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 26	95.30 2	70.98 63	93.57 7	94.06 10	77.24 50	93.10 1	95.72 8	82.99 1	97.44 6	89.07 14	96.63 4	94.88 14

test_241102_ONE					95.30 2	70.98 63		94.06 10	77.17 53	93.10 1	95.39 11	82.99 1	97.27 11

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 57	95.06 1	94.23 3	78.38 33	92.78 4	95.74 6	82.45 3	97.49 4	89.42 9	96.68 2	94.95 10

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 44	82.45 3	96.87 20	83.77 58	96.48 8	94.88 14

PC_three_1452									68.21 247	92.02 12	94.00 46	82.09 5	95.98 51	84.58 48	96.68 2	94.95 10

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 43	94.10 8	75.90 87	92.29 7	95.66 10	81.67 6	97.38 10	87.44 33	96.34 15	93.95 54
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 33	92.12 9	95.78 4	81.46 7	97.40 8	89.42 9	96.57 7	94.67 25

test_241102_TWO								94.06 10	77.24 50	92.78 4	95.72 8	81.26 8	97.44 6	89.07 14	96.58 6	94.26 43

DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 57	93.49 9	92.73 60	77.33 48	92.12 9	95.78 4	80.98 9	97.40 8	89.08 12	96.41 12	93.33 88
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 57	93.60 6	94.11 6	77.33 48	92.81 3	95.79 3	80.98 9

test_one_0601					95.07 7	71.46 55		94.14 5	78.27 35	92.05 11	95.74 6	80.83 11

DeepPCF-MVS	80.84 1	88.10 13	88.56 13	86.73 50	92.24 68	69.03 100	89.57 88	93.39 30	77.53 45	89.79 18	94.12 39	78.98 12	96.58 35	85.66 37	95.72 24	94.58 29

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 16	94.11 6	80.27 10	91.35 14	94.16 37	78.35 13	96.77 24	89.59 8	94.22 59	94.67 25
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 7	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 91	91.06 16	96.03 1	76.84 14	97.03 17	89.09 11	95.65 27	94.47 33
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
dcpmvs_2		85.63 53	86.15 44	84.06 127	91.71 75	64.94 198	86.47 191	91.87 97	73.63 134	86.60 45	93.02 72	76.57 15	91.87 219	83.36 60	92.15 76	95.35 3

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 61	93.00 43	80.90 7	88.06 26	94.06 42	76.43 16	96.84 21	88.48 24	95.99 18	94.34 39

MCST-MVS		87.37 27	87.25 26	87.73 28	94.53 17	72.46 38	89.82 77	93.82 16	73.07 150	84.86 64	92.89 74	76.22 17	96.33 38	84.89 44	95.13 36	94.40 36

CSCG		86.41 41	86.19 42	87.07 45	92.91 58	72.48 37	90.81 57	93.56 24	73.95 125	83.16 94	91.07 118	75.94 18	95.19 77	79.94 96	94.38 55	93.55 78

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 27	92.85 55	80.26 11	87.78 30	94.27 32	75.89 19	96.81 23	87.45 32	96.44 9	93.05 100

TSAR-MVS + MP.		88.02 18	88.11 16	87.72 30	93.68 43	72.13 46	91.41 47	92.35 76	74.62 113	88.90 20	93.85 52	75.75 20	96.00 49	87.80 28	94.63 48	95.04 7
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 12	88.74 12	87.64 35	92.78 61	71.95 50	92.40 24	94.74 2	75.71 89	89.16 19	95.10 14	75.65 21	96.19 43	87.07 34	96.01 17	94.79 21

9.14			88.26 15		92.84 60		91.52 46	94.75 1	73.93 127	88.57 22	94.67 19	75.57 22	95.79 54	86.77 35	95.76 23

SD-MVS		88.06 15	88.50 14	86.71 51	92.60 66	72.71 29	91.81 42	93.19 35	77.87 36	90.32 17	94.00 46	74.83 23	93.78 138	87.63 30	94.27 58	93.65 71
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 58	85.30 60	85.77 65	88.49 165	67.93 133	85.52 221	93.44 27	78.70 29	83.63 89	89.03 166	74.57 24	95.71 57	80.26 94	94.04 60	93.66 67
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 78	84.54 68	80.99 222	90.06 107	65.83 177	84.21 249	88.74 200	71.60 170	85.01 57	92.44 84	74.51 25	83.50 335	82.15 75	92.15 76	93.64 73

train_agg		86.43 39	86.20 41	87.13 44	93.26 50	72.96 25	88.75 117	91.89 95	68.69 239	85.00 59	93.10 67	74.43 26	95.41 69	84.97 41	95.71 25	93.02 102

test_8					93.13 52	72.57 35	88.68 122	91.84 99	68.69 239	84.87 63	93.10 67	74.43 26	95.16 78

TEST9					93.26 50	72.96 25	88.75 117	91.89 95	68.44 244	85.00 59	93.10 67	74.36 28	95.41 69

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 109	92.29 7	95.97 2	74.28 29	97.24 12	88.58 21	96.91 1	94.87 16
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							88.85 113		75.41 95	84.91 61	93.54 56	74.28 29		83.31 61	95.86 20

TSAR-MVS + GP.		85.71 52	85.33 58	86.84 47	91.34 78	72.50 36	89.07 106	87.28 230	76.41 74	85.80 49	90.22 136	74.15 31	95.37 74	81.82 77	91.88 79	92.65 113

ZD-MVS					94.38 25	72.22 44		92.67 62	70.98 184	87.75 32	94.07 41	74.01 32	96.70 27	84.66 47	94.84 44

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 69	72.96 25	93.73 5	93.67 20	80.19 12	88.10 25	94.80 17	73.76 33	97.11 15	87.51 31	95.82 21	94.90 13
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		87.44 23	87.52 23	87.19 42	94.24 32	72.39 39	91.86 41	92.83 56	73.01 152	88.58 21	94.52 21	73.36 34	96.49 36	84.26 52	95.01 37	92.70 109
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
casdiffmvs_mvg		85.99 44	86.09 46	85.70 67	87.65 201	67.22 151	88.69 121	93.04 38	79.64 18	85.33 54	92.54 83	73.30 35	94.50 108	83.49 59	91.14 90	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
sasdasda		85.91 47	85.87 49	86.04 60	89.84 112	69.44 95	90.45 66	93.00 43	76.70 69	88.01 28	91.23 110	73.28 36	93.91 132	81.50 79	88.80 121	94.77 22

canonicalmvs		85.91 47	85.87 49	86.04 60	89.84 112	69.44 95	90.45 66	93.00 43	76.70 69	88.01 28	91.23 110	73.28 36	93.91 132	81.50 79	88.80 121	94.77 22

segment_acmp												73.08 38

DPM-MVS		84.93 65	84.29 72	86.84 47	90.20 100	73.04 23	87.12 170	93.04 38	69.80 210	82.85 98	91.22 112	73.06 39	96.02 47	76.72 128	94.63 48	91.46 154

NCCC		88.06 15	88.01 19	88.24 11	94.41 22	73.62 11	91.22 52	92.83 56	81.50 5	85.79 50	93.47 60	73.02 40	97.00 18	84.90 42	94.94 39	94.10 47

test_fmvsmconf_n		85.92 46	86.04 47	85.57 69	85.03 255	69.51 90	89.62 87	90.58 133	73.42 141	87.75 32	94.02 44	72.85 41	93.24 163	90.37 3	90.75 94	93.96 53

MGCFI-Net		85.06 64	85.51 54	83.70 143	89.42 126	63.01 239	89.43 91	92.62 67	76.43 73	87.53 35	91.34 108	72.82 42	93.42 158	81.28 82	88.74 124	94.66 27

nrg030		83.88 73	83.53 77	84.96 87	86.77 225	69.28 99	90.46 65	92.67 62	74.79 108	82.95 95	91.33 109	72.70 43	93.09 177	80.79 89	79.28 253	92.50 118

CDPH-MVS		85.76 51	85.29 61	87.17 43	93.49 47	71.08 61	88.58 125	92.42 74	68.32 246	84.61 69	93.48 58	72.32 44	96.15 45	79.00 101	95.43 31	94.28 42

MP-MVS		87.71 20	87.64 22	87.93 21	94.36 26	73.88 6	92.71 22	92.65 65	77.57 41	83.84 84	94.40 30	72.24 45	96.28 40	85.65 38	95.30 35	93.62 74
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
casdiffmvs		85.11 62	85.14 62	85.01 85	87.20 217	65.77 181	87.75 154	92.83 56	77.84 37	84.36 75	92.38 85	72.15 46	93.93 131	81.27 83	90.48 97	95.33 4
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 32	86.88 34	87.69 33	91.16 80	72.32 43	90.31 69	93.94 14	77.12 55	82.82 99	94.23 35	72.13 47	97.09 16	84.83 45	95.37 32	93.65 71
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_l_conf0.5_n		84.47 69	84.54 68	84.27 115	85.42 245	68.81 106	88.49 127	87.26 231	68.08 248	88.03 27	93.49 57	72.04 48	91.77 221	88.90 17	89.14 117	92.24 129

baseline		84.93 65	84.98 63	84.80 95	87.30 215	65.39 189	87.30 166	92.88 53	77.62 39	84.04 81	92.26 87	71.81 49	93.96 125	81.31 81	90.30 100	95.03 8

ZNCC-MVS		87.94 19	87.85 20	88.20 12	94.39 24	73.33 19	93.03 14	93.81 17	76.81 63	85.24 55	94.32 31	71.76 50	96.93 19	85.53 39	95.79 22	94.32 40

test_fmvsmconf0.1_n		85.61 54	85.65 52	85.50 70	82.99 300	69.39 97	89.65 84	90.29 146	73.31 144	87.77 31	94.15 38	71.72 51	93.23 164	90.31 4	90.67 96	93.89 58

MM		89.16 6	89.23 7	88.97 4	90.79 90	73.65 10	92.66 23	91.17 118	86.57 1	87.39 37	94.97 16	71.70 52	97.68 1	92.19 1	95.63 28	95.57 1

test12				86.80 49	92.63 64	70.70 72		91.79 101		82.71 101		71.67 53	96.16 44		94.50 51	93.54 79

UniMVSNet_NR-MVSNet		81.88 108	81.54 108	82.92 174	88.46 167	63.46 229	87.13 169	92.37 75	80.19 12	78.38 158	89.14 161	71.66 54	93.05 179	70.05 188	76.46 283	92.25 127

CS-MVS		86.69 35	86.95 31	85.90 64	90.76 91	67.57 140	92.83 17	93.30 32	79.67 17	84.57 71	92.27 86	71.47 55	95.02 88	84.24 54	93.46 64	95.13 6

DeepC-MVS_fast	79.65 3	86.91 33	86.62 36	87.76 27	93.52 46	72.37 41	91.26 48	93.04 38	76.62 71	84.22 76	93.36 63	71.44 56	96.76 25	80.82 87	95.33 34	94.16 45
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 60	85.34 57	85.13 81	86.12 235	69.93 83	88.65 123	90.78 129	69.97 206	88.27 23	93.98 49	71.39 57	91.54 231	88.49 23	90.45 98	93.91 55

MVS_111021_HR		85.14 61	84.75 66	86.32 55	91.65 76	72.70 30	85.98 204	90.33 143	76.11 83	82.08 105	91.61 100	71.36 58	94.17 121	81.02 84	92.58 71	92.08 135

ACMMP_NAP		88.05 17	88.08 17	87.94 19	93.70 41	73.05 22	90.86 56	93.59 23	76.27 81	88.14 24	95.09 15	71.06 59	96.67 29	87.67 29	96.37 14	94.09 48

fmvsm_l_conf0.5_n_a		84.13 71	84.16 73	84.06 127	85.38 246	68.40 121	88.34 134	86.85 240	67.48 255	87.48 36	93.40 61	70.89 60	91.61 225	88.38 25	89.22 116	92.16 133

MP-MVS-pluss		87.67 21	87.72 21	87.54 36	93.64 44	72.04 48	89.80 79	93.50 25	75.17 102	86.34 46	95.29 12	70.86 61	96.00 49	88.78 19	96.04 16	94.58 29
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		87.58 22	87.47 24	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 65	84.91 61	94.44 28	70.78 62	96.61 32	84.53 49	94.89 41	93.66 67

EI-MVSNet-Vis-set		84.19 70	83.81 75	85.31 74	88.18 176	67.85 134	87.66 156	89.73 161	80.05 14	82.95 95	89.59 150	70.74 63	94.82 97	80.66 91	84.72 174	93.28 90

GST-MVS		87.42 25	87.26 25	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 61	84.68 65	93.99 48	70.67 64	96.82 22	84.18 56	95.01 37	93.90 57

CS-MVS-test		86.29 42	86.48 37	85.71 66	91.02 83	67.21 152	92.36 29	93.78 18	78.97 28	83.51 90	91.20 113	70.65 65	95.15 79	81.96 76	94.89 41	94.77 22

CANet		86.45 38	86.10 45	87.51 37	90.09 102	70.94 67	89.70 83	92.59 68	81.78 4	81.32 116	91.43 106	70.34 66	97.23 13	84.26 52	93.36 65	94.37 37

alignmvs		85.48 55	85.32 59	85.96 63	89.51 121	69.47 92	89.74 81	92.47 70	76.17 82	87.73 34	91.46 105	70.32 67	93.78 138	81.51 78	88.95 118	94.63 28

EI-MVSNet-UG-set		83.81 74	83.38 80	85.09 82	87.87 189	67.53 141	87.44 162	89.66 162	79.74 16	82.23 104	89.41 159	70.24 68	94.74 100	79.95 95	83.92 188	92.99 104

MVS_Test		83.15 90	83.06 85	83.41 152	86.86 221	63.21 235	86.11 202	92.00 89	74.31 118	82.87 97	89.44 158	70.03 69	93.21 166	77.39 119	88.50 129	93.81 62

FC-MVSNet-test		81.52 119	82.02 102	80.03 242	88.42 170	55.97 328	87.95 147	93.42 29	77.10 56	77.38 180	90.98 124	69.96 70	91.79 220	68.46 207	84.50 177	92.33 123

MVS_0304		88.08 14	88.08 17	88.08 14	89.67 115	72.04 48	92.26 33	89.26 175	84.19 2	85.01 57	95.18 13	69.93 71	97.20 14	91.63 2	95.60 29	94.99 9

FIs		82.07 105	82.42 93	81.04 221	88.80 154	58.34 290	88.26 137	93.49 26	76.93 60	78.47 157	91.04 119	69.92 72	92.34 202	69.87 192	84.97 171	92.44 122

UniMVSNet (Re)		81.60 118	81.11 113	83.09 165	88.38 171	64.41 210	87.60 157	93.02 42	78.42 32	78.56 154	88.16 192	69.78 73	93.26 162	69.58 195	76.49 282	91.60 144

HPM-MVS		87.11 30	86.98 30	87.50 38	93.88 39	72.16 45	92.19 34	93.33 31	76.07 84	83.81 85	93.95 51	69.77 74	96.01 48	85.15 40	94.66 47	94.32 40
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
Effi-MVS+		83.62 81	83.08 84	85.24 76	88.38 171	67.45 142	88.89 111	89.15 181	75.50 94	82.27 103	88.28 188	69.61 75	94.45 110	77.81 114	87.84 133	93.84 61

PHI-MVS		86.43 39	86.17 43	87.24 41	90.88 87	70.96 65	92.27 32	94.07 9	72.45 155	85.22 56	91.90 92	69.47 76	96.42 37	83.28 62	95.94 19	94.35 38

UA-Net		85.08 63	84.96 64	85.45 71	92.07 70	68.07 130	89.78 80	90.86 128	82.48 3	84.60 70	93.20 66	69.35 77	95.22 76	71.39 176	90.88 93	93.07 99

ETV-MVS		84.90 67	84.67 67	85.59 68	89.39 129	68.66 117	88.74 119	92.64 66	79.97 15	84.10 79	85.71 256	69.32 78	95.38 71	80.82 87	91.37 87	92.72 108

旧先验1					91.96 71	65.79 180		86.37 247			93.08 71	69.31 79			92.74 69	88.74 258

fmvsm_s_conf0.5_n_a		83.63 80	83.41 79	84.28 113	86.14 234	68.12 128	89.43 91	82.87 300	70.27 200	87.27 39	93.80 54	69.09 80	91.58 227	88.21 26	83.65 196	93.14 97

region2R		87.42 25	87.20 28	88.09 13	94.63 14	73.55 13	93.03 14	93.12 37	76.73 68	84.45 72	94.52 21	69.09 80	96.70 27	84.37 51	94.83 45	94.03 51

EIA-MVS		83.31 89	82.80 91	84.82 93	89.59 117	65.59 183	88.21 138	92.68 61	74.66 111	78.96 143	86.42 243	69.06 82	95.26 75	75.54 140	90.09 104	93.62 74

EPP-MVSNet		83.40 86	83.02 86	84.57 99	90.13 101	64.47 208	92.32 30	90.73 130	74.45 117	79.35 139	91.10 116	69.05 83	95.12 80	72.78 165	87.22 141	94.13 46

EC-MVSNet		86.01 43	86.38 38	84.91 91	89.31 134	66.27 166	92.32 30	93.63 21	79.37 20	84.17 78	91.88 93	69.04 84	95.43 67	83.93 57	93.77 62	93.01 103

fmvsm_s_conf0.5_n		83.80 75	83.71 76	84.07 125	86.69 227	67.31 147	89.46 90	83.07 295	71.09 181	86.96 43	93.70 55	69.02 85	91.47 236	88.79 18	84.62 176	93.44 84

ACMMPR		87.44 23	87.23 27	88.08 14	94.64 13	73.59 12	93.04 12	93.20 34	76.78 65	84.66 68	94.52 21	68.81 86	96.65 30	84.53 49	94.90 40	94.00 52

test_fmvsmvis_n_1920		84.02 72	83.87 74	84.49 104	84.12 271	69.37 98	88.15 142	87.96 214	70.01 204	83.95 82	93.23 65	68.80 87	91.51 234	88.61 20	89.96 107	92.57 114

mvs_anonymous		79.42 169	79.11 157	80.34 236	84.45 266	57.97 296	82.59 275	87.62 223	67.40 256	76.17 214	88.56 180	68.47 88	89.59 274	70.65 183	86.05 160	93.47 81

fmvsm_s_conf0.1_n		83.56 82	83.38 80	84.10 120	84.86 257	67.28 148	89.40 95	83.01 296	70.67 189	87.08 40	93.96 50	68.38 89	91.45 237	88.56 22	84.50 177	93.56 77

fmvsm_s_conf0.1_n_a		83.32 88	82.99 87	84.28 113	83.79 278	68.07 130	89.34 97	82.85 301	69.80 210	87.36 38	94.06 42	68.34 90	91.56 229	87.95 27	83.46 202	93.21 94

MTAPA		87.23 28	87.00 29	87.90 22	94.18 35	74.25 5	86.58 188	92.02 87	79.45 19	85.88 48	94.80 17	68.07 91	96.21 42	86.69 36	95.34 33	93.23 91

CP-MVS		87.11 30	86.92 32	87.68 34	94.20 34	73.86 7	93.98 3	92.82 59	76.62 71	83.68 86	94.46 25	67.93 92	95.95 52	84.20 55	94.39 54	93.23 91

PAPM_NR		83.02 94	82.41 94	84.82 93	92.47 67	66.37 164	87.93 149	91.80 100	73.82 129	77.32 182	90.66 127	67.90 93	94.90 93	70.37 185	89.48 113	93.19 95

PGM-MVS		86.68 36	86.27 40	87.90 22	94.22 33	73.38 18	90.22 71	93.04 38	75.53 93	83.86 83	94.42 29	67.87 94	96.64 31	82.70 72	94.57 50	93.66 67

PAPR		81.66 116	80.89 118	83.99 135	90.27 98	64.00 216	86.76 184	91.77 103	68.84 237	77.13 191	89.50 151	67.63 95	94.88 95	67.55 213	88.52 128	93.09 98

Fast-Effi-MVS+		80.81 132	79.92 135	83.47 148	88.85 149	64.51 205	85.53 219	89.39 169	70.79 186	78.49 156	85.06 274	67.54 96	93.58 146	67.03 221	86.58 150	92.32 124

XVS		87.18 29	86.91 33	88.00 17	94.42 20	73.33 19	92.78 18	92.99 46	79.14 21	83.67 87	94.17 36	67.45 97	96.60 33	83.06 63	94.50 51	94.07 49

X-MVStestdata		80.37 148	77.83 185	88.00 17	94.42 20	73.33 19	92.78 18	92.99 46	79.14 21	83.67 87	12.47 405	67.45 97	96.60 33	83.06 63	94.50 51	94.07 49

SR-MVS		86.73 34	86.67 35	86.91 46	94.11 37	72.11 47	92.37 28	92.56 69	74.50 114	86.84 44	94.65 20	67.31 99	95.77 55	84.80 46	92.85 68	92.84 107

NR-MVSNet		80.23 151	79.38 147	82.78 183	87.80 193	63.34 232	86.31 195	91.09 122	79.01 26	72.17 278	89.07 163	67.20 100	92.81 188	66.08 227	75.65 296	92.20 130

MSLP-MVS++		85.43 57	85.76 51	84.45 105	91.93 72	70.24 76	90.71 58	92.86 54	77.46 47	84.22 76	92.81 78	67.16 101	92.94 183	80.36 92	94.35 56	90.16 199

MG-MVS		83.41 85	83.45 78	83.28 155	92.74 62	62.28 250	88.17 140	89.50 166	75.22 98	81.49 115	92.74 82	66.75 102	95.11 82	72.85 164	91.58 84	92.45 121

test_fmvsmconf0.01_n		84.73 68	84.52 70	85.34 73	80.25 340	69.03 100	89.47 89	89.65 163	73.24 148	86.98 42	94.27 32	66.62 103	93.23 164	90.26 5	89.95 108	93.78 64

EI-MVSNet		80.52 144	79.98 134	82.12 193	84.28 267	63.19 237	86.41 192	88.95 191	74.18 122	78.69 149	87.54 208	66.62 103	92.43 196	72.57 168	80.57 237	90.74 177

IterMVS-LS		80.06 154	79.38 147	82.11 194	85.89 237	63.20 236	86.79 181	89.34 170	74.19 121	75.45 227	86.72 228	66.62 103	92.39 198	72.58 167	76.86 277	90.75 176
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		78.59 191	77.76 190	81.08 220	82.66 307	61.56 259	83.65 257	89.15 181	68.87 236	75.55 223	83.79 297	66.49 106	92.03 211	73.25 160	76.39 285	89.64 226

mPP-MVS		86.67 37	86.32 39	87.72 30	94.41 22	73.55 13	92.74 20	92.22 82	76.87 62	82.81 100	94.25 34	66.44 107	96.24 41	82.88 67	94.28 57	93.38 85

c3_l		78.75 185	77.91 182	81.26 214	82.89 302	61.56 259	84.09 252	89.13 183	69.97 206	75.56 222	84.29 286	66.36 108	92.09 210	73.47 157	75.48 300	90.12 202

GeoE		81.71 112	81.01 116	83.80 141	89.51 121	64.45 209	88.97 108	88.73 201	71.27 177	78.63 152	89.76 144	66.32 109	93.20 169	69.89 191	86.02 161	93.74 65

WR-MVS_H		78.51 192	78.49 168	78.56 269	88.02 185	56.38 322	88.43 128	92.67 62	77.14 54	73.89 258	87.55 207	66.25 110	89.24 280	58.92 288	73.55 326	90.06 209

PCF-MVS	73.52 7	80.38 146	78.84 162	85.01 85	87.71 198	68.99 103	83.65 257	91.46 113	63.00 306	77.77 174	90.28 133	66.10 111	95.09 86	61.40 268	88.22 132	90.94 170
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EPNet		83.72 77	82.92 89	86.14 59	84.22 269	69.48 91	91.05 55	85.27 261	81.30 6	76.83 193	91.65 97	66.09 112	95.56 60	76.00 134	93.85 61	93.38 85
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM1				84.35 109	93.01 57	68.79 107		92.44 71	63.96 299	81.09 121	91.57 101	66.06 113	95.45 65	67.19 218	94.82 46	88.81 254

PVSNet_BlendedMVS		80.60 141	80.02 133	82.36 192	88.85 149	65.40 187	86.16 201	92.00 89	69.34 221	78.11 166	86.09 251	66.02 114	94.27 114	71.52 173	82.06 219	87.39 282

PVSNet_Blended		80.98 127	80.34 128	82.90 175	88.85 149	65.40 187	84.43 244	92.00 89	67.62 252	78.11 166	85.05 275	66.02 114	94.27 114	71.52 173	89.50 112	89.01 244

diffmvs		82.10 103	81.88 105	82.76 185	83.00 298	63.78 221	83.68 256	89.76 159	72.94 153	82.02 106	89.85 142	65.96 116	90.79 255	82.38 74	87.30 140	93.71 66
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 45	85.88 48	86.22 57	92.69 63	69.53 89	91.93 38	92.99 46	73.54 138	85.94 47	94.51 24	65.80 117	95.61 59	83.04 65	92.51 72	93.53 80

miper_enhance_ethall		77.87 210	76.86 209	80.92 225	81.65 321	61.38 261	82.68 274	88.98 188	65.52 279	75.47 224	82.30 320	65.76 118	92.00 213	72.95 163	76.39 285	89.39 232

PVSNet_Blended_VisFu		82.62 98	81.83 106	84.96 87	90.80 89	69.76 87	88.74 119	91.70 104	69.39 219	78.96 143	88.46 183	65.47 119	94.87 96	74.42 147	88.57 126	90.24 197

API-MVS		81.99 107	81.23 111	84.26 116	90.94 85	70.18 82	91.10 53	89.32 171	71.51 173	78.66 151	88.28 188	65.26 120	95.10 85	64.74 238	91.23 89	87.51 280

TranMVSNet+NR-MVSNet		80.84 130	80.31 129	82.42 190	87.85 190	62.33 248	87.74 155	91.33 114	80.55 9	77.99 170	89.86 141	65.23 121	92.62 189	67.05 220	75.24 310	92.30 125

IS-MVSNet		83.15 90	82.81 90	84.18 118	89.94 110	63.30 233	91.59 43	88.46 206	79.04 25	79.49 137	92.16 88	65.10 122	94.28 113	67.71 211	91.86 82	94.95 10

DU-MVS		81.12 126	80.52 124	82.90 175	87.80 193	63.46 229	87.02 173	91.87 97	79.01 26	78.38 158	89.07 163	65.02 123	93.05 179	70.05 188	76.46 283	92.20 130

Baseline_NR-MVSNet		78.15 201	78.33 174	77.61 286	85.79 238	56.21 326	86.78 182	85.76 256	73.60 136	77.93 171	87.57 205	65.02 123	88.99 284	67.14 219	75.33 307	87.63 276

SR-MVS-dyc-post		85.77 50	85.61 53	86.23 56	93.06 55	70.63 73	91.88 39	92.27 78	73.53 139	85.69 51	94.45 26	65.00 125	95.56 60	82.75 68	91.87 80	92.50 118

VNet		82.21 102	82.41 94	81.62 203	90.82 88	60.93 264	84.47 240	89.78 158	76.36 79	84.07 80	91.88 93	64.71 126	90.26 261	70.68 182	88.89 119	93.66 67

Test By Simon												64.33 127

ACMMP		85.89 49	85.39 56	87.38 39	93.59 45	72.63 33	92.74 20	93.18 36	76.78 65	80.73 125	93.82 53	64.33 127	96.29 39	82.67 73	90.69 95	93.23 91
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
DP-MVS Recon		83.11 93	82.09 100	86.15 58	94.44 19	70.92 68	88.79 115	92.20 83	70.53 194	79.17 141	91.03 121	64.12 129	96.03 46	68.39 208	90.14 103	91.50 150

CLD-MVS		82.31 101	81.65 107	84.29 112	88.47 166	67.73 137	85.81 212	92.35 76	75.78 88	78.33 160	86.58 238	64.01 130	94.35 111	76.05 133	87.48 138	90.79 173
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 55		93.06 55	70.63 73	91.88 39	92.27 78	73.53 139	85.69 51	94.45 26	63.87 131		82.75 68	91.87 80	92.50 118

MVS		78.19 200	76.99 207	81.78 200	85.66 240	66.99 154	84.66 234	90.47 137	55.08 366	72.02 280	85.27 267	63.83 132	94.11 123	66.10 226	89.80 110	84.24 337

WR-MVS		79.49 165	79.22 154	80.27 238	88.79 155	58.35 289	85.06 226	88.61 204	78.56 30	77.65 175	88.34 186	63.81 133	90.66 258	64.98 236	77.22 272	91.80 142

VPA-MVSNet		80.60 141	80.55 123	80.76 228	88.07 183	60.80 267	86.86 178	91.58 107	75.67 92	80.24 129	89.45 157	63.34 134	90.25 262	70.51 184	79.22 254	91.23 159

新几何1				83.42 150	93.13 52	70.71 71		85.48 259	57.43 356	81.80 111	91.98 90	63.28 135	92.27 204	64.60 239	92.99 66	87.27 286

HY-MVS	69.67 12	77.95 207	77.15 203	80.36 235	87.57 207	60.21 277	83.37 264	87.78 221	66.11 270	75.37 230	87.06 223	63.27 136	90.48 260	61.38 269	82.43 215	90.40 191

XXY-MVS		75.41 253	75.56 231	74.96 311	83.59 282	57.82 300	80.59 302	83.87 281	66.54 267	74.93 247	88.31 187	63.24 137	80.09 353	62.16 260	76.85 278	86.97 295

ab-mvs		79.51 164	78.97 160	81.14 218	88.46 167	60.91 265	83.84 254	89.24 177	70.36 196	79.03 142	88.87 170	63.23 138	90.21 263	65.12 234	82.57 214	92.28 126

xiu_mvs_v2_base		81.69 113	81.05 114	83.60 145	89.15 141	68.03 132	84.46 242	90.02 152	70.67 189	81.30 119	86.53 241	63.17 139	94.19 120	75.60 139	88.54 127	88.57 262

pcd_1.5k_mvsjas		5.26 379	7.02 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	63.15 140	0.00 412	0.00 411	0.00 410	0.00 408

PS-MVSNAJss		82.07 105	81.31 109	84.34 110	86.51 230	67.27 149	89.27 98	91.51 109	71.75 164	79.37 138	90.22 136	63.15 140	94.27 114	77.69 115	82.36 216	91.49 151

PS-MVSNAJ		81.69 113	81.02 115	83.70 143	89.51 121	68.21 127	84.28 248	90.09 151	70.79 186	81.26 120	85.62 261	63.15 140	94.29 112	75.62 138	88.87 120	88.59 261

WTY-MVS		75.65 248	75.68 228	75.57 305	86.40 231	56.82 313	77.92 337	82.40 305	65.10 281	76.18 212	87.72 200	63.13 143	80.90 350	60.31 276	81.96 220	89.00 246

TransMVSNet (Re)		75.39 254	74.56 246	77.86 280	85.50 244	57.10 310	86.78 182	86.09 252	72.17 161	71.53 284	87.34 211	63.01 144	89.31 279	56.84 309	61.83 371	87.17 288

v8		79.97 158	79.02 159	82.80 180	84.09 272	64.50 207	87.96 146	90.29 146	74.13 124	75.24 238	86.81 225	62.88 145	93.89 135	74.39 148	75.40 305	90.00 211

HPM-MVS_fast		85.35 59	84.95 65	86.57 53	93.69 42	70.58 75	92.15 36	91.62 105	73.89 128	82.67 102	94.09 40	62.60 146	95.54 62	80.93 85	92.93 67	93.57 76

PAPM		77.68 216	76.40 222	81.51 206	87.29 216	61.85 255	83.78 255	89.59 164	64.74 286	71.23 286	88.70 173	62.59 147	93.66 145	52.66 328	87.03 144	89.01 244

1112_ss		77.40 221	76.43 221	80.32 237	89.11 146	60.41 274	83.65 257	87.72 222	62.13 319	73.05 267	86.72 228	62.58 148	89.97 267	62.11 262	80.80 233	90.59 183

LCM-MVSNet-Re		77.05 225	76.94 208	77.36 289	87.20 217	51.60 365	80.06 309	80.46 325	75.20 99	67.69 321	86.72 228	62.48 149	88.98 285	63.44 246	89.25 115	91.51 148

v148		78.72 187	77.80 187	81.47 207	82.73 305	61.96 254	86.30 196	88.08 211	73.26 146	76.18 212	85.47 264	62.46 150	92.36 200	71.92 172	73.82 324	90.09 205

baseline1		76.98 227	76.75 215	77.66 284	88.13 179	55.66 332	85.12 225	81.89 309	73.04 151	76.79 194	88.90 168	62.43 151	87.78 302	63.30 248	71.18 343	89.55 229

MAR-MVS		81.84 109	80.70 120	85.27 75	91.32 79	71.53 54	89.82 77	90.92 124	69.77 212	78.50 155	86.21 247	62.36 152	94.52 107	65.36 232	92.05 78	89.77 223
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 99	82.11 99	84.11 119	88.82 152	71.58 53	85.15 224	86.16 250	74.69 110	80.47 127	91.04 119	62.29 153	90.55 259	80.33 93	90.08 105	90.20 198

TAMVS		78.89 184	77.51 197	83.03 169	87.80 193	67.79 136	84.72 233	85.05 264	67.63 251	76.75 196	87.70 201	62.25 154	90.82 254	58.53 293	87.13 142	90.49 187

CP-MVSNet		78.22 197	78.34 173	77.84 281	87.83 192	54.54 344	87.94 148	91.17 118	77.65 38	73.48 262	88.49 182	62.24 155	88.43 294	62.19 259	74.07 319	90.55 184

OMC-MVS		82.69 97	81.97 104	84.85 92	88.75 157	67.42 143	87.98 145	90.87 127	74.92 105	79.72 134	91.65 97	62.19 156	93.96 125	75.26 142	86.42 153	93.16 96

cl____		77.72 213	76.76 213	80.58 231	82.49 311	60.48 272	83.09 269	87.87 217	69.22 225	74.38 255	85.22 270	62.10 157	91.53 232	71.09 178	75.41 304	89.73 225

DIV-MVS_self_test		77.72 213	76.76 213	80.58 231	82.48 312	60.48 272	83.09 269	87.86 218	69.22 225	74.38 255	85.24 268	62.10 157	91.53 232	71.09 178	75.40 305	89.74 224

testdata				79.97 243	90.90 86	64.21 213		84.71 267	59.27 340	85.40 53	92.91 73	62.02 159	89.08 283	68.95 201	91.37 87	86.63 303

eth_miper_zixun_eth		77.92 208	76.69 216	81.61 205	83.00 298	61.98 253	83.15 267	89.20 179	69.52 218	74.86 248	84.35 285	61.76 160	92.56 192	71.50 175	72.89 332	90.28 196

MVSFormer		82.85 96	82.05 101	85.24 76	87.35 209	70.21 77	90.50 62	90.38 139	68.55 241	81.32 116	89.47 153	61.68 161	93.46 155	78.98 102	90.26 101	92.05 136

lupinMVS		81.39 122	80.27 131	84.76 96	87.35 209	70.21 77	85.55 217	86.41 245	62.85 309	81.32 116	88.61 177	61.68 161	92.24 206	78.41 109	90.26 101	91.83 140

cdsmvs_eth3d_5k		19.96 373	26.61 375	0.00 393	0.00 416	0.00 418	0.00 404	89.26 175	0.00 411	0.00 412	88.61 177	61.62 163	0.00 412	0.00 411	0.00 410	0.00 408

h-mvs33		83.15 90	82.19 98	86.02 62	90.56 93	70.85 70	88.15 142	89.16 180	76.02 85	84.67 66	91.39 107	61.54 164	95.50 63	82.71 70	75.48 300	91.72 143

hse-mvs2		81.72 111	80.94 117	84.07 125	88.72 158	67.68 138	85.87 208	87.26 231	76.02 85	84.67 66	88.22 191	61.54 164	93.48 153	82.71 70	73.44 328	91.06 164

CDS-MVSNet		79.07 179	77.70 192	83.17 162	87.60 203	68.23 126	84.40 246	86.20 249	67.49 254	76.36 207	86.54 240	61.54 164	90.79 255	61.86 264	87.33 139	90.49 187
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v10		79.74 160	78.67 164	82.97 173	84.06 273	64.95 197	87.88 152	90.62 132	73.11 149	75.11 242	86.56 239	61.46 167	94.05 124	73.68 153	75.55 298	89.90 217

v1144		80.03 155	79.03 158	83.01 170	83.78 279	64.51 205	87.11 171	90.57 135	71.96 163	78.08 168	86.20 248	61.41 168	93.94 128	74.93 143	77.23 271	90.60 182

cl22		78.07 203	77.01 205	81.23 215	82.37 314	61.83 256	83.55 261	87.98 213	68.96 235	75.06 244	83.87 293	61.40 169	91.88 218	73.53 155	76.39 285	89.98 214

BH-w/o		78.21 198	77.33 201	80.84 226	88.81 153	65.13 194	84.87 230	87.85 219	69.75 214	74.52 253	84.74 279	61.34 170	93.11 176	58.24 296	85.84 164	84.27 336

Test_1112_low_res		76.40 238	75.44 233	79.27 257	89.28 136	58.09 292	81.69 284	87.07 235	59.53 338	72.48 274	86.67 233	61.30 171	89.33 278	60.81 274	80.15 242	90.41 190

Vis-MVSNet (Re-imp)		78.36 195	78.45 169	78.07 279	88.64 161	51.78 364	86.70 185	79.63 335	74.14 123	75.11 242	90.83 125	61.29 172	89.75 271	58.10 297	91.60 83	92.69 111

PEN-MVS		77.73 212	77.69 193	77.84 281	87.07 220	53.91 349	87.91 150	91.18 117	77.56 43	73.14 266	88.82 171	61.23 173	89.17 281	59.95 278	72.37 334	90.43 189

pm-mvs1		77.25 224	76.68 217	78.93 263	84.22 269	58.62 288	86.41 192	88.36 207	71.37 175	73.31 263	88.01 198	61.22 174	89.15 282	64.24 242	73.01 331	89.03 243

BH-untuned		79.47 166	78.60 166	82.05 195	89.19 140	65.91 175	86.07 203	88.52 205	72.18 160	75.42 228	87.69 202	61.15 175	93.54 150	60.38 275	86.83 147	86.70 301

v2v482		80.23 151	79.29 151	83.05 168	83.62 281	64.14 214	87.04 172	89.97 154	73.61 135	78.18 165	87.22 216	61.10 176	93.82 136	76.11 131	76.78 280	91.18 160

jason		81.39 122	80.29 130	84.70 97	86.63 229	69.90 85	85.95 205	86.77 241	63.24 302	81.07 122	89.47 153	61.08 177	92.15 208	78.33 110	90.07 106	92.05 136
jason: jason.
Vis-MVSNet		83.46 84	82.80 91	85.43 72	90.25 99	68.74 111	90.30 70	90.13 150	76.33 80	80.87 124	92.89 74	61.00 178	94.20 119	72.45 170	90.97 91	93.35 87
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAPA-MVS	73.13 9	79.15 176	77.94 181	82.79 182	89.59 117	62.99 243	88.16 141	91.51 109	65.77 275	77.14 190	91.09 117	60.91 179	93.21 166	50.26 343	87.05 143	92.17 132
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PS-CasMVS		78.01 206	78.09 178	77.77 283	87.71 198	54.39 346	88.02 144	91.22 115	77.50 46	73.26 264	88.64 176	60.73 180	88.41 295	61.88 263	73.88 323	90.53 185

OPM-MVS		83.50 83	82.95 88	85.14 79	88.79 155	70.95 66	89.13 105	91.52 108	77.55 44	80.96 123	91.75 95	60.71 181	94.50 108	79.67 99	86.51 152	89.97 215
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XVG-OURS-SEG-HR		80.81 132	79.76 139	83.96 137	85.60 242	68.78 108	83.54 262	90.50 136	70.66 192	76.71 197	91.66 96	60.69 182	91.26 242	76.94 123	81.58 224	91.83 140

v144192		79.47 166	78.37 172	82.78 183	83.35 286	63.96 217	86.96 174	90.36 142	69.99 205	77.50 177	85.67 259	60.66 183	93.77 140	74.27 149	76.58 281	90.62 180

V42		79.38 172	78.24 176	82.83 177	81.10 332	65.50 185	85.55 217	89.82 157	71.57 171	78.21 163	86.12 250	60.66 183	93.18 172	75.64 137	75.46 302	89.81 222

SDMVSNet		80.38 146	80.18 132	80.99 222	89.03 147	64.94 198	80.45 305	89.40 168	75.19 100	76.61 201	89.98 139	60.61 185	87.69 303	76.83 126	83.55 198	90.33 193

CPTT-MVS		83.73 76	83.33 82	84.92 90	93.28 49	70.86 69	92.09 37	90.38 139	68.75 238	79.57 136	92.83 76	60.60 186	93.04 181	80.92 86	91.56 85	90.86 172

DTE-MVSNet		76.99 226	76.80 211	77.54 288	86.24 232	53.06 357	87.52 159	90.66 131	77.08 57	72.50 273	88.67 175	60.48 187	89.52 275	57.33 304	70.74 345	90.05 210

HQP_MVS		83.64 79	83.14 83	85.14 79	90.08 103	68.71 113	91.25 50	92.44 71	79.12 23	78.92 145	91.00 122	60.42 188	95.38 71	78.71 105	86.32 154	91.33 155

plane_prior6					89.84 112	68.70 115						60.42 188

3Dnovator+	77.84 4	85.48 55	84.47 71	88.51 7	91.08 81	73.49 16	93.18 11	93.78 18	80.79 8	76.66 198	93.37 62	60.40 190	96.75 26	77.20 120	93.73 63	95.29 5

HQP2-MVS												60.17 191

HQP-MVS		82.61 99	82.02 102	84.37 107	89.33 131	66.98 155	89.17 100	92.19 84	76.41 74	77.23 185	90.23 135	60.17 191	95.11 82	77.47 117	85.99 162	91.03 166

VPNet		78.69 188	78.66 165	78.76 265	88.31 173	55.72 331	84.45 243	86.63 243	76.79 64	78.26 161	90.55 130	59.30 193	89.70 273	66.63 222	77.05 274	90.88 171

v1192		79.59 163	78.43 171	83.07 167	83.55 283	64.52 204	86.93 176	90.58 133	70.83 185	77.78 173	85.90 252	59.15 194	93.94 128	73.96 152	77.19 273	90.76 175

test222					91.50 77	68.26 125	84.16 250	83.20 293	54.63 367	79.74 133	91.63 99	58.97 195			91.42 86	86.77 299

CHOSEN 1792x2688		77.63 217	75.69 227	83.44 149	89.98 109	68.58 119	78.70 327	87.50 226	56.38 361	75.80 219	86.84 224	58.67 196	91.40 239	61.58 267	85.75 166	90.34 192

3Dnovator	76.31 5	83.38 87	82.31 97	86.59 52	87.94 187	72.94 28	90.64 59	92.14 86	77.21 52	75.47 224	92.83 76	58.56 197	94.72 101	73.24 161	92.71 70	92.13 134

v1921920		79.22 174	78.03 179	82.80 180	83.30 288	63.94 218	86.80 180	90.33 143	69.91 208	77.48 178	85.53 262	58.44 198	93.75 142	73.60 154	76.85 278	90.71 178

FA-MVS(test-final)		80.96 128	79.91 136	84.10 120	88.30 174	65.01 196	84.55 239	90.01 153	73.25 147	79.61 135	87.57 205	58.35 199	94.72 101	71.29 177	86.25 156	92.56 115

114514_t		80.68 139	79.51 144	84.20 117	94.09 38	67.27 149	89.64 85	91.11 121	58.75 346	74.08 257	90.72 126	58.10 200	95.04 87	69.70 193	89.42 114	90.30 195

v7n		78.97 182	77.58 196	83.14 163	83.45 285	65.51 184	88.32 135	91.21 116	73.69 133	72.41 275	86.32 246	57.93 201	93.81 137	69.18 198	75.65 296	90.11 203

CL-MVSNet_self_test		72.37 283	71.46 278	75.09 310	79.49 353	53.53 351	80.76 298	85.01 265	69.12 229	70.51 290	82.05 324	57.92 202	84.13 330	52.27 330	66.00 363	87.60 277

baseline2		75.70 247	73.83 257	81.30 213	83.26 289	61.79 257	82.57 276	80.65 321	66.81 257	66.88 330	83.42 304	57.86 203	92.19 207	63.47 245	79.57 247	89.91 216

QAPM		80.88 129	79.50 145	85.03 84	88.01 186	68.97 104	91.59 43	92.00 89	66.63 266	75.15 241	92.16 88	57.70 204	95.45 65	63.52 244	88.76 123	90.66 179

HyFIR lowres test		77.53 218	75.40 235	83.94 138	89.59 117	66.62 160	80.36 306	88.64 203	56.29 362	76.45 203	85.17 271	57.64 205	93.28 161	61.34 270	83.10 207	91.91 139

CNLPA		78.08 202	76.79 212	81.97 198	90.40 97	71.07 62	87.59 158	84.55 270	66.03 273	72.38 276	89.64 147	57.56 206	86.04 314	59.61 281	83.35 203	88.79 255

test_yl		81.17 124	80.47 125	83.24 158	89.13 142	63.62 222	86.21 198	89.95 155	72.43 158	81.78 112	89.61 148	57.50 207	93.58 146	70.75 180	86.90 145	92.52 116

DCV-MVSNet		81.17 124	80.47 125	83.24 158	89.13 142	63.62 222	86.21 198	89.95 155	72.43 158	81.78 112	89.61 148	57.50 207	93.58 146	70.75 180	86.90 145	92.52 116

sss		73.60 269	73.64 259	73.51 325	82.80 303	55.01 340	76.12 344	81.69 312	62.47 315	74.68 250	85.85 255	57.32 209	78.11 361	60.86 273	80.93 230	87.39 282

Effi-MVS+-dtu		80.03 155	78.57 167	84.42 106	85.13 253	68.74 111	88.77 116	88.10 210	74.99 104	74.97 246	83.49 303	57.27 210	93.36 159	73.53 155	80.88 231	91.18 160

AdaColmap		80.58 143	79.42 146	84.06 127	93.09 54	68.91 105	89.36 96	88.97 190	69.27 222	75.70 220	89.69 145	57.20 211	95.77 55	63.06 249	88.41 130	87.50 281

v1240		78.99 181	77.78 188	82.64 186	83.21 290	63.54 226	86.62 187	90.30 145	69.74 216	77.33 181	85.68 258	57.04 212	93.76 141	73.13 162	76.92 275	90.62 180

miper_lstm_enhance		74.11 263	73.11 264	77.13 293	80.11 342	59.62 282	72.23 364	86.92 239	66.76 259	70.40 292	82.92 311	56.93 213	82.92 339	69.06 200	72.63 333	88.87 251

BH-RMVSNet		79.61 161	78.44 170	83.14 163	89.38 130	65.93 174	84.95 229	87.15 234	73.56 137	78.19 164	89.79 143	56.67 214	93.36 159	59.53 282	86.74 148	90.13 201

test_djsdf		80.30 150	79.32 150	83.27 156	83.98 275	65.37 190	90.50 62	90.38 139	68.55 241	76.19 211	88.70 173	56.44 215	93.46 155	78.98 102	80.14 243	90.97 169

EPNet_dtu		75.46 251	74.86 242	77.23 292	82.57 309	54.60 343	86.89 177	83.09 294	71.64 165	66.25 341	85.86 254	55.99 216	88.04 299	54.92 317	86.55 151	89.05 242
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CostFormer		75.24 255	73.90 255	79.27 257	82.65 308	58.27 291	80.80 295	82.73 303	61.57 322	75.33 235	83.13 308	55.52 217	91.07 251	64.98 236	78.34 264	88.45 263

tpmrst		72.39 281	72.13 272	73.18 329	80.54 337	49.91 374	79.91 313	79.08 340	63.11 304	71.69 283	79.95 342	55.32 218	82.77 340	65.66 231	73.89 322	86.87 296

1314		76.53 233	75.30 239	80.21 239	83.93 276	62.32 249	84.66 234	88.81 194	60.23 331	70.16 297	84.07 292	55.30 219	90.73 257	67.37 215	83.21 205	87.59 279

tfpnnormal		74.39 259	73.16 263	78.08 278	86.10 236	58.05 293	84.65 236	87.53 225	70.32 198	71.22 287	85.63 260	54.97 220	89.86 268	43.03 375	75.02 312	86.32 305

sd_testset		77.70 215	77.40 198	78.60 268	89.03 147	60.02 278	79.00 323	85.83 255	75.19 100	76.61 201	89.98 139	54.81 221	85.46 321	62.63 255	83.55 198	90.33 193

GBi-Net		78.40 193	77.40 198	81.40 210	87.60 203	63.01 239	88.39 130	89.28 172	71.63 166	75.34 231	87.28 212	54.80 222	91.11 245	62.72 251	79.57 247	90.09 205

test1		78.40 193	77.40 198	81.40 210	87.60 203	63.01 239	88.39 130	89.28 172	71.63 166	75.34 231	87.28 212	54.80 222	91.11 245	62.72 251	79.57 247	90.09 205

FMVSNet2		78.20 199	77.21 202	81.20 216	87.60 203	62.89 244	87.47 161	89.02 186	71.63 166	75.29 237	87.28 212	54.80 222	91.10 248	62.38 256	79.38 251	89.61 227

Fast-Effi-MVS+-dtu		78.02 205	76.49 219	82.62 187	83.16 294	66.96 157	86.94 175	87.45 228	72.45 155	71.49 285	84.17 290	54.79 225	91.58 227	67.61 212	80.31 240	89.30 235

MVSTER		79.01 180	77.88 184	82.38 191	83.07 295	64.80 201	84.08 253	88.95 191	69.01 234	78.69 149	87.17 219	54.70 226	92.43 196	74.69 144	80.57 237	89.89 218

OpenMVS	72.83 10	79.77 159	78.33 174	84.09 123	85.17 249	69.91 84	90.57 60	90.97 123	66.70 260	72.17 278	91.91 91	54.70 226	93.96 125	61.81 265	90.95 92	88.41 265

XVG-OURS		80.41 145	79.23 153	83.97 136	85.64 241	69.02 102	83.03 273	90.39 138	71.09 181	77.63 176	91.49 104	54.62 228	91.35 240	75.71 136	83.47 201	91.54 147

mvsmamba		81.69 113	80.74 119	84.56 100	87.45 208	66.72 159	91.26 48	85.89 254	74.66 111	78.23 162	90.56 129	54.33 229	94.91 90	80.73 90	83.54 200	92.04 138

LPG-MVS_test		82.08 104	81.27 110	84.50 102	89.23 138	68.76 109	90.22 71	91.94 93	75.37 96	76.64 199	91.51 102	54.29 230	94.91 90	78.44 107	83.78 189	89.83 220

LGP-MVS_train				84.50 102	89.23 138	68.76 109		91.94 93	75.37 96	76.64 199	91.51 102	54.29 230	94.91 90	78.44 107	83.78 189	89.83 220

TR-MVS		77.44 219	76.18 224	81.20 216	88.24 175	63.24 234	84.61 237	86.40 246	67.55 253	77.81 172	86.48 242	54.10 232	93.15 173	57.75 300	82.72 212	87.20 287

FMVSNet3		77.88 209	76.85 210	80.97 224	86.84 223	62.36 247	86.52 190	88.77 196	71.13 179	75.34 231	86.66 234	54.07 233	91.10 248	62.72 251	79.57 247	89.45 231

DP-MVS		76.78 230	74.57 245	83.42 150	93.29 48	69.46 94	88.55 126	83.70 282	63.98 298	70.20 294	88.89 169	54.01 234	94.80 98	46.66 361	81.88 222	86.01 313

ACMP	74.13 6	81.51 121	80.57 122	84.36 108	89.42 126	68.69 116	89.97 75	91.50 112	74.46 116	75.04 245	90.41 132	53.82 235	94.54 105	77.56 116	82.91 208	89.86 219
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PLC	70.83 11	78.05 204	76.37 223	83.08 166	91.88 74	67.80 135	88.19 139	89.46 167	64.33 292	69.87 303	88.38 185	53.66 236	93.58 146	58.86 289	82.73 211	87.86 272
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dmvs_testset		62.63 344	64.11 335	58.19 372	78.55 358	24.76 408	75.28 351	65.94 388	67.91 250	60.34 367	76.01 369	53.56 237	73.94 387	31.79 391	67.65 356	75.88 379

CANet_DTU		80.61 140	79.87 137	82.83 177	85.60 242	63.17 238	87.36 163	88.65 202	76.37 78	75.88 217	88.44 184	53.51 238	93.07 178	73.30 159	89.74 111	92.25 127

WB-MVSnew		71.96 288	71.65 276	72.89 330	84.67 263	51.88 362	82.29 278	77.57 347	62.31 316	73.67 260	83.00 309	53.49 239	81.10 349	45.75 368	82.13 218	85.70 318

ACMM	73.20 8	80.78 137	79.84 138	83.58 146	89.31 134	68.37 122	89.99 74	91.60 106	70.28 199	77.25 183	89.66 146	53.37 240	93.53 151	74.24 150	82.85 209	88.85 252
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVP-Stereo		76.12 241	74.46 249	81.13 219	85.37 247	69.79 86	84.42 245	87.95 215	65.03 283	67.46 324	85.33 266	53.28 241	91.73 224	58.01 298	83.27 204	81.85 361
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
AUN-MVS		79.21 175	77.60 195	84.05 130	88.71 159	67.61 139	85.84 210	87.26 231	69.08 230	77.23 185	88.14 196	53.20 242	93.47 154	75.50 141	73.45 327	91.06 164

anonymousdsp		78.60 190	77.15 203	82.98 172	80.51 338	67.08 153	87.24 168	89.53 165	65.66 277	75.16 240	87.19 218	52.52 243	92.25 205	77.17 121	79.34 252	89.61 227

CR-MVSNet		73.37 271	71.27 282	79.67 251	81.32 330	65.19 192	75.92 346	80.30 328	59.92 334	72.73 270	81.19 328	52.50 244	86.69 308	59.84 279	77.71 267	87.11 292

Patchmtry		70.74 297	69.16 300	75.49 307	80.72 334	54.07 348	74.94 357	80.30 328	58.34 347	70.01 298	81.19 328	52.50 244	86.54 309	53.37 325	71.09 344	85.87 317

pmmvs4		74.03 266	71.91 273	80.39 234	81.96 317	68.32 123	81.45 288	82.14 307	59.32 339	69.87 303	85.13 272	52.40 246	88.13 298	60.21 277	74.74 315	84.73 333

RPMNet		73.51 270	70.49 290	82.58 188	81.32 330	65.19 192	75.92 346	92.27 78	57.60 354	72.73 270	76.45 367	52.30 247	95.43 67	48.14 356	77.71 267	87.11 292

LFMVS		81.82 110	81.23 111	83.57 147	91.89 73	63.43 231	89.84 76	81.85 311	77.04 58	83.21 92	93.10 67	52.26 248	93.43 157	71.98 171	89.95 108	93.85 59

VDD-MVS		83.01 95	82.36 96	84.96 87	91.02 83	66.40 163	88.91 110	88.11 209	77.57 41	84.39 74	93.29 64	52.19 249	93.91 132	77.05 122	88.70 125	94.57 31

tfpn200view9		76.42 237	75.37 237	79.55 255	89.13 142	57.65 302	85.17 222	83.60 283	73.41 142	76.45 203	86.39 244	52.12 250	91.95 214	48.33 352	83.75 192	89.07 237

thres400		76.50 234	75.37 237	79.86 245	89.13 142	57.65 302	85.17 222	83.60 283	73.41 142	76.45 203	86.39 244	52.12 250	91.95 214	48.33 352	83.75 192	90.00 211

Syy-MVS		68.05 321	67.85 312	68.67 357	84.68 260	40.97 398	78.62 328	73.08 371	66.65 264	66.74 333	79.46 346	52.11 252	82.30 342	32.89 390	76.38 288	82.75 355

thres200		75.55 249	74.47 248	78.82 264	87.78 196	57.85 299	83.07 271	83.51 286	72.44 157	75.84 218	84.42 281	52.08 253	91.75 222	47.41 359	83.64 197	86.86 297

PMMVS		69.34 310	68.67 302	71.35 342	75.67 369	62.03 252	75.17 352	73.46 369	50.00 378	68.68 313	79.05 349	52.07 254	78.13 360	61.16 271	82.77 210	73.90 381

tpm cat1		70.57 299	68.31 305	77.35 290	82.41 313	57.95 297	78.08 334	80.22 330	52.04 372	68.54 316	77.66 362	52.00 255	87.84 301	51.77 331	72.07 338	86.25 306

IterMVS-SCA-FT		75.43 252	73.87 256	80.11 241	82.69 306	64.85 200	81.57 286	83.47 287	69.16 228	70.49 291	84.15 291	51.95 256	88.15 297	69.23 197	72.14 337	87.34 284

SCA		74.22 262	72.33 271	79.91 244	84.05 274	62.17 251	79.96 312	79.29 338	66.30 269	72.38 276	80.13 340	51.95 256	88.60 292	59.25 284	77.67 269	88.96 248

thres100view900		76.50 234	75.55 232	79.33 256	89.52 120	56.99 311	85.83 211	83.23 291	73.94 126	76.32 208	87.12 220	51.89 258	91.95 214	48.33 352	83.75 192	89.07 237

thres600view7		76.50 234	75.44 233	79.68 250	89.40 128	57.16 308	85.53 219	83.23 291	73.79 131	76.26 209	87.09 221	51.89 258	91.89 217	48.05 357	83.72 195	90.00 211

tpm2		73.26 274	71.46 278	78.63 266	83.34 287	56.71 316	80.65 301	80.40 327	56.63 360	73.55 261	82.02 325	51.80 260	91.24 243	56.35 313	78.42 262	87.95 269

LS3D		76.95 228	74.82 243	83.37 153	90.45 95	67.36 146	89.15 104	86.94 238	61.87 321	69.52 306	90.61 128	51.71 261	94.53 106	46.38 364	86.71 149	88.21 267

IterMVS		74.29 260	72.94 265	78.35 274	81.53 324	63.49 228	81.58 285	82.49 304	68.06 249	69.99 300	83.69 300	51.66 262	85.54 319	65.85 229	71.64 340	86.01 313
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 283	71.71 275	74.35 318	82.19 315	52.00 359	79.22 320	77.29 351	64.56 288	72.95 268	83.68 301	51.35 263	83.26 338	58.33 295	75.80 294	87.81 273

sam_mvs1												51.32 264				88.96 248

PatchmatchNet		73.12 276	71.33 281	78.49 273	83.18 292	60.85 266	79.63 314	78.57 342	64.13 293	71.73 282	79.81 345	51.20 265	85.97 315	57.40 303	76.36 290	88.66 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
patchmatchnet-post											74.00 376	51.12 266	88.60 292

xiu_mvs_v1_base_debu		80.80 134	79.72 140	84.03 132	87.35 209	70.19 79	85.56 214	88.77 196	69.06 231	81.83 108	88.16 192	50.91 267	92.85 185	78.29 111	87.56 135	89.06 239

xiu_mvs_v1_base		80.80 134	79.72 140	84.03 132	87.35 209	70.19 79	85.56 214	88.77 196	69.06 231	81.83 108	88.16 192	50.91 267	92.85 185	78.29 111	87.56 135	89.06 239

xiu_mvs_v1_base_debi		80.80 134	79.72 140	84.03 132	87.35 209	70.19 79	85.56 214	88.77 196	69.06 231	81.83 108	88.16 192	50.91 267	92.85 185	78.29 111	87.56 135	89.06 239

Patchmatch-test		64.82 339	63.24 340	69.57 350	79.42 354	49.82 375	63.49 392	69.05 382	51.98 374	59.95 370	80.13 340	50.91 267	70.98 390	40.66 380	73.57 325	87.90 271

Patchmatch-RL test		70.24 303	67.78 316	77.61 286	77.43 362	59.57 284	71.16 367	70.33 376	62.94 308	68.65 314	72.77 379	50.62 271	85.49 320	69.58 195	66.58 360	87.77 274

Anonymous20231211		78.97 182	77.69 193	82.81 179	90.54 94	64.29 212	90.11 73	91.51 109	65.01 284	76.16 215	88.13 197	50.56 272	93.03 182	69.68 194	77.56 270	91.11 162

VDDNet		81.52 119	80.67 121	84.05 130	90.44 96	64.13 215	89.73 82	85.91 253	71.11 180	83.18 93	93.48 58	50.54 273	93.49 152	73.40 158	88.25 131	94.54 32

pmmvs6		74.69 258	73.39 260	78.61 267	81.38 327	57.48 305	86.64 186	87.95 215	64.99 285	70.18 295	86.61 235	50.43 274	89.52 275	62.12 261	70.18 347	88.83 253

test_post											5.46 406	50.36 275	84.24 329

ET-MVSNet_ETH3D		78.63 189	76.63 218	84.64 98	86.73 226	69.47 92	85.01 227	84.61 269	69.54 217	66.51 339	86.59 236	50.16 276	91.75 222	76.26 130	84.24 185	92.69 111

sam_mvs												50.01 277

Anonymous20240529		80.19 153	78.89 161	84.10 120	90.60 92	64.75 202	88.95 109	90.90 125	65.97 274	80.59 126	91.17 115	49.97 278	93.73 144	69.16 199	82.70 213	93.81 62

thisisatest0530		79.40 170	77.76 190	84.31 111	87.69 200	65.10 195	87.36 163	84.26 276	70.04 203	77.42 179	88.26 190	49.94 279	94.79 99	70.20 186	84.70 175	93.03 101

PatchT		68.46 319	67.85 312	70.29 348	80.70 335	43.93 390	72.47 363	74.88 363	60.15 332	70.55 289	76.57 366	49.94 279	81.59 345	50.58 337	74.83 314	85.34 322

tttt0517		79.40 170	77.91 182	83.90 140	88.10 181	63.84 219	88.37 133	84.05 278	71.45 174	76.78 195	89.12 162	49.93 281	94.89 94	70.18 187	83.18 206	92.96 105

tpmvs		71.09 293	69.29 298	76.49 297	82.04 316	56.04 327	78.92 325	81.37 316	64.05 296	67.18 328	78.28 357	49.74 282	89.77 270	49.67 346	72.37 334	83.67 344

thisisatest0515		77.33 222	75.38 236	83.18 161	85.27 248	63.80 220	82.11 280	83.27 290	65.06 282	75.91 216	83.84 295	49.54 283	94.27 114	67.24 217	86.19 157	91.48 152

UniMVSNet_ETH3D		79.10 178	78.24 176	81.70 202	86.85 222	60.24 276	87.28 167	88.79 195	74.25 120	76.84 192	90.53 131	49.48 284	91.56 229	67.98 209	82.15 217	93.29 89

dmvs_re		71.14 292	70.58 288	72.80 331	81.96 317	59.68 281	75.60 350	79.34 337	68.55 241	69.27 310	80.72 336	49.42 285	76.54 369	52.56 329	77.79 266	82.19 359

CVMVSNet		72.99 278	72.58 268	74.25 319	84.28 267	50.85 370	86.41 192	83.45 288	44.56 383	73.23 265	87.54 208	49.38 286	85.70 316	65.90 228	78.44 261	86.19 308

MDTV_nov1_ep13_2view						37.79 400	75.16 353		55.10 365	66.53 336		49.34 287		53.98 321		87.94 270

UGNet		80.83 131	79.59 143	84.54 101	88.04 184	68.09 129	89.42 93	88.16 208	76.95 59	76.22 210	89.46 155	49.30 288	93.94 128	68.48 206	90.31 99	91.60 144
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		71.55 289	70.20 295	75.61 304	77.83 360	56.39 321	81.74 283	80.89 317	57.76 352	67.46 324	84.49 280	49.26 289	85.32 323	57.08 306	75.29 308	85.11 328

mvsany_test1		62.30 345	61.26 349	65.41 364	69.52 389	54.86 341	66.86 383	49.78 404	46.65 381	68.50 317	83.21 306	49.15 290	66.28 396	56.93 308	60.77 374	75.11 380

LTVRE_ROB	69.57 13	76.25 240	74.54 247	81.41 209	88.60 162	64.38 211	79.24 319	89.12 184	70.76 188	69.79 305	87.86 199	49.09 291	93.20 169	56.21 314	80.16 241	86.65 302
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		77.44 219	76.12 225	81.40 210	86.81 224	63.01 239	88.39 130	89.28 172	70.49 195	74.39 254	87.28 212	49.06 292	91.11 245	60.91 272	78.52 259	90.09 205

RRT_MVS		80.35 149	79.22 154	83.74 142	87.63 202	65.46 186	91.08 54	88.92 193	73.82 129	76.44 206	90.03 138	49.05 293	94.25 118	76.84 124	79.20 255	91.51 148

test1111		79.43 168	79.18 156	80.15 240	89.99 108	53.31 355	87.33 165	77.05 353	75.04 103	80.23 130	92.77 81	48.97 294	92.33 203	68.87 202	92.40 75	94.81 20

ECVR-MVS		79.61 161	79.26 152	80.67 230	90.08 103	54.69 342	87.89 151	77.44 350	74.88 106	80.27 128	92.79 79	48.96 295	92.45 195	68.55 205	92.50 73	94.86 17

MDTV_nov1_ep13			69.97 296		83.18 292	53.48 352	77.10 342	80.18 331	60.45 328	69.33 309	80.44 337	48.89 296	86.90 307	51.60 333	78.51 260

test_post1							78.90 326				5.43 407	48.81 297	85.44 322	59.25 284

test-LLR		72.94 279	72.43 269	74.48 316	81.35 328	58.04 294	78.38 330	77.46 348	66.66 261	69.95 301	79.00 351	48.06 298	79.24 355	66.13 224	84.83 172	86.15 309

test0.0.03 1		68.00 322	67.69 317	68.90 354	77.55 361	47.43 379	75.70 349	72.95 373	66.66 261	66.56 335	82.29 321	48.06 298	75.87 376	44.97 372	74.51 317	83.41 346

our_test_3		69.14 311	67.00 324	75.57 305	79.80 348	58.80 286	77.96 335	77.81 345	59.55 337	62.90 361	78.25 358	47.43 300	83.97 331	51.71 332	67.58 357	83.93 342

MS-PatchMatch		73.83 267	72.67 266	77.30 291	83.87 277	66.02 171	81.82 281	84.66 268	61.37 325	68.61 315	82.82 314	47.29 301	88.21 296	59.27 283	84.32 183	77.68 375

cascas		76.72 231	74.64 244	82.99 171	85.78 239	65.88 176	82.33 277	89.21 178	60.85 327	72.74 269	81.02 331	47.28 302	93.75 142	67.48 214	85.02 170	89.34 234

WB-MVS		54.94 352	54.72 354	55.60 378	73.50 379	20.90 410	74.27 359	61.19 395	59.16 341	50.61 388	74.15 375	47.19 303	75.78 377	17.31 402	35.07 397	70.12 385

test20.03		67.45 324	66.95 325	68.94 353	75.48 371	44.84 388	77.50 338	77.67 346	66.66 261	63.01 359	83.80 296	47.02 304	78.40 359	42.53 377	68.86 354	83.58 345

test_0402		72.79 280	70.44 291	79.84 246	88.13 179	65.99 173	85.93 206	84.29 274	65.57 278	67.40 326	85.49 263	46.92 305	92.61 190	35.88 387	74.38 318	80.94 366

F-COLMAP		76.38 239	74.33 250	82.50 189	89.28 136	66.95 158	88.41 129	89.03 185	64.05 296	66.83 331	88.61 177	46.78 306	92.89 184	57.48 301	78.55 258	87.67 275

ppachtmachnet_test		70.04 305	67.34 322	78.14 277	79.80 348	61.13 262	79.19 321	80.59 322	59.16 341	65.27 346	79.29 348	46.75 307	87.29 305	49.33 347	66.72 358	86.00 315

tt0805		78.73 186	77.83 185	81.43 208	85.17 249	60.30 275	89.41 94	90.90 125	71.21 178	77.17 189	88.73 172	46.38 308	93.21 166	72.57 168	78.96 256	90.79 173

D2MVS		74.82 257	73.21 262	79.64 252	79.81 347	62.56 246	80.34 307	87.35 229	64.37 291	68.86 312	82.66 316	46.37 309	90.10 264	67.91 210	81.24 227	86.25 306

Anonymous20231206		68.60 315	67.80 315	71.02 345	80.23 341	50.75 371	78.30 333	80.47 324	56.79 359	66.11 342	82.63 317	46.35 310	78.95 357	43.62 374	75.70 295	83.36 347

SSC-MVS		53.88 355	53.59 356	54.75 380	72.87 384	19.59 411	73.84 361	60.53 397	57.58 355	49.18 390	73.45 378	46.34 311	75.47 380	16.20 405	32.28 399	69.20 386

CHOSEN 280x420		66.51 331	64.71 332	71.90 336	81.45 325	63.52 227	57.98 395	68.95 383	53.57 368	62.59 362	76.70 365	46.22 312	75.29 382	55.25 316	79.68 246	76.88 377

testing91		76.54 232	75.66 230	79.18 260	88.43 169	55.89 329	81.08 292	83.00 297	73.76 132	75.34 231	84.29 286	46.20 313	90.07 265	64.33 240	84.50 177	91.58 146

GA-MVS		76.87 229	75.17 240	81.97 198	82.75 304	62.58 245	81.44 289	86.35 248	72.16 162	74.74 249	82.89 312	46.20 313	92.02 212	68.85 203	81.09 229	91.30 158

MDA-MVSNet_test_wron		65.03 337	62.92 341	71.37 340	75.93 366	56.73 314	69.09 379	74.73 365	57.28 357	54.03 385	77.89 359	45.88 315	74.39 385	49.89 345	61.55 372	82.99 353

YYNet1		65.03 337	62.91 342	71.38 339	75.85 368	56.60 318	69.12 378	74.66 367	57.28 357	54.12 384	77.87 360	45.85 316	74.48 384	49.95 344	61.52 373	83.05 351

EPMVS		69.02 312	68.16 307	71.59 338	79.61 351	49.80 376	77.40 339	66.93 385	62.82 311	70.01 298	79.05 349	45.79 317	77.86 363	56.58 311	75.26 309	87.13 291

IB-MVS	68.01 15	75.85 246	73.36 261	83.31 154	84.76 258	66.03 169	83.38 263	85.06 263	70.21 202	69.40 307	81.05 330	45.76 318	94.66 103	65.10 235	75.49 299	89.25 236
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		79.29 173	77.96 180	83.27 156	84.68 260	66.57 162	89.25 99	90.16 149	69.20 227	75.46 226	89.49 152	45.75 319	93.13 175	76.84 124	80.80 233	90.11 203

PatchMatch-RL		72.38 282	70.90 286	76.80 296	88.60 162	67.38 145	79.53 315	76.17 359	62.75 312	69.36 308	82.00 326	45.51 320	84.89 326	53.62 323	80.58 236	78.12 374

FE-MVS		77.78 211	75.68 228	84.08 124	88.09 182	66.00 172	83.13 268	87.79 220	68.42 245	78.01 169	85.23 269	45.50 321	95.12 80	59.11 286	85.83 165	91.11 162

RPSCF		73.23 275	71.46 278	78.54 270	82.50 310	59.85 279	82.18 279	82.84 302	58.96 343	71.15 288	89.41 159	45.48 322	84.77 327	58.82 290	71.83 339	91.02 168

test_vis1_n_1920		75.52 250	75.78 226	74.75 315	79.84 346	57.44 306	83.26 265	85.52 258	62.83 310	79.34 140	86.17 249	45.10 323	79.71 354	78.75 104	81.21 228	87.10 294

MSDG		73.36 273	70.99 285	80.49 233	84.51 265	65.80 179	80.71 300	86.13 251	65.70 276	65.46 344	83.74 298	44.60 324	90.91 253	51.13 336	76.89 276	84.74 332

PVSNet_0	57.27 20	61.67 347	59.27 350	68.85 355	79.61 351	57.44 306	68.01 380	73.44 370	55.93 363	58.54 374	70.41 384	44.58 325	77.55 364	47.01 360	35.91 396	71.55 384

testing99		76.09 243	75.12 241	79.00 261	88.16 177	55.50 334	80.79 296	81.40 315	73.30 145	75.17 239	84.27 288	44.48 326	90.02 266	64.28 241	84.22 186	91.48 152

test_cas_vis1_n_1920		73.76 268	73.74 258	73.81 323	75.90 367	59.77 280	80.51 303	82.40 305	58.30 348	81.62 114	85.69 257	44.35 327	76.41 372	76.29 129	78.61 257	85.23 324

mvs_tets		79.13 177	77.77 189	83.22 160	84.70 259	66.37 164	89.17 100	90.19 148	69.38 220	75.40 229	89.46 155	44.17 328	93.15 173	76.78 127	80.70 235	90.14 200

MDA-MVSNet-bldmvs		66.68 329	63.66 338	75.75 302	79.28 355	60.56 271	73.92 360	78.35 343	64.43 289	50.13 389	79.87 344	44.02 329	83.67 333	46.10 366	56.86 379	83.03 352

iter_conf05		80.00 157	78.70 163	83.91 139	87.84 191	65.83 177	88.84 114	84.92 266	71.61 169	78.70 148	88.94 167	43.88 330	94.56 104	79.28 100	84.28 184	91.33 155

gg-mvs-nofinetune		69.95 306	67.96 310	75.94 300	83.07 295	54.51 345	77.23 341	70.29 377	63.11 304	70.32 293	62.33 388	43.62 331	88.69 290	53.88 322	87.76 134	84.62 334

testing11		75.14 256	74.01 252	78.53 271	88.16 177	56.38 322	80.74 299	80.42 326	70.67 189	72.69 272	83.72 299	43.61 332	89.86 268	62.29 258	83.76 191	89.36 233

bld_raw_dy_0_64		80.78 137	79.36 149	85.06 83	89.46 124	66.03 169	89.63 86	85.46 260	69.76 213	81.88 107	89.06 165	43.39 333	95.70 58	79.82 97	85.74 168	93.47 81

GG-mvs-BLEND				75.38 308	81.59 323	55.80 330	79.32 318	69.63 379		67.19 327	73.67 377	43.24 334	88.90 289	50.41 338	84.50 177	81.45 363

iter_conf05_11		81.63 117	80.44 127	85.20 78	89.46 124	66.20 167	86.21 198	86.97 237	71.53 172	83.35 91	88.53 181	43.22 335	95.94 53	79.82 97	94.85 43	93.47 81

CMPMVS	51.72 21	70.19 304	68.16 307	76.28 298	73.15 383	57.55 304	79.47 316	83.92 279	48.02 380	56.48 381	84.81 277	43.13 336	86.42 311	62.67 254	81.81 223	84.89 330
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dp		66.80 328	65.43 330	70.90 347	79.74 350	48.82 377	75.12 355	74.77 364	59.61 336	64.08 354	77.23 363	42.89 337	80.72 351	48.86 350	66.58 360	83.16 349

PVSNet	64.34 18	72.08 287	70.87 287	75.69 303	86.21 233	56.44 320	74.37 358	80.73 320	62.06 320	70.17 296	82.23 322	42.86 338	83.31 337	54.77 318	84.45 181	87.32 285

pmmvs-eth3d		70.50 301	67.83 314	78.52 272	77.37 363	66.18 168	81.82 281	81.51 313	58.90 344	63.90 356	80.42 338	42.69 339	86.28 312	58.56 292	65.30 365	83.11 350

UnsupCasMVSNet_eth		67.33 325	65.99 329	71.37 340	73.48 380	51.47 367	75.16 353	85.19 262	65.20 280	60.78 366	80.93 335	42.35 340	77.20 365	57.12 305	53.69 386	85.44 321

KD-MVS_self_test		68.81 313	67.59 320	72.46 334	74.29 375	45.45 383	77.93 336	87.00 236	63.12 303	63.99 355	78.99 353	42.32 341	84.77 327	56.55 312	64.09 368	87.16 290

ADS-MVSNet2		66.20 336	63.33 339	74.82 313	79.92 344	58.75 287	67.55 381	75.19 361	53.37 369	65.25 347	75.86 370	42.32 341	80.53 352	41.57 378	68.91 352	85.18 325

ADS-MVSNet		64.36 340	62.88 343	68.78 356	79.92 344	47.17 380	67.55 381	71.18 375	53.37 369	65.25 347	75.86 370	42.32 341	73.99 386	41.57 378	68.91 352	85.18 325

SixPastTwentyTwo		73.37 271	71.26 283	79.70 249	85.08 254	57.89 298	85.57 213	83.56 285	71.03 183	65.66 343	85.88 253	42.10 344	92.57 191	59.11 286	63.34 369	88.65 260

JIA-IIPM		66.32 333	62.82 344	76.82 295	77.09 364	61.72 258	65.34 388	75.38 360	58.04 351	64.51 351	62.32 389	42.05 345	86.51 310	51.45 334	69.22 351	82.21 358

ACMH	67.68 16	75.89 245	73.93 254	81.77 201	88.71 159	66.61 161	88.62 124	89.01 187	69.81 209	66.78 332	86.70 232	41.95 346	91.51 234	55.64 315	78.14 265	87.17 288
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	68.96 14	76.01 244	74.01 252	82.03 196	88.60 162	65.31 191	88.86 112	87.55 224	70.25 201	67.75 320	87.47 210	41.27 347	93.19 171	58.37 294	75.94 293	87.60 277

MIMVSNet		70.69 298	69.30 297	74.88 312	84.52 264	56.35 324	75.87 348	79.42 336	64.59 287	67.76 319	82.41 318	41.10 348	81.54 346	46.64 363	81.34 225	86.75 300

Anonymous202405211		78.25 196	77.01 205	81.99 197	91.03 82	60.67 269	84.77 232	83.90 280	70.65 193	80.00 132	91.20 113	41.08 349	91.43 238	65.21 233	85.26 169	93.85 59

N_pmnet		52.79 358	53.26 357	51.40 382	78.99 357	7.68 414	69.52 374	3.89 413	51.63 375	57.01 379	74.98 374	40.83 350	65.96 397	37.78 385	64.67 366	80.56 369

ETVMVS		72.25 285	71.05 284	75.84 301	87.77 197	51.91 361	79.39 317	74.98 362	69.26 223	73.71 259	82.95 310	40.82 351	86.14 313	46.17 365	84.43 182	89.47 230

EU-MVSNet		68.53 318	67.61 319	71.31 343	78.51 359	47.01 381	84.47 240	84.27 275	42.27 386	66.44 340	84.79 278	40.44 352	83.76 332	58.76 291	68.54 355	83.17 348

DSMNet-mixed		57.77 351	56.90 353	60.38 370	67.70 392	35.61 401	69.18 376	53.97 402	32.30 398	57.49 378	79.88 343	40.39 353	68.57 395	38.78 384	72.37 334	76.97 376

UWE-MVS		72.13 286	71.49 277	74.03 321	86.66 228	47.70 378	81.40 290	76.89 355	63.60 301	75.59 221	84.22 289	39.94 354	85.62 318	48.98 349	86.13 159	88.77 256

OurMVSNet-221017-0		74.26 261	72.42 270	79.80 247	83.76 280	59.59 283	85.92 207	86.64 242	66.39 268	66.96 329	87.58 204	39.46 355	91.60 226	65.76 230	69.27 350	88.22 266

K. test v3		71.19 291	68.51 303	79.21 259	83.04 297	57.78 301	84.35 247	76.91 354	72.90 154	62.99 360	82.86 313	39.27 356	91.09 250	61.65 266	52.66 387	88.75 257

lessismore_v0				78.97 262	81.01 333	57.15 309		65.99 387		61.16 365	82.82 314	39.12 357	91.34 241	59.67 280	46.92 393	88.43 264

testing222		74.04 264	72.66 267	78.19 276	87.89 188	55.36 335	81.06 293	79.20 339	71.30 176	74.65 251	83.57 302	39.11 358	88.67 291	51.43 335	85.75 166	90.53 185

UnsupCasMVSNet_bld		63.70 342	61.53 348	70.21 349	73.69 378	51.39 368	72.82 362	81.89 309	55.63 364	57.81 377	71.80 381	38.67 359	78.61 358	49.26 348	52.21 388	80.63 367

new-patchmatchnet		61.73 346	61.73 347	61.70 368	72.74 385	24.50 409	69.16 377	78.03 344	61.40 323	56.72 380	75.53 373	38.42 360	76.48 371	45.95 367	57.67 378	84.13 339

MVS-HIRNet		59.14 349	57.67 352	63.57 366	81.65 321	43.50 391	71.73 365	65.06 390	39.59 390	51.43 387	57.73 394	38.34 361	82.58 341	39.53 381	73.95 321	64.62 390

test2506		77.30 223	76.49 219	79.74 248	90.08 103	52.02 358	87.86 153	63.10 393	74.88 106	80.16 131	92.79 79	38.29 362	92.35 201	68.74 204	92.50 73	94.86 17

COLMAP_ROB	66.92 17	73.01 277	70.41 292	80.81 227	87.13 219	65.63 182	88.30 136	84.19 277	62.96 307	63.80 357	87.69 202	38.04 363	92.56 192	46.66 361	74.91 313	84.24 337
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TESTMET0.1,1		69.89 307	69.00 301	72.55 333	79.27 356	56.85 312	78.38 330	74.71 366	57.64 353	68.09 318	77.19 364	37.75 364	76.70 368	63.92 243	84.09 187	84.10 340

OpenMVS_ROB	64.09 19	70.56 300	68.19 306	77.65 285	80.26 339	59.41 285	85.01 227	82.96 299	58.76 345	65.43 345	82.33 319	37.63 365	91.23 244	45.34 371	76.03 292	82.32 357

FMVSNet5		69.50 309	67.96 310	74.15 320	82.97 301	55.35 336	80.01 311	82.12 308	62.56 314	63.02 358	81.53 327	36.92 366	81.92 344	48.42 351	74.06 320	85.17 327

MIMVSNet1		68.58 316	66.78 326	73.98 322	80.07 343	51.82 363	80.77 297	84.37 271	64.40 290	59.75 371	82.16 323	36.47 367	83.63 334	42.73 376	70.33 346	86.48 304

ITE_SJBPF				78.22 275	81.77 320	60.57 270		83.30 289	69.25 224	67.54 322	87.20 217	36.33 368	87.28 306	54.34 320	74.62 316	86.80 298

test-mter		71.41 290	70.39 293	74.48 316	81.35 328	58.04 294	78.38 330	77.46 348	60.32 330	69.95 301	79.00 351	36.08 369	79.24 355	66.13 224	84.83 172	86.15 309

testgi		66.67 330	66.53 327	67.08 362	75.62 370	41.69 397	75.93 345	76.50 356	66.11 270	65.20 349	86.59 236	35.72 370	74.71 383	43.71 373	73.38 329	84.84 331

EG-PatchMatch MVS		74.04 264	71.82 274	80.71 229	84.92 256	67.42 143	85.86 209	88.08 211	66.04 272	64.22 353	83.85 294	35.10 371	92.56 192	57.44 302	80.83 232	82.16 360

KD-MVS_2432*1600		66.22 334	63.89 336	73.21 326	75.47 372	53.42 353	70.76 370	84.35 272	64.10 294	66.52 337	78.52 355	34.55 372	84.98 324	50.40 339	50.33 390	81.23 364

miper_refine_blended		66.22 334	63.89 336	73.21 326	75.47 372	53.42 353	70.76 370	84.35 272	64.10 294	66.52 337	78.52 355	34.55 372	84.98 324	50.40 339	50.33 390	81.23 364

XVG-ACMP-BASELINE		76.11 242	74.27 251	81.62 203	83.20 291	64.67 203	83.60 260	89.75 160	69.75 214	71.85 281	87.09 221	32.78 374	92.11 209	69.99 190	80.43 239	88.09 268

AllTest		70.96 294	68.09 309	79.58 253	85.15 251	63.62 222	84.58 238	79.83 332	62.31 316	60.32 368	86.73 226	32.02 375	88.96 287	50.28 341	71.57 341	86.15 309

TestCases				79.58 253	85.15 251	63.62 222		79.83 332	62.31 316	60.32 368	86.73 226	32.02 375	88.96 287	50.28 341	71.57 341	86.15 309

USDC		70.33 302	68.37 304	76.21 299	80.60 336	56.23 325	79.19 321	86.49 244	60.89 326	61.29 364	85.47 264	31.78 377	89.47 277	53.37 325	76.21 291	82.94 354

myMVS_eth3d		67.02 327	66.29 328	69.21 352	84.68 260	42.58 393	78.62 328	73.08 371	66.65 264	66.74 333	79.46 346	31.53 378	82.30 342	39.43 383	76.38 288	82.75 355

test_fmvs1		70.93 295	70.52 289	72.16 335	73.71 377	55.05 339	80.82 294	78.77 341	51.21 377	78.58 153	84.41 282	31.20 379	76.94 367	75.88 135	80.12 244	84.47 335

Anonymous20240521		68.80 314	67.22 323	73.55 324	74.33 374	54.11 347	83.18 266	85.61 257	58.15 349	61.68 363	80.94 333	30.71 380	81.27 348	57.00 307	73.34 330	85.28 323

testing3		68.56 317	67.67 318	71.22 344	87.33 214	42.87 392	83.06 272	71.54 374	70.36 196	69.08 311	84.38 283	30.33 381	85.69 317	37.50 386	75.45 303	85.09 329

test_vis1_n		69.85 308	69.21 299	71.77 337	72.66 386	55.27 338	81.48 287	76.21 358	52.03 373	75.30 236	83.20 307	28.97 382	76.22 374	74.60 145	78.41 263	83.81 343

tmp_tt		18.61 374	21.40 377	10.23 390	4.82 413	10.11 413	34.70 400	30.74 411	1.48 407	23.91 403	26.07 404	28.42 383	13.41 409	27.12 395	15.35 406	7.17 404

test_fmvs1_n		70.86 296	70.24 294	72.73 332	72.51 387	55.28 337	81.27 291	79.71 334	51.49 376	78.73 147	84.87 276	27.54 384	77.02 366	76.06 132	79.97 245	85.88 316

TDRefinement		67.49 323	64.34 333	76.92 294	73.47 381	61.07 263	84.86 231	82.98 298	59.77 335	58.30 375	85.13 272	26.06 385	87.89 300	47.92 358	60.59 376	81.81 362

test_vis1_rt		60.28 348	58.42 351	65.84 363	67.25 393	55.60 333	70.44 372	60.94 396	44.33 384	59.00 372	66.64 386	24.91 386	68.67 394	62.80 250	69.48 348	73.25 382

TinyColmap		67.30 326	64.81 331	74.76 314	81.92 319	56.68 317	80.29 308	81.49 314	60.33 329	56.27 382	83.22 305	24.77 387	87.66 304	45.52 369	69.47 349	79.95 370

EGC-MVSNET		52.07 360	47.05 364	67.14 361	83.51 284	60.71 268	80.50 304	67.75 384	0.07 408	0.43 409	75.85 372	24.26 388	81.54 346	28.82 393	62.25 370	59.16 393

LF4IMVS		64.02 341	62.19 345	69.50 351	70.90 388	53.29 356	76.13 343	77.18 352	52.65 371	58.59 373	80.98 332	23.55 389	76.52 370	53.06 327	66.66 359	78.68 373

test_fmvs2		68.35 320	67.48 321	70.98 346	69.50 390	51.95 360	80.05 310	76.38 357	49.33 379	74.65 251	84.38 283	23.30 390	75.40 381	74.51 146	75.17 311	85.60 319

new_pmnet		50.91 361	50.29 361	52.78 381	68.58 391	34.94 403	63.71 390	56.63 401	39.73 389	44.95 391	65.47 387	21.93 391	58.48 400	34.98 388	56.62 380	64.92 389

pmmvs3		57.79 350	54.26 355	68.37 358	64.02 396	56.72 315	75.12 355	65.17 389	40.20 388	52.93 386	69.86 385	20.36 392	75.48 379	45.45 370	55.25 385	72.90 383

PM-MVS		66.41 332	64.14 334	73.20 328	73.92 376	56.45 319	78.97 324	64.96 391	63.88 300	64.72 350	80.24 339	19.84 393	83.44 336	66.24 223	64.52 367	79.71 371

mvsany_test3		53.99 354	51.45 359	61.61 369	55.51 401	44.74 389	63.52 391	45.41 408	43.69 385	58.11 376	76.45 367	17.99 394	63.76 399	54.77 318	47.59 392	76.34 378

ambc				75.24 309	73.16 382	50.51 372	63.05 393	87.47 227		64.28 352	77.81 361	17.80 395	89.73 272	57.88 299	60.64 375	85.49 320

ANet_high		50.57 362	46.10 366	63.99 365	48.67 408	39.13 399	70.99 369	80.85 318	61.39 324	31.18 397	57.70 395	17.02 396	73.65 388	31.22 392	15.89 405	79.18 372

FPMVS		53.68 356	51.64 358	59.81 371	65.08 395	51.03 369	69.48 375	69.58 380	41.46 387	40.67 393	72.32 380	16.46 397	70.00 393	24.24 399	65.42 364	58.40 395

test_method		31.52 370	29.28 374	38.23 385	27.03 412	6.50 415	20.94 403	62.21 394	4.05 406	22.35 404	52.50 398	13.33 398	47.58 405	27.04 396	34.04 398	60.62 392

EMVS		30.81 371	29.65 373	34.27 387	50.96 407	25.95 407	56.58 397	46.80 407	24.01 402	15.53 407	30.68 403	12.47 399	54.43 404	12.81 407	17.05 404	22.43 403

test_f		52.09 359	50.82 360	55.90 376	53.82 404	42.31 396	59.42 394	58.31 400	36.45 393	56.12 383	70.96 383	12.18 400	57.79 401	53.51 324	56.57 381	67.60 387

test_fmvs3		63.36 343	61.82 346	67.98 359	62.51 397	46.96 382	77.37 340	74.03 368	45.24 382	67.50 323	78.79 354	12.16 401	72.98 389	72.77 166	66.02 362	83.99 341

E-PMN		31.77 369	30.64 372	35.15 386	52.87 406	27.67 405	57.09 396	47.86 406	24.64 401	16.40 406	33.05 402	11.23 402	54.90 403	14.46 406	18.15 403	22.87 402

DeepMVS_CX				27.40 388	40.17 411	26.90 406		24.59 412	17.44 404	23.95 402	48.61 399	9.77 403	26.48 407	18.06 401	24.47 401	28.83 401

Gipuma		45.18 366	41.86 369	55.16 379	77.03 365	51.52 366	32.50 401	80.52 323	32.46 397	27.12 400	35.02 401	9.52 404	75.50 378	22.31 400	60.21 377	38.45 400
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		54.25 353	49.68 363	67.97 360	53.73 405	45.28 386	66.85 384	80.78 319	35.96 394	39.45 395	62.23 390	8.70 405	78.06 362	48.24 355	51.20 389	80.57 368

APD_test1		53.31 357	49.93 362	63.42 367	65.68 394	50.13 373	71.59 366	66.90 386	34.43 395	40.58 394	71.56 382	8.65 406	76.27 373	34.64 389	55.36 384	63.86 391

PMMVS2		40.82 368	38.86 371	46.69 383	53.84 403	16.45 412	48.61 398	49.92 403	37.49 391	31.67 396	60.97 391	8.14 407	56.42 402	28.42 394	30.72 400	67.19 388

test_vis3_rt		49.26 363	47.02 365	56.00 375	54.30 402	45.27 387	66.76 385	48.08 405	36.83 392	44.38 392	53.20 397	7.17 408	64.07 398	56.77 310	55.66 382	58.65 394

testf1		45.72 364	41.96 367	57.00 373	56.90 399	45.32 384	66.14 386	59.26 398	26.19 399	30.89 398	60.96 392	4.14 409	70.64 391	26.39 397	46.73 394	55.04 396

APD_test2		45.72 364	41.96 367	57.00 373	56.90 399	45.32 384	66.14 386	59.26 398	26.19 399	30.89 398	60.96 392	4.14 409	70.64 391	26.39 397	46.73 394	55.04 396

PMVS	37.38 22	44.16 367	40.28 370	55.82 377	40.82 410	42.54 395	65.12 389	63.99 392	34.43 395	24.48 401	57.12 396	3.92 411	76.17 375	17.10 403	55.52 383	48.75 398
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 372	25.89 376	43.81 384	44.55 409	35.46 402	28.87 402	39.07 409	18.20 403	18.58 405	40.18 400	2.68 412	47.37 406	17.07 404	23.78 402	48.60 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		16.82 375	15.94 378	19.46 389	58.74 398	31.45 404	39.22 399	3.74 414	6.84 405	6.04 408	2.70 408	1.27 413	24.29 408	10.54 408	14.40 407	2.63 405

test123		6.12 377	8.11 380	0.14 391	0.06 415	0.09 416	71.05 368	0.03 416	0.04 410	0.25 411	1.30 410	0.05 414	0.03 411	0.21 410	0.01 409	0.29 406

testmvs		6.04 378	8.02 381	0.10 392	0.08 414	0.03 417	69.74 373	0.04 415	0.05 409	0.31 410	1.68 409	0.02 415	0.04 410	0.24 409	0.02 408	0.25 407

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

ab-mvs-re		7.23 376	9.64 379	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	86.72 228	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						42.58 393								39.46 382

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 115	91.30 15

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 46					97.53 2	89.67 6	96.44 9	94.41 34

No_MVS				89.16 1	94.34 27	75.53 2		92.99 46					97.53 2	89.67 6	96.44 9	94.41 34

eth-test2					0.00 416

eth-test					0.00 416

IU-MVS					95.30 2	71.25 57		92.95 52	66.81 257	92.39 6				88.94 16	96.63 4	94.85 19

save fliter					93.80 40	72.35 42	90.47 64	91.17 118	74.31 118

test_0728_SECOND				87.71 32	95.34 1	71.43 56	93.49 9	94.23 3					97.49 4	89.08 12	96.41 12	94.21 44

GSMVS																88.96 248

test_part2					95.06 8	72.65 32				91.80 13

MTGPA								92.02 87

MTMP							92.18 35	32.83 410

gm-plane-assit					81.40 326	53.83 350			62.72 313		80.94 333		92.39 198	63.40 247

test9_res														84.90 42	95.70 26	92.87 106

agg_prior2														82.91 66	95.45 30	92.70 109

agg_prior					92.85 59	71.94 51		91.78 102		84.41 73			94.93 89

test_prior4						72.60 34	89.01 107

test_prior				86.33 54	92.61 65	69.59 88		92.97 51					95.48 64			93.91 55

旧先验2							86.56 189		58.10 350	87.04 41			88.98 285	74.07 151

新几何2							86.29 197

无先验							87.48 160	88.98 188	60.00 333				94.12 122	67.28 216		88.97 247

原ACMM2							86.86 178

testdata2													91.01 252	62.37 257

testdata1							84.14 251		75.71 89

plane_prior7					90.08 103	68.51 120

plane_prior5								92.44 71					95.38 71	78.71 105	86.32 154	91.33 155

plane_prior4											91.00 122

plane_prior3						68.60 118			78.44 31	78.92 145

plane_prior2							91.25 50		79.12 23

plane_prior1					89.90 111

plane_prior						68.71 113	90.38 68		77.62 39						86.16 158

n2								0.00 417

nn								0.00 417

door-mid								69.98 378

test11								92.23 81

door								69.44 381

HQP5-MVS						66.98 155

HQP-NCC					89.33 131		89.17 100		76.41 74	77.23 185

ACMP_Plane					89.33 131		89.17 100		76.41 74	77.23 185

BP-MVS														77.47 117

HQP4-MVS										77.24 184			95.11 82			91.03 166

HQP3-MVS								92.19 84							85.99 162

NP-MVS					89.62 116	68.32 123					90.24 134

ACMMP++_ref															81.95 221

ACMMP++															81.25 226

High-resolution multi-view benchmark