89.85 297	74.97 168	94.30 323	81.03 220	79.84 323	93.01 284

test0.0.03 1		82.41 285	81.69 281	84.59 325	88.23 340	72.89 316	90.24 292	87.83 350	83.41 199	79.86 308	89.78 298	67.25 264	88.99 365	65.18 344	83.42 274	91.90 313

K. test v3		81.59 294	80.15 296	85.91 315	89.89 323	69.42 349	92.57 240	87.71 351	85.56 153	73.44 348	89.71 299	55.58 337	95.52 303	77.17 267	69.76 354	92.78 292

CHOSEN 280x420		85.15 258	83.99 261	88.65 258	92.47 238	78.40 246	79.68 369	92.76 266	74.90 323	81.41 287	89.59 300	69.85 237	95.51 304	79.92 238	95.29 115	92.03 310

GA-MVS		86.61 227	85.27 239	90.66 184	91.33 277	78.71 237	90.40 287	93.81 247	85.34 158	85.12 221	89.57 301	61.25 312	97.11 225	80.99 221	89.59 202	96.15 140

Effi-MVS+-dtu		88.65 155	88.35 143	89.54 235	93.33 215	76.39 286	94.47 148	94.36 225	87.70 107	85.43 211	89.56 302	73.45 192	97.26 214	85.57 151	91.28 176	94.97 184

tpm2		84.08 271	82.94 274	87.48 285	91.39 273	71.27 335	89.23 311	90.37 326	71.95 347	84.64 228	89.33 303	67.30 263	96.55 259	75.17 285	87.09 243	94.63 199

Anonymous20231206		81.03 302	79.77 300	84.82 324	87.85 346	70.26 345	91.42 271	92.08 286	73.67 334	77.75 322	89.25 304	62.43 303	93.08 341	61.50 356	82.00 290	91.12 328

dmvs_re		84.20 270	83.22 271	87.14 296	91.83 258	77.81 262	90.04 298	90.19 329	84.70 174	81.49 284	89.17 305	64.37 292	91.13 355	71.58 306	85.65 253	92.46 300

miper_enhance_ethall		86.90 219	86.18 209	89.06 247	91.66 266	77.58 270	90.22 294	94.82 208	79.16 274	84.48 233	89.10 306	79.19 119	96.66 246	84.06 168	82.94 277	92.94 286

ppachtmachnet_test		81.84 289	80.07 297	87.15 295	88.46 337	74.43 304	89.04 315	92.16 282	75.33 317	77.75 322	88.99 307	66.20 280	95.37 309	65.12 345	77.60 333	91.65 316

gm-plane-assit					89.60 328	68.00 352			77.28 300		88.99 307		97.57 179	79.44 244

MDTV_nov1_ep13			83.56 267		91.69 265	69.93 347	87.75 329	91.54 303	78.60 284	84.86 225	88.90 309	69.54 240	96.03 283	70.25 314	88.93 214

SCA		86.32 237	85.18 240	89.73 230	92.15 245	76.60 282	91.12 277	91.69 298	83.53 196	85.50 204	88.81 310	66.79 272	96.48 262	76.65 271	90.35 187	96.12 143

Patchmatch-test		81.37 298	79.30 304	87.58 281	90.92 295	74.16 307	80.99 365	87.68 352	70.52 353	76.63 330	88.81 310	71.21 215	92.76 344	60.01 361	86.93 245	95.83 157

tpmrst		85.35 253	84.99 243	86.43 308	90.88 298	67.88 354	88.71 318	91.43 307	80.13 262	86.08 190	88.80 312	73.05 197	96.02 284	82.48 191	83.40 275	95.40 172

DSMNet-mixed		76.94 324	76.29 323	78.89 343	83.10 365	56.11 378	87.78 328	79.77 371	60.65 366	75.64 336	88.71 313	61.56 309	88.34 366	60.07 360	89.29 207	92.21 309

PatchmatchNet		85.85 244	84.70 251	89.29 241	91.76 260	75.54 295	88.49 321	91.30 309	81.63 242	85.05 222	88.70 314	71.71 210	96.24 276	74.61 292	89.05 211	96.08 146
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MIMVSNet		82.59 284	80.53 289	88.76 253	91.51 268	78.32 248	86.57 340	90.13 331	79.32 270	80.70 295	88.69 315	52.98 350	93.07 342	66.03 341	88.86 215	94.90 191

IB-MVS	80.51 15	85.24 257	83.26 269	91.19 162	92.13 247	79.86 213	91.75 264	91.29 310	83.28 203	80.66 296	88.49 316	61.28 311	98.46 108	80.99 221	79.46 325	95.25 177
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
cascas		86.43 236	84.98 244	90.80 182	92.10 249	80.92 180	90.24 292	95.91 134	73.10 339	83.57 260	88.39 317	65.15 287	97.46 189	84.90 158	91.43 175	94.03 236

EPMVS		83.90 276	82.70 278	87.51 282	90.23 316	72.67 320	88.62 320	81.96 367	81.37 247	85.01 223	88.34 318	66.31 279	94.45 318	75.30 284	87.12 242	95.43 171

MDA-MVSNet-bldmvs		78.85 317	76.31 322	86.46 307	89.76 324	73.88 308	88.79 317	90.42 325	79.16 274	59.18 367	88.33 319	60.20 320	94.04 326	62.00 354	68.96 358	91.48 320

our_test_3		81.93 288	80.46 291	86.33 310	88.46 337	73.48 312	88.46 322	91.11 312	76.46 304	76.69 329	88.25 320	66.89 270	94.36 321	68.75 324	79.08 328	91.14 327

OpenMVS_ROB	74.94 19	79.51 313	77.03 320	86.93 299	87.00 349	76.23 289	92.33 249	90.74 323	68.93 356	74.52 343	88.23 321	49.58 356	96.62 249	57.64 363	84.29 262	87.94 357

MIMVSNet1		79.38 314	77.28 316	85.69 317	86.35 351	73.67 309	91.61 269	92.75 267	78.11 294	72.64 351	88.12 322	48.16 359	91.97 351	60.32 358	77.49 334	91.43 321

UnsupCasMVSNet_eth		80.07 309	78.27 313	85.46 318	85.24 360	72.63 323	88.45 323	94.87 204	82.99 210	71.64 355	88.07 323	56.34 335	91.75 352	73.48 299	63.36 367	92.01 311

test-LLR		85.87 243	85.41 234	87.25 290	90.95 291	71.67 333	89.55 303	89.88 339	83.41 199	84.54 231	87.95 324	67.25 264	95.11 313	81.82 206	93.37 154	94.97 184

test-mter		84.54 267	83.64 266	87.25 290	90.95 291	71.67 333	89.55 303	89.88 339	79.17 273	84.54 231	87.95 324	55.56 338	95.11 313	81.82 206	93.37 154	94.97 184

FMVSNet5		81.52 296	79.60 302	87.27 288	91.17 281	77.95 256	91.49 270	92.26 280	76.87 302	76.16 332	87.91 326	51.67 351	92.34 346	67.74 332	81.16 299	91.52 318

CR-MVSNet		85.35 253	83.76 264	90.12 211	90.58 308	79.34 226	85.24 349	91.96 293	78.27 290	85.55 198	87.87 327	71.03 218	95.61 300	73.96 296	89.36 205	95.40 172

Patchmtry		82.71 282	80.93 288	88.06 272	90.05 319	76.37 287	84.74 354	91.96 293	72.28 346	81.32 289	87.87 327	71.03 218	95.50 306	68.97 323	80.15 318	92.32 306

YYNet1		79.22 315	77.20 317	85.28 321	88.20 342	72.66 321	85.87 343	90.05 335	74.33 328	62.70 365	87.61 329	66.09 282	92.03 348	66.94 336	72.97 347	91.15 326

MDA-MVSNet_test_wron		79.21 316	77.19 318	85.29 320	88.22 341	72.77 318	85.87 343	90.06 333	74.34 327	62.62 366	87.56 330	66.14 281	91.99 350	66.90 339	73.01 346	91.10 330

Anonymous20240521		80.44 306	79.21 306	84.11 330	85.75 357	67.89 353	92.86 233	93.23 256	75.61 315	75.59 337	87.47 331	50.03 354	94.33 322	71.14 311	81.21 298	90.12 339

TESTMET0.1,1		83.74 277	82.85 276	86.42 309	89.96 321	71.21 337	89.55 303	87.88 349	77.41 297	83.37 264	87.31 332	56.71 334	93.65 334	80.62 228	92.85 164	94.40 218

CL-MVSNet_self_test		81.74 291	80.53 289	85.36 319	85.96 354	72.45 326	90.25 290	93.07 259	81.24 251	79.85 309	87.29 333	70.93 220	92.52 345	66.95 335	69.23 356	91.11 329

tpmvs		83.35 280	82.07 279	87.20 294	91.07 287	71.00 340	88.31 324	91.70 297	78.91 276	80.49 299	87.18 334	69.30 247	97.08 226	68.12 331	83.56 271	93.51 265

dp		81.47 297	80.23 294	85.17 322	89.92 322	65.49 361	86.74 338	90.10 332	76.30 308	81.10 290	87.12 335	62.81 301	95.92 288	68.13 330	79.88 321	94.09 232

test_fmvs3		77.67 322	77.16 319	79.22 342	79.52 370	61.14 368	92.34 248	91.64 300	73.98 331	78.86 315	86.59 336	27.38 374	87.03 367	88.12 117	75.97 342	89.50 342

mvsany_test3		74.95 327	73.26 331	80.02 341	74.61 373	63.16 366	85.53 347	78.42 374	74.16 329	74.89 341	86.46 337	36.02 369	89.09 364	82.39 194	66.91 361	87.82 358

PM-MVS		78.11 320	76.12 324	84.09 331	83.54 364	70.08 346	88.97 316	85.27 358	79.93 264	74.73 342	86.43 338	34.70 370	93.48 335	79.43 245	72.06 350	88.72 351

KD-MVS_self_test		80.20 308	79.24 305	83.07 334	85.64 358	65.29 362	91.01 279	93.93 240	78.71 283	76.32 331	86.40 339	59.20 327	92.93 343	72.59 302	69.35 355	91.00 332

tpm cat1		81.96 287	80.27 293	87.01 297	91.09 286	71.02 339	87.38 334	91.53 304	66.25 359	80.17 301	86.35 340	68.22 260	96.15 280	69.16 322	82.29 285	93.86 244

pmmvs-eth3d		80.97 303	78.72 312	87.74 277	84.99 361	79.97 211	90.11 297	91.65 299	75.36 316	73.51 347	86.03 341	59.45 325	93.96 329	75.17 285	72.21 349	89.29 346

KD-MVS_2432*1600		78.50 318	76.02 325	85.93 313	86.22 352	74.47 302	84.80 352	92.33 276	79.29 271	76.98 327	85.92 342	53.81 348	93.97 327	67.39 333	57.42 372	89.36 343

miper_refine_blended		78.50 318	76.02 325	85.93 313	86.22 352	74.47 302	84.80 352	92.33 276	79.29 271	76.98 327	85.92 342	53.81 348	93.97 327	67.39 333	57.42 372	89.36 343

ADS-MVSNet2		81.66 293	79.71 301	87.50 283	91.35 275	74.19 306	83.33 359	88.48 348	72.90 341	82.24 277	85.77 344	64.98 288	93.20 340	64.57 347	83.74 267	95.12 180

ADS-MVSNet		81.56 295	79.78 299	86.90 301	91.35 275	71.82 330	83.33 359	89.16 345	72.90 341	82.24 277	85.77 344	64.98 288	93.76 331	64.57 347	83.74 267	95.12 180

dmvs_testset		74.57 328	75.81 327	70.86 353	87.72 347	40.47 384	87.05 337	77.90 377	82.75 215	71.15 357	85.47 346	67.98 261	84.12 373	45.26 371	76.98 339	88.00 356

N_pmnet		68.89 334	68.44 336	70.23 354	89.07 330	28.79 388	88.06 325	19.50 389	69.47 355	71.86 354	84.93 347	61.24 313	91.75 352	54.70 366	77.15 336	90.15 338

EGC-MVSNET		61.97 338	56.37 342	78.77 344	89.63 327	73.50 311	89.12 313	82.79 364	0.21 386	1.24 387	84.80 348	39.48 367	90.04 360	44.13 372	75.94 343	72.79 370

APD_test1		69.04 333	66.26 337	77.36 348	80.51 368	62.79 367	85.46 348	83.51 363	54.11 370	59.14 368	84.79 349	23.40 377	89.61 361	55.22 365	70.24 353	79.68 368

ambc				83.06 335	79.99 369	63.51 365	77.47 370	92.86 263		74.34 345	84.45 350	28.74 371	95.06 315	73.06 301	68.89 359	90.61 334

GG-mvs-BLEND				87.94 276	89.73 326	77.91 257	87.80 327	78.23 376		80.58 297	83.86 351	59.88 323	95.33 310	71.20 308	92.22 171	90.60 336

patchmatchnet-post											83.76 352	71.53 212	96.48 262

PatchT		82.68 283	81.27 285	86.89 302	90.09 318	70.94 341	84.06 356	90.15 330	74.91 322	85.63 197	83.57 353	69.37 242	94.87 317	65.19 343	88.50 221	94.84 193

new-patchmatchnet		76.41 325	75.17 328	80.13 340	82.65 367	59.61 370	87.66 331	91.08 313	78.23 292	69.85 359	83.22 354	54.76 342	91.63 354	64.14 349	64.89 365	89.16 348

test_f		71.95 331	70.87 333	75.21 349	74.21 375	59.37 371	85.07 351	85.82 355	65.25 361	70.42 358	83.13 355	23.62 375	82.93 375	78.32 254	71.94 351	83.33 362

PVSNet_0	73.20 20	77.22 323	74.83 329	84.37 327	90.70 305	71.10 338	83.09 361	89.67 342	72.81 343	73.93 346	83.13 355	60.79 317	93.70 333	68.54 325	50.84 375	88.30 355

RPMNet		83.95 274	81.53 283	91.21 161	90.58 308	79.34 226	85.24 349	96.76 73	71.44 349	85.55 198	82.97 357	70.87 221	98.91 76	61.01 357	89.36 205	95.40 172

Patchmatch-RL test		81.67 292	79.96 298	86.81 304	85.42 359	71.23 336	82.17 363	87.50 353	78.47 285	77.19 326	82.50 358	70.81 222	93.48 335	82.66 190	72.89 348	95.71 164

FPMVS		64.63 337	62.55 339	70.88 352	70.80 377	56.71 373	84.42 355	84.42 360	51.78 371	49.57 371	81.61 359	23.49 376	81.48 376	40.61 377	76.25 341	74.46 369

test_vis1_rt		77.96 321	76.46 321	82.48 337	85.89 355	71.74 332	90.25 290	78.89 373	71.03 352	71.30 356	81.35 360	42.49 366	91.05 356	84.55 163	82.37 284	84.65 360

pmmvs3		71.81 332	68.71 335	81.11 339	75.86 372	70.42 344	86.74 338	83.66 362	58.95 367	68.64 362	80.89 361	36.93 368	89.52 362	63.10 352	63.59 366	83.39 361

new_pmnet		72.15 330	70.13 334	78.20 345	82.95 366	65.68 359	83.91 357	82.40 366	62.94 365	64.47 364	79.82 362	42.85 365	86.26 369	57.41 364	74.44 345	82.65 365

UnsupCasMVSNet_bld		76.23 326	73.27 330	85.09 323	83.79 363	72.92 315	85.65 346	93.47 253	71.52 348	68.84 361	79.08 363	49.77 355	93.21 339	66.81 340	60.52 369	89.13 350

testf1		59.54 340	56.11 343	69.85 355	69.28 378	56.61 375	80.37 367	76.55 379	42.58 375	45.68 374	75.61 364	11.26 385	84.18 371	43.20 374	60.44 370	68.75 371

APD_test2		59.54 340	56.11 343	69.85 355	69.28 378	56.61 375	80.37 367	76.55 379	42.58 375	45.68 374	75.61 364	11.26 385	84.18 371	43.20 374	60.44 370	68.75 371

DeepMVS_CX				56.31 362	74.23 374	51.81 380		56.67 387	44.85 373	48.54 373	75.16 366	27.87 373	58.74 383	40.92 376	52.22 374	58.39 376

test_method		50.52 345	48.47 347	56.66 361	52.26 387	18.98 390	41.51 379	81.40 368	10.10 381	44.59 376	75.01 367	28.51 372	68.16 379	53.54 367	49.31 376	82.83 364

JIA-IIPM		81.04 301	78.98 311	87.25 290	88.64 333	73.48 312	81.75 364	89.61 343	73.19 338	82.05 279	73.71 368	66.07 283	95.87 291	71.18 310	84.60 260	92.41 302

LCM-MVSNet		66.00 335	62.16 340	77.51 347	64.51 383	58.29 372	83.87 358	90.90 319	48.17 372	54.69 369	73.31 369	16.83 383	86.75 368	65.47 342	61.67 368	87.48 359

PMMVS2		59.60 339	56.40 341	69.21 357	68.83 380	46.58 382	73.02 374	77.48 378	55.07 369	49.21 372	72.95 370	17.43 382	80.04 377	49.32 370	44.33 377	80.99 367

gg-mvs-nofinetune		81.77 290	79.37 303	88.99 250	90.85 299	77.73 267	86.29 341	79.63 372	74.88 324	83.19 268	69.05 371	60.34 319	96.11 281	75.46 282	94.64 127	93.11 280

MVS-HIRNet		73.70 329	72.20 332	78.18 346	91.81 259	56.42 377	82.94 362	82.58 365	55.24 368	68.88 360	66.48 372	55.32 340	95.13 312	58.12 362	88.42 223	83.01 363

PMVS	47.18 22	52.22 344	48.46 348	63.48 359	45.72 388	46.20 383	73.41 373	78.31 375	41.03 377	30.06 380	65.68 373	6.05 387	83.43 374	30.04 379	65.86 362	60.80 374
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		65.12 336	62.60 338	72.69 351	71.44 376	60.71 369	87.17 335	65.55 382	63.80 364	53.22 370	65.65 374	14.54 384	89.44 363	76.65 271	65.38 363	67.91 373

ANet_high		58.88 342	54.22 346	72.86 350	56.50 386	56.67 374	80.75 366	86.00 354	73.09 340	37.39 378	64.63 375	22.17 378	79.49 378	43.51 373	23.96 380	82.43 366

tmp_tt		35.64 349	39.24 351	24.84 365	14.87 389	23.90 389	62.71 375	51.51 388	6.58 383	36.66 379	62.08 376	44.37 364	30.34 385	52.40 368	22.00 382	20.27 380

MVE	39.65 23	43.39 346	38.59 352	57.77 360	56.52 385	48.77 381	55.38 376	58.64 386	29.33 380	28.96 381	52.65 377	4.68 388	64.62 382	28.11 380	33.07 378	59.93 375
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		57.99 343	54.91 345	67.24 358	88.51 334	65.59 360	52.21 377	90.33 328	43.58 374	42.84 377	51.18 378	20.29 380	85.07 370	34.77 378	70.45 352	51.05 377
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 347	42.29 349	46.03 363	65.58 382	37.41 385	73.51 372	64.62 383	33.99 378	28.47 382	47.87 379	19.90 381	67.91 380	22.23 381	24.45 379	32.77 378

EMVS		42.07 348	41.12 350	44.92 364	63.45 384	35.56 387	73.65 371	63.48 384	33.05 379	26.88 383	45.45 380	21.27 379	67.14 381	19.80 382	23.02 381	32.06 379

X-MVStestdata		88.31 164	86.13 210	94.85 24	98.54 13	86.60 32	96.93 22	97.19 34	90.66 23	92.85 59	23.41 381	85.02 55	99.49 25	91.99 64	98.56 47	98.47 32

test_post											10.29 382	70.57 228	95.91 290

test_post1							88.00 326				9.81 383	69.31 246	95.53 302	76.65 271

testmvs		8.92 352	11.52 355	1.12 368	1.06 390	0.46 392	86.02 342	0.65 391	0.62 384	2.74 385	9.52 384	0.31 391	0.45 387	2.38 384	0.39 384	2.46 383

test123		8.76 353	11.22 356	1.39 367	0.85 391	0.97 391	85.76 345	0.35 392	0.54 385	2.45 386	8.14 385	0.60 390	0.48 386	2.16 385	0.17 385	2.71 382

wuyk23d		21.27 351	20.48 354	23.63 366	68.59 381	36.41 386	49.57 378	6.85 390	9.37 382	7.89 384	4.46 386	4.03 389	31.37 384	17.47 383	16.07 383	3.12 381

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

pcd_1.5k_mvsjas		6.64 355	8.86 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	79.70 112	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

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					98.86 1	85.54 64	98.29 1	97.49 6	89.79 43	96.29 16

MSC_two_6792asdad				96.52 1	97.78 51	90.86 1		96.85 62					99.61 3	96.03 4	99.06 9	99.07 5

No_MVS				96.52 1	97.78 51	90.86 1		96.85 62					99.61 3	96.03 4	99.06 9	99.07 5

eth-test2					0.00 392

eth-test					0.00 392

IU-MVS					98.77 5	86.00 48		96.84 64	81.26 250	97.26 7				95.50 13	99.13 3	99.03 7

save fliter					97.85 46	85.63 63	95.21 101	96.82 67	89.44 50

test_0728_SECOND				95.01 16	98.79 2	86.43 37	97.09 16	97.49 6					99.61 3	95.62 11	99.08 7	98.99 8

GSMVS																96.12 143

test_part2					98.55 12	87.22 17				96.40 15

sam_mvs1												71.70 211				96.12 143

sam_mvs												70.60 224

MTGPA								96.97 49

MTMP							96.16 50	60.64 385

test9_res														91.91 68	98.71 31	98.07 65

agg_prior2														90.54 92	98.68 36	98.27 51

agg_prior					97.38 63	85.92 55		96.72 79		92.16 79			98.97 71

test_prior4						85.96 52	94.11 171

test_prior				93.82 57	97.29 67	84.49 79		96.88 60					98.87 78			98.11 64

旧先验2							93.36 209		71.25 350	94.37 29			97.13 224	86.74 136

新几何2							93.11 223

无先验							93.28 216	96.26 105	73.95 332				99.05 54	80.56 229		96.59 127

原ACMM2							92.94 230

testdata2													98.75 88	78.30 255

segment_acmp												87.16 34

testdata1							92.15 255		87.94 98

test12				94.34 48	97.13 70	86.15 46		96.29 102		91.04 105		85.08 53	99.01 62		98.13 60	97.86 78

plane_prior7					94.70 161	82.74 131

plane_prior6					94.52 170	82.75 129						74.23 177

plane_prior5								96.22 110					98.12 134	88.15 114	89.99 190	94.63 199

plane_prior3						82.75 129			90.26 32	86.91 170

plane_prior2							95.85 67		90.81 16

plane_prior1					94.59 165

plane_prior						82.73 132	95.21 101		89.66 47						89.88 195

n2								0.00 393

nn								0.00 393

door-mid								85.49 356

test11								96.57 90

door								85.33 357

HQP5-MVS						81.56 158

HQP-NCC					94.17 184		94.39 155		88.81 68	85.43 211

ACMP_Plane					94.17 184		94.39 155		88.81 68	85.43 211

BP-MVS														87.11 133

HQP4-MVS										85.43 211			97.96 155			94.51 209

HQP3-MVS								96.04 124							89.77 199

HQP2-MVS												73.83 187

MDTV_nov1_ep13_2view						55.91 379	87.62 332		73.32 337	84.59 230		70.33 231		74.65 291		95.50 169

ACMMP++_ref															87.47 236

ACMMP++															88.01 230

Test By Simon												80.02 107

High-resolution multi-view benchmark