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.

SED-MVS		90.08 2	90.85 2	87.77 25	95.30 2	70.98 62	93.57 7	94.06 10	77.24 49	93.10 1	95.72 8	82.99 1	97.44 5	89.07 11	96.63 4	94.88 13

test_241102_ONE					95.30 2	70.98 62		94.06 10	77.17 52	93.10 1	95.39 11	82.99 1	97.27 10

DVP-MVS++		90.23 1	91.01 1	87.89 23	94.34 27	71.25 56	95.06 1	94.23 3	78.38 32	92.78 4	95.74 6	82.45 3	97.49 3	89.42 6	96.68 2	94.95 9

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 40	82.45 3	96.87 19	83.77 49	96.48 8	94.88 13

PC_three_1452									68.21 233	92.02 12	94.00 42	82.09 5	95.98 50	84.58 39	96.68 2	94.95 9

DPE-MVS		89.48 5	89.98 4	88.01 15	94.80 11	72.69 30	91.59 42	94.10 8	75.90 84	92.29 7	95.66 10	81.67 6	97.38 9	87.44 24	96.34 15	93.95 51
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0728_THIRD									78.38 32	92.12 9	95.78 4	81.46 7	97.40 7	89.42 6	96.57 7	94.67 23

test_241102_TWO								94.06 10	77.24 49	92.78 4	95.72 8	81.26 8	97.44 5	89.07 11	96.58 6	94.26 40

DVP-MVS		89.60 3	90.35 3	87.33 39	95.27 5	71.25 56	93.49 9	92.73 59	77.33 47	92.12 9	95.78 4	80.98 9	97.40 7	89.08 9	96.41 12	93.33 79
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					95.27 5	71.25 56	93.60 6	94.11 6	77.33 47	92.81 3	95.79 3	80.98 9

test_one_0601					95.07 7	71.46 54		94.14 5	78.27 34	92.05 11	95.74 6	80.83 11

DeepPCF-MVS	80.84 1	88.10 12	88.56 12	86.73 49	92.24 68	69.03 97	89.57 85	93.39 30	77.53 44	89.79 18	94.12 36	78.98 12	96.58 34	85.66 28	95.72 24	94.58 26

MSP-MVS		89.51 4	89.91 5	88.30 9	94.28 30	73.46 16	92.90 16	94.11 6	80.27 9	91.35 14	94.16 35	78.35 13	96.77 23	89.59 5	94.22 57	94.67 23
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
APDe-MVS		89.15 6	89.63 6	87.73 27	94.49 18	71.69 51	93.83 4	93.96 13	75.70 88	91.06 16	96.03 1	76.84 14	97.03 16	89.09 8	95.65 27	94.47 30

dcpmvs_2		85.63 51	86.15 43	84.06 117	91.71 75	64.94 188	86.47 181	91.87 95	73.63 130	86.60 34	93.02 63	76.57 15	91.87 213	83.36 51	92.15 74	95.35 2

CNVR-MVS		88.93 9	89.13 9	88.33 7	94.77 12	73.82 8	90.51 60	93.00 43	80.90 6	88.06 26	94.06 39	76.43 16	96.84 20	88.48 18	95.99 18	94.34 36

MCST-MVS		87.37 26	87.25 25	87.73 27	94.53 17	72.46 37	89.82 76	93.82 16	73.07 144	84.86 53	92.89 65	76.22 17	96.33 37	84.89 35	95.13 35	94.40 33

CSCG		86.41 40	86.19 41	87.07 44	92.91 58	72.48 36	90.81 56	93.56 24	73.95 122	83.16 82	91.07 107	75.94 18	95.19 74	79.94 85	94.38 53	93.55 72

HPM-MVS++		89.02 8	89.15 8	88.63 4	95.01 9	76.03 1	92.38 26	92.85 54	80.26 10	87.78 28	94.27 31	75.89 19	96.81 22	87.45 23	96.44 9	93.05 89

TSAR-MVS + MP.		88.02 17	88.11 15	87.72 29	93.68 43	72.13 45	91.41 46	92.35 74	74.62 110	88.90 20	93.85 47	75.75 20	96.00 48	87.80 19	94.63 46	95.04 6
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		88.46 11	88.74 11	87.64 34	92.78 61	71.95 49	92.40 23	94.74 2	75.71 86	89.16 19	95.10 14	75.65 21	96.19 42	87.07 25	96.01 17	94.79 20

9.14			88.26 14		92.84 60		91.52 45	94.75 1	73.93 124	88.57 22	94.67 18	75.57 22	95.79 52	86.77 26	95.76 23

SD-MVS		88.06 14	88.50 13	86.71 50	92.60 66	72.71 28	91.81 41	93.19 35	77.87 35	90.32 17	94.00 42	74.83 23	93.78 135	87.63 21	94.27 56	93.65 66
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
DELS-MVS		85.41 55	85.30 56	85.77 63	88.49 161	67.93 125	85.52 210	93.44 27	78.70 28	83.63 78	89.03 155	74.57 24	95.71 55	80.26 83	94.04 58	93.66 62
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
patch_mono-2		83.65 70	84.54 64	80.99 211	90.06 106	65.83 166	84.21 238	88.74 195	71.60 164	85.01 46	92.44 75	74.51 25	83.50 318	82.15 66	92.15 74	93.64 68

train_agg		86.43 38	86.20 40	87.13 43	93.26 50	72.96 24	88.75 108	91.89 93	68.69 225	85.00 48	93.10 58	74.43 26	95.41 66	84.97 32	95.71 25	93.02 91

test_8					93.13 52	72.57 34	88.68 113	91.84 97	68.69 225	84.87 52	93.10 58	74.43 26	95.16 75

TEST9					93.26 50	72.96 24	88.75 108	91.89 93	68.44 230	85.00 48	93.10 58	74.36 28	95.41 66

SMA-MVS		89.08 7	89.23 7	88.61 5	94.25 31	73.73 9	92.40 23	93.63 21	74.77 106	92.29 7	95.97 2	74.28 29	97.24 11	88.58 16	96.91 1	94.87 15
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
test_prior2							88.85 104		75.41 92	84.91 50	93.54 49	74.28 29		83.31 52	95.86 20

TSAR-MVS + GP.		85.71 50	85.33 54	86.84 46	91.34 78	72.50 35	89.07 97	87.28 225	76.41 71	85.80 38	90.22 125	74.15 31	95.37 71	81.82 68	91.88 77	92.65 102

ZD-MVS					94.38 25	72.22 43		92.67 61	70.98 175	87.75 29	94.07 38	74.01 32	96.70 26	84.66 38	94.84 42

SteuartSystems-ACMMP		88.72 10	88.86 10	88.32 8	92.14 69	72.96 24	93.73 5	93.67 20	80.19 11	88.10 25	94.80 16	73.76 33	97.11 14	87.51 22	95.82 21	94.90 12
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		87.44 22	87.52 22	87.19 41	94.24 32	72.39 38	91.86 40	92.83 55	73.01 146	88.58 21	94.52 20	73.36 34	96.49 35	84.26 43	95.01 36	92.70 98
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
casdiffmvs_mvg		85.99 43	86.09 45	85.70 65	87.65 192	67.22 142	88.69 112	93.04 38	79.64 17	85.33 43	92.54 74	73.30 35	94.50 106	83.49 50	91.14 88	95.37 1
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
canonicalmvs		85.91 46	85.87 48	86.04 59	89.84 111	69.44 94	90.45 65	93.00 43	76.70 68	88.01 27	91.23 100	73.28 36	93.91 130	81.50 70	88.80 115	94.77 21

segment_acmp												73.08 37

DPM-MVS		84.93 61	84.29 66	86.84 46	90.20 99	73.04 22	87.12 160	93.04 38	69.80 198	82.85 86	91.22 101	73.06 38	96.02 46	76.72 117	94.63 46	91.46 139

NCCC		88.06 14	88.01 18	88.24 10	94.41 22	73.62 10	91.22 51	92.83 55	81.50 4	85.79 39	93.47 52	73.02 39	97.00 17	84.90 33	94.94 38	94.10 44

test_fmvsmconf_n		85.92 45	86.04 46	85.57 67	85.03 242	69.51 89	89.62 84	90.58 130	73.42 137	87.75 29	94.02 40	72.85 40	93.24 159	90.37 2	90.75 92	93.96 50

nrg030		83.88 66	83.53 69	84.96 81	86.77 216	69.28 96	90.46 64	92.67 61	74.79 105	82.95 83	91.33 99	72.70 41	93.09 171	80.79 78	79.28 235	92.50 107

CDPH-MVS		85.76 49	85.29 57	87.17 42	93.49 47	71.08 60	88.58 116	92.42 72	68.32 232	84.61 58	93.48 50	72.32 42	96.15 44	79.00 89	95.43 30	94.28 39

MP-MVS		87.71 19	87.64 21	87.93 20	94.36 26	73.88 6	92.71 22	92.65 64	77.57 40	83.84 73	94.40 29	72.24 43	96.28 39	85.65 29	95.30 34	93.62 69
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffmvs		85.11 59	85.14 58	85.01 79	87.20 208	65.77 170	87.75 144	92.83 55	77.84 36	84.36 64	92.38 76	72.15 44	93.93 129	81.27 72	90.48 94	95.33 3
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepC-MVS	79.81 2	87.08 31	86.88 33	87.69 32	91.16 80	72.32 42	90.31 67	93.94 14	77.12 54	82.82 87	94.23 33	72.13 45	97.09 15	84.83 36	95.37 31	93.65 66
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline		84.93 61	84.98 59	84.80 89	87.30 206	65.39 179	87.30 156	92.88 52	77.62 38	84.04 70	92.26 78	71.81 46	93.96 123	81.31 71	90.30 97	95.03 7

ZNCC-MVS		87.94 18	87.85 19	88.20 11	94.39 24	73.33 18	93.03 14	93.81 17	76.81 62	85.24 44	94.32 30	71.76 47	96.93 18	85.53 30	95.79 22	94.32 37

test12				86.80 48	92.63 64	70.70 71		91.79 99		82.71 89		71.67 48	96.16 43		94.50 49	93.54 73

UniMVSNet_NR-MVSNet		81.88 97	81.54 97	82.92 162	88.46 163	63.46 219	87.13 159	92.37 73	80.19 11	78.38 145	89.14 151	71.66 49	93.05 173	70.05 177	76.46 265	92.25 116

CS-MVS		86.69 34	86.95 30	85.90 62	90.76 90	67.57 133	92.83 17	93.30 32	79.67 16	84.57 60	92.27 77	71.47 50	95.02 85	84.24 45	93.46 62	95.13 5

DeepC-MVS_fast	79.65 3	86.91 32	86.62 35	87.76 26	93.52 46	72.37 40	91.26 47	93.04 38	76.62 69	84.22 65	93.36 54	71.44 51	96.76 24	80.82 76	95.33 33	94.16 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsm_n_1920		85.29 57	85.34 53	85.13 76	86.12 223	69.93 82	88.65 114	90.78 126	69.97 194	88.27 23	93.98 45	71.39 52	91.54 221	88.49 17	90.45 95	93.91 52

MVS_111021_HR		85.14 58	84.75 62	86.32 54	91.65 76	72.70 29	85.98 193	90.33 140	76.11 80	82.08 93	91.61 91	71.36 53	94.17 119	81.02 73	92.58 69	92.08 122

ACMMP_NAP		88.05 16	88.08 16	87.94 18	93.70 41	73.05 21	90.86 55	93.59 23	76.27 78	88.14 24	95.09 15	71.06 54	96.67 28	87.67 20	96.37 14	94.09 45

MP-MVS-pluss		87.67 20	87.72 20	87.54 35	93.64 44	72.04 47	89.80 78	93.50 25	75.17 99	86.34 35	95.29 12	70.86 55	96.00 48	88.78 14	96.04 16	94.58 26
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		87.58 21	87.47 23	87.94 18	94.58 16	73.54 14	93.04 12	93.24 33	76.78 64	84.91 50	94.44 27	70.78 56	96.61 31	84.53 40	94.89 40	93.66 62

EI-MVSNet-Vis-set		84.19 64	83.81 68	85.31 70	88.18 171	67.85 126	87.66 146	89.73 157	80.05 13	82.95 83	89.59 139	70.74 57	94.82 94	80.66 80	84.72 163	93.28 81

GST-MVS		87.42 24	87.26 24	87.89 23	94.12 36	72.97 23	92.39 25	93.43 28	76.89 60	84.68 54	93.99 44	70.67 58	96.82 21	84.18 47	95.01 36	93.90 54

CS-MVS-test		86.29 41	86.48 36	85.71 64	91.02 83	67.21 143	92.36 28	93.78 18	78.97 27	83.51 79	91.20 102	70.65 59	95.15 76	81.96 67	94.89 40	94.77 21

CANet		86.45 37	86.10 44	87.51 36	90.09 101	70.94 66	89.70 82	92.59 66	81.78 3	81.32 103	91.43 97	70.34 60	97.23 12	84.26 43	93.36 63	94.37 34

alignmvs		85.48 52	85.32 55	85.96 61	89.51 119	69.47 91	89.74 80	92.47 68	76.17 79	87.73 31	91.46 96	70.32 61	93.78 135	81.51 69	88.95 112	94.63 25

EI-MVSNet-UG-set		83.81 67	83.38 71	85.09 77	87.87 181	67.53 134	87.44 152	89.66 158	79.74 15	82.23 92	89.41 148	70.24 62	94.74 97	79.95 84	83.92 173	92.99 93

MVS_Test		83.15 79	83.06 75	83.41 140	86.86 212	63.21 225	86.11 191	92.00 87	74.31 115	82.87 85	89.44 147	70.03 63	93.21 160	77.39 107	88.50 121	93.81 58

FC-MVSNet-test		81.52 107	82.02 91	80.03 231	88.42 165	55.97 316	87.95 137	93.42 29	77.10 55	77.38 168	90.98 113	69.96 64	91.79 214	68.46 196	84.50 165	92.33 112

MVS_0304		88.08 13	88.08 16	88.08 13	89.67 113	72.04 47	92.26 32	89.26 170	84.19 1	85.01 46	95.18 13	69.93 65	97.20 13	91.63 1	95.60 28	94.99 8

FIs		82.07 94	82.42 82	81.04 210	88.80 150	58.34 279	88.26 126	93.49 26	76.93 59	78.47 144	91.04 108	69.92 66	92.34 196	69.87 181	84.97 160	92.44 111

UniMVSNet (Re)		81.60 106	81.11 102	83.09 153	88.38 166	64.41 200	87.60 147	93.02 42	78.42 31	78.56 141	88.16 181	69.78 67	93.26 158	69.58 184	76.49 264	91.60 131

HPM-MVS		87.11 29	86.98 29	87.50 37	93.88 39	72.16 44	92.19 33	93.33 31	76.07 81	83.81 74	93.95 46	69.77 68	96.01 47	85.15 31	94.66 45	94.32 37
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
Effi-MVS+		83.62 72	83.08 74	85.24 72	88.38 166	67.45 135	88.89 102	89.15 176	75.50 91	82.27 91	88.28 177	69.61 69	94.45 108	77.81 102	87.84 125	93.84 57

PHI-MVS		86.43 38	86.17 42	87.24 40	90.88 87	70.96 64	92.27 31	94.07 9	72.45 149	85.22 45	91.90 83	69.47 70	96.42 36	83.28 53	95.94 19	94.35 35

UA-Net		85.08 60	84.96 60	85.45 68	92.07 70	68.07 123	89.78 79	90.86 125	82.48 2	84.60 59	93.20 57	69.35 71	95.22 73	71.39 165	90.88 91	93.07 88

ETV-MVS		84.90 63	84.67 63	85.59 66	89.39 124	68.66 112	88.74 110	92.64 65	79.97 14	84.10 68	85.71 245	69.32 72	95.38 68	80.82 76	91.37 85	92.72 97

旧先验1					91.96 71	65.79 169		86.37 239			93.08 62	69.31 73			92.74 67	88.74 241

region2R		87.42 24	87.20 27	88.09 12	94.63 14	73.55 12	93.03 14	93.12 37	76.73 67	84.45 61	94.52 20	69.09 74	96.70 26	84.37 42	94.83 43	94.03 48

EIA-MVS		83.31 78	82.80 80	84.82 87	89.59 115	65.59 172	88.21 127	92.68 60	74.66 108	78.96 130	86.42 232	69.06 75	95.26 72	75.54 129	90.09 101	93.62 69

EPP-MVSNet		83.40 76	83.02 76	84.57 93	90.13 100	64.47 198	92.32 29	90.73 127	74.45 114	79.35 126	91.10 105	69.05 76	95.12 77	72.78 154	87.22 133	94.13 43

EC-MVSNet		86.01 42	86.38 37	84.91 85	89.31 130	66.27 157	92.32 29	93.63 21	79.37 19	84.17 67	91.88 84	69.04 77	95.43 64	83.93 48	93.77 60	93.01 92

ACMMPR		87.44 22	87.23 26	88.08 13	94.64 13	73.59 11	93.04 12	93.20 34	76.78 64	84.66 57	94.52 20	68.81 78	96.65 29	84.53 40	94.90 39	94.00 49

test_fmvsmvis_n_1920		84.02 65	83.87 67	84.49 98	84.12 254	69.37 95	88.15 131	87.96 209	70.01 192	83.95 71	93.23 56	68.80 79	91.51 224	88.61 15	89.96 104	92.57 103

mvs_anonymous		79.42 157	79.11 145	80.34 225	84.45 249	57.97 285	82.59 264	87.62 218	67.40 240	76.17 202	88.56 170	68.47 80	89.59 259	70.65 172	86.05 151	93.47 75

MTAPA		87.23 27	87.00 28	87.90 21	94.18 35	74.25 5	86.58 178	92.02 85	79.45 18	85.88 37	94.80 16	68.07 81	96.21 41	86.69 27	95.34 32	93.23 82

CP-MVS		87.11 29	86.92 31	87.68 33	94.20 34	73.86 7	93.98 3	92.82 58	76.62 69	83.68 75	94.46 24	67.93 82	95.95 51	84.20 46	94.39 52	93.23 82

PAPM_NR		83.02 83	82.41 83	84.82 87	92.47 67	66.37 155	87.93 139	91.80 98	73.82 126	77.32 170	90.66 116	67.90 83	94.90 90	70.37 174	89.48 109	93.19 85

PGM-MVS		86.68 35	86.27 39	87.90 21	94.22 33	73.38 17	90.22 69	93.04 38	75.53 90	83.86 72	94.42 28	67.87 84	96.64 30	82.70 63	94.57 48	93.66 62

PAPR		81.66 105	80.89 107	83.99 124	90.27 97	64.00 206	86.76 174	91.77 101	68.84 223	77.13 179	89.50 140	67.63 85	94.88 92	67.55 202	88.52 120	93.09 87

Fast-Effi-MVS+		80.81 120	79.92 123	83.47 136	88.85 145	64.51 195	85.53 208	89.39 164	70.79 177	78.49 143	85.06 263	67.54 86	93.58 143	67.03 210	86.58 142	92.32 113

XVS		87.18 28	86.91 32	88.00 16	94.42 20	73.33 18	92.78 18	92.99 45	79.14 20	83.67 76	94.17 34	67.45 87	96.60 32	83.06 54	94.50 49	94.07 46

X-MVStestdata		80.37 136	77.83 173	88.00 16	94.42 20	73.33 18	92.78 18	92.99 45	79.14 20	83.67 76	12.47 385	67.45 87	96.60 32	83.06 54	94.50 49	94.07 46

SR-MVS		86.73 33	86.67 34	86.91 45	94.11 37	72.11 46	92.37 27	92.56 67	74.50 111	86.84 33	94.65 19	67.31 89	95.77 53	84.80 37	92.85 66	92.84 96

NR-MVSNet		80.23 139	79.38 135	82.78 171	87.80 185	63.34 222	86.31 185	91.09 119	79.01 25	72.17 260	89.07 153	67.20 90	92.81 182	66.08 216	75.65 276	92.20 118

MSLP-MVS++		85.43 54	85.76 49	84.45 100	91.93 72	70.24 75	90.71 57	92.86 53	77.46 46	84.22 65	92.81 69	67.16 91	92.94 177	80.36 81	94.35 54	90.16 184

MG-MVS		83.41 75	83.45 70	83.28 143	92.74 62	62.28 239	88.17 129	89.50 161	75.22 95	81.49 102	92.74 73	66.75 92	95.11 79	72.85 153	91.58 82	92.45 110

EI-MVSNet		80.52 132	79.98 122	82.12 181	84.28 250	63.19 227	86.41 182	88.95 186	74.18 119	78.69 136	87.54 197	66.62 93	92.43 190	72.57 157	80.57 219	90.74 163

IterMVS-LS		80.06 142	79.38 135	82.11 182	85.89 225	63.20 226	86.79 171	89.34 165	74.19 118	75.45 214	86.72 217	66.62 93	92.39 192	72.58 156	76.86 259	90.75 162
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		78.59 179	77.76 178	81.08 209	82.66 288	61.56 248	83.65 246	89.15 176	68.87 222	75.55 210	83.79 283	66.49 95	92.03 205	73.25 149	76.39 267	89.64 211

mPP-MVS		86.67 36	86.32 38	87.72 29	94.41 22	73.55 12	92.74 20	92.22 80	76.87 61	82.81 88	94.25 32	66.44 96	96.24 40	82.88 58	94.28 55	93.38 76

c3_l		78.75 173	77.91 170	81.26 202	82.89 283	61.56 248	84.09 241	89.13 178	69.97 194	75.56 209	84.29 275	66.36 97	92.09 204	73.47 146	75.48 280	90.12 187

GeoE		81.71 101	81.01 105	83.80 130	89.51 119	64.45 199	88.97 99	88.73 196	71.27 169	78.63 139	89.76 133	66.32 98	93.20 163	69.89 180	86.02 152	93.74 60

WR-MVS_H		78.51 180	78.49 156	78.56 256	88.02 178	56.38 311	88.43 118	92.67 61	77.14 53	73.89 242	87.55 196	66.25 99	89.24 265	58.92 274	73.55 306	90.06 194

PCF-MVS	73.52 7	80.38 134	78.84 150	85.01 79	87.71 189	68.99 99	83.65 246	91.46 111	63.00 287	77.77 162	90.28 122	66.10 100	95.09 83	61.40 254	88.22 124	90.94 156
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EPNet		83.72 69	82.92 78	86.14 58	84.22 252	69.48 90	91.05 54	85.27 252	81.30 5	76.83 181	91.65 88	66.09 101	95.56 57	76.00 123	93.85 59	93.38 76
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM1				84.35 104	93.01 57	68.79 102		92.44 69	63.96 281	81.09 108	91.57 92	66.06 102	95.45 62	67.19 207	94.82 44	88.81 238

PVSNet_BlendedMVS		80.60 129	80.02 121	82.36 180	88.85 145	65.40 177	86.16 190	92.00 87	69.34 207	78.11 154	86.09 240	66.02 103	94.27 112	71.52 162	82.06 200	87.39 265

PVSNet_Blended		80.98 115	80.34 116	82.90 163	88.85 145	65.40 177	84.43 233	92.00 87	67.62 237	78.11 154	85.05 264	66.02 103	94.27 112	71.52 162	89.50 108	89.01 228

diffmvs		82.10 92	81.88 94	82.76 173	83.00 280	63.78 211	83.68 245	89.76 155	72.94 147	82.02 94	89.85 131	65.96 105	90.79 243	82.38 65	87.30 132	93.71 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
APD-MVS_3200maxsize		85.97 44	85.88 47	86.22 56	92.69 63	69.53 88	91.93 37	92.99 45	73.54 134	85.94 36	94.51 23	65.80 106	95.61 56	83.04 56	92.51 70	93.53 74

miper_enhance_ethall		77.87 198	76.86 197	80.92 214	81.65 302	61.38 250	82.68 263	88.98 183	65.52 261	75.47 211	82.30 302	65.76 107	92.00 207	72.95 152	76.39 267	89.39 216

PVSNet_Blended_VisFu		82.62 87	81.83 95	84.96 81	90.80 89	69.76 86	88.74 110	91.70 102	69.39 205	78.96 130	88.46 172	65.47 108	94.87 93	74.42 136	88.57 118	90.24 182

API-MVS		81.99 96	81.23 100	84.26 108	90.94 85	70.18 81	91.10 52	89.32 166	71.51 166	78.66 138	88.28 177	65.26 109	95.10 82	64.74 227	91.23 87	87.51 263

TranMVSNet+NR-MVSNet		80.84 118	80.31 117	82.42 178	87.85 182	62.33 237	87.74 145	91.33 112	80.55 8	77.99 158	89.86 130	65.23 110	92.62 183	67.05 209	75.24 290	92.30 114

IS-MVSNet		83.15 79	82.81 79	84.18 110	89.94 109	63.30 223	91.59 42	88.46 201	79.04 24	79.49 124	92.16 79	65.10 111	94.28 111	67.71 200	91.86 80	94.95 9

DU-MVS		81.12 114	80.52 113	82.90 163	87.80 185	63.46 219	87.02 163	91.87 95	79.01 25	78.38 145	89.07 153	65.02 112	93.05 173	70.05 177	76.46 265	92.20 118

Baseline_NR-MVSNet		78.15 189	78.33 162	77.61 271	85.79 226	56.21 314	86.78 172	85.76 248	73.60 132	77.93 159	87.57 194	65.02 112	88.99 269	67.14 208	75.33 287	87.63 259

SR-MVS-dyc-post		85.77 48	85.61 50	86.23 55	93.06 55	70.63 72	91.88 38	92.27 76	73.53 135	85.69 40	94.45 25	65.00 114	95.56 57	82.75 59	91.87 78	92.50 107

VNet		82.21 91	82.41 83	81.62 191	90.82 88	60.93 253	84.47 229	89.78 154	76.36 76	84.07 69	91.88 84	64.71 115	90.26 249	70.68 171	88.89 113	93.66 62

Test By Simon												64.33 116

ACMMP		85.89 47	85.39 52	87.38 38	93.59 45	72.63 32	92.74 20	93.18 36	76.78 64	80.73 112	93.82 48	64.33 116	96.29 38	82.67 64	90.69 93	93.23 82
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
DP-MVS Recon		83.11 82	82.09 89	86.15 57	94.44 19	70.92 67	88.79 106	92.20 81	70.53 183	79.17 128	91.03 110	64.12 118	96.03 45	68.39 197	90.14 100	91.50 136

CLD-MVS		82.31 90	81.65 96	84.29 107	88.47 162	67.73 129	85.81 201	92.35 74	75.78 85	78.33 147	86.58 227	64.01 119	94.35 109	76.05 122	87.48 130	90.79 159
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
RE-MVS-def			85.48 51		93.06 55	70.63 72	91.88 38	92.27 76	73.53 135	85.69 40	94.45 25	63.87 120		82.75 59	91.87 78	92.50 107

MVS		78.19 188	76.99 195	81.78 188	85.66 228	66.99 145	84.66 223	90.47 134	55.08 346	72.02 262	85.27 256	63.83 121	94.11 121	66.10 215	89.80 106	84.24 319

WR-MVS		79.49 153	79.22 142	80.27 227	88.79 151	58.35 278	85.06 215	88.61 199	78.56 29	77.65 163	88.34 175	63.81 122	90.66 246	64.98 225	77.22 254	91.80 129

VPA-MVSNet		80.60 129	80.55 112	80.76 217	88.07 176	60.80 256	86.86 168	91.58 105	75.67 89	80.24 116	89.45 146	63.34 123	90.25 250	70.51 173	79.22 236	91.23 144

新几何1				83.42 138	93.13 52	70.71 70		85.48 251	57.43 336	81.80 98	91.98 81	63.28 124	92.27 198	64.60 228	92.99 64	87.27 269

HY-MVS	69.67 12	77.95 195	77.15 191	80.36 224	87.57 198	60.21 266	83.37 253	87.78 216	66.11 252	75.37 217	87.06 212	63.27 125	90.48 248	61.38 255	82.43 197	90.40 176

XXY-MVS		75.41 240	75.56 219	74.96 295	83.59 264	57.82 289	80.59 285	83.87 273	66.54 249	74.93 232	88.31 176	63.24 126	80.09 333	62.16 246	76.85 260	86.97 278

ab-mvs		79.51 152	78.97 148	81.14 207	88.46 163	60.91 254	83.84 243	89.24 172	70.36 185	79.03 129	88.87 160	63.23 127	90.21 251	65.12 223	82.57 196	92.28 115

xiu_mvs_v2_base		81.69 102	81.05 103	83.60 133	89.15 137	68.03 124	84.46 231	90.02 148	70.67 180	81.30 106	86.53 230	63.17 128	94.19 118	75.60 128	88.54 119	88.57 245

pcd_1.5k_mvsjas		5.26 359	7.02 362	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	63.15 129	0.00 392	0.00 390	0.00 390	0.00 388

PS-MVSNAJss		82.07 94	81.31 98	84.34 105	86.51 219	67.27 140	89.27 89	91.51 107	71.75 158	79.37 125	90.22 125	63.15 129	94.27 112	77.69 103	82.36 198	91.49 137

PS-MVSNAJ		81.69 102	81.02 104	83.70 132	89.51 119	68.21 121	84.28 237	90.09 147	70.79 177	81.26 107	85.62 250	63.15 129	94.29 110	75.62 127	88.87 114	88.59 244

WTY-MVS		75.65 235	75.68 217	75.57 289	86.40 220	56.82 302	77.92 317	82.40 292	65.10 263	76.18 200	87.72 189	63.13 132	80.90 330	60.31 262	81.96 201	89.00 230

TransMVSNet (Re)		75.39 241	74.56 233	77.86 265	85.50 232	57.10 299	86.78 172	86.09 244	72.17 155	71.53 266	87.34 200	63.01 133	89.31 264	56.84 295	61.83 351	87.17 271

v8		79.97 146	79.02 147	82.80 168	84.09 255	64.50 197	87.96 136	90.29 143	74.13 121	75.24 224	86.81 214	62.88 134	93.89 132	74.39 137	75.40 285	90.00 196

HPM-MVS_fast		85.35 56	84.95 61	86.57 52	93.69 42	70.58 74	92.15 35	91.62 103	73.89 125	82.67 90	94.09 37	62.60 135	95.54 59	80.93 74	92.93 65	93.57 71

PAPM		77.68 204	76.40 210	81.51 194	87.29 207	61.85 244	83.78 244	89.59 159	64.74 268	71.23 268	88.70 163	62.59 136	93.66 142	52.66 314	87.03 136	89.01 228

1112_ss		77.40 209	76.43 209	80.32 226	89.11 142	60.41 263	83.65 246	87.72 217	62.13 299	73.05 250	86.72 217	62.58 137	89.97 253	62.11 248	80.80 215	90.59 169

LCM-MVSNet-Re		77.05 214	76.94 196	77.36 274	87.20 208	51.60 348	80.06 292	80.46 311	75.20 96	67.69 303	86.72 217	62.48 138	88.98 270	63.44 233	89.25 111	91.51 134

v148		78.72 175	77.80 175	81.47 195	82.73 286	61.96 243	86.30 186	88.08 206	73.26 140	76.18 200	85.47 253	62.46 139	92.36 194	71.92 161	73.82 304	90.09 190

baseline1		76.98 216	76.75 203	77.66 269	88.13 172	55.66 319	85.12 214	81.89 296	73.04 145	76.79 182	88.90 158	62.43 140	87.78 287	63.30 235	71.18 323	89.55 214

MAR-MVS		81.84 98	80.70 109	85.27 71	91.32 79	71.53 53	89.82 76	90.92 121	69.77 199	78.50 142	86.21 236	62.36 141	94.52 105	65.36 221	92.05 76	89.77 208
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
MVS_111021_LR		82.61 88	82.11 88	84.11 111	88.82 148	71.58 52	85.15 213	86.16 242	74.69 107	80.47 114	91.04 108	62.29 142	90.55 247	80.33 82	90.08 102	90.20 183

TAMVS		78.89 172	77.51 185	83.03 157	87.80 185	67.79 128	84.72 222	85.05 255	67.63 236	76.75 184	87.70 190	62.25 143	90.82 242	58.53 279	87.13 134	90.49 172

CP-MVSNet		78.22 185	78.34 161	77.84 266	87.83 184	54.54 329	87.94 138	91.17 116	77.65 37	73.48 245	88.49 171	62.24 144	88.43 279	62.19 245	74.07 299	90.55 170

OMC-MVS		82.69 86	81.97 93	84.85 86	88.75 153	67.42 136	87.98 135	90.87 124	74.92 102	79.72 121	91.65 88	62.19 145	93.96 123	75.26 131	86.42 145	93.16 86

cl____		77.72 201	76.76 201	80.58 220	82.49 292	60.48 261	83.09 258	87.87 212	69.22 210	74.38 239	85.22 259	62.10 146	91.53 222	71.09 167	75.41 284	89.73 210

DIV-MVS_self_test		77.72 201	76.76 201	80.58 220	82.48 293	60.48 261	83.09 258	87.86 213	69.22 210	74.38 239	85.24 257	62.10 146	91.53 222	71.09 167	75.40 285	89.74 209

testdata				79.97 232	90.90 86	64.21 203		84.71 258	59.27 320	85.40 42	92.91 64	62.02 148	89.08 268	68.95 190	91.37 85	86.63 286

eth_miper_zixun_eth		77.92 196	76.69 204	81.61 193	83.00 280	61.98 242	83.15 256	89.20 174	69.52 204	74.86 233	84.35 274	61.76 149	92.56 186	71.50 164	72.89 312	90.28 181

MVSFormer		82.85 85	82.05 90	85.24 72	87.35 200	70.21 76	90.50 61	90.38 136	68.55 227	81.32 103	89.47 142	61.68 150	93.46 152	78.98 90	90.26 98	92.05 123

lupinMVS		81.39 110	80.27 119	84.76 90	87.35 200	70.21 76	85.55 206	86.41 237	62.85 290	81.32 103	88.61 167	61.68 150	92.24 200	78.41 97	90.26 98	91.83 127

cdsmvs_eth3d_5k		19.96 353	26.61 355	0.00 373	0.00 396	0.00 397	0.00 384	89.26 170	0.00 391	0.00 392	88.61 167	61.62 152	0.00 392	0.00 390	0.00 390	0.00 388

h-mvs33		83.15 79	82.19 87	86.02 60	90.56 92	70.85 69	88.15 131	89.16 175	76.02 82	84.67 55	91.39 98	61.54 153	95.50 60	82.71 61	75.48 280	91.72 130

hse-mvs2		81.72 100	80.94 106	84.07 116	88.72 154	67.68 131	85.87 197	87.26 226	76.02 82	84.67 55	88.22 180	61.54 153	93.48 150	82.71 61	73.44 308	91.06 150

CDS-MVSNet		79.07 167	77.70 180	83.17 150	87.60 194	68.23 120	84.40 235	86.20 241	67.49 239	76.36 195	86.54 229	61.54 153	90.79 243	61.86 250	87.33 131	90.49 172
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v10		79.74 148	78.67 152	82.97 161	84.06 256	64.95 187	87.88 142	90.62 129	73.11 143	75.11 227	86.56 228	61.46 156	94.05 122	73.68 142	75.55 278	89.90 202

v1144		80.03 143	79.03 146	83.01 158	83.78 261	64.51 195	87.11 161	90.57 132	71.96 157	78.08 156	86.20 237	61.41 157	93.94 126	74.93 132	77.23 253	90.60 168

cl22		78.07 191	77.01 193	81.23 203	82.37 295	61.83 245	83.55 250	87.98 208	68.96 221	75.06 229	83.87 279	61.40 158	91.88 212	73.53 144	76.39 267	89.98 199

BH-w/o		78.21 186	77.33 189	80.84 215	88.81 149	65.13 184	84.87 219	87.85 214	69.75 200	74.52 237	84.74 268	61.34 159	93.11 170	58.24 282	85.84 155	84.27 318

Test_1112_low_res		76.40 226	75.44 221	79.27 246	89.28 132	58.09 281	81.69 272	87.07 229	59.53 318	72.48 256	86.67 222	61.30 160	89.33 263	60.81 260	80.15 224	90.41 175

Vis-MVSNet (Re-imp)		78.36 183	78.45 157	78.07 264	88.64 157	51.78 347	86.70 175	79.63 320	74.14 120	75.11 227	90.83 114	61.29 161	89.75 256	58.10 283	91.60 81	92.69 100

PEN-MVS		77.73 200	77.69 181	77.84 266	87.07 211	53.91 334	87.91 140	91.18 115	77.56 42	73.14 249	88.82 161	61.23 162	89.17 266	59.95 264	72.37 314	90.43 174

pm-mvs1		77.25 213	76.68 205	78.93 250	84.22 252	58.62 277	86.41 182	88.36 202	71.37 168	73.31 246	88.01 187	61.22 163	89.15 267	64.24 229	73.01 311	89.03 227

BH-untuned		79.47 154	78.60 154	82.05 183	89.19 136	65.91 164	86.07 192	88.52 200	72.18 154	75.42 215	87.69 191	61.15 164	93.54 147	60.38 261	86.83 139	86.70 284

v2v482		80.23 139	79.29 139	83.05 156	83.62 263	64.14 204	87.04 162	89.97 150	73.61 131	78.18 153	87.22 205	61.10 165	93.82 133	76.11 120	76.78 262	91.18 145

jason		81.39 110	80.29 118	84.70 91	86.63 218	69.90 84	85.95 194	86.77 233	63.24 283	81.07 109	89.47 142	61.08 166	92.15 202	78.33 98	90.07 103	92.05 123
jason: jason.
Vis-MVSNet		83.46 74	82.80 80	85.43 69	90.25 98	68.74 106	90.30 68	90.13 146	76.33 77	80.87 111	92.89 65	61.00 167	94.20 117	72.45 159	90.97 89	93.35 78
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAPA-MVS	73.13 9	79.15 164	77.94 169	82.79 170	89.59 115	62.99 232	88.16 130	91.51 107	65.77 257	77.14 178	91.09 106	60.91 168	93.21 160	50.26 328	87.05 135	92.17 120
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PS-CasMVS		78.01 194	78.09 166	77.77 268	87.71 189	54.39 331	88.02 134	91.22 113	77.50 45	73.26 247	88.64 166	60.73 169	88.41 280	61.88 249	73.88 303	90.53 171

OPM-MVS		83.50 73	82.95 77	85.14 74	88.79 151	70.95 65	89.13 96	91.52 106	77.55 43	80.96 110	91.75 86	60.71 170	94.50 106	79.67 86	86.51 144	89.97 200
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XVG-OURS-SEG-HR		80.81 120	79.76 127	83.96 126	85.60 230	68.78 103	83.54 251	90.50 133	70.66 181	76.71 185	91.66 87	60.69 171	91.26 230	76.94 111	81.58 206	91.83 127

v144192		79.47 154	78.37 160	82.78 171	83.35 268	63.96 207	86.96 164	90.36 139	69.99 193	77.50 165	85.67 248	60.66 172	93.77 137	74.27 138	76.58 263	90.62 166

V42		79.38 160	78.24 164	82.83 165	81.10 313	65.50 174	85.55 206	89.82 153	71.57 165	78.21 151	86.12 239	60.66 172	93.18 166	75.64 126	75.46 282	89.81 207

SDMVSNet		80.38 134	80.18 120	80.99 211	89.03 143	64.94 188	80.45 288	89.40 163	75.19 97	76.61 189	89.98 128	60.61 174	87.69 288	76.83 114	83.55 181	90.33 178

CPTT-MVS		83.73 68	83.33 72	84.92 84	93.28 49	70.86 68	92.09 36	90.38 136	68.75 224	79.57 123	92.83 67	60.60 175	93.04 175	80.92 75	91.56 83	90.86 158

DTE-MVSNet		76.99 215	76.80 199	77.54 273	86.24 221	53.06 342	87.52 149	90.66 128	77.08 56	72.50 255	88.67 165	60.48 176	89.52 260	57.33 290	70.74 325	90.05 195

HQP_MVS		83.64 71	83.14 73	85.14 74	90.08 102	68.71 108	91.25 49	92.44 69	79.12 22	78.92 132	91.00 111	60.42 177	95.38 68	78.71 93	86.32 146	91.33 140

plane_prior6					89.84 111	68.70 110						60.42 177

3Dnovator+	77.84 4	85.48 52	84.47 65	88.51 6	91.08 81	73.49 15	93.18 11	93.78 18	80.79 7	76.66 186	93.37 53	60.40 179	96.75 25	77.20 108	93.73 61	95.29 4

HQP2-MVS												60.17 180

HQP-MVS		82.61 88	82.02 91	84.37 102	89.33 127	66.98 146	89.17 91	92.19 82	76.41 71	77.23 173	90.23 124	60.17 180	95.11 79	77.47 105	85.99 153	91.03 152

VPNet		78.69 176	78.66 153	78.76 252	88.31 168	55.72 318	84.45 232	86.63 235	76.79 63	78.26 149	90.55 119	59.30 182	89.70 258	66.63 211	77.05 256	90.88 157

v1192		79.59 151	78.43 159	83.07 155	83.55 265	64.52 194	86.93 166	90.58 130	70.83 176	77.78 161	85.90 241	59.15 183	93.94 126	73.96 141	77.19 255	90.76 161

test222					91.50 77	68.26 119	84.16 239	83.20 285	54.63 347	79.74 120	91.63 90	58.97 184			91.42 84	86.77 282

CHOSEN 1792x2688		77.63 205	75.69 216	83.44 137	89.98 108	68.58 114	78.70 309	87.50 221	56.38 341	75.80 207	86.84 213	58.67 185	91.40 227	61.58 253	85.75 157	90.34 177

3Dnovator	76.31 5	83.38 77	82.31 86	86.59 51	87.94 180	72.94 27	90.64 58	92.14 84	77.21 51	75.47 211	92.83 67	58.56 186	94.72 98	73.24 150	92.71 68	92.13 121

v1921920		79.22 162	78.03 167	82.80 168	83.30 270	63.94 208	86.80 170	90.33 140	69.91 196	77.48 166	85.53 251	58.44 187	93.75 139	73.60 143	76.85 260	90.71 164

FA-MVS(test-final)		80.96 116	79.91 124	84.10 112	88.30 169	65.01 186	84.55 228	90.01 149	73.25 141	79.61 122	87.57 194	58.35 188	94.72 98	71.29 166	86.25 148	92.56 104

114514_t		80.68 126	79.51 132	84.20 109	94.09 38	67.27 140	89.64 83	91.11 118	58.75 326	74.08 241	90.72 115	58.10 189	95.04 84	69.70 182	89.42 110	90.30 180

v7n		78.97 170	77.58 184	83.14 151	83.45 267	65.51 173	88.32 124	91.21 114	73.69 129	72.41 257	86.32 235	57.93 190	93.81 134	69.18 187	75.65 276	90.11 188

CL-MVSNet_self_test		72.37 268	71.46 261	75.09 294	79.49 333	53.53 336	80.76 282	85.01 256	69.12 215	70.51 272	82.05 306	57.92 191	84.13 313	52.27 316	66.00 343	87.60 260

baseline2		75.70 234	73.83 243	81.30 201	83.26 271	61.79 246	82.57 265	80.65 307	66.81 241	66.88 312	83.42 288	57.86 192	92.19 201	63.47 232	79.57 229	89.91 201

QAPM		80.88 117	79.50 133	85.03 78	88.01 179	68.97 100	91.59 42	92.00 87	66.63 248	75.15 226	92.16 79	57.70 193	95.45 62	63.52 231	88.76 116	90.66 165

HyFIR lowres test		77.53 206	75.40 223	83.94 127	89.59 115	66.62 151	80.36 289	88.64 198	56.29 342	76.45 191	85.17 260	57.64 194	93.28 157	61.34 256	83.10 189	91.91 126

CNLPA		78.08 190	76.79 200	81.97 186	90.40 96	71.07 61	87.59 148	84.55 261	66.03 255	72.38 258	89.64 136	57.56 195	86.04 298	59.61 267	83.35 185	88.79 239

test_yl		81.17 112	80.47 114	83.24 146	89.13 138	63.62 212	86.21 188	89.95 151	72.43 152	81.78 99	89.61 137	57.50 196	93.58 143	70.75 169	86.90 137	92.52 105

DCV-MVSNet		81.17 112	80.47 114	83.24 146	89.13 138	63.62 212	86.21 188	89.95 151	72.43 152	81.78 99	89.61 137	57.50 196	93.58 143	70.75 169	86.90 137	92.52 105

sss		73.60 254	73.64 245	73.51 308	82.80 284	55.01 325	76.12 324	81.69 299	62.47 296	74.68 235	85.85 244	57.32 198	78.11 341	60.86 259	80.93 212	87.39 265

Effi-MVS+-dtu		80.03 143	78.57 155	84.42 101	85.13 239	68.74 106	88.77 107	88.10 205	74.99 101	74.97 231	83.49 287	57.27 199	93.36 155	73.53 144	80.88 213	91.18 145

AdaColmap		80.58 131	79.42 134	84.06 117	93.09 54	68.91 101	89.36 88	88.97 185	69.27 208	75.70 208	89.69 134	57.20 200	95.77 53	63.06 236	88.41 122	87.50 264

v1240		78.99 169	77.78 176	82.64 174	83.21 272	63.54 216	86.62 177	90.30 142	69.74 202	77.33 169	85.68 247	57.04 201	93.76 138	73.13 151	76.92 257	90.62 166

miper_lstm_enhance		74.11 249	73.11 250	77.13 278	80.11 322	59.62 271	72.23 344	86.92 232	66.76 243	70.40 274	82.92 293	56.93 202	82.92 322	69.06 189	72.63 313	88.87 235

BH-RMVSNet		79.61 149	78.44 158	83.14 151	89.38 125	65.93 163	84.95 218	87.15 228	73.56 133	78.19 152	89.79 132	56.67 203	93.36 155	59.53 268	86.74 140	90.13 186

test_djsdf		80.30 138	79.32 138	83.27 144	83.98 258	65.37 180	90.50 61	90.38 136	68.55 227	76.19 199	88.70 163	56.44 204	93.46 152	78.98 90	80.14 225	90.97 155

EPNet_dtu		75.46 238	74.86 229	77.23 277	82.57 290	54.60 328	86.89 167	83.09 286	71.64 159	66.25 321	85.86 243	55.99 205	88.04 284	54.92 303	86.55 143	89.05 226
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CostFormer		75.24 242	73.90 241	79.27 246	82.65 289	58.27 280	80.80 280	82.73 290	61.57 302	75.33 221	83.13 292	55.52 206	91.07 239	64.98 225	78.34 246	88.45 246

tpmrst		72.39 266	72.13 257	73.18 312	80.54 318	49.91 357	79.91 296	79.08 324	63.11 285	71.69 265	79.95 324	55.32 207	82.77 323	65.66 220	73.89 302	86.87 279

1314		76.53 221	75.30 227	80.21 228	83.93 259	62.32 238	84.66 223	88.81 189	60.23 311	70.16 279	84.07 278	55.30 208	90.73 245	67.37 204	83.21 187	87.59 262

tfpnnormal		74.39 245	73.16 249	78.08 263	86.10 224	58.05 282	84.65 225	87.53 220	70.32 187	71.22 269	85.63 249	54.97 209	89.86 254	43.03 357	75.02 292	86.32 288

sd_testset		77.70 203	77.40 186	78.60 255	89.03 143	60.02 267	79.00 305	85.83 247	75.19 97	76.61 189	89.98 128	54.81 210	85.46 304	62.63 242	83.55 181	90.33 178

GBi-Net		78.40 181	77.40 186	81.40 198	87.60 194	63.01 229	88.39 120	89.28 167	71.63 160	75.34 218	87.28 201	54.80 211	91.11 233	62.72 238	79.57 229	90.09 190

test1		78.40 181	77.40 186	81.40 198	87.60 194	63.01 229	88.39 120	89.28 167	71.63 160	75.34 218	87.28 201	54.80 211	91.11 233	62.72 238	79.57 229	90.09 190

FMVSNet2		78.20 187	77.21 190	81.20 205	87.60 194	62.89 233	87.47 151	89.02 181	71.63 160	75.29 223	87.28 201	54.80 211	91.10 236	62.38 243	79.38 233	89.61 212

Fast-Effi-MVS+-dtu		78.02 193	76.49 207	82.62 175	83.16 276	66.96 148	86.94 165	87.45 223	72.45 149	71.49 267	84.17 276	54.79 214	91.58 219	67.61 201	80.31 222	89.30 219

MVSTER		79.01 168	77.88 172	82.38 179	83.07 277	64.80 191	84.08 242	88.95 186	69.01 220	78.69 136	87.17 208	54.70 215	92.43 190	74.69 133	80.57 219	89.89 203

OpenMVS	72.83 10	79.77 147	78.33 162	84.09 114	85.17 235	69.91 83	90.57 59	90.97 120	66.70 244	72.17 260	91.91 82	54.70 215	93.96 123	61.81 251	90.95 90	88.41 248

XVG-OURS		80.41 133	79.23 141	83.97 125	85.64 229	69.02 98	83.03 262	90.39 135	71.09 173	77.63 164	91.49 95	54.62 217	91.35 228	75.71 125	83.47 184	91.54 133

mvsmamba		81.69 102	80.74 108	84.56 94	87.45 199	66.72 150	91.26 47	85.89 246	74.66 108	78.23 150	90.56 118	54.33 218	94.91 87	80.73 79	83.54 183	92.04 125

LPG-MVS_test		82.08 93	81.27 99	84.50 96	89.23 134	68.76 104	90.22 69	91.94 91	75.37 93	76.64 187	91.51 93	54.29 219	94.91 87	78.44 95	83.78 174	89.83 205

LGP-MVS_train				84.50 96	89.23 134	68.76 104		91.94 91	75.37 93	76.64 187	91.51 93	54.29 219	94.91 87	78.44 95	83.78 174	89.83 205

TR-MVS		77.44 207	76.18 212	81.20 205	88.24 170	63.24 224	84.61 226	86.40 238	67.55 238	77.81 160	86.48 231	54.10 221	93.15 167	57.75 286	82.72 194	87.20 270

FMVSNet3		77.88 197	76.85 198	80.97 213	86.84 214	62.36 236	86.52 180	88.77 191	71.13 171	75.34 218	86.66 223	54.07 222	91.10 236	62.72 238	79.57 229	89.45 215

DP-MVS		76.78 219	74.57 232	83.42 138	93.29 48	69.46 93	88.55 117	83.70 274	63.98 280	70.20 276	88.89 159	54.01 223	94.80 95	46.66 345	81.88 203	86.01 296

ACMP	74.13 6	81.51 109	80.57 111	84.36 103	89.42 122	68.69 111	89.97 73	91.50 110	74.46 113	75.04 230	90.41 121	53.82 224	94.54 103	77.56 104	82.91 190	89.86 204
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PLC	70.83 11	78.05 192	76.37 211	83.08 154	91.88 74	67.80 127	88.19 128	89.46 162	64.33 274	69.87 285	88.38 174	53.66 225	93.58 143	58.86 275	82.73 193	87.86 255
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dmvs_testset		62.63 324	64.11 315	58.19 352	78.55 338	24.76 387	75.28 331	65.94 368	67.91 235	60.34 347	76.01 349	53.56 226	73.94 367	31.79 370	67.65 336	75.88 359

CANet_DTU		80.61 128	79.87 125	82.83 165	85.60 230	63.17 228	87.36 153	88.65 197	76.37 75	75.88 205	88.44 173	53.51 227	93.07 172	73.30 148	89.74 107	92.25 116

ACMM	73.20 8	80.78 125	79.84 126	83.58 134	89.31 130	68.37 116	89.99 72	91.60 104	70.28 188	77.25 171	89.66 135	53.37 228	93.53 148	74.24 139	82.85 191	88.85 236
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVP-Stereo		76.12 229	74.46 236	81.13 208	85.37 233	69.79 85	84.42 234	87.95 210	65.03 265	67.46 306	85.33 255	53.28 229	91.73 217	58.01 284	83.27 186	81.85 341
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
AUN-MVS		79.21 163	77.60 183	84.05 119	88.71 155	67.61 132	85.84 199	87.26 226	69.08 216	77.23 173	88.14 185	53.20 230	93.47 151	75.50 130	73.45 307	91.06 150

anonymousdsp		78.60 178	77.15 191	82.98 160	80.51 319	67.08 144	87.24 158	89.53 160	65.66 259	75.16 225	87.19 207	52.52 231	92.25 199	77.17 109	79.34 234	89.61 212

CR-MVSNet		73.37 256	71.27 265	79.67 240	81.32 311	65.19 182	75.92 326	80.30 313	59.92 314	72.73 253	81.19 310	52.50 232	86.69 293	59.84 265	77.71 249	87.11 275

Patchmtry		70.74 279	69.16 282	75.49 291	80.72 315	54.07 333	74.94 337	80.30 313	58.34 327	70.01 280	81.19 310	52.50 232	86.54 294	53.37 311	71.09 324	85.87 300

pmmvs4		74.03 251	71.91 258	80.39 223	81.96 298	68.32 117	81.45 276	82.14 294	59.32 319	69.87 285	85.13 261	52.40 234	88.13 283	60.21 263	74.74 295	84.73 315

RPMNet		73.51 255	70.49 272	82.58 176	81.32 311	65.19 182	75.92 326	92.27 76	57.60 334	72.73 253	76.45 347	52.30 235	95.43 64	48.14 340	77.71 249	87.11 275

LFMVS		81.82 99	81.23 100	83.57 135	91.89 73	63.43 221	89.84 75	81.85 298	77.04 57	83.21 80	93.10 58	52.26 236	93.43 154	71.98 160	89.95 105	93.85 55

VDD-MVS		83.01 84	82.36 85	84.96 81	91.02 83	66.40 154	88.91 101	88.11 204	77.57 40	84.39 63	93.29 55	52.19 237	93.91 130	77.05 110	88.70 117	94.57 28

tfpn200view9		76.42 225	75.37 225	79.55 244	89.13 138	57.65 291	85.17 211	83.60 275	73.41 138	76.45 191	86.39 233	52.12 238	91.95 208	48.33 336	83.75 176	89.07 221

thres400		76.50 222	75.37 225	79.86 234	89.13 138	57.65 291	85.17 211	83.60 275	73.41 138	76.45 191	86.39 233	52.12 238	91.95 208	48.33 336	83.75 176	90.00 196

thres200		75.55 236	74.47 235	78.82 251	87.78 188	57.85 288	83.07 260	83.51 278	72.44 151	75.84 206	84.42 270	52.08 240	91.75 215	47.41 343	83.64 180	86.86 280

PMMVS		69.34 292	68.67 284	71.35 324	75.67 349	62.03 241	75.17 332	73.46 351	50.00 358	68.68 295	79.05 329	52.07 241	78.13 340	61.16 257	82.77 192	73.90 361

tpm cat1		70.57 281	68.31 287	77.35 275	82.41 294	57.95 286	78.08 314	80.22 315	52.04 352	68.54 298	77.66 342	52.00 242	87.84 286	51.77 317	72.07 318	86.25 289

IterMVS-SCA-FT		75.43 239	73.87 242	80.11 230	82.69 287	64.85 190	81.57 274	83.47 279	69.16 214	70.49 273	84.15 277	51.95 243	88.15 282	69.23 186	72.14 317	87.34 267

SCA		74.22 248	72.33 256	79.91 233	84.05 257	62.17 240	79.96 295	79.29 323	66.30 251	72.38 258	80.13 322	51.95 243	88.60 277	59.25 270	77.67 251	88.96 232

thres100view900		76.50 222	75.55 220	79.33 245	89.52 118	56.99 300	85.83 200	83.23 283	73.94 123	76.32 196	87.12 209	51.89 245	91.95 208	48.33 336	83.75 176	89.07 221

thres600view7		76.50 222	75.44 221	79.68 239	89.40 123	57.16 297	85.53 208	83.23 283	73.79 128	76.26 197	87.09 210	51.89 245	91.89 211	48.05 341	83.72 179	90.00 196

tpm2		73.26 259	71.46 261	78.63 253	83.34 269	56.71 305	80.65 284	80.40 312	56.63 340	73.55 244	82.02 307	51.80 247	91.24 231	56.35 299	78.42 244	87.95 252

LS3D		76.95 217	74.82 230	83.37 141	90.45 94	67.36 139	89.15 95	86.94 231	61.87 301	69.52 288	90.61 117	51.71 248	94.53 104	46.38 348	86.71 141	88.21 250

IterMVS		74.29 246	72.94 251	78.35 260	81.53 305	63.49 218	81.58 273	82.49 291	68.06 234	69.99 282	83.69 285	51.66 249	85.54 302	65.85 218	71.64 320	86.01 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 268	71.71 260	74.35 302	82.19 296	52.00 344	79.22 302	77.29 335	64.56 270	72.95 251	83.68 286	51.35 250	83.26 321	58.33 281	75.80 274	87.81 256

sam_mvs1												51.32 251				88.96 232

PatchmatchNet		73.12 261	71.33 264	78.49 259	83.18 274	60.85 255	79.63 297	78.57 326	64.13 275	71.73 264	79.81 327	51.20 252	85.97 299	57.40 289	76.36 270	88.66 242
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
patchmatchnet-post											74.00 356	51.12 253	88.60 277

xiu_mvs_v1_base_debu		80.80 122	79.72 128	84.03 121	87.35 200	70.19 78	85.56 203	88.77 191	69.06 217	81.83 95	88.16 181	50.91 254	92.85 179	78.29 99	87.56 127	89.06 223

xiu_mvs_v1_base		80.80 122	79.72 128	84.03 121	87.35 200	70.19 78	85.56 203	88.77 191	69.06 217	81.83 95	88.16 181	50.91 254	92.85 179	78.29 99	87.56 127	89.06 223

xiu_mvs_v1_base_debi		80.80 122	79.72 128	84.03 121	87.35 200	70.19 78	85.56 203	88.77 191	69.06 217	81.83 95	88.16 181	50.91 254	92.85 179	78.29 99	87.56 127	89.06 223

Patchmatch-test		64.82 319	63.24 320	69.57 332	79.42 334	49.82 358	63.49 372	69.05 362	51.98 354	59.95 350	80.13 322	50.91 254	70.98 370	40.66 362	73.57 305	87.90 254

Patchmatch-RL test		70.24 285	67.78 297	77.61 271	77.43 342	59.57 273	71.16 347	70.33 356	62.94 289	68.65 296	72.77 359	50.62 258	85.49 303	69.58 184	66.58 340	87.77 257

Anonymous20231211		78.97 170	77.69 181	82.81 167	90.54 93	64.29 202	90.11 71	91.51 107	65.01 266	76.16 203	88.13 186	50.56 259	93.03 176	69.68 183	77.56 252	91.11 147

VDDNet		81.52 107	80.67 110	84.05 119	90.44 95	64.13 205	89.73 81	85.91 245	71.11 172	83.18 81	93.48 50	50.54 260	93.49 149	73.40 147	88.25 123	94.54 29

pmmvs6		74.69 244	73.39 246	78.61 254	81.38 308	57.48 294	86.64 176	87.95 210	64.99 267	70.18 277	86.61 224	50.43 261	89.52 260	62.12 247	70.18 327	88.83 237

test_post											5.46 386	50.36 262	84.24 312

ET-MVSNet_ETH3D		78.63 177	76.63 206	84.64 92	86.73 217	69.47 91	85.01 216	84.61 260	69.54 203	66.51 319	86.59 225	50.16 263	91.75 215	76.26 119	84.24 171	92.69 100

sam_mvs												50.01 264

Anonymous20240529		80.19 141	78.89 149	84.10 112	90.60 91	64.75 192	88.95 100	90.90 122	65.97 256	80.59 113	91.17 104	49.97 265	93.73 141	69.16 188	82.70 195	93.81 58

thisisatest0530		79.40 158	77.76 178	84.31 106	87.69 191	65.10 185	87.36 153	84.26 268	70.04 191	77.42 167	88.26 179	49.94 266	94.79 96	70.20 175	84.70 164	93.03 90

PatchT		68.46 301	67.85 294	70.29 330	80.70 316	43.93 372	72.47 343	74.88 345	60.15 312	70.55 271	76.57 346	49.94 266	81.59 326	50.58 322	74.83 294	85.34 304

tttt0517		79.40 158	77.91 170	83.90 129	88.10 174	63.84 209	88.37 123	84.05 270	71.45 167	76.78 183	89.12 152	49.93 268	94.89 91	70.18 176	83.18 188	92.96 94

tpmvs		71.09 275	69.29 280	76.49 282	82.04 297	56.04 315	78.92 307	81.37 302	64.05 278	67.18 310	78.28 337	49.74 269	89.77 255	49.67 331	72.37 314	83.67 326

thisisatest0515		77.33 210	75.38 224	83.18 149	85.27 234	63.80 210	82.11 268	83.27 282	65.06 264	75.91 204	83.84 281	49.54 270	94.27 112	67.24 206	86.19 149	91.48 138

UniMVSNet_ETH3D		79.10 166	78.24 164	81.70 190	86.85 213	60.24 265	87.28 157	88.79 190	74.25 117	76.84 180	90.53 120	49.48 271	91.56 220	67.98 198	82.15 199	93.29 80

dmvs_re		71.14 274	70.58 270	72.80 313	81.96 298	59.68 270	75.60 330	79.34 322	68.55 227	69.27 292	80.72 318	49.42 272	76.54 349	52.56 315	77.79 248	82.19 339

CVMVSNet		72.99 263	72.58 253	74.25 303	84.28 250	50.85 353	86.41 182	83.45 280	44.56 363	73.23 248	87.54 197	49.38 273	85.70 300	65.90 217	78.44 243	86.19 291

MDTV_nov1_ep13_2view						37.79 379	75.16 333		55.10 345	66.53 316		49.34 274		53.98 307		87.94 253

UGNet		80.83 119	79.59 131	84.54 95	88.04 177	68.09 122	89.42 86	88.16 203	76.95 58	76.22 198	89.46 144	49.30 275	93.94 126	68.48 195	90.31 96	91.60 131
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
pmmvs5		71.55 271	70.20 277	75.61 288	77.83 340	56.39 310	81.74 271	80.89 303	57.76 332	67.46 306	84.49 269	49.26 276	85.32 306	57.08 292	75.29 288	85.11 310

mvsany_test1		62.30 325	61.26 329	65.41 344	69.52 369	54.86 326	66.86 363	49.78 384	46.65 361	68.50 299	83.21 290	49.15 277	66.28 376	56.93 294	60.77 354	75.11 360

LTVRE_ROB	69.57 13	76.25 228	74.54 234	81.41 197	88.60 158	64.38 201	79.24 301	89.12 179	70.76 179	69.79 287	87.86 188	49.09 278	93.20 163	56.21 300	80.16 223	86.65 285
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
FMVSNet1		77.44 207	76.12 213	81.40 198	86.81 215	63.01 229	88.39 120	89.28 167	70.49 184	74.39 238	87.28 201	49.06 279	91.11 233	60.91 258	78.52 241	90.09 190

RRT_MVS		80.35 137	79.22 142	83.74 131	87.63 193	65.46 176	91.08 53	88.92 188	73.82 126	76.44 194	90.03 127	49.05 280	94.25 116	76.84 112	79.20 237	91.51 134

test1111		79.43 156	79.18 144	80.15 229	89.99 107	53.31 340	87.33 155	77.05 337	75.04 100	80.23 117	92.77 72	48.97 281	92.33 197	68.87 191	92.40 73	94.81 19

ECVR-MVS		79.61 149	79.26 140	80.67 219	90.08 102	54.69 327	87.89 141	77.44 334	74.88 103	80.27 115	92.79 70	48.96 282	92.45 189	68.55 194	92.50 71	94.86 16

MDTV_nov1_ep13			69.97 278		83.18 274	53.48 337	77.10 322	80.18 316	60.45 308	69.33 291	80.44 319	48.89 283	86.90 292	51.60 319	78.51 242

test_post1							78.90 308				5.43 387	48.81 284	85.44 305	59.25 270

test-LLR		72.94 264	72.43 254	74.48 300	81.35 309	58.04 283	78.38 310	77.46 332	66.66 245	69.95 283	79.00 331	48.06 285	79.24 335	66.13 213	84.83 161	86.15 292

test0.0.03 1		68.00 303	67.69 298	68.90 335	77.55 341	47.43 361	75.70 329	72.95 353	66.66 245	66.56 315	82.29 303	48.06 285	75.87 356	44.97 354	74.51 297	83.41 328

our_test_3		69.14 293	67.00 305	75.57 289	79.80 328	58.80 275	77.96 315	77.81 329	59.55 317	62.90 341	78.25 338	47.43 287	83.97 314	51.71 318	67.58 337	83.93 324

MS-PatchMatch		73.83 252	72.67 252	77.30 276	83.87 260	66.02 160	81.82 269	84.66 259	61.37 305	68.61 297	82.82 296	47.29 288	88.21 281	59.27 269	84.32 169	77.68 355

cascas		76.72 220	74.64 231	82.99 159	85.78 227	65.88 165	82.33 266	89.21 173	60.85 307	72.74 252	81.02 313	47.28 289	93.75 139	67.48 203	85.02 159	89.34 217

WB-MVS		54.94 332	54.72 334	55.60 358	73.50 359	20.90 389	74.27 339	61.19 375	59.16 321	50.61 368	74.15 355	47.19 290	75.78 357	17.31 381	35.07 377	70.12 365

test20.03		67.45 305	66.95 306	68.94 334	75.48 351	44.84 370	77.50 318	77.67 330	66.66 245	63.01 339	83.80 282	47.02 291	78.40 339	42.53 359	68.86 334	83.58 327

test_0402		72.79 265	70.44 273	79.84 235	88.13 172	65.99 162	85.93 195	84.29 266	65.57 260	67.40 308	85.49 252	46.92 292	92.61 184	35.88 367	74.38 298	80.94 346

F-COLMAP		76.38 227	74.33 237	82.50 177	89.28 132	66.95 149	88.41 119	89.03 180	64.05 278	66.83 313	88.61 167	46.78 293	92.89 178	57.48 287	78.55 240	87.67 258

ppachtmachnet_test		70.04 287	67.34 303	78.14 262	79.80 328	61.13 251	79.19 303	80.59 308	59.16 321	65.27 326	79.29 328	46.75 294	87.29 290	49.33 332	66.72 338	86.00 298

tt0805		78.73 174	77.83 173	81.43 196	85.17 235	60.30 264	89.41 87	90.90 122	71.21 170	77.17 177	88.73 162	46.38 295	93.21 160	72.57 157	78.96 238	90.79 159

D2MVS		74.82 243	73.21 248	79.64 241	79.81 327	62.56 235	80.34 290	87.35 224	64.37 273	68.86 294	82.66 298	46.37 296	90.10 252	67.91 199	81.24 209	86.25 289

Anonymous20231206		68.60 297	67.80 296	71.02 327	80.23 321	50.75 354	78.30 313	80.47 310	56.79 339	66.11 322	82.63 299	46.35 297	78.95 337	43.62 356	75.70 275	83.36 329

SSC-MVS		53.88 335	53.59 336	54.75 360	72.87 364	19.59 390	73.84 341	60.53 377	57.58 335	49.18 370	73.45 358	46.34 298	75.47 360	16.20 384	32.28 379	69.20 366

CHOSEN 280x420		66.51 311	64.71 312	71.90 318	81.45 306	63.52 217	57.98 375	68.95 363	53.57 348	62.59 342	76.70 345	46.22 299	75.29 362	55.25 302	79.68 228	76.88 357

GA-MVS		76.87 218	75.17 228	81.97 186	82.75 285	62.58 234	81.44 277	86.35 240	72.16 156	74.74 234	82.89 294	46.20 300	92.02 206	68.85 192	81.09 211	91.30 143

iter_conf_final		80.63 127	79.35 137	84.46 99	89.36 126	67.70 130	89.85 74	84.49 262	73.19 142	78.30 148	88.94 156	45.98 301	94.56 101	79.59 87	84.48 167	91.11 147

MDA-MVSNet_test_wron		65.03 317	62.92 321	71.37 322	75.93 346	56.73 303	69.09 359	74.73 347	57.28 337	54.03 365	77.89 339	45.88 302	74.39 365	49.89 330	61.55 352	82.99 335

YYNet1		65.03 317	62.91 322	71.38 321	75.85 348	56.60 307	69.12 358	74.66 349	57.28 337	54.12 364	77.87 340	45.85 303	74.48 364	49.95 329	61.52 353	83.05 333

EPMVS		69.02 294	68.16 289	71.59 320	79.61 331	49.80 359	77.40 319	66.93 365	62.82 292	70.01 280	79.05 329	45.79 304	77.86 343	56.58 297	75.26 289	87.13 274

IB-MVS	68.01 15	75.85 233	73.36 247	83.31 142	84.76 244	66.03 159	83.38 252	85.06 254	70.21 190	69.40 289	81.05 312	45.76 305	94.66 100	65.10 224	75.49 279	89.25 220
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
jajsoiax		79.29 161	77.96 168	83.27 144	84.68 246	66.57 153	89.25 90	90.16 145	69.20 212	75.46 213	89.49 141	45.75 306	93.13 169	76.84 112	80.80 215	90.11 188

PatchMatch-RL		72.38 267	70.90 268	76.80 281	88.60 158	67.38 138	79.53 298	76.17 342	62.75 293	69.36 290	82.00 308	45.51 307	84.89 309	53.62 309	80.58 218	78.12 354

FE-MVS		77.78 199	75.68 217	84.08 115	88.09 175	66.00 161	83.13 257	87.79 215	68.42 231	78.01 157	85.23 258	45.50 308	95.12 77	59.11 272	85.83 156	91.11 147

RPSCF		73.23 260	71.46 261	78.54 257	82.50 291	59.85 268	82.18 267	82.84 289	58.96 323	71.15 270	89.41 148	45.48 309	84.77 310	58.82 276	71.83 319	91.02 154

test_vis1_n_1920		75.52 237	75.78 215	74.75 299	79.84 326	57.44 295	83.26 254	85.52 250	62.83 291	79.34 127	86.17 238	45.10 310	79.71 334	78.75 92	81.21 210	87.10 277

MSDG		73.36 258	70.99 267	80.49 222	84.51 248	65.80 168	80.71 283	86.13 243	65.70 258	65.46 324	83.74 284	44.60 311	90.91 241	51.13 321	76.89 258	84.74 314

PVSNet_0	57.27 20	61.67 327	59.27 330	68.85 336	79.61 331	57.44 295	68.01 360	73.44 352	55.93 343	58.54 354	70.41 364	44.58 312	77.55 344	47.01 344	35.91 376	71.55 364

test_cas_vis1_n_1920		73.76 253	73.74 244	73.81 306	75.90 347	59.77 269	80.51 286	82.40 292	58.30 328	81.62 101	85.69 246	44.35 313	76.41 352	76.29 118	78.61 239	85.23 306

mvs_tets		79.13 165	77.77 177	83.22 148	84.70 245	66.37 155	89.17 91	90.19 144	69.38 206	75.40 216	89.46 144	44.17 314	93.15 167	76.78 115	80.70 217	90.14 185

MDA-MVSNet-bldmvs		66.68 309	63.66 318	75.75 286	79.28 335	60.56 260	73.92 340	78.35 327	64.43 271	50.13 369	79.87 326	44.02 315	83.67 316	46.10 349	56.86 359	83.03 334

iter_conf05		80.00 145	78.70 151	83.91 128	87.84 183	65.83 166	88.84 105	84.92 257	71.61 163	78.70 135	88.94 156	43.88 316	94.56 101	79.28 88	84.28 170	91.33 140

gg-mvs-nofinetune		69.95 288	67.96 292	75.94 285	83.07 277	54.51 330	77.23 321	70.29 357	63.11 285	70.32 275	62.33 368	43.62 317	88.69 276	53.88 308	87.76 126	84.62 316

GG-mvs-BLEND				75.38 292	81.59 304	55.80 317	79.32 300	69.63 359		67.19 309	73.67 357	43.24 318	88.90 274	50.41 323	84.50 165	81.45 343

CMPMVS	51.72 21	70.19 286	68.16 289	76.28 283	73.15 363	57.55 293	79.47 299	83.92 271	48.02 360	56.48 361	84.81 266	43.13 319	86.42 296	62.67 241	81.81 204	84.89 312
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dp		66.80 308	65.43 310	70.90 329	79.74 330	48.82 360	75.12 335	74.77 346	59.61 316	64.08 334	77.23 343	42.89 320	80.72 331	48.86 334	66.58 340	83.16 331

PVSNet	64.34 18	72.08 270	70.87 269	75.69 287	86.21 222	56.44 309	74.37 338	80.73 306	62.06 300	70.17 278	82.23 304	42.86 321	83.31 320	54.77 304	84.45 168	87.32 268

pmmvs-eth3d		70.50 283	67.83 295	78.52 258	77.37 343	66.18 158	81.82 269	81.51 300	58.90 324	63.90 336	80.42 320	42.69 322	86.28 297	58.56 278	65.30 345	83.11 332

UnsupCasMVSNet_eth		67.33 306	65.99 309	71.37 322	73.48 360	51.47 350	75.16 333	85.19 253	65.20 262	60.78 346	80.93 317	42.35 323	77.20 345	57.12 291	53.69 366	85.44 303

KD-MVS_self_test		68.81 295	67.59 301	72.46 316	74.29 355	45.45 365	77.93 316	87.00 230	63.12 284	63.99 335	78.99 333	42.32 324	84.77 310	56.55 298	64.09 348	87.16 273

ADS-MVSNet2		66.20 316	63.33 319	74.82 297	79.92 324	58.75 276	67.55 361	75.19 344	53.37 349	65.25 327	75.86 350	42.32 324	80.53 332	41.57 360	68.91 332	85.18 307

ADS-MVSNet		64.36 320	62.88 323	68.78 337	79.92 324	47.17 362	67.55 361	71.18 355	53.37 349	65.25 327	75.86 350	42.32 324	73.99 366	41.57 360	68.91 332	85.18 307

bld_raw_dy_0_64		77.29 212	75.98 214	81.22 204	85.04 241	65.47 175	88.14 133	77.56 331	69.20 212	73.77 243	89.40 150	42.24 327	88.85 275	76.78 115	81.64 205	89.33 218

SixPastTwentyTwo		73.37 256	71.26 266	79.70 238	85.08 240	57.89 287	85.57 202	83.56 277	71.03 174	65.66 323	85.88 242	42.10 328	92.57 185	59.11 272	63.34 349	88.65 243

JIA-IIPM		66.32 313	62.82 324	76.82 280	77.09 344	61.72 247	65.34 368	75.38 343	58.04 331	64.51 331	62.32 369	42.05 329	86.51 295	51.45 320	69.22 331	82.21 338

ACMH	67.68 16	75.89 232	73.93 240	81.77 189	88.71 155	66.61 152	88.62 115	89.01 182	69.81 197	66.78 314	86.70 221	41.95 330	91.51 224	55.64 301	78.14 247	87.17 271
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	68.96 14	76.01 231	74.01 239	82.03 184	88.60 158	65.31 181	88.86 103	87.55 219	70.25 189	67.75 302	87.47 199	41.27 331	93.19 165	58.37 280	75.94 273	87.60 260

MIMVSNet		70.69 280	69.30 279	74.88 296	84.52 247	56.35 312	75.87 328	79.42 321	64.59 269	67.76 301	82.41 300	41.10 332	81.54 327	46.64 347	81.34 207	86.75 283

Anonymous202405211		78.25 184	77.01 193	81.99 185	91.03 82	60.67 258	84.77 221	83.90 272	70.65 182	80.00 119	91.20 102	41.08 333	91.43 226	65.21 222	85.26 158	93.85 55

N_pmnet		52.79 338	53.26 337	51.40 362	78.99 337	7.68 393	69.52 354	3.89 393	51.63 355	57.01 359	74.98 354	40.83 334	65.96 377	37.78 365	64.67 346	80.56 349

EU-MVSNet		68.53 300	67.61 300	71.31 325	78.51 339	47.01 363	84.47 229	84.27 267	42.27 366	66.44 320	84.79 267	40.44 335	83.76 315	58.76 277	68.54 335	83.17 330

DSMNet-mixed		57.77 331	56.90 333	60.38 350	67.70 372	35.61 380	69.18 356	53.97 382	32.30 378	57.49 358	79.88 325	40.39 336	68.57 375	38.78 364	72.37 314	76.97 356

OurMVSNet-221017-0		74.26 247	72.42 255	79.80 236	83.76 262	59.59 272	85.92 196	86.64 234	66.39 250	66.96 311	87.58 193	39.46 337	91.60 218	65.76 219	69.27 330	88.22 249

K. test v3		71.19 273	68.51 285	79.21 248	83.04 279	57.78 290	84.35 236	76.91 338	72.90 148	62.99 340	82.86 295	39.27 338	91.09 238	61.65 252	52.66 367	88.75 240

lessismore_v0				78.97 249	81.01 314	57.15 298		65.99 367		61.16 345	82.82 296	39.12 339	91.34 229	59.67 266	46.92 373	88.43 247

UnsupCasMVSNet_bld		63.70 322	61.53 328	70.21 331	73.69 358	51.39 351	72.82 342	81.89 296	55.63 344	57.81 357	71.80 361	38.67 340	78.61 338	49.26 333	52.21 368	80.63 347

new-patchmatchnet		61.73 326	61.73 327	61.70 348	72.74 365	24.50 388	69.16 357	78.03 328	61.40 303	56.72 360	75.53 353	38.42 341	76.48 351	45.95 350	57.67 358	84.13 321

MVS-HIRNet		59.14 329	57.67 332	63.57 346	81.65 302	43.50 373	71.73 345	65.06 370	39.59 370	51.43 367	57.73 374	38.34 342	82.58 324	39.53 363	73.95 301	64.62 370

test2506		77.30 211	76.49 207	79.74 237	90.08 102	52.02 343	87.86 143	63.10 373	74.88 103	80.16 118	92.79 70	38.29 343	92.35 195	68.74 193	92.50 71	94.86 16

COLMAP_ROB	66.92 17	73.01 262	70.41 274	80.81 216	87.13 210	65.63 171	88.30 125	84.19 269	62.96 288	63.80 337	87.69 191	38.04 344	92.56 186	46.66 345	74.91 293	84.24 319
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TESTMET0.1,1		69.89 289	69.00 283	72.55 315	79.27 336	56.85 301	78.38 310	74.71 348	57.64 333	68.09 300	77.19 344	37.75 345	76.70 348	63.92 230	84.09 172	84.10 322

OpenMVS_ROB	64.09 19	70.56 282	68.19 288	77.65 270	80.26 320	59.41 274	85.01 216	82.96 288	58.76 325	65.43 325	82.33 301	37.63 346	91.23 232	45.34 353	76.03 272	82.32 337

FMVSNet5		69.50 291	67.96 292	74.15 304	82.97 282	55.35 321	80.01 294	82.12 295	62.56 295	63.02 338	81.53 309	36.92 347	81.92 325	48.42 335	74.06 300	85.17 309

MIMVSNet1		68.58 298	66.78 307	73.98 305	80.07 323	51.82 346	80.77 281	84.37 263	64.40 272	59.75 351	82.16 305	36.47 348	83.63 317	42.73 358	70.33 326	86.48 287

ITE_SJBPF				78.22 261	81.77 301	60.57 259		83.30 281	69.25 209	67.54 304	87.20 206	36.33 349	87.28 291	54.34 306	74.62 296	86.80 281

test-mter		71.41 272	70.39 275	74.48 300	81.35 309	58.04 283	78.38 310	77.46 332	60.32 310	69.95 283	79.00 331	36.08 350	79.24 335	66.13 213	84.83 161	86.15 292

testgi		66.67 310	66.53 308	67.08 342	75.62 350	41.69 377	75.93 325	76.50 339	66.11 252	65.20 329	86.59 225	35.72 351	74.71 363	43.71 355	73.38 309	84.84 313

EG-PatchMatch MVS		74.04 250	71.82 259	80.71 218	84.92 243	67.42 136	85.86 198	88.08 206	66.04 254	64.22 333	83.85 280	35.10 352	92.56 186	57.44 288	80.83 214	82.16 340

KD-MVS_2432*1600		66.22 314	63.89 316	73.21 309	75.47 352	53.42 338	70.76 350	84.35 264	64.10 276	66.52 317	78.52 335	34.55 353	84.98 307	50.40 324	50.33 370	81.23 344

miper_refine_blended		66.22 314	63.89 316	73.21 309	75.47 352	53.42 338	70.76 350	84.35 264	64.10 276	66.52 317	78.52 335	34.55 353	84.98 307	50.40 324	50.33 370	81.23 344

XVG-ACMP-BASELINE		76.11 230	74.27 238	81.62 191	83.20 273	64.67 193	83.60 249	89.75 156	69.75 200	71.85 263	87.09 210	32.78 355	92.11 203	69.99 179	80.43 221	88.09 251

AllTest		70.96 276	68.09 291	79.58 242	85.15 237	63.62 212	84.58 227	79.83 317	62.31 297	60.32 348	86.73 215	32.02 356	88.96 272	50.28 326	71.57 321	86.15 292

TestCases				79.58 242	85.15 237	63.62 212		79.83 317	62.31 297	60.32 348	86.73 215	32.02 356	88.96 272	50.28 326	71.57 321	86.15 292

USDC		70.33 284	68.37 286	76.21 284	80.60 317	56.23 313	79.19 303	86.49 236	60.89 306	61.29 344	85.47 253	31.78 358	89.47 262	53.37 311	76.21 271	82.94 336

test_fmvs1		70.93 277	70.52 271	72.16 317	73.71 357	55.05 324	80.82 279	78.77 325	51.21 357	78.58 140	84.41 271	31.20 359	76.94 347	75.88 124	80.12 226	84.47 317

Anonymous20240521		68.80 296	67.22 304	73.55 307	74.33 354	54.11 332	83.18 255	85.61 249	58.15 329	61.68 343	80.94 315	30.71 360	81.27 329	57.00 293	73.34 310	85.28 305

testing3		68.56 299	67.67 299	71.22 326	87.33 205	42.87 374	83.06 261	71.54 354	70.36 185	69.08 293	84.38 272	30.33 361	85.69 301	37.50 366	75.45 283	85.09 311

test_vis1_n		69.85 290	69.21 281	71.77 319	72.66 366	55.27 323	81.48 275	76.21 341	52.03 353	75.30 222	83.20 291	28.97 362	76.22 354	74.60 134	78.41 245	83.81 325

tmp_tt		18.61 354	21.40 357	10.23 370	4.82 393	10.11 392	34.70 380	30.74 391	1.48 387	23.91 383	26.07 384	28.42 363	13.41 389	27.12 374	15.35 386	7.17 384

test_fmvs1_n		70.86 278	70.24 276	72.73 314	72.51 367	55.28 322	81.27 278	79.71 319	51.49 356	78.73 134	84.87 265	27.54 364	77.02 346	76.06 121	79.97 227	85.88 299

TDRefinement		67.49 304	64.34 313	76.92 279	73.47 361	61.07 252	84.86 220	82.98 287	59.77 315	58.30 355	85.13 261	26.06 365	87.89 285	47.92 342	60.59 356	81.81 342

test_vis1_rt		60.28 328	58.42 331	65.84 343	67.25 373	55.60 320	70.44 352	60.94 376	44.33 364	59.00 352	66.64 366	24.91 366	68.67 374	62.80 237	69.48 328	73.25 362

TinyColmap		67.30 307	64.81 311	74.76 298	81.92 300	56.68 306	80.29 291	81.49 301	60.33 309	56.27 362	83.22 289	24.77 367	87.66 289	45.52 351	69.47 329	79.95 350

EGC-MVSNET		52.07 340	47.05 344	67.14 341	83.51 266	60.71 257	80.50 287	67.75 364	0.07 388	0.43 389	75.85 352	24.26 368	81.54 327	28.82 372	62.25 350	59.16 373

LF4IMVS		64.02 321	62.19 325	69.50 333	70.90 368	53.29 341	76.13 323	77.18 336	52.65 351	58.59 353	80.98 314	23.55 369	76.52 350	53.06 313	66.66 339	78.68 353

test_fmvs2		68.35 302	67.48 302	70.98 328	69.50 370	51.95 345	80.05 293	76.38 340	49.33 359	74.65 236	84.38 272	23.30 370	75.40 361	74.51 135	75.17 291	85.60 301

new_pmnet		50.91 341	50.29 341	52.78 361	68.58 371	34.94 382	63.71 370	56.63 381	39.73 369	44.95 371	65.47 367	21.93 371	58.48 380	34.98 368	56.62 360	64.92 369

pmmvs3		57.79 330	54.26 335	68.37 338	64.02 376	56.72 304	75.12 335	65.17 369	40.20 368	52.93 366	69.86 365	20.36 372	75.48 359	45.45 352	55.25 365	72.90 363

PM-MVS		66.41 312	64.14 314	73.20 311	73.92 356	56.45 308	78.97 306	64.96 371	63.88 282	64.72 330	80.24 321	19.84 373	83.44 319	66.24 212	64.52 347	79.71 351

mvsany_test3		53.99 334	51.45 339	61.61 349	55.51 381	44.74 371	63.52 371	45.41 388	43.69 365	58.11 356	76.45 347	17.99 374	63.76 379	54.77 304	47.59 372	76.34 358

ambc				75.24 293	73.16 362	50.51 355	63.05 373	87.47 222		64.28 332	77.81 341	17.80 375	89.73 257	57.88 285	60.64 355	85.49 302

ANet_high		50.57 342	46.10 346	63.99 345	48.67 388	39.13 378	70.99 349	80.85 304	61.39 304	31.18 377	57.70 375	17.02 376	73.65 368	31.22 371	15.89 385	79.18 352

FPMVS		53.68 336	51.64 338	59.81 351	65.08 375	51.03 352	69.48 355	69.58 360	41.46 367	40.67 373	72.32 360	16.46 377	70.00 373	24.24 378	65.42 344	58.40 375

test_method		31.52 350	29.28 354	38.23 365	27.03 392	6.50 394	20.94 383	62.21 374	4.05 386	22.35 384	52.50 378	13.33 378	47.58 385	27.04 375	34.04 378	60.62 372

EMVS		30.81 351	29.65 353	34.27 367	50.96 387	25.95 386	56.58 377	46.80 387	24.01 382	15.53 387	30.68 383	12.47 379	54.43 384	12.81 386	17.05 384	22.43 383

test_f		52.09 339	50.82 340	55.90 356	53.82 384	42.31 376	59.42 374	58.31 380	36.45 373	56.12 363	70.96 363	12.18 380	57.79 381	53.51 310	56.57 361	67.60 367

test_fmvs3		63.36 323	61.82 326	67.98 339	62.51 377	46.96 364	77.37 320	74.03 350	45.24 362	67.50 305	78.79 334	12.16 381	72.98 369	72.77 155	66.02 342	83.99 323

E-PMN		31.77 349	30.64 352	35.15 366	52.87 386	27.67 384	57.09 376	47.86 386	24.64 381	16.40 386	33.05 382	11.23 382	54.90 383	14.46 385	18.15 383	22.87 382

DeepMVS_CX				27.40 368	40.17 391	26.90 385		24.59 392	17.44 384	23.95 382	48.61 379	9.77 383	26.48 387	18.06 380	24.47 381	28.83 381

Gipuma		45.18 346	41.86 349	55.16 359	77.03 345	51.52 349	32.50 381	80.52 309	32.46 377	27.12 380	35.02 381	9.52 384	75.50 358	22.31 379	60.21 357	38.45 380
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		54.25 333	49.68 343	67.97 340	53.73 385	45.28 368	66.85 364	80.78 305	35.96 374	39.45 375	62.23 370	8.70 385	78.06 342	48.24 339	51.20 369	80.57 348

APD_test1		53.31 337	49.93 342	63.42 347	65.68 374	50.13 356	71.59 346	66.90 366	34.43 375	40.58 374	71.56 362	8.65 386	76.27 353	34.64 369	55.36 364	63.86 371

PMMVS2		40.82 348	38.86 351	46.69 363	53.84 383	16.45 391	48.61 378	49.92 383	37.49 371	31.67 376	60.97 371	8.14 387	56.42 382	28.42 373	30.72 380	67.19 368

test_vis3_rt		49.26 343	47.02 345	56.00 355	54.30 382	45.27 369	66.76 365	48.08 385	36.83 372	44.38 372	53.20 377	7.17 388	64.07 378	56.77 296	55.66 362	58.65 374

testf1		45.72 344	41.96 347	57.00 353	56.90 379	45.32 366	66.14 366	59.26 378	26.19 379	30.89 378	60.96 372	4.14 389	70.64 371	26.39 376	46.73 374	55.04 376

APD_test2		45.72 344	41.96 347	57.00 353	56.90 379	45.32 366	66.14 366	59.26 378	26.19 379	30.89 378	60.96 372	4.14 389	70.64 371	26.39 376	46.73 374	55.04 376

PMVS	37.38 22	44.16 347	40.28 350	55.82 357	40.82 390	42.54 375	65.12 369	63.99 372	34.43 375	24.48 381	57.12 376	3.92 391	76.17 355	17.10 382	55.52 363	48.75 378
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 352	25.89 356	43.81 364	44.55 389	35.46 381	28.87 382	39.07 389	18.20 383	18.58 385	40.18 380	2.68 392	47.37 386	17.07 383	23.78 382	48.60 379
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		16.82 355	15.94 358	19.46 369	58.74 378	31.45 383	39.22 379	3.74 394	6.84 385	6.04 388	2.70 388	1.27 393	24.29 388	10.54 387	14.40 387	2.63 385

test123		6.12 357	8.11 360	0.14 371	0.06 395	0.09 395	71.05 348	0.03 396	0.04 390	0.25 391	1.30 390	0.05 394	0.03 391	0.21 389	0.01 389	0.29 386

testmvs		6.04 358	8.02 361	0.10 372	0.08 394	0.03 396	69.74 353	0.04 395	0.05 389	0.31 390	1.68 389	0.02 395	0.04 390	0.24 388	0.02 388	0.25 387

test_blank		0.00 360	0.00 363	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

uanet_test		0.00 360	0.00 363	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

DCPMVS		0.00 360	0.00 363	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

sosnet-low-res		0.00 360	0.00 363	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

sosnet		0.00 360	0.00 363	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

uncertanet		0.00 360	0.00 363	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

Regformer		0.00 360	0.00 363	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

ab-mvs-re		7.23 356	9.64 359	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	86.72 217	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

uanet		0.00 360	0.00 363	0.00 373	0.00 396	0.00 397	0.00 384	0.00 397	0.00 391	0.00 392	0.00 391	0.00 396	0.00 392	0.00 390	0.00 390	0.00 388

FOURS1					95.00 10	72.39 38	95.06 1	93.84 15	74.49 112	91.30 15

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 45					97.53 1	89.67 3	96.44 9	94.41 31

No_MVS				89.16 1	94.34 27	75.53 2		92.99 45					97.53 1	89.67 3	96.44 9	94.41 31

eth-test2					0.00 396

eth-test					0.00 396

IU-MVS					95.30 2	71.25 56		92.95 51	66.81 241	92.39 6				88.94 13	96.63 4	94.85 18

save fliter					93.80 40	72.35 41	90.47 63	91.17 116	74.31 115

test_0728_SECOND				87.71 31	95.34 1	71.43 55	93.49 9	94.23 3					97.49 3	89.08 9	96.41 12	94.21 41

GSMVS																88.96 232

test_part2					95.06 8	72.65 31				91.80 13

MTGPA								92.02 85

MTMP							92.18 34	32.83 390

gm-plane-assit					81.40 307	53.83 335			62.72 294		80.94 315		92.39 192	63.40 234

test9_res														84.90 33	95.70 26	92.87 95

agg_prior2														82.91 57	95.45 29	92.70 98

agg_prior					92.85 59	71.94 50		91.78 100		84.41 62			94.93 86

test_prior4						72.60 33	89.01 98

test_prior				86.33 53	92.61 65	69.59 87		92.97 50					95.48 61			93.91 52

旧先验2							86.56 179		58.10 330	87.04 32			88.98 270	74.07 140

新几何2							86.29 187

无先验							87.48 150	88.98 183	60.00 313				94.12 120	67.28 205		88.97 231

原ACMM2							86.86 168

testdata2													91.01 240	62.37 244

testdata1							84.14 240		75.71 86

plane_prior7					90.08 102	68.51 115

plane_prior5								92.44 69					95.38 68	78.71 93	86.32 146	91.33 140

plane_prior4											91.00 111

plane_prior3						68.60 113			78.44 30	78.92 132

plane_prior2							91.25 49		79.12 22

plane_prior1					89.90 110

plane_prior						68.71 108	90.38 66		77.62 38						86.16 150

n2								0.00 397

nn								0.00 397

door-mid								69.98 358

test11								92.23 79

door								69.44 361

HQP5-MVS						66.98 146

HQP-NCC					89.33 127		89.17 91		76.41 71	77.23 173

ACMP_Plane					89.33 127		89.17 91		76.41 71	77.23 173

BP-MVS														77.47 105

HQP4-MVS										77.24 172			95.11 79			91.03 152

HQP3-MVS								92.19 82							85.99 153

NP-MVS					89.62 114	68.32 117					90.24 123

ACMMP++_ref															81.95 202

ACMMP++															81.25 208

High-resolution multi-view benchmark