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.

DVP-MVS++		81.67 1	82.40 1	79.47 10	87.24 14	59.15 63	88.18 1	87.15 3	65.04 16	84.26 5	91.86 6	67.01 1	90.84 3	79.48 6	91.38 2	88.42 16

OPU-MVS				79.83 7	87.54 11	60.93 35	87.82 7				89.89 45	67.01 1	90.33 12	73.16 58	91.15 4	88.23 22

SED-MVS		81.56 2	82.30 2	79.32 13	87.77 4	58.90 72	87.82 7	86.78 10	64.18 32	85.97 1	91.84 8	66.87 3	90.83 5	78.63 18	90.87 5	88.23 22

test_241102_ONE					87.77 4	58.90 72		86.78 10	64.20 31	85.97 1	91.34 15	66.87 3	90.78 7

PC_three_1452									55.09 213	84.46 4	89.84 46	66.68 5	89.41 18	74.24 48	91.38 2	88.42 16

test_241102_TWO								86.73 12	64.18 32	84.26 5	91.84 8	65.19 6	90.83 5	78.63 18	90.70 7	87.65 41

DPE-MVS		80.56 5	80.98 5	79.29 15	87.27 13	60.56 41	85.71 26	86.42 14	63.28 44	83.27 13	91.83 10	64.96 7	90.47 11	76.41 30	89.67 18	86.84 65
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		80.84 4	81.64 3	78.42 34	87.75 7	59.07 67	87.85 5	85.03 36	64.26 29	83.82 8	92.00 3	64.82 8	90.75 8	78.66 16	90.61 11	85.45 124
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					87.75 7	59.07 67	87.86 4	86.83 8	64.26 29	84.19 7	91.92 5	64.82 8

test_0728_THIRD									65.04 16	83.82 8	92.00 3	64.69 10	90.75 8	79.48 6	90.63 10	88.09 27

test_one_0601					87.58 9	59.30 60		86.84 7	65.01 20	83.80 11	91.86 6	64.03 11

MSP-MVS		81.06 3	81.40 4	80.02 1	86.21 31	62.73 9	86.09 18	86.83 8	65.51 12	83.81 10	90.51 25	63.71 12	89.23 20	81.51 2	88.44 27	88.09 27
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
dcpmvs_2		74.55 63	75.23 53	72.48 160	82.34 80	53.34 161	77.87 142	81.46 111	57.80 160	75.49 42	86.81 95	62.22 13	77.75 259	71.09 77	82.02 97	86.34 84

DeepPCF-MVS	69.58 1	79.03 12	79.00 13	79.13 19	84.92 56	60.32 46	83.03 60	85.33 28	62.86 54	80.17 17	90.03 41	61.76 14	88.95 24	74.21 49	88.67 26	88.12 26

CSCG		76.92 33	76.75 31	77.41 49	83.96 64	59.60 54	82.95 61	86.50 13	60.78 90	75.27 44	84.83 144	60.76 15	86.56 76	67.86 93	87.87 41	86.06 97

TSAR-MVS + MP.		78.44 19	78.28 19	78.90 27	84.96 52	61.41 26	84.03 48	83.82 63	59.34 127	79.37 19	89.76 48	59.84 16	87.62 51	76.69 28	86.74 53	87.68 40
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
sasdasda		74.67 59	74.98 55	73.71 126	78.94 146	50.56 210	80.23 98	83.87 60	60.30 104	77.15 33	86.56 107	59.65 17	82.00 179	66.01 111	82.12 94	88.58 14

canonicalmvs		74.67 59	74.98 55	73.71 126	78.94 146	50.56 210	80.23 98	83.87 60	60.30 104	77.15 33	86.56 107	59.65 17	82.00 179	66.01 111	82.12 94	88.58 14

APDe-MVS		80.16 8	80.59 6	78.86 29	86.64 21	60.02 48	88.12 3	86.42 14	62.94 51	82.40 14	92.12 2	59.64 19	89.76 16	78.70 13	88.32 31	86.79 67
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DELS-MVS		74.76 57	74.46 60	75.65 78	77.84 184	52.25 184	75.59 199	84.17 49	63.76 38	73.15 83	82.79 184	59.58 20	86.80 69	67.24 100	86.04 59	87.89 30
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
CNVR-MVS		79.84 10	79.97 10	79.45 11	87.90 2	62.17 17	84.37 39	85.03 36	66.96 5	77.58 30	90.06 39	59.47 21	89.13 22	78.67 15	89.73 16	87.03 59

casdiffmvs_mvg		76.14 45	76.30 39	75.66 77	76.46 227	51.83 193	79.67 111	85.08 33	65.02 19	75.84 39	88.58 65	59.42 22	85.08 111	72.75 61	83.93 76	90.08 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
MCST-MVS		77.48 28	77.45 27	77.54 47	86.67 20	58.36 79	83.22 58	86.93 5	56.91 170	74.91 54	88.19 67	59.15 23	87.68 50	73.67 55	87.45 43	86.57 76

nrg030		72.96 80	73.01 76	72.84 153	75.41 242	50.24 214	80.02 102	82.89 91	58.36 146	74.44 64	86.73 98	58.90 24	80.83 206	65.84 114	74.46 192	87.44 48

HPM-MVS++		79.88 9	80.14 9	79.10 21	88.17 1	64.80 1	86.59 12	83.70 65	65.37 13	78.78 22	90.64 21	58.63 25	87.24 54	79.00 12	90.37 14	85.26 135

SF-MVS		78.82 13	79.22 12	77.60 46	82.88 77	57.83 84	84.99 31	88.13 2	61.86 75	79.16 20	90.75 20	57.96 26	87.09 63	77.08 27	90.18 15	87.87 32

casdiffmvs		74.80 56	74.89 57	74.53 101	75.59 239	50.37 213	78.17 136	85.06 35	62.80 58	74.40 65	87.86 75	57.88 27	83.61 143	69.46 85	82.79 90	89.59 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
MGCFI-Net		72.45 89	73.34 74	69.81 224	77.77 186	43.21 300	75.84 196	81.18 125	59.59 123	75.45 43	86.64 101	57.74 28	77.94 254	63.92 130	81.90 99	88.30 19

DeepC-MVS	69.38 2	78.56 17	78.14 22	79.83 7	83.60 65	61.62 23	84.17 45	86.85 6	63.23 46	73.84 73	90.25 35	57.68 29	89.96 15	74.62 47	89.03 22	87.89 30
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline		74.61 61	74.70 58	74.34 105	75.70 235	49.99 221	77.54 153	84.63 42	62.73 59	73.98 70	87.79 78	57.67 30	83.82 139	69.49 83	82.74 91	89.20 7

patch_mono-2		69.85 137	71.09 104	66.16 273	79.11 143	54.80 139	71.97 267	74.31 248	53.50 244	70.90 115	84.17 159	57.63 31	63.31 357	66.17 108	82.02 97	80.38 258

9.14			78.75 15		83.10 72		84.15 46	88.26 1	59.90 113	78.57 24	90.36 30	57.51 32	86.86 68	77.39 24	89.52 21

MM		80.20 7	80.28 8	79.99 2	82.19 82	60.01 49	86.19 17	83.93 54	73.19 1	77.08 35	91.21 17	57.23 33	90.73 10	83.35 1	88.12 34	89.22 6

MVSMamba_PlusPlus		75.75 51	75.44 49	76.67 60	80.84 105	53.06 167	78.62 126	85.13 32	59.65 118	71.53 110	87.47 82	56.92 34	88.17 35	72.18 67	86.63 56	88.80 10

DPM-MVS		75.47 53	75.00 54	76.88 54	81.38 96	59.16 62	79.94 104	85.71 22	56.59 179	72.46 99	86.76 96	56.89 35	87.86 45	66.36 107	88.91 25	83.64 191

UniMVSNet_NR-MVSNet		71.11 111	71.00 106	71.44 186	79.20 139	44.13 289	76.02 192	82.60 94	66.48 11	68.20 155	84.60 152	56.82 36	82.82 163	54.62 203	70.43 252	87.36 54

SMA-MVS		80.28 6	80.39 7	79.95 4	86.60 23	61.95 19	86.33 13	85.75 21	62.49 62	82.20 15	92.28 1	56.53 37	89.70 17	79.85 5	91.48 1	88.19 24
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
balanced_conf03		76.58 38	76.55 37	76.68 59	81.73 88	52.90 170	80.94 91	85.70 23	61.12 85	74.90 55	87.17 90	56.46 38	88.14 36	72.87 60	88.03 38	89.00 8

Effi-MVS+		73.31 75	72.54 81	75.62 79	77.87 182	53.64 154	79.62 113	79.61 151	61.63 77	72.02 104	82.61 189	56.44 39	85.97 91	63.99 129	79.07 136	87.25 56

alignmvs		73.86 69	73.99 65	73.45 140	78.20 169	50.50 212	78.57 128	82.43 95	59.40 125	76.57 36	86.71 100	56.42 40	81.23 196	65.84 114	81.79 100	88.62 12

test_prior2							81.75 81		60.37 100	75.01 50	89.06 55	56.22 41		72.19 66	88.96 24

ZD-MVS					86.64 21	60.38 45		82.70 93	57.95 155	78.10 25	90.06 39	56.12 42	88.84 26	74.05 51	87.00 49

TSAR-MVS + GP.		74.90 55	74.15 64	77.17 52	82.00 84	58.77 75	81.80 80	78.57 172	58.58 141	74.32 67	84.51 155	55.94 43	87.22 57	67.11 101	84.48 71	85.52 118

fmvsm_s_conf0.5_n_3		73.55 71	74.39 61	71.03 201	74.09 269	51.86 192	77.77 147	75.60 222	61.18 83	78.67 23	88.98 57	55.88 44	77.73 260	78.69 14	78.68 143	83.50 194

MVS_Test		72.45 89	72.46 82	72.42 164	74.88 248	48.50 244	76.28 184	83.14 86	59.40 125	72.46 99	84.68 147	55.66 45	81.12 197	65.98 113	79.66 123	87.63 42

APD-MVS		78.02 23	78.04 23	77.98 41	86.44 27	60.81 38	85.52 27	84.36 46	60.61 93	79.05 21	90.30 33	55.54 46	88.32 32	73.48 57	87.03 46	84.83 149
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		78.58 16	78.31 18	79.39 12	87.51 12	62.61 13	85.20 30	84.42 45	66.73 8	74.67 62	89.38 52	55.30 47	89.18 21	74.19 50	87.34 44	86.38 80

FIs		70.82 118	71.43 94	68.98 237	78.33 166	38.14 344	76.96 169	83.59 68	61.02 86	67.33 177	86.73 98	55.07 48	81.64 185	54.61 205	79.22 131	87.14 58

CS-MVS		76.25 44	75.98 43	77.06 53	80.15 121	55.63 123	84.51 38	83.90 57	63.24 45	73.30 78	87.27 88	55.06 49	86.30 86	71.78 71	84.58 66	89.25 5

fmvsm_l_conf0.5_n_3		73.23 76	73.13 75	73.55 136	74.40 262	55.13 133	78.97 120	74.96 240	56.64 173	74.76 60	88.75 63	55.02 50	78.77 246	76.33 31	78.31 150	86.74 69

SD-MVS		77.70 26	77.62 26	77.93 42	84.47 59	61.88 21	84.55 37	83.87 60	60.37 100	79.89 18	89.38 52	54.97 51	85.58 100	76.12 33	84.94 64	86.33 86
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
CANet		76.46 40	75.93 44	78.06 39	81.29 97	57.53 88	82.35 72	83.31 80	67.78 3	70.09 122	86.34 114	54.92 52	88.90 25	72.68 62	84.55 67	87.76 38

MP-MVS		78.35 20	78.26 21	78.64 31	86.54 25	63.47 4	86.02 20	83.55 69	63.89 37	73.60 75	90.60 22	54.85 53	86.72 71	77.20 26	88.06 36	85.74 112
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test_fmvsmconf_n		73.01 79	72.59 80	74.27 108	71.28 314	55.88 117	78.21 135	75.56 224	54.31 234	74.86 56	87.80 77	54.72 54	80.23 220	78.07 22	78.48 146	86.70 70

mvs_anonymous		68.03 183	67.51 172	69.59 227	72.08 297	44.57 286	71.99 266	75.23 232	51.67 259	67.06 182	82.57 190	54.68 55	77.94 254	56.56 185	75.71 185	86.26 93

test12				77.76 45	84.52 58	58.41 78		83.36 76		72.93 91		54.61 56	88.05 39		88.12 34	86.81 66

FC-MVSNet-test		69.80 140	70.58 114	67.46 253	77.61 198	34.73 377	76.05 190	83.19 84	60.84 88	65.88 206	86.46 111	54.52 57	80.76 209	52.52 220	78.12 152	86.91 62

SteuartSystems-ACMMP		79.48 11	79.31 11	79.98 3	83.01 75	62.18 16	87.60 9	85.83 19	66.69 9	78.03 27	90.98 18	54.26 58	90.06 14	78.42 20	89.02 23	87.69 39
Skip Steuart: Steuart Systems R&D Blog.
segment_acmp												54.23 59

MVS_111021_HR		74.02 67	73.46 72	75.69 76	83.01 75	60.63 40	77.29 161	78.40 183	61.18 83	70.58 117	85.97 126	54.18 60	84.00 136	67.52 98	82.98 85	82.45 218

MVS_0304		78.45 18	78.28 19	78.98 26	80.73 107	57.91 83	84.68 35	81.64 107	68.35 2	75.77 40	90.38 29	53.98 61	90.26 13	81.30 3	87.68 42	88.77 11

Fast-Effi-MVS+		70.28 129	69.12 139	73.73 125	78.50 157	51.50 195	75.01 212	79.46 155	56.16 189	68.59 148	79.55 256	53.97 62	84.05 132	53.34 215	77.53 160	85.65 115

ZNCC-MVS		78.82 13	78.67 16	79.30 14	86.43 28	62.05 18	86.62 11	86.01 18	63.32 43	75.08 49	90.47 28	53.96 63	88.68 27	76.48 29	89.63 20	87.16 57

UniMVSNet (Re)		70.63 121	70.20 120	71.89 170	78.55 156	45.29 279	75.94 193	82.92 88	63.68 40	68.16 158	83.59 173	53.89 64	83.49 146	53.97 209	71.12 245	86.89 63

SPE-MVS-test		75.62 52	75.31 52	76.56 64	80.63 111	55.13 133	83.88 51	85.22 29	62.05 71	71.49 111	86.03 124	53.83 65	86.36 84	67.74 94	86.91 50	88.19 24

test_fmvsmconf0.1_n		72.81 81	72.33 83	74.24 109	69.89 336	55.81 118	78.22 134	75.40 228	54.17 236	75.00 51	88.03 73	53.82 66	80.23 220	78.08 21	78.34 149	86.69 71

fmvsm_l_conf0.5_n		70.99 114	70.82 108	71.48 183	71.45 307	54.40 143	77.18 164	70.46 282	48.67 301	75.17 46	86.86 93	53.77 67	76.86 278	76.33 31	77.51 161	83.17 205

DeepC-MVS_fast	68.24 3	77.25 30	76.63 33	79.12 20	86.15 34	60.86 36	84.71 34	84.85 40	61.98 74	73.06 88	88.88 59	53.72 68	89.06 23	68.27 88	88.04 37	87.42 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TEST9					85.58 43	61.59 24	81.62 83	81.26 122	55.65 200	74.93 52	88.81 60	53.70 69	84.68 123

train_agg		76.27 43	76.15 40	76.64 62	85.58 43	61.59 24	81.62 83	81.26 122	55.86 192	74.93 52	88.81 60	53.70 69	84.68 123	75.24 42	88.33 30	83.65 190

test_8					85.40 46	60.96 34	81.54 86	81.18 125	55.86 192	74.81 57	88.80 62	53.70 69	84.45 127

ETV-MVS		74.46 64	73.84 68	76.33 67	79.27 137	55.24 132	79.22 117	85.00 38	64.97 21	72.65 96	79.46 258	53.65 72	87.87 44	67.45 99	82.91 86	85.89 103

CDPH-MVS		76.31 42	75.67 48	78.22 37	85.35 48	59.14 65	81.31 88	84.02 51	56.32 184	74.05 69	88.98 57	53.34 73	87.92 43	69.23 86	88.42 28	87.59 44

HFP-MVS		78.01 24	77.65 25	79.10 21	86.71 19	62.81 8	86.29 14	84.32 47	62.82 55	73.96 71	90.50 26	53.20 74	88.35 31	74.02 52	87.05 45	86.13 95

EC-MVSNet		75.84 49	75.87 46	75.74 75	78.86 148	52.65 175	83.73 53	86.08 17	63.47 42	72.77 94	87.25 89	53.13 75	87.93 42	71.97 70	85.57 62	86.66 73

test_fmvsm_n_1920		71.73 103	71.14 103	73.50 137	72.52 288	56.53 104	75.60 198	76.16 213	48.11 310	77.22 32	85.56 135	53.10 76	77.43 264	74.86 44	77.14 168	86.55 77

fmvsm_l_conf0.5_n_a		70.50 124	70.27 119	71.18 196	71.30 313	54.09 146	76.89 172	69.87 286	47.90 314	74.37 66	86.49 110	53.07 77	76.69 283	75.41 39	77.11 169	82.76 212

EI-MVSNet-Vis-set		72.42 91	71.59 90	74.91 88	78.47 159	54.02 147	77.05 167	79.33 157	65.03 18	71.68 108	79.35 262	52.75 78	84.89 118	66.46 106	74.23 196	85.83 105

fmvsm_s_conf0.5_n_a		69.54 150	68.74 147	71.93 169	72.47 290	53.82 150	78.25 132	62.26 351	49.78 287	73.12 86	86.21 117	52.66 79	76.79 280	75.02 43	68.88 284	85.18 136

GST-MVS		78.14 22	77.85 24	78.99 25	86.05 38	61.82 22	85.84 21	85.21 30	63.56 41	74.29 68	90.03 41	52.56 80	88.53 29	74.79 46	88.34 29	86.63 75

ACMMP_NAP		78.77 15	78.78 14	78.74 30	85.44 45	61.04 31	83.84 52	85.16 31	62.88 53	78.10 25	91.26 16	52.51 81	88.39 30	79.34 8	90.52 13	86.78 68

PCF-MVS	61.88 8	70.95 115	69.49 131	75.35 83	77.63 193	55.71 120	76.04 191	81.81 104	50.30 280	69.66 133	85.40 141	52.51 81	84.89 118	51.82 228	80.24 117	85.45 124
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MP-MVS-pluss		78.35 20	78.46 17	78.03 40	84.96 52	59.52 56	82.93 62	85.39 27	62.15 67	76.41 38	91.51 11	52.47 83	86.78 70	80.66 4	89.64 19	87.80 36
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CLD-MVS		73.33 74	72.68 79	75.29 86	78.82 150	53.33 162	78.23 133	84.79 41	61.30 81	70.41 119	81.04 226	52.41 84	87.12 61	64.61 125	82.49 93	85.41 128
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		71.01 113	70.15 122	73.60 134	79.57 131	52.17 185	78.93 121	78.12 186	58.02 152	67.76 172	83.87 167	52.36 85	82.72 165	56.90 183	75.79 183	85.92 101

NR-MVSNet		69.54 150	68.85 143	71.59 181	78.05 177	43.81 294	74.20 229	80.86 134	65.18 14	62.76 258	84.52 153	52.35 86	83.59 144	50.96 236	70.78 247	87.37 52

fmvsm_s_conf0.5_n		69.58 148	68.84 144	71.79 174	72.31 295	52.90 170	77.90 141	62.43 349	49.97 285	72.85 92	85.90 128	52.21 87	76.49 286	75.75 35	70.26 259	85.97 99

EI-MVSNet-UG-set		71.92 99	71.06 105	74.52 102	77.98 180	53.56 156	76.62 176	79.16 158	64.40 27	71.18 113	78.95 267	52.19 88	84.66 125	65.47 117	73.57 207	85.32 131

miper_ehance_all_eth		68.03 183	67.24 185	70.40 212	70.54 323	46.21 268	73.98 232	78.68 170	55.07 216	66.05 200	77.80 287	52.16 89	81.31 193	61.53 154	69.32 276	83.67 187

EIA-MVS		71.78 101	70.60 112	75.30 85	79.85 125	53.54 157	77.27 162	83.26 83	57.92 156	66.49 192	79.39 260	52.07 90	86.69 72	60.05 162	79.14 135	85.66 114

fmvsm_s_conf0.1_n_a		69.32 156	68.44 156	71.96 168	70.91 318	53.78 151	78.12 137	62.30 350	49.35 293	73.20 82	86.55 109	51.99 91	76.79 280	74.83 45	68.68 289	85.32 131

c3_l		68.33 177	67.56 168	70.62 208	70.87 319	46.21 268	74.47 225	78.80 166	56.22 188	66.19 198	78.53 275	51.88 92	81.40 190	62.08 145	69.04 282	84.25 163

PAPM_NR		72.63 86	71.80 88	75.13 87	81.72 89	53.42 160	79.91 106	83.28 82	59.14 129	66.31 197	85.90 128	51.86 93	86.06 87	57.45 180	80.62 109	85.91 102

test_fmvsmvis_n_1920		70.84 116	70.38 117	72.22 167	71.16 315	55.39 130	75.86 194	72.21 269	49.03 297	73.28 80	86.17 119	51.83 94	77.29 268	75.80 34	78.05 153	83.98 172

MG-MVS		73.96 68	73.89 67	74.16 111	85.65 42	49.69 226	81.59 85	81.29 121	61.45 78	71.05 114	88.11 68	51.77 95	87.73 47	61.05 155	83.09 81	85.05 142

EPP-MVSNet		72.16 97	71.31 99	74.71 91	78.68 154	49.70 224	82.10 78	81.65 106	60.40 97	65.94 202	85.84 130	51.74 96	86.37 83	55.93 189	79.55 126	88.07 29

fmvsm_s_conf0.1_n		69.41 155	68.60 150	71.83 172	71.07 316	52.88 172	77.85 144	62.44 348	49.58 290	72.97 89	86.22 116	51.68 97	76.48 287	75.53 38	70.10 262	86.14 94

TranMVSNet+NR-MVSNet		70.36 127	70.10 124	71.17 197	78.64 155	42.97 303	76.53 179	81.16 127	66.95 6	68.53 151	85.42 140	51.61 98	83.07 152	52.32 221	69.70 272	87.46 47

diffmvs		70.69 120	70.43 115	71.46 184	69.45 342	48.95 238	72.93 251	78.46 178	57.27 164	71.69 107	83.97 166	51.48 99	77.92 256	70.70 79	77.95 155	87.53 46
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet		69.27 158	68.44 156	71.73 176	74.47 259	49.39 231	75.20 207	78.45 179	59.60 120	69.16 144	76.51 310	51.29 100	82.50 171	59.86 167	71.45 242	83.30 197

IterMVS-LS		69.22 160	68.48 152	71.43 188	74.44 261	49.40 230	76.23 185	77.55 195	59.60 120	65.85 207	81.59 218	51.28 101	81.58 188	59.87 166	69.90 267	83.30 197
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TransMVSNet (Re)		64.72 237	64.33 227	65.87 281	75.22 244	38.56 340	74.66 222	75.08 239	58.90 134	61.79 274	82.63 188	51.18 102	78.07 253	43.63 301	55.87 372	80.99 248

miper_enhance_ethall		67.11 204	66.09 208	70.17 216	69.21 345	45.98 270	72.85 253	78.41 182	51.38 266	65.65 209	75.98 320	51.17 103	81.25 194	60.82 157	69.32 276	83.29 199

VNet		69.68 144	70.19 121	68.16 247	79.73 127	41.63 316	70.53 287	77.38 199	60.37 100	70.69 116	86.63 103	51.08 104	77.09 271	53.61 213	81.69 105	85.75 111

VPA-MVSNet		69.02 161	69.47 132	67.69 251	77.42 203	41.00 321	74.04 231	79.68 149	60.06 110	69.26 142	84.81 145	51.06 105	77.58 262	54.44 206	74.43 194	84.48 158

PAPR		71.72 104	70.82 108	74.41 104	81.20 101	51.17 196	79.55 115	83.33 79	55.81 195	66.93 185	84.61 151	50.95 106	86.06 87	55.79 192	79.20 132	86.00 98

PHI-MVS		75.87 48	75.36 50	77.41 49	80.62 112	55.91 116	84.28 42	85.78 20	56.08 190	73.41 77	86.58 106	50.94 107	88.54 28	70.79 78	89.71 17	87.79 37

HPM-MVS		77.28 29	76.85 30	78.54 32	85.00 51	60.81 38	82.91 63	85.08 33	62.57 60	73.09 87	89.97 44	50.90 108	87.48 52	75.30 40	86.85 51	87.33 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
reproduce-ours		76.90 34	76.58 34	77.87 43	83.99 62	60.46 43	84.75 32	83.34 77	60.22 107	77.85 28	91.42 13	50.67 109	87.69 48	72.46 63	84.53 68	85.46 122

our_new_method		76.90 34	76.58 34	77.87 43	83.99 62	60.46 43	84.75 32	83.34 77	60.22 107	77.85 28	91.42 13	50.67 109	87.69 48	72.46 63	84.53 68	85.46 122

WR-MVS_H		67.02 206	66.92 190	67.33 257	77.95 181	37.75 348	77.57 151	82.11 100	62.03 73	62.65 261	82.48 195	50.57 111	79.46 228	42.91 308	64.01 324	84.79 151

EPNet		73.09 78	72.16 85	75.90 71	75.95 233	56.28 107	83.05 59	72.39 267	66.53 10	65.27 216	87.00 91	50.40 112	85.47 105	62.48 143	86.32 58	85.94 100
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WR-MVS		68.47 174	68.47 154	68.44 244	80.20 118	39.84 328	73.75 241	76.07 216	64.68 22	68.11 160	83.63 172	50.39 113	79.14 238	49.78 241	69.66 273	86.34 84

test_fmvsmconf0.01_n		72.17 95	71.50 92	74.16 111	67.96 354	55.58 126	78.06 139	74.67 243	54.19 235	74.54 63	88.23 66	50.35 114	80.24 219	78.07 22	77.46 162	86.65 74

region2R		77.67 27	77.18 29	79.15 18	86.76 17	62.95 6	86.29 14	84.16 50	62.81 57	73.30 78	90.58 23	49.90 115	88.21 34	73.78 54	87.03 46	86.29 92

UA-Net		73.13 77	72.93 77	73.76 121	83.58 66	51.66 194	78.75 122	77.66 193	67.75 4	72.61 97	89.42 50	49.82 116	83.29 148	53.61 213	83.14 80	86.32 88

ACMMPR		77.71 25	77.23 28	79.16 17	86.75 18	62.93 7	86.29 14	84.24 48	62.82 55	73.55 76	90.56 24	49.80 117	88.24 33	74.02 52	87.03 46	86.32 88

API-MVS		72.17 95	71.41 95	74.45 103	81.95 86	57.22 92	84.03 48	80.38 142	59.89 116	68.40 152	82.33 198	49.64 118	87.83 46	51.87 227	84.16 75	78.30 284

reproduce_model		76.43 41	76.08 41	77.49 48	83.47 69	60.09 47	84.60 36	82.90 89	59.65 118	77.31 31	91.43 12	49.62 119	87.24 54	71.99 69	83.75 78	85.14 137

ab-mvs		66.65 214	66.42 198	67.37 255	76.17 230	41.73 313	70.41 290	76.14 215	53.99 238	65.98 201	83.51 175	49.48 120	76.24 291	48.60 254	73.46 211	84.14 167

v8		70.33 128	69.28 135	73.49 138	73.15 275	50.22 215	78.62 126	80.78 135	60.79 89	66.45 194	82.11 207	49.35 121	84.98 114	63.58 135	68.71 287	85.28 133

IS-MVSNet		71.57 105	71.00 106	73.27 146	78.86 148	45.63 276	80.22 100	78.69 169	64.14 35	66.46 193	87.36 85	49.30 122	85.60 98	50.26 240	83.71 79	88.59 13

XXY-MVS		60.68 281	61.67 261	57.70 344	70.43 326	38.45 342	64.19 341	66.47 316	48.05 312	63.22 248	80.86 232	49.28 123	60.47 366	45.25 289	67.28 300	74.19 339

cdsmvs_eth3d_5k		17.50 394	23.34 393	0.00 414	0.00 437	0.00 438	0.00 425	78.63 171	0.00 432	0.00 433	82.18 201	49.25 124	0.00 431	0.00 432	0.00 429	0.00 429

PVSNet_Blended_VisFu		71.45 109	70.39 116	74.65 95	82.01 83	58.82 74	79.93 105	80.35 143	55.09 213	65.82 208	82.16 204	49.17 125	82.64 168	60.34 160	78.62 145	82.50 217

PVSNet_BlendedMVS		68.56 173	67.72 165	71.07 200	77.03 214	50.57 208	74.50 224	81.52 108	53.66 243	64.22 240	79.72 252	49.13 126	82.87 159	55.82 190	73.92 200	79.77 271

PVSNet_Blended		68.59 169	67.72 165	71.19 195	77.03 214	50.57 208	72.51 259	81.52 108	51.91 258	64.22 240	77.77 290	49.13 126	82.87 159	55.82 190	79.58 124	80.14 262

DU-MVS		70.01 133	69.53 130	71.44 186	78.05 177	44.13 289	75.01 212	81.51 110	64.37 28	68.20 155	84.52 153	49.12 128	82.82 163	54.62 203	70.43 252	87.37 52

Baseline_NR-MVSNet		67.05 205	67.56 168	65.50 285	75.65 236	37.70 350	75.42 202	74.65 244	59.90 113	68.14 159	83.15 182	49.12 128	77.20 269	52.23 222	69.78 269	81.60 231

VPNet		67.52 194	68.11 161	65.74 282	79.18 140	36.80 359	72.17 264	72.83 264	62.04 72	67.79 170	85.83 131	48.88 130	76.60 285	51.30 232	72.97 220	83.81 179

MTAPA		76.90 34	76.42 38	78.35 35	86.08 37	63.57 2	74.92 216	80.97 132	65.13 15	75.77 40	90.88 19	48.63 131	86.66 73	77.23 25	88.17 33	84.81 150

原ACMM1				74.69 92	85.39 47	59.40 57		83.42 73	51.47 265	70.27 121	86.61 104	48.61 132	86.51 79	53.85 211	87.96 39	78.16 286

v148		68.24 180	67.19 187	71.40 189	70.43 326	47.77 253	75.76 197	77.03 204	58.91 133	67.36 176	80.10 245	48.60 133	81.89 181	60.01 163	66.52 306	84.53 156

PGM-MVS		76.77 37	76.06 42	78.88 28	86.14 35	62.73 9	82.55 70	83.74 64	61.71 76	72.45 101	90.34 32	48.48 134	88.13 37	72.32 65	86.85 51	85.78 106

Test By Simon												48.33 135

CP-MVS		77.12 32	76.68 32	78.43 33	86.05 38	63.18 5	87.55 10	83.45 72	62.44 64	72.68 95	90.50 26	48.18 136	87.34 53	73.59 56	85.71 60	84.76 153

MVS		67.37 196	66.33 202	70.51 211	75.46 241	50.94 200	73.95 234	81.85 103	41.57 370	62.54 264	78.57 274	47.98 137	85.47 105	52.97 218	82.05 96	75.14 324

XVS		77.17 31	76.56 36	79.00 23	86.32 29	62.62 11	85.83 22	83.92 55	64.55 23	72.17 102	90.01 43	47.95 138	88.01 40	71.55 74	86.74 53	86.37 82

X-MVStestdata		70.21 130	67.28 181	79.00 23	86.32 29	62.62 11	85.83 22	83.92 55	64.55 23	72.17 102	6.49 426	47.95 138	88.01 40	71.55 74	86.74 53	86.37 82

SDMVSNet		68.03 183	68.10 162	67.84 249	77.13 210	48.72 242	65.32 332	79.10 159	58.02 152	65.08 223	82.55 191	47.83 140	73.40 303	63.92 130	73.92 200	81.41 234

MAR-MVS		71.51 106	70.15 122	75.60 80	81.84 87	59.39 58	81.38 87	82.90 89	54.90 223	68.08 161	78.70 268	47.73 141	85.51 102	51.68 231	84.17 74	81.88 229
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
PAPM		67.92 187	66.69 191	71.63 180	78.09 175	49.02 235	77.09 166	81.24 124	51.04 272	60.91 284	83.98 165	47.71 142	84.99 112	40.81 321	79.32 130	80.90 249

SR-MVS		76.13 46	75.70 47	77.40 51	85.87 40	61.20 29	85.52 27	82.19 98	59.99 112	75.10 48	90.35 31	47.66 143	86.52 78	71.64 73	82.99 83	84.47 159

cl22		67.47 195	66.45 195	70.54 210	69.85 337	46.49 264	73.85 239	77.35 200	55.07 216	65.51 211	77.92 283	47.64 144	81.10 198	61.58 153	69.32 276	84.01 171

v10		70.21 130	69.02 140	73.81 118	73.51 272	50.92 202	78.74 123	81.39 113	60.05 111	66.39 195	81.83 212	47.58 145	85.41 108	62.80 140	68.86 286	85.09 141

mamv4		56.85 312	58.00 300	53.43 366	72.46 291	54.47 141	57.56 379	54.74 381	38.81 384	57.42 323	79.45 259	47.57 146	38.70 419	60.88 156	53.07 380	67.11 389

v1144		70.42 126	69.31 134	73.76 121	73.22 273	50.64 207	77.83 145	81.43 112	58.58 141	69.40 138	81.16 223	47.53 147	85.29 110	64.01 128	70.64 248	85.34 130

v2v482		70.50 124	69.45 133	73.66 129	72.62 285	50.03 220	77.58 150	80.51 139	59.90 113	69.52 134	82.14 205	47.53 147	84.88 120	65.07 120	70.17 260	86.09 96

pm-mvs1		65.24 233	64.97 223	66.04 277	72.38 292	39.40 334	72.62 256	75.63 221	55.53 202	62.35 270	83.18 181	47.45 149	76.47 288	49.06 251	66.54 305	82.24 222

HY-MVS	56.14 13	64.55 241	63.89 230	66.55 265	74.73 253	41.02 318	69.96 295	74.43 245	49.29 294	61.66 276	80.92 230	47.43 150	76.68 284	44.91 290	71.69 238	81.94 227

cl____		67.18 201	66.26 206	69.94 219	70.20 329	45.74 272	73.30 245	76.83 207	55.10 211	65.27 216	79.57 255	47.39 151	80.53 211	59.41 171	69.22 280	83.53 193

DIV-MVS_self_test		67.18 201	66.26 206	69.94 219	70.20 329	45.74 272	73.29 247	76.83 207	55.10 211	65.27 216	79.58 254	47.38 152	80.53 211	59.43 170	69.22 280	83.54 192

eth_miper_zixun_eth		67.63 192	66.28 205	71.67 178	71.60 305	48.33 246	73.68 242	77.88 188	55.80 196	65.91 203	78.62 273	47.35 153	82.88 158	59.45 169	66.25 307	83.81 179

OPM-MVS		74.73 58	74.25 63	76.19 68	80.81 106	59.01 70	82.60 69	83.64 66	63.74 39	72.52 98	87.49 81	47.18 154	85.88 93	69.47 84	80.78 107	83.66 189
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline1		63.81 249	63.87 232	63.62 300	76.29 228	36.36 362	71.78 270	67.29 309	56.05 191	64.23 239	82.95 183	47.11 155	74.41 300	47.30 265	61.85 343	80.10 263

pcd_1.5k_mvsjas		3.92 400	5.23 403	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	47.05 156	0.00 431	0.00 432	0.00 429	0.00 429

PS-MVSNAJss		72.24 93	71.21 101	75.31 84	78.50 157	55.93 115	81.63 82	82.12 99	56.24 187	70.02 126	85.68 134	47.05 156	84.34 129	65.27 118	74.41 195	85.67 113

PS-MVSNAJ		70.51 123	69.70 128	72.93 151	81.52 91	55.79 119	74.92 216	79.00 161	55.04 219	69.88 130	78.66 270	47.05 156	82.19 176	61.61 151	79.58 124	80.83 250

WTY-MVS		59.75 291	60.39 278	57.85 342	72.32 294	37.83 347	61.05 362	64.18 334	45.95 338	61.91 272	79.11 265	47.01 159	60.88 365	42.50 311	69.49 275	74.83 330

xiu_mvs_v2_base		70.52 122	69.75 126	72.84 153	81.21 100	55.63 123	75.11 209	78.92 163	54.92 222	69.96 129	79.68 253	47.00 160	82.09 178	61.60 152	79.37 127	80.81 251

v144192		69.71 141	68.51 151	73.33 145	73.10 276	50.13 217	77.54 153	80.64 136	56.65 172	68.57 150	80.55 236	46.87 161	84.96 116	62.98 138	69.66 273	84.89 148

PEN-MVS		66.60 215	66.45 195	67.04 258	77.11 212	36.56 361	77.03 168	80.42 141	62.95 50	62.51 266	84.03 163	46.69 162	79.07 239	44.22 291	63.08 334	85.51 119

mPP-MVS		76.54 39	75.93 44	78.34 36	86.47 26	63.50 3	85.74 25	82.28 97	62.90 52	71.77 106	90.26 34	46.61 163	86.55 77	71.71 72	85.66 61	84.97 146

CP-MVSNet		66.49 218	66.41 199	66.72 260	77.67 191	36.33 364	76.83 175	79.52 153	62.45 63	62.54 264	83.47 177	46.32 164	78.37 248	45.47 286	63.43 331	85.45 124

V42		68.65 168	67.35 179	72.56 158	68.93 348	50.18 216	72.90 252	79.47 154	56.92 169	69.45 137	80.26 242	46.29 165	82.99 153	64.07 126	67.82 295	84.53 156

1112_ss		64.00 248	63.36 240	65.93 279	79.28 136	42.58 305	71.35 273	72.36 268	46.41 331	60.55 287	77.89 285	46.27 166	73.28 304	46.18 274	69.97 264	81.92 228

MSLP-MVS++		73.77 70	73.47 71	74.66 94	83.02 74	59.29 61	82.30 77	81.88 102	59.34 127	71.59 109	86.83 94	45.94 167	83.65 142	65.09 119	85.22 63	81.06 246

PS-CasMVS		66.42 219	66.32 203	66.70 262	77.60 199	36.30 366	76.94 170	79.61 151	62.36 65	62.43 268	83.66 171	45.69 168	78.37 248	45.35 288	63.26 332	85.42 127

APD-MVS_3200maxsize		74.96 54	74.39 61	76.67 60	82.20 81	58.24 80	83.67 54	83.29 81	58.41 144	73.71 74	90.14 36	45.62 169	85.99 90	69.64 82	82.85 89	85.78 106

DTE-MVSNet		65.58 227	65.34 218	66.31 269	76.06 232	34.79 374	76.43 181	79.38 156	62.55 61	61.66 276	83.83 168	45.60 170	79.15 237	41.64 320	60.88 349	85.00 143

BH-w/o		66.85 209	65.83 211	69.90 222	79.29 135	52.46 181	74.66 222	76.65 210	54.51 231	64.85 229	78.12 277	45.59 171	82.95 155	43.26 304	75.54 187	74.27 338

h-mvs33		72.71 84	71.49 93	76.40 65	81.99 85	59.58 55	76.92 171	76.74 209	60.40 97	74.81 57	85.95 127	45.54 172	85.76 96	70.41 80	70.61 250	83.86 178

hse-mvs2		71.04 112	69.86 125	74.60 98	79.58 130	57.12 99	73.96 233	75.25 231	60.40 97	74.81 57	81.95 209	45.54 172	82.90 156	70.41 80	66.83 303	83.77 183

HQP2-MVS												45.46 174

HQP-MVS		73.45 72	72.80 78	75.40 82	80.66 108	54.94 135	82.31 74	83.90 57	62.10 68	67.85 164	85.54 138	45.46 174	86.93 66	67.04 102	80.35 115	84.32 161

ACMMP		76.02 47	75.33 51	78.07 38	85.20 49	61.91 20	85.49 29	84.44 44	63.04 49	69.80 132	89.74 49	45.43 176	87.16 60	72.01 68	82.87 88	85.14 137
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
OMC-MVS		71.40 110	70.60 112	73.78 119	76.60 223	53.15 164	79.74 110	79.78 147	58.37 145	68.75 147	86.45 112	45.43 176	80.60 210	62.58 141	77.73 157	87.58 45

BH-untuned		68.27 178	67.29 180	71.21 194	79.74 126	53.22 163	76.06 189	77.46 198	57.19 165	66.10 199	81.61 216	45.37 178	83.50 145	45.42 287	76.68 175	76.91 308

v1192		69.97 135	68.68 148	73.85 116	73.19 274	50.94 200	77.68 149	81.36 115	57.51 162	68.95 146	80.85 233	45.28 179	85.33 109	62.97 139	70.37 254	85.27 134

HQP_MVS		74.31 65	73.73 69	76.06 69	81.41 94	56.31 105	84.22 43	84.01 52	64.52 25	69.27 140	86.10 121	45.26 180	87.21 58	68.16 91	80.58 111	84.65 154

plane_prior6					81.20 101	56.24 109						45.26 180

CL-MVSNet_self_test		61.53 276	60.94 274	63.30 303	68.95 347	36.93 358	67.60 312	72.80 265	55.67 199	59.95 294	76.63 305	45.01 182	72.22 310	39.74 328	62.09 342	80.74 253

SR-MVS-dyc-post		74.57 62	73.90 66	76.58 63	83.49 67	59.87 52	84.29 40	81.36 115	58.07 150	73.14 84	90.07 37	44.74 183	85.84 94	68.20 89	81.76 101	84.03 169

v1921920		69.47 153	68.17 160	73.36 144	73.06 277	50.10 218	77.39 156	80.56 137	56.58 180	68.59 148	80.37 238	44.72 184	84.98 114	62.47 144	69.82 268	85.00 143

RRT-MVS		71.46 108	70.70 111	73.74 124	77.76 187	49.30 232	76.60 177	80.45 140	61.25 82	68.17 157	84.78 146	44.64 185	84.90 117	64.79 121	77.88 156	87.03 59

Vis-MVSNet (Re-imp)		63.69 250	63.88 231	63.14 305	74.75 252	31.04 397	71.16 278	63.64 339	56.32 184	59.80 297	84.99 142	44.51 186	75.46 295	39.12 330	80.62 109	82.92 208

DP-MVS Recon		72.15 98	70.73 110	76.40 65	86.57 24	57.99 82	81.15 90	82.96 87	57.03 167	66.78 186	85.56 135	44.50 187	88.11 38	51.77 229	80.23 118	83.10 206

TAMVS		66.78 212	65.27 220	71.33 193	79.16 142	53.67 153	73.84 240	69.59 290	52.32 255	65.28 215	81.72 214	44.49 188	77.40 266	42.32 312	78.66 144	82.92 208

Vis-MVSNet		72.18 94	71.37 97	74.61 97	81.29 97	55.41 129	80.90 92	78.28 185	60.73 91	69.23 143	88.09 69	44.36 189	82.65 167	57.68 178	81.75 103	85.77 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
旧先验1					83.04 73	53.15 164		67.52 306			87.85 76	44.08 190			80.76 108	78.03 291

Test_1112_low_res		62.32 266	61.77 260	64.00 299	79.08 144	39.53 333	68.17 307	70.17 283	43.25 359	59.03 307	79.90 247	44.08 190	71.24 315	43.79 299	68.42 290	81.25 240

fmvsm_s_conf0.5_n_2		69.82 138	69.27 136	71.46 184	72.00 299	51.08 197	73.30 245	67.79 305	55.06 218	75.24 45	87.51 80	44.02 192	77.00 274	75.67 36	72.86 221	86.31 91

MVSFormer		71.50 107	70.38 117	74.88 89	78.76 151	57.15 97	82.79 64	78.48 176	51.26 269	69.49 135	83.22 179	43.99 193	83.24 149	66.06 109	79.37 127	84.23 164

lupinMVS		69.57 149	68.28 159	73.44 141	78.76 151	57.15 97	76.57 178	73.29 260	46.19 333	69.49 135	82.18 201	43.99 193	79.23 232	64.66 123	79.37 127	83.93 173

v7n		69.01 162	67.36 178	73.98 114	72.51 289	52.65 175	78.54 130	81.30 120	60.26 106	62.67 260	81.62 215	43.61 195	84.49 126	57.01 182	68.70 288	84.79 151

CDS-MVSNet		66.80 211	65.37 217	71.10 199	78.98 145	53.13 166	73.27 248	71.07 277	52.15 256	64.72 230	80.23 243	43.56 196	77.10 270	45.48 285	78.88 137	83.05 207
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
jason		69.65 145	68.39 158	73.43 142	78.27 168	56.88 101	77.12 165	73.71 257	46.53 330	69.34 139	83.22 179	43.37 197	79.18 233	64.77 122	79.20 132	84.23 164
jason: jason.
v1240		69.24 159	67.91 163	73.25 148	73.02 279	49.82 222	77.21 163	80.54 138	56.43 182	68.34 154	80.51 237	43.33 198	84.99 112	62.03 148	69.77 271	84.95 147

LCM-MVSNet-Re		61.88 273	61.35 265	63.46 301	74.58 257	31.48 396	61.42 357	58.14 367	58.71 138	53.02 363	79.55 256	43.07 199	76.80 279	45.69 279	77.96 154	82.11 226

RE-MVS-def			73.71 70		83.49 67	59.87 52	84.29 40	81.36 115	58.07 150	73.14 84	90.07 37	43.06 200		68.20 89	81.76 101	84.03 169

baseline2		63.42 252	61.26 268	69.89 223	72.55 287	47.62 255	71.54 271	68.38 301	50.11 282	54.82 345	75.55 325	43.06 200	80.96 201	48.13 259	67.16 301	81.11 244

fmvsm_s_conf0.1_n_2		69.64 146	69.01 142	71.52 182	71.66 304	51.04 198	73.39 244	67.14 311	55.02 220	75.11 47	87.64 79	42.94 202	77.01 273	75.55 37	72.63 227	86.52 78

FA-MVS(test-final)		69.82 138	68.48 152	73.84 117	78.44 160	50.04 219	75.58 201	78.99 162	58.16 148	67.59 173	82.14 205	42.66 203	85.63 97	56.60 184	76.19 179	85.84 104

BH-RMVSNet		68.81 164	67.42 175	72.97 150	80.11 122	52.53 179	74.26 228	76.29 212	58.48 143	68.38 153	84.20 158	42.59 204	83.83 138	46.53 271	75.91 181	82.56 213

LFMVS		71.78 101	71.59 90	72.32 165	83.40 70	46.38 265	79.75 109	71.08 276	64.18 32	72.80 93	88.64 64	42.58 205	83.72 140	57.41 181	84.49 70	86.86 64

test_yl		69.69 142	69.13 137	71.36 190	78.37 164	45.74 272	74.71 220	80.20 144	57.91 157	70.01 127	83.83 168	42.44 206	82.87 159	54.97 199	79.72 121	85.48 120

DCV-MVSNet		69.69 142	69.13 137	71.36 190	78.37 164	45.74 272	74.71 220	80.20 144	57.91 157	70.01 127	83.83 168	42.44 206	82.87 159	54.97 199	79.72 121	85.48 120

3Dnovator	64.47 5	72.49 88	71.39 96	75.79 72	77.70 189	58.99 71	80.66 96	83.15 85	62.24 66	65.46 212	86.59 105	42.38 208	85.52 101	59.59 168	84.72 65	82.85 211

VDD-MVS		72.50 87	72.09 86	73.75 123	81.58 90	49.69 226	77.76 148	77.63 194	63.21 47	73.21 81	89.02 56	42.14 209	83.32 147	61.72 150	82.50 92	88.25 21

3Dnovator+	66.72 4	75.84 49	74.57 59	79.66 9	82.40 79	59.92 51	85.83 22	86.32 16	66.92 7	67.80 169	89.24 54	42.03 210	89.38 19	64.07 126	86.50 57	89.69 3

MVS_111021_LR		69.50 152	68.78 146	71.65 179	78.38 162	59.33 59	74.82 218	70.11 284	58.08 149	67.83 168	84.68 147	41.96 211	76.34 290	65.62 116	77.54 159	79.30 276

CPTT-MVS		72.78 82	72.08 87	74.87 90	84.88 57	61.41 26	84.15 46	77.86 189	55.27 208	67.51 175	88.08 70	41.93 212	81.85 182	69.04 87	80.01 119	81.35 239

GBi-Net		67.21 198	66.55 193	69.19 233	77.63 193	43.33 297	77.31 158	77.83 190	56.62 176	65.04 225	82.70 185	41.85 213	80.33 216	47.18 266	72.76 223	83.92 174

test1		67.21 198	66.55 193	69.19 233	77.63 193	43.33 297	77.31 158	77.83 190	56.62 176	65.04 225	82.70 185	41.85 213	80.33 216	47.18 266	72.76 223	83.92 174

FMVSNet2		66.93 208	66.31 204	68.79 240	77.63 193	42.98 302	76.11 187	77.47 196	56.62 176	65.22 222	82.17 203	41.85 213	80.18 222	47.05 269	72.72 226	83.20 201

CostFormer		64.04 247	62.51 251	68.61 242	71.88 301	45.77 271	71.30 275	70.60 281	47.55 318	64.31 236	76.61 308	41.63 216	79.62 227	49.74 243	69.00 283	80.42 256

AdaColmap		69.99 134	68.66 149	73.97 115	84.94 54	57.83 84	82.63 68	78.71 168	56.28 186	64.34 234	84.14 160	41.57 217	87.06 64	46.45 272	78.88 137	77.02 304

Effi-MVS+-dtu		69.64 146	67.53 171	75.95 70	76.10 231	62.29 15	80.20 101	76.06 217	59.83 117	65.26 219	77.09 298	41.56 218	84.02 135	60.60 159	71.09 246	81.53 232

QAPM		70.05 132	68.81 145	73.78 119	76.54 225	53.43 159	83.23 57	83.48 70	52.89 249	65.90 204	86.29 115	41.55 219	86.49 80	51.01 234	78.40 148	81.42 233

VDDNet		71.81 100	71.33 98	73.26 147	82.80 78	47.60 256	78.74 123	75.27 230	59.59 123	72.94 90	89.40 51	41.51 220	83.91 137	58.75 173	82.99 83	88.26 20

CHOSEN 1792x2688		65.08 236	62.84 248	71.82 173	81.49 93	56.26 108	66.32 320	74.20 252	40.53 376	63.16 251	78.65 271	41.30 221	77.80 258	45.80 278	74.09 197	81.40 236

新几何1				70.76 205	85.66 41	61.13 30		66.43 317	44.68 345	70.29 120	86.64 101	41.29 222	75.23 296	49.72 244	81.75 103	75.93 315

tpmrst		58.24 301	58.70 292	56.84 346	66.97 360	34.32 380	69.57 299	61.14 357	47.17 325	58.58 313	71.60 356	41.28 223	60.41 367	49.20 249	62.84 335	75.78 317

tfpnnormal		62.47 264	61.63 262	64.99 292	74.81 251	39.01 336	71.22 276	73.72 256	55.22 210	60.21 288	80.09 246	41.26 224	76.98 276	30.02 387	68.09 293	78.97 280

sd_testset		64.46 242	64.45 226	64.51 295	77.13 210	42.25 308	62.67 350	72.11 270	58.02 152	65.08 223	82.55 191	41.22 225	69.88 324	47.32 264	73.92 200	81.41 234

HPM-MVS_fast		74.30 66	73.46 72	76.80 56	84.45 60	59.04 69	83.65 55	81.05 129	60.15 109	70.43 118	89.84 46	41.09 226	85.59 99	67.61 97	82.90 87	85.77 109

BP-MVS1		73.41 73	72.25 84	76.88 54	76.68 220	53.70 152	79.15 118	81.07 128	60.66 92	71.81 105	87.39 84	40.93 227	87.24 54	71.23 76	81.29 106	89.71 2

114514_t		70.83 117	69.56 129	74.64 96	86.21 31	54.63 140	82.34 73	81.81 104	48.22 308	63.01 255	85.83 131	40.92 228	87.10 62	57.91 177	79.79 120	82.18 223

WB-MVSnew		59.66 292	59.69 282	59.56 325	75.19 246	35.78 371	69.34 301	64.28 333	46.88 327	61.76 275	75.79 321	40.61 229	65.20 352	32.16 370	71.21 243	77.70 293

HyFIR lowres test		65.67 226	63.01 246	73.67 128	79.97 124	55.65 122	69.07 303	75.52 225	42.68 364	63.53 245	77.95 281	40.43 230	81.64 185	46.01 276	71.91 236	83.73 185

miper_lstm_enhance		62.03 271	60.88 275	65.49 286	66.71 363	46.25 266	56.29 384	75.70 220	50.68 275	61.27 280	75.48 327	40.21 231	68.03 333	56.31 187	65.25 314	82.18 223

GDP-MVS		72.64 85	71.28 100	76.70 57	77.72 188	54.22 145	79.57 114	84.45 43	55.30 207	71.38 112	86.97 92	39.94 232	87.00 65	67.02 104	79.20 132	88.89 9

FMVSNet3		66.32 220	65.61 215	68.46 243	76.48 226	42.34 306	74.98 214	77.15 203	55.83 194	65.04 225	81.16 223	39.91 233	80.14 223	47.18 266	72.76 223	82.90 210

Syy-MVS		56.00 321	56.23 314	55.32 353	74.69 254	26.44 412	65.52 327	57.49 371	50.97 273	56.52 329	72.18 349	39.89 234	68.09 331	24.20 404	64.59 321	71.44 367

MVP-Stereo		65.41 230	63.80 233	70.22 213	77.62 197	55.53 127	76.30 183	78.53 174	50.59 278	56.47 331	78.65 271	39.84 235	82.68 166	44.10 295	72.12 235	72.44 353
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TR-MVS		66.59 217	65.07 222	71.17 197	79.18 140	49.63 228	73.48 243	75.20 234	52.95 247	67.90 162	80.33 241	39.81 236	83.68 141	43.20 305	73.56 208	80.20 260

pmmvs6		63.69 250	62.82 249	66.27 271	70.63 321	39.27 335	73.13 249	75.47 227	52.69 251	59.75 299	82.30 199	39.71 237	77.03 272	47.40 263	64.35 323	82.53 215

XVG-OURS-SEG-HR		68.81 164	67.47 174	72.82 155	74.40 262	56.87 102	70.59 286	79.04 160	54.77 225	66.99 183	86.01 125	39.57 238	78.21 251	62.54 142	73.33 213	83.37 196

Anonymous20231211		69.28 157	68.47 154	71.73 176	80.28 114	47.18 260	79.98 103	82.37 96	54.61 227	67.24 178	84.01 164	39.43 239	82.41 174	55.45 197	72.83 222	85.62 116

Fast-Effi-MVS+-dtu		67.37 196	65.33 219	73.48 139	72.94 280	57.78 86	77.47 155	76.88 205	57.60 161	61.97 271	76.85 302	39.31 240	80.49 214	54.72 202	70.28 258	82.17 225

dmvs_testset		50.16 353	51.90 343	44.94 388	66.49 365	11.78 428	61.01 363	51.50 390	51.17 271	50.30 378	67.44 382	39.28 241	60.29 368	22.38 407	57.49 365	62.76 393

ACMP	63.53 6	72.30 92	71.20 102	75.59 81	80.28 114	57.54 87	82.74 66	82.84 92	60.58 94	65.24 220	86.18 118	39.25 242	86.03 89	66.95 105	76.79 173	83.22 200
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20240529		69.91 136	69.02 140	72.56 158	80.19 119	47.65 254	77.56 152	80.99 131	55.45 205	69.88 130	86.76 96	39.24 243	82.18 177	54.04 208	77.10 170	87.85 33

LPG-MVS_test		72.74 83	71.74 89	75.76 73	80.22 116	57.51 89	82.55 70	83.40 74	61.32 79	66.67 190	87.33 86	39.15 244	86.59 74	67.70 95	77.30 166	83.19 202

LGP-MVS_train				75.76 73	80.22 116	57.51 89		83.40 74	61.32 79	66.67 190	87.33 86	39.15 244	86.59 74	67.70 95	77.30 166	83.19 202

TAPA-MVS	59.36 10	66.60 215	65.20 221	70.81 204	76.63 222	48.75 240	76.52 180	80.04 146	50.64 277	65.24 220	84.93 143	39.15 244	78.54 247	36.77 344	76.88 172	85.14 137
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OpenMVS	61.03 9	68.85 163	67.56 168	72.70 157	74.26 266	53.99 148	81.21 89	81.34 119	52.70 250	62.75 259	85.55 137	38.86 247	84.14 131	48.41 256	83.01 82	79.97 264

sss		56.17 320	56.57 310	54.96 355	66.93 361	36.32 365	57.94 374	61.69 354	41.67 368	58.64 311	75.32 330	38.72 248	56.25 390	42.04 315	66.19 308	72.31 357

ACMM	61.98 7	70.80 119	69.73 127	74.02 113	80.59 113	58.59 77	82.68 67	82.02 101	55.46 204	67.18 180	84.39 157	38.51 249	83.17 151	60.65 158	76.10 180	80.30 259
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVSTER		67.16 203	65.58 216	71.88 171	70.37 328	49.70 224	70.25 292	78.45 179	51.52 263	69.16 144	80.37 238	38.45 250	82.50 171	60.19 161	71.46 241	83.44 195

test_djsdf		69.45 154	67.74 164	74.58 99	74.57 258	54.92 137	82.79 64	78.48 176	51.26 269	65.41 213	83.49 176	38.37 251	83.24 149	66.06 109	69.25 279	85.56 117

MonoMVSNet		64.15 245	63.31 242	66.69 263	70.51 324	44.12 291	74.47 225	74.21 251	57.81 159	63.03 253	76.62 306	38.33 252	77.31 267	54.22 207	60.59 354	78.64 282

tpm2		62.07 270	60.10 280	67.99 248	72.79 282	43.86 293	71.05 282	66.85 314	43.14 361	62.77 257	75.39 329	38.32 253	80.80 207	41.69 317	68.88 284	79.32 275

tpm cat1		59.25 296	56.95 306	66.15 274	72.19 296	46.96 261	68.09 308	65.76 321	40.03 380	57.81 319	70.56 363	38.32 253	74.51 299	38.26 335	61.50 346	77.00 305

CNLPA		65.43 229	64.02 229	69.68 225	78.73 153	58.07 81	77.82 146	70.71 280	51.49 264	61.57 278	83.58 174	38.23 255	70.82 316	43.90 297	70.10 262	80.16 261

1314		64.61 240	63.21 244	68.80 239	71.87 302	47.46 257	73.95 234	78.39 184	42.88 363	59.97 293	76.60 309	38.11 256	79.39 230	54.84 201	72.32 231	79.55 272

testdata				64.66 293	81.52 91	52.93 169		65.29 325	46.09 334	73.88 72	87.46 83	38.08 257	66.26 347	53.31 216	78.48 146	74.78 332

FMVSNet1		66.70 213	65.87 210	69.19 233	77.49 201	43.33 297	77.31 158	77.83 190	56.45 181	64.60 233	82.70 185	38.08 257	80.33 216	46.08 275	72.31 232	83.92 174

UniMVSNet_ETH3D		67.60 193	67.07 189	69.18 236	77.39 204	42.29 307	74.18 230	75.59 223	60.37 100	66.77 187	86.06 123	37.64 259	78.93 245	52.16 223	73.49 209	86.32 88

EPNet_dtu		61.90 272	61.97 258	61.68 313	72.89 281	39.78 329	75.85 195	65.62 323	55.09 213	54.56 349	79.36 261	37.59 260	67.02 342	39.80 327	76.95 171	78.25 285
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IterMVS-SCA-FT		62.49 263	61.52 263	65.40 287	71.99 300	50.80 205	71.15 279	69.63 289	45.71 339	60.61 286	77.93 282	37.45 261	65.99 349	55.67 194	63.50 330	79.42 274

SCA		60.49 284	58.38 295	66.80 259	74.14 268	48.06 249	63.35 346	63.23 342	49.13 296	59.33 305	72.10 351	37.45 261	74.27 301	44.17 292	62.57 337	78.05 288

tt0805		67.77 190	67.24 185	69.34 232	74.87 249	40.08 325	77.36 157	81.37 114	55.31 206	66.33 196	84.65 149	37.35 263	82.55 170	55.65 195	72.28 233	85.39 129

IterMVS		62.79 261	61.27 267	67.35 256	69.37 343	52.04 189	71.17 277	68.24 303	52.63 252	59.82 296	76.91 301	37.32 264	72.36 307	52.80 219	63.19 333	77.66 294
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpn200view9		63.18 257	62.18 256	66.21 272	76.85 217	39.62 331	71.96 268	69.44 293	56.63 174	62.61 262	79.83 248	37.18 265	79.17 234	31.84 374	73.25 215	79.83 268

thres400		63.31 253	62.18 256	66.72 260	76.85 217	39.62 331	71.96 268	69.44 293	56.63 174	62.61 262	79.83 248	37.18 265	79.17 234	31.84 374	73.25 215	81.36 237

tpm		57.34 308	58.16 297	54.86 356	71.80 303	34.77 375	67.47 315	56.04 380	48.20 309	60.10 290	76.92 300	37.17 267	53.41 400	40.76 322	65.01 315	76.40 311

test222					83.14 71	58.68 76	72.57 258	63.45 340	41.78 366	67.56 174	86.12 120	37.13 268			78.73 142	74.98 328

AUN-MVS		68.45 176	66.41 199	74.57 100	79.53 132	57.08 100	73.93 236	75.23 232	54.44 232	66.69 189	81.85 211	37.10 269	82.89 157	62.07 146	66.84 302	83.75 184

thres200		62.20 269	61.16 271	65.34 288	75.38 243	39.99 327	69.60 298	69.29 295	55.64 201	61.87 273	76.99 299	37.07 270	78.96 244	31.28 382	73.28 214	77.06 303

thres100view900		63.28 255	62.41 253	65.89 280	77.31 207	38.66 339	72.65 254	69.11 297	57.07 166	62.45 267	81.03 227	37.01 271	79.17 234	31.84 374	73.25 215	79.83 268

thres600view7		63.30 254	62.27 254	66.41 267	77.18 209	38.87 337	72.35 261	69.11 297	56.98 168	62.37 269	80.96 229	37.01 271	79.00 243	31.43 381	73.05 219	81.36 237

DP-MVS		65.68 225	63.66 236	71.75 175	84.93 55	56.87 102	80.74 95	73.16 261	53.06 246	59.09 306	82.35 197	36.79 273	85.94 92	32.82 368	69.96 265	72.45 352

mvsmamba		68.47 174	66.56 192	74.21 110	79.60 129	52.95 168	74.94 215	75.48 226	52.09 257	60.10 290	83.27 178	36.54 274	84.70 122	59.32 172	77.69 158	84.99 145

XVG-OURS		68.76 167	67.37 177	72.90 152	74.32 265	57.22 92	70.09 294	78.81 165	55.24 209	67.79 170	85.81 133	36.54 274	78.28 250	62.04 147	75.74 184	83.19 202

ECVR-MVS		67.72 191	67.51 172	68.35 245	79.46 133	36.29 367	74.79 219	66.93 313	58.72 136	67.19 179	88.05 71	36.10 276	81.38 191	52.07 224	84.25 72	87.39 50

test1111		67.21 198	67.14 188	67.42 254	79.24 138	34.76 376	73.89 238	65.65 322	58.71 138	66.96 184	87.95 74	36.09 277	80.53 211	52.03 225	83.79 77	86.97 61

pmmvs4		61.48 278	59.39 284	67.76 250	71.57 306	53.86 149	71.42 272	65.34 324	44.20 350	59.46 301	77.92 283	35.90 278	74.71 298	43.87 298	64.87 317	74.71 334

CR-MVSNet		59.91 289	57.90 301	65.96 278	69.96 334	52.07 187	65.31 333	63.15 343	42.48 365	59.36 302	74.84 332	35.83 279	70.75 317	45.50 284	64.65 319	75.06 325

Patchmtry		57.16 309	56.47 311	59.23 329	69.17 346	34.58 378	62.98 348	63.15 343	44.53 346	56.83 326	74.84 332	35.83 279	68.71 328	40.03 325	60.91 348	74.39 337

dmvs_re		56.77 313	56.83 308	56.61 347	69.23 344	41.02 318	58.37 371	64.18 334	50.59 278	57.45 322	71.42 357	35.54 281	58.94 376	37.23 340	67.45 298	69.87 380

RPMNet		61.53 276	58.42 294	70.86 203	69.96 334	52.07 187	65.31 333	81.36 115	43.20 360	59.36 302	70.15 368	35.37 282	85.47 105	36.42 351	64.65 319	75.06 325

CANet_DTU		68.18 181	67.71 167	69.59 227	74.83 250	46.24 267	78.66 125	76.85 206	59.60 120	63.45 246	82.09 208	35.25 283	77.41 265	59.88 165	78.76 141	85.14 137

thisisatest0530		67.92 187	65.78 212	74.33 106	76.29 228	51.03 199	76.89 172	74.25 250	53.67 242	65.59 210	81.76 213	35.15 284	85.50 103	55.94 188	72.47 228	86.47 79

tttt0517		67.83 189	65.66 214	74.33 106	76.69 219	50.82 204	77.86 143	73.99 254	54.54 230	64.64 232	82.53 194	35.06 285	85.50 103	55.71 193	69.91 266	86.67 72

test_0402		63.25 256	61.01 273	69.96 218	80.00 123	54.37 144	76.86 174	72.02 271	54.58 229	58.71 309	80.79 235	35.00 286	84.36 128	26.41 401	64.71 318	71.15 371

thisisatest0515		65.83 224	63.50 238	72.82 155	73.75 270	49.50 229	71.32 274	73.12 263	49.39 292	63.82 242	76.50 312	34.95 287	84.84 121	53.20 217	75.49 188	84.13 168

sam_mvs1												34.74 288				78.05 288

pmmvs5		56.47 316	55.68 318	58.86 333	61.41 390	36.71 360	66.37 319	62.75 345	40.38 377	53.70 356	76.62 306	34.56 289	67.05 341	40.02 326	65.27 313	72.83 347

patchmatchnet-post											64.03 394	34.50 290	74.27 301

PatchmatchNet		59.84 290	58.24 296	64.65 294	73.05 278	46.70 263	69.42 300	62.18 352	47.55 318	58.88 308	71.96 353	34.49 291	69.16 326	42.99 307	63.60 328	78.07 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmatch-test		49.08 356	48.28 358	51.50 378	64.40 376	30.85 398	45.68 408	48.46 400	35.60 389	46.10 391	72.10 351	34.47 292	46.37 411	27.08 399	60.65 352	77.27 300

MS-PatchMatch		62.42 265	61.46 264	65.31 289	75.21 245	52.10 186	72.05 265	74.05 253	46.41 331	57.42 323	74.36 336	34.35 293	77.57 263	45.62 281	73.67 204	66.26 390

tpmvs		58.47 299	56.95 306	63.03 307	70.20 329	41.21 317	67.90 310	67.23 310	49.62 289	54.73 347	70.84 361	34.14 294	76.24 291	36.64 348	61.29 347	71.64 363

testing91		64.46 242	63.80 233	66.47 266	78.43 161	40.06 326	67.63 311	69.59 290	59.06 130	63.18 250	78.05 279	34.05 295	76.99 275	48.30 257	75.87 182	82.37 220

PMMVS		53.96 333	53.26 339	56.04 349	62.60 385	50.92 202	61.17 360	56.09 379	32.81 393	53.51 361	66.84 387	34.04 296	59.93 370	44.14 294	68.18 292	57.27 402

Patchmatch-RL test		58.16 302	55.49 319	66.15 274	67.92 355	48.89 239	60.66 364	51.07 393	47.86 315	59.36 302	62.71 398	34.02 297	72.27 309	56.41 186	59.40 358	77.30 299

WB-MVS		43.26 366	43.41 366	42.83 392	63.32 381	10.32 430	58.17 373	45.20 408	45.42 340	40.44 403	67.26 385	34.01 298	58.98 375	11.96 421	24.88 415	59.20 396

test_post											3.55 428	33.90 299	66.52 344

WBMVS		60.54 283	60.61 277	60.34 323	78.00 179	35.95 369	64.55 339	64.89 327	49.63 288	63.39 247	78.70 268	33.85 300	67.65 336	42.10 314	70.35 256	77.43 297

PLC	56.13 14	65.09 235	63.21 244	70.72 207	81.04 103	54.87 138	78.57 128	77.47 196	48.51 304	55.71 334	81.89 210	33.71 301	79.71 224	41.66 318	70.37 254	77.58 295
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ET-MVSNet_ETH3D		67.96 186	65.72 213	74.68 93	76.67 221	55.62 125	75.11 209	74.74 241	52.91 248	60.03 292	80.12 244	33.68 302	82.64 168	61.86 149	76.34 177	85.78 106

GA-MVS		65.53 228	63.70 235	71.02 202	70.87 319	48.10 248	70.48 288	74.40 246	56.69 171	64.70 231	76.77 303	33.66 303	81.10 198	55.42 198	70.32 257	83.87 177

LS3D		64.71 238	62.50 252	71.34 192	79.72 128	55.71 120	79.82 107	74.72 242	48.50 305	56.62 327	84.62 150	33.59 304	82.34 175	29.65 389	75.23 189	75.97 314

sam_mvs												33.43 305

PatchT		53.17 341	53.44 338	52.33 374	68.29 353	25.34 416	58.21 372	54.41 384	44.46 348	54.56 349	69.05 376	33.32 306	60.94 364	36.93 343	61.76 345	70.73 374

test20.03		53.87 335	54.02 333	53.41 367	61.47 389	28.11 405	61.30 358	59.21 363	51.34 268	52.09 366	77.43 294	33.29 307	58.55 378	29.76 388	60.27 356	73.58 343

UBG		59.62 294	59.53 283	59.89 324	78.12 174	35.92 370	64.11 343	60.81 359	49.45 291	61.34 279	75.55 325	33.05 308	67.39 340	38.68 332	74.62 191	76.35 312

our_test_3		56.49 315	54.42 327	62.68 309	69.51 340	45.48 277	66.08 321	61.49 355	44.11 353	50.73 374	69.60 373	33.05 308	68.15 330	38.38 334	56.86 367	74.40 336

anonymousdsp		67.00 207	64.82 224	73.57 135	70.09 332	56.13 110	76.35 182	77.35 200	48.43 306	64.99 228	80.84 234	33.01 310	80.34 215	64.66 123	67.64 297	84.23 164

MDTV_nov1_ep13_2view						25.89 414	61.22 359		40.10 379	51.10 369		32.97 311		38.49 333		78.61 283

IB-MVS	56.42 12	65.40 231	62.73 250	73.40 143	74.89 247	52.78 174	73.09 250	75.13 235	55.69 198	58.48 314	73.73 341	32.86 312	86.32 85	50.63 237	70.11 261	81.10 245
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
xiu_mvs_v1_base_debu		68.58 170	67.28 181	72.48 160	78.19 170	57.19 94	75.28 204	75.09 236	51.61 260	70.04 123	81.41 220	32.79 313	79.02 240	63.81 132	77.31 163	81.22 241

xiu_mvs_v1_base		68.58 170	67.28 181	72.48 160	78.19 170	57.19 94	75.28 204	75.09 236	51.61 260	70.04 123	81.41 220	32.79 313	79.02 240	63.81 132	77.31 163	81.22 241

xiu_mvs_v1_base_debi		68.58 170	67.28 181	72.48 160	78.19 170	57.19 94	75.28 204	75.09 236	51.61 260	70.04 123	81.41 220	32.79 313	79.02 240	63.81 132	77.31 163	81.22 241

Anonymous20231206		55.10 330	55.30 321	54.48 358	69.81 338	33.94 384	62.91 349	62.13 353	41.08 372	55.18 341	75.65 323	32.75 316	56.59 389	30.32 386	67.86 294	72.91 345

UGNet		68.81 164	67.39 176	73.06 149	78.33 166	54.47 141	79.77 108	75.40 228	60.45 96	63.22 248	84.40 156	32.71 317	80.91 205	51.71 230	80.56 113	83.81 179
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
myMVS_eth3d28		60.66 282	61.04 272	59.51 326	77.32 206	31.58 395	63.11 347	63.87 336	59.00 131	60.90 285	78.26 276	32.69 318	66.15 348	36.10 353	78.13 151	80.81 251

SSC-MVS		41.96 371	41.99 370	41.90 393	62.46 386	9.28 432	57.41 380	44.32 411	43.38 357	38.30 409	66.45 388	32.67 319	58.42 379	10.98 422	21.91 418	57.99 400

test-LLR		58.15 303	58.13 299	58.22 338	68.57 349	44.80 282	65.46 329	57.92 368	50.08 283	55.44 337	69.82 370	32.62 320	57.44 383	49.66 245	73.62 205	72.41 354

test0.0.03 1		53.32 340	53.59 337	52.50 373	62.81 384	29.45 400	59.51 367	54.11 385	50.08 283	54.40 351	74.31 337	32.62 320	55.92 392	30.50 385	63.95 326	72.15 359

MDTV_nov1_ep13			57.00 305		72.73 283	38.26 343	65.02 336	64.73 330	44.74 344	55.46 336	72.48 347	32.61 322	70.47 318	37.47 338	67.75 296

testing99		64.05 246	63.29 243	66.34 268	78.17 173	39.76 330	67.33 316	68.00 304	58.60 140	63.03 253	78.10 278	32.57 323	76.94 277	48.22 258	75.58 186	82.34 221

cascas		65.98 222	63.42 239	73.64 131	77.26 208	52.58 178	72.26 263	77.21 202	48.56 302	61.21 281	74.60 335	32.57 323	85.82 95	50.38 239	76.75 174	82.52 216

test_post1							68.67 305				3.64 427	32.39 325	69.49 325	44.17 292

CVMVSNet		59.63 293	59.14 286	61.08 321	74.47 259	38.84 338	75.20 207	68.74 299	31.15 396	58.24 315	76.51 310	32.39 325	68.58 329	49.77 242	65.84 310	75.81 316

ppachtmachnet_test		58.06 304	55.38 320	66.10 276	69.51 340	48.99 236	68.01 309	66.13 320	44.50 347	54.05 354	70.74 362	32.09 327	72.34 308	36.68 347	56.71 370	76.99 307

MIMVSNet		57.35 307	57.07 304	58.22 338	74.21 267	37.18 353	62.46 351	60.88 358	48.88 299	55.29 340	75.99 319	31.68 328	62.04 362	31.87 373	72.35 230	75.43 322

testing11		62.81 260	61.90 259	65.54 284	78.38 162	40.76 323	67.59 313	66.78 315	55.48 203	60.13 289	77.11 297	31.67 329	76.79 280	45.53 283	74.45 193	79.06 277

test_vis1_n_1920		58.86 297	59.06 288	58.25 337	63.76 378	43.14 301	67.49 314	66.36 318	40.22 378	65.89 205	71.95 354	31.04 330	59.75 371	59.94 164	64.90 316	71.85 361

PVSNet_0	43.31 20	47.46 361	45.64 364	52.92 370	67.60 357	44.65 284	54.06 390	54.64 382	41.59 369	46.15 390	58.75 401	30.99 331	58.66 377	32.18 369	24.81 416	55.46 404

gg-mvs-nofinetune		57.86 305	56.43 312	62.18 311	72.62 285	35.35 372	66.57 317	56.33 377	50.65 276	57.64 320	57.10 404	30.65 332	76.36 289	37.38 339	78.88 137	74.82 331

D2MVS		62.30 267	60.29 279	68.34 246	66.46 366	48.42 245	65.70 324	73.42 258	47.71 316	58.16 316	75.02 331	30.51 333	77.71 261	53.96 210	71.68 239	78.90 281

GG-mvs-BLEND				62.34 310	71.36 312	37.04 357	69.20 302	57.33 373		54.73 347	65.48 392	30.37 334	77.82 257	34.82 358	74.93 190	72.17 358

MDA-MVSNet-bldmvs		53.87 335	50.81 348	63.05 306	66.25 367	48.58 243	56.93 382	63.82 337	48.09 311	41.22 400	70.48 366	30.34 335	68.00 334	34.24 360	45.92 396	72.57 350

EPMVS		53.96 333	53.69 336	54.79 357	66.12 369	31.96 394	62.34 353	49.05 397	44.42 349	55.54 335	71.33 359	30.22 336	56.70 386	41.65 319	62.54 338	75.71 318

YYNet1		50.73 351	48.96 353	56.03 350	61.10 392	41.78 312	51.94 395	56.44 375	40.94 374	44.84 392	67.80 380	30.08 337	55.08 396	36.77 344	50.71 386	71.22 369

MDA-MVSNet_test_wron		50.71 352	48.95 354	56.00 351	61.17 391	41.84 311	51.90 396	56.45 374	40.96 373	44.79 393	67.84 379	30.04 338	55.07 397	36.71 346	50.69 387	71.11 372

test_cas_vis1_n_1920		56.91 311	56.71 309	57.51 345	59.13 400	45.40 278	63.58 344	61.29 356	36.24 388	67.14 181	71.85 355	29.89 339	56.69 387	57.65 179	63.58 329	70.46 375

Anonymous202405211		66.84 210	65.99 209	69.40 231	80.19 119	42.21 309	71.11 280	71.31 275	58.80 135	67.90 162	86.39 113	29.83 340	79.65 225	49.60 247	78.78 140	86.33 86

ETVMVS		59.51 295	58.81 289	61.58 315	77.46 202	34.87 373	64.94 337	59.35 362	54.06 237	61.08 283	76.67 304	29.54 341	71.87 312	32.16 370	74.07 198	78.01 292

MSDG		61.81 274	59.23 285	69.55 230	72.64 284	52.63 177	70.45 289	75.81 218	51.38 266	53.70 356	76.11 315	29.52 342	81.08 200	37.70 337	65.79 311	74.93 329

CMPMVS	42.80 21	57.81 306	55.97 315	63.32 302	60.98 394	47.38 258	64.66 338	69.50 292	32.06 394	46.83 387	77.80 287	29.50 343	71.36 314	48.68 253	73.75 203	71.21 370
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LTVRE_ROB	55.42 16	63.15 258	61.23 269	68.92 238	76.57 224	47.80 251	59.92 366	76.39 211	54.35 233	58.67 310	82.46 196	29.44 344	81.49 189	42.12 313	71.14 244	77.46 296
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
UnsupCasMVSNet_eth		53.16 342	52.47 340	55.23 354	59.45 398	33.39 388	59.43 368	69.13 296	45.98 335	50.35 377	72.32 348	29.30 345	58.26 380	42.02 316	44.30 398	74.05 340

CHOSEN 280x420		47.83 359	46.36 363	52.24 376	67.37 358	49.78 223	38.91 416	43.11 413	35.00 390	43.27 398	63.30 397	28.95 346	49.19 407	36.53 349	60.80 350	57.76 401

pmmvs-eth3d		58.81 298	56.31 313	66.30 270	67.61 356	52.42 183	72.30 262	64.76 329	43.55 356	54.94 344	74.19 338	28.95 346	72.60 306	43.31 302	57.21 366	73.88 342

dp		51.89 346	51.60 345	52.77 371	68.44 352	32.45 392	62.36 352	54.57 383	44.16 351	49.31 380	67.91 378	28.87 348	56.61 388	33.89 361	54.89 374	69.24 385

FE-MVS		65.91 223	63.33 241	73.63 132	77.36 205	51.95 191	72.62 256	75.81 218	53.70 241	65.31 214	78.96 266	28.81 349	86.39 82	43.93 296	73.48 210	82.55 214

testing222		62.29 268	61.31 266	65.25 290	77.87 182	38.53 341	68.34 306	66.31 319	56.37 183	63.15 252	77.58 293	28.47 350	76.18 293	37.04 342	76.65 176	81.05 247

KD-MVS_self_test		55.22 328	53.89 334	59.21 330	57.80 403	27.47 408	57.75 377	74.32 247	47.38 320	50.90 371	70.00 369	28.45 351	70.30 322	40.44 323	57.92 363	79.87 267

jajsoiax		68.25 179	66.45 195	73.66 129	75.62 237	55.49 128	80.82 93	78.51 175	52.33 254	64.33 235	84.11 161	28.28 352	81.81 184	63.48 136	70.62 249	83.67 187

RPSCF		55.80 323	54.22 332	60.53 322	65.13 373	42.91 304	64.30 340	57.62 370	36.84 387	58.05 318	82.28 200	28.01 353	56.24 391	37.14 341	58.61 361	82.44 219

F-COLMAP		63.05 259	60.87 276	69.58 229	76.99 216	53.63 155	78.12 137	76.16 213	47.97 313	52.41 365	81.61 216	27.87 354	78.11 252	40.07 324	66.66 304	77.00 305

K. test v3		60.47 285	57.11 303	70.56 209	73.74 271	48.22 247	75.10 211	62.55 346	58.27 147	53.62 359	76.31 314	27.81 355	81.59 187	47.42 262	39.18 405	81.88 229

UWE-MVS-28		52.25 344	52.35 342	51.93 377	66.99 359	22.79 420	63.48 345	48.31 401	46.78 328	52.73 364	76.11 315	27.78 356	57.82 382	20.58 410	68.41 291	75.17 323

ACMH+	57.40 11	66.12 221	64.06 228	72.30 166	77.79 185	52.83 173	80.39 97	78.03 187	57.30 163	57.47 321	82.55 191	27.68 357	84.17 130	45.54 282	69.78 269	79.90 266

UnsupCasMVSNet_bld		50.07 354	48.87 355	53.66 363	60.97 395	33.67 386	57.62 378	64.56 331	39.47 382	47.38 384	64.02 396	27.47 358	59.32 372	34.69 359	43.68 399	67.98 388

mvs_tets		68.18 181	66.36 201	73.63 132	75.61 238	55.35 131	80.77 94	78.56 173	52.48 253	64.27 237	84.10 162	27.45 359	81.84 183	63.45 137	70.56 251	83.69 186

lessismore_v0				69.91 221	71.42 310	47.80 251		50.90 394		50.39 376	75.56 324	27.43 360	81.33 192	45.91 277	34.10 411	80.59 254

UWE-MVS		60.18 287	59.78 281	61.39 318	77.67 191	33.92 385	69.04 304	63.82 337	48.56 302	64.27 237	77.64 292	27.20 361	70.40 321	33.56 365	76.24 178	79.83 268

ACMH	55.70 15	65.20 234	63.57 237	70.07 217	78.07 176	52.01 190	79.48 116	79.69 148	55.75 197	56.59 328	80.98 228	27.12 362	80.94 202	42.90 309	71.58 240	77.25 302
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		61.65 275	58.80 291	70.20 215	75.80 234	47.22 259	75.59 199	69.68 288	54.61 227	54.11 353	79.26 263	27.07 363	82.96 154	43.27 303	49.79 390	80.41 257

mmtdpeth		60.40 286	59.12 287	64.27 298	69.59 339	48.99 236	70.67 285	70.06 285	54.96 221	62.78 256	73.26 345	27.00 364	67.66 335	58.44 176	45.29 397	76.16 313

PVSNet	50.76 19	58.40 300	57.39 302	61.42 316	75.53 240	44.04 292	61.43 356	63.45 340	47.04 326	56.91 325	73.61 342	27.00 364	64.76 353	39.12 330	72.40 229	75.47 321

OpenMVS_ROB	52.78 18	60.03 288	58.14 298	65.69 283	70.47 325	44.82 281	75.33 203	70.86 279	45.04 342	56.06 332	76.00 317	26.89 366	79.65 225	35.36 357	67.29 299	72.60 349

ADS-MVSNet2		51.33 349	48.76 356	59.07 332	66.02 370	44.60 285	50.90 398	59.76 361	36.90 385	50.74 372	66.18 390	26.38 367	63.11 358	27.17 397	54.76 375	69.50 382

ADS-MVSNet		48.48 358	47.77 359	50.63 379	66.02 370	29.92 399	50.90 398	50.87 395	36.90 385	50.74 372	66.18 390	26.38 367	52.47 402	27.17 397	54.76 375	69.50 382

N_pmnet		39.35 376	40.28 373	36.54 399	63.76 378	1.62 436	49.37 401	0.76 435	34.62 391	43.61 397	66.38 389	26.25 369	42.57 415	26.02 402	51.77 383	65.44 391

MVS-HIRNet		45.52 363	44.48 365	48.65 382	68.49 351	34.05 383	59.41 369	44.50 410	27.03 403	37.96 410	50.47 412	26.16 370	64.10 354	26.74 400	59.52 357	47.82 411

test2506		65.33 232	64.61 225	67.50 252	79.46 133	34.19 382	74.43 227	51.92 389	58.72 136	66.75 188	88.05 71	25.99 371	80.92 204	51.94 226	84.25 72	87.39 50

FMVSNet5		55.86 322	54.93 322	58.66 335	71.05 317	36.35 363	64.18 342	62.48 347	46.76 329	50.66 375	74.73 334	25.80 372	64.04 355	33.11 366	65.57 312	75.59 319

new-patchmatchnet		47.56 360	47.73 360	47.06 383	58.81 401	9.37 431	48.78 402	59.21 363	43.28 358	44.22 395	68.66 377	25.67 373	57.20 385	31.57 380	49.35 391	74.62 335

reproduce_monomvs		62.56 262	61.20 270	66.62 264	70.62 322	44.30 288	70.13 293	73.13 262	54.78 224	61.13 282	76.37 313	25.63 374	75.63 294	58.75 173	60.29 355	79.93 265

MIMVSNet1		55.17 329	54.31 330	57.77 343	70.03 333	32.01 393	65.68 325	64.81 328	49.19 295	46.75 388	76.00 317	25.53 375	64.04 355	28.65 392	62.13 341	77.26 301

PatchMatch-RL		56.25 319	54.55 326	61.32 319	77.06 213	56.07 112	65.57 326	54.10 386	44.13 352	53.49 362	71.27 360	25.20 376	66.78 343	36.52 350	63.66 327	61.12 394

JIA-IIPM		51.56 347	47.68 361	63.21 304	64.61 375	50.73 206	47.71 404	58.77 365	42.90 362	48.46 382	51.72 408	24.97 377	70.24 323	36.06 354	53.89 378	68.64 386

EU-MVSNet		55.61 325	54.41 328	59.19 331	65.41 372	33.42 387	72.44 260	71.91 272	28.81 398	51.27 368	73.87 340	24.76 378	69.08 327	43.04 306	58.20 362	75.06 325

EG-PatchMatch MVS		64.71 238	62.87 247	70.22 213	77.68 190	53.48 158	77.99 140	78.82 164	53.37 245	56.03 333	77.41 295	24.75 379	84.04 133	46.37 273	73.42 212	73.14 344

TESTMET0.1,1		55.28 327	54.90 323	56.42 348	66.56 364	43.67 295	65.46 329	56.27 378	39.18 383	53.83 355	67.44 382	24.21 380	55.46 394	48.04 260	73.11 218	70.13 378

mvsany_test1		39.38 375	38.16 378	43.02 391	49.05 412	34.28 381	44.16 412	25.94 426	22.74 412	46.57 389	62.21 399	23.85 381	41.16 418	33.01 367	35.91 408	53.63 405

COLMAP_ROB	52.97 17	61.27 280	58.81 289	68.64 241	74.63 256	52.51 180	78.42 131	73.30 259	49.92 286	50.96 370	81.51 219	23.06 382	79.40 229	31.63 378	65.85 309	74.01 341
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testgi		51.90 345	52.37 341	50.51 380	60.39 397	23.55 419	58.42 370	58.15 366	49.03 297	51.83 367	79.21 264	22.39 383	55.59 393	29.24 391	62.64 336	72.40 356

DSMNet-mixed		39.30 377	38.72 376	41.03 394	51.22 411	19.66 423	45.53 409	31.35 422	15.83 421	39.80 405	67.42 384	22.19 384	45.13 412	22.43 406	52.69 382	58.31 399

test-mter		56.42 317	55.82 317	58.22 338	68.57 349	44.80 282	65.46 329	57.92 368	39.94 381	55.44 337	69.82 370	21.92 385	57.44 383	49.66 245	73.62 205	72.41 354

KD-MVS_2432*1600		53.45 337	51.50 346	59.30 327	62.82 382	37.14 354	55.33 385	71.79 273	47.34 322	55.09 342	70.52 364	21.91 386	70.45 319	35.72 355	42.97 400	70.31 376

miper_refine_blended		53.45 337	51.50 346	59.30 327	62.82 382	37.14 354	55.33 385	71.79 273	47.34 322	55.09 342	70.52 364	21.91 386	70.45 319	35.72 355	42.97 400	70.31 376

myMVS_eth3d		54.86 331	54.61 325	55.61 352	74.69 254	27.31 409	65.52 327	57.49 371	50.97 273	56.52 329	72.18 349	21.87 388	68.09 331	27.70 395	64.59 321	71.44 367

OurMVSNet-221017-0		61.37 279	58.63 293	69.61 226	72.05 298	48.06 249	73.93 236	72.51 266	47.23 324	54.74 346	80.92 230	21.49 389	81.24 195	48.57 255	56.22 371	79.53 273

testing3		56.54 314	55.92 316	58.41 336	77.52 200	27.93 406	69.72 297	56.36 376	54.75 226	58.63 312	77.80 287	20.88 390	71.75 313	25.31 403	62.25 340	75.53 320

ITE_SJBPF				62.09 312	66.16 368	44.55 287		64.32 332	47.36 321	55.31 339	80.34 240	19.27 391	62.68 360	36.29 352	62.39 339	79.04 278

AllTest		57.08 310	54.65 324	64.39 296	71.44 308	49.03 233	69.92 296	67.30 307	45.97 336	47.16 385	79.77 250	17.47 392	67.56 338	33.65 362	59.16 359	76.57 309

TestCases				64.39 296	71.44 308	49.03 233		67.30 307	45.97 336	47.16 385	79.77 250	17.47 392	67.56 338	33.65 362	59.16 359	76.57 309

mvs5depth		55.64 324	53.81 335	61.11 320	59.39 399	40.98 322	65.89 322	68.28 302	50.21 281	58.11 317	75.42 328	17.03 394	67.63 337	43.79 299	46.21 394	74.73 333

Anonymous20240521		55.30 326	54.41 328	57.96 341	60.92 396	41.73 313	71.09 281	71.06 278	41.18 371	48.65 381	73.31 343	16.93 395	59.25 373	42.54 310	64.01 324	72.90 346

dongtai		34.52 381	34.94 381	33.26 402	61.06 393	16.00 427	52.79 394	23.78 428	40.71 375	39.33 407	48.65 416	16.91 396	48.34 408	12.18 420	19.05 420	35.44 419

test_fmvs1		51.32 350	50.48 350	53.81 362	53.57 405	37.51 351	60.63 365	51.16 391	28.02 402	63.62 244	69.23 375	16.41 397	53.93 399	51.01 234	60.70 351	69.99 379

XVG-ACMP-BASELINE		64.36 244	62.23 255	70.74 206	72.35 293	52.45 182	70.80 284	78.45 179	53.84 240	59.87 295	81.10 225	16.24 398	79.32 231	55.64 196	71.76 237	80.47 255

kuosan		29.62 388	30.82 387	26.02 407	52.99 406	16.22 426	51.09 397	22.71 429	33.91 392	33.99 411	40.85 417	15.89 399	33.11 424	7.59 428	18.37 421	28.72 421

tmp_tt		9.43 396	11.14 399	4.30 411	2.38 434	4.40 434	13.62 423	16.08 432	0.39 428	15.89 423	13.06 425	15.80 400	5.54 430	12.63 419	10.46 427	2.95 425

USDC		56.35 318	54.24 331	62.69 308	64.74 374	40.31 324	65.05 335	73.83 255	43.93 354	47.58 383	77.71 291	15.36 401	75.05 297	38.19 336	61.81 344	72.70 348

test_fmvs1_n		51.37 348	50.35 351	54.42 360	52.85 407	37.71 349	61.16 361	51.93 388	28.15 400	63.81 243	69.73 372	13.72 402	53.95 398	51.16 233	60.65 352	71.59 364

test_vis1_n		49.89 355	48.69 357	53.50 365	53.97 404	37.38 352	61.53 355	47.33 405	28.54 399	59.62 300	67.10 386	13.52 403	52.27 403	49.07 250	57.52 364	70.84 373

EGC-MVSNET		42.47 369	38.48 377	54.46 359	74.33 264	48.73 241	70.33 291	51.10 392	0.03 429	0.18 430	67.78 381	13.28 404	66.49 345	18.91 412	50.36 388	48.15 409

MVStest1		42.65 368	39.29 375	52.71 372	47.26 417	34.58 378	54.41 389	50.84 396	23.35 408	39.31 408	74.08 339	12.57 405	55.09 395	23.32 405	28.47 414	68.47 387

ANet_high		41.38 372	37.47 379	53.11 369	39.73 425	24.45 417	56.94 381	69.69 287	47.65 317	26.04 417	52.32 407	12.44 406	62.38 361	21.80 408	10.61 426	72.49 351

FPMVS		42.18 370	41.11 372	45.39 385	58.03 402	41.01 320	49.50 400	53.81 387	30.07 397	33.71 412	64.03 394	11.69 407	52.08 405	14.01 416	55.11 373	43.09 413

TinyColmap		54.14 332	51.72 344	61.40 317	66.84 362	41.97 310	66.52 318	68.51 300	44.81 343	42.69 399	75.77 322	11.66 408	72.94 305	31.96 372	56.77 369	69.27 384

test_fmvs2		48.69 357	47.49 362	52.29 375	48.63 414	33.06 390	57.76 376	48.05 403	25.71 406	59.76 298	69.60 373	11.57 409	52.23 404	49.45 248	56.86 367	71.58 365

TDRefinement		53.44 339	50.72 349	61.60 314	64.31 377	46.96 261	70.89 283	65.27 326	41.78 366	44.61 394	77.98 280	11.52 410	66.36 346	28.57 393	51.59 384	71.49 366

ambc				65.13 291	63.72 380	37.07 356	47.66 405	78.78 167		54.37 352	71.42 357	11.24 411	80.94 202	45.64 280	53.85 379	77.38 298

test_vis1_rt		41.35 373	39.45 374	47.03 384	46.65 418	37.86 346	47.76 403	38.65 416	23.10 410	44.21 396	51.22 410	11.20 412	44.08 413	39.27 329	53.02 381	59.14 397

pmmvs3		44.92 364	41.95 371	53.86 361	52.58 409	43.55 296	62.11 354	46.90 407	26.05 405	40.63 401	60.19 400	11.08 413	57.91 381	31.83 377	46.15 395	60.11 395

new_pmnet		34.13 382	34.29 383	33.64 401	52.63 408	18.23 425	44.43 411	33.90 421	22.81 411	30.89 414	53.18 406	10.48 414	35.72 423	20.77 409	39.51 404	46.98 412

LF4IMVS		42.95 367	42.26 369	45.04 386	48.30 415	32.50 391	54.80 387	48.49 399	28.03 401	40.51 402	70.16 367	9.24 415	43.89 414	31.63 378	49.18 392	58.72 398

PM-MVS		52.33 343	50.19 352	58.75 334	62.10 387	45.14 280	65.75 323	40.38 415	43.60 355	53.52 360	72.65 346	9.16 416	65.87 350	50.41 238	54.18 377	65.24 392

ttmdpeth		45.56 362	42.95 367	53.39 368	52.33 410	29.15 401	57.77 375	48.20 402	31.81 395	49.86 379	77.21 296	8.69 417	59.16 374	27.31 396	33.40 412	71.84 362

EMVS		22.97 391	21.84 395	26.36 406	40.20 424	19.53 424	41.95 414	34.64 420	17.09 418	9.73 428	22.83 424	7.29 418	42.22 417	9.18 426	13.66 424	17.32 423

E-PMN		23.77 390	22.73 394	26.90 405	42.02 421	20.67 422	42.66 413	35.70 419	17.43 417	10.28 427	25.05 423	6.42 419	42.39 416	10.28 424	14.71 423	17.63 422

test_method		19.68 393	18.10 396	24.41 408	13.68 433	3.11 435	12.06 424	42.37 414	2.00 427	11.97 425	36.38 419	5.77 420	29.35 427	15.06 414	23.65 417	40.76 416

mvsany_test3		32.62 383	30.57 388	38.77 397	36.16 428	24.20 418	38.10 417	20.63 430	19.14 416	40.36 404	57.43 403	5.06 421	36.63 422	29.59 390	28.66 413	55.49 403

test_f		31.86 385	31.05 386	34.28 400	32.33 431	21.86 421	32.34 418	30.46 423	16.02 420	39.78 406	55.45 405	4.80 422	32.36 425	30.61 384	37.66 407	48.64 407

Gipuma		34.77 380	31.91 385	43.33 390	62.05 388	37.87 345	20.39 421	67.03 312	23.23 409	18.41 422	25.84 422	4.24 423	62.73 359	14.71 415	51.32 385	29.38 420
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvs3		44.30 365	42.55 368	49.55 381	42.83 419	27.15 411	53.03 392	44.93 409	22.03 414	53.69 358	64.94 393	4.21 424	49.63 406	47.47 261	49.82 389	71.88 360

PMMVS2		27.40 389	25.91 392	31.87 404	39.46 426	6.57 433	31.17 419	28.52 424	23.96 407	20.45 421	48.94 415	4.20 425	37.94 420	16.51 413	19.97 419	51.09 406

LCM-MVSNet		40.30 374	35.88 380	53.57 364	42.24 420	29.15 401	45.21 410	60.53 360	22.23 413	28.02 415	50.98 411	3.72 426	61.78 363	31.22 383	38.76 406	69.78 381

DeepMVS_CX				12.03 410	17.97 432	10.91 429		10.60 433	7.46 425	11.07 426	28.36 421	3.28 427	11.29 429	8.01 427	9.74 428	13.89 424

APD_test1		37.39 378	34.94 381	44.72 389	48.88 413	33.19 389	52.95 393	44.00 412	19.49 415	27.28 416	58.59 402	3.18 428	52.84 401	18.92 411	41.17 403	48.14 410

PMVS	28.69 22	36.22 379	33.29 384	45.02 387	36.82 427	35.98 368	54.68 388	48.74 398	26.31 404	21.02 420	51.61 409	2.88 429	60.10 369	9.99 425	47.58 393	38.99 418
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		32.09 384	30.20 389	37.76 398	35.36 429	27.48 407	40.60 415	28.29 425	16.69 419	32.52 413	40.53 418	1.96 430	37.40 421	33.64 364	42.21 402	48.39 408

MVE	17.77 23	21.41 392	17.77 397	32.34 403	34.34 430	25.44 415	16.11 422	24.11 427	11.19 424	13.22 424	31.92 420	1.58 431	30.95 426	10.47 423	17.03 422	40.62 417
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		31.46 386	28.89 390	39.16 395	41.99 422	28.78 403	46.45 406	37.56 417	14.28 422	21.10 418	48.96 413	1.48 432	47.11 409	13.63 417	34.56 409	41.60 414

APD_test2		31.46 386	28.89 390	39.16 395	41.99 422	28.78 403	46.45 406	37.56 417	14.28 422	21.10 418	48.96 413	1.48 432	47.11 409	13.63 417	34.56 409	41.60 414

wuyk23d		13.32 395	12.52 398	15.71 409	47.54 416	26.27 413	31.06 420	1.98 434	4.93 426	5.18 429	1.94 429	0.45 434	18.54 428	6.81 429	12.83 425	2.33 426

test123		4.73 398	6.30 401	0.02 412	0.01 435	0.01 437	56.36 383	0.00 436	0.01 430	0.04 431	0.21 431	0.01 435	0.00 431	0.03 431	0.00 429	0.04 427

mmdepth		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

monomultidepth		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

test_blank		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

uanet_test		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

DCPMVS		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

sosnet-low-res		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

sosnet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

uncertanet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

Regformer		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

testmvs		4.52 399	6.03 402	0.01 413	0.01 435	0.00 438	53.86 391	0.00 436	0.01 430	0.04 431	0.27 430	0.00 436	0.00 431	0.04 430	0.00 429	0.03 428

ab-mvs-re		6.49 397	8.65 400	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	77.89 285	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

uanet		0.00 401	0.00 404	0.00 414	0.00 437	0.00 438	0.00 425	0.00 436	0.00 432	0.00 433	0.00 432	0.00 436	0.00 431	0.00 432	0.00 429	0.00 429

WAC-MVS						27.31 409								27.77 394

FOURS1					86.12 36	60.82 37	88.18 1	83.61 67	60.87 87	81.50 16

MSC_two_6792asdad				79.95 4	87.24 14	61.04 31		85.62 24					90.96 1	79.31 9	90.65 8	87.85 33

No_MVS				79.95 4	87.24 14	61.04 31		85.62 24					90.96 1	79.31 9	90.65 8	87.85 33

eth-test2					0.00 437

eth-test					0.00 437

IU-MVS					87.77 4	59.15 63		85.53 26	53.93 239	84.64 3				79.07 11	90.87 5	88.37 18

save fliter					86.17 33	61.30 28	83.98 50	79.66 150	59.00 131

test_0728_SECOND				79.19 16	87.82 3	59.11 66	87.85 5	87.15 3					90.84 3	78.66 16	90.61 11	87.62 43

GSMVS																78.05 288

test_part2					87.58 9	60.47 42				83.42 12

MTGPA								80.97 132

MTMP							86.03 19	17.08 431

gm-plane-assit					71.40 311	41.72 315			48.85 300		73.31 343		82.48 173	48.90 252

test9_res														75.28 41	88.31 32	83.81 179

agg_prior2														73.09 59	87.93 40	84.33 160

agg_prior					85.04 50	59.96 50		81.04 130		74.68 61			84.04 133

test_prior4						62.51 14	82.08 79

test_prior				76.69 58	84.20 61	57.27 91		84.88 39					86.43 81			86.38 80

旧先验2							76.08 188		45.32 341	76.55 37			65.56 351	58.75 173

新几何2							76.12 186

无先验							79.66 112	74.30 249	48.40 307				80.78 208	53.62 212		79.03 279

原ACMM2							79.02 119

testdata2													72.18 311	46.95 270

testdata1							72.65 254		60.50 95

plane_prior7					81.41 94	55.96 114

plane_prior5								84.01 52					87.21 58	68.16 91	80.58 111	84.65 154

plane_prior4											86.10 121

plane_prior3						56.09 111			63.92 36	69.27 140

plane_prior2							84.22 43		64.52 25

plane_prior1					81.27 99

plane_prior						56.31 105	83.58 56		63.19 48						80.48 114

n2								0.00 436

nn								0.00 436

door-mid								47.19 406

test11								83.47 71

door								47.60 404

HQP5-MVS						54.94 135

HQP-NCC					80.66 108		82.31 74		62.10 68	67.85 164

ACMP_Plane					80.66 108		82.31 74		62.10 68	67.85 164

BP-MVS														67.04 102

HQP4-MVS										67.85 164			86.93 66			84.32 161

HQP3-MVS								83.90 57							80.35 115

NP-MVS					80.98 104	56.05 113					85.54 138

ACMMP++_ref															74.07 198

ACMMP++															72.16 234

High-resolution multi-view benchmark