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 69	88.18 1	87.15 3	65.04 17	84.26 5	91.86 6	67.01 1	90.84 3	79.48 7	91.38 2	88.42 32

OPU-MVS				79.83 7	87.54 11	60.93 35	87.82 7				89.89 51	67.01 1	90.33 12	73.16 72	91.15 4	88.23 40

SED-MVS		81.56 2	82.30 2	79.32 13	87.77 4	58.90 79	87.82 7	86.78 10	64.18 35	85.97 1	91.84 8	66.87 3	90.83 5	78.63 20	90.87 5	88.23 40

test_241102_ONE					87.77 4	58.90 79		86.78 10	64.20 34	85.97 1	91.34 18	66.87 3	90.78 7

PC_three_1452									55.09 259	84.46 4	89.84 52	66.68 5	89.41 24	74.24 62	91.38 2	88.42 32

test_241102_TWO								86.73 12	64.18 35	84.26 5	91.84 8	65.19 6	90.83 5	78.63 20	90.70 7	87.65 64

DPE-MVS		80.56 5	80.98 5	79.29 15	87.27 13	60.56 41	85.71 31	86.42 16	63.28 52	83.27 15	91.83 10	64.96 7	90.47 11	76.41 41	89.67 20	86.84 99
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 38	87.75 7	59.07 74	87.85 5	85.03 43	64.26 32	83.82 8	92.00 3	64.82 8	90.75 8	78.66 18	90.61 11	85.45 169
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 74	87.86 4	86.83 8	64.26 32	84.19 7	91.92 5	64.82 8

MED-MVS		80.42 6	80.87 6	79.07 25	85.30 51	59.25 64	86.84 11	85.86 24	63.31 49	83.65 12	91.48 12	64.70 10	89.91 16	77.02 35	89.69 18	88.06 50

test_0728_THIRD									65.04 17	83.82 8	92.00 3	64.69 11	90.75 8	79.48 7	90.63 10	88.09 47

test_one_0601					87.58 9	59.30 62		86.84 7	65.01 21	83.80 11	91.86 6	64.03 12

MSP-MVS		81.06 3	81.40 4	80.02 1	86.21 33	62.73 9	86.09 22	86.83 8	65.51 13	83.81 10	90.51 30	63.71 13	89.23 26	81.51 2	88.44 31	88.09 47
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
test-260524					86.59 25	59.16 67		86.47 15		82.32 18		62.54 14	89.91 16	77.25 30	89.69 18

dcpmvs_2		74.55 72	75.23 59	72.48 199	82.34 89	53.34 178	77.87 166	81.46 138	57.80 192	75.49 55	86.81 120	62.22 15	77.75 322	71.09 93	82.02 109	86.34 123

TestfortrainingZip				78.05 44	84.66 63	58.22 88	86.84 11	85.98 23	63.31 49	79.39 25	88.94 65	62.01 16	89.61 22		86.45 64	86.34 123

ME-MVS		80.04 10	80.36 9	79.08 24	86.63 23	59.25 64	85.62 32	86.73 12	63.10 58	82.27 19	90.57 27	61.90 17	89.88 19	77.02 35	89.43 24	88.10 45

DeepPCF-MVS	69.58 1	79.03 15	79.00 16	79.13 19	84.92 61	60.32 46	83.03 68	85.33 35	62.86 64	80.17 22	90.03 47	61.76 18	88.95 30	74.21 63	88.67 30	88.12 44

TestfortrainingZip a		79.61 13	79.84 13	78.92 30	85.30 51	59.08 73	86.84 11	86.01 21	63.31 49	82.37 17	91.48 12	60.88 19	89.61 22	76.25 44	86.13 66	88.06 50

CSCG		76.92 37	76.75 35	77.41 56	83.96 70	59.60 56	82.95 69	86.50 14	60.78 112	75.27 58	84.83 184	60.76 20	86.56 84	67.86 120	87.87 45	86.06 137

TSAR-MVS + MP.		78.44 22	78.28 22	78.90 31	84.96 57	61.41 26	84.03 56	83.82 76	59.34 156	79.37 26	89.76 54	59.84 21	87.62 58	76.69 38	86.74 59	87.68 63
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 68	74.98 63	73.71 158	78.94 158	50.56 246	80.23 108	83.87 69	60.30 129	77.15 43	86.56 135	59.65 22	82.00 212	66.01 147	82.12 106	88.58 29

canonicalmvs		74.67 68	74.98 63	73.71 158	78.94 158	50.56 246	80.23 108	83.87 69	60.30 129	77.15 43	86.56 135	59.65 22	82.00 212	66.01 147	82.12 106	88.58 29

APDe-MVS		80.16 9	80.59 7	78.86 33	86.64 21	60.02 48	88.12 3	86.42 16	62.94 61	82.40 16	92.12 2	59.64 24	89.76 20	78.70 15	88.32 35	86.79 101
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DELS-MVS		74.76 66	74.46 69	75.65 90	77.84 201	52.25 209	75.59 238	84.17 57	63.76 41	73.15 111	82.79 236	59.58 25	86.80 76	67.24 131	86.04 67	87.89 52
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 12	79.97 12	79.45 11	87.90 2	62.17 17	84.37 45	85.03 43	66.96 5	77.58 40	90.06 45	59.47 26	89.13 28	78.67 17	89.73 16	87.03 92

casdiffmvs_mvg		76.14 51	76.30 44	75.66 89	76.46 259	51.83 220	79.67 122	85.08 40	65.02 20	75.84 51	88.58 75	59.42 27	85.08 128	72.75 75	83.93 84	90.08 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Casviewmamba		76.62 42	76.52 42	76.90 62	77.91 198	53.66 166	80.76 103	84.47 50	66.73 8	75.75 54	88.63 74	59.17 28	86.66 80	72.28 80	83.01 92	90.39 1

MCST-MVS		77.48 32	77.45 31	77.54 53	86.67 20	58.36 86	83.22 66	86.93 5	56.91 210	74.91 68	88.19 77	59.15 29	87.68 57	73.67 69	87.45 49	86.57 112

hybridcas		74.86 64	75.07 61	74.24 129	76.30 260	50.58 243	79.30 128	83.88 68	63.15 57	74.69 75	88.13 79	58.91 30	82.98 178	68.30 107	82.93 97	89.15 11

nrg030		72.96 106	73.01 100	72.84 188	75.41 279	50.24 255	80.02 113	82.89 117	58.36 177	74.44 79	86.73 125	58.90 31	80.83 245	65.84 150	74.46 247	87.44 73

HPM-MVS++		79.88 11	80.14 11	79.10 21	88.17 1	64.80 1	86.59 16	83.70 81	65.37 14	78.78 30	90.64 24	58.63 32	87.24 61	79.00 14	90.37 14	85.26 181

SF-MVS		78.82 16	79.22 15	77.60 52	82.88 84	57.83 92	84.99 37	88.13 2	61.86 90	79.16 27	90.75 23	57.96 33	87.09 70	77.08 34	90.18 15	87.87 54

casdiffmvs		74.80 65	74.89 65	74.53 119	75.59 274	50.37 252	78.17 157	85.06 42	62.80 68	74.40 80	87.86 88	57.88 34	83.61 161	69.46 102	82.79 102	89.59 5
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		72.45 118	73.34 95	69.81 278	77.77 203	43.21 364	75.84 235	81.18 153	59.59 151	75.45 56	86.64 128	57.74 35	77.94 314	63.92 167	81.90 111	88.30 36

DeepC-MVS	69.38 2	78.56 20	78.14 25	79.83 7	83.60 72	61.62 23	84.17 53	86.85 6	63.23 54	73.84 95	90.25 40	57.68 36	89.96 15	74.62 61	89.03 26	87.89 52
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 70	74.70 66	74.34 124	75.70 269	49.99 263	77.54 178	84.63 49	62.73 69	73.98 87	87.79 91	57.67 37	83.82 157	69.49 100	82.74 103	89.20 10

patch_mono-2		69.85 178	71.09 136	66.16 341	79.11 155	54.80 149	71.97 323	74.31 310	53.50 299	70.90 154	84.17 206	57.63 38	63.31 438	66.17 144	82.02 109	80.38 325

9.14			78.75 18		83.10 79		84.15 54	88.26 1	59.90 140	78.57 32	90.36 35	57.51 39	86.86 75	77.39 29	89.52 23

MM		80.20 8	80.28 10	79.99 2	82.19 91	60.01 49	86.19 21	83.93 62	73.19 1	77.08 46	91.21 20	57.23 40	90.73 10	83.35 1	88.12 38	89.22 9

fmvsm_s_conf0.5_n_9		75.16 61	75.22 60	75.01 102	78.34 181	55.37 140	77.30 188	73.95 319	61.40 97	79.46 24	90.14 41	57.07 41	81.15 232	80.00 5	79.31 155	88.51 31

MVSMamba_PlusPlus		75.75 57	75.44 55	76.67 69	80.84 114	53.06 186	78.62 140	85.13 39	59.65 146	71.53 145	87.47 95	56.92 42	88.17 41	72.18 82	86.63 62	88.80 16

DPM-MVS		75.47 59	75.00 62	76.88 63	81.38 105	59.16 67	79.94 115	85.71 29	56.59 221	72.46 130	86.76 121	56.89 43	87.86 51	66.36 143	88.91 29	83.64 244

UniMVSNet_NR-MVSNet		71.11 145	71.00 138	71.44 232	79.20 150	44.13 350	76.02 230	82.60 120	66.48 12	68.20 201	84.60 197	56.82 44	82.82 194	54.62 261	70.43 315	87.36 81

SMA-MVS		80.28 7	80.39 8	79.95 4	86.60 24	61.95 19	86.33 17	85.75 28	62.49 72	82.20 20	92.28 1	56.53 45	89.70 21	79.85 6	91.48 1	88.19 42
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
BridgeMVS		76.58 43	76.55 41	76.68 68	81.73 97	52.90 189	80.94 99	85.70 30	61.12 105	74.90 69	87.17 112	56.46 46	88.14 42	72.87 74	88.03 42	89.00 12

Effi-MVS+		73.31 97	72.54 109	75.62 91	77.87 199	53.64 167	79.62 124	79.61 182	61.63 95	72.02 137	82.61 241	56.44 47	85.97 107	63.99 166	79.07 166	87.25 85

alignmvs		73.86 85	73.99 79	73.45 172	78.20 185	50.50 248	78.57 142	82.43 122	59.40 154	76.57 48	86.71 127	56.42 48	81.23 231	65.84 150	81.79 112	88.62 26

viewdifsd2359ckpt07		71.90 131	71.97 117	71.69 222	74.81 294	48.08 306	75.30 243	80.49 168	60.00 137	71.63 142	86.33 144	56.34 49	79.25 278	65.40 154	77.41 201	87.76 60

test_prior2							81.75 89		60.37 125	75.01 64	89.06 61	56.22 50		72.19 81	88.96 28

fmvsm_l_conf0.5_n_9		73.27 98	73.66 87	72.09 208	73.82 320	52.72 197	77.45 182	74.28 312	56.61 220	77.10 45	88.16 78	56.17 51	77.09 338	78.27 24	81.13 120	86.48 116

E2		73.72 88	73.60 88	74.06 140	77.16 228	50.40 250	76.97 200	83.74 78	61.64 93	73.36 102	86.75 124	56.14 52	82.99 175	67.50 128	79.18 163	88.80 16

E3		73.72 88	73.60 88	74.06 140	77.16 228	50.40 250	76.97 200	83.74 78	61.64 93	73.36 102	86.76 121	56.13 53	82.99 175	67.50 128	79.18 163	88.80 16

ZD-MVS					86.64 21	60.38 45		82.70 119	57.95 187	78.10 35	90.06 45	56.12 54	88.84 32	74.05 65	87.00 55

viewcassd2359sk11		73.56 90	73.41 93	74.00 144	77.13 234	50.35 253	76.86 207	83.69 82	61.23 102	73.14 112	86.38 142	56.09 55	82.96 179	67.15 132	79.01 168	88.70 25

E4		73.91 84	73.83 84	74.15 135	77.13 234	50.47 249	77.15 195	83.79 77	62.21 81	73.61 97	87.19 111	56.08 56	83.03 173	67.91 119	79.35 153	88.94 14

E3new		73.41 94	73.22 96	73.95 147	77.06 239	50.31 254	76.78 210	83.66 83	60.90 108	72.93 120	86.02 155	55.99 57	82.95 181	66.89 140	78.77 173	88.61 27

E6new		74.10 78	74.09 75	74.15 135	77.14 230	50.74 236	78.24 149	83.85 74	62.34 76	73.95 89	87.27 104	55.98 58	82.95 181	68.17 111	79.85 141	88.77 19

E6		74.10 78	74.09 75	74.15 135	77.14 230	50.74 236	78.24 149	83.85 74	62.34 76	73.95 89	87.27 104	55.98 58	82.95 181	68.17 111	79.85 141	88.77 19

E5new		74.10 78	74.09 75	74.15 135	77.14 230	50.74 236	78.24 149	83.86 72	62.34 76	73.95 89	87.27 104	55.97 60	82.95 181	68.16 113	79.86 139	88.77 19

E5		74.10 78	74.09 75	74.15 135	77.14 230	50.74 236	78.24 149	83.86 72	62.34 76	73.95 89	87.27 104	55.97 60	82.95 181	68.16 113	79.86 139	88.77 19

TSAR-MVS + GP.		74.90 63	74.15 74	77.17 60	82.00 93	58.77 82	81.80 88	78.57 210	58.58 172	74.32 82	84.51 200	55.94 62	87.22 64	67.11 133	84.48 79	85.52 163

fmvsm_s_conf0.5_n_3		73.55 91	74.39 70	71.03 251	74.09 319	51.86 219	77.77 172	75.60 283	61.18 103	78.67 31	88.98 63	55.88 63	77.73 323	78.69 16	78.68 176	83.50 247

MVS_Test		72.45 118	72.46 110	72.42 203	74.88 290	48.50 297	76.28 220	83.14 109	59.40 154	72.46 130	84.68 189	55.66 64	81.12 233	65.98 149	79.66 146	87.63 65

APD-MVS		78.02 26	78.04 26	77.98 46	86.44 29	60.81 38	85.52 33	84.36 54	60.61 116	79.05 28	90.30 38	55.54 65	88.32 38	73.48 71	87.03 52	84.83 196
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		78.58 19	78.31 21	79.39 12	87.51 12	62.61 13	85.20 36	84.42 53	66.73 8	74.67 77	89.38 58	55.30 66	89.18 27	74.19 64	87.34 50	86.38 119

FIs		70.82 155	71.43 126	68.98 293	78.33 182	38.14 421	76.96 202	83.59 86	61.02 106	67.33 230	86.73 125	55.07 67	81.64 218	54.61 263	79.22 159	87.14 90

CS-MVS		76.25 50	75.98 48	77.06 61	80.15 130	55.63 132	84.51 44	83.90 65	63.24 53	73.30 105	87.27 104	55.06 68	86.30 96	71.78 87	84.58 74	89.25 8

fmvsm_l_conf0.5_n_3		73.23 99	73.13 99	73.55 168	74.40 308	55.13 143	78.97 132	74.96 302	56.64 214	74.76 74	88.75 72	55.02 69	78.77 302	76.33 42	78.31 187	86.74 104

SD-MVS		77.70 30	77.62 30	77.93 47	84.47 65	61.88 21	84.55 43	83.87 69	60.37 125	79.89 23	89.38 58	54.97 70	85.58 116	76.12 46	84.94 72	86.33 126
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 45	75.93 49	78.06 43	81.29 106	57.53 97	82.35 80	83.31 98	67.78 3	70.09 165	86.34 143	54.92 71	88.90 31	72.68 76	84.55 75	87.76 60

MP-MVS		78.35 23	78.26 24	78.64 35	86.54 27	63.47 4	86.02 24	83.55 87	63.89 40	73.60 98	90.60 25	54.85 72	86.72 78	77.20 32	88.06 40	85.74 155
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test_fmvsmconf_n		73.01 104	72.59 107	74.27 127	71.28 374	55.88 126	78.21 156	75.56 285	54.31 283	74.86 70	87.80 90	54.72 73	80.23 261	78.07 26	78.48 182	86.70 105

mvs_anonymous		68.03 234	67.51 221	69.59 281	72.08 355	44.57 347	71.99 322	75.23 294	51.67 326	67.06 237	82.57 246	54.68 74	77.94 314	56.56 243	75.71 233	86.26 133

test12				77.76 51	84.52 64	58.41 85		83.36 94		72.93 120		54.61 75	88.05 45		88.12 38	86.81 100

FC-MVSNet-test		69.80 181	70.58 148	67.46 316	77.61 215	34.73 455	76.05 228	83.19 107	60.84 110	65.88 264	86.46 139	54.52 76	80.76 248	52.52 278	78.12 189	86.91 95

SteuartSystems-ACMMP		79.48 14	79.31 14	79.98 3	83.01 82	62.18 16	87.60 9	85.83 26	66.69 10	78.03 37	90.98 21	54.26 77	90.06 14	78.42 23	89.02 27	87.69 62
Skip Steuart: Steuart Systems R&D Blog.
segment_acmp												54.23 78

MVS_111021_HR		74.02 82	73.46 91	75.69 88	83.01 82	60.63 40	77.29 189	78.40 221	61.18 103	70.58 158	85.97 157	54.18 79	84.00 154	67.52 127	82.98 96	82.45 277

viewmanbaseed2359cas		72.92 107	72.89 102	73.00 183	75.16 285	49.25 282	77.25 192	83.11 111	59.52 153	72.93 120	86.63 130	54.11 80	80.98 238	66.63 141	80.67 125	88.76 24

fmvsm_s_conf0.5_n_11		73.16 100	73.35 94	72.58 193	75.48 276	52.41 208	78.84 134	76.85 255	58.64 170	73.58 99	87.25 109	54.09 81	79.47 273	76.19 45	79.27 156	85.86 145

MGCNet		78.45 21	78.28 22	78.98 29	80.73 116	57.91 91	84.68 41	81.64 134	68.35 2	75.77 52	90.38 34	53.98 82	90.26 13	81.30 3	87.68 46	88.77 19

Fast-Effi-MVS+		70.28 167	69.12 178	73.73 157	78.50 172	51.50 223	75.01 252	79.46 186	56.16 232	68.59 193	79.55 317	53.97 83	84.05 150	53.34 273	77.53 198	85.65 160

ZNCC-MVS		78.82 16	78.67 19	79.30 14	86.43 30	62.05 18	86.62 15	86.01 21	63.32 48	75.08 63	90.47 33	53.96 84	88.68 33	76.48 40	89.63 22	87.16 89

UniMVSNet (Re)		70.63 158	70.20 155	71.89 212	78.55 171	45.29 338	75.94 231	82.92 114	63.68 43	68.16 204	83.59 222	53.89 85	83.49 165	53.97 267	71.12 306	86.89 96

SPE-MVS-test		75.62 58	75.31 58	76.56 73	80.63 120	55.13 143	83.88 59	85.22 36	62.05 86	71.49 146	86.03 154	53.83 86	86.36 94	67.74 122	86.91 56	88.19 42

viewmacassd2359aftdt		73.15 101	73.16 98	73.11 181	75.15 287	49.31 279	77.53 180	83.21 103	60.42 121	73.20 109	87.34 101	53.82 87	81.05 237	67.02 137	80.79 121	88.96 13

test_fmvsmconf0.1_n		72.81 108	72.33 112	74.24 129	69.89 400	55.81 127	78.22 155	75.40 290	54.17 285	75.00 65	88.03 86	53.82 87	80.23 261	78.08 25	78.34 186	86.69 106

fmvsm_l_conf0.5_n		70.99 150	70.82 141	71.48 228	71.45 367	54.40 152	77.18 194	70.46 356	48.67 374	75.17 60	86.86 118	53.77 89	76.86 346	76.33 42	77.51 199	83.17 259

DeepC-MVS_fast	68.24 3	77.25 34	76.63 37	79.12 20	86.15 36	60.86 36	84.71 40	84.85 47	61.98 89	73.06 117	88.88 67	53.72 90	89.06 29	68.27 108	88.04 41	87.42 74
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 45	61.59 24	81.62 91	81.26 149	55.65 243	74.93 66	88.81 68	53.70 91	84.68 140

train_agg		76.27 48	76.15 45	76.64 71	85.58 45	61.59 24	81.62 91	81.26 149	55.86 235	74.93 66	88.81 68	53.70 91	84.68 140	75.24 56	88.33 34	83.65 243

test_8					85.40 48	60.96 34	81.54 94	81.18 153	55.86 235	74.81 71	88.80 70	53.70 91	84.45 144

ETV-MVS		74.46 73	73.84 83	76.33 76	79.27 148	55.24 142	79.22 129	85.00 45	64.97 22	72.65 127	79.46 319	53.65 94	87.87 50	67.45 130	82.91 98	85.89 143

fmvsm_s_conf0.5_n_5		72.69 112	72.80 104	72.37 204	74.11 318	53.21 182	78.12 158	73.31 326	53.98 288	76.81 47	88.05 83	53.38 95	77.37 333	76.64 39	80.78 122	86.53 114

CDPH-MVS		76.31 47	75.67 54	78.22 41	85.35 50	59.14 71	81.31 96	84.02 59	56.32 227	74.05 86	88.98 63	53.34 96	87.92 49	69.23 103	88.42 32	87.59 68

casdiffseed414692147		73.73 87	73.22 96	75.28 99	76.76 250	52.16 211	80.05 112	83.01 112	63.38 47	73.35 104	87.11 113	53.22 97	84.14 148	61.71 197	80.38 132	89.55 6

viewdifsd2359ckpt09		73.42 93	72.45 111	76.30 77	77.25 226	53.27 180	80.36 107	82.48 121	57.96 186	72.24 133	85.73 167	53.22 97	86.27 97	63.79 173	79.06 167	89.36 7

HFP-MVS		78.01 27	77.65 29	79.10 21	86.71 19	62.81 8	86.29 18	84.32 55	62.82 65	73.96 88	90.50 31	53.20 99	88.35 37	74.02 66	87.05 51	86.13 135

EC-MVSNet		75.84 55	75.87 51	75.74 87	78.86 160	52.65 198	83.73 61	86.08 20	63.47 46	72.77 125	87.25 109	53.13 100	87.93 48	71.97 85	85.57 70	86.66 109

viewdifsd2359ckpt13		72.40 121	71.79 120	74.22 131	75.63 271	51.77 221	78.67 138	83.13 110	57.08 203	71.59 143	85.36 178	53.10 101	82.64 199	63.07 183	78.51 181	88.24 39

test_fmvsm_n_1920		71.73 135	71.14 135	73.50 169	72.52 345	56.53 113	75.60 237	76.16 270	48.11 385	77.22 42	85.56 170	53.10 101	77.43 330	74.86 58	77.14 208	86.55 113

fmvsm_l_conf0.5_n_a		70.50 161	70.27 154	71.18 244	71.30 373	54.09 157	76.89 205	69.87 360	47.90 389	74.37 81	86.49 138	53.07 103	76.69 352	75.41 53	77.11 209	82.76 266

fmvsm_s_conf0.5_n_10		74.11 77	73.98 80	74.48 121	74.61 301	52.86 193	78.10 161	77.06 250	57.14 202	78.24 33	88.79 71	52.83 104	82.26 208	77.79 28	81.30 118	88.32 35

fmvsm_s_conf0.5_n_8		74.30 75	74.39 70	74.01 143	75.33 281	52.89 191	78.24 149	77.32 245	61.65 92	78.13 34	88.90 66	52.82 105	81.54 222	78.46 22	78.67 177	87.60 67

EI-MVSNet-Vis-set		72.42 120	71.59 122	74.91 103	78.47 174	54.02 158	77.05 198	79.33 188	65.03 19	71.68 141	79.35 322	52.75 106	84.89 135	66.46 142	74.23 251	85.83 148

fmvsm_s_conf0.5_n_a		69.54 191	68.74 188	71.93 211	72.47 347	53.82 162	78.25 148	62.26 433	49.78 359	73.12 115	86.21 147	52.66 107	76.79 348	75.02 57	68.88 349	85.18 182

GST-MVS		78.14 25	77.85 27	78.99 28	86.05 40	61.82 22	85.84 26	85.21 37	63.56 44	74.29 83	90.03 47	52.56 108	88.53 35	74.79 60	88.34 33	86.63 111

ACMMP_NAP		78.77 18	78.78 17	78.74 34	85.44 47	61.04 31	83.84 60	85.16 38	62.88 63	78.10 35	91.26 19	52.51 109	88.39 36	79.34 9	90.52 13	86.78 102

PCF-MVS	61.88 8	70.95 151	69.49 168	75.35 95	77.63 210	55.71 129	76.04 229	81.81 131	50.30 352	69.66 176	85.40 177	52.51 109	84.89 135	51.82 286	80.24 135	85.45 169
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MP-MVS-pluss		78.35 23	78.46 20	78.03 45	84.96 57	59.52 58	82.93 70	85.39 34	62.15 82	76.41 50	91.51 11	52.47 111	86.78 77	80.66 4	89.64 21	87.80 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CLD-MVS		73.33 96	72.68 106	75.29 98	78.82 162	53.33 179	78.23 154	84.79 48	61.30 100	70.41 162	81.04 285	52.41 112	87.12 68	64.61 162	82.49 105	85.41 173
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		71.01 148	70.15 158	73.60 166	79.57 140	52.17 210	78.93 133	78.12 226	58.02 183	67.76 225	83.87 214	52.36 113	82.72 196	56.90 239	75.79 231	85.92 141

NR-MVSNet		69.54 191	68.85 184	71.59 226	78.05 193	43.81 355	74.20 272	80.86 162	65.18 15	62.76 318	84.52 198	52.35 114	83.59 162	50.96 294	70.78 310	87.37 79

viewmamba		71.13 144	70.66 145	72.56 195	70.23 391	50.07 260	74.25 271	77.85 230	59.92 139	70.94 152	85.55 172	52.30 115	80.25 259	68.42 106	76.47 219	87.35 82

fmvsm_s_conf0.5_n		69.58 189	68.84 185	71.79 217	72.31 353	52.90 189	77.90 164	62.43 431	49.97 357	72.85 123	85.90 160	52.21 116	76.49 355	75.75 48	70.26 322	85.97 139

EI-MVSNet-UG-set		71.92 130	71.06 137	74.52 120	77.98 196	53.56 170	76.62 212	79.16 189	64.40 30	71.18 149	78.95 327	52.19 117	84.66 142	65.47 153	73.57 264	85.32 177

miper_ehance_all_eth		68.03 234	67.24 234	70.40 266	70.54 383	46.21 327	73.98 276	78.68 204	55.07 262	66.05 258	77.80 351	52.16 118	81.31 228	61.53 202	69.32 341	83.67 240

fmvsm_s_conf0.5_n_4		72.04 129	71.85 118	72.58 193	73.74 323	52.49 204	76.69 211	72.42 337	56.42 225	75.32 57	87.04 114	52.13 119	78.01 313	79.29 12	73.65 261	87.26 84

EIA-MVS		71.78 133	70.60 146	75.30 97	79.85 134	53.54 171	77.27 191	83.26 102	57.92 188	66.49 248	79.39 320	52.07 120	86.69 79	60.05 210	79.14 165	85.66 159

fmvsm_s_conf0.1_n_a		69.32 199	68.44 197	71.96 209	70.91 378	53.78 163	78.12 158	62.30 432	49.35 365	73.20 109	86.55 137	51.99 121	76.79 348	74.83 59	68.68 354	85.32 177

c3_l		68.33 226	67.56 217	70.62 262	70.87 379	46.21 327	74.47 266	78.80 200	56.22 231	66.19 254	78.53 335	51.88 122	81.40 225	62.08 191	69.04 347	84.25 214

PAPM_NR		72.63 114	71.80 119	75.13 100	81.72 98	53.42 177	79.91 117	83.28 101	59.14 158	66.31 253	85.90 160	51.86 123	86.06 103	57.45 236	80.62 126	85.91 142

diffmvs_AUTHOR		71.02 147	70.87 140	71.45 231	69.89 400	48.97 288	73.16 299	78.33 223	57.79 193	72.11 136	85.26 179	51.84 124	77.89 318	71.00 94	78.47 184	87.49 71

test_fmvsmvis_n_1920		70.84 152	70.38 151	72.22 207	71.16 375	55.39 139	75.86 233	72.21 340	49.03 369	73.28 107	86.17 149	51.83 125	77.29 335	75.80 47	78.05 190	83.98 224

MG-MVS		73.96 83	73.89 82	74.16 133	85.65 44	49.69 272	81.59 93	81.29 148	61.45 96	71.05 151	88.11 80	51.77 126	87.73 54	61.05 203	83.09 91	85.05 188

EPP-MVSNet		72.16 127	71.31 131	74.71 108	78.68 166	49.70 270	82.10 86	81.65 133	60.40 122	65.94 260	85.84 162	51.74 127	86.37 93	55.93 247	79.55 149	88.07 49

fmvsm_s_conf0.1_n		69.41 197	68.60 191	71.83 214	71.07 376	52.88 192	77.85 168	62.44 430	49.58 362	72.97 118	86.22 146	51.68 128	76.48 356	75.53 52	70.10 325	86.14 134

TranMVSNet+NR-MVSNet		70.36 165	70.10 160	71.17 245	78.64 170	42.97 371	76.53 215	81.16 155	66.95 6	68.53 196	85.42 176	51.61 129	83.07 172	52.32 279	69.70 336	87.46 72

fmvsm_s_conf0.5_n_6		72.59 115	72.87 103	71.73 219	75.14 288	51.96 217	76.28 220	77.12 248	57.63 196	73.85 94	86.91 117	51.54 130	77.87 319	77.18 33	80.18 137	85.37 175

lecture		77.75 28	77.84 28	77.50 54	82.75 86	57.62 95	85.92 25	86.20 19	60.53 118	78.99 29	91.45 14	51.51 131	87.78 53	75.65 50	87.55 47	87.10 91

diffmvs		70.69 157	70.43 149	71.46 229	69.45 407	48.95 289	72.93 302	78.46 216	57.27 200	71.69 140	83.97 213	51.48 132	77.92 317	70.70 96	77.95 192	87.53 70
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmambaseed2359dif		68.91 209	68.18 205	71.11 248	70.21 392	48.05 309	72.28 318	75.90 276	51.96 323	70.93 153	84.47 201	51.37 133	78.59 304	61.55 201	74.97 242	86.68 107

EI-MVSNet		69.27 201	68.44 197	71.73 219	74.47 305	49.39 277	75.20 247	78.45 217	59.60 148	69.16 188	76.51 376	51.29 134	82.50 203	59.86 215	71.45 303	83.30 250

IterMVS-LS		69.22 203	68.48 193	71.43 234	74.44 307	49.40 276	76.23 222	77.55 236	59.60 148	65.85 265	81.59 277	51.28 135	81.58 221	59.87 214	69.90 330	83.30 250
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TransMVSNet (Re)		64.72 293	64.33 283	65.87 350	75.22 282	38.56 416	74.66 262	75.08 301	58.90 163	61.79 335	82.63 240	51.18 136	78.07 312	43.63 374	55.87 450	80.99 312

miper_enhance_ethall		67.11 257	66.09 261	70.17 270	69.21 411	45.98 329	72.85 305	78.41 220	51.38 336	65.65 267	75.98 386	51.17 137	81.25 229	60.82 205	69.32 341	83.29 252

VNet		69.68 185	70.19 156	68.16 306	79.73 136	41.63 386	70.53 348	77.38 242	60.37 125	70.69 155	86.63 130	51.08 138	77.09 338	53.61 271	81.69 117	85.75 154

VPA-MVSNet		69.02 207	69.47 169	67.69 312	77.42 220	41.00 393	74.04 275	79.68 180	60.06 135	69.26 186	84.81 185	51.06 139	77.58 328	54.44 264	74.43 249	84.48 208

onestephybrid01		71.00 149	70.34 153	72.99 184	70.38 388	50.88 233	74.14 274	77.41 240	58.80 164	71.36 148	84.93 181	50.96 140	80.87 244	67.73 123	77.35 202	87.23 86

PAPR		71.72 136	70.82 141	74.41 123	81.20 110	51.17 225	79.55 126	83.33 97	55.81 238	66.93 240	84.61 194	50.95 141	86.06 103	55.79 250	79.20 160	86.00 138

PHI-MVS		75.87 54	75.36 56	77.41 56	80.62 121	55.91 125	84.28 50	85.78 27	56.08 233	73.41 101	86.58 134	50.94 142	88.54 34	70.79 95	89.71 17	87.79 59

HPM-MVS		77.28 33	76.85 34	78.54 36	85.00 56	60.81 38	82.91 71	85.08 40	62.57 70	73.09 116	89.97 50	50.90 143	87.48 59	75.30 54	86.85 57	87.33 83
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
reproduce-ours		76.90 38	76.58 38	77.87 48	83.99 68	60.46 43	84.75 38	83.34 95	60.22 132	77.85 38	91.42 16	50.67 144	87.69 55	72.46 77	84.53 76	85.46 167

our_new_method		76.90 38	76.58 38	77.87 48	83.99 68	60.46 43	84.75 38	83.34 95	60.22 132	77.85 38	91.42 16	50.67 144	87.69 55	72.46 77	84.53 76	85.46 167

WR-MVS_H		67.02 259	66.92 240	67.33 320	77.95 197	37.75 425	77.57 176	82.11 127	62.03 88	62.65 321	82.48 251	50.57 146	79.46 274	42.91 381	64.01 390	84.79 198

hybridnocas07		69.86 177	69.44 171	71.14 247	68.10 429	48.28 300	72.52 312	77.08 249	56.94 208	70.50 159	84.91 183	50.48 147	78.37 306	67.84 121	76.55 218	86.76 103

EPNet		73.09 103	72.16 114	75.90 81	75.95 266	56.28 116	83.05 67	72.39 338	66.53 11	65.27 274	87.00 115	50.40 148	85.47 121	62.48 189	86.32 65	85.94 140
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WR-MVS		68.47 223	68.47 195	68.44 301	80.20 127	39.84 403	73.75 285	76.07 273	64.68 25	68.11 209	83.63 221	50.39 149	79.14 285	49.78 299	69.66 337	86.34 123

test_fmvsmconf0.01_n		72.17 125	71.50 124	74.16 133	67.96 431	55.58 135	78.06 162	74.67 305	54.19 284	74.54 78	88.23 76	50.35 150	80.24 260	78.07 26	77.46 200	86.65 110

dtuplus		68.48 222	67.76 212	70.63 261	70.33 390	48.09 305	72.62 308	75.88 278	52.33 317	71.09 150	84.66 191	50.09 151	77.93 316	58.02 232	74.82 245	85.87 144

viewdifsd2359ckpt11		69.13 204	68.38 200	71.38 236	71.57 364	48.61 294	73.22 297	73.18 329	57.65 194	70.67 156	84.73 187	50.03 152	79.80 265	63.25 179	71.10 307	85.74 155

viewmsd2359difaftdt		69.13 204	68.38 200	71.38 236	71.57 364	48.61 294	73.22 297	73.18 329	57.65 194	70.67 156	84.73 187	50.03 152	79.80 265	63.25 179	71.10 307	85.74 155

region2R		77.67 31	77.18 33	79.15 18	86.76 17	62.95 6	86.29 18	84.16 58	62.81 67	73.30 105	90.58 26	49.90 154	88.21 40	73.78 68	87.03 52	86.29 132

fmvsm_s_conf0.5_n_7		69.54 191	69.67 165	69.15 292	73.47 328	51.41 224	70.35 352	73.34 325	57.05 205	68.41 197	85.83 163	49.86 155	72.84 376	71.86 86	76.83 213	83.19 255

UA-Net		73.13 102	72.93 101	73.76 153	83.58 73	51.66 222	78.75 135	77.66 234	67.75 4	72.61 128	89.42 56	49.82 156	83.29 168	53.61 271	83.14 90	86.32 128

ACMMPR		77.71 29	77.23 32	79.16 17	86.75 18	62.93 7	86.29 18	84.24 56	62.82 65	73.55 100	90.56 29	49.80 157	88.24 39	74.02 66	87.03 52	86.32 128

hybrid		69.38 198	68.93 183	70.75 257	67.86 433	48.20 302	72.49 314	76.90 253	55.23 255	70.42 161	84.34 204	49.76 158	77.62 327	67.11 133	76.20 222	86.42 118

API-MVS		72.17 125	71.41 127	74.45 122	81.95 95	57.22 101	84.03 56	80.38 171	59.89 144	68.40 198	82.33 254	49.64 159	87.83 52	51.87 285	84.16 83	78.30 361

reproduce_model		76.43 46	76.08 46	77.49 55	83.47 76	60.09 47	84.60 42	82.90 115	59.65 146	77.31 41	91.43 15	49.62 160	87.24 61	71.99 84	83.75 88	85.14 183

NormalMVS		76.26 49	75.74 52	77.83 50	82.75 86	59.89 52	84.36 46	83.21 103	64.69 23	74.21 84	87.40 97	49.48 161	86.17 99	68.04 117	87.55 47	87.42 74

SymmetryMVS		75.28 60	74.60 67	77.30 59	83.85 71	59.89 52	84.36 46	75.51 287	64.69 23	74.21 84	87.40 97	49.48 161	86.17 99	68.04 117	83.88 85	85.85 146

ab-mvs		66.65 267	66.42 251	67.37 318	76.17 263	41.73 383	70.41 351	76.14 272	53.99 287	65.98 259	83.51 226	49.48 161	76.24 360	48.60 312	73.46 268	84.14 219

balanced_ft_v1		72.98 105	72.55 108	74.27 127	79.52 142	50.64 241	77.78 171	83.29 99	56.76 211	67.88 215	85.95 158	49.42 164	85.29 126	68.64 105	83.76 87	86.87 97

v8		70.33 166	69.28 174	73.49 170	73.15 332	50.22 256	78.62 140	80.78 163	60.79 111	66.45 250	82.11 265	49.35 165	84.98 131	63.58 176	68.71 352	85.28 179

IS-MVSNet		71.57 137	71.00 138	73.27 178	78.86 160	45.63 335	80.22 110	78.69 203	64.14 38	66.46 249	87.36 100	49.30 166	85.60 114	50.26 298	83.71 89	88.59 28

XXY-MVS		60.68 350	61.67 322	57.70 425	70.43 386	38.45 418	64.19 417	66.47 390	48.05 387	63.22 307	80.86 291	49.28 167	60.47 447	45.25 357	67.28 366	74.19 419

cdsmvs_eth3d_5k		17.50 475	23.34 472	0.00 534	0.00 558	0.00 559	0.00 545	78.63 205	0.00 552	0.00 554	82.18 259	49.25 168	0.00 552	0.00 552	0.00 550	0.00 549

PVSNet_Blended_VisFu		71.45 141	70.39 150	74.65 112	82.01 92	58.82 81	79.93 116	80.35 172	55.09 259	65.82 266	82.16 262	49.17 169	82.64 199	60.34 208	78.62 179	82.50 276

PVSNet_BlendedMVS		68.56 221	67.72 214	71.07 250	77.03 245	50.57 244	74.50 265	81.52 135	53.66 298	64.22 299	79.72 313	49.13 170	82.87 190	55.82 248	73.92 255	79.77 344

PVSNet_Blended		68.59 217	67.72 214	71.19 243	77.03 245	50.57 244	72.51 313	81.52 135	51.91 324	64.22 299	77.77 354	49.13 170	82.87 190	55.82 248	79.58 147	80.14 334

DU-MVS		70.01 173	69.53 167	71.44 232	78.05 193	44.13 350	75.01 252	81.51 137	64.37 31	68.20 201	84.52 198	49.12 172	82.82 194	54.62 261	70.43 315	87.37 79

Baseline_NR-MVSNet		67.05 258	67.56 217	65.50 355	75.65 270	37.70 427	75.42 241	74.65 306	59.90 140	68.14 205	83.15 234	49.12 172	77.20 336	52.23 280	69.78 332	81.60 290

VPNet		67.52 247	68.11 208	65.74 351	79.18 152	36.80 436	72.17 320	72.83 334	62.04 87	67.79 223	85.83 163	48.88 174	76.60 354	51.30 290	72.97 278	83.81 232

MTAPA		76.90 38	76.42 43	78.35 39	86.08 39	63.57 2	74.92 256	80.97 160	65.13 16	75.77 52	90.88 22	48.63 175	86.66 80	77.23 31	88.17 37	84.81 197

原ACMM1				74.69 109	85.39 49	59.40 59		83.42 91	51.47 335	70.27 164	86.61 132	48.61 176	86.51 89	53.85 269	87.96 43	78.16 363

v148		68.24 229	67.19 237	71.40 235	70.43 386	47.77 312	75.76 236	77.03 251	58.91 162	67.36 229	80.10 305	48.60 177	81.89 214	60.01 211	66.52 372	84.53 206

PGM-MVS		76.77 41	76.06 47	78.88 32	86.14 37	62.73 9	82.55 78	83.74 78	61.71 91	72.45 132	90.34 37	48.48 178	88.13 43	72.32 79	86.85 57	85.78 149

Test By Simon												48.33 179

CP-MVS		77.12 36	76.68 36	78.43 37	86.05 40	63.18 5	87.55 10	83.45 90	62.44 74	72.68 126	90.50 31	48.18 180	87.34 60	73.59 70	85.71 68	84.76 200

MVS		67.37 249	66.33 255	70.51 265	75.46 277	50.94 229	73.95 278	81.85 130	41.57 450	62.54 324	78.57 334	47.98 181	85.47 121	52.97 276	82.05 108	75.14 403

XVS		77.17 35	76.56 40	79.00 26	86.32 31	62.62 11	85.83 27	83.92 63	64.55 26	72.17 134	90.01 49	47.95 182	88.01 46	71.55 90	86.74 59	86.37 121

X-MVStestdata		70.21 168	67.28 230	79.00 26	86.32 31	62.62 11	85.83 27	83.92 63	64.55 26	72.17 134	6.49 523	47.95 182	88.01 46	71.55 90	86.74 59	86.37 121

SDMVSNet		68.03 234	68.10 209	67.84 308	77.13 234	48.72 293	65.32 405	79.10 190	58.02 183	65.08 281	82.55 247	47.83 184	73.40 373	63.92 167	73.92 255	81.41 295

MAR-MVS		71.51 138	70.15 158	75.60 92	81.84 96	59.39 60	81.38 95	82.90 115	54.90 271	68.08 211	78.70 328	47.73 185	85.51 118	51.68 289	84.17 82	81.88 288
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		67.92 238	66.69 244	71.63 225	78.09 191	49.02 285	77.09 197	81.24 151	51.04 344	60.91 347	83.98 212	47.71 186	84.99 129	40.81 395	79.32 154	80.90 313

SR-MVS		76.13 52	75.70 53	77.40 58	85.87 42	61.20 29	85.52 33	82.19 125	59.99 138	75.10 62	90.35 36	47.66 187	86.52 88	71.64 89	82.99 94	84.47 209

cl22		67.47 248	66.45 248	70.54 264	69.85 402	46.49 323	73.85 283	77.35 243	55.07 262	65.51 269	77.92 344	47.64 188	81.10 234	61.58 200	69.32 341	84.01 223

v10		70.21 168	69.02 179	73.81 150	73.51 326	50.92 231	78.74 136	81.39 140	60.05 136	66.39 251	81.83 270	47.58 189	85.41 124	62.80 186	68.86 351	85.09 187

v1144		70.42 163	69.31 173	73.76 153	73.22 330	50.64 241	77.83 169	81.43 139	58.58 172	69.40 181	81.16 282	47.53 190	85.29 126	64.01 165	70.64 311	85.34 176

v2v482		70.50 161	69.45 170	73.66 161	72.62 342	50.03 262	77.58 175	80.51 167	59.90 140	69.52 177	82.14 263	47.53 190	84.88 137	65.07 157	70.17 323	86.09 136

pm-mvs1		65.24 288	64.97 279	66.04 345	72.38 350	39.40 410	72.62 308	75.63 282	55.53 246	62.35 331	83.18 233	47.45 192	76.47 357	49.06 309	66.54 371	82.24 281

HY-MVS	56.14 13	64.55 298	63.89 287	66.55 333	74.73 297	41.02 390	69.96 357	74.43 307	49.29 366	61.66 339	80.92 289	47.43 193	76.68 353	44.91 360	71.69 299	81.94 286

cl____		67.18 254	66.26 259	69.94 273	70.20 393	45.74 331	73.30 292	76.83 257	55.10 257	65.27 274	79.57 316	47.39 194	80.53 251	59.41 219	69.22 345	83.53 246

DIV-MVS_self_test		67.18 254	66.26 259	69.94 273	70.20 393	45.74 331	73.29 294	76.83 257	55.10 257	65.27 274	79.58 315	47.38 195	80.53 251	59.43 218	69.22 345	83.54 245

eth_miper_zixun_eth		67.63 245	66.28 258	71.67 223	71.60 363	48.33 299	73.68 286	77.88 228	55.80 239	65.91 261	78.62 333	47.35 196	82.88 189	59.45 217	66.25 373	83.81 232

OPM-MVS		74.73 67	74.25 73	76.19 78	80.81 115	59.01 77	82.60 77	83.64 84	63.74 42	72.52 129	87.49 94	47.18 197	85.88 109	69.47 101	80.78 122	83.66 242
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline1		63.81 308	63.87 289	63.62 375	76.29 261	36.36 439	71.78 327	67.29 383	56.05 234	64.23 298	82.95 235	47.11 198	74.41 369	47.30 327	61.85 419	80.10 335

pcd_1.5k_mvsjas		3.92 492	5.23 492	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	47.05 199	0.00 552	0.00 552	0.00 550	0.00 549

PS-MVSNAJss		72.24 123	71.21 133	75.31 96	78.50 172	55.93 124	81.63 90	82.12 126	56.24 230	70.02 169	85.68 169	47.05 199	84.34 146	65.27 155	74.41 250	85.67 158

PS-MVSNAJ		70.51 160	69.70 164	72.93 186	81.52 100	55.79 128	74.92 256	79.00 194	55.04 265	69.88 173	78.66 330	47.05 199	82.19 209	61.61 198	79.58 147	80.83 314

WTY-MVS		59.75 362	60.39 345	57.85 423	72.32 352	37.83 424	61.05 441	64.18 411	45.95 417	61.91 333	79.11 325	47.01 202	60.88 446	42.50 384	69.49 340	74.83 409

xiu_mvs_v2_base		70.52 159	69.75 162	72.84 188	81.21 109	55.63 132	75.11 249	78.92 196	54.92 270	69.96 172	79.68 314	47.00 203	82.09 211	61.60 199	79.37 150	80.81 315

v144192		69.71 182	68.51 192	73.33 177	73.10 333	50.13 258	77.54 178	80.64 164	56.65 213	68.57 195	80.55 295	46.87 204	84.96 133	62.98 184	69.66 337	84.89 195

PEN-MVS		66.60 268	66.45 248	67.04 322	77.11 238	36.56 438	77.03 199	80.42 170	62.95 60	62.51 326	84.03 210	46.69 205	79.07 288	44.22 363	63.08 403	85.51 164

mPP-MVS		76.54 44	75.93 49	78.34 40	86.47 28	63.50 3	85.74 30	82.28 124	62.90 62	71.77 139	90.26 39	46.61 206	86.55 87	71.71 88	85.66 69	84.97 192

IMVS_0403		69.09 206	68.14 207	71.95 210	77.06 239	49.73 266	74.51 264	78.60 206	52.70 309	66.69 244	82.58 242	46.43 207	83.38 166	59.20 221	75.46 237	82.74 267

CP-MVSNet		66.49 271	66.41 252	66.72 325	77.67 208	36.33 441	76.83 209	79.52 184	62.45 73	62.54 324	83.47 228	46.32 208	78.37 306	45.47 354	63.43 399	85.45 169

V42		68.65 216	67.35 228	72.56 195	68.93 417	50.18 257	72.90 304	79.47 185	56.92 209	69.45 180	80.26 301	46.29 209	82.99 175	64.07 163	67.82 360	84.53 206

1112_ss		64.00 307	63.36 300	65.93 347	79.28 147	42.58 375	71.35 331	72.36 339	46.41 410	60.55 350	77.89 348	46.27 210	73.28 374	46.18 341	69.97 327	81.92 287

MSLP-MVS++		73.77 86	73.47 90	74.66 111	83.02 81	59.29 63	82.30 85	81.88 129	59.34 156	71.59 143	86.83 119	45.94 211	83.65 160	65.09 156	85.22 71	81.06 310

PS-CasMVS		66.42 272	66.32 256	66.70 327	77.60 216	36.30 443	76.94 203	79.61 182	62.36 75	62.43 329	83.66 220	45.69 212	78.37 306	45.35 356	63.26 401	85.42 172

APD-MVS_3200maxsize		74.96 62	74.39 70	76.67 69	82.20 90	58.24 87	83.67 62	83.29 99	58.41 175	73.71 96	90.14 41	45.62 213	85.99 106	69.64 99	82.85 101	85.78 149

DTE-MVSNet		65.58 282	65.34 274	66.31 337	76.06 265	34.79 452	76.43 217	79.38 187	62.55 71	61.66 339	83.83 215	45.60 214	79.15 284	41.64 393	60.88 425	85.00 189

BH-w/o		66.85 262	65.83 264	69.90 276	79.29 145	52.46 205	74.66 262	76.65 262	54.51 280	64.85 288	78.12 338	45.59 215	82.95 181	43.26 377	75.54 235	74.27 418

h-mvs33		72.71 111	71.49 125	76.40 74	81.99 94	59.58 57	76.92 204	76.74 261	60.40 122	74.81 71	85.95 158	45.54 216	85.76 112	70.41 97	70.61 313	83.86 231

hse-mvs2		71.04 146	69.86 161	74.60 115	79.58 139	57.12 108	73.96 277	75.25 293	60.40 122	74.81 71	81.95 267	45.54 216	82.90 187	70.41 97	66.83 369	83.77 236

HQP2-MVS												45.46 218

HQP-MVS		73.45 92	72.80 104	75.40 94	80.66 117	54.94 145	82.31 82	83.90 65	62.10 83	67.85 216	85.54 174	45.46 218	86.93 73	67.04 135	80.35 133	84.32 211

ACMMP		76.02 53	75.33 57	78.07 42	85.20 54	61.91 20	85.49 35	84.44 52	63.04 59	69.80 175	89.74 55	45.43 220	87.16 67	72.01 83	82.87 100	85.14 183
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		71.40 142	70.60 146	73.78 151	76.60 255	53.15 183	79.74 121	79.78 178	58.37 176	68.75 192	86.45 140	45.43 220	80.60 249	62.58 187	77.73 194	87.58 69

BH-untuned		68.27 227	67.29 229	71.21 242	79.74 135	53.22 181	76.06 227	77.46 239	57.19 201	66.10 257	81.61 275	45.37 222	83.50 164	45.42 355	76.68 216	76.91 386

v1192		69.97 175	68.68 189	73.85 148	73.19 331	50.94 229	77.68 174	81.36 142	57.51 198	68.95 191	80.85 292	45.28 223	85.33 125	62.97 185	70.37 317	85.27 180

HQP_MVS		74.31 74	73.73 85	76.06 79	81.41 103	56.31 114	84.22 51	84.01 60	64.52 28	69.27 184	86.10 151	45.26 224	87.21 65	68.16 113	80.58 128	84.65 201

plane_prior6					81.20 110	56.24 118						45.26 224

icg_test_0407_2		66.41 273	66.75 243	65.37 359	77.06 239	49.73 266	63.79 421	78.60 206	52.70 309	66.19 254	82.58 242	45.17 226	63.65 437	59.20 221	75.46 237	82.74 267

IMVS_0407		68.90 210	67.93 210	71.82 215	77.06 239	49.73 266	74.40 269	78.60 206	52.70 309	66.19 254	82.58 242	45.17 226	83.00 174	59.20 221	75.46 237	82.74 267

SD_0403		63.07 318	63.49 298	61.82 388	75.16 285	31.14 477	71.89 326	73.47 323	53.34 301	58.22 381	81.81 271	45.17 226	73.86 372	37.43 417	74.87 244	80.45 322

CL-MVSNet_self_test		61.53 344	60.94 336	63.30 378	68.95 415	36.93 435	67.60 383	72.80 335	55.67 242	59.95 357	76.63 371	45.01 229	72.22 383	39.74 405	62.09 418	80.74 317

SR-MVS-dyc-post		74.57 71	73.90 81	76.58 72	83.49 74	59.87 54	84.29 48	81.36 142	58.07 181	73.14 112	90.07 43	44.74 230	85.84 110	68.20 109	81.76 113	84.03 221

v1921920		69.47 195	68.17 206	73.36 176	73.06 334	50.10 259	77.39 183	80.56 165	56.58 222	68.59 193	80.37 297	44.72 231	84.98 131	62.47 190	69.82 331	85.00 189

RRT-MVS		71.46 140	70.70 144	73.74 156	77.76 204	49.30 280	76.60 213	80.45 169	61.25 101	68.17 203	84.78 186	44.64 232	84.90 134	64.79 158	77.88 193	87.03 92

Vis-MVSNet (Re-imp)		63.69 309	63.88 288	63.14 380	74.75 296	31.04 478	71.16 336	63.64 418	56.32 227	59.80 360	84.99 180	44.51 233	75.46 364	39.12 408	80.62 126	82.92 262

DP-MVS Recon		72.15 128	70.73 143	76.40 74	86.57 26	57.99 90	81.15 98	82.96 113	57.03 206	66.78 241	85.56 170	44.50 234	88.11 44	51.77 287	80.23 136	83.10 260

TAMVS		66.78 265	65.27 276	71.33 241	79.16 154	53.67 165	73.84 284	69.59 364	52.32 319	65.28 273	81.72 273	44.49 235	77.40 332	42.32 385	78.66 178	82.92 262

Vis-MVSNet		72.18 124	71.37 129	74.61 114	81.29 106	55.41 138	80.90 100	78.28 224	60.73 113	69.23 187	88.09 81	44.36 236	82.65 198	57.68 234	81.75 115	85.77 152
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
旧先验1					83.04 80	53.15 183		67.52 380			87.85 89	44.08 237			80.76 124	78.03 368

Test_1112_low_res		62.32 330	61.77 321	64.00 372	79.08 156	39.53 409	68.17 378	70.17 357	43.25 438	59.03 370	79.90 307	44.08 237	71.24 389	43.79 371	68.42 355	81.25 302

fmvsm_s_conf0.5_n_2		69.82 179	69.27 175	71.46 229	72.00 357	51.08 226	73.30 292	67.79 379	55.06 264	75.24 59	87.51 93	44.02 239	77.00 342	75.67 49	72.86 279	86.31 131

MVSFormer		71.50 139	70.38 151	74.88 104	78.76 163	57.15 106	82.79 72	78.48 214	51.26 339	69.49 178	83.22 231	43.99 240	83.24 169	66.06 145	79.37 150	84.23 215

lupinMVS		69.57 190	68.28 204	73.44 173	78.76 163	57.15 106	76.57 214	73.29 328	46.19 412	69.49 178	82.18 259	43.99 240	79.23 279	64.66 160	79.37 150	83.93 226

v7n		69.01 208	67.36 227	73.98 145	72.51 346	52.65 198	78.54 144	81.30 147	60.26 131	62.67 320	81.62 274	43.61 242	84.49 143	57.01 238	68.70 353	84.79 198

CDS-MVSNet		66.80 264	65.37 273	71.10 249	78.98 157	53.13 185	73.27 296	71.07 348	52.15 320	64.72 289	80.23 302	43.56 243	77.10 337	45.48 353	78.88 169	83.05 261
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
jason		69.65 186	68.39 199	73.43 174	78.27 184	56.88 110	77.12 196	73.71 322	46.53 409	69.34 183	83.22 231	43.37 244	79.18 280	64.77 159	79.20 160	84.23 215
jason: jason.
v1240		69.24 202	67.91 211	73.25 180	73.02 336	49.82 264	77.21 193	80.54 166	56.43 224	68.34 200	80.51 296	43.33 245	84.99 129	62.03 194	69.77 334	84.95 193

SSM_0407		70.41 164	68.96 182	74.75 107	78.65 167	53.46 173	77.28 190	80.00 176	53.88 290	68.14 205	84.61 194	43.21 246	86.26 98	58.80 226	76.11 224	84.54 203

SSM_0404		70.84 152	69.41 172	75.12 101	79.20 150	53.86 160	77.89 165	80.00 176	53.88 290	69.40 181	84.61 194	43.21 246	86.56 84	58.80 226	77.68 196	84.95 193

LCM-MVSNet-Re		61.88 341	61.35 327	63.46 376	74.58 303	31.48 476	61.42 436	58.14 449	58.71 168	53.02 443	79.55 317	43.07 248	76.80 347	45.69 346	77.96 191	82.11 285

RE-MVS-def			73.71 86		83.49 74	59.87 54	84.29 48	81.36 142	58.07 181	73.14 112	90.07 43	43.06 249		68.20 109	81.76 113	84.03 221

baseline2		63.42 311	61.26 330	69.89 277	72.55 344	47.62 314	71.54 329	68.38 375	50.11 354	54.82 420	75.55 391	43.06 249	80.96 239	48.13 317	67.16 367	81.11 307

fmvsm_s_conf0.1_n_2		69.64 187	69.01 181	71.52 227	71.66 362	51.04 227	73.39 291	67.14 385	55.02 268	75.11 61	87.64 92	42.94 251	77.01 341	75.55 51	72.63 285	86.52 115

FA-MVS(test-final)		69.82 179	68.48 193	73.84 149	78.44 175	50.04 261	75.58 240	78.99 195	58.16 179	67.59 226	82.14 263	42.66 252	85.63 113	56.60 240	76.19 223	85.84 147

BH-RMVSNet		68.81 212	67.42 224	72.97 185	80.11 131	52.53 202	74.26 270	76.29 269	58.48 174	68.38 199	84.20 205	42.59 253	83.83 156	46.53 336	75.91 229	82.56 271

LFMVS		71.78 133	71.59 122	72.32 205	83.40 77	46.38 324	79.75 120	71.08 347	64.18 35	72.80 124	88.64 73	42.58 254	83.72 158	57.41 237	84.49 78	86.86 98

test_yl		69.69 183	69.13 176	71.36 238	78.37 179	45.74 331	74.71 260	80.20 173	57.91 189	70.01 170	83.83 215	42.44 255	82.87 190	54.97 257	79.72 144	85.48 165

DCV-MVSNet		69.69 183	69.13 176	71.36 238	78.37 179	45.74 331	74.71 260	80.20 173	57.91 189	70.01 170	83.83 215	42.44 255	82.87 190	54.97 257	79.72 144	85.48 165

3Dnovator	64.47 5	72.49 117	71.39 128	75.79 84	77.70 206	58.99 78	80.66 105	83.15 108	62.24 80	65.46 270	86.59 133	42.38 257	85.52 117	59.59 216	84.72 73	82.85 265

VDD-MVS		72.50 116	72.09 115	73.75 155	81.58 99	49.69 272	77.76 173	77.63 235	63.21 55	73.21 108	89.02 62	42.14 258	83.32 167	61.72 196	82.50 104	88.25 38

3Dnovator+	66.72 4	75.84 55	74.57 68	79.66 9	82.40 88	59.92 51	85.83 27	86.32 18	66.92 7	67.80 222	89.24 60	42.03 259	89.38 25	64.07 163	86.50 63	89.69 4

SSC-MVS3.2		60.57 352	61.39 326	58.12 421	74.29 312	32.63 470	59.52 446	65.53 399	59.90 140	62.45 327	79.75 312	41.96 260	63.90 436	39.47 406	69.65 339	77.84 370

MVS_111021_LR		69.50 194	68.78 187	71.65 224	78.38 177	59.33 61	74.82 258	70.11 358	58.08 180	67.83 221	84.68 189	41.96 260	76.34 359	65.62 152	77.54 197	79.30 349

CPTT-MVS		72.78 109	72.08 116	74.87 105	84.88 62	61.41 26	84.15 54	77.86 229	55.27 253	67.51 228	88.08 82	41.93 262	81.85 215	69.04 104	80.01 138	81.35 300

usedtu_dtu_shiyan1		64.34 302	63.57 294	66.66 329	72.44 348	40.74 396	69.60 363	76.80 259	53.21 302	61.73 337	77.92 344	41.92 263	77.68 325	46.23 339	72.25 292	81.57 291

FE-MVSNET3		64.34 302	63.57 294	66.66 329	72.44 348	40.74 396	69.60 363	76.80 259	53.21 302	61.73 337	77.92 344	41.92 263	77.68 325	46.23 339	72.25 292	81.57 291

GBi-Net		67.21 251	66.55 246	69.19 287	77.63 210	43.33 361	77.31 185	77.83 231	56.62 217	65.04 283	82.70 237	41.85 265	80.33 256	47.18 328	72.76 281	83.92 227

test1		67.21 251	66.55 246	69.19 287	77.63 210	43.33 361	77.31 185	77.83 231	56.62 217	65.04 283	82.70 237	41.85 265	80.33 256	47.18 328	72.76 281	83.92 227

FMVSNet2		66.93 261	66.31 257	68.79 296	77.63 210	42.98 370	76.11 225	77.47 237	56.62 217	65.22 280	82.17 261	41.85 265	80.18 263	47.05 334	72.72 284	83.20 254

mamba_0408		67.78 242	65.42 271	74.85 106	78.65 167	53.46 173	50.83 479	79.09 191	53.75 293	68.14 205	83.83 215	41.79 268	86.56 84	56.58 241	76.11 224	84.54 203

SSM_04072		64.98 292	65.42 271	63.68 374	78.65 167	53.46 173	50.83 479	79.09 191	53.75 293	68.14 205	83.83 215	41.79 268	53.03 482	56.58 241	76.11 224	84.54 203

KinetiMVS		71.26 143	70.16 157	74.57 117	74.59 302	52.77 196	75.91 232	81.20 152	60.72 114	69.10 190	85.71 168	41.67 270	83.53 163	63.91 169	78.62 179	87.42 74

CostFormer		64.04 306	62.51 311	68.61 298	71.88 359	45.77 330	71.30 333	70.60 355	47.55 396	64.31 295	76.61 374	41.63 271	79.62 270	49.74 301	69.00 348	80.42 323

AdaColmap		69.99 174	68.66 190	73.97 146	84.94 59	57.83 92	82.63 76	78.71 202	56.28 229	64.34 293	84.14 207	41.57 272	87.06 71	46.45 337	78.88 169	77.02 382

Effi-MVS+-dtu		69.64 187	67.53 220	75.95 80	76.10 264	62.29 15	80.20 111	76.06 274	59.83 145	65.26 277	77.09 363	41.56 273	84.02 153	60.60 207	71.09 309	81.53 293

QAPM		70.05 172	68.81 186	73.78 151	76.54 257	53.43 176	83.23 65	83.48 88	52.89 307	65.90 262	86.29 145	41.55 274	86.49 90	51.01 292	78.40 185	81.42 294

VDDNet		71.81 132	71.33 130	73.26 179	82.80 85	47.60 315	78.74 136	75.27 292	59.59 151	72.94 119	89.40 57	41.51 275	83.91 155	58.75 228	82.99 94	88.26 37

CHOSEN 1792x2688		65.08 291	62.84 308	71.82 215	81.49 102	56.26 117	66.32 393	74.20 315	40.53 456	63.16 310	78.65 331	41.30 276	77.80 321	45.80 345	74.09 252	81.40 297

新几何1				70.76 256	85.66 43	61.13 30		66.43 391	44.68 424	70.29 163	86.64 128	41.29 277	75.23 365	49.72 302	81.75 115	75.93 394

tpmrst		58.24 377	58.70 362	56.84 427	66.97 439	34.32 458	69.57 366	61.14 439	47.17 403	58.58 377	71.60 425	41.28 278	60.41 448	49.20 307	62.84 405	75.78 396

tfpnnormal		62.47 325	61.63 323	64.99 364	74.81 294	39.01 412	71.22 334	73.72 321	55.22 256	60.21 351	80.09 306	41.26 279	76.98 344	30.02 467	68.09 358	78.97 355

guyue		68.10 233	67.23 236	70.71 260	73.67 325	49.27 281	73.65 287	76.04 275	55.62 245	67.84 220	82.26 257	41.24 280	78.91 300	61.01 204	73.72 259	83.94 225

sd_testset		64.46 299	64.45 282	64.51 367	77.13 234	42.25 378	62.67 428	72.11 341	58.02 183	65.08 281	82.55 247	41.22 281	69.88 399	47.32 326	73.92 255	81.41 295

HPM-MVS_fast		74.30 75	73.46 91	76.80 65	84.45 66	59.04 76	83.65 63	81.05 157	60.15 134	70.43 160	89.84 52	41.09 282	85.59 115	67.61 126	82.90 99	85.77 152

BP-MVS1		73.41 94	72.25 113	76.88 63	76.68 252	53.70 164	79.15 130	81.07 156	60.66 115	71.81 138	87.39 99	40.93 283	87.24 61	71.23 92	81.29 119	89.71 3

114514_t		70.83 154	69.56 166	74.64 113	86.21 33	54.63 150	82.34 81	81.81 131	48.22 383	63.01 314	85.83 163	40.92 284	87.10 69	57.91 233	79.79 143	82.18 282

VortexMVS		66.41 273	65.50 270	69.16 291	73.75 321	48.14 303	73.41 290	78.28 224	53.73 295	64.98 287	78.33 336	40.62 285	79.07 288	58.88 225	67.50 363	80.26 331

WB-MVSnew		59.66 363	59.69 351	59.56 403	75.19 284	35.78 449	69.34 368	64.28 410	46.88 406	61.76 336	75.79 387	40.61 286	65.20 430	32.16 449	71.21 304	77.70 371

HyFIR lowres test		65.67 281	63.01 306	73.67 160	79.97 133	55.65 131	69.07 371	75.52 286	42.68 444	63.53 304	77.95 342	40.43 287	81.64 218	46.01 343	71.91 296	83.73 238

miper_lstm_enhance		62.03 336	60.88 337	65.49 356	66.71 442	46.25 325	56.29 463	75.70 281	50.68 347	61.27 343	75.48 393	40.21 288	68.03 409	56.31 245	65.25 380	82.18 282

GDP-MVS		72.64 113	71.28 132	76.70 66	77.72 205	54.22 156	79.57 125	84.45 51	55.30 252	71.38 147	86.97 116	39.94 289	87.00 72	67.02 137	79.20 160	88.89 15

FMVSNet3		66.32 275	65.61 268	68.46 300	76.48 258	42.34 376	74.98 254	77.15 247	55.83 237	65.04 283	81.16 282	39.91 290	80.14 264	47.18 328	72.76 281	82.90 264

Syy-MVS		56.00 396	56.23 387	55.32 434	74.69 298	26.44 494	65.52 400	57.49 453	50.97 345	56.52 400	72.18 418	39.89 291	68.09 407	24.20 485	64.59 387	71.44 448

MVP-Stereo		65.41 285	63.80 290	70.22 267	77.62 214	55.53 136	76.30 219	78.53 212	50.59 350	56.47 402	78.65 331	39.84 292	82.68 197	44.10 367	72.12 295	72.44 434
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TR-MVS		66.59 270	65.07 278	71.17 245	79.18 152	49.63 274	73.48 288	75.20 296	52.95 305	67.90 213	80.33 300	39.81 293	83.68 159	43.20 378	73.56 265	80.20 332

pmmvs6		63.69 309	62.82 309	66.27 339	70.63 381	39.27 411	73.13 300	75.47 289	52.69 314	59.75 362	82.30 255	39.71 294	77.03 340	47.40 323	64.35 389	82.53 273

XVG-OURS-SEG-HR		68.81 212	67.47 223	72.82 190	74.40 308	56.87 111	70.59 347	79.04 193	54.77 273	66.99 238	86.01 156	39.57 295	78.21 310	62.54 188	73.33 271	83.37 249

Anonymous20231211		69.28 200	68.47 195	71.73 219	80.28 123	47.18 319	79.98 114	82.37 123	54.61 276	67.24 233	84.01 211	39.43 296	82.41 206	55.45 255	72.83 280	85.62 161

blended_shiyan8		62.46 326	60.71 341	67.71 310	69.15 413	43.43 359	70.83 342	76.52 263	51.49 333	57.67 386	71.36 429	39.38 297	79.07 288	47.37 324	62.67 406	80.62 319

blended_shiyan6		62.46 326	60.71 341	67.71 310	69.14 414	43.42 360	70.82 343	76.52 263	51.50 332	57.64 387	71.37 428	39.38 297	79.08 287	47.36 325	62.67 406	80.65 318

Fast-Effi-MVS+-dtu		67.37 249	65.33 275	73.48 171	72.94 337	57.78 94	77.47 181	76.88 254	57.60 197	61.97 332	76.85 367	39.31 299	80.49 254	54.72 260	70.28 321	82.17 284

dmvs_testset		50.16 432	51.90 421	44.94 469	66.49 444	11.78 512	61.01 442	51.50 472	51.17 343	50.30 458	67.44 460	39.28 300	60.29 449	22.38 488	57.49 443	62.76 474

ACMP	63.53 6	72.30 122	71.20 134	75.59 93	80.28 123	57.54 96	82.74 74	82.84 118	60.58 117	65.24 278	86.18 148	39.25 301	86.03 105	66.95 139	76.79 214	83.22 253
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20240529		69.91 176	69.02 179	72.56 195	80.19 128	47.65 313	77.56 177	80.99 159	55.45 249	69.88 173	86.76 121	39.24 302	82.18 210	54.04 266	77.10 210	87.85 55

LPG-MVS_test		72.74 110	71.74 121	75.76 85	80.22 125	57.51 98	82.55 78	83.40 92	61.32 98	66.67 246	87.33 102	39.15 303	86.59 82	67.70 124	77.30 206	83.19 255

LGP-MVS_train				75.76 85	80.22 125	57.51 98		83.40 92	61.32 98	66.67 246	87.33 102	39.15 303	86.59 82	67.70 124	77.30 206	83.19 255

TAPA-MVS	59.36 10	66.60 268	65.20 277	70.81 255	76.63 254	48.75 291	76.52 216	80.04 175	50.64 349	65.24 278	84.93 181	39.15 303	78.54 305	36.77 423	76.88 212	85.14 183
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
AstraMVS		67.86 240	66.83 241	70.93 253	73.50 327	49.34 278	73.28 295	74.01 317	55.45 249	68.10 210	83.28 229	38.93 306	79.14 285	63.22 181	71.74 298	84.30 213

OpenMVS	61.03 9	68.85 211	67.56 217	72.70 192	74.26 313	53.99 159	81.21 97	81.34 146	52.70 309	62.75 319	85.55 172	38.86 307	84.14 148	48.41 314	83.01 92	79.97 336

wanda-best-256-512		62.00 338	60.17 347	67.49 314	68.53 422	43.07 368	69.65 360	76.38 267	51.26 339	57.10 393	69.95 441	38.83 308	79.04 291	47.14 332	62.67 406	80.37 326

FE-blended-shiyan7		62.00 338	60.17 347	67.49 314	68.53 422	43.07 368	69.65 360	76.38 267	51.26 339	57.10 393	69.95 441	38.83 308	79.04 291	47.14 332	62.67 406	80.37 326

usedtu_blend_shiyan5		62.63 322	60.77 340	68.20 304	68.53 422	44.64 344	73.47 289	77.00 252	51.91 324	57.10 393	69.95 441	38.83 308	79.61 271	47.44 320	62.67 406	80.37 326

sss		56.17 395	56.57 382	54.96 436	66.93 440	36.32 442	57.94 454	61.69 436	41.67 448	58.64 375	75.32 396	38.72 311	56.25 471	42.04 388	66.19 374	72.31 438

ACMM	61.98 7	70.80 156	69.73 163	74.02 142	80.59 122	58.59 84	82.68 75	82.02 128	55.46 248	67.18 235	84.39 203	38.51 312	83.17 171	60.65 206	76.10 227	80.30 330
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVSTER		67.16 256	65.58 269	71.88 213	70.37 389	49.70 270	70.25 354	78.45 217	51.52 331	69.16 188	80.37 297	38.45 313	82.50 203	60.19 209	71.46 302	83.44 248

test_djsdf		69.45 196	67.74 213	74.58 116	74.57 304	54.92 147	82.79 72	78.48 214	51.26 339	65.41 271	83.49 227	38.37 314	83.24 169	66.06 145	69.25 344	85.56 162

MonoMVSNet		64.15 304	63.31 302	66.69 328	70.51 384	44.12 352	74.47 266	74.21 314	57.81 191	63.03 312	76.62 372	38.33 315	77.31 334	54.22 265	60.59 431	78.64 358

tpm2		62.07 334	60.10 349	67.99 307	72.79 339	43.86 354	71.05 340	66.85 388	43.14 440	62.77 317	75.39 395	38.32 316	80.80 246	41.69 390	68.88 349	79.32 348

tpm cat1		59.25 368	56.95 376	66.15 342	72.19 354	46.96 320	68.09 379	65.76 396	40.03 460	57.81 385	70.56 434	38.32 316	74.51 368	38.26 413	61.50 422	77.00 383

CNLPA		65.43 284	64.02 286	69.68 279	78.73 165	58.07 89	77.82 170	70.71 354	51.49 333	61.57 341	83.58 225	38.23 318	70.82 391	43.90 369	70.10 325	80.16 333

1314		64.61 297	63.21 304	68.80 295	71.87 360	47.46 316	73.95 278	78.39 222	42.88 443	59.97 356	76.60 375	38.11 319	79.39 276	54.84 259	72.32 289	79.55 345

testdata				64.66 365	81.52 100	52.93 188		65.29 401	46.09 413	73.88 93	87.46 96	38.08 320	66.26 424	53.31 274	78.48 182	74.78 411

FMVSNet1		66.70 266	65.87 263	69.19 287	77.49 218	43.33 361	77.31 185	77.83 231	56.45 223	64.60 292	82.70 237	38.08 320	80.33 256	46.08 342	72.31 290	83.92 227

UniMVSNet_ETH3D		67.60 246	67.07 239	69.18 290	77.39 221	42.29 377	74.18 273	75.59 284	60.37 125	66.77 242	86.06 153	37.64 322	78.93 298	52.16 281	73.49 266	86.32 128

EPNet_dtu		61.90 340	61.97 319	61.68 389	72.89 338	39.78 404	75.85 234	65.62 398	55.09 259	54.56 425	79.36 321	37.59 323	67.02 418	39.80 404	76.95 211	78.25 362
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IterMVS-SCA-FT		62.49 324	61.52 324	65.40 358	71.99 358	50.80 235	71.15 337	69.63 363	45.71 418	60.61 349	77.93 343	37.45 324	65.99 427	55.67 252	63.50 398	79.42 347

SCA		60.49 354	58.38 365	66.80 324	74.14 317	48.06 307	63.35 424	63.23 422	49.13 368	59.33 368	72.10 420	37.45 324	74.27 370	44.17 364	62.57 412	78.05 365

tt0805		67.77 243	67.24 234	69.34 286	74.87 291	40.08 400	77.36 184	81.37 141	55.31 251	66.33 252	84.65 192	37.35 326	82.55 202	55.65 253	72.28 291	85.39 174

IterMVS		62.79 321	61.27 329	67.35 319	69.37 408	52.04 215	71.17 335	68.24 377	52.63 315	59.82 359	76.91 366	37.32 327	72.36 379	52.80 277	63.19 402	77.66 372
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tfpn200view9		63.18 316	62.18 317	66.21 340	76.85 248	39.62 407	71.96 324	69.44 367	56.63 215	62.61 322	79.83 308	37.18 328	79.17 281	31.84 453	73.25 273	79.83 341

thres400		63.31 312	62.18 317	66.72 325	76.85 248	39.62 407	71.96 324	69.44 367	56.63 215	62.61 322	79.83 308	37.18 328	79.17 281	31.84 453	73.25 273	81.36 298

tpm		57.34 384	58.16 367	54.86 437	71.80 361	34.77 453	67.47 386	56.04 463	48.20 384	60.10 353	76.92 365	37.17 330	53.41 481	40.76 396	65.01 381	76.40 390

test222					83.14 78	58.68 83	72.57 311	63.45 420	41.78 446	67.56 227	86.12 150	37.13 331			78.73 175	74.98 407

AUN-MVS		68.45 225	66.41 252	74.57 117	79.53 141	57.08 109	73.93 280	75.23 294	54.44 281	66.69 244	81.85 269	37.10 332	82.89 188	62.07 192	66.84 368	83.75 237

thres200		62.20 333	61.16 333	65.34 360	75.38 280	39.99 402	69.60 363	69.29 369	55.64 244	61.87 334	76.99 364	37.07 333	78.96 297	31.28 461	73.28 272	77.06 381

thres100view900		63.28 314	62.41 313	65.89 348	77.31 224	38.66 415	72.65 306	69.11 371	57.07 204	62.45 327	81.03 286	37.01 334	79.17 281	31.84 453	73.25 273	79.83 341

thres600view7		63.30 313	62.27 315	66.41 335	77.18 227	38.87 413	72.35 316	69.11 371	56.98 207	62.37 330	80.96 288	37.01 334	79.00 296	31.43 460	73.05 277	81.36 298

gbinet_0.2-2-1-0.02		62.43 328	60.41 344	68.49 299	68.91 418	43.71 356	71.73 328	75.89 277	52.10 321	58.33 379	69.67 448	36.86 336	80.59 250	47.18 328	63.05 404	81.16 306

DP-MVS		65.68 280	63.66 293	71.75 218	84.93 60	56.87 111	80.74 104	73.16 331	53.06 304	59.09 369	82.35 253	36.79 337	85.94 108	32.82 447	69.96 328	72.45 433

mvsmamba		68.47 223	66.56 245	74.21 132	79.60 138	52.95 187	74.94 255	75.48 288	52.09 322	60.10 353	83.27 230	36.54 338	84.70 139	59.32 220	77.69 195	84.99 191

XVG-OURS		68.76 215	67.37 226	72.90 187	74.32 311	57.22 101	70.09 356	78.81 199	55.24 254	67.79 223	85.81 166	36.54 338	78.28 309	62.04 193	75.74 232	83.19 255

dtuonlycased		55.96 397	54.88 400	59.22 409	68.38 427	40.38 398	69.17 370	63.12 425	40.00 461	53.62 435	68.84 453	36.27 340	66.23 425	40.57 397	53.92 459	71.06 454

ECVR-MVS		67.72 244	67.51 221	68.35 302	79.46 143	36.29 444	74.79 259	66.93 387	58.72 166	67.19 234	88.05 83	36.10 341	81.38 226	52.07 282	84.25 80	87.39 77

test1111		67.21 251	67.14 238	67.42 317	79.24 149	34.76 454	73.89 282	65.65 397	58.71 168	66.96 239	87.95 87	36.09 342	80.53 251	52.03 283	83.79 86	86.97 94

pmmvs4		61.48 346	59.39 353	67.76 309	71.57 364	53.86 160	71.42 330	65.34 400	44.20 429	59.46 364	77.92 344	35.90 343	74.71 367	43.87 370	64.87 383	74.71 413

CR-MVSNet		59.91 359	57.90 370	65.96 346	69.96 398	52.07 213	65.31 406	63.15 423	42.48 445	59.36 365	74.84 398	35.83 344	70.75 392	45.50 351	64.65 385	75.06 404

Patchmtry		57.16 385	56.47 383	59.23 408	69.17 412	34.58 456	62.98 426	63.15 423	44.53 425	56.83 397	74.84 398	35.83 344	68.71 404	40.03 400	60.91 424	74.39 417

dmvs_re		56.77 388	56.83 378	56.61 428	69.23 410	41.02 390	58.37 451	64.18 411	50.59 350	57.45 391	71.42 426	35.54 346	58.94 457	37.23 419	67.45 364	69.87 462

FE-MVSNET2		62.01 337	60.88 337	65.42 357	68.74 419	38.43 419	72.92 303	77.39 241	54.74 275	55.40 412	76.71 369	35.46 347	76.72 351	44.25 362	62.31 415	81.10 308

RPMNet		61.53 344	58.42 364	70.86 254	69.96 398	52.07 213	65.31 406	81.36 142	43.20 439	59.36 365	70.15 439	35.37 348	85.47 121	36.42 430	64.65 385	75.06 404

CANet_DTU		68.18 231	67.71 216	69.59 281	74.83 293	46.24 326	78.66 139	76.85 255	59.60 148	63.45 305	82.09 266	35.25 349	77.41 331	59.88 213	78.76 174	85.14 183

thisisatest0530		67.92 238	65.78 265	74.33 125	76.29 261	51.03 228	76.89 205	74.25 313	53.67 297	65.59 268	81.76 272	35.15 350	85.50 119	55.94 246	72.47 286	86.47 117

tttt0517		67.83 241	65.66 267	74.33 125	76.69 251	50.82 234	77.86 167	73.99 318	54.54 279	64.64 291	82.53 250	35.06 351	85.50 119	55.71 251	69.91 329	86.67 108

test_0402		63.25 315	61.01 335	69.96 272	80.00 132	54.37 153	76.86 207	72.02 342	54.58 278	58.71 372	80.79 294	35.00 352	84.36 145	26.41 482	64.71 384	71.15 452

thisisatest0515		65.83 279	63.50 297	72.82 190	73.75 321	49.50 275	71.32 332	73.12 333	49.39 364	63.82 301	76.50 378	34.95 353	84.84 138	53.20 275	75.49 236	84.13 220

IMVS_0404		64.63 296	64.22 284	65.88 349	77.06 239	49.73 266	64.40 414	78.60 206	52.70 309	53.16 441	82.58 242	34.82 354	65.16 431	59.20 221	75.46 237	82.74 267

sam_mvs1												34.74 355				78.05 365

pmmvs5		56.47 391	55.68 391	58.86 413	61.41 471	36.71 437	66.37 392	62.75 426	40.38 457	53.70 432	76.62 372	34.56 356	67.05 417	40.02 401	65.27 379	72.83 427

patchmatchnet-post											64.03 472	34.50 357	74.27 370

PatchmatchNet		59.84 360	58.24 366	64.65 366	73.05 335	46.70 322	69.42 367	62.18 434	47.55 396	58.88 371	71.96 422	34.49 358	69.16 401	42.99 380	63.60 396	78.07 364
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Patchmatch-test		49.08 435	48.28 437	51.50 459	64.40 456	30.85 479	45.68 489	48.46 482	35.60 470	46.10 472	72.10 420	34.47 359	46.37 494	27.08 480	60.65 429	77.27 378

MS-PatchMatch		62.42 329	61.46 325	65.31 361	75.21 283	52.10 212	72.05 321	74.05 316	46.41 410	57.42 392	74.36 402	34.35 360	77.57 329	45.62 348	73.67 260	66.26 471

dtuonly		54.95 408	55.26 397	54.01 442	59.03 482	35.99 445	61.92 433	56.33 459	38.48 465	54.61 424	77.85 350	34.27 361	51.60 488	45.10 358	69.74 335	74.43 415

tpmvs		58.47 372	56.95 376	63.03 382	70.20 393	41.21 389	67.90 381	67.23 384	49.62 361	54.73 422	70.84 432	34.14 362	76.24 360	36.64 427	61.29 423	71.64 444

testing91		64.46 299	63.80 290	66.47 334	78.43 176	40.06 401	67.63 382	69.59 364	59.06 159	63.18 309	78.05 340	34.05 363	76.99 343	48.30 315	75.87 230	82.37 279

PMMVS		53.96 411	53.26 417	56.04 430	62.60 465	50.92 231	61.17 439	56.09 462	32.81 474	53.51 438	66.84 465	34.04 364	59.93 451	44.14 366	68.18 357	57.27 483

Patchmatch-RL test		58.16 378	55.49 394	66.15 342	67.92 432	48.89 290	60.66 443	51.07 475	47.86 392	59.36 365	62.71 476	34.02 365	72.27 382	56.41 244	59.40 435	77.30 377

WB-MVS		43.26 445	43.41 445	42.83 473	63.32 461	10.32 514	58.17 453	45.20 490	45.42 419	40.44 485	67.26 463	34.01 366	58.98 456	11.96 504	24.88 497	59.20 477

test_post											3.55 529	33.90 367	66.52 421

WBMVS		60.54 353	60.61 343	60.34 401	78.00 195	35.95 447	64.55 413	64.89 403	49.63 360	63.39 306	78.70 328	33.85 368	67.65 412	42.10 387	70.35 319	77.43 375

PLC	56.13 14	65.09 290	63.21 304	70.72 259	81.04 112	54.87 148	78.57 142	77.47 237	48.51 378	55.71 407	81.89 268	33.71 369	79.71 267	41.66 391	70.37 317	77.58 373
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ET-MVSNet_ETH3D		67.96 237	65.72 266	74.68 110	76.67 253	55.62 134	75.11 249	74.74 303	52.91 306	60.03 355	80.12 304	33.68 370	82.64 199	61.86 195	76.34 220	85.78 149

GA-MVS		65.53 283	63.70 292	71.02 252	70.87 379	48.10 304	70.48 349	74.40 308	56.69 212	64.70 290	76.77 368	33.66 371	81.10 234	55.42 256	70.32 320	83.87 230

LS3D		64.71 294	62.50 312	71.34 240	79.72 137	55.71 129	79.82 118	74.72 304	48.50 379	56.62 398	84.62 193	33.59 372	82.34 207	29.65 469	75.23 241	75.97 393

sam_mvs												33.43 373

PatchT		53.17 420	53.44 416	52.33 455	68.29 428	25.34 498	58.21 452	54.41 466	44.46 427	54.56 425	69.05 452	33.32 374	60.94 445	36.93 422	61.76 421	70.73 456

test20.03		53.87 413	54.02 410	53.41 448	61.47 470	28.11 487	61.30 437	59.21 445	51.34 338	52.09 446	77.43 358	33.29 375	58.55 459	29.76 468	60.27 433	73.58 423

UBG		59.62 365	59.53 352	59.89 402	78.12 190	35.92 448	64.11 419	60.81 441	49.45 363	61.34 342	75.55 391	33.05 376	67.39 416	38.68 410	74.62 246	76.35 391

our_test_3		56.49 390	54.42 404	62.68 384	69.51 405	45.48 336	66.08 394	61.49 437	44.11 432	50.73 454	69.60 449	33.05 376	68.15 406	38.38 412	56.86 445	74.40 416

anonymousdsp		67.00 260	64.82 280	73.57 167	70.09 396	56.13 119	76.35 218	77.35 243	48.43 380	64.99 286	80.84 293	33.01 378	80.34 255	64.66 160	67.64 362	84.23 215

MDTV_nov1_ep13_2view						25.89 496	61.22 438		40.10 459	51.10 449		32.97 379		38.49 411		78.61 359

IB-MVS	56.42 12	65.40 286	62.73 310	73.40 175	74.89 289	52.78 195	73.09 301	75.13 297	55.69 241	58.48 378	73.73 409	32.86 380	86.32 95	50.63 295	70.11 324	81.10 308
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		68.58 218	67.28 230	72.48 199	78.19 186	57.19 103	75.28 244	75.09 298	51.61 328	70.04 166	81.41 279	32.79 381	79.02 293	63.81 170	77.31 203	81.22 303

xiu_mvs_v1_base		68.58 218	67.28 230	72.48 199	78.19 186	57.19 103	75.28 244	75.09 298	51.61 328	70.04 166	81.41 279	32.79 381	79.02 293	63.81 170	77.31 203	81.22 303

xiu_mvs_v1_base_debi		68.58 218	67.28 230	72.48 199	78.19 186	57.19 103	75.28 244	75.09 298	51.61 328	70.04 166	81.41 279	32.79 381	79.02 293	63.81 170	77.31 203	81.22 303

Anonymous20231206		55.10 407	55.30 396	54.48 439	69.81 403	33.94 462	62.91 427	62.13 435	41.08 452	55.18 415	75.65 389	32.75 384	56.59 470	30.32 466	67.86 359	72.91 425

UGNet		68.81 212	67.39 225	73.06 182	78.33 182	54.47 151	79.77 119	75.40 290	60.45 120	63.22 307	84.40 202	32.71 385	80.91 243	51.71 288	80.56 130	83.81 232
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
LuminaMVS		68.24 229	66.82 242	72.51 198	73.46 329	53.60 169	76.23 222	78.88 197	52.78 308	68.08 211	80.13 303	32.70 386	81.41 224	63.16 182	75.97 228	82.53 273

myMVS_eth3d28		60.66 351	61.04 334	59.51 404	77.32 223	31.58 475	63.11 425	63.87 415	59.00 160	60.90 348	78.26 337	32.69 387	66.15 426	36.10 432	78.13 188	80.81 315

SSC-MVS		41.96 450	41.99 449	41.90 474	62.46 466	9.28 516	57.41 459	44.32 493	43.38 436	38.30 491	66.45 466	32.67 388	58.42 460	10.98 506	21.91 500	57.99 481

test-LLR		58.15 379	58.13 369	58.22 418	68.57 420	44.80 341	65.46 402	57.92 450	50.08 355	55.44 410	69.82 445	32.62 389	57.44 464	49.66 303	73.62 262	72.41 435

test0.0.03 1		53.32 419	53.59 415	52.50 454	62.81 464	29.45 482	59.51 447	54.11 467	50.08 355	54.40 427	74.31 403	32.62 389	55.92 473	30.50 464	63.95 392	72.15 440

MDTV_nov1_ep13			57.00 375		72.73 340	38.26 420	65.02 410	64.73 406	44.74 423	55.46 409	72.48 416	32.61 391	70.47 393	37.47 416	67.75 361

testing99		64.05 305	63.29 303	66.34 336	78.17 189	39.76 405	67.33 387	68.00 378	58.60 171	63.03 312	78.10 339	32.57 392	76.94 345	48.22 316	75.58 234	82.34 280

cascas		65.98 277	63.42 299	73.64 163	77.26 225	52.58 201	72.26 319	77.21 246	48.56 376	61.21 344	74.60 401	32.57 392	85.82 111	50.38 297	76.75 215	82.52 275

test_post1							68.67 373				3.64 528	32.39 394	69.49 400	44.17 364

CVMVSNet		59.63 364	59.14 355	61.08 398	74.47 305	38.84 414	75.20 247	68.74 373	31.15 477	58.24 380	76.51 376	32.39 394	68.58 405	49.77 300	65.84 376	75.81 395

testing3-2		62.06 335	62.36 314	61.17 396	79.29 145	30.31 480	64.09 420	63.49 419	63.50 45	62.84 315	82.22 258	32.35 396	69.02 403	40.01 402	73.43 269	84.17 218

ppachtmachnet_test		58.06 380	55.38 395	66.10 344	69.51 405	48.99 286	68.01 380	66.13 395	44.50 426	54.05 430	70.74 433	32.09 397	72.34 381	36.68 426	56.71 448	76.99 385

MIMVSNet		57.35 383	57.07 374	58.22 418	74.21 314	37.18 430	62.46 429	60.88 440	48.88 372	55.29 414	75.99 385	31.68 398	62.04 443	31.87 452	72.35 288	75.43 401

testing11		62.81 320	61.90 320	65.54 353	78.38 177	40.76 395	67.59 384	66.78 389	55.48 247	60.13 352	77.11 362	31.67 399	76.79 348	45.53 350	74.45 248	79.06 352

test_vis1_n_1920		58.86 369	59.06 358	58.25 417	63.76 458	43.14 366	67.49 385	66.36 392	40.22 458	65.89 263	71.95 423	31.04 400	59.75 452	59.94 212	64.90 382	71.85 442

PVSNet_0	43.31 20	47.46 440	45.64 443	52.92 451	67.60 435	44.65 343	54.06 469	54.64 464	41.59 449	46.15 471	58.75 482	30.99 401	58.66 458	32.18 448	24.81 498	55.46 485

gg-mvs-nofinetune		57.86 381	56.43 384	62.18 386	72.62 342	35.35 450	66.57 390	56.33 459	50.65 348	57.64 387	57.10 485	30.65 402	76.36 358	37.38 418	78.88 169	74.82 410

D2MVS		62.30 331	60.29 346	68.34 303	66.46 445	48.42 298	65.70 397	73.42 324	47.71 393	58.16 382	75.02 397	30.51 403	77.71 324	53.96 268	71.68 300	78.90 356

GG-mvs-BLEND				62.34 385	71.36 372	37.04 434	69.20 369	57.33 455		54.73 422	65.48 470	30.37 404	77.82 320	34.82 437	74.93 243	72.17 439

tt0320		58.59 371	56.81 379	63.92 373	75.46 277	41.32 388	68.63 374	64.06 414	47.05 404	56.19 404	74.19 404	30.34 405	71.36 387	39.92 403	55.45 451	79.09 351

MDA-MVSNet-bldmvs		53.87 413	50.81 426	63.05 381	66.25 446	48.58 296	56.93 461	63.82 416	48.09 386	41.22 482	70.48 437	30.34 405	68.00 410	34.24 439	45.92 478	72.57 430

EPMVS		53.96 411	53.69 414	54.79 438	66.12 448	31.96 474	62.34 431	49.05 479	44.42 428	55.54 408	71.33 430	30.22 407	56.70 467	41.65 392	62.54 413	75.71 397

Elysia		70.19 170	68.29 202	75.88 82	74.15 315	54.33 154	78.26 146	83.21 103	55.04 265	67.28 231	83.59 222	30.16 408	86.11 101	63.67 174	79.26 157	87.20 87

StellarMVS		70.19 170	68.29 202	75.88 82	74.15 315	54.33 154	78.26 146	83.21 103	55.04 265	67.28 231	83.59 222	30.16 408	86.11 101	63.67 174	79.26 157	87.20 87

YYNet1		50.73 430	48.96 432	56.03 431	61.10 473	41.78 382	51.94 474	56.44 457	40.94 454	44.84 474	67.80 457	30.08 410	55.08 477	36.77 423	50.71 468	71.22 450

MDA-MVSNet_test_wron		50.71 431	48.95 433	56.00 432	61.17 472	41.84 381	51.90 475	56.45 456	40.96 453	44.79 475	67.84 456	30.04 411	55.07 478	36.71 425	50.69 469	71.11 453

test_cas_vis1_n_1920		56.91 387	56.71 380	57.51 426	59.13 481	45.40 337	63.58 422	61.29 438	36.24 469	67.14 236	71.85 424	29.89 412	56.69 468	57.65 235	63.58 397	70.46 457

Anonymous202405211		66.84 263	65.99 262	69.40 285	80.19 128	42.21 379	71.11 338	71.31 346	58.80 164	67.90 213	86.39 141	29.83 413	79.65 268	49.60 305	78.78 172	86.33 126

ETVMVS		59.51 366	58.81 359	61.58 391	77.46 219	34.87 451	64.94 411	59.35 444	54.06 286	61.08 346	76.67 370	29.54 414	71.87 385	32.16 449	74.07 253	78.01 369

MSDG		61.81 342	59.23 354	69.55 284	72.64 341	52.63 200	70.45 350	75.81 279	51.38 336	53.70 432	76.11 381	29.52 415	81.08 236	37.70 415	65.79 377	74.93 408

CMPMVS	42.80 21	57.81 382	55.97 388	63.32 377	60.98 475	47.38 317	64.66 412	69.50 366	32.06 475	46.83 468	77.80 351	29.50 416	71.36 387	48.68 311	73.75 258	71.21 451
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LTVRE_ROB	55.42 16	63.15 317	61.23 331	68.92 294	76.57 256	47.80 310	59.92 445	76.39 266	54.35 282	58.67 374	82.46 252	29.44 417	81.49 223	42.12 386	71.14 305	77.46 374
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		53.16 421	52.47 418	55.23 435	59.45 479	33.39 466	59.43 448	69.13 370	45.98 414	50.35 457	72.32 417	29.30 418	58.26 461	42.02 389	44.30 480	74.05 420

FE-MVSNET		55.16 406	53.75 413	59.41 405	65.29 452	33.20 467	67.21 388	66.21 394	48.39 382	49.56 460	73.53 411	29.03 419	72.51 378	30.38 465	54.10 458	72.52 431

CHOSEN 280x420		47.83 438	46.36 442	52.24 457	67.37 437	49.78 265	38.91 497	43.11 495	35.00 471	43.27 480	63.30 475	28.95 420	49.19 490	36.53 428	60.80 426	57.76 482

pmmvs-eth3d		58.81 370	56.31 386	66.30 338	67.61 434	52.42 207	72.30 317	64.76 405	43.55 435	54.94 419	74.19 404	28.95 420	72.60 377	43.31 375	57.21 444	73.88 422

dp		51.89 425	51.60 423	52.77 452	68.44 426	32.45 472	62.36 430	54.57 465	44.16 430	49.31 461	67.91 455	28.87 422	56.61 469	33.89 440	54.89 454	69.24 467

FE-MVS		65.91 278	63.33 301	73.63 164	77.36 222	51.95 218	72.62 308	75.81 279	53.70 296	65.31 272	78.96 326	28.81 423	86.39 92	43.93 368	73.48 267	82.55 272

tt0320-xc		58.33 375	56.41 385	64.08 371	75.79 268	41.34 387	68.30 377	62.72 427	47.90 389	56.29 403	74.16 406	28.53 424	71.04 390	41.50 394	52.50 464	79.88 339

testing222		62.29 332	61.31 328	65.25 362	77.87 199	38.53 417	68.34 376	66.31 393	56.37 226	63.15 311	77.58 357	28.47 425	76.18 362	37.04 421	76.65 217	81.05 311

KD-MVS_self_test		55.22 404	53.89 411	59.21 410	57.80 485	27.47 490	57.75 457	74.32 309	47.38 398	50.90 451	70.00 440	28.45 426	70.30 397	40.44 398	57.92 441	79.87 340

0.4-1-1-0.2		58.31 376	55.53 393	66.64 331	67.46 436	42.78 374	64.38 415	70.97 350	47.65 394	53.38 440	59.02 481	28.39 427	78.72 303	44.86 361	63.63 395	78.42 360

blend_shiyan4		61.38 347	59.10 357	68.20 304	68.94 416	44.64 344	70.81 344	76.52 263	51.63 327	57.56 389	69.94 444	28.30 428	79.61 271	47.44 320	60.78 427	80.36 329

jajsoiax		68.25 228	66.45 248	73.66 161	75.62 272	55.49 137	80.82 101	78.51 213	52.33 317	64.33 294	84.11 208	28.28 429	81.81 217	63.48 177	70.62 312	83.67 240

0.4-1-1-0.1		59.29 367	56.70 381	67.07 321	69.35 409	43.16 365	66.59 389	70.87 352	48.59 375	55.11 416	62.25 477	28.22 430	78.92 299	45.49 352	63.79 393	79.14 350

sc_t1		59.76 361	57.84 371	65.54 353	74.87 291	42.95 372	69.61 362	64.16 413	48.90 371	58.68 373	77.12 361	28.19 431	72.35 380	43.75 373	55.28 452	81.31 301

RPSCF		55.80 399	54.22 409	60.53 400	65.13 453	42.91 373	64.30 416	57.62 452	36.84 468	58.05 384	82.28 256	28.01 432	56.24 472	37.14 420	58.61 439	82.44 278

F-COLMAP		63.05 319	60.87 339	69.58 283	76.99 247	53.63 168	78.12 158	76.16 270	47.97 388	52.41 445	81.61 275	27.87 433	78.11 311	40.07 399	66.66 370	77.00 383

K. test v3		60.47 355	57.11 373	70.56 263	73.74 323	48.22 301	75.10 251	62.55 428	58.27 178	53.62 435	76.31 380	27.81 434	81.59 220	47.42 322	39.18 487	81.88 288

UWE-MVS-28		52.25 423	52.35 420	51.93 458	66.99 438	22.79 502	63.48 423	48.31 483	46.78 407	52.73 444	76.11 381	27.78 435	57.82 463	20.58 493	68.41 356	75.17 402

ACMH+	57.40 11	66.12 276	64.06 285	72.30 206	77.79 202	52.83 194	80.39 106	78.03 227	57.30 199	57.47 390	82.55 247	27.68 436	84.17 147	45.54 349	69.78 332	79.90 338

UnsupCasMVSNet_bld		50.07 433	48.87 434	53.66 445	60.97 476	33.67 464	57.62 458	64.56 408	39.47 463	47.38 465	64.02 474	27.47 437	59.32 453	34.69 438	43.68 481	67.98 470

mvs_tets		68.18 231	66.36 254	73.63 164	75.61 273	55.35 141	80.77 102	78.56 211	52.48 316	64.27 296	84.10 209	27.45 438	81.84 216	63.45 178	70.56 314	83.69 239

lessismore_v0				69.91 275	71.42 370	47.80 310		50.90 476		50.39 456	75.56 390	27.43 439	81.33 227	45.91 344	34.10 493	80.59 320

UWE-MVS		60.18 357	59.78 350	61.39 394	77.67 208	33.92 463	69.04 372	63.82 416	48.56 376	64.27 296	77.64 356	27.20 440	70.40 396	33.56 444	76.24 221	79.83 341

ACMH	55.70 15	65.20 289	63.57 294	70.07 271	78.07 192	52.01 216	79.48 127	79.69 179	55.75 240	56.59 399	80.98 287	27.12 441	80.94 240	42.90 382	71.58 301	77.25 380
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		61.65 343	58.80 361	70.20 269	75.80 267	47.22 318	75.59 238	69.68 362	54.61 276	54.11 429	79.26 323	27.07 442	82.96 179	43.27 376	49.79 472	80.41 324

mmtdpeth		60.40 356	59.12 356	64.27 370	69.59 404	48.99 286	70.67 346	70.06 359	54.96 269	62.78 316	73.26 414	27.00 443	67.66 411	58.44 231	45.29 479	76.16 392

PVSNet	50.76 19	58.40 373	57.39 372	61.42 392	75.53 275	44.04 353	61.43 435	63.45 420	47.04 405	56.91 396	73.61 410	27.00 443	64.76 432	39.12 408	72.40 287	75.47 400

OpenMVS_ROB	52.78 18	60.03 358	58.14 368	65.69 352	70.47 385	44.82 340	75.33 242	70.86 353	45.04 421	56.06 405	76.00 383	26.89 445	79.65 268	35.36 436	67.29 365	72.60 429

0.3-1-1-0.015		58.40 373	55.56 392	66.91 323	68.08 430	43.09 367	65.25 408	70.96 351	47.89 391	53.10 442	59.82 480	26.48 446	78.79 301	45.07 359	63.43 399	78.84 357

ADS-MVSNet2		51.33 428	48.76 435	59.07 412	66.02 449	44.60 346	50.90 477	59.76 443	36.90 466	50.74 452	66.18 468	26.38 447	63.11 439	27.17 478	54.76 455	69.50 464

ADS-MVSNet		48.48 437	47.77 438	50.63 460	66.02 449	29.92 481	50.90 477	50.87 477	36.90 466	50.74 452	66.18 468	26.38 447	52.47 484	27.17 478	54.76 455	69.50 464

N_pmnet		39.35 455	40.28 452	36.54 480	63.76 458	1.62 532	49.37 482	0.76 531	34.62 472	43.61 479	66.38 467	26.25 449	42.57 498	26.02 483	51.77 465	65.44 472

MVS-HIRNet		45.52 442	44.48 444	48.65 463	68.49 425	34.05 461	59.41 449	44.50 492	27.03 484	37.96 492	50.47 495	26.16 450	64.10 433	26.74 481	59.52 434	47.82 492

test2506		65.33 287	64.61 281	67.50 313	79.46 143	34.19 460	74.43 268	51.92 471	58.72 166	66.75 243	88.05 83	25.99 451	80.92 242	51.94 284	84.25 80	87.39 77

FMVSNet5		55.86 398	54.93 398	58.66 415	71.05 377	36.35 440	64.18 418	62.48 429	46.76 408	50.66 455	74.73 400	25.80 452	64.04 434	33.11 445	65.57 378	75.59 398

new-patchmatchnet		47.56 439	47.73 439	47.06 464	58.81 483	9.37 515	48.78 483	59.21 445	43.28 437	44.22 477	68.66 454	25.67 453	57.20 466	31.57 459	49.35 473	74.62 414

reproduce_monomvs		62.56 323	61.20 332	66.62 332	70.62 382	44.30 349	70.13 355	73.13 332	54.78 272	61.13 345	76.37 379	25.63 454	75.63 363	58.75 228	60.29 432	79.93 337

MIMVSNet1		55.17 405	54.31 407	57.77 424	70.03 397	32.01 473	65.68 398	64.81 404	49.19 367	46.75 469	76.00 383	25.53 455	64.04 434	28.65 472	62.13 417	77.26 379

PatchMatch-RL		56.25 394	54.55 403	61.32 395	77.06 239	56.07 121	65.57 399	54.10 468	44.13 431	53.49 439	71.27 431	25.20 456	66.78 419	36.52 429	63.66 394	61.12 475

JIA-IIPM		51.56 426	47.68 440	63.21 379	64.61 455	50.73 240	47.71 485	58.77 447	42.90 442	48.46 463	51.72 489	24.97 457	70.24 398	36.06 433	53.89 460	68.64 468

EU-MVSNet		55.61 401	54.41 405	59.19 411	65.41 451	33.42 465	72.44 315	71.91 343	28.81 479	51.27 448	73.87 408	24.76 458	69.08 402	43.04 379	58.20 440	75.06 404

EG-PatchMatch MVS		64.71 294	62.87 307	70.22 267	77.68 207	53.48 172	77.99 163	78.82 198	53.37 300	56.03 406	77.41 359	24.75 459	84.04 151	46.37 338	73.42 270	73.14 424

TESTMET0.1,1		55.28 403	54.90 399	56.42 429	66.56 443	43.67 357	65.46 402	56.27 461	39.18 464	53.83 431	67.44 460	24.21 460	55.46 475	48.04 318	73.11 276	70.13 460

mvsany_test1		39.38 454	38.16 457	43.02 472	49.05 494	34.28 459	44.16 493	25.94 508	22.74 493	46.57 470	62.21 478	23.85 461	41.16 501	33.01 446	35.91 490	53.63 486

COLMAP_ROB	52.97 17	61.27 349	58.81 359	68.64 297	74.63 300	52.51 203	78.42 145	73.30 327	49.92 358	50.96 450	81.51 278	23.06 462	79.40 275	31.63 457	65.85 375	74.01 421
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testgi		51.90 424	52.37 419	50.51 461	60.39 478	23.55 501	58.42 450	58.15 448	49.03 369	51.83 447	79.21 324	22.39 463	55.59 474	29.24 471	62.64 411	72.40 437

DSMNet-mixed		39.30 456	38.72 455	41.03 475	51.22 493	19.66 505	45.53 490	31.35 504	15.83 502	39.80 487	67.42 462	22.19 464	45.13 495	22.43 487	52.69 463	58.31 480

test-mter		56.42 392	55.82 390	58.22 418	68.57 420	44.80 341	65.46 402	57.92 450	39.94 462	55.44 410	69.82 445	21.92 465	57.44 464	49.66 303	73.62 262	72.41 435

KD-MVS_2432*1600		53.45 415	51.50 424	59.30 406	62.82 462	37.14 431	55.33 464	71.79 344	47.34 400	55.09 417	70.52 435	21.91 466	70.45 394	35.72 434	42.97 482	70.31 458

miper_refine_blended		53.45 415	51.50 424	59.30 406	62.82 462	37.14 431	55.33 464	71.79 344	47.34 400	55.09 417	70.52 435	21.91 466	70.45 394	35.72 434	42.97 482	70.31 458

myMVS_eth3d		54.86 409	54.61 402	55.61 433	74.69 298	27.31 491	65.52 400	57.49 453	50.97 345	56.52 400	72.18 418	21.87 468	68.09 407	27.70 476	64.59 387	71.44 448

OurMVSNet-221017-0		61.37 348	58.63 363	69.61 280	72.05 356	48.06 307	73.93 280	72.51 336	47.23 402	54.74 421	80.92 289	21.49 469	81.24 230	48.57 313	56.22 449	79.53 346

testing3		56.54 389	55.92 389	58.41 416	77.52 217	27.93 488	69.72 359	56.36 458	54.75 274	58.63 376	77.80 351	20.88 470	71.75 386	25.31 484	62.25 416	75.53 399

ITE_SJBPF				62.09 387	66.16 447	44.55 348		64.32 409	47.36 399	55.31 413	80.34 299	19.27 471	62.68 441	36.29 431	62.39 414	79.04 353

usedtu_dtu_shiyan2		53.34 418	50.78 427	61.00 399	61.86 469	39.63 406	68.47 375	64.58 407	42.94 441	45.22 473	67.61 459	19.25 472	66.71 420	28.08 474	59.05 438	76.66 387

AllTest		57.08 386	54.65 401	64.39 368	71.44 368	49.03 283	69.92 358	67.30 381	45.97 415	47.16 466	79.77 310	17.47 473	67.56 414	33.65 441	59.16 436	76.57 388

TestCases				64.39 368	71.44 368	49.03 283		67.30 381	45.97 415	47.16 466	79.77 310	17.47 473	67.56 414	33.65 441	59.16 436	76.57 388

mvs5depth		55.64 400	53.81 412	61.11 397	59.39 480	40.98 394	65.89 395	68.28 376	50.21 353	58.11 383	75.42 394	17.03 475	67.63 413	43.79 371	46.21 476	74.73 412

Anonymous20240521		55.30 402	54.41 405	57.96 422	60.92 477	41.73 383	71.09 339	71.06 349	41.18 451	48.65 462	73.31 412	16.93 476	59.25 454	42.54 383	64.01 390	72.90 426

dongtai		34.52 460	34.94 460	33.26 483	61.06 474	16.00 509	52.79 473	23.78 510	40.71 455	39.33 489	48.65 499	16.91 477	48.34 491	12.18 503	19.05 502	35.44 502

test_fmvs1		51.32 429	50.48 429	53.81 444	53.57 487	37.51 428	60.63 444	51.16 473	28.02 483	63.62 303	69.23 451	16.41 478	53.93 480	51.01 292	60.70 428	69.99 461

XVG-ACMP-BASELINE		64.36 301	62.23 316	70.74 258	72.35 351	52.45 206	70.80 345	78.45 217	53.84 292	59.87 358	81.10 284	16.24 479	79.32 277	55.64 254	71.76 297	80.47 321

kuosan		29.62 467	30.82 466	26.02 488	52.99 488	16.22 508	51.09 476	22.71 511	33.91 473	33.99 493	40.85 501	15.89 480	33.11 506	7.59 517	18.37 503	28.72 504

tmp_tt		9.43 481	11.14 482	4.30 505	2.38 533	4.40 521	13.62 509	16.08 514	0.39 524	15.89 507	13.06 521	15.80 481	5.54 522	12.63 502	10.46 509	2.95 521

USDC		56.35 393	54.24 408	62.69 383	64.74 454	40.31 399	65.05 409	73.83 320	43.93 433	47.58 464	77.71 355	15.36 482	75.05 366	38.19 414	61.81 420	72.70 428

test_fmvs1_n		51.37 427	50.35 430	54.42 441	52.85 489	37.71 426	61.16 440	51.93 470	28.15 481	63.81 302	69.73 447	13.72 483	53.95 479	51.16 291	60.65 429	71.59 445

test_vis1_n		49.89 434	48.69 436	53.50 447	53.97 486	37.38 429	61.53 434	47.33 487	28.54 480	59.62 363	67.10 464	13.52 484	52.27 485	49.07 308	57.52 442	70.84 455

EGC-MVSNET		42.47 448	38.48 456	54.46 440	74.33 310	48.73 292	70.33 353	51.10 474	0.03 549	0.18 548	67.78 458	13.28 485	66.49 422	18.91 495	50.36 470	48.15 490

MVStest1		42.65 447	39.29 454	52.71 453	47.26 499	34.58 456	54.41 468	50.84 478	23.35 489	39.31 490	74.08 407	12.57 486	55.09 476	23.32 486	28.47 496	68.47 469

ANet_high		41.38 451	37.47 458	53.11 450	39.73 507	24.45 499	56.94 460	69.69 361	47.65 394	26.04 499	52.32 488	12.44 487	62.38 442	21.80 489	10.61 508	72.49 432

FPMVS		42.18 449	41.11 451	45.39 466	58.03 484	41.01 392	49.50 481	53.81 469	30.07 478	33.71 494	64.03 472	11.69 488	52.08 487	14.01 499	55.11 453	43.09 494

TinyColmap		54.14 410	51.72 422	61.40 393	66.84 441	41.97 380	66.52 391	68.51 374	44.81 422	42.69 481	75.77 388	11.66 489	72.94 375	31.96 451	56.77 447	69.27 466

test_fmvs2		48.69 436	47.49 441	52.29 456	48.63 496	33.06 469	57.76 456	48.05 485	25.71 487	59.76 361	69.60 449	11.57 490	52.23 486	49.45 306	56.86 445	71.58 446

TDRefinement		53.44 417	50.72 428	61.60 390	64.31 457	46.96 320	70.89 341	65.27 402	41.78 446	44.61 476	77.98 341	11.52 491	66.36 423	28.57 473	51.59 466	71.49 447

ambc				65.13 363	63.72 460	37.07 433	47.66 486	78.78 201		54.37 428	71.42 426	11.24 492	80.94 240	45.64 347	53.85 461	77.38 376

test_vis1_rt		41.35 452	39.45 453	47.03 465	46.65 500	37.86 423	47.76 484	38.65 498	23.10 491	44.21 478	51.22 493	11.20 493	44.08 496	39.27 407	53.02 462	59.14 478

pmmvs3		44.92 443	41.95 450	53.86 443	52.58 491	43.55 358	62.11 432	46.90 489	26.05 486	40.63 483	60.19 479	11.08 494	57.91 462	31.83 456	46.15 477	60.11 476

new_pmnet		34.13 461	34.29 462	33.64 482	52.63 490	18.23 507	44.43 492	33.90 503	22.81 492	30.89 496	53.18 487	10.48 495	35.72 505	20.77 492	39.51 486	46.98 493

LF4IMVS		42.95 446	42.26 448	45.04 467	48.30 497	32.50 471	54.80 466	48.49 481	28.03 482	40.51 484	70.16 438	9.24 496	43.89 497	31.63 457	49.18 474	58.72 479

PM-MVS		52.33 422	50.19 431	58.75 414	62.10 467	45.14 339	65.75 396	40.38 497	43.60 434	53.52 437	72.65 415	9.16 497	65.87 428	50.41 296	54.18 457	65.24 473

ttmdpeth		45.56 441	42.95 446	53.39 449	52.33 492	29.15 483	57.77 455	48.20 484	31.81 476	49.86 459	77.21 360	8.69 498	59.16 455	27.31 477	33.40 494	71.84 443

EMVS		22.97 470	21.84 474	26.36 487	40.20 506	19.53 506	41.95 495	34.64 502	17.09 499	9.73 516	22.83 515	7.29 499	42.22 500	9.18 512	13.66 506	17.32 510

E-PMN		23.77 469	22.73 473	26.90 486	42.02 503	20.67 504	42.66 494	35.70 501	17.43 498	10.28 515	25.05 513	6.42 500	42.39 499	10.28 509	14.71 505	17.63 509

test_method		19.68 474	18.10 477	24.41 490	13.68 519	3.11 527	12.06 511	42.37 496	2.00 517	11.97 511	36.38 504	5.77 501	29.35 509	15.06 497	23.65 499	40.76 498

mvsany_test3		32.62 462	30.57 467	38.77 478	36.16 510	24.20 500	38.10 498	20.63 512	19.14 497	40.36 486	57.43 484	5.06 502	36.63 504	29.59 470	28.66 495	55.49 484

test_f		31.86 464	31.05 465	34.28 481	32.33 513	21.86 503	32.34 500	30.46 505	16.02 501	39.78 488	55.45 486	4.80 503	32.36 507	30.61 463	37.66 489	48.64 488

Gipuma		34.77 459	31.91 464	43.33 471	62.05 468	37.87 422	20.39 504	67.03 386	23.23 490	18.41 506	25.84 512	4.24 504	62.73 440	14.71 498	51.32 467	29.38 503
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvs3		44.30 444	42.55 447	49.55 462	42.83 501	27.15 493	53.03 471	44.93 491	22.03 495	53.69 434	64.94 471	4.21 505	49.63 489	47.47 319	49.82 471	71.88 441

PMMVS2		27.40 468	25.91 471	31.87 485	39.46 508	6.57 519	31.17 501	28.52 506	23.96 488	20.45 505	48.94 498	4.20 506	37.94 502	16.51 496	19.97 501	51.09 487

LCM-MVSNet		40.30 453	35.88 459	53.57 446	42.24 502	29.15 483	45.21 491	60.53 442	22.23 494	28.02 497	50.98 494	3.72 507	61.78 444	31.22 462	38.76 488	69.78 463

DeepMVS_CX				12.03 495	17.97 516	10.91 513		10.60 515	7.46 509	11.07 513	28.36 511	3.28 508	11.29 515	8.01 514	9.74 510	13.89 514

APD_test1		37.39 457	34.94 460	44.72 470	48.88 495	33.19 468	52.95 472	44.00 494	19.49 496	27.28 498	58.59 483	3.18 509	52.84 483	18.92 494	41.17 485	48.14 491

PMVS	28.69 22	36.22 458	33.29 463	45.02 468	36.82 509	35.98 446	54.68 467	48.74 480	26.31 485	21.02 504	51.61 491	2.88 510	60.10 450	9.99 510	47.58 475	38.99 500
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		32.09 463	30.20 468	37.76 479	35.36 511	27.48 489	40.60 496	28.29 507	16.69 500	32.52 495	40.53 503	1.96 511	37.40 503	33.64 443	42.21 484	48.39 489

MVE	17.77 23	21.41 471	17.77 478	32.34 484	34.34 512	25.44 497	16.11 506	24.11 509	11.19 506	13.22 509	31.92 507	1.58 512	30.95 508	10.47 508	17.03 504	40.62 499
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		31.46 465	28.89 469	39.16 476	41.99 504	28.78 485	46.45 487	37.56 499	14.28 503	21.10 502	48.96 496	1.48 513	47.11 492	13.63 500	34.56 491	41.60 496

APD_test2		31.46 465	28.89 469	39.16 476	41.99 504	28.78 485	46.45 487	37.56 499	14.28 503	21.10 502	48.96 496	1.48 513	47.11 492	13.63 500	34.56 491	41.60 496

ArgMatch-Sym		21.00 472	19.89 475	24.35 491	23.32 514	15.10 510	32.50 499	4.90 517	11.83 505	24.09 500	51.35 492	0.56 515	19.55 511	21.24 490	9.18 511	38.40 501

ArgMatch-SfM		20.82 473	19.10 476	25.97 489	21.54 515	13.77 511	29.84 503	6.08 516	9.69 507	22.36 501	51.71 490	0.53 516	21.69 510	20.98 491	9.18 511	42.43 495

wuyk23d		13.32 477	12.52 480	15.71 493	47.54 498	26.27 495	31.06 502	1.98 521	4.93 512	5.18 522	1.94 535	0.45 517	18.54 512	6.81 518	12.83 507	2.33 522

PDCNetPlus		9.23 482	8.89 485	10.23 498	13.70 518	3.70 523	12.27 510	1.51 523	3.98 513	6.73 520	29.50 510	0.24 518	8.07 519	7.83 515	4.30 516	18.93 507

DenseAffine		14.16 476	13.16 479	17.15 492	17.01 517	8.89 517	19.68 505	2.17 520	7.89 508	15.00 508	40.64 502	0.19 519	15.28 513	11.16 505	4.69 515	27.27 505

RoMa-SfM		11.96 478	11.39 481	13.68 494	10.24 521	6.80 518	15.83 507	1.33 524	6.34 510	13.06 510	41.41 500	0.16 520	12.72 514	10.58 507	3.56 517	21.52 506

LoFTR		9.45 480	9.00 484	10.79 497	10.22 522	4.31 522	11.11 512	4.11 518	2.40 516	10.53 514	30.89 508	0.13 521	10.75 516	3.12 520	8.52 513	17.31 511

ALIKED-LG		2.35 495	2.54 498	1.78 508	5.54 526	1.79 529	3.81 517	0.96 528	0.33 525	1.86 527	7.18 522	0.13 521	1.60 527	0.20 533	2.81 519	1.94 523

RoMa-HiRes		8.28 483	8.27 487	8.28 499	6.12 525	3.67 524	10.07 514	0.74 532	3.93 514	9.17 517	34.46 506	0.12 523	7.12 520	7.80 516	2.05 523	14.04 513

DKM		10.33 479	10.10 483	11.02 496	10.54 520	5.43 520	14.18 508	1.03 527	4.97 511	11.74 512	36.09 505	0.11 524	9.09 517	9.38 511	2.85 518	18.53 508

SP-DiffGlue		0.98 499	1.05 502	0.75 515	0.81 553	0.40 543	1.24 528	0.37 535	0.19 528	1.26 532	3.80 527	0.11 524	0.34 537	0.51 526	1.18 529	1.52 528

MASt3R-SfM		3.33 493	3.70 494	2.21 507	2.02 537	1.04 535	3.52 520	1.05 526	0.67 522	4.93 523	16.68 517	0.10 526	1.50 529	2.06 522	2.29 522	4.09 520

ALIKED-NN		1.96 497	2.12 500	1.48 510	4.72 528	1.65 530	3.19 523	0.77 529	0.23 527	1.43 530	5.87 525	0.10 526	1.37 530	0.16 535	2.61 521	1.42 530

SP-SuperGlue		0.93 501	0.98 504	0.77 512	2.54 532	0.38 544	1.70 525	0.34 537	0.17 529	0.52 533	2.13 532	0.10 526	0.36 536	0.26 529	1.10 531	1.57 527

SP-LightGlue		0.94 500	0.99 503	0.78 511	2.60 531	0.38 544	1.71 524	0.34 537	0.17 529	0.50 534	2.14 531	0.09 529	0.38 534	0.26 529	1.13 530	1.59 525

ALIKED-MNN		2.09 496	2.23 499	1.67 509	5.15 527	1.82 528	3.53 519	0.77 529	0.25 526	1.45 529	6.03 524	0.09 529	1.52 528	0.17 534	2.64 520	1.66 524

DKM-HiRes		7.91 484	7.93 488	7.83 500	7.35 524	3.58 525	10.03 515	0.66 533	3.58 515	9.05 518	30.62 509	0.08 531	5.66 521	8.09 513	1.91 524	14.26 512

SP-NN		0.85 504	0.90 507	0.73 516	2.22 536	0.33 550	1.63 527	0.31 540	0.14 532	0.47 536	1.97 534	0.08 531	0.38 534	0.25 531	1.01 534	1.47 529

GLUNet-SfM		4.33 490	3.64 495	6.41 502	3.38 529	1.65 530	3.23 522	1.54 522	0.66 523	6.36 521	15.13 520	0.08 531	5.54 522	0.94 525	1.44 527	12.05 515

MatchFormer		7.03 485	6.96 489	7.26 501	7.64 523	3.36 526	10.21 513	3.04 519	1.31 518	9.02 519	22.94 514	0.08 531	8.15 518	1.46 524	6.91 514	10.26 516

SP-MNN		0.89 502	0.93 506	0.77 512	2.32 535	0.34 548	1.68 526	0.33 539	0.13 533	0.49 535	2.07 533	0.08 531	0.39 533	0.25 531	1.07 533	1.58 526

XFeat-MNN		1.07 498	1.17 501	0.77 512	0.52 554	0.31 551	1.15 529	0.41 534	0.15 531	1.62 528	4.35 526	0.07 536	0.77 531	0.38 527	1.88 525	1.22 531

XFeat-NN		0.87 503	0.97 505	0.59 517	0.48 555	0.24 554	0.94 530	0.29 541	0.12 534	1.41 531	3.45 530	0.06 537	0.56 532	0.29 528	1.65 526	0.95 532

ELoFTR		4.04 491	3.55 496	5.50 503	2.33 534	1.25 534	3.58 518	1.18 525	0.90 520	4.23 525	16.28 518	0.03 538	5.46 524	1.95 523	1.42 528	9.81 517

SIFT-UM-Cal		0.41 515	0.46 517	0.28 528	1.35 546	0.29 552	0.57 540	0.08 553	0.09 538	0.20 546	1.10 545	0.02 539	0.23 547	0.03 544	0.68 545	0.30 545

SIFT-NCM-Cal		0.51 508	0.55 511	0.38 521	1.66 541	0.45 540	0.75 534	0.12 546	0.09 538	0.21 545	1.18 543	0.02 539	0.27 540	0.03 544	0.89 538	0.43 539

SIFT-CM-Cal		0.42 514	0.46 517	0.31 527	1.40 545	0.35 547	0.56 541	0.09 552	0.09 538	0.20 546	1.09 546	0.02 539	0.23 547	0.03 544	0.66 546	0.34 543

SIFT-NN-UMatch		0.48 510	0.52 513	0.36 523	1.27 548	0.36 546	0.75 534	0.12 546	0.10 535	0.25 542	1.29 538	0.02 539	0.26 542	0.04 536	0.85 539	0.44 537

SIFT-NN-NCMNet		0.53 507	0.58 510	0.40 520	1.60 542	0.49 539	0.80 533	0.15 545	0.09 538	0.28 540	1.29 538	0.02 539	0.27 540	0.04 536	0.94 536	0.44 537

SIFT-NN-CMatch		0.49 509	0.53 512	0.38 521	1.35 546	0.41 542	0.70 536	0.12 546	0.09 538	0.30 538	1.28 540	0.02 539	0.26 542	0.04 536	0.83 540	0.47 535

SIFT-NN-PointCN		0.44 513	0.47 516	0.33 525	1.17 549	0.29 552	0.64 538	0.11 549	0.09 538	0.25 542	1.14 544	0.02 539	0.25 544	0.03 544	0.78 541	0.46 536

SIFT-NN		0.60 505	0.65 508	0.45 518	1.90 539	0.55 537	0.90 531	0.16 543	0.10 535	0.34 537	1.43 536	0.02 539	0.28 538	0.04 536	0.95 535	0.50 533

SIFT-UMatch		0.45 512	0.50 515	0.32 526	1.46 544	0.34 548	0.66 537	0.10 551	0.09 538	0.22 544	1.19 542	0.02 539	0.25 544	0.04 536	0.73 543	0.36 542

SIFT-ConvMatch		0.48 510	0.52 513	0.35 524	1.51 543	0.42 541	0.64 538	0.11 549	0.09 538	0.26 541	1.24 541	0.02 539	0.25 544	0.04 536	0.76 542	0.38 540

SIFT-MNN		0.56 506	0.61 509	0.43 519	1.75 540	0.50 538	0.82 532	0.16 543	0.10 535	0.30 538	1.38 537	0.02 539	0.28 538	0.04 536	0.92 537	0.50 533

PMatch-Up-SfM		3.14 494	3.26 497	2.81 506	1.97 538	1.00 536	3.35 521	0.23 542	0.79 521	3.44 526	16.19 519	0.01 550	2.11 526	2.62 521	0.70 544	5.32 519

PMatch-SfM		4.42 489	4.43 493	4.39 504	2.90 530	1.50 533	4.85 516	0.36 536	1.17 519	4.73 524	20.99 516	0.01 550	3.26 525	3.74 519	1.10 531	8.40 518

SIFT-PCN-Cal		0.36 516	0.39 519	0.26 529	1.16 550	0.21 555	0.46 543	0.07 555	0.08 546	0.17 549	0.92 547	0.01 550	0.20 550	0.03 544	0.59 548	0.37 541

SIFT-NCMNet		0.30 518	0.33 521	0.19 531	1.04 552	0.18 557	0.39 544	0.05 556	0.08 546	0.14 551	0.77 549	0.01 550	0.16 551	0.02 551	0.49 549	0.22 546

SIFT-PointCN		0.36 516	0.39 519	0.25 530	1.14 551	0.21 555	0.50 542	0.08 553	0.08 546	0.17 549	0.89 548	0.01 550	0.21 549	0.03 544	0.60 547	0.34 543

test123		4.73 487	6.30 490	0.02 532	0.01 556	0.01 558	56.36 462	0.00 557	0.01 550	0.04 552	0.21 551	0.01 550	0.00 552	0.03 544	0.00 550	0.04 547

mmdepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

uanet_test		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

testmvs		4.52 488	6.03 491	0.01 533	0.01 556	0.00 559	53.86 470	0.00 557	0.01 550	0.04 552	0.27 550	0.00 556	0.00 552	0.04 536	0.00 550	0.03 548

ab-mvs-re		6.49 486	8.65 486	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	77.89 348	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 559	0.00 545	0.00 557	0.00 552	0.00 554	0.00 552	0.00 556	0.00 552	0.00 552	0.00 550	0.00 549

MED-MVS test				79.09 23	85.30 51	59.25 64	86.84 11	85.86 24	60.95 107	83.65 12	90.57 27		89.91 16	77.02 35	89.43 24	88.10 45

WAC-MVS						27.31 491								27.77 475

FOURS1					86.12 38	60.82 37	88.18 1	83.61 85	60.87 109	81.50 21

MSC_two_6792asdad				79.95 4	87.24 14	61.04 31		85.62 31					90.96 1	79.31 10	90.65 8	87.85 55

No_MVS				79.95 4	87.24 14	61.04 31		85.62 31					90.96 1	79.31 10	90.65 8	87.85 55

eth-test2					0.00 558

eth-test					0.00 558

IU-MVS					87.77 4	59.15 69		85.53 33	53.93 289	84.64 3				79.07 13	90.87 5	88.37 34

save fliter					86.17 35	61.30 28	83.98 58	79.66 181	59.00 160

test_0728_SECOND				79.19 16	87.82 3	59.11 72	87.85 5	87.15 3					90.84 3	78.66 18	90.61 11	87.62 66

GSMVS																78.05 365

test_part2					87.58 9	60.47 42				83.42 14

MTGPA								80.97 160

MTMP							86.03 23	17.08 513

gm-plane-assit					71.40 371	41.72 385			48.85 373		73.31 412		82.48 205	48.90 310

test9_res														75.28 55	88.31 36	83.81 232

agg_prior2														73.09 73	87.93 44	84.33 210

agg_prior					85.04 55	59.96 50		81.04 158		74.68 76			84.04 151

test_prior4						62.51 14	82.08 87

test_prior				76.69 67	84.20 67	57.27 100		84.88 46					86.43 91			86.38 119

旧先验2							76.08 226		45.32 420	76.55 49			65.56 429	58.75 228

新几何2							76.12 224

无先验							79.66 123	74.30 311	48.40 381				80.78 247	53.62 270		79.03 354

原ACMM2							79.02 131

testdata2													72.18 384	46.95 335

testdata1							72.65 306		60.50 119

plane_prior7					81.41 103	55.96 123

plane_prior5								84.01 60					87.21 65	68.16 113	80.58 128	84.65 201

plane_prior4											86.10 151

plane_prior3						56.09 120			63.92 39	69.27 184

plane_prior2							84.22 51		64.52 28

plane_prior1					81.27 108

plane_prior						56.31 114	83.58 64		63.19 56						80.48 131

n2								0.00 557

nn								0.00 557

door-mid								47.19 488

test11								83.47 89

door								47.60 486

HQP5-MVS						54.94 145

HQP-NCC					80.66 117		82.31 82		62.10 83	67.85 216

ACMP_Plane					80.66 117		82.31 82		62.10 83	67.85 216

BP-MVS														67.04 135

HQP4-MVS										67.85 216			86.93 73			84.32 211

HQP3-MVS								83.90 65							80.35 133

NP-MVS					80.98 113	56.05 122					85.54 174

ACMMP++_ref															74.07 253

ACMMP++															72.16 294

High-resolution multi-view benchmark