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.

TestfortrainingZip				97.22 3	99.48 2	91.93 7	98.35 58	97.26 25	85.61 190	99.54 1	99.26 1	91.36 5	99.98 2		96.55 118	99.73 3

IU-MVS					99.03 21	85.34 69		96.86 63	92.05 43	98.74 2				98.15 23	98.97 17	99.42 14

fmvsm_s_conf0.5_n_6		94.17 40	94.70 31	92.58 138	93.50 229	81.20 195	99.08 22	96.48 124	92.24 37	98.62 3	98.39 48	78.58 117	99.72 60	98.08 27	97.36 86	96.81 225

fmvsm_l_conf0.5_n_9		94.91 17	95.60 14	92.84 120	95.20 159	80.55 226	99.45 2	96.36 142	95.17 4	98.48 4	98.55 30	80.53 85	99.78 40	98.87 7	97.79 71	98.19 88

fmvsm_l_mol_unc0.5_1		96.23 2	96.47 3	95.50 17	94.71 178	88.70 16	99.47 1	95.70 199	95.05 7	98.42 5	98.85 11	89.10 15	99.77 44	98.76 10	98.14 58	98.02 102

PC_three_1452									91.12 53	98.33 6	98.42 46	92.51 2	99.81 29	98.96 6	99.37 1	99.70 4

fmvsm_l_conf0.5_n		94.89 19	95.24 21	93.86 62	94.42 194	84.61 93	99.13 16	96.15 161	92.06 41	97.92 7	98.52 36	84.52 48	99.74 55	98.76 10	95.67 138	97.22 190

SMA-MVS		94.70 25	94.68 32	94.76 32	98.02 66	85.94 51	97.47 125	96.77 76	85.32 199	97.92 7	98.70 25	83.09 67	99.84 19	95.79 64	99.08 10	98.49 66
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
fmvsm_s_conf0.5_n_10		94.36 34	94.73 30	93.23 98	95.19 160	82.87 133	99.18 10	96.39 135	93.97 19	97.91 9	98.53 34	75.88 178	99.82 25	98.58 12	96.95 103	97.00 211

fmvsm_l_conf0.5_n_a		94.91 17	95.30 20	93.72 72	94.50 190	84.30 100	99.14 15	95.99 174	91.94 44	97.91 9	98.60 28	84.78 45	99.77 44	98.84 8	96.03 131	97.08 208

fmvsm_s_conf0.5_n_8		94.52 30	95.04 25	92.96 112	95.15 164	81.14 197	99.09 21	96.66 94	95.53 3	97.84 11	98.71 24	76.33 165	99.81 29	99.24 1	96.85 110	97.92 116

SED-MVS		95.88 6	96.22 5	94.87 28	99.03 21	85.03 84	99.12 17	96.78 70	88.72 87	97.79 12	98.91 4	88.48 20	99.82 25	98.15 23	98.97 17	99.74 1

test_241102_ONE					99.03 21	85.03 84		96.78 70	88.72 87	97.79 12	98.90 7	88.48 20	99.82 25

fmvsm_s_conf0.5_n_9		94.52 30	95.22 22	92.41 149	95.79 136	78.61 300	98.73 39	96.00 173	94.91 9	97.73 14	98.73 23	79.09 107	99.79 37	99.14 4	96.86 108	98.83 46

DVP-MVS++		96.05 5	96.41 4	94.96 27	99.05 15	85.34 69	98.13 73	96.77 76	88.38 95	97.70 15	98.77 18	92.06 3	99.84 19	97.47 43	99.37 1	99.70 4

test_241102_TWO								96.78 70	88.72 87	97.70 15	98.91 4	87.86 25	99.82 25	98.15 23	99.00 15	99.47 10

fmvsm_s_conf0.5_n_11		94.41 33	95.19 23	92.09 173	95.65 140	80.91 213	99.23 8	94.85 253	94.92 8	97.68 17	98.82 14	79.31 101	99.78 40	98.83 9	97.38 85	95.60 269

patch_mono-2		95.14 15	96.08 8	92.33 155	98.44 50	77.84 330	98.43 53	97.21 27	92.58 30	97.68 17	97.65 100	86.88 30	99.83 23	98.25 19	97.60 76	99.33 19

test0726					99.05 15	85.18 75	99.11 20	96.78 70	88.75 85	97.65 19	98.91 4	87.69 26

fmvsm_s_conf0.5_n_3		93.95 46	94.53 34	92.20 167	94.41 195	80.04 250	98.90 34	95.96 178	94.53 13	97.63 20	98.58 29	75.95 175	99.79 37	98.25 19	96.60 116	96.77 228

fmvsm_l_conf0.5_n_3		94.61 26	94.92 28	93.68 76	94.52 185	82.80 135	99.33 3	96.37 140	95.08 6	97.59 21	98.48 40	77.40 138	99.79 37	98.28 17	97.21 91	98.44 70

TSAR-MVS + MP.		94.79 24	95.17 24	93.64 78	97.66 78	84.10 103	95.85 283	96.42 130	91.26 51	97.49 22	96.80 145	86.50 32	98.49 158	95.54 69	99.03 13	98.33 75
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.5_n_4		93.59 52	94.32 41	91.41 221	93.89 213	79.24 273	98.89 35	96.53 116	92.82 28	97.37 23	98.47 41	77.21 146	99.78 40	98.11 26	95.59 140	95.21 284

test_fmvsm_n_1920		94.81 23	95.60 14	92.45 144	95.29 155	80.96 210	99.29 5	97.21 27	94.50 14	97.29 24	98.44 43	82.15 72	99.78 40	98.56 13	97.68 74	96.61 235

RA-MVS			96.03 10		99.29 7	81.77 177	98.15 69	96.88 60	91.29 50	97.13 25	99.12 3	85.84 38	99.69 67	97.92 30	98.70 33

MSP-MVS		95.62 9	96.54 1	92.86 117	98.31 55	80.10 248	97.42 132	96.78 70	92.20 38	97.11 26	98.29 55	93.46 1	99.10 125	96.01 60	99.30 5	99.38 15
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
MGCNet		95.58 11	95.44 19	96.01 11	97.63 79	89.26 13	99.27 6	96.59 105	94.71 10	97.08 27	97.99 76	78.69 115	99.86 15	99.15 3	97.85 68	98.91 43

fmvsm_s_conf0.5_n_2		92.97 66	93.38 64	91.73 203	94.10 207	80.64 221	98.96 31	95.88 188	94.09 17	97.05 28	98.40 47	68.92 291	99.80 33	98.53 14	94.50 153	94.74 296

aaatest				94.20 53	99.06 12	83.70 112	98.35 58	97.14 32	87.45 126	97.03 29	98.90 7		99.96 4	97.78 38	98.60 37	98.94 40

MED-MVS		95.59 10	96.05 9	94.21 50	99.06 12	83.70 112	98.35 58	97.14 32	87.65 120	97.03 29	98.83 12	89.87 13	99.96 4	97.78 38	98.71 31	98.97 38

fmvsm_s_conf0.5_n_a		93.34 59	93.71 52	92.22 164	93.38 232	81.71 181	98.86 36	96.98 47	91.64 45	96.85 31	98.55 30	75.58 185	99.77 44	97.88 34	93.68 168	95.18 285

CNVR-MVS		96.30 1	96.54 1	95.55 16	99.31 6	87.69 27	99.06 24	97.12 36	94.66 11	96.79 32	98.78 17	86.42 33	99.95 6	97.59 42	99.18 7	99.00 35

DVP-MVS		95.58 11	95.91 12	94.57 38	99.05 15	85.18 75	99.06 24	96.46 125	88.75 85	96.69 33	98.76 20	87.69 26	99.76 47	97.90 32	98.85 21	98.77 49
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
test_0728_THIRD									88.38 95	96.69 33	98.76 20	89.64 14	99.76 47	97.47 43	98.84 23	99.38 15

SD-MVS		94.84 21	95.02 27	94.29 45	97.87 71	84.61 93	97.76 101	96.19 159	89.59 77	96.66 35	98.17 63	84.33 50	99.60 79	96.09 59	98.50 43	98.66 58
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
MM		95.85 7	95.74 13	96.15 9	96.34 112	89.50 10	99.18 10	98.10 8	95.68 1	96.64 36	97.92 82	80.72 82	99.80 33	99.16 2	97.96 64	99.15 28

fmvsm_s_conf0.1_n_a		92.38 95	92.49 85	92.06 177	88.08 401	81.62 186	97.97 85	96.01 172	90.62 61	96.58 37	98.33 54	74.09 216	99.71 63	97.23 48	93.46 173	94.86 292

test_one_0601					98.91 25	84.56 95		96.70 87	88.06 105	96.57 38	98.77 18	88.04 24

DPE-MVS		95.32 13	95.55 16	94.64 36	98.79 30	84.87 90	97.77 99	96.74 81	86.11 172	96.54 39	98.89 10	88.39 22	99.74 55	97.67 41	99.05 12	99.31 21
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DPM-MVS		96.21 3	95.53 17	98.26 1	96.26 115	95.09 1	99.15 13	96.98 47	93.39 24	96.45 40	98.79 16	90.17 10	99.99 1	89.33 182	99.25 6	99.70 4

fmvsm_s_conf0.5_n		93.69 50	94.13 47	92.34 153	94.56 182	82.01 161	99.07 23	97.13 34	92.09 39	96.25 41	98.53 34	76.47 160	99.80 33	98.39 15	94.71 149	95.22 283

PS-MVSNAJ		94.17 40	93.52 59	96.10 10	95.65 140	92.35 2	98.21 67	95.79 194	92.42 33	96.24 42	98.18 60	71.04 267	99.17 119	96.77 55	97.39 84	96.79 226

fmvsm_s_conf0.1_n_2		92.26 99	92.48 86	91.60 211	92.29 289	80.55 226	98.73 39	94.33 302	93.80 21	96.18 43	98.11 67	66.93 310	99.75 52	98.19 22	93.74 167	94.50 303

旧先验2							96.97 175		74.06 419	96.10 44			97.76 202	88.38 203

test_part2					98.90 26	85.14 81				96.07 45

fmvsm_s_conf0.1_n		92.93 68	93.16 68	92.24 161	90.52 352	81.92 167	98.42 55	96.24 153	91.17 52	96.02 46	98.35 53	75.34 196	99.74 55	97.84 36	94.58 151	95.05 288

xiu_mvs_v2_base		93.92 47	93.26 65	95.91 12	95.07 167	92.02 6	98.19 68	95.68 201	92.06 41	96.01 47	98.14 65	70.83 272	98.96 133	96.74 57	96.57 117	96.76 230

TestfortrainingZip a		94.24 39	94.19 45	94.40 42	99.06 12	84.33 98	98.35 58	96.81 69	87.65 120	95.97 48	98.83 12	84.06 56	99.89 11	91.98 130	95.03 145	98.97 38

BridgeMVS		94.60 28	94.30 42	95.48 18	96.45 109	88.82 15	96.33 234	95.58 206	91.12 53	95.84 49	93.87 268	83.47 63	98.37 168	97.26 47	98.81 24	99.24 24

HPM-MVS++		95.32 13	95.48 18	94.85 29	98.62 41	86.04 47	97.81 96	96.93 55	92.45 32	95.69 50	98.50 37	85.38 39	99.85 17	94.75 81	99.18 7	98.65 59

fmvsm_s_conf0.5_n_5		93.57 54	93.75 50	93.01 109	92.87 258	82.73 136	98.93 33	95.90 186	90.96 58	95.61 51	98.39 48	76.57 158	99.63 76	98.32 16	96.24 123	96.68 234

NCCC		95.63 8	95.94 11	94.69 35	99.21 8	85.15 80	99.16 12	96.96 51	94.11 16	95.59 52	98.64 27	85.07 42	99.91 8	95.61 67	99.10 9	99.00 35

PRO-TEST		93.79 49	93.63 54	94.29 45	95.54 145	86.59 40	97.30 142	95.42 222	92.49 31	95.39 53	97.33 116	75.72 181	97.16 272	97.19 50	96.29 121	99.11 29

EPNet		94.06 44	94.15 46	93.76 66	97.27 100	84.35 97	98.29 64	97.64 14	94.57 12	95.36 54	96.88 140	79.96 96	99.12 124	91.30 136	96.11 128	97.82 127
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
aaEdge-Enhanced		94.82 22	95.04 25	94.17 54	99.17 10	83.70 112	97.66 108	97.22 26	85.79 186	95.34 55	98.90 7	84.89 43	99.86 15	97.78 38	98.60 37	98.94 40

CANet		94.89 19	94.64 33	95.63 14	97.55 85	88.12 20	99.06 24	96.39 135	94.07 18	95.34 55	97.80 91	76.83 154	99.87 13	97.08 52	97.64 75	98.89 44

test-260524					99.01 24	85.87 53		96.82 68		95.25 57		86.23 35	99.92 7	97.87 35	98.71 31

fmvsm_s_conf0.5_n_7		92.88 70	93.82 49	90.08 273	92.79 262	76.45 361	98.54 49	96.74 81	92.28 36	95.22 58	98.49 38	74.91 203	98.15 179	98.28 17	97.13 95	95.63 267

test_fmvsmconf_n		93.99 45	94.36 40	92.86 117	92.82 259	81.12 198	99.26 7	96.37 140	93.47 23	95.16 59	98.21 58	79.00 108	99.64 74	98.21 21	96.73 114	97.83 125

TEST9					98.64 38	83.71 110	97.82 94	96.65 95	84.29 241	95.16 59	98.09 69	84.39 49	99.36 101

train_agg		94.28 36	94.45 37	93.74 68	98.64 38	83.71 110	97.82 94	96.65 95	84.50 231	95.16 59	98.09 69	84.33 50	99.36 101	95.91 63	98.96 19	98.16 91

test_8					98.63 40	83.64 116	97.81 96	96.63 100	84.50 231	95.10 62	98.11 67	84.33 50	99.23 109

DeepPCF-MVS	89.82 1	94.61 26	96.17 6	89.91 282	97.09 103	70.21 434	98.99 30	96.69 89	95.57 2	95.08 63	99.23 2	86.40 34	99.87 13	97.84 36	98.66 35	99.65 7

SF-MVS		94.17 40	94.05 48	94.55 39	97.56 84	85.95 49	97.73 103	96.43 129	84.02 248	95.07 64	98.74 22	82.93 68	99.38 98	95.42 72	98.51 41	98.32 77

APDe-MVS		94.56 29	94.75 29	93.96 60	98.84 29	83.40 121	98.04 81	96.41 131	85.79 186	95.00 65	98.28 56	84.32 53	99.18 118	97.35 46	98.77 28	99.28 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVSFormer		91.36 124	90.57 131	93.73 70	93.00 246	88.08 21	94.80 336	94.48 282	80.74 323	94.90 66	97.13 128	78.84 111	95.10 391	83.77 248	97.46 79	98.02 102

lupinMVS		93.87 48	93.58 57	94.75 33	93.00 246	88.08 21	99.15 13	95.50 213	91.03 56	94.90 66	97.66 96	78.84 111	97.56 219	94.64 84	97.46 79	98.62 61

SPE-MVS-test		92.98 65	93.67 53	90.90 246	96.52 108	76.87 353	98.68 42	94.73 260	90.36 68	94.84 68	97.89 86	77.94 127	97.15 277	94.28 89	97.80 70	98.70 57

9.14			94.26 44		98.10 64		98.14 70	96.52 117	84.74 220	94.83 69	98.80 15	82.80 70	99.37 100	95.95 62	98.42 47

testdata				90.13 272	95.92 129	74.17 391		96.49 123	73.49 424	94.82 70	97.99 76	78.80 113	97.93 189	83.53 256	97.52 78	98.29 81

lecture		93.17 60	93.57 58	91.96 185	97.80 72	78.79 295	98.50 51	96.98 47	86.61 162	94.75 71	98.16 64	78.36 121	99.35 103	93.89 92	97.12 96	97.75 133

APD-MVS		93.61 51	93.59 56	93.69 75	98.76 31	83.26 124	97.21 146	96.09 165	82.41 295	94.65 72	98.21 58	81.96 75	98.81 143	94.65 83	98.36 52	99.01 34
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_prior2							98.37 57		86.08 174	94.57 73	98.02 75	83.14 65		95.05 77	98.79 27

CS-MVS		92.73 76	93.48 61	90.48 259	96.27 114	75.93 374	98.55 48	94.93 246	89.32 80	94.54 74	97.67 95	78.91 110	97.02 282	93.80 93	97.32 88	98.49 66

FOURS1					98.51 46	78.01 322	98.13 73	96.21 156	83.04 278	94.39 75

ACMMP_NAP		93.46 56	93.23 66	94.17 54	97.16 101	84.28 101	96.82 190	96.65 95	86.24 169	94.27 76	97.99 76	77.94 127	99.83 23	93.39 99	98.57 39	98.39 73

agg_prior					98.59 42	83.13 127		96.56 110		94.19 77			99.16 120

SteuartSystems-ACMMP		94.13 43	94.44 38	93.20 100	95.41 150	81.35 193	99.02 28	96.59 105	89.50 79	94.18 78	98.36 52	83.68 62	99.45 95	94.77 80	98.45 46	98.81 48
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		93.59 52	93.63 54	93.48 89	98.05 65	81.76 178	98.64 45	97.13 34	82.60 291	94.09 79	98.49 38	80.35 86	99.85 17	94.74 82	98.62 36	98.83 46

test_fmvsmconf0.1_n		93.08 64	93.22 67	92.65 130	88.45 396	80.81 216	99.00 29	95.11 238	93.21 25	94.00 80	97.91 84	76.84 152	99.59 80	97.91 31	96.55 118	97.54 155

MVSMamba_PlusPlus		92.37 96	91.55 109	94.83 30	95.37 152	87.69 27	95.60 297	95.42 222	74.65 414	93.95 81	92.81 288	83.11 66	97.70 205	94.49 85	98.53 40	99.11 29

TSAR-MVS + GP.		94.35 35	94.50 35	93.89 61	97.38 97	83.04 129	98.10 75	95.29 232	91.57 46	93.81 82	97.45 109	86.64 31	99.43 96	96.28 58	94.01 159	99.20 26

CANet_DTU		90.98 135	90.04 152	93.83 63	94.76 177	86.23 45	96.32 235	93.12 397	93.11 26	93.71 83	96.82 144	63.08 341	99.48 93	84.29 241	95.12 144	95.77 263

VNet		92.11 102	91.22 115	94.79 31	96.91 104	86.98 34	97.91 89	97.96 10	86.38 166	93.65 84	95.74 169	70.16 279	98.95 135	93.39 99	88.87 245	98.43 71

test_vis1_n_1920		89.95 169	90.59 130	88.03 332	92.36 278	68.98 444	99.12 17	94.34 299	93.86 20	93.64 85	97.01 136	51.54 427	99.59 80	96.76 56	96.71 115	95.53 273

ZD-MVS					99.09 11	83.22 125		96.60 104	82.88 284	93.61 86	98.06 74	82.93 68	99.14 121	95.51 70	98.49 44

xiu_mvs_v1_base_debu		90.54 149	89.54 168	93.55 84	92.31 281	87.58 29	96.99 170	94.87 250	87.23 137	93.27 87	97.56 105	57.43 394	98.32 170	92.72 115	93.46 173	94.74 296

xiu_mvs_v1_base		90.54 149	89.54 168	93.55 84	92.31 281	87.58 29	96.99 170	94.87 250	87.23 137	93.27 87	97.56 105	57.43 394	98.32 170	92.72 115	93.46 173	94.74 296

xiu_mvs_v1_base_debi		90.54 149	89.54 168	93.55 84	92.31 281	87.58 29	96.99 170	94.87 250	87.23 137	93.27 87	97.56 105	57.43 394	98.32 170	92.72 115	93.46 173	94.74 296

CDPH-MVS		93.12 62	92.91 74	93.74 68	98.65 37	83.88 105	97.67 107	96.26 151	83.00 281	93.22 90	98.24 57	81.31 77	99.21 111	89.12 183	98.74 30	98.14 93

GDP-MVS		92.85 73	92.55 84	93.75 67	92.82 259	85.76 55	97.63 109	95.05 242	88.34 97	93.15 91	97.10 131	86.92 29	98.01 186	87.95 207	94.00 160	97.47 166

ETV-MVS		92.72 78	92.87 75	92.28 159	94.54 184	81.89 170	97.98 83	95.21 236	89.77 75	93.11 92	96.83 142	77.23 144	97.50 232	95.74 65	95.38 142	97.44 172

MSLP-MVS++		94.28 36	94.39 39	93.97 59	98.30 56	84.06 104	98.63 46	96.93 55	90.71 60	93.08 93	98.70 25	79.98 95	99.21 111	94.12 90	99.07 11	98.63 60

alignmvs		92.97 66	92.26 93	95.12 23	95.54 145	87.77 25	98.67 43	96.38 137	88.04 106	93.01 94	97.45 109	79.20 105	98.60 149	93.25 105	88.76 246	98.99 37

sasdasda		92.27 97	91.22 115	95.41 19	95.80 134	88.31 17	97.09 164	94.64 272	88.49 92	92.99 95	97.31 117	72.68 236	98.57 151	93.38 101	88.58 254	99.36 17

canonicalmvs		92.27 97	91.22 115	95.41 19	95.80 134	88.31 17	97.09 164	94.64 272	88.49 92	92.99 95	97.31 117	72.68 236	98.57 151	93.38 101	88.58 254	99.36 17

EC-MVSNet		91.73 111	92.11 98	90.58 255	93.54 223	77.77 334	98.07 78	94.40 294	87.44 129	92.99 95	97.11 130	74.59 210	96.87 299	93.75 95	97.08 98	97.11 201

MGCFI-Net		91.95 105	91.03 122	94.72 34	95.68 139	86.38 41	96.93 180	94.48 282	88.25 100	92.78 98	97.24 123	72.34 243	98.46 161	93.13 110	88.43 263	99.32 20

jason		92.73 76	92.23 94	94.21 50	90.50 353	87.30 33	98.65 44	95.09 239	90.61 62	92.76 99	97.13 128	75.28 197	97.30 261	93.32 103	96.75 113	98.02 102
jason: jason.
reproduce_model		92.53 90	92.87 75	91.50 216	97.41 92	77.14 351	96.02 260	95.91 185	83.65 266	92.45 100	98.39 48	79.75 98	99.21 111	95.27 76	96.98 101	98.14 93

reproduce-ours		92.70 81	93.02 69	91.75 200	97.45 88	77.77 334	96.16 250	95.94 182	84.12 244	92.45 100	98.43 44	80.06 93	99.24 107	95.35 73	97.18 92	98.24 85

our_new_method		92.70 81	93.02 69	91.75 200	97.45 88	77.77 334	96.16 250	95.94 182	84.12 244	92.45 100	98.43 44	80.06 93	99.24 107	95.35 73	97.18 92	98.24 85

test_cas_vis1_n_1920		89.90 170	90.02 153	89.54 292	90.14 364	74.63 386	98.71 41	94.43 291	93.04 27	92.40 103	96.35 156	53.41 423	99.08 127	95.59 68	96.16 125	94.90 290

test12				94.25 47	98.34 53	85.55 65		96.35 143		92.36 104		80.84 81	99.22 110		98.31 54	97.98 111

MG-MVS		94.25 38	93.72 51	95.85 13	99.38 4	89.35 12	97.98 83	98.09 9	89.99 71	92.34 105	96.97 137	81.30 78	98.99 131	88.54 199	98.88 20	99.20 26

test_fmvs1		87.79 237	88.52 197	85.62 384	92.98 250	64.31 466	97.88 91	92.42 408	87.95 108	92.24 106	95.82 166	47.94 446	98.44 165	95.31 75	94.09 156	94.09 310

h-mvs33		89.30 190	88.95 184	90.36 265	95.07 167	76.04 368	96.96 177	97.11 37	90.39 66	92.22 107	95.10 214	74.70 206	98.86 140	93.14 108	65.89 442	96.16 248

hse-mvs2		88.22 224	88.21 203	88.25 322	93.54 223	73.41 395	95.41 305	95.89 187	90.39 66	92.22 107	94.22 253	74.70 206	96.66 311	93.14 108	64.37 447	94.69 301

NormalMVS		92.88 70	92.97 72	92.59 137	97.80 72	82.02 159	97.94 86	94.70 261	92.34 34	92.15 109	96.53 153	77.03 147	98.57 151	91.13 140	97.12 96	97.19 197

SymmetryMVS		92.45 92	92.33 90	92.82 121	95.19 160	82.02 159	97.94 86	97.43 17	92.34 34	92.15 109	96.53 153	77.03 147	98.57 151	91.13 140	91.19 209	97.87 120

MCST-MVS		96.17 4	96.12 7	96.32 8	99.42 3	89.36 11	98.94 32	97.10 38	95.17 4	92.11 111	98.46 42	87.33 28	99.97 3	97.21 49	99.31 4	99.63 8

BP-MVS1		93.55 55	93.50 60	93.71 73	92.64 270	85.39 68	97.78 98	96.84 64	89.52 78	92.00 112	97.06 134	88.21 23	98.03 183	91.45 135	96.00 133	97.70 139

test_fmvsmconf0.01_n		91.08 132	90.68 129	92.29 158	82.43 461	80.12 247	97.94 86	93.93 334	92.07 40	91.97 113	97.60 103	67.56 301	99.53 88	97.09 51	95.56 141	97.21 193

SR-MVS		92.16 100	92.27 92	91.83 198	98.37 52	78.41 306	96.67 206	95.76 195	82.19 299	91.97 113	98.07 73	76.44 161	98.64 147	93.71 96	97.27 89	98.45 69

region2R		92.72 78	92.70 79	92.79 122	98.68 33	80.53 231	97.53 120	96.51 118	85.22 202	91.94 115	97.98 79	77.26 140	99.67 72	90.83 149	98.37 51	98.18 89

testing915		93.45 57	92.94 73	94.98 26	95.44 148	87.97 23	97.33 139	97.28 21	87.45 126	91.88 116	95.54 185	85.11 41	97.87 198	95.44 71	91.00 215	99.11 29

Effi-MVS+		90.70 144	89.90 160	93.09 106	93.61 220	83.48 119	95.20 316	92.79 402	83.22 273	91.82 117	95.70 172	71.82 257	97.48 235	91.25 137	93.67 169	98.32 77

HFP-MVS		92.89 69	92.86 77	92.98 111	98.71 32	81.12 198	97.58 115	96.70 87	85.20 204	91.75 118	97.97 81	78.47 118	99.71 63	90.95 142	98.41 48	98.12 96

DeepC-MVS_fast	89.06 2	94.48 32	94.30 42	95.02 24	98.86 28	85.68 59	98.06 79	96.64 98	93.64 22	91.74 119	98.54 32	80.17 91	99.90 9	92.28 122	98.75 29	99.49 9
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMPR		92.69 83	92.67 80	92.75 124	98.66 35	80.57 225	97.58 115	96.69 89	85.20 204	91.57 120	97.92 82	77.01 149	99.67 72	90.95 142	98.41 48	98.00 109

DELS-MVS		94.98 16	94.49 36	96.44 7	96.42 110	90.59 8	99.21 9	97.02 44	94.40 15	91.46 121	97.08 132	83.32 64	99.69 67	92.83 113	98.70 33	99.04 33
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
XVS		92.69 83	92.71 78	92.63 133	98.52 44	80.29 237	97.37 136	96.44 127	87.04 147	91.38 122	97.83 90	77.24 142	99.59 80	90.46 157	98.07 60	98.02 102

X-MVStestdata		86.26 269	84.14 291	92.63 133	98.52 44	80.29 237	97.37 136	96.44 127	87.04 147	91.38 122	20.73 540	77.24 142	99.59 80	90.46 157	98.07 60	98.02 102

PMMVS		89.46 183	89.92 159	88.06 330	94.64 179	69.57 441	96.22 245	94.95 245	87.27 136	91.37 124	96.54 152	65.88 318	97.39 251	88.54 199	93.89 164	97.23 189

test_fmvs1_n		86.34 267	86.72 243	85.17 392	87.54 408	63.64 471	96.91 182	92.37 410	87.49 125	91.33 125	95.58 183	40.81 475	98.46 161	95.00 78	93.49 171	93.41 324

dcpmvs_2		93.10 63	93.46 62	92.02 183	97.77 74	79.73 261	94.82 334	93.86 341	86.91 150	91.33 125	96.76 146	85.20 40	98.06 181	96.90 54	97.60 76	98.27 83

原ACMM1				91.22 233	97.77 74	78.10 320		96.61 101	81.05 316	91.28 127	97.42 113	77.92 129	98.98 132	79.85 294	98.51 41	96.59 236

新几何1				93.12 104	97.44 90	81.60 187		96.71 86	74.54 415	91.22 128	97.57 104	79.13 106	99.51 91	77.40 327	98.46 45	98.26 84

UA-Net		88.92 201	88.48 198	90.24 269	94.06 209	77.18 349	93.04 386	94.66 269	87.39 131	91.09 129	93.89 267	74.92 202	98.18 177	75.83 345	91.43 205	95.35 278

ZNCC-MVS		92.75 74	92.60 82	93.23 98	98.24 58	81.82 175	97.63 109	96.50 120	85.00 215	91.05 130	97.74 93	78.38 119	99.80 33	90.48 155	98.34 53	98.07 99

APD-MVS_3200maxsize		91.23 128	91.35 112	90.89 247	97.89 69	76.35 364	96.30 237	95.52 211	79.82 350	91.03 131	97.88 87	74.70 206	98.54 155	92.11 127	96.89 105	97.77 131

test_vis1_n		85.60 283	85.70 258	85.33 389	84.79 442	64.98 463	96.83 187	91.61 426	87.36 132	91.00 132	94.84 231	36.14 482	97.18 271	95.66 66	93.03 178	93.82 315

GST-MVS		92.43 94	92.22 96	93.04 108	98.17 61	81.64 184	97.40 134	96.38 137	84.71 222	90.90 133	97.40 114	77.55 136	99.76 47	89.75 173	97.74 72	97.72 136

PGM-MVS		91.93 106	91.80 104	92.32 157	98.27 57	79.74 260	95.28 308	97.27 23	83.83 258	90.89 134	97.78 92	76.12 172	99.56 86	88.82 192	97.93 67	97.66 142

SR-MVS-dyc-post		91.29 126	91.45 111	90.80 249	97.76 76	76.03 369	96.20 247	95.44 218	80.56 328	90.72 135	97.84 88	75.76 180	98.61 148	91.99 128	96.79 111	97.75 133

RE-MVS-def			91.18 119		97.76 76	76.03 369	96.20 247	95.44 218	80.56 328	90.72 135	97.84 88	73.36 227		91.99 128	96.79 111	97.75 133

FBQ-MVS		91.64 115	90.94 124	93.73 70	95.88 130	84.93 87	96.78 195	96.95 52	87.21 140	90.53 137	94.44 247	80.88 79	97.92 194	87.30 216	88.50 262	98.33 75

MP-MVS		92.61 87	92.67 80	92.42 148	98.13 63	79.73 261	97.33 139	96.20 157	85.63 189	90.53 137	97.66 96	78.14 125	99.70 66	92.12 126	98.30 55	97.85 123
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HY-MVS	84.06 6	91.63 116	90.37 139	95.39 21	96.12 120	88.25 19	90.22 426	97.58 15	88.33 98	90.50 139	91.96 305	79.26 103	99.06 128	90.29 164	89.07 241	98.88 45

CP-MVS		92.54 89	92.60 82	92.34 153	98.50 47	79.90 253	98.40 56	96.40 133	84.75 219	90.48 140	98.09 69	77.40 138	99.21 111	91.15 139	98.23 57	97.92 116

diffmvs_AUTHOR		90.86 141	90.41 136	92.24 161	92.01 312	82.22 155	96.18 249	93.64 368	87.28 134	90.46 141	95.64 177	72.82 234	97.39 251	93.17 107	92.46 187	97.11 201

onestephybrid01		90.58 148	90.37 139	91.20 234	92.69 264	78.81 289	96.04 259	93.94 333	86.55 164	90.40 142	95.64 177	72.84 233	97.43 244	93.77 94	91.46 204	97.36 179

diffmvs		91.17 129	90.74 128	92.44 146	93.11 244	82.50 145	96.25 241	93.62 370	87.79 113	90.40 142	95.93 163	73.44 226	97.42 245	93.62 98	92.55 184	97.41 174
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		90.29 163	89.18 175	93.62 80	95.23 156	84.93 87	94.41 342	94.66 269	84.31 237	90.37 144	91.02 319	75.13 199	97.82 200	83.11 261	94.42 154	98.12 96

MTAPA		92.45 92	92.31 91	92.86 117	97.90 68	80.85 215	92.88 390	96.33 144	87.92 109	90.20 145	98.18 60	76.71 157	99.76 47	92.57 119	98.09 59	97.96 115

balanced_ft_v1		92.00 104	91.12 120	94.64 36	96.35 111	86.78 36	94.96 329	94.70 261	87.65 120	90.20 145	93.01 286	69.71 282	98.02 184	97.40 45	96.13 127	99.11 29

test_yl		91.46 120	90.53 132	94.24 48	97.41 92	85.18 75	98.08 76	97.72 11	80.94 317	89.85 147	96.14 159	75.61 182	98.81 143	90.42 160	88.56 256	98.74 51

DCV-MVSNet		91.46 120	90.53 132	94.24 48	97.41 92	85.18 75	98.08 76	97.72 11	80.94 317	89.85 147	96.14 159	75.61 182	98.81 143	90.42 160	88.56 256	98.74 51

WTY-MVS		92.65 86	91.68 106	95.56 15	96.00 123	88.90 14	98.23 66	97.65 13	88.57 90	89.82 149	97.22 125	79.29 102	99.06 128	89.57 176	88.73 247	98.73 55

MVS_111021_HR		93.41 58	93.39 63	93.47 91	97.34 98	82.83 134	97.56 117	98.27 6	89.16 83	89.71 150	97.14 127	79.77 97	99.56 86	93.65 97	97.94 65	98.02 102

sss		90.87 140	89.96 157	93.60 81	94.15 203	83.84 108	97.14 157	98.13 7	85.93 183	89.68 151	96.09 161	71.67 258	99.30 104	87.69 212	89.16 240	97.66 142

test222					96.15 119	78.41 306	95.87 281	96.46 125	71.97 441	89.66 152	97.45 109	76.33 165			98.24 56	98.30 80

LFMVS		89.27 191	87.64 215	94.16 57	97.16 101	85.52 66	97.18 150	94.66 269	79.17 364	89.63 153	96.57 151	55.35 412	98.22 174	89.52 180	89.54 231	98.74 51

CostFormer		89.08 195	88.39 199	91.15 235	93.13 242	79.15 278	88.61 442	96.11 164	83.14 275	89.58 154	86.93 387	83.83 61	96.87 299	88.22 205	85.92 293	97.42 173

hybrid		90.42 155	89.87 162	92.06 177	92.20 295	81.45 190	96.09 256	93.61 371	85.80 185	89.55 155	95.52 187	72.14 252	97.39 251	92.60 118	91.36 207	97.34 182

PVSNet_BlendedMVS		90.05 166	89.96 157	90.33 266	97.47 86	83.86 106	98.02 82	96.73 83	87.98 107	89.53 156	89.61 343	76.42 162	99.57 84	94.29 87	79.59 339	87.57 422

PVSNet_Blended		93.13 61	92.98 71	93.57 83	97.47 86	83.86 106	99.32 4	96.73 83	91.02 57	89.53 156	96.21 158	76.42 162	99.57 84	94.29 87	95.81 137	97.29 188

HPM-MVS		91.62 117	91.53 110	91.89 189	97.88 70	79.22 275	96.99 170	95.73 198	82.07 301	89.50 158	97.19 126	75.59 184	98.93 138	90.91 144	97.94 65	97.54 155
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testing11		92.48 91	92.04 101	93.78 65	95.94 127	86.00 48	97.56 117	97.08 39	87.52 124	89.32 159	95.40 194	84.60 46	98.02 184	91.93 132	89.04 242	97.32 183

hybridnocas07		90.53 152	90.02 153	92.05 181	92.36 278	81.48 189	96.27 238	93.57 375	86.86 153	89.28 160	95.48 190	72.17 248	97.47 236	92.77 114	91.41 206	97.21 193

UBG		92.68 85	92.35 88	93.70 74	95.61 142	85.65 62	97.25 144	97.06 41	87.92 109	89.28 160	95.03 217	86.06 37	98.07 180	92.24 123	90.69 220	97.37 178

EI-MVSNet-Vis-set		91.84 110	91.77 105	92.04 182	97.60 81	81.17 196	96.61 207	96.87 61	88.20 102	89.19 162	97.55 108	78.69 115	99.14 121	90.29 164	90.94 216	95.80 258

testing222		91.09 131	90.49 134	92.87 116	95.82 132	85.04 83	96.51 217	97.28 21	86.05 175	89.13 163	95.34 196	80.16 92	96.62 312	85.82 229	88.31 266	96.96 215

MP-MVS-pluss		92.58 88	92.35 88	93.29 95	97.30 99	82.53 140	96.44 222	96.04 171	84.68 223	89.12 164	98.37 51	77.48 137	99.74 55	93.31 104	98.38 50	97.59 151
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VDD-MVS		88.28 222	87.02 235	92.06 177	95.09 165	80.18 245	97.55 119	94.45 288	83.09 276	89.10 165	95.92 165	47.97 445	98.49 158	93.08 112	86.91 281	97.52 161

baseline		90.76 142	90.10 148	92.74 125	92.90 257	82.56 139	94.60 339	94.56 278	87.69 117	89.06 166	95.67 175	73.76 221	97.51 231	90.43 159	92.23 195	98.16 91

viewmanbaseed2359cas		90.74 143	90.07 150	92.76 123	92.98 250	82.93 132	96.53 214	94.28 305	87.08 145	88.96 167	95.64 177	72.03 255	97.58 217	90.85 147	92.26 193	97.76 132

testing99		91.91 107	91.35 112	93.60 81	95.98 125	85.70 57	97.31 141	96.92 57	86.82 154	88.91 168	95.25 199	84.26 54	97.89 197	88.80 193	87.94 270	97.21 193

EIA-MVS		91.73 111	92.05 100	90.78 251	94.52 185	76.40 363	98.06 79	95.34 228	89.19 82	88.90 169	97.28 122	77.56 135	97.73 204	90.77 150	96.86 108	98.20 87

testing91		91.90 108	91.31 114	93.66 77	95.99 124	85.68 59	97.39 135	96.89 58	86.75 158	88.85 170	95.23 203	83.93 59	97.90 196	88.91 186	87.89 271	97.41 174

mvsany_test1		87.58 245	88.22 202	85.67 382	89.78 370	67.18 452	95.25 313	87.93 466	83.96 251	88.79 171	97.06 134	72.52 239	94.53 415	92.21 124	86.45 285	95.30 280

HPM-MVS_fast		90.38 159	90.17 147	91.03 239	97.61 80	77.35 345	97.15 156	95.48 214	79.51 356	88.79 171	96.90 138	71.64 260	98.81 143	87.01 221	97.44 81	96.94 216

ETVMVS		90.99 134	90.26 142	93.19 101	95.81 133	85.64 63	96.97 175	97.18 30	85.43 196	88.77 173	94.86 229	82.00 74	96.37 319	82.70 264	88.60 252	97.57 152

PAPM		92.87 72	92.40 87	94.30 44	92.25 293	87.85 24	96.40 227	96.38 137	91.07 55	88.72 174	96.90 138	82.11 73	97.37 257	90.05 168	97.70 73	97.67 141

MVS_111021_LR		91.60 118	91.64 108	91.47 219	95.74 137	78.79 295	96.15 252	96.77 76	88.49 92	88.64 175	97.07 133	72.33 244	99.19 117	93.13 110	96.48 120	96.43 240

E3new		90.90 139	90.35 141	92.55 139	93.63 219	82.40 148	96.79 193	94.49 281	87.07 146	88.54 176	95.70 172	73.85 219	97.60 213	91.23 138	91.86 199	97.64 144

casdiffmvs		90.95 137	90.39 137	92.63 133	92.82 259	82.53 140	96.83 187	94.47 285	87.69 117	88.47 177	95.56 184	74.04 217	97.54 226	90.90 145	92.74 182	97.83 125
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
mPP-MVS		91.88 109	91.82 103	92.07 176	98.38 51	78.63 299	97.29 143	96.09 165	85.12 210	88.45 178	97.66 96	75.53 186	99.68 70	89.83 169	98.02 63	97.88 118

PAPR		92.74 75	92.17 97	94.45 40	98.89 27	84.87 90	97.20 148	96.20 157	87.73 115	88.40 179	98.12 66	78.71 114	99.76 47	87.99 206	96.28 122	98.74 51

tpmrst		88.36 219	87.38 226	91.31 224	94.36 197	79.92 252	87.32 454	95.26 234	85.32 199	88.34 180	86.13 404	80.60 84	96.70 308	83.78 247	85.34 301	97.30 186

viewmamba		90.30 162	89.90 160	91.48 218	92.14 302	79.76 256	95.92 267	93.50 377	87.73 115	88.32 181	95.82 166	72.39 241	97.36 258	92.19 125	91.12 212	97.30 186

GG-mvs-BLEND				93.49 88	94.94 171	86.26 42	81.62 482	97.00 45		88.32 181	94.30 250	91.23 6	96.21 327	88.49 201	97.43 82	98.00 109

EI-MVSNet-UG-set		91.35 125	91.22 115	91.73 203	97.39 95	80.68 219	96.47 219	96.83 65	87.92 109	88.30 183	97.36 115	77.84 130	99.13 123	89.43 181	89.45 232	95.37 277

viewmambaseed2359dif		89.52 181	89.02 179	91.03 239	92.24 294	78.83 286	95.89 277	93.77 356	83.04 278	88.28 184	95.80 168	72.08 253	97.40 249	89.76 172	90.32 222	96.87 223

viewcassd2359sk11		90.66 145	90.06 151	92.47 142	93.22 236	82.21 156	96.70 204	94.47 285	86.94 149	88.22 185	95.50 189	73.15 229	97.59 215	90.86 146	91.48 203	97.60 150

myMVS_eth3d28		92.72 78	92.23 94	94.21 50	96.16 118	87.46 32	97.37 136	96.99 46	88.13 104	88.18 186	95.47 191	84.12 55	98.04 182	92.46 121	91.17 211	97.14 200

MAR-MVS		90.63 146	90.22 144	91.86 191	98.47 49	78.20 318	97.18 150	96.61 101	83.87 255	88.18 186	98.18 60	68.71 292	99.75 52	83.66 253	97.15 94	97.63 146
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
viewmacassd2359aftdt		89.89 171	89.01 181	92.52 141	91.56 326	82.46 146	96.32 235	94.06 328	86.41 165	88.11 188	95.01 219	69.68 283	97.47 236	88.73 197	91.19 209	97.63 146

KinetiMVS		89.13 194	87.95 208	92.65 130	92.16 300	82.39 150	97.04 168	96.05 169	86.59 163	88.08 189	94.85 230	61.54 358	98.38 167	81.28 279	93.99 162	97.19 197

DP-MVS Recon		91.72 113	90.85 125	94.34 43	99.50 1	85.00 86	98.51 50	95.96 178	80.57 327	88.08 189	97.63 102	76.84 152	99.89 11	85.67 231	94.88 146	98.13 95

E2		90.33 160	89.65 166	92.37 151	92.66 266	81.99 162	96.58 209	94.39 295	86.71 160	87.88 191	95.25 199	72.18 247	97.56 219	90.37 162	90.88 217	97.57 152

E3		90.33 160	89.65 166	92.37 151	92.64 270	81.99 162	96.58 209	94.39 295	86.71 160	87.87 192	95.27 198	72.17 248	97.56 219	90.37 162	90.88 217	97.57 152

VDDNet		86.44 263	84.51 280	92.22 164	91.56 326	81.83 174	97.10 163	94.64 272	69.50 454	87.84 193	95.19 207	48.01 444	97.92 194	89.82 170	86.92 280	96.89 220

UGNet		87.73 239	86.55 247	91.27 228	95.16 163	79.11 279	96.35 232	96.23 154	88.14 103	87.83 194	90.48 328	50.65 432	99.09 126	80.13 290	94.03 157	95.60 269
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
dtuplus		89.18 193	88.59 192	90.96 242	91.84 321	78.40 309	95.89 277	93.81 350	83.26 272	87.77 195	95.53 186	70.57 275	97.49 234	88.57 198	90.08 224	96.99 212

test2506		90.96 136	90.39 137	92.65 130	93.54 223	82.46 146	96.37 228	97.35 19	86.78 156	87.55 196	95.25 199	77.83 131	97.50 232	84.07 243	94.80 147	97.98 111

viewdifsd2359ckpt13		90.08 165	89.36 171	92.26 160	93.03 245	81.90 169	96.37 228	94.34 299	86.16 170	87.44 197	95.30 197	70.93 271	97.55 223	89.05 184	91.59 202	97.35 181

tpm2		87.35 250	86.26 249	90.62 254	92.93 256	78.67 298	88.06 449	95.99 174	79.33 359	87.40 198	86.43 398	80.28 88	96.40 317	80.23 288	85.73 297	96.79 226

CPTT-MVS		89.72 176	89.87 162	89.29 295	98.33 54	73.30 398	97.70 105	95.35 227	75.68 404	87.40 198	97.44 112	70.43 276	98.25 173	89.56 178	96.90 104	96.33 245

gg-mvs-nofinetune		85.48 286	82.90 317	93.24 97	94.51 189	85.82 54	79.22 489	96.97 50	61.19 482	87.33 200	53.01 519	90.58 7	96.07 331	86.07 228	97.23 90	97.81 129

Casviewmamba		90.52 154	90.00 155	92.06 177	92.72 263	80.42 235	96.87 184	94.28 305	87.45 126	87.30 201	95.73 170	73.10 230	97.67 209	90.27 167	92.29 192	98.10 98

E4		89.85 172	89.06 177	92.22 164	91.88 317	81.63 185	96.43 224	94.27 307	86.32 168	87.29 202	94.97 223	70.81 273	97.52 229	89.57 176	90.00 226	97.51 162

CHOSEN 280x420		91.71 114	91.85 102	91.29 227	94.94 171	82.69 137	87.89 450	96.17 160	85.94 182	87.27 203	94.31 249	90.27 9	95.65 358	94.04 91	95.86 135	95.53 273

test_fmvsmvis_n_1920		92.12 101	92.10 99	92.17 169	90.87 344	81.04 201	98.34 62	93.90 338	92.71 29	87.24 204	97.90 85	74.83 204	99.72 60	96.96 53	96.20 124	95.76 264

0.3-1-1-0.015		87.79 237	85.93 254	93.38 93	89.87 368	85.09 82	98.43 53	96.55 111	81.13 314	87.21 205	89.75 339	77.23 144	97.02 282	86.87 223	66.38 439	98.02 102

casdiffmvs_mvg		91.13 130	90.45 135	93.17 102	92.99 249	83.58 117	97.46 127	94.56 278	87.69 117	87.19 206	94.98 222	74.50 211	97.60 213	91.88 133	92.79 181	98.34 74
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
0.4-1-1-0.2		87.73 239	85.82 257	93.46 92	89.97 367	85.31 72	98.49 52	96.55 111	81.24 312	87.14 207	89.63 342	76.16 170	97.02 282	86.84 224	66.38 439	98.05 100

EPNet_dtu		87.65 244	87.89 209	86.93 360	94.57 181	71.37 426	96.72 200	96.50 120	88.56 91	87.12 208	95.02 218	75.91 177	94.01 425	66.62 412	90.00 226	95.42 276
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Vis-MVSNet		88.67 209	87.82 211	91.24 230	92.68 265	78.82 287	96.95 178	93.85 342	87.55 123	87.07 209	95.13 212	63.43 338	97.21 268	77.58 323	96.15 126	97.70 139
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
mvsmamba		90.53 152	90.08 149	91.88 190	94.81 175	80.93 211	93.94 361	94.45 288	88.24 101	87.02 210	92.35 295	68.04 294	95.80 346	94.86 79	97.03 100	98.92 42

0.4-1-1-0.1		87.53 247	85.67 259	93.13 103	89.70 375	84.41 96	98.30 63	96.55 111	80.85 319	86.94 211	89.53 344	76.18 168	96.99 287	86.62 227	66.36 441	97.98 111

E5new		89.38 184	88.55 193	91.85 193	91.77 322	80.97 205	95.90 273	94.22 313	86.03 177	86.88 212	94.90 226	69.05 287	97.47 236	88.86 187	89.35 233	97.10 203

E6new		89.37 186	88.55 193	91.85 193	91.75 324	80.97 205	95.90 273	94.22 313	86.03 177	86.88 212	94.91 224	69.05 287	97.47 236	88.86 187	89.34 235	97.10 203

E6		89.37 186	88.55 193	91.85 193	91.75 324	80.97 205	95.90 273	94.22 313	86.03 177	86.88 212	94.91 224	69.05 287	97.47 236	88.86 187	89.34 235	97.10 203

E5		89.38 184	88.55 193	91.85 193	91.77 322	80.97 205	95.90 273	94.22 313	86.03 177	86.88 212	94.90 226	69.05 287	97.47 236	88.86 187	89.35 233	97.10 203

thisisatest0515		90.95 137	90.26 142	93.01 109	94.03 212	84.27 102	97.91 89	96.67 91	83.18 274	86.87 216	95.51 188	88.66 18	97.85 199	80.46 284	89.01 243	96.92 219

TESTMET0.1,1		89.83 174	89.34 172	91.31 224	92.54 274	80.19 244	97.11 160	96.57 108	86.15 171	86.85 217	91.83 310	79.32 100	96.95 290	81.30 278	92.35 191	96.77 228

testing3-2		91.37 123	91.01 123	92.44 146	95.93 128	83.77 109	98.83 37	97.45 16	86.88 151	86.63 218	94.69 237	84.57 47	97.75 203	89.65 174	84.44 304	95.80 258

viewdifsd2359ckpt09		90.00 168	89.28 174	92.15 171	93.31 234	81.38 191	96.37 228	93.64 368	86.34 167	86.62 219	95.64 177	71.58 261	97.52 229	88.93 185	91.06 213	97.54 155

hybridcas		90.40 156	89.67 165	92.60 136	92.39 276	82.32 152	96.83 187	94.25 309	87.19 141	86.59 220	95.43 193	72.54 238	97.65 210	88.77 195	93.02 179	97.82 127

LuminaMVS		88.02 230	86.89 240	91.43 220	88.65 394	83.16 126	94.84 333	94.41 293	83.67 265	86.56 221	91.95 307	62.04 352	96.88 298	89.78 171	90.06 225	94.24 305

guyue		89.85 172	89.33 173	91.40 222	92.53 275	80.15 246	96.82 190	95.68 201	89.66 76	86.43 222	94.23 252	67.00 308	97.16 272	91.96 131	89.65 230	96.89 220

PVSNet_Blended_VisFu		91.24 127	90.77 127	92.66 129	95.09 165	82.40 148	97.77 99	95.87 191	88.26 99	86.39 223	93.94 266	76.77 155	99.27 105	88.80 193	94.00 160	96.31 246

API-MVS		90.18 164	88.97 182	93.80 64	98.66 35	82.95 131	97.50 124	95.63 205	75.16 409	86.31 224	97.69 94	72.49 240	99.90 9	81.26 280	96.07 129	98.56 63

test-LLR		88.48 215	87.98 207	89.98 278	92.26 291	77.23 347	97.11 160	95.96 178	83.76 261	86.30 225	91.38 313	72.30 245	96.78 306	80.82 281	91.92 197	95.94 254

test-mter		88.95 199	88.60 190	89.98 278	92.26 291	77.23 347	97.11 160	95.96 178	85.32 199	86.30 225	91.38 313	76.37 164	96.78 306	80.82 281	91.92 197	95.94 254

AstraMVS		88.99 198	88.35 200	90.92 244	90.81 348	78.29 310	96.73 199	94.24 310	89.96 72	86.13 227	95.04 216	62.12 351	97.41 247	92.54 120	87.57 277	97.06 210

PAPM_NR		91.46 120	90.82 126	93.37 94	98.50 47	81.81 176	95.03 328	96.13 162	84.65 224	86.10 228	97.65 100	79.24 104	99.75 52	83.20 259	96.88 106	98.56 63

FA-MVS(test-final)		87.71 242	86.23 251	92.17 169	94.19 201	80.55 226	87.16 456	96.07 168	82.12 300	85.98 229	88.35 363	72.04 254	98.49 158	80.26 287	89.87 228	97.48 165

RRT-MVS		89.67 178	88.67 188	92.67 128	94.44 192	81.08 200	94.34 347	94.45 288	86.05 175	85.79 230	92.39 294	63.39 339	98.16 178	93.22 106	93.95 163	98.76 50

MDTV_nov1_ep13_2view						81.74 179	86.80 458		80.65 325	85.65 231		74.26 213		76.52 337		96.98 214

casdiffseed414692147		88.22 224	86.93 239	92.08 174	92.04 310	81.84 173	96.08 258	94.08 326	84.56 227	85.59 232	93.98 265	67.37 304	97.42 245	80.12 291	88.52 258	96.99 212

ECVR-MVS		88.35 220	87.25 228	91.65 207	93.54 223	79.40 269	96.56 213	90.78 442	86.78 156	85.57 233	95.25 199	57.25 398	97.56 219	84.73 239	94.80 147	97.98 111

mmtdpeth		78.04 395	76.76 390	81.86 434	89.60 379	66.12 460	92.34 400	87.18 470	76.83 396	85.55 234	76.49 482	46.77 451	97.02 282	90.85 147	45.24 499	82.43 476

AUN-MVS		86.25 270	85.57 261	88.26 320	93.57 222	73.38 396	95.45 303	95.88 188	83.94 252	85.47 235	94.21 254	73.70 224	96.67 310	83.54 255	64.41 446	94.73 300

PVSNet	82.34 9	89.02 197	87.79 212	92.71 127	95.49 147	81.50 188	97.70 105	97.29 20	87.76 114	85.47 235	95.12 213	56.90 400	98.90 139	80.33 285	94.02 158	97.71 138

viewdifsd2359ckpt07		89.04 196	88.30 201	91.27 228	92.32 280	78.90 284	95.89 277	93.77 356	84.48 233	85.18 237	95.16 209	69.83 280	97.70 205	88.75 196	89.29 238	97.22 190

EPP-MVSNet		89.76 175	89.72 164	89.87 283	93.78 215	76.02 371	97.22 145	96.51 118	79.35 358	85.11 238	95.01 219	84.82 44	97.10 280	87.46 215	88.21 268	96.50 238

test1111		88.11 226	87.04 234	91.35 223	93.15 240	78.79 295	96.57 211	90.78 442	86.88 151	85.04 239	95.20 206	57.23 399	97.39 251	83.88 245	94.59 150	97.87 120

FE-MVS		86.06 272	84.15 290	91.78 199	94.33 198	79.81 254	84.58 474	96.61 101	76.69 398	85.00 240	87.38 378	70.71 274	98.37 168	70.39 394	91.70 201	97.17 199

OMC-MVS		88.80 206	88.16 205	90.72 252	95.30 154	77.92 327	94.81 335	94.51 280	86.80 155	84.97 241	96.85 141	67.53 302	98.60 149	85.08 235	87.62 274	95.63 267

CHOSEN 1792x2688		91.07 133	90.21 145	93.64 78	95.18 162	83.53 118	96.26 240	96.13 162	88.92 84	84.90 242	93.10 284	72.86 232	99.62 78	88.86 187	95.67 138	97.79 130

thres200		88.92 201	87.65 214	92.73 126	96.30 113	85.62 64	97.85 92	98.86 1	84.38 236	84.82 243	93.99 264	75.12 200	98.01 186	70.86 391	86.67 282	94.56 302

UWE-MVS		88.56 214	88.91 186	87.50 347	94.17 202	72.19 411	95.82 285	97.05 42	84.96 216	84.78 244	93.51 278	81.33 76	94.75 407	79.43 297	89.17 239	95.57 271

MDTV_nov1_ep13			83.69 295		94.09 208	81.01 203	86.78 459	96.09 165	83.81 259	84.75 245	84.32 428	74.44 212	96.54 313	63.88 428	85.07 302

CDS-MVSNet		89.50 182	88.96 183	91.14 236	91.94 316	80.93 211	97.09 164	95.81 193	84.26 242	84.72 246	94.20 255	80.31 87	95.64 359	83.37 258	88.96 244	96.85 224
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ACMMP		90.39 157	89.97 156	91.64 208	97.58 83	78.21 317	96.78 195	96.72 85	84.73 221	84.72 246	97.23 124	71.22 264	99.63 76	88.37 204	92.41 190	97.08 208
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
SSM_0404		87.69 243	86.26 249	91.95 186	92.94 252	83.02 130	94.69 338	92.33 411	80.11 343	84.65 248	94.18 256	64.68 331	96.90 294	82.34 267	90.44 221	95.94 254

CSCG		92.02 103	91.65 107	93.12 104	98.53 43	80.59 222	97.47 125	97.18 30	77.06 392	84.64 249	97.98 79	83.98 58	99.52 89	90.72 151	97.33 87	99.23 25

ab-mvs		87.08 252	84.94 276	93.48 89	93.34 233	83.67 115	88.82 439	95.70 199	81.18 313	84.55 250	90.14 336	62.72 342	98.94 137	85.49 233	82.54 323	97.85 123

IMVS_0403		88.07 227	87.02 235	91.24 230	92.30 284	78.81 289	93.62 369	93.84 343	85.14 206	84.36 251	94.49 243	69.49 284	97.46 243	81.33 274	88.61 248	97.46 167

viewmsd2359difaftdt		86.38 264	85.29 266	89.67 290	90.42 355	75.65 378	95.27 311	92.45 406	85.54 194	84.28 252	94.73 233	62.16 347	97.39 251	87.78 209	74.97 370	95.96 251

viewdifsd2359ckpt11		86.38 264	85.29 266	89.66 291	90.42 355	75.65 378	95.27 311	92.45 406	85.54 194	84.27 253	94.73 233	62.16 347	97.39 251	87.78 209	74.97 370	95.96 251

EPMVS		87.47 249	85.90 255	92.18 168	95.41 150	82.26 154	87.00 457	96.28 148	85.88 184	84.23 254	85.57 411	75.07 201	96.26 323	71.14 389	92.50 185	98.03 101

Elysia		85.62 281	83.66 298	91.51 214	88.76 387	82.21 156	95.15 320	94.70 261	76.96 394	84.13 255	92.20 298	50.81 430	97.26 265	77.81 314	92.42 188	95.06 286

StellarMVS		85.62 281	83.66 298	91.51 214	88.76 387	82.21 156	95.15 320	94.70 261	76.96 394	84.13 255	92.20 298	50.81 430	97.26 265	77.81 314	92.42 188	95.06 286

Anonymous202405211		84.41 310	81.93 332	91.85 193	96.78 106	78.41 306	97.44 128	91.34 431	70.29 449	84.06 257	94.26 251	41.09 472	98.96 133	79.46 296	82.65 322	98.17 90

HyFIR lowres test		89.35 188	88.60 190	91.63 210	94.91 173	80.76 218	95.60 297	95.53 209	82.56 292	84.03 258	91.24 316	78.03 126	96.81 303	87.07 220	88.41 264	97.32 183

tfpn200view9		88.48 215	87.15 230	92.47 142	96.21 116	85.30 73	97.44 128	98.85 2	83.37 270	83.99 259	93.82 270	75.36 193	97.93 189	69.04 399	86.24 289	94.17 306

thres400		88.42 218	87.15 230	92.23 163	96.21 116	85.30 73	97.44 128	98.85 2	83.37 270	83.99 259	93.82 270	75.36 193	97.93 189	69.04 399	86.24 289	93.45 322

tpm		85.55 284	84.47 283	88.80 306	90.19 361	75.39 381	88.79 440	94.69 265	84.82 218	83.96 261	85.21 417	78.22 123	94.68 411	76.32 341	78.02 356	96.34 243

Fast-Effi-MVS+		87.93 233	86.94 238	90.92 244	94.04 210	79.16 277	98.26 65	93.72 363	81.29 311	83.94 262	92.90 287	69.83 280	96.68 309	76.70 333	91.74 200	96.93 217

XVG-OURS-SEG-HR		85.74 278	85.16 272	87.49 349	90.22 359	71.45 424	91.29 415	94.09 325	81.37 310	83.90 263	95.22 204	60.30 364	97.53 228	85.58 232	84.42 306	93.50 320

thisisatest0530		89.65 179	89.02 179	91.53 213	93.46 230	80.78 217	96.52 215	96.67 91	81.69 308	83.79 264	94.90 226	88.85 17	97.68 207	77.80 316	87.49 278	96.14 249

DeepC-MVS	86.58 3	91.53 119	91.06 121	92.94 114	94.52 185	81.89 170	95.95 264	95.98 176	90.76 59	83.76 265	96.76 146	73.24 228	99.71 63	91.67 134	96.96 102	97.22 190
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
icg_test_0407_2		87.55 246	86.59 246	90.43 260	92.30 284	78.81 289	92.17 401	93.84 343	85.14 206	83.68 266	94.49 243	67.75 297	95.02 399	81.33 274	88.61 248	97.46 167

IMVS_0407		87.82 235	86.72 243	91.14 236	92.30 284	78.81 289	93.34 377	93.84 343	85.14 206	83.68 266	94.49 243	67.75 297	97.14 278	81.33 274	88.61 248	97.46 167

IS-MVSNet		88.67 209	88.16 205	90.20 271	93.61 220	76.86 354	96.77 198	93.07 398	84.02 248	83.62 268	95.60 182	74.69 209	96.24 326	78.43 311	93.66 170	97.49 164

mamba_0408		85.26 292	83.10 313	91.74 202	92.94 252	82.53 140	72.52 504	91.77 420	80.36 335	83.50 269	94.01 261	64.97 327	96.90 294	79.37 298	88.51 259	95.79 260

SSM_04072		84.64 303	83.10 313	89.25 296	92.94 252	82.53 140	72.52 504	91.77 420	80.36 335	83.50 269	94.01 261	64.97 327	89.41 473	79.37 298	88.51 259	95.79 260

SSM_0407		87.33 251	85.87 256	91.71 206	92.94 252	82.53 140	94.30 350	92.33 411	80.11 343	83.50 269	94.18 256	64.68 331	96.80 305	82.34 267	88.51 259	95.79 260

thres100view900		88.30 221	86.95 237	92.33 155	96.10 121	84.90 89	97.14 157	98.85 2	82.69 289	83.41 272	93.66 274	75.43 190	97.93 189	69.04 399	86.24 289	94.17 306

thres600view7		88.06 228	86.70 245	92.15 171	96.10 121	85.17 79	97.14 157	98.85 2	82.70 288	83.41 272	93.66 274	75.43 190	97.82 200	67.13 408	85.88 294	93.45 322

XVG-OURS		85.18 293	84.38 285	87.59 343	90.42 355	71.73 421	91.06 419	94.07 327	82.00 303	83.29 274	95.08 215	56.42 405	97.55 223	83.70 252	83.42 311	93.49 321

Vis-MVSNet (Re-imp)		88.88 203	88.87 187	88.91 303	93.89 213	74.43 389	96.93 180	94.19 319	84.39 235	83.22 275	95.67 175	78.24 122	94.70 409	78.88 307	94.40 155	97.61 149

TAMVS		88.48 215	87.79 212	90.56 256	91.09 339	79.18 276	96.45 221	95.88 188	83.64 267	83.12 276	93.33 279	75.94 176	95.74 354	82.40 266	88.27 267	96.75 231

baseline1		88.85 204	87.49 222	92.93 115	95.21 158	86.85 35	95.47 302	94.61 275	87.29 133	83.11 277	94.99 221	80.70 83	96.89 296	82.28 269	73.72 376	95.05 288

nomal-1		89.71 177	89.18 175	91.30 226	94.43 193	81.03 202	94.35 346	96.27 149	85.05 212	83.05 278	90.78 324	80.87 80	97.21 268	89.53 179	88.34 265	95.66 266

AdaColmap		88.81 205	87.61 218	92.39 150	99.33 5	79.95 251	96.70 204	95.58 206	77.51 384	83.05 278	96.69 150	61.90 356	99.72 60	84.29 241	93.47 172	97.50 163

PatchmatchNet		86.83 258	85.12 273	91.95 186	94.12 206	82.27 153	86.55 461	95.64 204	84.59 226	82.98 280	84.99 423	77.26 140	95.96 338	68.61 402	91.34 208	97.64 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		85.63 280	83.64 301	91.60 211	92.30 284	81.86 172	92.88 390	95.56 208	84.85 217	82.52 281	85.12 421	58.04 382	95.39 369	73.89 367	87.58 276	97.54 155

114514_t		88.79 207	87.57 220	92.45 144	98.21 60	81.74 179	96.99 170	95.45 217	75.16 409	82.48 282	95.69 174	68.59 293	98.50 157	80.33 285	95.18 143	97.10 203

PatchT		79.75 376	76.85 389	88.42 312	89.55 380	75.49 380	77.37 495	94.61 275	63.07 471	82.46 283	73.32 491	75.52 187	93.41 437	51.36 479	84.43 305	96.36 241

TR-MVS		86.30 268	84.93 277	90.42 261	94.63 180	77.58 340	96.57 211	93.82 347	80.30 338	82.42 284	95.16 209	58.74 375	97.55 223	74.88 357	87.82 272	96.13 250

HQP-NCC					92.08 306		97.63 109		90.52 63	82.30 285

ACMP_Plane					92.08 306		97.63 109		90.52 63	82.30 285

HQP4-MVS										82.30 285			97.32 259			91.13 335

HQP-MVS		87.91 234	87.55 221	88.98 302	92.08 306	78.48 302	97.63 109	94.80 256	90.52 63	82.30 285	94.56 239	65.40 322	97.32 259	87.67 213	83.01 315	91.13 335

CR-MVSNet		83.53 323	81.36 341	90.06 274	90.16 362	79.75 258	79.02 491	91.12 434	84.24 243	82.27 289	80.35 463	75.45 188	93.67 432	63.37 433	86.25 287	96.75 231

RPMNet		79.85 375	75.92 396	91.64 208	90.16 362	79.75 258	79.02 491	95.44 218	58.43 494	82.27 289	72.55 494	73.03 231	98.41 166	46.10 492	86.25 287	96.75 231

CVMVSNet		84.83 300	85.57 261	82.63 426	91.55 328	60.38 484	95.13 322	95.03 243	80.60 326	82.10 291	94.71 235	66.40 316	90.19 470	74.30 364	90.32 222	97.31 185

PLC	83.97 7	88.00 231	87.38 226	89.83 285	98.02 66	76.46 360	97.16 154	94.43 291	79.26 363	81.98 292	96.28 157	69.36 285	99.27 105	77.71 320	92.25 194	93.77 316
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
JIA-IIPM		79.00 385	77.20 385	84.40 406	89.74 374	64.06 469	75.30 499	95.44 218	62.15 476	81.90 293	59.08 513	78.92 109	95.59 363	66.51 415	85.78 296	93.54 319

Anonymous20240529		83.15 330	80.60 352	90.80 249	95.74 137	78.27 312	96.81 192	94.92 247	60.10 487	81.89 294	92.54 292	45.82 454	98.82 142	79.25 302	78.32 354	95.31 279

tttt0517		88.57 213	88.19 204	89.71 289	93.00 246	75.99 372	95.67 292	96.67 91	80.78 322	81.82 295	94.40 248	88.97 16	97.58 217	76.05 343	86.31 286	95.57 271

WB-MVSnew		84.08 315	83.51 305	85.80 377	91.34 333	76.69 358	95.62 296	96.27 149	81.77 306	81.81 296	92.81 288	58.23 379	94.70 409	66.66 411	87.06 279	85.99 447

BH-RMVSNet		86.84 257	85.28 268	91.49 217	95.35 153	80.26 240	96.95 178	92.21 413	82.86 285	81.77 297	95.46 192	59.34 371	97.64 211	69.79 397	93.81 166	96.57 237

HQP_MVS		87.50 248	87.09 233	88.74 307	91.86 318	77.96 324	97.18 150	94.69 265	89.89 73	81.33 298	94.15 258	64.77 329	97.30 261	87.08 218	82.82 319	90.96 337

plane_prior3						77.75 337			90.17 70	81.33 298

VPA-MVSNet		85.32 290	83.83 294	89.77 288	90.25 358	82.63 138	96.36 231	97.07 40	83.03 280	81.21 300	89.02 349	61.58 357	96.31 322	85.02 237	70.95 394	90.36 344

GeoE		86.36 266	85.20 269	89.83 285	93.17 239	76.13 366	97.53 120	92.11 414	79.58 355	80.99 301	94.01 261	66.60 314	96.17 330	73.48 371	89.30 237	97.20 196

GA-MVS		85.79 277	84.04 293	91.02 241	89.47 382	80.27 239	96.90 183	94.84 254	85.57 191	80.88 302	89.08 347	56.56 404	96.47 316	77.72 319	85.35 300	96.34 243

dtuonly		84.63 304	84.08 292	86.30 372	86.14 425	69.59 439	92.71 393	90.28 446	82.00 303	80.87 303	94.51 241	62.61 343	96.18 328	79.00 305	88.60 252	93.14 325

1112_ss		88.60 212	87.47 224	92.00 184	93.21 237	80.97 205	96.47 219	92.46 405	83.64 267	80.86 304	97.30 120	80.24 89	97.62 212	77.60 322	85.49 298	97.40 176

dp		84.30 312	82.31 326	90.28 268	94.24 200	77.97 323	86.57 460	95.53 209	79.94 349	80.75 305	85.16 419	71.49 263	96.39 318	63.73 429	83.36 312	96.48 239

Test_1112_low_res		88.03 229	86.73 242	91.94 188	93.15 240	80.88 214	96.44 222	92.41 409	83.59 269	80.74 306	91.16 317	80.18 90	97.59 215	77.48 325	85.40 299	97.36 179

cascas		86.50 262	84.48 282	92.55 139	92.64 270	85.95 49	97.04 168	95.07 241	75.32 407	80.50 307	91.02 319	54.33 420	97.98 188	86.79 225	87.62 274	93.71 317

TAPA-MVS	81.61 12	85.02 297	83.67 297	89.06 299	96.79 105	73.27 401	95.92 267	94.79 258	74.81 412	80.47 308	96.83 142	71.07 266	98.19 176	49.82 485	92.57 183	95.71 265
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OPM-MVS		85.84 275	85.10 274	88.06 330	88.34 398	77.83 331	95.72 288	94.20 318	87.89 112	80.45 309	94.05 260	58.57 376	97.26 265	83.88 245	82.76 321	89.09 377
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
nrg030		86.79 259	85.43 263	90.87 248	88.76 387	85.34 69	97.06 167	94.33 302	84.31 237	80.45 309	91.98 304	72.36 242	96.36 320	88.48 202	71.13 392	90.93 339

EI-MVSNet		85.80 276	85.20 269	87.59 343	91.55 328	77.41 343	95.13 322	95.36 225	80.43 333	80.33 311	94.71 235	73.72 222	95.97 335	76.96 331	78.64 348	89.39 363

MVSTER		89.25 192	88.92 185	90.24 269	95.98 125	84.66 92	96.79 193	95.36 225	87.19 141	80.33 311	90.61 327	90.02 12	95.97 335	85.38 234	78.64 348	90.09 353

ADS-MVSNet2		79.57 379	77.53 383	85.71 381	93.78 215	72.13 412	79.48 487	86.11 479	73.09 427	80.14 313	79.99 466	62.15 349	90.14 471	59.49 450	83.52 309	94.85 293

ADS-MVSNet		81.26 361	78.36 376	89.96 280	93.78 215	79.78 255	79.48 487	93.60 372	73.09 427	80.14 313	79.99 466	62.15 349	95.24 380	59.49 450	83.52 309	94.85 293

test_fmvs2		79.59 378	79.90 364	78.67 453	82.86 460	55.82 496	95.20 316	89.55 452	81.09 315	80.12 315	89.80 338	34.31 487	93.51 435	87.82 208	78.36 353	86.69 435

baseline2		90.39 157	90.21 145	90.93 243	90.86 345	80.99 204	95.20 316	97.41 18	86.03 177	80.07 316	94.61 238	90.58 7	97.47 236	87.29 217	89.86 229	94.35 304

Effi-MVS+-dtu		84.61 306	84.90 278	83.72 414	91.96 314	63.14 474	94.95 330	93.34 387	85.57 191	79.79 317	87.12 384	61.99 354	95.61 362	83.55 254	85.83 295	92.41 330

VPNet		84.69 302	82.92 316	90.01 276	89.01 386	83.45 120	96.71 201	95.46 216	85.71 188	79.65 318	92.18 300	56.66 403	96.01 334	83.05 262	67.84 425	90.56 342

SDMVSNet		87.02 253	85.61 260	91.24 230	94.14 204	83.30 123	93.88 363	95.98 176	84.30 239	79.63 319	92.01 301	58.23 379	97.68 207	90.28 166	82.02 327	92.75 326

sd_testset		84.62 305	83.11 312	89.17 297	94.14 204	77.78 333	91.54 414	94.38 297	84.30 239	79.63 319	92.01 301	52.28 425	96.98 288	77.67 321	82.02 327	92.75 326

CLD-MVS		87.97 232	87.48 223	89.44 293	92.16 300	80.54 230	98.14 70	94.92 247	91.41 48	79.43 321	95.40 194	62.34 345	97.27 264	90.60 154	82.90 318	90.50 343
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IB-MVS	85.34 4	88.67 209	87.14 232	93.26 96	93.12 243	84.32 99	98.76 38	97.27 23	87.19 141	79.36 322	90.45 329	83.92 60	98.53 156	84.41 240	69.79 405	96.93 217
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
PatchMatch-RL		85.00 298	83.66 298	89.02 301	95.86 131	74.55 388	92.49 395	93.60 372	79.30 361	79.29 323	91.47 311	58.53 377	98.45 163	70.22 395	92.17 196	94.07 311

CNLPA		86.96 254	85.37 265	91.72 205	97.59 82	79.34 272	97.21 146	91.05 437	74.22 416	78.90 324	96.75 148	67.21 307	98.95 135	74.68 359	90.77 219	96.88 222

MVS		90.60 147	88.64 189	96.50 6	94.25 199	90.53 9	93.33 378	97.21 27	77.59 383	78.88 325	97.31 117	71.52 262	99.69 67	89.60 175	98.03 62	99.27 23

mvs_anonymous		88.68 208	87.62 217	91.86 191	94.80 176	81.69 182	93.53 373	94.92 247	82.03 302	78.87 326	90.43 330	75.77 179	95.34 372	85.04 236	93.16 177	98.55 65

UWE-MVS-28		85.41 288	86.36 248	82.59 427	91.12 338	66.81 457	93.88 363	97.03 43	83.86 257	78.55 327	93.84 269	77.76 133	88.55 477	73.47 372	87.69 273	92.41 330

tpm cat1		83.63 322	81.38 340	90.39 262	93.53 228	78.19 319	85.56 468	95.09 239	70.78 447	78.51 328	83.28 439	74.80 205	97.03 281	66.77 410	84.05 307	95.95 253

UniMVSNet (Re)		85.31 291	84.23 287	88.55 311	89.75 372	80.55 226	96.71 201	96.89 58	85.42 197	78.40 329	88.93 350	75.38 192	95.52 366	78.58 309	68.02 422	89.57 362

FIs		86.73 261	86.10 252	88.61 310	90.05 365	80.21 242	96.14 253	96.95 52	85.56 193	78.37 330	92.30 296	76.73 156	95.28 376	79.51 295	79.27 342	90.35 345

WBMVS		87.73 239	86.79 241	90.56 256	95.61 142	85.68 59	97.63 109	95.52 211	83.77 260	78.30 331	88.44 361	86.14 36	95.78 348	82.54 265	73.15 383	90.21 348

BH-w/o		88.24 223	87.47 224	90.54 258	95.03 170	78.54 301	97.41 133	93.82 347	84.08 246	78.23 332	94.51 241	69.34 286	97.21 268	80.21 289	94.58 151	95.87 257

MonoMVSNet		85.68 279	84.22 288	90.03 275	88.43 397	77.83 331	92.95 389	91.46 427	87.28 134	78.11 333	85.96 406	66.31 317	94.81 405	90.71 152	76.81 359	97.46 167

UniMVSNet_NR-MVSNet		85.49 285	84.59 279	88.21 326	89.44 383	79.36 270	96.71 201	96.41 131	85.22 202	78.11 333	90.98 321	76.97 151	95.14 388	79.14 303	68.30 419	90.12 351

DU-MVS		84.57 307	83.33 308	88.28 319	88.76 387	79.36 270	96.43 224	95.41 224	85.42 197	78.11 333	90.82 322	67.61 299	95.14 388	79.14 303	68.30 419	90.33 346

dmvs_re		84.10 314	82.90 317	87.70 337	91.41 332	73.28 399	90.59 424	93.19 391	85.02 213	77.96 336	93.68 273	57.92 387	96.18 328	75.50 351	80.87 331	93.63 318

miper_enhance_ethall		85.95 274	85.20 269	88.19 327	94.85 174	79.76 256	96.00 261	94.06 328	82.98 282	77.74 337	88.76 352	79.42 99	95.46 368	80.58 283	72.42 385	89.36 369

v1144		82.90 336	81.27 342	87.78 336	86.29 421	79.07 282	96.14 253	93.93 334	80.05 346	77.38 338	86.80 389	65.50 320	95.93 340	75.21 355	70.13 400	88.33 408

FC-MVSNet-test		85.96 273	85.39 264	87.66 340	89.38 384	78.02 321	95.65 294	96.87 61	85.12 210	77.34 339	91.94 308	76.28 167	94.74 408	77.09 328	78.82 346	90.21 348

v2v482		83.46 324	81.86 333	88.25 322	86.19 423	79.65 263	96.34 233	94.02 331	81.56 309	77.32 340	88.23 365	65.62 319	96.03 332	77.77 317	69.72 407	89.09 377

Baseline_NR-MVSNet		81.22 362	80.07 360	84.68 398	85.32 438	75.12 383	96.48 218	88.80 461	76.24 402	77.28 341	86.40 399	67.61 299	94.39 419	75.73 347	66.73 436	84.54 460

usedtu_dtu_shiyan1		85.03 295	83.24 309	90.37 263	86.62 415	86.24 43	96.23 243	95.30 230	84.55 228	77.22 342	88.47 359	67.85 295	95.27 377	76.59 334	76.35 360	89.61 360

FE-MVSNET3		85.03 295	83.24 309	90.37 263	86.62 415	86.24 43	96.23 243	95.30 230	84.55 228	77.22 342	88.47 359	67.85 295	95.27 377	76.59 334	76.35 360	89.61 360

V42		83.04 333	81.53 338	87.57 345	86.27 422	79.09 281	95.87 281	94.11 324	80.35 337	77.22 342	86.79 390	65.32 324	96.02 333	77.74 318	70.14 399	87.61 421

v144192		82.43 342	80.73 349	87.54 346	85.81 431	78.22 314	95.98 262	93.78 353	79.09 366	77.11 345	86.49 394	64.66 333	95.91 341	74.20 365	69.42 408	88.49 402

ACMM	80.70 13	83.72 321	82.85 319	86.31 370	91.19 335	72.12 413	95.88 280	94.29 304	80.44 331	77.02 346	91.96 305	55.24 413	97.14 278	79.30 301	80.38 334	89.67 359
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v1192		82.31 346	80.55 353	87.60 342	85.94 428	78.47 305	95.85 283	93.80 351	79.33 359	76.97 347	86.51 393	63.33 340	95.87 342	73.11 374	70.13 400	88.46 404

PCF-MVS	84.09 5	86.77 260	85.00 275	92.08 174	92.06 309	83.07 128	92.14 402	94.47 285	79.63 354	76.90 348	94.78 232	71.15 265	99.20 116	72.87 375	91.05 214	93.98 312
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
cl22		85.11 294	84.17 289	87.92 333	95.06 169	78.82 287	95.51 300	94.22 313	79.74 352	76.77 349	87.92 370	75.96 174	95.68 355	79.93 293	72.42 385	89.27 371

v1921920		82.02 349	80.23 357	87.41 350	85.62 432	77.92 327	95.79 287	93.69 365	78.86 370	76.67 350	86.44 396	62.50 344	95.83 344	72.69 376	69.77 406	88.47 403

WR-MVS		84.32 311	82.96 315	88.41 313	89.38 384	80.32 236	96.59 208	96.25 152	83.97 250	76.63 351	90.36 331	67.53 302	94.86 403	75.82 346	70.09 403	90.06 355

BH-untuned		86.95 255	85.94 253	89.99 277	94.52 185	77.46 342	96.78 195	93.37 386	81.80 305	76.62 352	93.81 272	66.64 313	97.02 282	76.06 342	93.88 165	95.48 275

SSC-MVS3.2		81.06 364	79.49 369	85.75 380	89.78 370	73.00 404	94.40 345	95.23 235	83.76 261	76.61 353	87.82 372	49.48 439	94.88 401	66.80 409	71.56 390	89.38 365

v1240		81.70 354	79.83 365	87.30 354	85.50 433	77.70 339	95.48 301	93.44 379	78.46 375	76.53 354	86.44 396	60.85 362	95.84 343	71.59 383	70.17 398	88.35 407

PS-MVSNAJss		84.91 299	84.30 286	86.74 361	85.89 430	74.40 390	94.95 330	94.16 321	83.93 253	76.45 355	90.11 337	71.04 267	95.77 349	83.16 260	79.02 345	90.06 355

miper_ehance_all_eth		84.57 307	83.60 303	87.50 347	92.64 270	78.25 313	95.40 306	93.47 378	79.28 362	76.41 356	87.64 375	76.53 159	95.24 380	78.58 309	72.42 385	89.01 389

LPG-MVS_test		84.20 313	83.49 306	86.33 367	90.88 342	73.06 402	95.28 308	94.13 322	82.20 297	76.31 357	93.20 280	54.83 417	96.95 290	83.72 250	80.83 332	88.98 390

LGP-MVS_train				86.33 367	90.88 342	73.06 402		94.13 322	82.20 297	76.31 357	93.20 280	54.83 417	96.95 290	83.72 250	80.83 332	88.98 390

F-COLMAP		84.50 309	83.44 307	87.67 339	95.22 157	72.22 408	95.95 264	93.78 353	75.74 403	76.30 359	95.18 208	59.50 369	98.45 163	72.67 377	86.59 284	92.35 332

tpmvs		83.04 333	80.77 348	89.84 284	95.43 149	77.96 324	85.59 467	95.32 229	75.31 408	76.27 360	83.70 434	73.89 218	97.41 247	59.53 449	81.93 329	94.14 308

tt0805		81.20 363	79.06 373	87.61 341	86.50 417	72.97 405	93.66 367	95.48 214	74.11 417	76.23 361	91.99 303	41.36 471	97.40 249	77.44 326	74.78 372	92.45 329

3Dnovator	82.32 10	89.33 189	87.64 215	94.42 41	93.73 218	85.70 57	97.73 103	96.75 80	86.73 159	76.21 362	95.93 163	62.17 346	99.68 70	81.67 273	97.81 69	97.88 118

TranMVSNet+NR-MVSNet		83.24 329	81.71 335	87.83 334	87.71 405	78.81 289	96.13 255	94.82 255	84.52 230	76.18 363	90.78 324	64.07 334	94.60 413	74.60 362	66.59 438	90.09 353

c3_l		83.80 319	82.65 322	87.25 355	92.10 305	77.74 338	95.25 313	93.04 399	78.58 373	76.01 364	87.21 383	75.25 198	95.11 390	77.54 324	68.89 413	88.91 395

1314		88.94 200	87.20 229	94.17 54	93.21 237	85.73 56	93.33 378	96.64 98	82.89 283	75.98 365	96.36 155	66.83 312	99.39 97	83.52 257	96.02 132	97.39 177

Fast-Effi-MVS+-dtu		83.33 326	82.60 323	85.50 386	89.55 380	69.38 442	96.09 256	91.38 428	82.30 296	75.96 366	91.41 312	56.71 401	95.58 364	75.13 356	84.90 303	91.54 333

XXY-MVS		83.84 318	82.00 331	89.35 294	87.13 410	81.38 191	95.72 288	94.26 308	80.15 342	75.92 367	90.63 326	61.96 355	96.52 314	78.98 306	73.28 381	90.14 350

GBi-Net		82.42 343	80.43 355	88.39 315	92.66 266	81.95 164	94.30 350	93.38 383	79.06 367	75.82 368	85.66 407	56.38 406	93.84 428	71.23 386	75.38 367	89.38 365

test1		82.42 343	80.43 355	88.39 315	92.66 266	81.95 164	94.30 350	93.38 383	79.06 367	75.82 368	85.66 407	56.38 406	93.84 428	71.23 386	75.38 367	89.38 365

FMVSNet3		84.71 301	82.71 321	90.70 253	94.55 183	87.71 26	95.92 267	94.67 268	81.73 307	75.82 368	88.08 368	66.99 309	94.47 416	71.23 386	75.38 367	89.91 357

eth_miper_zixun_eth		83.12 331	82.01 330	86.47 366	91.85 320	74.80 384	94.33 348	93.18 393	79.11 365	75.74 371	87.25 382	72.71 235	95.32 374	76.78 332	67.13 432	89.27 371

IterMVS-LS		83.93 317	82.80 320	87.31 353	91.46 331	77.39 344	95.66 293	93.43 381	80.44 331	75.51 372	87.26 381	73.72 222	95.16 385	76.99 329	70.72 396	89.39 363
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
3Dnovator+	82.88 8	89.63 180	87.85 210	94.99 25	94.49 191	86.76 38	97.84 93	95.74 197	86.10 173	75.47 373	96.02 162	65.00 326	99.51 91	82.91 263	97.07 99	98.72 56

test_djsdf		83.00 335	82.45 325	84.64 400	84.07 451	69.78 437	94.80 336	94.48 282	80.74 323	75.41 374	87.70 373	61.32 361	95.10 391	83.77 248	79.76 335	89.04 383

v148		82.41 345	80.89 346	86.99 359	86.18 424	76.81 355	96.27 238	93.82 347	80.49 330	75.28 375	86.11 405	67.32 306	95.75 351	75.48 352	67.03 434	88.42 406

QAPM		86.88 256	84.51 280	93.98 58	94.04 210	85.89 52	97.19 149	96.05 169	73.62 421	75.12 376	95.62 181	62.02 353	99.74 55	70.88 390	96.06 130	96.30 247

VortexMVS		85.45 287	84.40 284	88.63 309	93.25 235	81.66 183	95.39 307	94.34 299	87.15 144	75.10 377	87.65 374	66.58 315	95.19 382	86.89 222	73.21 382	89.03 385

UniMVSNet_ETH3D		80.86 368	78.75 375	87.22 356	86.31 420	72.02 414	91.95 404	93.76 358	73.51 422	75.06 378	90.16 335	43.04 463	95.66 356	76.37 340	78.55 351	93.98 312

cl____		83.27 327	82.12 328	86.74 361	92.20 295	75.95 373	95.11 324	93.27 389	78.44 376	74.82 379	87.02 386	74.19 214	95.19 382	74.67 360	69.32 409	89.09 377

DIV-MVS_self_test		83.27 327	82.12 328	86.74 361	92.19 297	75.92 375	95.11 324	93.26 390	78.44 376	74.81 380	87.08 385	74.19 214	95.19 382	74.66 361	69.30 410	89.11 376

FMVSNet2		82.79 337	80.44 354	89.83 285	92.66 266	85.43 67	95.42 304	94.35 298	79.06 367	74.46 381	87.28 379	56.38 406	94.31 420	69.72 398	74.68 373	89.76 358

MIMVSNet		79.18 384	75.99 395	88.72 308	87.37 409	80.66 220	79.96 485	91.82 418	77.38 386	74.33 382	81.87 452	41.78 467	90.74 465	66.36 417	83.10 314	94.76 295

RPSCF		77.73 400	76.63 391	81.06 439	88.66 393	55.76 497	87.77 451	87.88 467	64.82 468	74.14 383	92.79 290	49.22 440	96.81 303	67.47 406	76.88 358	90.62 341

ACMP	81.66 11	84.00 316	83.22 311	86.33 367	91.53 330	72.95 406	95.91 272	93.79 352	83.70 264	73.79 384	92.22 297	54.31 421	96.89 296	83.98 244	79.74 337	89.16 375
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
reproduce_monomvs		87.80 236	87.60 219	88.40 314	96.56 107	80.26 240	95.80 286	96.32 146	91.56 47	73.60 385	88.36 362	88.53 19	96.25 325	90.47 156	67.23 431	88.67 397

pmmvs5		81.34 359	79.54 367	86.73 364	85.02 440	76.91 352	96.22 245	91.65 424	77.65 382	73.55 386	88.61 354	55.70 410	94.43 418	74.12 366	73.35 380	88.86 396

jajsoiax		82.12 348	81.15 344	85.03 394	84.19 449	70.70 429	94.22 355	93.95 332	83.07 277	73.48 387	89.75 339	49.66 438	95.37 371	82.24 270	79.76 335	89.02 387

Syy-MVS		77.97 398	78.05 379	77.74 457	92.13 303	56.85 492	93.97 359	94.23 311	82.43 293	73.39 388	93.57 276	57.95 385	87.86 482	32.40 512	82.34 324	88.51 400

myMVS_eth3d		81.93 350	82.18 327	81.18 438	92.13 303	67.18 452	93.97 359	94.23 311	82.43 293	73.39 388	93.57 276	76.98 150	87.86 482	50.53 483	82.34 324	88.51 400

mvs_tets		81.74 353	80.71 350	84.84 395	84.22 448	70.29 433	93.91 362	93.78 353	82.77 287	73.37 390	89.46 345	47.36 450	95.31 375	81.99 271	79.55 341	88.92 394

pmmvs4		82.54 341	80.79 347	87.79 335	86.11 426	80.49 234	93.55 372	93.18 393	77.29 387	73.35 391	89.40 346	65.26 325	95.05 398	75.32 354	73.61 377	87.83 416

LS3D		82.22 347	79.94 363	89.06 299	97.43 91	74.06 393	93.20 384	92.05 415	61.90 477	73.33 392	95.21 205	59.35 370	99.21 111	54.54 471	92.48 186	93.90 314

v10		81.43 358	79.53 368	87.11 357	86.38 418	78.87 285	94.31 349	93.43 381	77.88 379	73.24 393	85.26 415	65.44 321	95.75 351	72.14 380	67.71 426	86.72 434

v8		81.88 351	80.06 361	87.32 352	86.63 414	79.04 283	94.41 342	93.65 367	78.77 371	73.19 394	85.57 411	66.87 311	95.81 345	73.84 369	67.61 427	87.11 430

test0.0.03 1		82.79 337	82.48 324	83.74 413	86.81 413	72.22 408	96.52 215	95.03 243	83.76 261	73.00 395	93.20 280	72.30 245	88.88 475	64.15 427	77.52 357	90.12 351

anonymousdsp		80.98 367	79.97 362	84.01 408	81.73 463	70.44 432	92.49 395	93.58 374	77.10 391	72.98 396	86.31 400	57.58 393	94.90 400	79.32 300	78.63 350	86.69 435

XVG-ACMP-BASELINE		79.38 382	77.90 381	83.81 410	84.98 441	67.14 456	89.03 438	93.18 393	80.26 341	72.87 397	88.15 367	38.55 477	96.26 323	76.05 343	78.05 355	88.02 413

WR-MVS_H		81.02 365	80.09 358	83.79 411	88.08 401	71.26 427	94.46 340	96.54 114	80.08 345	72.81 398	86.82 388	70.36 277	92.65 441	64.18 426	67.50 428	87.46 427

OpenMVS	79.58 14	86.09 271	83.62 302	93.50 87	90.95 341	86.71 39	97.44 128	95.83 192	75.35 406	72.64 399	95.72 171	57.42 397	99.64 74	71.41 384	95.85 136	94.13 309

Anonymous20231211		79.72 377	77.19 386	87.33 351	95.59 144	77.16 350	95.18 319	94.18 320	59.31 491	72.57 400	86.20 403	47.89 447	95.66 356	74.53 363	69.24 411	89.18 374

CP-MVSNet		81.01 366	80.08 359	83.79 411	87.91 403	70.51 430	94.29 354	95.65 203	80.83 320	72.54 401	88.84 351	63.71 336	92.32 446	68.58 403	68.36 418	88.55 399

IMVS_0404		85.34 289	83.69 295	90.29 267	92.30 284	78.81 289	90.62 423	93.84 343	85.14 206	72.51 402	94.49 243	54.36 419	94.61 412	81.33 274	88.61 248	97.46 167

miper_lstm_enhance		81.66 356	80.66 351	84.67 399	91.19 335	71.97 416	91.94 405	93.19 391	77.86 380	72.27 403	85.26 415	73.46 225	93.42 436	73.71 370	67.05 433	88.61 398

PS-CasMVS		80.27 373	79.18 370	83.52 417	87.56 407	69.88 436	94.08 357	95.29 232	80.27 340	72.08 404	88.51 358	59.22 373	92.23 448	67.49 405	68.15 421	88.45 405

FMVSNet1		79.50 380	76.54 392	88.39 315	88.47 395	81.95 164	94.30 350	93.38 383	73.14 426	72.04 405	85.66 407	43.86 457	93.84 428	65.48 419	72.53 384	89.38 365

SD_0403		81.29 360	81.13 345	81.78 435	90.20 360	60.43 483	89.97 428	91.31 433	83.87 255	71.78 406	93.08 285	63.86 335	89.61 472	60.00 448	86.07 292	95.30 280

mvs5depth		71.40 440	68.36 445	80.54 443	75.31 494	65.56 462	79.94 486	85.14 482	69.11 456	71.75 407	81.59 453	41.02 473	93.94 426	60.90 444	50.46 488	82.10 478

gbinet_0.2-2-1-0.02		78.67 390	75.67 400	87.70 337	80.38 469	79.60 265	96.25 241	94.03 330	72.51 435	71.41 408	83.33 438	55.97 409	94.45 417	73.37 373	53.73 480	89.04 383

PEN-MVS		79.47 381	78.26 378	83.08 420	86.36 419	68.58 445	93.85 365	94.77 259	79.76 351	71.37 409	88.55 355	59.79 365	92.46 442	64.50 424	65.40 443	88.19 410

testing3		80.74 369	81.17 343	79.44 448	91.15 337	63.48 472	97.16 154	95.76 195	80.83 320	71.36 410	93.15 283	78.22 123	87.30 487	43.19 497	79.67 338	87.55 425

Patchmtry		77.36 405	74.59 410	85.67 382	89.75 372	75.75 377	77.85 494	91.12 434	60.28 485	71.23 411	80.35 463	75.45 188	93.56 434	57.94 456	67.34 430	87.68 419

IterMVS		80.67 370	79.16 371	85.20 391	89.79 369	76.08 367	92.97 388	91.86 417	80.28 339	71.20 412	85.14 420	57.93 386	91.34 459	72.52 378	70.74 395	88.18 411
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
blend_shiyan4		81.76 352	79.58 366	88.31 318	80.00 471	80.59 222	95.95 264	93.73 361	72.26 439	71.14 413	82.52 443	76.13 171	95.15 386	77.83 312	66.62 437	89.19 373

DP-MVS		81.47 357	78.28 377	91.04 238	98.14 62	78.48 302	95.09 327	86.97 471	61.14 483	71.12 414	92.78 291	59.59 367	99.38 98	53.11 475	86.61 283	95.27 282

IterMVS-SCA-FT		80.51 372	79.10 372	84.73 397	89.63 378	74.66 385	92.98 387	91.81 419	80.05 346	71.06 415	85.18 418	58.04 382	91.40 458	72.48 379	70.70 397	88.12 412

v7n		79.32 383	77.34 384	85.28 390	84.05 452	72.89 407	93.38 375	93.87 340	75.02 411	70.68 416	84.37 427	59.58 368	95.62 361	67.60 404	67.50 428	87.32 429

MS-PatchMatch		83.05 332	81.82 334	86.72 365	89.64 377	79.10 280	94.88 332	94.59 277	79.70 353	70.67 417	89.65 341	50.43 434	96.82 302	70.82 393	95.99 134	84.25 463

DTE-MVSNet		78.37 392	77.06 387	82.32 431	85.22 439	67.17 455	93.40 374	93.66 366	78.71 372	70.53 418	88.29 364	59.06 374	92.23 448	61.38 440	63.28 453	87.56 423

pm-mvs1		80.05 374	78.02 380	86.15 373	85.42 434	75.81 376	95.11 324	92.69 404	77.13 389	70.36 419	87.43 377	58.44 378	95.27 377	71.36 385	64.25 448	87.36 428

wanda-best-256-512		78.87 386	75.75 397	88.22 324	79.74 472	80.51 232	95.92 267	93.75 359	72.60 432	70.34 420	82.14 444	57.91 388	95.09 393	75.61 348	53.77 476	89.05 380

FE-blended-shiyan7		78.87 386	75.75 397	88.22 324	79.74 472	80.51 232	95.92 267	93.75 359	72.60 432	70.34 420	82.14 444	57.91 388	95.09 393	75.61 348	53.77 476	89.05 380

usedtu_blend_shiyan5		77.51 403	73.93 418	88.26 320	79.74 472	80.59 222	90.76 422	89.69 450	63.21 470	70.34 420	82.14 444	57.91 388	95.15 386	77.83 312	53.77 476	89.05 380

blended_shiyan8		78.76 388	75.65 401	88.10 328	79.58 477	80.20 243	95.70 291	93.71 364	72.43 437	70.26 423	82.12 447	57.66 392	95.08 395	75.57 350	53.80 475	89.02 387

D2MVS		82.67 339	81.55 337	86.04 375	87.77 404	76.47 359	95.21 315	96.58 107	82.66 290	70.26 423	85.46 414	60.39 363	95.80 346	76.40 339	79.18 343	85.83 450

PVSNet_0	77.72 15	81.70 354	78.95 374	89.94 281	90.77 349	76.72 357	95.96 263	96.95 52	85.01 214	70.24 425	88.53 357	52.32 424	98.20 175	86.68 226	44.08 502	94.89 291

blended_shiyan6		78.74 389	75.63 402	88.07 329	79.63 476	80.10 248	95.72 288	93.73 361	72.43 437	70.17 426	82.09 449	57.69 391	95.07 396	75.47 353	53.77 476	89.03 385

CL-MVSNet_self_test		75.81 414	74.14 416	80.83 441	78.33 482	67.79 449	94.22 355	93.52 376	77.28 388	69.82 427	81.54 455	61.47 360	89.22 474	57.59 459	53.51 481	85.48 452

tfpnnormal		78.14 394	75.42 403	86.31 370	88.33 399	79.24 273	94.41 342	96.22 155	73.51 422	69.81 428	85.52 413	55.43 411	95.75 351	47.65 490	67.86 424	83.95 466

EU-MVSNet		76.92 409	76.95 388	76.83 463	84.10 450	54.73 499	91.77 409	92.71 403	72.74 430	69.57 429	88.69 353	58.03 384	87.43 486	64.91 422	70.00 404	88.33 408

ITE_SJBPF				82.38 429	87.00 411	65.59 461		89.55 452	79.99 348	69.37 430	91.30 315	41.60 469	95.33 373	62.86 435	74.63 374	86.24 441

DSMNet-mixed		73.13 429	72.45 424	75.19 470	77.51 485	46.82 504	85.09 472	82.01 497	67.61 463	69.27 431	81.33 457	50.89 429	86.28 490	54.54 471	83.80 308	92.46 328

MVP-Stereo		82.65 340	81.67 336	85.59 385	86.10 427	78.29 310	93.33 378	92.82 401	77.75 381	69.17 432	87.98 369	59.28 372	95.76 350	71.77 381	96.88 106	82.73 472
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
sc_t1		72.37 434	68.03 446	85.39 388	83.78 455	70.51 430	91.27 416	83.70 492	52.46 500	68.29 433	82.02 450	30.58 495	94.81 405	64.50 424	55.69 467	90.85 340

MSDG		80.62 371	77.77 382	89.14 298	93.43 231	77.24 346	91.89 406	90.18 447	69.86 453	68.02 434	91.94 308	52.21 426	98.84 141	59.32 452	83.12 313	91.35 334

NR-MVSNet		83.35 325	81.52 339	88.84 304	88.76 387	81.31 194	94.45 341	95.16 237	84.65 224	67.81 435	90.82 322	70.36 277	94.87 402	74.75 358	66.89 435	90.33 346

TransMVSNet (Re)		76.94 408	74.38 412	84.62 401	85.92 429	75.25 382	95.28 308	89.18 457	73.88 420	67.22 436	86.46 395	59.64 366	94.10 423	59.24 453	52.57 485	84.50 461

Anonymous20231206		75.29 417	73.64 419	80.22 444	80.75 465	63.38 473	93.36 376	90.71 444	73.09 427	67.12 437	83.70 434	50.33 435	90.85 464	53.63 474	70.10 402	86.44 438

ppachtmachnet_test		77.19 406	74.22 414	86.13 374	85.39 435	78.22 314	93.98 358	91.36 430	71.74 443	67.11 438	84.87 424	56.67 402	93.37 438	52.21 476	64.59 445	86.80 433

KD-MVS_2432*1600		77.63 401	74.92 407	85.77 378	90.86 345	79.44 267	88.08 447	93.92 336	76.26 400	67.05 439	82.78 441	72.15 250	91.92 451	61.53 437	41.62 505	85.94 448

miper_refine_blended		77.63 401	74.92 407	85.77 378	90.86 345	79.44 267	88.08 447	93.92 336	76.26 400	67.05 439	82.78 441	72.15 250	91.92 451	61.53 437	41.62 505	85.94 448

Patchmatch-test		78.25 393	74.72 409	88.83 305	91.20 334	74.10 392	73.91 502	88.70 464	59.89 488	66.82 441	85.12 421	78.38 119	94.54 414	48.84 488	79.58 340	97.86 122

test_fmvs3		69.56 446	69.19 442	70.67 474	69.01 503	47.05 503	90.87 420	86.81 473	71.31 446	66.79 442	77.15 478	16.40 506	83.17 499	81.84 272	62.51 455	81.79 483

LTVRE_ROB	73.68 18	77.99 396	75.74 399	84.74 396	90.45 354	72.02 414	86.41 462	91.12 434	72.57 434	66.63 443	87.27 380	54.95 416	96.98 288	56.29 465	75.98 362	85.21 454
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
OurMVSNet-221017-0		77.18 407	76.06 394	80.55 442	83.78 455	60.00 486	90.35 425	91.05 437	77.01 393	66.62 444	87.92 370	47.73 448	94.03 424	71.63 382	68.44 417	87.62 420

testgi		74.88 419	73.40 420	79.32 449	80.13 470	61.75 478	93.21 383	86.64 476	79.49 357	66.56 445	91.06 318	35.51 485	88.67 476	56.79 464	71.25 391	87.56 423

LCM-MVSNet-Re		83.75 320	83.54 304	84.39 407	93.54 223	64.14 468	92.51 394	84.03 490	83.90 254	66.14 446	86.59 392	67.36 305	92.68 440	84.89 238	92.87 180	96.35 242

pmmvs6		74.65 420	71.67 428	83.60 416	79.13 479	69.94 435	93.31 381	90.88 441	61.05 484	65.83 447	84.15 430	43.43 459	94.83 404	66.62 412	60.63 458	86.02 446

our_test_3		77.90 399	75.37 404	85.48 387	85.39 435	76.74 356	93.63 368	91.67 423	73.39 425	65.72 448	84.65 426	58.20 381	93.13 439	57.82 457	67.87 423	86.57 437

ttmdpeth		69.58 445	66.92 450	77.54 459	75.95 493	62.40 476	88.09 446	84.32 487	62.87 473	65.70 449	86.25 402	36.53 480	88.53 478	55.65 469	46.96 498	81.70 484

COLMAP_ROB	73.24 19	75.74 415	73.00 423	83.94 409	92.38 277	69.08 443	91.85 408	86.93 472	61.48 480	65.32 450	90.27 332	42.27 465	96.93 293	50.91 481	75.63 366	85.80 451
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FMVSNet5		76.46 411	74.16 415	83.35 419	90.05 365	76.17 365	89.58 432	89.85 449	71.39 445	65.29 451	80.42 462	50.61 433	87.70 485	61.05 443	69.24 411	86.18 442

ACMH+	76.62 16	77.47 404	74.94 406	85.05 393	91.07 340	71.58 423	93.26 382	90.01 448	71.80 442	64.76 452	88.55 355	41.62 468	96.48 315	62.35 436	71.00 393	87.09 431

Patchmatch-RL test		76.65 410	74.01 417	84.55 402	77.37 486	64.23 467	78.49 493	82.84 495	78.48 374	64.63 453	73.40 490	76.05 173	91.70 457	76.99 329	57.84 463	97.72 136

SixPastTwentyTwo		76.04 412	74.32 413	81.22 437	84.54 444	61.43 481	91.16 417	89.30 456	77.89 378	64.04 454	86.31 400	48.23 442	94.29 421	63.54 432	63.84 451	87.93 415

AllTest		75.92 413	73.06 422	84.47 403	92.18 298	67.29 450	91.07 418	84.43 485	67.63 459	63.48 455	90.18 333	38.20 478	97.16 272	57.04 461	73.37 378	88.97 392

TestCases				84.47 403	92.18 298	67.29 450		84.43 485	67.63 459	63.48 455	90.18 333	38.20 478	97.16 272	57.04 461	73.37 378	88.97 392

ACMH	75.40 17	77.99 396	74.96 405	87.10 358	90.67 350	76.41 362	93.19 385	91.64 425	72.47 436	63.44 457	87.61 376	43.34 460	97.16 272	58.34 455	73.94 375	87.72 417
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ET-MVSNet_ETH3D		90.01 167	89.03 178	92.95 113	94.38 196	86.77 37	98.14 70	96.31 147	89.30 81	63.33 458	96.72 149	90.09 11	93.63 433	90.70 153	82.29 326	98.46 68

USDC		78.65 391	76.25 393	85.85 376	87.58 406	74.60 387	89.58 432	90.58 445	84.05 247	63.13 459	88.23 365	40.69 476	96.86 301	66.57 414	75.81 365	86.09 444

LF4IMVS		72.36 435	70.82 432	76.95 462	79.18 478	56.33 493	86.12 464	86.11 479	69.30 455	63.06 460	86.66 391	33.03 490	92.25 447	65.33 420	68.64 415	82.28 477

dmvs_testset		72.00 438	73.36 421	67.91 477	83.83 454	31.90 524	85.30 470	77.12 504	82.80 286	63.05 461	92.46 293	61.54 358	82.55 501	42.22 500	71.89 389	89.29 370

KD-MVS_self_test		70.97 442	69.31 441	75.95 468	76.24 492	55.39 498	87.45 452	90.94 440	70.20 451	62.96 462	77.48 475	44.01 456	88.09 480	61.25 441	53.26 482	84.37 462

tt0320		70.21 443	66.07 452	82.64 425	83.42 458	70.82 428	89.63 430	84.10 488	49.75 503	62.71 463	77.28 477	33.35 488	92.45 444	58.78 454	55.62 468	84.64 459

Anonymous20240521		72.06 437	69.91 438	78.50 455	77.11 487	61.67 480	91.62 413	90.97 439	65.52 466	62.37 464	79.05 469	36.32 481	90.96 463	57.75 458	68.52 416	82.87 469

test_0402		72.68 431	69.54 440	82.09 432	88.67 392	71.81 420	92.72 392	86.77 475	61.52 479	62.21 465	83.91 432	43.22 461	93.76 431	34.60 508	72.23 388	80.72 489

OpenMVS_ROB	68.52 20	73.02 430	69.57 439	83.37 418	80.54 468	71.82 419	93.60 371	88.22 465	62.37 474	61.98 466	83.15 440	35.31 486	95.47 367	45.08 495	75.88 364	82.82 470

MVS-HIRNet		71.36 441	67.00 448	84.46 405	90.58 351	69.74 438	79.15 490	87.74 468	46.09 504	61.96 467	50.50 520	45.14 455	95.64 359	53.74 473	88.11 269	88.00 414

tt0320-xc		69.70 444	65.27 457	82.99 421	84.33 446	71.92 417	89.56 434	82.08 496	50.11 501	61.87 468	77.50 474	30.48 496	92.34 445	60.30 446	51.20 487	84.71 458

test20.03		72.36 435	71.15 431	75.98 467	77.79 483	59.16 488	92.40 398	89.35 455	74.09 418	61.50 469	84.32 428	48.09 443	85.54 494	50.63 482	62.15 456	83.24 467

mvsany_test3		67.19 454	65.34 456	72.72 472	63.08 510	48.57 502	83.12 479	78.09 503	72.07 440	61.21 470	77.11 479	22.94 501	87.78 484	78.59 308	51.88 486	81.80 482

PM-MVS		69.32 449	66.93 449	76.49 464	73.60 498	55.84 495	85.91 465	79.32 502	74.72 413	61.09 471	78.18 472	21.76 502	91.10 462	70.86 391	56.90 466	82.51 473

TDRefinement		69.20 451	65.78 455	79.48 447	66.04 508	62.21 477	88.21 444	86.12 478	62.92 472	61.03 472	85.61 410	33.23 489	94.16 422	55.82 468	53.02 483	82.08 479

ambc				76.02 466	68.11 505	51.43 500	64.97 510	89.59 451		60.49 473	74.49 487	17.17 505	92.46 442	61.50 439	52.85 484	84.17 464

pmmvs-eth3d		73.59 424	70.66 434	82.38 429	76.40 490	73.38 396	89.39 436	89.43 454	72.69 431	60.34 474	77.79 473	46.43 453	91.26 461	66.42 416	57.06 465	82.51 473

test_vis1_rt		73.96 421	72.40 425	78.64 454	83.91 453	61.16 482	95.63 295	68.18 512	76.32 399	60.09 475	74.77 485	29.01 498	97.54 226	87.74 211	75.94 363	77.22 494

kuosan		73.55 425	72.39 426	77.01 461	89.68 376	66.72 458	85.24 471	93.44 379	67.76 458	60.04 476	83.40 437	71.90 256	84.25 496	45.34 494	54.75 469	80.06 490

dtuonlycased		72.49 432	71.58 430	75.22 469	81.04 464	64.71 464	92.43 397	86.46 477	75.62 405	59.79 477	78.43 471	48.54 441	85.84 492	63.66 431	58.28 461	75.10 496

FE-MVSNET2		73.72 422	70.80 433	82.46 428	74.97 495	73.81 394	91.88 407	91.73 422	76.70 397	59.74 478	77.41 476	42.26 466	90.52 467	64.75 423	57.79 464	83.06 468

K. test v3		73.62 423	71.59 429	79.69 446	82.98 459	59.85 487	90.85 421	88.83 460	77.13 389	58.90 479	82.11 448	43.62 458	91.72 456	65.83 418	54.10 474	87.50 426

EG-PatchMatch MVS		74.92 418	72.02 427	83.62 415	83.76 457	73.28 399	93.62 369	92.04 416	68.57 457	58.88 480	83.80 433	31.87 492	95.57 365	56.97 463	78.67 347	82.00 481

lessismore_v0				79.98 445	80.59 467	58.34 490		80.87 498		58.49 481	83.46 436	43.10 462	93.89 427	63.11 434	48.68 492	87.72 417

N_pmnet		61.30 460	60.20 464	64.60 483	84.32 447	17.00 539	91.67 412	10.98 539	61.77 478	58.45 482	78.55 470	49.89 437	91.83 454	42.27 499	63.94 450	84.97 456

TinyColmap		72.41 433	68.99 443	82.68 424	88.11 400	69.59 439	88.41 443	85.20 481	65.55 465	57.91 483	84.82 425	30.80 494	95.94 339	51.38 478	68.70 414	82.49 475

UnsupCasMVSNet_eth		73.25 428	70.57 435	81.30 436	77.53 484	66.33 459	87.24 455	93.89 339	80.38 334	57.90 484	81.59 453	42.91 464	90.56 466	65.18 421	48.51 493	87.01 432

FE-MVSNET		69.26 450	66.03 453	78.93 451	73.82 497	68.33 447	89.65 429	84.06 489	70.21 450	57.79 485	76.94 481	41.48 470	86.98 489	45.85 493	54.51 472	81.48 486

MIMVSNet1		69.44 448	66.65 451	77.84 456	76.48 489	62.84 475	87.42 453	88.97 459	66.96 464	57.75 486	79.72 468	32.77 491	85.83 493	46.32 491	63.42 452	84.85 457

pmmvs3		65.75 457	62.18 461	76.45 465	67.12 507	64.54 465	88.68 441	85.05 483	54.77 498	57.54 487	73.79 488	29.40 497	86.21 491	55.49 470	47.77 496	78.62 492

dongtai		69.47 447	68.98 444	70.93 473	86.87 412	58.45 489	88.19 445	93.18 393	63.98 469	56.04 488	80.17 465	70.97 270	79.24 503	33.46 510	47.94 495	75.09 497

test_f		64.01 459	62.13 462	69.65 475	63.00 511	45.30 510	83.66 478	80.68 499	61.30 481	55.70 489	72.62 493	14.23 508	84.64 495	69.84 396	58.11 462	79.00 491

new-patchmatchnet		68.85 452	65.93 454	77.61 458	73.57 499	63.94 470	90.11 427	88.73 463	71.62 444	55.08 490	73.60 489	40.84 474	87.22 488	51.35 480	48.49 494	81.67 485

UnsupCasMVSNet_bld		68.60 453	64.50 458	80.92 440	74.63 496	67.80 448	83.97 476	92.94 400	65.12 467	54.63 491	68.23 501	35.97 483	92.17 450	60.13 447	44.83 500	82.78 471

CMPMVS	54.94 21	75.71 416	74.56 411	79.17 450	79.69 475	55.98 494	89.59 431	93.30 388	60.28 485	53.85 492	89.07 348	47.68 449	96.33 321	76.55 336	81.02 330	85.22 453
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
usedtu_dtu_shiyan2		64.65 458	60.40 463	77.38 460	64.24 509	57.84 491	89.16 437	87.60 469	52.95 499	53.43 493	71.31 500	23.41 500	88.27 479	51.95 477	49.58 490	86.03 445

ArgMatch-Sym		59.60 462	56.89 466	67.74 478	71.40 500	45.64 509	81.24 483	58.34 520	58.65 493	52.79 494	81.51 456	11.35 515	76.76 508	60.83 445	35.86 510	80.81 488

new_pmnet		66.18 456	63.18 459	75.18 471	76.27 491	61.74 479	83.79 477	84.66 484	56.64 496	51.57 495	71.85 497	31.29 493	87.93 481	49.98 484	62.55 454	75.86 495

ArgMatch-SfM		60.14 461	57.35 465	68.50 476	71.14 501	45.17 511	80.16 484	63.06 516	59.74 490	51.33 496	80.81 460	11.74 513	78.30 504	61.13 442	37.05 509	82.04 480

test_method		56.77 464	54.53 469	63.49 485	76.49 488	40.70 514	75.68 498	74.24 506	19.47 524	48.73 497	71.89 496	19.31 503	65.80 519	57.46 460	47.51 497	83.97 465

MVStest1		66.93 455	63.01 460	78.69 452	78.56 480	71.43 425	85.51 469	86.81 473	49.79 502	48.57 498	84.15 430	53.46 422	83.31 497	43.14 498	37.15 508	81.34 487

YYNet1		73.53 427	70.43 436	82.85 423	84.52 445	71.73 421	91.69 411	91.37 429	67.63 459	46.79 499	81.21 458	55.04 415	90.43 468	55.93 466	59.70 460	86.38 439

MDA-MVSNet_test_wron		73.54 426	70.43 436	82.86 422	84.55 443	71.85 418	91.74 410	91.32 432	67.63 459	46.73 500	81.09 459	55.11 414	90.42 469	55.91 467	59.76 459	86.31 440

WB-MVS		57.26 463	56.22 467	60.39 490	69.29 502	35.91 520	86.39 463	70.06 510	59.84 489	46.46 501	72.71 492	51.18 428	78.11 505	15.19 530	34.89 511	67.14 504

SSC-MVS		56.01 466	54.96 468	59.17 491	68.42 504	34.13 521	84.98 473	69.23 511	58.08 495	45.36 502	71.67 498	50.30 436	77.46 506	14.28 531	32.33 512	65.91 506

MDA-MVSNet-bldmvs		71.45 439	67.94 447	81.98 433	85.33 437	68.50 446	92.35 399	88.76 462	70.40 448	42.99 503	81.96 451	46.57 452	91.31 460	48.75 489	54.39 473	86.11 443

APD_test1		56.56 465	53.58 470	65.50 480	67.93 506	46.51 506	77.24 497	72.95 507	38.09 506	42.75 504	75.17 484	13.38 509	82.78 500	40.19 503	54.53 471	67.23 503

DeepMVS_CX				64.06 484	78.53 481	43.26 512		68.11 514	69.94 452	38.55 505	76.14 483	18.53 504	79.34 502	43.72 496	41.62 505	69.57 501

LCM-MVSNet		52.52 469	48.24 473	65.35 481	47.63 526	41.45 513	72.55 503	83.62 493	31.75 511	37.66 506	57.92 515	9.19 517	76.76 508	49.26 486	44.60 501	77.84 493

test_vis3_rt		54.10 468	51.04 472	63.27 486	58.16 514	46.08 508	84.17 475	49.32 526	56.48 497	36.56 507	49.48 523	8.03 518	91.91 453	67.29 407	49.87 489	51.82 519

VLMVS_CLIP		31.24 490	31.62 490	30.09 512	23.48 545	9.99 545	39.45 522	43.68 527	8.32 531	35.12 508	61.15 511	5.95 524	42.45 531	35.23 507	32.16 513	37.83 527

FPMVS		55.09 467	52.93 471	61.57 487	55.98 515	40.51 515	83.11 480	83.41 494	37.61 507	34.95 509	71.95 495	14.40 507	76.95 507	29.81 514	65.16 444	67.25 502

PMMVS2		50.90 471	46.31 475	64.67 482	55.53 516	46.67 505	77.30 496	71.02 509	40.89 505	34.16 510	59.32 512	9.83 516	76.14 511	40.09 504	28.63 515	71.21 499

VLMVS		26.26 492	26.52 496	25.45 513	25.35 544	7.91 549	30.71 528	15.37 535	3.37 544	34.11 511	65.40 504	8.03 518	21.07 537	32.40 512	23.95 518	47.39 522

MASt3R-SfM		33.79 485	32.03 489	39.08 506	30.86 535	18.05 538	44.70 521	25.59 531	21.32 521	31.97 512	71.52 499	3.78 528	38.14 533	35.97 505	22.58 519	61.06 510

MVS_clip		23.81 495	25.14 497	19.82 514	33.23 534	11.41 544	26.86 532	4.32 551	5.29 535	31.51 513	63.24 506	7.08 520	7.43 547	28.82 517	25.90 516	40.62 526

DenseAffine		43.98 477	39.51 482	57.39 492	60.41 512	37.29 518	67.44 509	34.50 528	35.36 509	31.38 514	65.55 503	4.21 526	67.77 517	35.59 506	21.11 520	67.10 505

RoMa-SfM		40.68 479	36.49 483	53.24 497	52.27 522	33.01 523	62.88 511	23.78 533	32.85 510	31.33 515	67.39 502	3.87 527	64.89 520	33.77 509	20.24 522	61.82 509

testf1		45.70 473	42.41 476	55.58 493	53.29 519	40.02 516	68.96 507	62.67 517	27.45 515	29.85 516	61.58 509	5.98 522	73.83 514	28.49 519	43.46 503	52.90 515

APD_test2		45.70 473	42.41 476	55.58 493	53.29 519	40.02 516	68.96 507	62.67 517	27.45 515	29.85 516	61.58 509	5.98 522	73.83 514	28.49 519	43.46 503	52.90 515

tmp_tt		41.54 478	41.93 479	40.38 505	20.10 550	26.84 529	61.93 512	59.09 519	14.81 528	28.51 518	80.58 461	35.53 484	48.33 529	63.70 430	13.11 530	45.96 525

Gipuma		45.11 476	42.05 478	54.30 495	80.69 466	51.30 501	35.80 524	83.81 491	28.13 514	27.94 519	34.53 529	11.41 514	76.70 510	21.45 525	54.65 470	34.90 528
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DKM		38.02 482	33.59 487	51.32 498	50.45 524	30.46 525	61.04 513	19.18 534	30.65 512	26.88 520	61.89 508	2.55 536	61.16 521	32.68 511	16.95 523	62.34 508

RoMa-HiRes		33.28 486	29.63 492	44.22 503	41.01 530	25.30 532	51.82 519	14.13 536	25.85 519	26.34 521	61.96 507	2.78 534	54.52 525	28.42 521	14.36 524	52.83 518

LoFTR		45.13 475	39.91 481	60.78 489	58.50 513	33.07 522	59.69 514	57.64 521	30.48 513	25.92 522	63.30 505	4.30 525	74.96 512	28.23 522	31.12 514	74.31 498

DKM-HiRes		32.92 487	29.13 494	44.31 502	42.93 527	25.35 531	53.22 518	13.26 537	25.92 518	24.31 523	57.58 516	1.88 545	50.95 528	28.87 516	14.19 525	56.63 514

PDCNetPlus		37.10 483	34.54 486	44.76 501	50.06 525	29.19 527	58.72 516	23.89 532	37.05 508	24.11 524	58.95 514	6.11 521	55.29 523	40.76 502	11.21 539	49.81 520

MatchFormer		39.45 480	34.61 485	54.00 496	53.28 521	28.79 528	58.06 517	51.35 525	21.48 520	23.10 525	55.83 517	3.50 530	70.37 516	19.01 527	25.84 517	62.84 507

ANet_high		46.22 472	41.28 480	61.04 488	39.91 532	46.25 507	70.59 506	76.18 505	58.87 492	23.09 526	48.00 525	12.58 511	66.54 518	28.65 518	13.62 528	70.35 500

PMatch-SfM		26.26 492	22.21 499	38.43 508	28.29 540	16.65 541	37.61 523	8.91 543	18.02 527	18.64 527	53.32 518	0.55 560	41.01 532	24.74 523	9.79 541	57.63 513

MVE	35.65 22	33.85 484	29.49 493	46.92 500	41.86 529	36.28 519	50.45 520	56.52 522	18.75 525	18.28 528	37.84 527	2.41 539	58.41 522	18.71 528	20.62 521	46.06 524
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ELoFTR		28.06 491	23.17 498	42.73 504	26.41 543	16.73 540	32.43 526	29.00 529	18.06 526	18.03 529	50.11 521	1.10 547	53.50 527	21.73 524	11.65 538	57.96 512

PMVS	34.80 23	39.19 481	35.53 484	50.18 499	29.72 536	30.30 526	59.60 515	66.20 515	26.06 517	17.91 530	49.53 522	3.12 531	74.09 513	18.19 529	49.40 491	46.14 523
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		32.70 488	32.39 488	33.65 509	53.35 518	25.70 530	74.07 501	53.33 523	21.08 522	17.17 531	33.63 531	11.85 512	54.84 524	12.98 533	14.04 526	20.42 533

EMVS		31.70 489	31.45 491	32.48 510	50.72 523	23.95 533	74.78 500	52.30 524	20.36 523	16.08 532	31.48 532	12.80 510	53.60 526	11.39 534	13.10 531	19.88 535

PMatch-Up-SfM		21.53 496	18.34 501	31.10 511	23.05 546	12.66 543	29.81 530	5.63 550	13.87 529	16.04 533	48.08 524	0.39 564	31.11 534	21.09 526	7.09 549	49.53 521

GLUNet-SfM		23.82 494	18.93 500	38.50 507	29.22 537	15.72 542	24.44 535	26.94 530	12.76 530	13.93 534	40.99 526	2.01 544	46.93 530	13.88 532	6.19 552	52.85 517

SP-DiffGlue		11.69 504	11.68 510	11.70 522	11.01 562	7.08 553	18.35 538	8.44 544	4.41 537	11.18 535	28.64 534	2.84 532	7.44 546	7.44 536	12.85 532	20.56 532

ALIKED-LG		17.53 498	16.82 502	19.64 515	42.07 528	19.09 535	31.53 527	11.93 538	7.76 532	10.68 536	26.90 535	3.52 529	22.14 535	3.10 544	13.89 527	17.68 536

ALIKED-NN		16.22 500	15.63 503	17.99 517	39.36 533	18.31 537	29.26 531	10.71 540	5.97 534	10.10 537	26.06 536	2.80 533	20.08 538	2.91 545	13.46 529	15.60 539

MVS_baseline		7.08 513	7.68 517	5.28 534	7.84 565	0.20 570	2.38 555	0.52 567	0.10 562	10.02 538	34.66 528	0.64 556	0.00 564	4.06 539	8.92 543	15.64 538

ALIKED-MNN		16.35 499	15.48 504	18.95 516	40.20 531	19.09 535	30.16 529	10.63 541	6.03 533	9.48 539	24.90 537	2.59 535	21.29 536	2.88 546	12.46 533	16.48 537

XFeat-NN		9.17 509	9.18 515	9.14 525	8.78 564	5.26 563	15.30 540	7.57 548	3.56 542	8.63 540	22.05 539	1.87 546	11.03 541	4.95 538	9.92 540	11.13 541

XFeat-MNN		10.03 507	9.79 514	10.74 524	9.46 563	6.05 561	16.60 539	9.52 542	4.29 538	8.53 541	22.45 538	2.10 542	13.28 540	5.47 537	9.68 542	12.89 540

SP-SuperGlue		12.00 503	12.07 507	11.81 520	28.37 539	6.58 554	24.63 533	8.02 545	3.99 539	7.02 542	18.00 541	2.44 538	7.72 545	3.95 541	12.19 535	21.13 531

SP-LightGlue		12.02 502	12.06 508	11.90 519	28.59 538	6.58 554	24.58 534	7.89 546	3.94 540	6.94 543	17.94 542	2.45 537	7.82 543	3.96 540	12.26 534	21.30 529

SP-NN		11.53 506	11.59 512	11.38 523	27.20 542	6.14 559	24.02 537	7.42 549	3.57 541	6.38 544	17.94 542	2.17 540	7.78 544	3.71 542	11.86 536	20.23 534

SP-MNN		11.64 505	11.60 511	11.74 521	27.48 541	6.11 560	24.23 536	7.72 547	3.40 543	6.22 545	17.81 544	2.13 541	7.94 542	3.69 543	11.73 537	21.18 530

wuyk23d		14.10 501	13.89 505	14.72 518	55.23 517	22.91 534	33.83 525	3.56 557	4.94 536	4.11 546	2.28 561	2.06 543	19.66 539	10.23 535	8.74 544	1.59 558

SIFT-NN		7.34 512	7.57 518	6.67 526	22.83 547	8.78 546	12.92 541	4.04 553	2.52 545	3.88 547	11.56 546	0.86 548	6.16 548	0.95 549	8.56 545	5.09 542

SIFT-NN-NCMNet		6.77 515	6.92 520	6.30 528	19.98 551	8.05 548	11.79 543	3.97 554	2.43 548	3.43 548	10.93 548	0.75 550	5.95 551	0.88 551	8.15 546	4.90 544

SIFT-MNN		6.97 514	7.12 519	6.51 527	21.26 548	8.28 547	11.89 542	4.05 552	2.50 546	3.39 549	11.27 547	0.76 549	6.14 549	0.95 549	8.05 547	5.09 542

SIFT-NN-CMatch		6.23 517	6.33 522	5.94 530	18.10 555	7.22 552	10.34 546	3.54 558	2.42 549	3.36 550	10.93 548	0.72 552	5.71 553	0.87 552	6.67 551	4.89 545

SIFT-NN-PointCN		5.63 522	5.80 526	5.10 536	16.00 558	5.22 564	10.00 548	3.21 560	2.26 555	2.92 551	10.15 555	0.72 552	5.35 557	0.81 556	6.14 553	4.74 547

testmvs		9.92 508	12.94 506	0.84 542	0.65 566	0.29 569	93.78 366	0.39 568	0.42 559	2.85 552	15.84 545	0.17 566	0.30 563	2.18 547	0.21 561	1.91 557

SIFT-NN-UMatch		6.11 518	6.25 523	5.68 532	17.01 557	6.50 556	11.20 544	3.58 556	2.44 547	2.68 553	10.88 550	0.74 551	5.70 554	0.87 552	6.85 550	4.82 546

SIFT-ConvMatch		6.05 519	6.14 524	5.78 531	19.43 552	7.31 551	9.58 549	3.30 559	2.42 549	2.67 554	10.54 552	0.65 555	5.73 552	0.83 555	5.84 554	4.29 549

SIFT-CM-Cal		5.56 523	5.66 527	5.26 535	18.45 554	6.34 557	8.44 551	2.81 562	2.36 553	2.42 555	9.99 557	0.64 556	5.41 556	0.74 559	5.05 556	4.02 551

SIFT-UMatch		5.86 521	6.01 525	5.38 533	18.70 553	6.22 558	10.07 547	3.07 561	2.39 552	2.42 555	10.54 552	0.63 558	5.65 555	0.84 554	5.49 555	4.28 550

SIFT-NCM-Cal		6.46 516	6.58 521	6.10 529	20.43 549	7.62 550	11.15 545	3.59 555	2.40 551	2.33 557	10.33 554	0.68 554	6.03 550	0.77 557	7.51 548	4.64 548

test123		9.07 510	11.73 509	1.11 541	0.50 567	0.77 568	89.44 435	0.20 569	0.34 560	2.15 558	10.72 551	0.34 565	0.32 562	1.79 548	0.08 562	2.23 556

SIFT-UM-Cal		5.40 524	5.58 528	4.87 537	18.00 556	5.37 562	9.03 550	2.49 564	2.33 554	2.14 559	10.11 556	0.60 559	5.27 558	0.77 557	4.78 558	3.95 552

SIFT-PCN-Cal		4.71 526	4.89 530	4.18 538	15.70 559	3.90 566	7.58 553	2.37 565	2.09 557	1.95 560	8.68 558	0.51 561	4.71 559	0.68 560	4.45 559	3.93 553

SIFT-PointCN		4.77 525	4.97 529	4.17 539	15.53 560	3.97 565	8.20 552	2.62 563	2.10 556	1.91 561	8.44 559	0.47 562	4.70 560	0.67 561	4.79 557	3.85 554

SIFT-NCMNet		4.03 527	4.21 531	3.50 540	14.53 561	3.56 567	6.14 554	1.51 566	2.08 558	1.72 562	7.39 560	0.42 563	4.00 561	0.57 562	3.56 560	2.93 555

EGC-MVSNET		52.46 470	47.56 474	67.15 479	81.98 462	60.11 485	82.54 481	72.44 508	0.11 561	0.70 563	74.59 486	25.11 499	83.26 498	29.04 515	61.51 457	58.09 511

mmdepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet_test		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		21.43 497	28.57 495	0.00 543	0.00 568	0.00 571	0.00 556	95.93 184	0.00 563	0.00 564	97.66 96	63.57 337	0.00 564	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		5.92 520	7.89 516	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	71.04 267	0.00 564	0.00 563	0.00 563	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

ab-mvs-re		8.11 511	10.81 513	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	97.30 120	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet2					0.00 568	72.22 408	92.05 403	89.18 457	62.36 475
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														42.17 501	64.00 449	85.01 455
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.74 455
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						67.18 452								49.00 487

MSC_two_6792asdad				97.14 4	99.05 15	92.19 4		96.83 65					99.81 29	98.08 27	98.81 24	99.43 12

No_MVS				97.14 4	99.05 15	92.19 4		96.83 65					99.81 29	98.08 27	98.81 24	99.43 12

eth-test2					0.00 568

eth-test					0.00 568

OPU-MVS				97.30 2	99.19 9	92.31 3	99.12 17				98.54 32	92.06 3	99.84 19	99.11 5	99.37 1	99.74 1

save fliter					98.24 58	83.34 122	98.61 47	96.57 108	91.32 49

test_0728_SECOND				95.14 22	99.04 20	86.14 46	99.06 24	96.77 76					99.84 19	97.90 32	98.85 21	99.45 11

GSMVS																97.54 155

sam_mvs1												77.59 134				97.54 155

sam_mvs												75.35 195

MTGPA								96.33 144

test_post1							85.88 466				30.24 533	73.77 220	95.07 396	73.89 367

test_post											33.80 530	76.17 169	95.97 335

patchmatchnet-post											77.09 480	77.78 132	95.39 369

MTMP							97.53 120	68.16 513

gm-plane-assit					92.27 290	79.64 264			84.47 234		95.15 211		97.93 189	85.81 230

test9_res														96.00 61	99.03 13	98.31 79

agg_prior2														94.30 86	99.00 15	98.57 62

test_prior4						82.34 151	97.75 102

test_prior				93.09 106	98.68 33	81.91 168		96.40 133					99.06 128			98.29 81

新几何2							96.42 226

旧先验1					97.39 95	79.58 266		96.54 114			98.08 72	84.00 57			97.42 83	97.62 148

无先验							96.87 184	96.78 70	77.39 385				99.52 89	79.95 292		98.43 71

原ACMM2							96.84 186

testdata2													99.48 93	76.45 338

segment_acmp												82.69 71

testdata1							95.57 299		87.44 129

plane_prior7					91.86 318	77.55 341

plane_prior6					91.98 313	77.92 327						64.77 329

plane_prior5								94.69 265					97.30 261	87.08 218	82.82 319	90.96 337

plane_prior4											94.15 258

plane_prior2							97.18 150		89.89 73

plane_prior1					91.95 315

plane_prior						77.96 324	97.52 123		90.36 68						82.96 317

n2								0.00 570

nn								0.00 570

door-mid								79.75 501

test11								96.50 120

door								80.13 500

HQP5-MVS						78.48 302

BP-MVS														87.67 213

HQP3-MVS								94.80 256							83.01 315

HQP2-MVS												65.40 322

NP-MVS					92.04 310	78.22 314					94.56 239

ACMMP++_ref															78.45 352

ACMMP++															79.05 344

Test By Simon												71.65 259

High-resolution multi-view benchmark