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 60	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 11

OPU-MVS				79.83 7	87.54 11	60.93 35	87.82 7				89.89 42	67.01 1	90.33 12	73.16 54	91.15 4	88.23 16

SED-MVS		81.56 2	82.30 2	79.32 13	87.77 4	58.90 69	87.82 7	86.78 10	64.18 32	85.97 1	91.84 8	66.87 3	90.83 5	78.63 17	90.87 5	88.23 16

test_241102_ONE					87.77 4	58.90 69		86.78 10	64.20 31	85.97 1	91.34 12	66.87 3	90.78 7

PC_three_1452									55.09 197	84.46 4	89.84 43	66.68 5	89.41 18	74.24 44	91.38 2	88.42 11

test_241102_TWO								86.73 12	64.18 32	84.26 5	91.84 8	65.19 6	90.83 5	78.63 17	90.70 7	87.65 35

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 29	89.67 18	86.84 59
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 64	87.85 5	85.03 34	64.26 29	83.82 8	92.00 3	64.82 8	90.75 8	78.66 15	90.61 11	85.45 116
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 64	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 21

test_one_0601					87.58 9	59.30 57		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 23	63.71 12	89.23 20	81.51 3	88.44 27	88.09 21
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 56	75.23 47	72.48 153	82.34 77	53.34 155	77.87 138	81.46 103	57.80 146	75.49 36	86.81 84	62.22 13	77.75 251	71.09 67	82.02 91	86.34 76

DeepPCF-MVS	69.58 1	79.03 11	79.00 12	79.13 19	84.92 56	60.32 44	83.03 57	85.33 27	62.86 54	80.17 17	90.03 38	61.76 14	88.95 24	74.21 45	88.67 26	88.12 20

CSCG		76.92 32	76.75 30	77.41 46	83.96 62	59.60 51	82.95 58	86.50 13	60.78 87	75.27 37	84.83 133	60.76 15	86.56 73	67.86 84	87.87 41	86.06 89

TSAR-MVS + MP.		78.44 18	78.28 19	78.90 26	84.96 52	61.41 26	84.03 45	83.82 59	59.34 117	79.37 19	89.76 45	59.84 16	87.62 47	76.69 27	86.74 52	87.68 34
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
canonicalmvs		74.67 53	74.98 49	73.71 121	78.94 140	50.56 202	80.23 96	83.87 57	60.30 100	77.15 29	86.56 95	59.65 17	82.00 174	66.01 101	82.12 89	88.58 10

APDe-MVS		80.16 7	80.59 6	78.86 28	86.64 21	60.02 45	88.12 3	86.42 14	62.94 51	82.40 14	92.12 2	59.64 18	89.76 15	78.70 13	88.32 31	86.79 61
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DELS-MVS		74.76 51	74.46 53	75.65 72	77.84 172	52.25 178	75.59 192	84.17 46	63.76 38	73.15 73	82.79 174	59.58 19	86.80 66	67.24 91	86.04 57	87.89 24
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 9	79.97 9	79.45 11	87.90 2	62.17 17	84.37 36	85.03 34	66.96 5	77.58 27	90.06 36	59.47 20	89.13 22	78.67 14	89.73 16	87.03 53

casdiffmvs_mvg		76.14 40	76.30 35	75.66 71	76.46 210	51.83 186	79.67 109	85.08 31	65.02 19	75.84 34	88.58 60	59.42 21	85.08 108	72.75 56	83.93 72	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 27	77.45 26	77.54 45	86.67 20	58.36 76	83.22 55	86.93 5	56.91 157	74.91 45	88.19 62	59.15 22	87.68 46	73.67 51	87.45 42	86.57 69

nrg030		72.96 70	73.01 66	72.84 146	75.41 225	50.24 205	80.02 100	82.89 84	58.36 133	74.44 53	86.73 87	58.90 23	80.83 200	65.84 103	74.46 176	87.44 42

HPM-MVS++		79.88 8	80.14 8	79.10 21	88.17 1	64.80 1	86.59 12	83.70 61	65.37 13	78.78 22	90.64 19	58.63 24	87.24 51	79.00 12	90.37 14	85.26 127

SF-MVS		78.82 12	79.22 11	77.60 44	82.88 74	57.83 80	84.99 32	88.13 2	61.86 75	79.16 20	90.75 18	57.96 25	87.09 60	77.08 26	90.18 15	87.87 26

casdiffmvs		74.80 50	74.89 50	74.53 98	75.59 222	50.37 204	78.17 131	85.06 33	62.80 58	74.40 54	87.86 70	57.88 26	83.61 138	69.46 75	82.79 85	89.59 3
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepC-MVS	69.38 2	78.56 17	78.14 21	79.83 7	83.60 63	61.62 23	84.17 42	86.85 6	63.23 46	73.84 63	90.25 32	57.68 27	89.96 14	74.62 43	89.03 22	87.89 24
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 54	74.70 51	74.34 102	75.70 218	49.99 212	77.54 148	84.63 40	62.73 59	73.98 60	87.79 73	57.67 28	83.82 134	69.49 73	82.74 86	89.20 6

patch_mono-2		69.85 125	71.09 92	66.16 259	79.11 137	54.80 135	71.97 256	74.31 237	53.50 225	70.90 102	84.17 147	57.63 29	63.31 333	66.17 98	82.02 91	80.38 244

9.14			78.75 14		83.10 69		84.15 43	88.26 1	59.90 106	78.57 23	90.36 27	57.51 30	86.86 64	77.39 23	89.52 21

MM				79.99 2		60.01 46	86.19 17	83.93 51	73.19 1	77.08 30	91.21 15	57.23 31	90.73 10	83.35 1	88.12 35	89.22 5

DPM-MVS		75.47 47	75.00 48	76.88 51	81.38 91	59.16 59	79.94 102	85.71 22	56.59 165	72.46 89	86.76 85	56.89 32	87.86 43	66.36 97	88.91 25	83.64 181

UniMVSNet_NR-MVSNet		71.11 99	71.00 94	71.44 177	79.20 133	44.13 277	76.02 186	82.60 87	66.48 11	68.20 142	84.60 140	56.82 33	82.82 158	54.62 190	70.43 232	87.36 48

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 34	89.70 16	79.85 5	91.48 1	88.19 18
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
Effi-MVS+		73.31 66	72.54 71	75.62 73	77.87 171	53.64 147	79.62 111	79.61 141	61.63 77	72.02 94	82.61 179	56.44 35	85.97 88	63.99 119	79.07 127	87.25 50

alignmvs		73.86 62	73.99 57	73.45 133	78.20 160	50.50 203	78.57 123	82.43 88	59.40 115	76.57 31	86.71 89	56.42 36	81.23 190	65.84 103	81.79 93	88.62 8

test_prior2							81.75 80		60.37 96	75.01 41	89.06 52	56.22 37		72.19 59	88.96 24

ZD-MVS					86.64 21	60.38 43		82.70 86	57.95 142	78.10 24	90.06 36	56.12 38	88.84 26	74.05 47	87.00 48

TSAR-MVS + GP.		74.90 49	74.15 56	77.17 49	82.00 80	58.77 72	81.80 79	78.57 162	58.58 128	74.32 56	84.51 143	55.94 39	87.22 52	67.11 92	84.48 67	85.52 112

MVS_Test		72.45 78	72.46 72	72.42 157	74.88 230	48.50 233	76.28 178	83.14 80	59.40 115	72.46 89	84.68 135	55.66 40	81.12 191	65.98 102	79.66 115	87.63 36

APD-MVS		78.02 22	78.04 22	77.98 41	86.44 27	60.81 38	85.52 27	84.36 43	60.61 89	79.05 21	90.30 30	55.54 41	88.32 32	73.48 53	87.03 45	84.83 139
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 31	84.42 42	66.73 8	74.67 51	89.38 49	55.30 42	89.18 21	74.19 46	87.34 43	86.38 72

FIs		70.82 106	71.43 83	68.98 227	78.33 157	38.14 325	76.96 164	83.59 64	61.02 83	67.33 165	86.73 87	55.07 43	81.64 179	54.61 192	79.22 123	87.14 52

CS-MVS		76.25 39	75.98 38	77.06 50	80.15 115	55.63 120	84.51 35	83.90 54	63.24 45	73.30 68	87.27 79	55.06 44	86.30 83	71.78 62	84.58 64	89.25 4

MVS_0304		78.73 15	78.75 14	78.66 30	80.82 100	57.62 83	85.31 30	81.31 112	70.51 2	74.17 58	91.24 14	54.99 45	89.56 17	82.29 2	88.13 34	88.80 7

SD-MVS		77.70 25	77.62 25	77.93 42	84.47 59	61.88 21	84.55 34	83.87 57	60.37 96	79.89 18	89.38 49	54.97 46	85.58 97	76.12 31	84.94 62	86.33 78
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 36	75.93 39	78.06 39	81.29 92	57.53 85	82.35 69	83.31 74	67.78 3	70.09 109	86.34 101	54.92 47	88.90 25	72.68 57	84.55 65	87.76 32

MP-MVS		78.35 19	78.26 20	78.64 31	86.54 25	63.47 4	86.02 20	83.55 65	63.89 37	73.60 65	90.60 20	54.85 48	86.72 68	77.20 25	88.06 37	85.74 105
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test_fmvsmconf_n		73.01 69	72.59 70	74.27 105	71.28 292	55.88 114	78.21 130	75.56 214	54.31 216	74.86 46	87.80 72	54.72 49	80.23 214	78.07 21	78.48 136	86.70 63

mvs_anonymous		68.03 171	67.51 160	69.59 217	72.08 277	44.57 275	71.99 255	75.23 221	51.67 239	67.06 170	82.57 180	54.68 50	77.94 247	56.56 172	75.71 170	86.26 84

test12				77.76 43	84.52 58	58.41 75		83.36 72		72.93 81		54.61 51	88.05 37		88.12 35	86.81 60

FC-MVSNet-test		69.80 128	70.58 101	67.46 243	77.61 183	34.73 354	76.05 184	83.19 78	60.84 85	65.88 195	86.46 98	54.52 52	80.76 203	52.52 206	78.12 140	86.91 56

SteuartSystems-ACMMP		79.48 10	79.31 10	79.98 3	83.01 72	62.18 16	87.60 9	85.83 19	66.69 9	78.03 26	90.98 16	54.26 53	90.06 13	78.42 19	89.02 23	87.69 33
Skip Steuart: Steuart Systems R&D Blog.
segment_acmp												54.23 54

MVS_111021_HR		74.02 60	73.46 64	75.69 70	83.01 72	60.63 40	77.29 156	78.40 173	61.18 82	70.58 104	85.97 113	54.18 55	84.00 131	67.52 89	82.98 80	82.45 207

Fast-Effi-MVS+		70.28 117	69.12 126	73.73 120	78.50 150	51.50 188	75.01 205	79.46 145	56.16 174	68.59 135	79.55 246	53.97 56	84.05 127	53.34 201	77.53 147	85.65 108

ZNCC-MVS		78.82 12	78.67 16	79.30 14	86.43 28	62.05 18	86.62 11	86.01 18	63.32 43	75.08 40	90.47 26	53.96 57	88.68 27	76.48 28	89.63 20	87.16 51

UniMVSNet (Re)		70.63 109	70.20 107	71.89 163	78.55 149	45.29 268	75.94 187	82.92 82	63.68 40	68.16 145	83.59 161	53.89 58	83.49 141	53.97 195	71.12 225	86.89 57

CS-MVS-test		75.62 46	75.31 46	76.56 57	80.63 105	55.13 130	83.88 48	85.22 28	62.05 71	71.49 99	86.03 111	53.83 59	86.36 81	67.74 85	86.91 49	88.19 18

test_fmvsmconf0.1_n		72.81 71	72.33 73	74.24 106	69.89 312	55.81 115	78.22 129	75.40 217	54.17 218	75.00 42	88.03 68	53.82 60	80.23 214	78.08 20	78.34 139	86.69 64

fmvsm_l_conf0.5_n		70.99 102	70.82 96	71.48 175	71.45 285	54.40 138	77.18 159	70.46 271	48.67 279	75.17 38	86.86 82	53.77 61	76.86 264	76.33 30	77.51 148	83.17 194

DeepC-MVS_fast	68.24 3	77.25 29	76.63 32	79.12 20	86.15 34	60.86 36	84.71 33	84.85 38	61.98 74	73.06 78	88.88 55	53.72 62	89.06 23	68.27 78	88.04 38	87.42 43
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 82	81.26 115	55.65 186	74.93 43	88.81 56	53.70 63	84.68 118

train_agg		76.27 38	76.15 36	76.64 55	85.58 43	61.59 24	81.62 82	81.26 115	55.86 177	74.93 43	88.81 56	53.70 63	84.68 118	75.24 38	88.33 30	83.65 180

test_8					85.40 46	60.96 34	81.54 85	81.18 118	55.86 177	74.81 47	88.80 58	53.70 63	84.45 122

ETV-MVS		74.46 57	73.84 60	76.33 60	79.27 131	55.24 129	79.22 115	85.00 36	64.97 21	72.65 86	79.46 248	53.65 66	87.87 42	67.45 90	82.91 81	85.89 96

CDPH-MVS		76.31 37	75.67 43	78.22 37	85.35 48	59.14 62	81.31 87	84.02 48	56.32 169	74.05 59	88.98 54	53.34 67	87.92 41	69.23 76	88.42 28	87.59 38

HFP-MVS		78.01 23	77.65 24	79.10 21	86.71 19	62.81 8	86.29 14	84.32 44	62.82 55	73.96 61	90.50 24	53.20 68	88.35 31	74.02 48	87.05 44	86.13 87

EC-MVSNet		75.84 44	75.87 41	75.74 69	78.86 141	52.65 168	83.73 50	86.08 17	63.47 42	72.77 84	87.25 80	53.13 69	87.93 40	71.97 61	85.57 60	86.66 66

test_fmvsm_n_1920		71.73 91	71.14 91	73.50 130	72.52 269	56.53 101	75.60 191	76.16 204	48.11 287	77.22 28	85.56 123	53.10 70	77.43 255	74.86 40	77.14 155	86.55 70

fmvsm_l_conf0.5_n_a		70.50 112	70.27 106	71.18 187	71.30 291	54.09 140	76.89 167	69.87 274	47.90 291	74.37 55	86.49 97	53.07 71	76.69 268	75.41 35	77.11 156	82.76 201

EI-MVSNet-Vis-set		72.42 79	71.59 79	74.91 84	78.47 152	54.02 141	77.05 162	79.33 147	65.03 18	71.68 97	79.35 251	52.75 72	84.89 114	66.46 96	74.23 179	85.83 98

fmvsm_s_conf0.5_n_a		69.54 137	68.74 133	71.93 162	72.47 271	53.82 144	78.25 127	62.26 328	49.78 267	73.12 76	86.21 104	52.66 73	76.79 266	75.02 39	68.88 264	85.18 128

GST-MVS		78.14 21	77.85 23	78.99 25	86.05 38	61.82 22	85.84 21	85.21 29	63.56 41	74.29 57	90.03 38	52.56 74	88.53 29	74.79 42	88.34 29	86.63 68

ACMMP_NAP		78.77 14	78.78 13	78.74 29	85.44 45	61.04 31	83.84 49	85.16 30	62.88 53	78.10 24	91.26 13	52.51 75	88.39 30	79.34 8	90.52 13	86.78 62

PCF-MVS	61.88 8	70.95 103	69.49 119	75.35 77	77.63 178	55.71 117	76.04 185	81.81 97	50.30 261	69.66 120	85.40 129	52.51 75	84.89 114	51.82 214	80.24 109	85.45 116
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MP-MVS-pluss		78.35 19	78.46 17	78.03 40	84.96 52	59.52 53	82.93 59	85.39 26	62.15 67	76.41 33	91.51 11	52.47 77	86.78 67	80.66 4	89.64 19	87.80 30
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CLD-MVS		73.33 65	72.68 69	75.29 80	78.82 143	53.33 156	78.23 128	84.79 39	61.30 81	70.41 106	81.04 216	52.41 78	87.12 58	64.61 115	82.49 88	85.41 120
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		71.01 101	70.15 109	73.60 128	79.57 124	52.17 179	78.93 117	78.12 177	58.02 139	67.76 160	83.87 155	52.36 79	82.72 160	56.90 170	75.79 168	85.92 93

NR-MVSNet		69.54 137	68.85 129	71.59 174	78.05 166	43.81 281	74.20 220	80.86 125	65.18 14	62.76 241	84.52 141	52.35 80	83.59 139	50.96 222	70.78 227	87.37 46

fmvsm_s_conf0.5_n		69.58 135	68.84 130	71.79 167	72.31 275	52.90 164	77.90 137	62.43 326	49.97 265	72.85 82	85.90 116	52.21 81	76.49 271	75.75 33	70.26 238	85.97 91

EI-MVSNet-UG-set		71.92 87	71.06 93	74.52 99	77.98 169	53.56 149	76.62 171	79.16 148	64.40 27	71.18 100	78.95 256	52.19 82	84.66 120	65.47 107	73.57 189	85.32 123

miper_ehance_all_eth		68.03 171	67.24 174	70.40 202	70.54 300	46.21 257	73.98 223	78.68 160	55.07 200	66.05 189	77.80 272	52.16 83	81.31 187	61.53 145	69.32 256	83.67 177

EIA-MVS		71.78 89	70.60 99	75.30 79	79.85 119	53.54 150	77.27 157	83.26 77	57.92 143	66.49 181	79.39 249	52.07 84	86.69 69	60.05 152	79.14 126	85.66 107

fmvsm_s_conf0.1_n_a		69.32 145	68.44 142	71.96 161	70.91 296	53.78 145	78.12 133	62.30 327	49.35 271	73.20 72	86.55 96	51.99 85	76.79 266	74.83 41	68.68 269	85.32 123

c3_l		68.33 165	67.56 156	70.62 198	70.87 297	46.21 257	74.47 217	78.80 156	56.22 173	66.19 187	78.53 263	51.88 86	81.40 184	62.08 135	69.04 262	84.25 153

PAPM_NR		72.63 75	71.80 77	75.13 83	81.72 84	53.42 154	79.91 104	83.28 76	59.14 119	66.31 186	85.90 116	51.86 87	86.06 84	57.45 167	80.62 101	85.91 94

test_fmvsmvis_n_1920		70.84 104	70.38 104	72.22 160	71.16 293	55.39 127	75.86 188	72.21 258	49.03 275	73.28 70	86.17 106	51.83 88	77.29 258	75.80 32	78.05 141	83.98 162

MG-MVS		73.96 61	73.89 59	74.16 107	85.65 42	49.69 217	81.59 84	81.29 114	61.45 78	71.05 101	88.11 63	51.77 89	87.73 45	61.05 146	83.09 76	85.05 133

EPP-MVSNet		72.16 85	71.31 88	74.71 88	78.68 147	49.70 215	82.10 76	81.65 99	60.40 93	65.94 191	85.84 118	51.74 90	86.37 80	55.93 176	79.55 118	88.07 23

fmvsm_s_conf0.1_n		69.41 143	68.60 136	71.83 165	71.07 294	52.88 165	77.85 140	62.44 325	49.58 269	72.97 79	86.22 103	51.68 91	76.48 272	75.53 34	70.10 241	86.14 86

TranMVSNet+NR-MVSNet		70.36 115	70.10 111	71.17 188	78.64 148	42.97 289	76.53 173	81.16 119	66.95 6	68.53 138	85.42 128	51.61 92	83.07 147	52.32 207	69.70 252	87.46 41

diffmvs		70.69 108	70.43 102	71.46 176	69.45 317	48.95 227	72.93 240	78.46 168	57.27 151	71.69 96	83.97 154	51.48 93	77.92 248	70.70 69	77.95 143	87.53 40
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		69.27 147	68.44 142	71.73 169	74.47 242	49.39 222	75.20 200	78.45 169	59.60 111	69.16 131	76.51 289	51.29 94	82.50 166	59.86 157	71.45 223	83.30 186

IterMVS-LS		69.22 149	68.48 138	71.43 179	74.44 244	49.40 221	76.23 179	77.55 186	59.60 111	65.85 196	81.59 208	51.28 95	81.58 182	59.87 156	69.90 247	83.30 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TransMVSNet (Re)		64.72 226	64.33 215	65.87 267	75.22 227	38.56 322	74.66 214	75.08 229	58.90 122	61.79 257	82.63 178	51.18 96	78.07 246	43.63 283	55.87 349	80.99 235

miper_enhance_ethall		67.11 192	66.09 196	70.17 206	69.21 320	45.98 259	72.85 242	78.41 172	51.38 246	65.65 198	75.98 297	51.17 97	81.25 188	60.82 147	69.32 256	83.29 188

VNet		69.68 132	70.19 108	68.16 237	79.73 121	41.63 302	70.53 275	77.38 190	60.37 96	70.69 103	86.63 91	51.08 98	77.09 261	53.61 199	81.69 98	85.75 104

VPA-MVSNet		69.02 150	69.47 120	67.69 241	77.42 188	41.00 307	74.04 222	79.68 139	60.06 103	69.26 129	84.81 134	51.06 99	77.58 253	54.44 193	74.43 177	84.48 148

PAPR		71.72 92	70.82 96	74.41 101	81.20 96	51.17 189	79.55 112	83.33 73	55.81 181	66.93 174	84.61 139	50.95 100	86.06 84	55.79 179	79.20 124	86.00 90

PHI-MVS		75.87 43	75.36 44	77.41 46	80.62 106	55.91 113	84.28 39	85.78 20	56.08 175	73.41 67	86.58 94	50.94 101	88.54 28	70.79 68	89.71 17	87.79 31

HPM-MVS		77.28 28	76.85 29	78.54 32	85.00 51	60.81 38	82.91 60	85.08 31	62.57 60	73.09 77	89.97 41	50.90 102	87.48 49	75.30 36	86.85 50	87.33 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
WR-MVS_H		67.02 194	66.92 179	67.33 247	77.95 170	37.75 329	77.57 146	82.11 93	62.03 73	62.65 244	82.48 185	50.57 103	79.46 222	42.91 290	64.01 303	84.79 141

EPNet		73.09 68	72.16 74	75.90 65	75.95 216	56.28 104	83.05 56	72.39 256	66.53 10	65.27 206	87.00 81	50.40 104	85.47 102	62.48 133	86.32 56	85.94 92
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WR-MVS		68.47 163	68.47 140	68.44 234	80.20 112	39.84 311	73.75 232	76.07 207	64.68 22	68.11 147	83.63 160	50.39 105	79.14 232	49.78 227	69.66 253	86.34 76

test_fmvsmconf0.01_n		72.17 83	71.50 81	74.16 107	67.96 329	55.58 123	78.06 135	74.67 232	54.19 217	74.54 52	88.23 61	50.35 106	80.24 213	78.07 21	77.46 149	86.65 67

region2R		77.67 26	77.18 28	79.15 18	86.76 17	62.95 6	86.29 14	84.16 47	62.81 57	73.30 68	90.58 21	49.90 107	88.21 34	73.78 50	87.03 45	86.29 83

UA-Net		73.13 67	72.93 67	73.76 117	83.58 64	51.66 187	78.75 118	77.66 184	67.75 4	72.61 87	89.42 47	49.82 108	83.29 143	53.61 199	83.14 75	86.32 80

ACMMPR		77.71 24	77.23 27	79.16 17	86.75 18	62.93 7	86.29 14	84.24 45	62.82 55	73.55 66	90.56 22	49.80 109	88.24 33	74.02 48	87.03 45	86.32 80

API-MVS		72.17 83	71.41 84	74.45 100	81.95 82	57.22 89	84.03 45	80.38 132	59.89 109	68.40 139	82.33 188	49.64 110	87.83 44	51.87 213	84.16 71	78.30 266

ab-mvs		66.65 202	66.42 186	67.37 245	76.17 213	41.73 299	70.41 278	76.14 206	53.99 219	65.98 190	83.51 165	49.48 111	76.24 276	48.60 240	73.46 193	84.14 157

v8		70.33 116	69.28 123	73.49 131	73.15 256	50.22 206	78.62 122	80.78 126	60.79 86	66.45 183	82.11 197	49.35 112	84.98 111	63.58 124	68.71 267	85.28 125

IS-MVSNet		71.57 93	71.00 94	73.27 139	78.86 141	45.63 265	80.22 97	78.69 159	64.14 35	66.46 182	87.36 76	49.30 113	85.60 95	50.26 226	83.71 74	88.59 9

XXY-MVS		60.68 264	61.67 246	57.70 320	70.43 302	38.45 323	64.19 319	66.47 298	48.05 289	63.22 236	80.86 222	49.28 114	60.47 342	45.25 272	67.28 279	74.19 314

cdsmvs_eth3d_5k		17.50 363	23.34 362	0.00 384	0.00 406	0.00 408	0.00 395	78.63 161	0.00 402	0.00 403	82.18 191	49.25 115	0.00 401	0.00 402	0.00 399	0.00 399

PVSNet_Blended_VisFu		71.45 96	70.39 103	74.65 92	82.01 79	58.82 71	79.93 103	80.35 133	55.09 197	65.82 197	82.16 194	49.17 116	82.64 163	60.34 150	78.62 135	82.50 206

PVSNet_BlendedMVS		68.56 162	67.72 152	71.07 191	77.03 198	50.57 200	74.50 216	81.52 100	53.66 224	64.22 229	79.72 242	49.13 117	82.87 154	55.82 177	73.92 182	79.77 255

PVSNet_Blended		68.59 158	67.72 152	71.19 186	77.03 198	50.57 200	72.51 248	81.52 100	51.91 238	64.22 229	77.77 275	49.13 117	82.87 154	55.82 177	79.58 116	80.14 248

DU-MVS		70.01 121	69.53 118	71.44 177	78.05 166	44.13 277	75.01 205	81.51 102	64.37 28	68.20 142	84.52 141	49.12 119	82.82 158	54.62 190	70.43 232	87.37 46

Baseline_NR-MVSNet		67.05 193	67.56 156	65.50 270	75.65 219	37.70 331	75.42 195	74.65 233	59.90 106	68.14 146	83.15 171	49.12 119	77.20 259	52.23 208	69.78 249	81.60 219

VPNet		67.52 182	68.11 147	65.74 268	79.18 134	36.80 340	72.17 253	72.83 253	62.04 72	67.79 158	85.83 119	48.88 121	76.60 270	51.30 218	72.97 202	83.81 169

MTAPA		76.90 33	76.42 34	78.35 35	86.08 37	63.57 2	74.92 208	80.97 123	65.13 15	75.77 35	90.88 17	48.63 122	86.66 70	77.23 24	88.17 33	84.81 140

原ACMM1				74.69 89	85.39 47	59.40 54		83.42 69	51.47 245	70.27 108	86.61 92	48.61 123	86.51 76	53.85 197	87.96 39	78.16 268

v148		68.24 168	67.19 176	71.40 180	70.43 302	47.77 242	75.76 190	77.03 195	58.91 121	67.36 164	80.10 235	48.60 124	81.89 175	60.01 153	66.52 285	84.53 146

PGM-MVS		76.77 34	76.06 37	78.88 27	86.14 35	62.73 9	82.55 67	83.74 60	61.71 76	72.45 91	90.34 29	48.48 125	88.13 35	72.32 58	86.85 50	85.78 99

Test By Simon												48.33 126

CP-MVS		77.12 31	76.68 31	78.43 33	86.05 38	63.18 5	87.55 10	83.45 68	62.44 64	72.68 85	90.50 24	48.18 127	87.34 50	73.59 52	85.71 58	84.76 143

MVS		67.37 184	66.33 190	70.51 201	75.46 224	50.94 192	73.95 225	81.85 96	41.57 345	62.54 247	78.57 262	47.98 128	85.47 102	52.97 204	82.05 90	75.14 300

XVS		77.17 30	76.56 33	79.00 23	86.32 29	62.62 11	85.83 22	83.92 52	64.55 23	72.17 92	90.01 40	47.95 129	88.01 38	71.55 65	86.74 52	86.37 74

X-MVStestdata		70.21 118	67.28 170	79.00 23	86.32 29	62.62 11	85.83 22	83.92 52	64.55 23	72.17 92	6.49 396	47.95 129	88.01 38	71.55 65	86.74 52	86.37 74

SDMVSNet		68.03 171	68.10 148	67.84 239	77.13 194	48.72 231	65.32 312	79.10 149	58.02 139	65.08 213	82.55 181	47.83 131	73.40 287	63.92 120	73.92 182	81.41 222

MAR-MVS		71.51 94	70.15 109	75.60 74	81.84 83	59.39 55	81.38 86	82.90 83	54.90 205	68.08 148	78.70 257	47.73 132	85.51 99	51.68 217	84.17 70	81.88 217
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		67.92 175	66.69 180	71.63 173	78.09 164	49.02 225	77.09 161	81.24 117	51.04 253	60.91 263	83.98 153	47.71 133	84.99 109	40.81 302	79.32 122	80.90 236

SR-MVS		76.13 41	75.70 42	77.40 48	85.87 40	61.20 29	85.52 27	82.19 91	59.99 105	75.10 39	90.35 28	47.66 134	86.52 75	71.64 64	82.99 78	84.47 149

cl22		67.47 183	66.45 183	70.54 200	69.85 313	46.49 253	73.85 230	77.35 191	55.07 200	65.51 201	77.92 268	47.64 135	81.10 192	61.58 143	69.32 256	84.01 161

v10		70.21 118	69.02 127	73.81 114	73.51 253	50.92 194	78.74 119	81.39 105	60.05 104	66.39 184	81.83 202	47.58 136	85.41 105	62.80 130	68.86 266	85.09 132

v1144		70.42 114	69.31 122	73.76 117	73.22 254	50.64 199	77.83 141	81.43 104	58.58 128	69.40 125	81.16 213	47.53 137	85.29 107	64.01 118	70.64 228	85.34 122

v2v482		70.50 112	69.45 121	73.66 123	72.62 266	50.03 211	77.58 145	80.51 130	59.90 106	69.52 121	82.14 195	47.53 137	84.88 116	65.07 111	70.17 239	86.09 88

pm-mvs1		65.24 221	64.97 211	66.04 263	72.38 272	39.40 316	72.62 245	75.63 212	55.53 188	62.35 253	83.18 170	47.45 139	76.47 273	49.06 237	66.54 284	82.24 209

HY-MVS	56.14 13	64.55 230	63.89 218	66.55 253	74.73 236	41.02 304	69.96 282	74.43 234	49.29 272	61.66 258	80.92 220	47.43 140	76.68 269	44.91 273	71.69 219	81.94 215

cl____		67.18 189	66.26 194	69.94 209	70.20 305	45.74 261	73.30 235	76.83 198	55.10 195	65.27 206	79.57 245	47.39 141	80.53 205	59.41 161	69.22 260	83.53 183

DIV-MVS_self_test		67.18 189	66.26 194	69.94 209	70.20 305	45.74 261	73.29 236	76.83 198	55.10 195	65.27 206	79.58 244	47.38 142	80.53 205	59.43 160	69.22 260	83.54 182

eth_miper_zixun_eth		67.63 180	66.28 193	71.67 171	71.60 283	48.33 235	73.68 233	77.88 179	55.80 182	65.91 192	78.62 261	47.35 143	82.88 153	59.45 159	66.25 286	83.81 169

OPM-MVS		74.73 52	74.25 55	76.19 61	80.81 101	59.01 67	82.60 66	83.64 62	63.74 39	72.52 88	87.49 74	47.18 144	85.88 90	69.47 74	80.78 99	83.66 179
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline1		63.81 235	63.87 220	63.62 283	76.29 211	36.36 343	71.78 259	67.29 293	56.05 176	64.23 228	82.95 173	47.11 145	74.41 283	47.30 249	61.85 322	80.10 249

pcd_1.5k_mvsjas		3.92 369	5.23 372	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	47.05 146	0.00 401	0.00 402	0.00 399	0.00 399

PS-MVSNAJss		72.24 81	71.21 89	75.31 78	78.50 150	55.93 112	81.63 81	82.12 92	56.24 172	70.02 113	85.68 122	47.05 146	84.34 124	65.27 109	74.41 178	85.67 106

PS-MVSNAJ		70.51 111	69.70 115	72.93 144	81.52 86	55.79 116	74.92 208	79.00 151	55.04 202	69.88 117	78.66 258	47.05 146	82.19 171	61.61 141	79.58 116	80.83 237

WTY-MVS		59.75 270	60.39 259	57.85 318	72.32 274	37.83 328	61.05 337	64.18 313	45.95 313	61.91 255	79.11 254	47.01 149	60.88 341	42.50 293	69.49 255	74.83 306

xiu_mvs_v2_base		70.52 110	69.75 113	72.84 146	81.21 95	55.63 120	75.11 202	78.92 153	54.92 204	69.96 116	79.68 243	47.00 150	82.09 173	61.60 142	79.37 119	80.81 238

v144192		69.71 129	68.51 137	73.33 138	73.10 257	50.13 208	77.54 148	80.64 127	56.65 159	68.57 137	80.55 226	46.87 151	84.96 113	62.98 128	69.66 253	84.89 138

PEN-MVS		66.60 203	66.45 183	67.04 248	77.11 196	36.56 342	77.03 163	80.42 131	62.95 50	62.51 249	84.03 151	46.69 152	79.07 233	44.22 274	63.08 313	85.51 113

mPP-MVS		76.54 35	75.93 39	78.34 36	86.47 26	63.50 3	85.74 25	82.28 90	62.90 52	71.77 95	90.26 31	46.61 153	86.55 74	71.71 63	85.66 59	84.97 136

CP-MVSNet		66.49 206	66.41 187	66.72 250	77.67 177	36.33 345	76.83 170	79.52 143	62.45 63	62.54 247	83.47 167	46.32 154	78.37 241	45.47 269	63.43 310	85.45 116

V42		68.65 157	67.35 168	72.56 151	68.93 323	50.18 207	72.90 241	79.47 144	56.92 156	69.45 124	80.26 232	46.29 155	82.99 148	64.07 116	67.82 274	84.53 146

1112_ss		64.00 234	63.36 227	65.93 265	79.28 130	42.58 291	71.35 262	72.36 257	46.41 306	60.55 265	77.89 270	46.27 156	73.28 288	46.18 258	69.97 244	81.92 216

MSLP-MVS++		73.77 63	73.47 63	74.66 91	83.02 71	59.29 58	82.30 74	81.88 95	59.34 117	71.59 98	86.83 83	45.94 157	83.65 137	65.09 110	85.22 61	81.06 234

PS-CasMVS		66.42 207	66.32 191	66.70 252	77.60 185	36.30 347	76.94 165	79.61 141	62.36 65	62.43 251	83.66 159	45.69 158	78.37 241	45.35 271	63.26 311	85.42 119

APD-MVS_3200maxsize		74.96 48	74.39 54	76.67 54	82.20 78	58.24 77	83.67 51	83.29 75	58.41 131	73.71 64	90.14 33	45.62 159	85.99 87	69.64 72	82.85 84	85.78 99

DTE-MVSNet		65.58 215	65.34 206	66.31 255	76.06 215	34.79 351	76.43 175	79.38 146	62.55 61	61.66 258	83.83 156	45.60 160	79.15 231	41.64 301	60.88 328	85.00 134

BH-w/o		66.85 197	65.83 199	69.90 212	79.29 129	52.46 175	74.66 214	76.65 201	54.51 213	64.85 219	78.12 264	45.59 161	82.95 150	43.26 286	75.54 171	74.27 313

h-mvs33		72.71 74	71.49 82	76.40 58	81.99 81	59.58 52	76.92 166	76.74 200	60.40 93	74.81 47	85.95 115	45.54 162	85.76 93	70.41 70	70.61 230	83.86 168

hse-mvs2		71.04 100	69.86 112	74.60 95	79.58 123	57.12 96	73.96 224	75.25 220	60.40 93	74.81 47	81.95 199	45.54 162	82.90 151	70.41 70	66.83 282	83.77 173

HQP2-MVS												45.46 164

HQP-MVS		73.45 64	72.80 68	75.40 76	80.66 102	54.94 131	82.31 71	83.90 54	62.10 68	67.85 152	85.54 126	45.46 164	86.93 62	67.04 93	80.35 107	84.32 151

ACMMP		76.02 42	75.33 45	78.07 38	85.20 49	61.91 20	85.49 29	84.44 41	63.04 49	69.80 119	89.74 46	45.43 166	87.16 55	72.01 60	82.87 83	85.14 129
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 97	70.60 99	73.78 115	76.60 206	53.15 159	79.74 108	79.78 137	58.37 132	68.75 134	86.45 99	45.43 166	80.60 204	62.58 131	77.73 144	87.58 39

BH-untuned		68.27 166	67.29 169	71.21 185	79.74 120	53.22 158	76.06 183	77.46 189	57.19 152	66.10 188	81.61 206	45.37 168	83.50 140	45.42 270	76.68 163	76.91 287

v1192		69.97 123	68.68 134	73.85 112	73.19 255	50.94 192	77.68 144	81.36 107	57.51 149	68.95 133	80.85 223	45.28 169	85.33 106	62.97 129	70.37 234	85.27 126

HQP_MVS		74.31 58	73.73 61	76.06 62	81.41 89	56.31 102	84.22 40	84.01 49	64.52 25	69.27 127	86.10 108	45.26 170	87.21 53	68.16 81	80.58 103	84.65 144

plane_prior6					81.20 96	56.24 106						45.26 170

CL-MVSNet_self_test		61.53 259	60.94 256	63.30 286	68.95 322	36.93 339	67.60 295	72.80 254	55.67 185	59.95 271	76.63 285	45.01 172	72.22 294	39.74 309	62.09 321	80.74 239

SR-MVS-dyc-post		74.57 55	73.90 58	76.58 56	83.49 65	59.87 49	84.29 37	81.36 107	58.07 137	73.14 74	90.07 34	44.74 173	85.84 91	68.20 79	81.76 94	84.03 159

v1921920		69.47 140	68.17 146	73.36 137	73.06 258	50.10 209	77.39 151	80.56 128	56.58 166	68.59 135	80.37 228	44.72 174	84.98 111	62.47 134	69.82 248	85.00 134

Vis-MVSNet (Re-imp)		63.69 236	63.88 219	63.14 288	74.75 235	31.04 371	71.16 267	63.64 316	56.32 169	59.80 274	84.99 131	44.51 175	75.46 278	39.12 311	80.62 101	82.92 197

DP-MVS Recon		72.15 86	70.73 98	76.40 58	86.57 24	57.99 79	81.15 89	82.96 81	57.03 154	66.78 175	85.56 123	44.50 176	88.11 36	51.77 215	80.23 110	83.10 195

TAMVS		66.78 200	65.27 208	71.33 184	79.16 136	53.67 146	73.84 231	69.59 278	52.32 236	65.28 205	81.72 204	44.49 177	77.40 257	42.32 294	78.66 134	82.92 197

Vis-MVSNet		72.18 82	71.37 86	74.61 94	81.29 92	55.41 126	80.90 90	78.28 175	60.73 88	69.23 130	88.09 64	44.36 178	82.65 162	57.68 165	81.75 96	85.77 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
旧先验1					83.04 70	53.15 159		67.52 290			87.85 71	44.08 179			80.76 100	78.03 273

Test_1112_low_res		62.32 250	61.77 245	64.00 282	79.08 138	39.53 315	68.17 291	70.17 272	43.25 334	59.03 284	79.90 237	44.08 179	71.24 298	43.79 282	68.42 270	81.25 228

MVSFormer		71.50 95	70.38 104	74.88 85	78.76 144	57.15 94	82.79 61	78.48 166	51.26 249	69.49 122	83.22 168	43.99 181	83.24 144	66.06 99	79.37 119	84.23 154

lupinMVS		69.57 136	68.28 145	73.44 134	78.76 144	57.15 94	76.57 172	73.29 250	46.19 308	69.49 122	82.18 191	43.99 181	79.23 226	64.66 113	79.37 119	83.93 163

v7n		69.01 151	67.36 167	73.98 110	72.51 270	52.65 168	78.54 125	81.30 113	60.26 101	62.67 243	81.62 205	43.61 183	84.49 121	57.01 169	68.70 268	84.79 141

CDS-MVSNet		66.80 199	65.37 205	71.10 190	78.98 139	53.13 161	73.27 237	71.07 266	52.15 237	64.72 220	80.23 233	43.56 184	77.10 260	45.48 268	78.88 128	83.05 196
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
jason		69.65 133	68.39 144	73.43 135	78.27 159	56.88 98	77.12 160	73.71 246	46.53 305	69.34 126	83.22 168	43.37 185	79.18 227	64.77 112	79.20 124	84.23 154
jason: jason.
v1240		69.24 148	67.91 150	73.25 141	73.02 260	49.82 213	77.21 158	80.54 129	56.43 168	68.34 141	80.51 227	43.33 186	84.99 109	62.03 138	69.77 251	84.95 137

LCM-MVSNet-Re		61.88 256	61.35 250	63.46 284	74.58 240	31.48 370	61.42 332	58.14 343	58.71 126	53.02 338	79.55 246	43.07 187	76.80 265	45.69 263	77.96 142	82.11 213

RE-MVS-def			73.71 62		83.49 65	59.87 49	84.29 37	81.36 107	58.07 137	73.14 74	90.07 34	43.06 188		68.20 79	81.76 94	84.03 159

baseline2		63.42 238	61.26 252	69.89 213	72.55 268	47.62 244	71.54 260	68.38 288	50.11 262	54.82 320	75.55 301	43.06 188	80.96 195	48.13 243	67.16 280	81.11 232

FA-MVS(test-final)		69.82 126	68.48 138	73.84 113	78.44 153	50.04 210	75.58 194	78.99 152	58.16 135	67.59 161	82.14 195	42.66 190	85.63 94	56.60 171	76.19 165	85.84 97

BH-RMVSNet		68.81 153	67.42 164	72.97 143	80.11 116	52.53 173	74.26 219	76.29 203	58.48 130	68.38 140	84.20 146	42.59 191	83.83 133	46.53 255	75.91 167	82.56 202

LFMVS		71.78 89	71.59 79	72.32 158	83.40 67	46.38 254	79.75 107	71.08 265	64.18 32	72.80 83	88.64 59	42.58 192	83.72 135	57.41 168	84.49 66	86.86 58

test_yl		69.69 130	69.13 124	71.36 181	78.37 155	45.74 261	74.71 212	80.20 134	57.91 144	70.01 114	83.83 156	42.44 193	82.87 154	54.97 186	79.72 113	85.48 114

DCV-MVSNet		69.69 130	69.13 124	71.36 181	78.37 155	45.74 261	74.71 212	80.20 134	57.91 144	70.01 114	83.83 156	42.44 193	82.87 154	54.97 186	79.72 113	85.48 114

3Dnovator	64.47 5	72.49 77	71.39 85	75.79 66	77.70 175	58.99 68	80.66 94	83.15 79	62.24 66	65.46 202	86.59 93	42.38 195	85.52 98	59.59 158	84.72 63	82.85 200

VDD-MVS		72.50 76	72.09 75	73.75 119	81.58 85	49.69 217	77.76 143	77.63 185	63.21 47	73.21 71	89.02 53	42.14 196	83.32 142	61.72 140	82.50 87	88.25 15

3Dnovator+	66.72 4	75.84 44	74.57 52	79.66 9	82.40 76	59.92 48	85.83 22	86.32 16	66.92 7	67.80 157	89.24 51	42.03 197	89.38 19	64.07 116	86.50 55	89.69 2

MVS_111021_LR		69.50 139	68.78 132	71.65 172	78.38 154	59.33 56	74.82 210	70.11 273	58.08 136	67.83 156	84.68 135	41.96 198	76.34 275	65.62 106	77.54 146	79.30 260

CPTT-MVS		72.78 72	72.08 76	74.87 86	84.88 57	61.41 26	84.15 43	77.86 180	55.27 192	67.51 163	88.08 65	41.93 199	81.85 176	69.04 77	80.01 111	81.35 227

GBi-Net		67.21 186	66.55 181	69.19 223	77.63 178	43.33 284	77.31 153	77.83 181	56.62 162	65.04 215	82.70 175	41.85 200	80.33 210	47.18 250	72.76 204	83.92 164

test1		67.21 186	66.55 181	69.19 223	77.63 178	43.33 284	77.31 153	77.83 181	56.62 162	65.04 215	82.70 175	41.85 200	80.33 210	47.18 250	72.76 204	83.92 164

FMVSNet2		66.93 196	66.31 192	68.79 230	77.63 178	42.98 288	76.11 181	77.47 187	56.62 162	65.22 212	82.17 193	41.85 200	80.18 216	47.05 253	72.72 207	83.20 190

CostFormer		64.04 233	62.51 237	68.61 232	71.88 280	45.77 260	71.30 264	70.60 270	47.55 295	64.31 226	76.61 287	41.63 203	79.62 221	49.74 229	69.00 263	80.42 242

AdaColmap		69.99 122	68.66 135	73.97 111	84.94 54	57.83 80	82.63 65	78.71 158	56.28 171	64.34 224	84.14 148	41.57 204	87.06 61	46.45 256	78.88 128	77.02 283

Effi-MVS+-dtu		69.64 134	67.53 159	75.95 64	76.10 214	62.29 15	80.20 98	76.06 208	59.83 110	65.26 209	77.09 279	41.56 205	84.02 130	60.60 149	71.09 226	81.53 220

QAPM		70.05 120	68.81 131	73.78 115	76.54 208	53.43 153	83.23 54	83.48 66	52.89 230	65.90 193	86.29 102	41.55 206	86.49 77	51.01 220	78.40 138	81.42 221

VDDNet		71.81 88	71.33 87	73.26 140	82.80 75	47.60 245	78.74 119	75.27 219	59.59 114	72.94 80	89.40 48	41.51 207	83.91 132	58.75 162	82.99 78	88.26 14

CHOSEN 1792x2688		65.08 224	62.84 234	71.82 166	81.49 88	56.26 105	66.32 301	74.20 240	40.53 350	63.16 238	78.65 259	41.30 208	77.80 250	45.80 262	74.09 180	81.40 224

新几何1				70.76 195	85.66 41	61.13 30		66.43 299	44.68 320	70.29 107	86.64 90	41.29 209	75.23 279	49.72 230	81.75 96	75.93 292

tpmrst		58.24 277	58.70 268	56.84 322	66.97 334	34.32 356	69.57 286	61.14 335	47.17 302	58.58 290	71.60 328	41.28 210	60.41 343	49.20 235	62.84 314	75.78 294

tfpnnormal		62.47 248	61.63 247	64.99 276	74.81 233	39.01 318	71.22 265	73.72 245	55.22 194	60.21 266	80.09 236	41.26 211	76.98 263	30.02 362	68.09 272	78.97 263

sd_testset		64.46 231	64.45 214	64.51 279	77.13 194	42.25 294	62.67 325	72.11 259	58.02 139	65.08 213	82.55 181	41.22 212	69.88 306	47.32 248	73.92 182	81.41 222

HPM-MVS_fast		74.30 59	73.46 64	76.80 52	84.45 60	59.04 66	83.65 52	81.05 120	60.15 102	70.43 105	89.84 43	41.09 213	85.59 96	67.61 88	82.90 82	85.77 102

114514_t		70.83 105	69.56 116	74.64 93	86.21 31	54.63 136	82.34 70	81.81 97	48.22 285	63.01 239	85.83 119	40.92 214	87.10 59	57.91 164	79.79 112	82.18 210

HyFIR lowres test		65.67 214	63.01 232	73.67 122	79.97 118	55.65 119	69.07 289	75.52 215	42.68 339	63.53 234	77.95 266	40.43 215	81.64 179	46.01 260	71.91 217	83.73 175

miper_lstm_enhance		62.03 254	60.88 257	65.49 271	66.71 337	46.25 255	56.29 357	75.70 211	50.68 256	61.27 261	75.48 302	40.21 216	68.03 315	56.31 174	65.25 293	82.18 210

FMVSNet3		66.32 208	65.61 203	68.46 233	76.48 209	42.34 292	74.98 207	77.15 194	55.83 180	65.04 215	81.16 213	39.91 217	80.14 217	47.18 250	72.76 204	82.90 199

Syy-MVS		56.00 296	56.23 289	55.32 329	74.69 237	26.44 385	65.52 307	57.49 347	50.97 254	56.52 304	72.18 321	39.89 218	68.09 313	24.20 378	64.59 300	71.44 341

MVP-Stereo		65.41 218	63.80 221	70.22 203	77.62 182	55.53 124	76.30 177	78.53 164	50.59 259	56.47 306	78.65 259	39.84 219	82.68 161	44.10 278	72.12 216	72.44 328
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TR-MVS		66.59 205	65.07 210	71.17 188	79.18 134	49.63 219	73.48 234	75.20 223	52.95 228	67.90 150	80.33 231	39.81 220	83.68 136	43.20 287	73.56 190	80.20 246

pmmvs6		63.69 236	62.82 235	66.27 257	70.63 299	39.27 317	73.13 238	75.47 216	52.69 232	59.75 276	82.30 189	39.71 221	77.03 262	47.40 247	64.35 302	82.53 204

XVG-OURS-SEG-HR		68.81 153	67.47 163	72.82 148	74.40 245	56.87 99	70.59 274	79.04 150	54.77 206	66.99 171	86.01 112	39.57 222	78.21 244	62.54 132	73.33 195	83.37 185

Anonymous20231211		69.28 146	68.47 140	71.73 169	80.28 108	47.18 249	79.98 101	82.37 89	54.61 209	67.24 166	84.01 152	39.43 223	82.41 169	55.45 184	72.83 203	85.62 110

Fast-Effi-MVS+-dtu		67.37 184	65.33 207	73.48 132	72.94 261	57.78 82	77.47 150	76.88 196	57.60 148	61.97 254	76.85 283	39.31 224	80.49 208	54.72 189	70.28 237	82.17 212

dmvs_testset		50.16 326	51.90 316	44.94 360	66.49 339	11.78 398	61.01 338	51.50 365	51.17 252	50.30 352	67.44 354	39.28 225	60.29 344	22.38 380	57.49 342	62.76 365

ACMP	63.53 6	72.30 80	71.20 90	75.59 75	80.28 108	57.54 84	82.74 63	82.84 85	60.58 90	65.24 210	86.18 105	39.25 226	86.03 86	66.95 95	76.79 161	83.22 189
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20240529		69.91 124	69.02 127	72.56 151	80.19 113	47.65 243	77.56 147	80.99 122	55.45 190	69.88 117	86.76 85	39.24 227	82.18 172	54.04 194	77.10 157	87.85 27

LPG-MVS_test		72.74 73	71.74 78	75.76 67	80.22 110	57.51 86	82.55 67	83.40 70	61.32 79	66.67 179	87.33 77	39.15 228	86.59 71	67.70 86	77.30 153	83.19 191

LGP-MVS_train				75.76 67	80.22 110	57.51 86		83.40 70	61.32 79	66.67 179	87.33 77	39.15 228	86.59 71	67.70 86	77.30 153	83.19 191

TAPA-MVS	59.36 10	66.60 203	65.20 209	70.81 194	76.63 205	48.75 229	76.52 174	80.04 136	50.64 258	65.24 210	84.93 132	39.15 228	78.54 240	36.77 323	76.88 160	85.14 129
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OpenMVS	61.03 9	68.85 152	67.56 156	72.70 150	74.26 248	53.99 142	81.21 88	81.34 111	52.70 231	62.75 242	85.55 125	38.86 231	84.14 126	48.41 242	83.01 77	79.97 250

sss		56.17 295	56.57 285	54.96 331	66.93 335	36.32 346	57.94 349	61.69 332	41.67 343	58.64 288	75.32 304	38.72 232	56.25 364	42.04 296	66.19 287	72.31 332

ACMM	61.98 7	70.80 107	69.73 114	74.02 109	80.59 107	58.59 74	82.68 64	82.02 94	55.46 189	67.18 168	84.39 145	38.51 233	83.17 146	60.65 148	76.10 166	80.30 245
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVSTER		67.16 191	65.58 204	71.88 164	70.37 304	49.70 215	70.25 280	78.45 169	51.52 243	69.16 131	80.37 228	38.45 234	82.50 166	60.19 151	71.46 222	83.44 184

test_djsdf		69.45 141	67.74 151	74.58 96	74.57 241	54.92 133	82.79 61	78.48 166	51.26 249	65.41 203	83.49 166	38.37 235	83.24 144	66.06 99	69.25 259	85.56 111

tpm2		62.07 253	60.10 261	67.99 238	72.79 263	43.86 280	71.05 271	66.85 297	43.14 336	62.77 240	75.39 303	38.32 236	80.80 201	41.69 298	68.88 264	79.32 259

tpm cat1		59.25 272	56.95 281	66.15 260	72.19 276	46.96 250	68.09 292	65.76 302	40.03 354	57.81 295	70.56 335	38.32 236	74.51 282	38.26 315	61.50 325	77.00 284

CNLPA		65.43 217	64.02 217	69.68 215	78.73 146	58.07 78	77.82 142	70.71 269	51.49 244	61.57 260	83.58 164	38.23 238	70.82 299	43.90 280	70.10 241	80.16 247

1314		64.61 229	63.21 230	68.80 229	71.87 281	47.46 246	73.95 225	78.39 174	42.88 338	59.97 270	76.60 288	38.11 239	79.39 224	54.84 188	72.32 212	79.55 256

testdata				64.66 277	81.52 86	52.93 162		65.29 306	46.09 309	73.88 62	87.46 75	38.08 240	66.26 325	53.31 202	78.48 136	74.78 308

FMVSNet1		66.70 201	65.87 198	69.19 223	77.49 187	43.33 284	77.31 153	77.83 181	56.45 167	64.60 223	82.70 175	38.08 240	80.33 210	46.08 259	72.31 213	83.92 164

UniMVSNet_ETH3D		67.60 181	67.07 178	69.18 226	77.39 189	42.29 293	74.18 221	75.59 213	60.37 96	66.77 176	86.06 110	37.64 242	78.93 239	52.16 209	73.49 191	86.32 80

EPNet_dtu		61.90 255	61.97 244	61.68 296	72.89 262	39.78 312	75.85 189	65.62 304	55.09 197	54.56 324	79.36 250	37.59 243	67.02 320	39.80 308	76.95 158	78.25 267
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IterMVS-SCA-FT		62.49 247	61.52 248	65.40 272	71.99 279	50.80 197	71.15 268	69.63 277	45.71 314	60.61 264	77.93 267	37.45 244	65.99 326	55.67 181	63.50 309	79.42 258

SCA		60.49 265	58.38 271	66.80 249	74.14 250	48.06 238	63.35 322	63.23 319	49.13 274	59.33 282	72.10 323	37.45 244	74.27 284	44.17 275	62.57 316	78.05 270

tt0805		67.77 178	67.24 174	69.34 222	74.87 231	40.08 309	77.36 152	81.37 106	55.31 191	66.33 185	84.65 137	37.35 246	82.55 165	55.65 182	72.28 214	85.39 121

IterMVS		62.79 246	61.27 251	67.35 246	69.37 318	52.04 183	71.17 266	68.24 289	52.63 233	59.82 273	76.91 282	37.32 247	72.36 291	52.80 205	63.19 312	77.66 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpn200view9		63.18 243	62.18 242	66.21 258	76.85 201	39.62 313	71.96 257	69.44 280	56.63 160	62.61 245	79.83 238	37.18 248	79.17 228	31.84 349	73.25 197	79.83 253

thres400		63.31 239	62.18 242	66.72 250	76.85 201	39.62 313	71.96 257	69.44 280	56.63 160	62.61 245	79.83 238	37.18 248	79.17 228	31.84 349	73.25 197	81.36 225

tpm		57.34 284	58.16 273	54.86 332	71.80 282	34.77 352	67.47 297	56.04 356	48.20 286	60.10 268	76.92 281	37.17 250	53.41 373	40.76 303	65.01 294	76.40 290

mvsmamba		71.15 98	69.54 117	75.99 63	77.61 183	53.46 152	81.95 78	75.11 225	57.73 147	66.95 173	85.96 114	37.14 251	87.56 48	67.94 83	75.49 172	86.97 54

test222					83.14 68	58.68 73	72.57 247	63.45 317	41.78 341	67.56 162	86.12 107	37.13 252			78.73 133	74.98 304

AUN-MVS		68.45 164	66.41 187	74.57 97	79.53 125	57.08 97	73.93 227	75.23 221	54.44 214	66.69 178	81.85 201	37.10 253	82.89 152	62.07 136	66.84 281	83.75 174

thres200		62.20 252	61.16 254	65.34 273	75.38 226	39.99 310	69.60 285	69.29 282	55.64 187	61.87 256	76.99 280	37.07 254	78.96 238	31.28 357	73.28 196	77.06 282

thres100view900		63.28 241	62.41 239	65.89 266	77.31 191	38.66 321	72.65 243	69.11 284	57.07 153	62.45 250	81.03 217	37.01 255	79.17 228	31.84 349	73.25 197	79.83 253

thres600view7		63.30 240	62.27 240	66.41 254	77.18 193	38.87 319	72.35 250	69.11 284	56.98 155	62.37 252	80.96 219	37.01 255	79.00 237	31.43 356	73.05 201	81.36 225

DP-MVS		65.68 213	63.66 223	71.75 168	84.93 55	56.87 99	80.74 93	73.16 251	53.06 227	59.09 283	82.35 187	36.79 257	85.94 89	32.82 345	69.96 245	72.45 327

XVG-OURS		68.76 156	67.37 166	72.90 145	74.32 247	57.22 89	70.09 281	78.81 155	55.24 193	67.79 158	85.81 121	36.54 258	78.28 243	62.04 137	75.74 169	83.19 191

ECVR-MVS		67.72 179	67.51 160	68.35 235	79.46 126	36.29 348	74.79 211	66.93 296	58.72 124	67.19 167	88.05 66	36.10 259	81.38 185	52.07 210	84.25 68	87.39 44

test1111		67.21 186	67.14 177	67.42 244	79.24 132	34.76 353	73.89 229	65.65 303	58.71 126	66.96 172	87.95 69	36.09 260	80.53 205	52.03 211	83.79 73	86.97 54

pmmvs4		61.48 261	59.39 262	67.76 240	71.57 284	53.86 143	71.42 261	65.34 305	44.20 325	59.46 278	77.92 268	35.90 261	74.71 281	43.87 281	64.87 296	74.71 309

CR-MVSNet		59.91 268	57.90 276	65.96 264	69.96 310	52.07 181	65.31 313	63.15 320	42.48 340	59.36 279	74.84 306	35.83 262	70.75 300	45.50 267	64.65 298	75.06 301

Patchmtry		57.16 285	56.47 286	59.23 305	69.17 321	34.58 355	62.98 323	63.15 320	44.53 321	56.83 301	74.84 306	35.83 262	68.71 310	40.03 306	60.91 327	74.39 312

dmvs_re		56.77 288	56.83 283	56.61 323	69.23 319	41.02 304	58.37 346	64.18 313	50.59 259	57.45 298	71.42 329	35.54 264	58.94 351	37.23 320	67.45 277	69.87 354

RPMNet		61.53 259	58.42 270	70.86 193	69.96 310	52.07 181	65.31 313	81.36 107	43.20 335	59.36 279	70.15 340	35.37 265	85.47 102	36.42 330	64.65 298	75.06 301

CANet_DTU		68.18 169	67.71 154	69.59 217	74.83 232	46.24 256	78.66 121	76.85 197	59.60 111	63.45 235	82.09 198	35.25 266	77.41 256	59.88 155	78.76 132	85.14 129

thisisatest0530		67.92 175	65.78 200	74.33 103	76.29 211	51.03 191	76.89 167	74.25 239	53.67 223	65.59 200	81.76 203	35.15 267	85.50 100	55.94 175	72.47 208	86.47 71

tttt0517		67.83 177	65.66 202	74.33 103	76.69 203	50.82 196	77.86 139	73.99 242	54.54 212	64.64 222	82.53 184	35.06 268	85.50 100	55.71 180	69.91 246	86.67 65

test_0402		63.25 242	61.01 255	69.96 208	80.00 117	54.37 139	76.86 169	72.02 260	54.58 211	58.71 286	80.79 225	35.00 269	84.36 123	26.41 375	64.71 297	71.15 345

thisisatest0515		65.83 212	63.50 225	72.82 148	73.75 251	49.50 220	71.32 263	73.12 252	49.39 270	63.82 231	76.50 291	34.95 270	84.84 117	53.20 203	75.49 172	84.13 158

sam_mvs1												34.74 271				78.05 270

pmmvs5		56.47 291	55.68 293	58.86 309	61.41 364	36.71 341	66.37 300	62.75 322	40.38 351	53.70 331	76.62 286	34.56 272	67.05 319	40.02 307	65.27 292	72.83 322

patchmatchnet-post											64.03 366	34.50 273	74.27 284

PatchmatchNet		59.84 269	58.24 272	64.65 278	73.05 259	46.70 252	69.42 287	62.18 329	47.55 295	58.88 285	71.96 325	34.49 274	69.16 308	42.99 289	63.60 307	78.07 269
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmatch-test		49.08 329	48.28 331	51.50 350	64.40 350	30.85 372	45.68 378	48.46 374	35.60 362	46.10 364	72.10 323	34.47 275	46.37 383	27.08 373	60.65 331	77.27 279

MS-PatchMatch		62.42 249	61.46 249	65.31 274	75.21 228	52.10 180	72.05 254	74.05 241	46.41 306	57.42 299	74.36 310	34.35 276	77.57 254	45.62 265	73.67 186	66.26 362

tpmvs		58.47 275	56.95 281	63.03 290	70.20 305	41.21 303	67.90 294	67.23 294	49.62 268	54.73 322	70.84 333	34.14 277	76.24 276	36.64 327	61.29 326	71.64 337

PMMVS		53.96 307	53.26 313	56.04 325	62.60 359	50.92 194	61.17 335	56.09 355	32.81 365	53.51 336	66.84 359	34.04 278	59.93 346	44.14 277	68.18 271	57.27 374

Patchmatch-RL test		58.16 278	55.49 294	66.15 260	67.92 330	48.89 228	60.66 339	51.07 368	47.86 292	59.36 279	62.71 370	34.02 279	72.27 293	56.41 173	59.40 335	77.30 278

WB-MVS		43.26 338	43.41 339	42.83 364	63.32 355	10.32 400	58.17 348	45.20 380	45.42 315	40.44 376	67.26 357	34.01 280	58.98 350	11.96 392	24.88 387	59.20 368

test_post											3.55 398	33.90 281	66.52 322

PLC	56.13 14	65.09 223	63.21 230	70.72 197	81.04 98	54.87 134	78.57 123	77.47 187	48.51 281	55.71 309	81.89 200	33.71 282	79.71 218	41.66 299	70.37 234	77.58 275
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ET-MVSNet_ETH3D		67.96 174	65.72 201	74.68 90	76.67 204	55.62 122	75.11 202	74.74 230	52.91 229	60.03 269	80.12 234	33.68 283	82.64 163	61.86 139	76.34 164	85.78 99

GA-MVS		65.53 216	63.70 222	71.02 192	70.87 297	48.10 237	70.48 276	74.40 235	56.69 158	64.70 221	76.77 284	33.66 284	81.10 192	55.42 185	70.32 236	83.87 167

LS3D		64.71 227	62.50 238	71.34 183	79.72 122	55.71 117	79.82 105	74.72 231	48.50 282	56.62 302	84.62 138	33.59 285	82.34 170	29.65 364	75.23 174	75.97 291

sam_mvs												33.43 286

PatchT		53.17 315	53.44 312	52.33 347	68.29 328	25.34 389	58.21 347	54.41 359	44.46 323	54.56 324	69.05 348	33.32 287	60.94 340	36.93 322	61.76 324	70.73 348

test20.03		53.87 309	54.02 308	53.41 342	61.47 363	28.11 378	61.30 333	59.21 339	51.34 248	52.09 340	77.43 277	33.29 288	58.55 353	29.76 363	60.27 333	73.58 318

our_test_3		56.49 290	54.42 302	62.68 292	69.51 315	45.48 266	66.08 302	61.49 333	44.11 328	50.73 348	69.60 345	33.05 289	68.15 312	38.38 314	56.86 344	74.40 311

anonymousdsp		67.00 195	64.82 212	73.57 129	70.09 308	56.13 107	76.35 176	77.35 191	48.43 283	64.99 218	80.84 224	33.01 290	80.34 209	64.66 113	67.64 276	84.23 154

MDTV_nov1_ep13_2view						25.89 387	61.22 334		40.10 353	51.10 343		32.97 291		38.49 313		78.61 265

IB-MVS	56.42 12	65.40 219	62.73 236	73.40 136	74.89 229	52.78 167	73.09 239	75.13 224	55.69 184	58.48 291	73.73 314	32.86 292	86.32 82	50.63 223	70.11 240	81.10 233
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		68.58 159	67.28 170	72.48 153	78.19 161	57.19 91	75.28 197	75.09 226	51.61 240	70.04 110	81.41 210	32.79 293	79.02 234	63.81 121	77.31 150	81.22 229

xiu_mvs_v1_base		68.58 159	67.28 170	72.48 153	78.19 161	57.19 91	75.28 197	75.09 226	51.61 240	70.04 110	81.41 210	32.79 293	79.02 234	63.81 121	77.31 150	81.22 229

xiu_mvs_v1_base_debi		68.58 159	67.28 170	72.48 153	78.19 161	57.19 91	75.28 197	75.09 226	51.61 240	70.04 110	81.41 210	32.79 293	79.02 234	63.81 121	77.31 150	81.22 229

Anonymous20231206		55.10 304	55.30 296	54.48 334	69.81 314	33.94 360	62.91 324	62.13 330	41.08 347	55.18 316	75.65 299	32.75 296	56.59 363	30.32 361	67.86 273	72.91 320

UGNet		68.81 153	67.39 165	73.06 142	78.33 157	54.47 137	79.77 106	75.40 217	60.45 92	63.22 236	84.40 144	32.71 297	80.91 199	51.71 216	80.56 105	83.81 169
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
SSC-MVS		41.96 342	41.99 342	41.90 365	62.46 360	9.28 402	57.41 353	44.32 383	43.38 332	38.30 380	66.45 360	32.67 298	58.42 354	10.98 393	21.91 390	57.99 372

test-LLR		58.15 279	58.13 275	58.22 314	68.57 324	44.80 271	65.46 309	57.92 344	50.08 263	55.44 312	69.82 342	32.62 299	57.44 357	49.66 231	73.62 187	72.41 329

test0.0.03 1		53.32 314	53.59 311	52.50 346	62.81 358	29.45 374	59.51 342	54.11 360	50.08 263	54.40 326	74.31 311	32.62 299	55.92 366	30.50 360	63.95 305	72.15 334

MDTV_nov1_ep13			57.00 280		72.73 264	38.26 324	65.02 316	64.73 310	44.74 319	55.46 311	72.48 319	32.61 301	70.47 301	37.47 318	67.75 275

cascas		65.98 210	63.42 226	73.64 125	77.26 192	52.58 171	72.26 252	77.21 193	48.56 280	61.21 262	74.60 309	32.57 302	85.82 92	50.38 225	76.75 162	82.52 205

test_post1							68.67 290				3.64 397	32.39 303	69.49 307	44.17 275

CVMVSNet		59.63 271	59.14 264	61.08 301	74.47 242	38.84 320	75.20 200	68.74 286	31.15 367	58.24 292	76.51 289	32.39 303	68.58 311	49.77 228	65.84 289	75.81 293

ppachtmachnet_test		58.06 280	55.38 295	66.10 262	69.51 315	48.99 226	68.01 293	66.13 301	44.50 322	54.05 329	70.74 334	32.09 305	72.34 292	36.68 326	56.71 347	76.99 286

MIMVSNet		57.35 283	57.07 279	58.22 314	74.21 249	37.18 334	62.46 326	60.88 336	48.88 277	55.29 315	75.99 296	31.68 306	62.04 338	31.87 348	72.35 210	75.43 299

test_vis1_n_1920		58.86 273	59.06 265	58.25 313	63.76 352	43.14 287	67.49 296	66.36 300	40.22 352	65.89 194	71.95 326	31.04 307	59.75 347	59.94 154	64.90 295	71.85 336

PVSNet_0	43.31 20	47.46 334	45.64 337	52.92 344	67.60 332	44.65 273	54.06 362	54.64 357	41.59 344	46.15 363	58.75 373	30.99 308	58.66 352	32.18 346	24.81 388	55.46 376

RRT_MVS		69.42 142	67.49 162	75.21 82	78.01 168	52.56 172	82.23 75	78.15 176	55.84 179	65.65 198	85.07 130	30.86 309	86.83 65	61.56 144	70.00 243	86.24 85

gg-mvs-nofinetune		57.86 281	56.43 287	62.18 294	72.62 266	35.35 350	66.57 298	56.33 353	50.65 257	57.64 296	57.10 376	30.65 310	76.36 274	37.38 319	78.88 128	74.82 307

D2MVS		62.30 251	60.29 260	68.34 236	66.46 340	48.42 234	65.70 304	73.42 248	47.71 293	58.16 293	75.02 305	30.51 311	77.71 252	53.96 196	71.68 220	78.90 264

GG-mvs-BLEND				62.34 293	71.36 290	37.04 338	69.20 288	57.33 349		54.73 322	65.48 364	30.37 312	77.82 249	34.82 336	74.93 175	72.17 333

MDA-MVSNet-bldmvs		53.87 309	50.81 321	63.05 289	66.25 341	48.58 232	56.93 355	63.82 315	48.09 288	41.22 373	70.48 338	30.34 313	68.00 316	34.24 338	45.92 371	72.57 325

EPMVS		53.96 307	53.69 310	54.79 333	66.12 343	31.96 369	62.34 328	49.05 371	44.42 324	55.54 310	71.33 331	30.22 314	56.70 360	41.65 300	62.54 317	75.71 295

YYNet1		50.73 324	48.96 326	56.03 326	61.10 366	41.78 298	51.94 366	56.44 351	40.94 349	44.84 365	67.80 352	30.08 315	55.08 369	36.77 323	50.71 362	71.22 343

MDA-MVSNet_test_wron		50.71 325	48.95 327	56.00 327	61.17 365	41.84 297	51.90 367	56.45 350	40.96 348	44.79 366	67.84 351	30.04 316	55.07 370	36.71 325	50.69 363	71.11 346

test_cas_vis1_n_1920		56.91 287	56.71 284	57.51 321	59.13 372	45.40 267	63.58 321	61.29 334	36.24 361	67.14 169	71.85 327	29.89 317	56.69 361	57.65 166	63.58 308	70.46 349

Anonymous202405211		66.84 198	65.99 197	69.40 221	80.19 113	42.21 295	71.11 269	71.31 264	58.80 123	67.90 150	86.39 100	29.83 318	79.65 219	49.60 233	78.78 131	86.33 78

MSDG		61.81 257	59.23 263	69.55 220	72.64 265	52.63 170	70.45 277	75.81 209	51.38 246	53.70 331	76.11 293	29.52 319	81.08 194	37.70 317	65.79 290	74.93 305

CMPMVS	42.80 21	57.81 282	55.97 290	63.32 285	60.98 367	47.38 247	64.66 317	69.50 279	32.06 366	46.83 360	77.80 272	29.50 320	71.36 297	48.68 239	73.75 185	71.21 344
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LTVRE_ROB	55.42 16	63.15 244	61.23 253	68.92 228	76.57 207	47.80 240	59.92 341	76.39 202	54.35 215	58.67 287	82.46 186	29.44 321	81.49 183	42.12 295	71.14 224	77.46 276
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		53.16 316	52.47 314	55.23 330	59.45 371	33.39 363	59.43 343	69.13 283	45.98 310	50.35 351	72.32 320	29.30 322	58.26 355	42.02 297	44.30 372	74.05 315

iter_conf_final		69.82 126	68.02 149	75.23 81	79.38 128	52.91 163	80.11 99	73.96 243	54.99 203	68.04 149	83.59 161	29.05 323	87.16 55	65.41 108	77.62 145	85.63 109

CHOSEN 280x420		47.83 332	46.36 336	52.24 349	67.37 333	49.78 214	38.91 386	43.11 385	35.00 363	43.27 371	63.30 369	28.95 324	49.19 380	36.53 328	60.80 329	57.76 373

pmmvs-eth3d		58.81 274	56.31 288	66.30 256	67.61 331	52.42 177	72.30 251	64.76 309	43.55 331	54.94 319	74.19 312	28.95 324	72.60 290	43.31 284	57.21 343	73.88 317

dp		51.89 319	51.60 318	52.77 345	68.44 327	32.45 367	62.36 327	54.57 358	44.16 326	49.31 353	67.91 350	28.87 326	56.61 362	33.89 339	54.89 351	69.24 359

FE-MVS		65.91 211	63.33 228	73.63 126	77.36 190	51.95 185	72.62 245	75.81 209	53.70 222	65.31 204	78.96 255	28.81 327	86.39 79	43.93 279	73.48 192	82.55 203

iter_conf05		69.40 144	67.62 155	74.73 87	77.84 172	51.13 190	79.28 114	73.71 246	54.62 208	68.17 144	83.59 161	28.68 328	87.16 55	65.74 105	76.95 158	85.91 94

KD-MVS_self_test		55.22 302	53.89 309	59.21 306	57.80 375	27.47 381	57.75 351	74.32 236	47.38 297	50.90 345	70.00 341	28.45 329	70.30 304	40.44 304	57.92 340	79.87 252

jajsoiax		68.25 167	66.45 183	73.66 123	75.62 220	55.49 125	80.82 91	78.51 165	52.33 235	64.33 225	84.11 149	28.28 330	81.81 178	63.48 125	70.62 229	83.67 177

RPSCF		55.80 298	54.22 307	60.53 302	65.13 347	42.91 290	64.30 318	57.62 346	36.84 360	58.05 294	82.28 190	28.01 331	56.24 365	37.14 321	58.61 338	82.44 208

F-COLMAP		63.05 245	60.87 258	69.58 219	76.99 200	53.63 148	78.12 133	76.16 204	47.97 290	52.41 339	81.61 206	27.87 332	78.11 245	40.07 305	66.66 283	77.00 284

K. test v3		60.47 266	57.11 278	70.56 199	73.74 252	48.22 236	75.10 204	62.55 323	58.27 134	53.62 334	76.31 292	27.81 333	81.59 181	47.42 246	39.18 379	81.88 217

ACMH+	57.40 11	66.12 209	64.06 216	72.30 159	77.79 174	52.83 166	80.39 95	78.03 178	57.30 150	57.47 297	82.55 181	27.68 334	84.17 125	45.54 266	69.78 249	79.90 251

UnsupCasMVSNet_bld		50.07 327	48.87 328	53.66 339	60.97 368	33.67 361	57.62 352	64.56 311	39.47 356	47.38 357	64.02 368	27.47 335	59.32 348	34.69 337	43.68 373	67.98 361

mvs_tets		68.18 169	66.36 189	73.63 126	75.61 221	55.35 128	80.77 92	78.56 163	52.48 234	64.27 227	84.10 150	27.45 336	81.84 177	63.45 126	70.56 231	83.69 176

lessismore_v0				69.91 211	71.42 288	47.80 240		50.90 369		50.39 350	75.56 300	27.43 337	81.33 186	45.91 261	34.10 385	80.59 240

ACMH	55.70 15	65.20 222	63.57 224	70.07 207	78.07 165	52.01 184	79.48 113	79.69 138	55.75 183	56.59 303	80.98 218	27.12 338	80.94 196	42.90 291	71.58 221	77.25 281
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		61.65 258	58.80 267	70.20 205	75.80 217	47.22 248	75.59 192	69.68 276	54.61 209	54.11 328	79.26 252	27.07 339	82.96 149	43.27 285	49.79 366	80.41 243

PVSNet	50.76 19	58.40 276	57.39 277	61.42 298	75.53 223	44.04 279	61.43 331	63.45 317	47.04 303	56.91 300	73.61 315	27.00 340	64.76 329	39.12 311	72.40 209	75.47 298

OpenMVS_ROB	52.78 18	60.03 267	58.14 274	65.69 269	70.47 301	44.82 270	75.33 196	70.86 268	45.04 317	56.06 307	76.00 294	26.89 341	79.65 219	35.36 335	67.29 278	72.60 324

ADS-MVSNet2		51.33 322	48.76 329	59.07 308	66.02 344	44.60 274	50.90 368	59.76 338	36.90 358	50.74 346	66.18 362	26.38 342	63.11 334	27.17 371	54.76 352	69.50 356

ADS-MVSNet		48.48 331	47.77 332	50.63 351	66.02 344	29.92 373	50.90 368	50.87 370	36.90 358	50.74 346	66.18 362	26.38 342	52.47 375	27.17 371	54.76 352	69.50 356

N_pmnet		39.35 347	40.28 345	36.54 371	63.76 352	1.62 406	49.37 371	0.76 405	34.62 364	43.61 370	66.38 361	26.25 344	42.57 387	26.02 376	51.77 359	65.44 363

MVS-HIRNet		45.52 335	44.48 338	48.65 354	68.49 326	34.05 359	59.41 344	44.50 382	27.03 374	37.96 381	50.47 384	26.16 345	64.10 330	26.74 374	59.52 334	47.82 383

test2506		65.33 220	64.61 213	67.50 242	79.46 126	34.19 358	74.43 218	51.92 364	58.72 124	66.75 177	88.05 66	25.99 346	80.92 198	51.94 212	84.25 68	87.39 44

FMVSNet5		55.86 297	54.93 297	58.66 311	71.05 295	36.35 344	64.18 320	62.48 324	46.76 304	50.66 349	74.73 308	25.80 347	64.04 331	33.11 343	65.57 291	75.59 296

new-patchmatchnet		47.56 333	47.73 333	47.06 355	58.81 373	9.37 401	48.78 372	59.21 339	43.28 333	44.22 368	68.66 349	25.67 348	57.20 359	31.57 355	49.35 367	74.62 310

MIMVSNet1		55.17 303	54.31 305	57.77 319	70.03 309	32.01 368	65.68 305	64.81 308	49.19 273	46.75 361	76.00 294	25.53 349	64.04 331	28.65 367	62.13 320	77.26 280

PatchMatch-RL		56.25 294	54.55 301	61.32 300	77.06 197	56.07 109	65.57 306	54.10 361	44.13 327	53.49 337	71.27 332	25.20 350	66.78 321	36.52 329	63.66 306	61.12 366

JIA-IIPM		51.56 320	47.68 334	63.21 287	64.61 349	50.73 198	47.71 374	58.77 341	42.90 337	48.46 355	51.72 380	24.97 351	70.24 305	36.06 332	53.89 355	68.64 360

EU-MVSNet		55.61 299	54.41 303	59.19 307	65.41 346	33.42 362	72.44 249	71.91 261	28.81 369	51.27 342	73.87 313	24.76 352	69.08 309	43.04 288	58.20 339	75.06 301

EG-PatchMatch MVS		64.71 227	62.87 233	70.22 203	77.68 176	53.48 151	77.99 136	78.82 154	53.37 226	56.03 308	77.41 278	24.75 353	84.04 128	46.37 257	73.42 194	73.14 319

TESTMET0.1,1		55.28 301	54.90 298	56.42 324	66.56 338	43.67 282	65.46 309	56.27 354	39.18 357	53.83 330	67.44 354	24.21 354	55.46 368	48.04 244	73.11 200	70.13 352

bld_raw_dy_0_64		64.87 225	63.22 229	69.83 214	74.79 234	53.32 157	78.15 132	62.02 331	51.20 251	60.17 267	83.12 172	24.15 355	74.20 286	63.08 127	72.33 211	81.96 214

mvsany_test1		39.38 346	38.16 349	43.02 363	49.05 382	34.28 357	44.16 382	25.94 398	22.74 382	46.57 362	62.21 371	23.85 356	41.16 390	33.01 344	35.91 382	53.63 377

COLMAP_ROB	52.97 17	61.27 263	58.81 266	68.64 231	74.63 239	52.51 174	78.42 126	73.30 249	49.92 266	50.96 344	81.51 209	23.06 357	79.40 223	31.63 353	65.85 288	74.01 316
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testgi		51.90 318	52.37 315	50.51 352	60.39 370	23.55 392	58.42 345	58.15 342	49.03 275	51.83 341	79.21 253	22.39 358	55.59 367	29.24 366	62.64 315	72.40 331

DSMNet-mixed		39.30 348	38.72 347	41.03 366	51.22 381	19.66 395	45.53 379	31.35 394	15.83 391	39.80 378	67.42 356	22.19 359	45.13 384	22.43 379	52.69 358	58.31 371

test-mter		56.42 292	55.82 292	58.22 314	68.57 324	44.80 271	65.46 309	57.92 344	39.94 355	55.44 312	69.82 342	21.92 360	57.44 357	49.66 231	73.62 187	72.41 329

KD-MVS_2432*1600		53.45 311	51.50 319	59.30 303	62.82 356	37.14 335	55.33 358	71.79 262	47.34 299	55.09 317	70.52 336	21.91 361	70.45 302	35.72 333	42.97 374	70.31 350

miper_refine_blended		53.45 311	51.50 319	59.30 303	62.82 356	37.14 335	55.33 358	71.79 262	47.34 299	55.09 317	70.52 336	21.91 361	70.45 302	35.72 333	42.97 374	70.31 350

myMVS_eth3d		54.86 305	54.61 300	55.61 328	74.69 237	27.31 382	65.52 307	57.49 347	50.97 254	56.52 304	72.18 321	21.87 363	68.09 313	27.70 370	64.59 300	71.44 341

OurMVSNet-221017-0		61.37 262	58.63 269	69.61 216	72.05 278	48.06 238	73.93 227	72.51 255	47.23 301	54.74 321	80.92 220	21.49 364	81.24 189	48.57 241	56.22 348	79.53 257

testing3		56.54 289	55.92 291	58.41 312	77.52 186	27.93 379	69.72 284	56.36 352	54.75 207	58.63 289	77.80 272	20.88 365	71.75 296	25.31 377	62.25 319	75.53 297

ITE_SJBPF				62.09 295	66.16 342	44.55 276		64.32 312	47.36 298	55.31 314	80.34 230	19.27 366	62.68 336	36.29 331	62.39 318	79.04 261

AllTest		57.08 286	54.65 299	64.39 280	71.44 286	49.03 223	69.92 283	67.30 291	45.97 311	47.16 358	79.77 240	17.47 367	67.56 317	33.65 340	59.16 336	76.57 288

TestCases				64.39 280	71.44 286	49.03 223		67.30 291	45.97 311	47.16 358	79.77 240	17.47 367	67.56 317	33.65 340	59.16 336	76.57 288

Anonymous20240521		55.30 300	54.41 303	57.96 317	60.92 369	41.73 299	71.09 270	71.06 267	41.18 346	48.65 354	73.31 316	16.93 369	59.25 349	42.54 292	64.01 303	72.90 321

test_fmvs1		51.32 323	50.48 323	53.81 338	53.57 377	37.51 332	60.63 340	51.16 366	28.02 373	63.62 233	69.23 347	16.41 370	53.93 372	51.01 220	60.70 330	69.99 353

XVG-ACMP-BASELINE		64.36 232	62.23 241	70.74 196	72.35 273	52.45 176	70.80 273	78.45 169	53.84 221	59.87 272	81.10 215	16.24 371	79.32 225	55.64 183	71.76 218	80.47 241

tmp_tt		9.43 365	11.14 368	4.30 381	2.38 403	4.40 404	13.62 393	16.08 402	0.39 398	15.89 393	13.06 395	15.80 372	5.54 400	12.63 391	10.46 397	2.95 395

USDC		56.35 293	54.24 306	62.69 291	64.74 348	40.31 308	65.05 315	73.83 244	43.93 329	47.58 356	77.71 276	15.36 373	75.05 280	38.19 316	61.81 323	72.70 323

test_fmvs1_n		51.37 321	50.35 324	54.42 336	52.85 378	37.71 330	61.16 336	51.93 363	28.15 371	63.81 232	69.73 344	13.72 374	53.95 371	51.16 219	60.65 331	71.59 338

test_vis1_n		49.89 328	48.69 330	53.50 341	53.97 376	37.38 333	61.53 330	47.33 377	28.54 370	59.62 277	67.10 358	13.52 375	52.27 376	49.07 236	57.52 341	70.84 347

EGC-MVSNET		42.47 340	38.48 348	54.46 335	74.33 246	48.73 230	70.33 279	51.10 367	0.03 399	0.18 400	67.78 353	13.28 376	66.49 323	18.91 384	50.36 364	48.15 381

ANet_high		41.38 343	37.47 350	53.11 343	39.73 394	24.45 390	56.94 354	69.69 275	47.65 294	26.04 387	52.32 379	12.44 377	62.38 337	21.80 381	10.61 396	72.49 326

FPMVS		42.18 341	41.11 344	45.39 357	58.03 374	41.01 306	49.50 370	53.81 362	30.07 368	33.71 382	64.03 366	11.69 378	52.08 378	14.01 388	55.11 350	43.09 385

TinyColmap		54.14 306	51.72 317	61.40 299	66.84 336	41.97 296	66.52 299	68.51 287	44.81 318	42.69 372	75.77 298	11.66 379	72.94 289	31.96 347	56.77 346	69.27 358

test_fmvs2		48.69 330	47.49 335	52.29 348	48.63 384	33.06 365	57.76 350	48.05 375	25.71 377	59.76 275	69.60 345	11.57 380	52.23 377	49.45 234	56.86 344	71.58 339

TDRefinement		53.44 313	50.72 322	61.60 297	64.31 351	46.96 250	70.89 272	65.27 307	41.78 341	44.61 367	77.98 265	11.52 381	66.36 324	28.57 368	51.59 360	71.49 340

ambc				65.13 275	63.72 354	37.07 337	47.66 375	78.78 157		54.37 327	71.42 329	11.24 382	80.94 196	45.64 264	53.85 356	77.38 277

test_vis1_rt		41.35 344	39.45 346	47.03 356	46.65 387	37.86 327	47.76 373	38.65 388	23.10 380	44.21 369	51.22 382	11.20 383	44.08 385	39.27 310	53.02 357	59.14 369

pmmvs3		44.92 336	41.95 343	53.86 337	52.58 380	43.55 283	62.11 329	46.90 379	26.05 376	40.63 374	60.19 372	11.08 384	57.91 356	31.83 352	46.15 370	60.11 367

new_pmnet		34.13 352	34.29 353	33.64 373	52.63 379	18.23 397	44.43 381	33.90 393	22.81 381	30.89 384	53.18 378	10.48 385	35.72 394	20.77 382	39.51 378	46.98 384

LF4IMVS		42.95 339	42.26 341	45.04 358	48.30 385	32.50 366	54.80 360	48.49 373	28.03 372	40.51 375	70.16 339	9.24 386	43.89 386	31.63 353	49.18 368	58.72 370

PM-MVS		52.33 317	50.19 325	58.75 310	62.10 361	45.14 269	65.75 303	40.38 387	43.60 330	53.52 335	72.65 318	9.16 387	65.87 327	50.41 224	54.18 354	65.24 364

EMVS		22.97 360	21.84 364	26.36 377	40.20 393	19.53 396	41.95 384	34.64 392	17.09 388	9.73 398	22.83 394	7.29 388	42.22 389	9.18 397	13.66 394	17.32 393

E-PMN		23.77 359	22.73 363	26.90 376	42.02 390	20.67 394	42.66 383	35.70 391	17.43 387	10.28 397	25.05 393	6.42 389	42.39 388	10.28 395	14.71 393	17.63 392

test_method		19.68 362	18.10 365	24.41 378	13.68 402	3.11 405	12.06 394	42.37 386	2.00 397	11.97 395	36.38 389	5.77 390	29.35 397	15.06 386	23.65 389	40.76 388

mvsany_test3		32.62 353	30.57 357	38.77 369	36.16 397	24.20 391	38.10 387	20.63 400	19.14 386	40.36 377	57.43 375	5.06 391	36.63 393	29.59 365	28.66 386	55.49 375

test_f		31.86 355	31.05 356	34.28 372	32.33 400	21.86 393	32.34 388	30.46 395	16.02 390	39.78 379	55.45 377	4.80 392	32.36 395	30.61 359	37.66 381	48.64 379

Gipuma		34.77 351	31.91 355	43.33 362	62.05 362	37.87 326	20.39 391	67.03 295	23.23 379	18.41 392	25.84 392	4.24 393	62.73 335	14.71 387	51.32 361	29.38 391
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvs3		44.30 337	42.55 340	49.55 353	42.83 388	27.15 384	53.03 364	44.93 381	22.03 384	53.69 333	64.94 365	4.21 394	49.63 379	47.47 245	49.82 365	71.88 335

PMMVS2		27.40 358	25.91 361	31.87 375	39.46 395	6.57 403	31.17 389	28.52 396	23.96 378	20.45 391	48.94 387	4.20 395	37.94 391	16.51 385	19.97 391	51.09 378

LCM-MVSNet		40.30 345	35.88 351	53.57 340	42.24 389	29.15 375	45.21 380	60.53 337	22.23 383	28.02 385	50.98 383	3.72 396	61.78 339	31.22 358	38.76 380	69.78 355

DeepMVS_CX				12.03 380	17.97 401	10.91 399		10.60 403	7.46 395	11.07 396	28.36 391	3.28 397	11.29 399	8.01 398	9.74 398	13.89 394

APD_test1		37.39 349	34.94 352	44.72 361	48.88 383	33.19 364	52.95 365	44.00 384	19.49 385	27.28 386	58.59 374	3.18 398	52.84 374	18.92 383	41.17 377	48.14 382

PMVS	28.69 22	36.22 350	33.29 354	45.02 359	36.82 396	35.98 349	54.68 361	48.74 372	26.31 375	21.02 390	51.61 381	2.88 399	60.10 345	9.99 396	47.58 369	38.99 390
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		32.09 354	30.20 358	37.76 370	35.36 398	27.48 380	40.60 385	28.29 397	16.69 389	32.52 383	40.53 388	1.96 400	37.40 392	33.64 342	42.21 376	48.39 380

MVE	17.77 23	21.41 361	17.77 366	32.34 374	34.34 399	25.44 388	16.11 392	24.11 399	11.19 394	13.22 394	31.92 390	1.58 401	30.95 396	10.47 394	17.03 392	40.62 389
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		31.46 356	28.89 359	39.16 367	41.99 391	28.78 376	46.45 376	37.56 389	14.28 392	21.10 388	48.96 385	1.48 402	47.11 381	13.63 389	34.56 383	41.60 386

APD_test2		31.46 356	28.89 359	39.16 367	41.99 391	28.78 376	46.45 376	37.56 389	14.28 392	21.10 388	48.96 385	1.48 402	47.11 381	13.63 389	34.56 383	41.60 386

wuyk23d		13.32 364	12.52 367	15.71 379	47.54 386	26.27 386	31.06 390	1.98 404	4.93 396	5.18 399	1.94 399	0.45 404	18.54 398	6.81 399	12.83 395	2.33 396

test123		4.73 367	6.30 370	0.02 382	0.01 404	0.01 407	56.36 356	0.00 406	0.01 400	0.04 401	0.21 401	0.01 405	0.00 401	0.03 401	0.00 399	0.04 397

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

testmvs		4.52 368	6.03 371	0.01 383	0.01 404	0.00 408	53.86 363	0.00 406	0.01 400	0.04 401	0.27 400	0.00 406	0.00 401	0.04 400	0.00 399	0.03 398

ab-mvs-re		6.49 366	8.65 369	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	77.89 270	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 408	0.00 395	0.00 406	0.00 402	0.00 403	0.00 402	0.00 406	0.00 401	0.00 402	0.00 399	0.00 399

WAC-MVS						27.31 382								27.77 369

FOURS1					86.12 36	60.82 37	88.18 1	83.61 63	60.87 84	81.50 16

MSC_two_6792asdad				79.95 4	87.24 14	61.04 31		85.62 23					90.96 1	79.31 9	90.65 8	87.85 27

No_MVS				79.95 4	87.24 14	61.04 31		85.62 23					90.96 1	79.31 9	90.65 8	87.85 27

eth-test2					0.00 406

eth-test					0.00 406

IU-MVS					87.77 4	59.15 60		85.53 25	53.93 220	84.64 3				79.07 11	90.87 5	88.37 13

save fliter					86.17 33	61.30 28	83.98 47	79.66 140	59.00 120

test_0728_SECOND				79.19 16	87.82 3	59.11 63	87.85 5	87.15 3					90.84 3	78.66 15	90.61 11	87.62 37

GSMVS																78.05 270

test_part2					87.58 9	60.47 42				83.42 12

MTGPA								80.97 123

MTMP							86.03 19	17.08 401

gm-plane-assit					71.40 289	41.72 301			48.85 278		73.31 316		82.48 168	48.90 238

test9_res														75.28 37	88.31 32	83.81 169

agg_prior2														73.09 55	87.93 40	84.33 150

agg_prior					85.04 50	59.96 47		81.04 121		74.68 50			84.04 128

test_prior4						62.51 14	82.08 77

test_prior				76.69 53	84.20 61	57.27 88		84.88 37					86.43 78			86.38 72

旧先验2							76.08 182		45.32 316	76.55 32			65.56 328	58.75 162

新几何2							76.12 180

无先验							79.66 110	74.30 238	48.40 284				80.78 202	53.62 198		79.03 262

原ACMM2							79.02 116

testdata2													72.18 295	46.95 254

testdata1							72.65 243		60.50 91

plane_prior7					81.41 89	55.96 111

plane_prior5								84.01 49					87.21 53	68.16 81	80.58 103	84.65 144

plane_prior4											86.10 108

plane_prior3						56.09 108			63.92 36	69.27 127

plane_prior2							84.22 40		64.52 25

plane_prior1					81.27 94

plane_prior						56.31 102	83.58 53		63.19 48						80.48 106

n2								0.00 406

nn								0.00 406

door-mid								47.19 378

test11								83.47 67

door								47.60 376

HQP5-MVS						54.94 131

HQP-NCC					80.66 102		82.31 71		62.10 68	67.85 152

ACMP_Plane					80.66 102		82.31 71		62.10 68	67.85 152

BP-MVS														67.04 93

HQP4-MVS										67.85 152			86.93 62			84.32 151

HQP3-MVS								83.90 54							80.35 107

NP-MVS					80.98 99	56.05 110					85.54 126

ACMMP++_ref															74.07 181

ACMMP++															72.16 215

High-resolution multi-view benchmark