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.

OPU-MVS				99.49 4	99.64 24	98.51 4	99.77 30				99.19 47	95.12 9	99.97 27	99.90 1	99.92 3	99.99 2

PC_three_1452									94.60 54	99.41 13	99.12 65	95.50 7	99.96 35	99.84 2	99.92 3	99.97 8

MM		97.76 13	97.39 24	98.86 6	98.30 106	96.83 8	99.81 21	99.13 9	97.66 3	98.29 62	98.96 90	85.84 149	99.90 64	99.72 3	98.80 107	99.85 35

MGCNet		97.81 11	97.51 18	98.74 11	98.97 82	96.57 13	99.91 3	98.17 39	97.45 6	98.76 41	98.97 85	86.69 128	99.96 35	99.72 3	98.92 98	99.69 66

SED-MVS		98.18 3	98.10 5	98.41 20	99.63 25	95.24 30	99.77 30	97.72 101	94.17 62	99.30 19	99.54 5	93.32 22	99.98 14	99.70 5	99.81 24	99.99 2

test_241102_TWO								97.72 101	94.17 62	99.23 22	99.54 5	93.14 28	99.98 14	99.70 5	99.82 20	99.99 2

IU-MVS					99.63 25	95.38 27		97.73 100	95.54 39	99.54 11				99.69 7	99.81 24	99.99 2

fmvsm_s_conf0.5_n_8		97.06 34	96.94 32	97.44 55	97.78 125	92.77 110	99.83 16	97.83 80	97.58 4	99.25 21	99.20 43	82.71 212	99.92 51	99.64 8	98.61 119	99.64 78

DVP-MVS		98.07 8	98.00 9	98.29 21	99.66 19	95.20 35	99.72 39	97.47 167	93.95 69	99.07 28	99.46 16	93.18 26	99.97 27	99.64 8	99.82 20	99.69 66
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_SECOND				98.77 9	99.66 19	96.37 16	99.72 39	97.68 112					99.98 14	99.64 8	99.82 20	99.96 11

RA-MVS			98.44 1		99.80 5	92.91 105	99.63 60	98.00 60	96.64 22	99.57 10	99.59 3	93.23 25	99.98 14	99.61 11	99.85 13

patch_mono-2		97.10 32	97.97 11	94.49 246	99.21 70	83.73 383	99.62 62	98.25 34	95.28 43	99.38 16	98.91 98	92.28 35	99.94 42	99.61 11	99.22 80	99.78 47

DPE-MVS		98.11 7	98.00 9	98.44 18	99.50 49	95.39 26	99.29 107	97.72 101	94.50 55	98.64 46	99.54 5	93.32 22	99.97 27	99.58 13	99.90 7	99.95 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.5_n_11		96.80 42	96.97 31	96.28 133	98.09 115	92.26 123	99.87 7	96.49 267	97.55 5	99.75 3	99.32 29	83.20 197	99.91 59	99.57 14	98.88 101	96.67 302

fmvsm_l_conf0.5_n_a		97.70 15	97.80 14	97.42 58	97.59 137	92.91 105	99.86 10	98.04 56	96.70 20	99.58 9	99.26 32	90.90 46	99.94 42	99.57 14	98.66 117	99.40 107

fmvsm_s_conf0.5_n_9		96.76 46	96.92 33	96.29 132	97.95 120	89.21 222	99.81 21	97.55 148	97.04 15	99.68 6	99.22 39	82.84 206	99.94 42	99.56 16	98.61 119	99.71 61

test-260524					99.74 12	96.14 18		97.62 133		97.79 80		91.57 38	100.00 1	99.55 17	99.75 30

fmvsm_l_conf0.5_n		97.65 16	97.72 15	97.41 59	97.51 143	92.78 109	99.85 13	98.05 54	96.78 18	99.60 8	99.23 37	90.42 59	99.92 51	99.55 17	98.50 126	99.55 89

MSC_two_6792asdad				99.51 2	99.61 31	98.60 2		97.69 110					99.98 14	99.55 17	99.83 16	99.96 11

No_MVS				99.51 2	99.61 31	98.60 2		97.69 110					99.98 14	99.55 17	99.83 16	99.96 11

aaatest				97.84 38	99.75 9	93.67 76	99.65 53	98.11 47	92.89 103	98.58 51	99.53 9		100.00 1	99.53 21	99.64 45	99.87 32

MED-MVS		98.04 9	98.10 5	97.86 37	99.75 9	93.67 76	99.65 53	98.11 47	94.03 67	98.58 51	99.49 13	93.98 18	100.00 1	99.53 21	99.75 30	99.90 23

aaEdge-Enhanced		97.59 17	97.51 18	97.84 38	99.73 13	93.67 76	99.52 74	98.07 50	92.38 117	98.32 61	99.53 9	90.83 50	99.97 27	99.53 21	99.64 45	99.87 32

fmvsm_l_conf0.5_n_9		97.33 23	97.32 26	97.37 62	97.64 132	92.45 119	99.93 1	97.85 74	97.39 7	99.84 2	99.09 71	85.42 158	99.92 51	99.52 24	99.20 84	99.73 59

fmvsm_l_mol_unc0.5_1		98.26 2	98.09 7	98.75 10	97.31 154	96.69 10	99.89 5	96.97 230	97.78 2	99.69 5	99.31 30	92.95 29	99.92 51	99.50 25	99.46 62	99.65 76

fmvsm_s_conf0.5_n_10		96.95 36	96.82 42	97.33 64	97.76 126	93.00 100	99.87 7	97.95 63	97.32 10	99.71 4	99.20 43	81.48 236	99.90 64	99.32 26	98.78 111	99.09 139

fmvsm_s_conf0.5_n_2		95.85 87	95.83 81	95.91 161	97.19 164	91.79 132	99.78 29	97.65 125	97.23 11	99.22 24	99.06 75	75.93 310	99.90 64	99.30 27	97.09 166	96.02 322

DeepPCF-MVS	93.56 1	96.55 58	97.84 13	92.68 313	98.71 98	78.11 449	99.70 42	97.71 105	98.18 1	97.36 88	99.76 1	90.37 61	99.94 42	99.27 28	99.54 59	99.99 2

fmvsm_s_conf0.5_n_3		96.58 55	96.55 52	96.66 107	97.23 159	92.59 116	99.81 21	97.82 81	97.35 8	99.42 12	99.16 53	80.27 249	99.93 48	99.26 29	98.60 121	97.45 274

APDe-MVS		97.53 18	97.47 20	97.70 46	99.58 37	93.63 79	99.56 67	97.52 157	93.59 86	98.01 74	99.12 65	90.80 51	99.55 131	99.26 29	99.79 28	99.93 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS++		98.18 3	98.09 7	98.44 18	99.61 31	95.38 27	99.55 68	97.68 112	93.01 96	99.23 22	99.45 20	95.12 9	99.98 14	99.25 31	99.92 3	99.97 8

test_0728_THIRD									93.01 96	99.07 28	99.46 16	94.66 14	99.97 27	99.25 31	99.82 20	99.95 16

fmvsm_s_conf0.5_n_5		96.46 60	96.23 64	97.15 75	96.42 202	92.80 108	99.83 16	97.39 181	94.50 55	98.71 42	99.13 62	82.52 215	99.90 64	99.24 33	98.38 130	98.74 185

fmvsm_l_conf0.5_n_3		97.12 30	96.89 36	97.79 45	97.39 148	93.84 73	99.87 7	97.70 106	97.34 9	99.39 15	99.20 43	82.86 204	99.94 42	99.21 34	99.07 87	99.58 88

dcpmvs_2		95.67 99	96.18 67	94.12 267	98.82 94	84.22 376	97.37 345	95.45 389	90.70 159	95.77 137	98.63 125	90.47 57	98.68 199	99.20 35	99.22 80	99.45 103

fmvsm_s_conf0.5_n_7		95.87 85	96.25 63	94.72 234	96.19 217	87.74 277	99.66 51	97.94 65	95.78 33	98.44 55	99.23 37	81.26 242	99.90 64	99.17 36	98.57 123	96.52 310

fmvsm_s_conf0.5_n		96.19 69	96.49 54	95.30 200	97.37 150	89.16 225	99.86 10	98.47 26	95.68 36	98.87 36	99.15 57	82.44 222	99.92 51	99.14 37	97.43 157	96.83 296

test_fmvsmconf_n		96.78 44	96.84 39	96.61 109	95.99 229	90.25 180	99.90 4	98.13 45	96.68 21	98.42 56	98.92 97	85.34 160	99.88 74	99.12 38	99.08 85	99.70 63

test_fmvsm_n_1920		97.08 33	97.55 17	95.67 172	97.94 121	89.61 211	99.93 1	98.48 25	97.08 13	99.08 27	99.13 62	88.17 91	99.93 48	99.11 39	99.06 88	97.47 273

fmvsm_s_conf0.5_n_4		96.17 70	96.49 54	95.21 206	97.06 175	89.26 220	99.76 33	98.07 50	95.99 30	99.35 17	99.22 39	82.19 226	99.89 72	99.06 40	97.68 148	96.49 311

fmvsm_s_conf0.5_n_6		96.78 44	96.64 50	97.20 72	96.03 228	93.20 93	99.82 20	97.68 112	95.20 44	99.61 7	99.11 69	84.52 174	99.90 64	99.04 41	98.77 112	98.50 215

TSAR-MVS + GP.		96.95 36	96.91 35	97.07 76	98.88 92	91.62 139	99.58 65	96.54 260	95.09 46	96.84 103	98.63 125	91.16 39	99.77 110	99.04 41	96.42 178	99.81 40

fmvsm_s_conf0.1_n_2		95.24 112	95.04 113	95.83 164	95.60 243	91.71 138	99.65 53	96.18 292	96.99 16	98.79 40	98.91 98	73.91 334	99.87 78	99.00 43	96.30 182	95.91 324

MCST-MVS		98.18 3	97.95 12	98.86 6	99.85 4	96.60 12	99.70 42	97.98 62	97.18 12	95.96 128	99.33 28	92.62 31	100.00 1	98.99 44	99.93 1	99.98 7

CNVR-MVS		98.46 1	98.38 2	98.72 12	99.80 5	96.19 17	99.80 27	97.99 61	97.05 14	99.41 13	99.59 3	92.89 30	100.00 1	98.99 44	99.90 7	99.96 11

test_fmvsmconf0.1_n		95.94 82	95.79 87	96.40 123	92.42 384	89.92 197	99.79 28	96.85 235	96.53 26	97.22 91	98.67 121	82.71 212	99.84 90	98.92 46	98.98 93	99.43 106

fmvsm_s_conf0.5_n_a		95.97 78	96.19 65	95.31 197	96.51 198	89.01 234	99.81 21	98.39 29	95.46 41	99.19 26	99.16 53	81.44 239	99.91 59	98.83 47	96.97 167	97.01 292

CANet		97.00 35	96.49 54	98.55 14	98.86 93	96.10 19	99.83 16	97.52 157	95.90 31	97.21 92	98.90 100	82.66 214	99.93 48	98.71 48	98.80 107	99.63 81

9.14			96.87 37		99.34 57		99.50 76	97.49 164	89.41 221	98.59 49	99.43 22	89.78 69	99.69 116	98.69 49	99.62 51

SD-MVS		97.51 19	97.40 23	97.81 42	99.01 81	93.79 75	99.33 105	97.38 182	93.73 81	98.83 39	99.02 81	90.87 49	99.88 74	98.69 49	99.74 32	99.77 52
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
balanced_ft_v1		94.96 120	94.35 125	96.78 95	97.54 140	92.05 126	98.03 304	96.20 287	90.90 152	96.83 105	95.51 302	76.75 300	98.77 189	98.68 51	98.70 114	99.52 92

fmvsm_s_conf0.1_n		95.56 101	95.68 90	95.20 208	94.35 324	89.10 227	99.50 76	97.67 117	94.76 52	98.68 45	99.03 79	81.13 243	99.86 84	98.63 52	97.36 159	96.63 303

test9_res														98.60 53	99.87 9	99.90 23

PS-MVSNAJ		96.87 39	96.40 58	98.29 21	97.35 151	97.29 6	99.03 151	97.11 215	95.83 32	98.97 33	99.14 60	82.48 218	99.60 128	98.60 53	99.08 85	98.00 253

xiu_mvs_v2_base		96.66 49	96.17 70	98.11 31	97.11 173	96.96 7	99.01 154	97.04 222	95.51 40	98.86 37	99.11 69	82.19 226	99.36 155	98.59 55	98.14 137	98.00 253

train_agg		97.20 28	97.08 29	97.57 52	99.57 40	93.17 94	99.38 97	97.66 118	90.18 186	98.39 57	99.18 50	90.94 44	99.66 119	98.58 56	99.85 13	99.88 29

reproduce_model		96.57 56	96.75 46	96.02 152	98.93 89	88.46 258	98.56 225	97.34 189	93.18 94	96.96 99	99.35 27	88.69 84	99.80 102	98.53 57	99.21 83	99.79 44

reproduce-ours		96.66 49	96.80 43	96.22 135	98.95 86	89.03 232	98.62 209	97.38 182	93.42 88	96.80 109	99.36 25	88.92 79	99.80 102	98.51 58	99.26 77	99.82 37

our_new_method		96.66 49	96.80 43	96.22 135	98.95 86	89.03 232	98.62 209	97.38 182	93.42 88	96.80 109	99.36 25	88.92 79	99.80 102	98.51 58	99.26 77	99.82 37

TSAR-MVS + MP.		97.44 21	97.46 21	97.39 61	99.12 74	93.49 87	98.52 229	97.50 162	94.46 57	98.99 31	98.64 123	91.58 37	99.08 175	98.49 60	99.83 16	99.60 84
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		97.22 27	96.92 33	98.12 30	99.11 75	94.88 41	99.44 87	97.45 170	89.60 211	98.70 43	99.42 23	90.42 59	99.72 114	98.47 61	99.65 43	99.77 52

BridgeMVS		96.83 40	96.51 53	97.81 42	97.60 136	95.15 37	98.40 253	96.77 241	93.00 98	98.69 44	96.19 283	89.75 70	98.76 192	98.45 62	99.72 35	99.51 95

PRO-TEST		96.23 67	95.99 76	96.95 87	96.86 183	93.81 74	99.19 118	96.51 261	94.78 51	98.27 63	98.49 136	83.43 190	97.60 307	98.43 63	97.99 139	99.46 102

PHI-MVS		96.65 52	96.46 57	97.21 71	99.34 57	91.77 134	99.70 42	98.05 54	86.48 327	98.05 71	99.20 43	89.33 74	99.96 35	98.38 64	99.62 51	99.90 23

test_fmvsmvis_n_1920		95.47 103	95.40 99	95.70 170	94.33 328	90.22 183	99.70 42	96.98 229	96.80 17	92.75 209	98.89 102	82.46 221	99.92 51	98.36 65	98.33 132	96.97 293

ZD-MVS					99.67 17	93.28 90		97.61 135	87.78 289	97.41 86	99.16 53	90.15 66	99.56 130	98.35 66	99.70 40

test_prior2							99.57 66		91.43 139	98.12 68	98.97 85	90.43 58		98.33 67	99.81 24

SMA-MVS		97.24 25	96.99 30	98.00 34	99.30 61	94.20 66	99.16 125	97.65 125	89.55 215	99.22 24	99.52 12	90.34 63	99.99 9	98.32 68	99.83 16	99.82 37
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
CHOSEN 280x420		96.80 42	96.85 38	96.66 107	97.85 124	94.42 60	94.76 427	98.36 31	92.50 110	95.62 143	97.52 191	97.92 1	97.38 321	98.31 69	98.80 107	98.20 241

test_fmvsmconf0.01_n		94.14 151	93.51 162	96.04 150	86.79 464	89.19 223	99.28 110	95.94 322	95.70 34	95.50 144	98.49 136	73.27 340	99.79 106	98.28 70	98.32 134	99.15 131

NCCC		98.12 6	98.11 4	98.13 28	99.76 8	94.46 57	99.81 21	97.88 70	96.54 24	98.84 38	99.46 16	92.55 32	99.98 14	98.25 71	99.93 1	99.94 19

fmvsm_s_conf0.1_n_a		95.16 114	95.15 107	95.18 209	92.06 391	88.94 240	99.29 107	97.53 153	94.46 57	98.98 32	98.99 83	79.99 252	99.85 88	98.24 72	96.86 171	96.73 300

MSP-MVS		97.77 12	98.18 3	96.53 116	99.54 43	90.14 186	99.41 94	97.70 106	95.46 41	98.60 48	99.19 47	95.71 5	99.49 137	98.15 73	99.85 13	99.95 16
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
ETV-MVS		96.00 75	96.00 75	96.00 155	96.56 194	91.05 157	99.63 60	96.61 250	93.26 93	97.39 87	98.30 148	86.62 130	98.13 236	98.07 74	97.57 150	98.82 172

MSLP-MVS++		97.50 20	97.45 22	97.63 48	99.65 23	93.21 92	99.70 42	98.13 45	94.61 53	97.78 81	99.46 16	89.85 68	99.81 100	97.97 75	99.91 6	99.88 29

APD-MVS		96.95 36	96.72 47	97.63 48	99.51 48	93.58 82	99.16 125	97.44 174	90.08 192	98.59 49	99.07 72	89.06 76	99.42 148	97.92 76	99.66 42	99.88 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SteuartSystems-ACMMP		97.25 24	97.34 25	97.01 79	97.38 149	91.46 144	99.75 36	97.66 118	94.14 66	98.13 66	99.26 32	92.16 36	99.66 119	97.91 77	99.64 45	99.90 23
Skip Steuart: Steuart Systems R&D Blog.
MVSMamba_PlusPlus		95.73 97	95.15 107	97.44 55	97.28 158	94.35 63	98.26 273	96.75 242	83.09 390	97.84 78	95.97 291	89.59 72	98.48 210	97.86 78	99.73 34	99.49 98

test_vis1_n_1920		93.08 204	93.42 165	92.04 326	96.31 209	79.36 434	99.83 16	96.06 307	96.72 19	98.53 53	98.10 156	58.57 443	99.91 59	97.86 78	98.79 110	96.85 295

agg_prior2														97.84 80	99.87 9	99.91 22

lecture		96.67 48	96.77 45	96.39 124	99.27 64	89.71 207	99.65 53	98.62 22	92.28 119	98.62 47	99.07 72	86.74 125	99.79 106	97.83 81	98.82 104	99.66 72

mvsany_test1		94.57 139	95.09 111	92.98 300	95.84 234	82.07 407	98.76 183	95.24 404	92.87 105	96.45 117	98.71 118	84.81 170	99.15 168	97.68 82	95.49 202	97.73 261

HPM-MVS++		97.72 14	97.59 16	98.14 27	99.53 47	94.76 49	99.19 118	97.75 96	95.66 37	98.21 64	99.29 31	91.10 41	99.99 9	97.68 82	99.87 9	99.68 68

test_vis1_n		90.40 280	90.27 263	90.79 361	91.55 403	76.48 459	99.12 140	94.44 430	94.31 60	97.34 89	96.95 242	43.60 489	99.42 148	97.57 84	97.60 149	96.47 312

SR-MVS		96.13 71	96.16 72	96.07 149	99.42 54	89.04 230	98.59 219	97.33 192	90.44 173	96.84 103	99.12 65	86.75 124	99.41 151	97.47 85	99.44 66	99.76 54

testing915		95.97 78	95.46 97	97.50 54	97.05 177	94.32 64	99.08 143	97.94 65	90.40 176	96.01 126	97.09 230	90.37 61	98.39 214	97.45 86	93.74 242	99.80 43

PVSNet_BlendedMVS		93.36 190	93.20 174	93.84 280	98.77 96	91.61 141	99.47 80	98.04 56	91.44 138	94.21 171	92.63 363	83.50 187	99.87 78	97.41 87	83.37 356	90.05 436

PVSNet_Blended		95.94 82	95.66 91	96.75 98	98.77 96	91.61 141	99.88 6	98.04 56	93.64 85	94.21 171	97.76 169	83.50 187	99.87 78	97.41 87	97.75 147	98.79 176

mvsmamba		94.27 147	93.91 147	95.35 192	96.42 202	88.61 252	97.77 320	96.38 274	91.17 148	94.05 176	95.27 309	78.41 283	97.96 269	97.36 89	98.40 129	99.48 99

test_fmvs1		92.35 225	92.94 186	90.57 366	97.19 164	75.43 465	99.55 68	94.97 414	95.20 44	96.82 107	97.57 188	59.59 441	99.84 90	97.30 90	98.29 135	96.46 313

EC-MVSNet		95.09 116	95.17 106	94.84 227	95.42 254	88.17 265	99.48 78	95.92 327	91.47 137	97.34 89	98.36 145	82.77 208	97.41 320	97.24 91	98.58 122	98.94 158

MVS_111021_HR		96.69 47	96.69 48	96.72 102	98.58 101	91.00 159	99.14 133	99.45 1	93.86 76	95.15 151	98.73 113	88.48 86	99.76 111	97.23 92	99.56 57	99.40 107

test_fmvs1_n		91.07 260	91.41 234	90.06 380	94.10 337	74.31 469	99.18 121	94.84 418	94.81 49	96.37 120	97.46 195	50.86 476	99.82 97	97.14 93	97.90 141	96.04 320

xiu_mvs_v1_base_debu		94.73 130	93.98 139	96.99 81	95.19 268	95.24 30	98.62 209	96.50 263	92.99 99	97.52 83	98.83 106	72.37 349	99.15 168	97.03 94	96.74 172	96.58 306

xiu_mvs_v1_base		94.73 130	93.98 139	96.99 81	95.19 268	95.24 30	98.62 209	96.50 263	92.99 99	97.52 83	98.83 106	72.37 349	99.15 168	97.03 94	96.74 172	96.58 306

xiu_mvs_v1_base_debi		94.73 130	93.98 139	96.99 81	95.19 268	95.24 30	98.62 209	96.50 263	92.99 99	97.52 83	98.83 106	72.37 349	99.15 168	97.03 94	96.74 172	96.58 306

lupinMVS		96.32 64	95.94 77	97.44 55	95.05 287	94.87 42	99.86 10	96.50 263	93.82 79	98.04 72	98.77 109	85.52 151	98.09 245	96.98 97	98.97 94	99.37 110

SPE-MVS-test		95.98 77	96.34 61	94.90 223	98.06 117	87.66 282	99.69 49	96.10 299	93.66 83	98.35 60	99.05 77	86.28 140	97.66 301	96.96 98	98.90 100	99.37 110

MVS_111021_LR		95.78 91	95.94 77	95.28 201	98.19 112	87.69 278	98.80 176	99.26 7	93.39 90	95.04 153	98.69 120	84.09 181	99.76 111	96.96 98	99.06 88	98.38 224

RRT-MVS		93.39 187	92.64 195	95.64 174	96.11 226	88.75 249	97.40 341	95.77 350	89.46 219	92.70 212	95.42 306	72.98 343	98.81 187	96.91 100	96.97 167	99.37 110

VNet		95.08 117	94.26 127	97.55 53	98.07 116	93.88 71	98.68 196	98.73 17	90.33 178	97.16 95	97.43 197	79.19 265	99.53 134	96.91 100	91.85 284	99.24 123

myMVS_eth3d28		95.74 96	95.34 100	96.92 89	97.41 146	93.58 82	99.28 110	97.70 106	90.97 151	93.91 180	97.25 213	90.59 55	98.75 193	96.85 102	94.14 230	98.44 218

test_cas_vis1_n_1920		93.86 167	93.74 155	94.22 263	95.39 257	86.08 338	99.73 38	96.07 306	96.38 28	97.19 94	97.78 167	65.46 414	99.86 84	96.71 103	98.92 98	96.73 300

CS-MVS		95.75 94	96.19 65	94.40 250	97.88 123	86.22 328	99.66 51	96.12 297	92.69 107	98.07 70	98.89 102	87.09 116	97.59 308	96.71 103	98.62 118	99.39 109

APD-MVS_3200maxsize		95.64 100	95.65 93	95.62 178	99.24 67	87.80 276	98.42 246	97.22 201	88.93 240	96.64 116	98.98 84	85.49 154	99.36 155	96.68 105	99.27 76	99.70 63

SR-MVS-dyc-post		95.75 94	95.86 80	95.41 188	99.22 68	87.26 304	98.40 253	97.21 202	89.63 208	96.67 114	98.97 85	86.73 127	99.36 155	96.62 106	99.31 73	99.60 84

RE-MVS-def			95.70 89		99.22 68	87.26 304	98.40 253	97.21 202	89.63 208	96.67 114	98.97 85	85.24 164		96.62 106	99.31 73	99.60 84

DeepC-MVS_fast	93.52 2	97.16 29	96.84 39	98.13 28	99.61 31	94.45 58	98.85 169	97.64 127	96.51 27	95.88 131	99.39 24	87.35 112	99.99 9	96.61 108	99.69 41	99.96 11
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		91.24 257	90.18 264	94.45 249	97.08 174	85.84 349	98.40 253	96.10 299	86.99 309	93.36 194	98.16 154	54.27 463	99.20 165	96.59 109	90.63 309	98.31 233

MP-MVS-pluss		95.80 90	95.30 101	97.29 66	98.95 86	92.66 111	98.59 219	97.14 211	88.95 238	93.12 197	99.25 34	85.62 150	99.94 42	96.56 110	99.48 61	99.28 120
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
diffmvs		94.59 138	94.19 130	95.81 165	95.54 248	90.69 167	98.70 192	95.68 363	91.61 131	95.96 128	97.81 164	80.11 250	98.06 255	96.52 111	95.76 194	98.67 198
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMMP_NAP		96.59 53	96.18 67	97.81 42	98.82 94	93.55 84	98.88 168	97.59 141	90.66 161	97.98 75	99.14 60	86.59 131	100.00 1	96.47 112	99.46 62	99.89 28

onestephybrid01		94.12 152	93.87 150	94.86 226	95.26 262	87.86 274	98.60 216	95.82 346	90.70 159	95.67 141	97.72 176	79.72 254	98.13 236	96.37 113	94.99 213	98.60 208

PAPM		96.35 62	95.94 77	97.58 50	94.10 337	95.25 29	98.93 161	98.17 39	94.26 61	93.94 179	98.72 115	89.68 71	97.88 275	96.36 114	99.29 75	99.62 83

mmtdpeth		83.69 400	82.59 400	86.99 430	92.82 377	76.98 457	96.16 399	91.63 476	82.89 399	92.41 220	82.90 481	54.95 460	98.19 228	96.27 115	53.27 502	85.81 481

MTAPA		96.09 72	95.80 86	96.96 86	99.29 62	91.19 149	97.23 352	97.45 170	92.58 108	94.39 168	99.24 36	86.43 138	99.99 9	96.22 116	99.40 70	99.71 61

diffmvs_AUTHOR		94.30 146	93.92 145	95.45 183	94.77 308	89.92 197	98.55 228	95.68 363	91.33 142	95.83 136	97.64 183	79.58 257	98.05 259	96.19 117	95.66 197	98.37 227

alignmvs		95.77 92	95.00 114	98.06 32	97.35 151	95.68 23	99.71 41	97.50 162	91.50 136	96.16 125	98.61 127	86.28 140	99.00 178	96.19 117	91.74 286	99.51 95

UBG		95.73 97	95.41 98	96.69 104	96.97 180	93.23 91	99.13 138	97.79 89	91.28 144	94.38 169	96.78 260	92.37 34	98.56 204	96.17 119	93.84 236	98.26 234

AstraMVS		93.38 189	93.01 182	94.50 245	93.94 345	86.55 314	98.91 165	95.86 341	93.88 75	92.88 205	97.49 193	75.61 318	98.21 226	96.15 120	92.39 270	98.73 190

sasdasda		95.02 118	93.96 142	98.20 24	97.53 141	95.92 20	98.71 189	96.19 290	91.78 128	95.86 133	98.49 136	79.53 260	99.03 176	96.12 121	91.42 298	99.66 72

canonicalmvs		95.02 118	93.96 142	98.20 24	97.53 141	95.92 20	98.71 189	96.19 290	91.78 128	95.86 133	98.49 136	79.53 260	99.03 176	96.12 121	91.42 298	99.66 72

DELS-MVS		97.12 30	96.60 51	98.68 13	98.03 118	96.57 13	99.84 15	97.84 76	96.36 29	95.20 150	98.24 150	88.17 91	99.83 94	96.11 123	99.60 55	99.64 78
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
jason		95.40 107	94.86 116	97.03 78	92.91 375	94.23 65	99.70 42	96.30 279	93.56 87	96.73 112	98.52 131	81.46 238	97.91 271	96.08 124	98.47 128	98.96 153
jason: jason.
guyue		94.21 149	93.72 156	95.66 173	95.22 265	90.17 185	98.74 185	96.85 235	93.67 82	93.01 202	96.72 264	78.83 274	98.06 255	96.04 125	94.44 224	98.77 181

CP-MVS		96.22 68	96.15 73	96.42 121	99.67 17	89.62 210	99.70 42	97.61 135	90.07 193	96.00 127	99.16 53	87.43 106	99.92 51	96.03 126	99.72 35	99.70 63

MP-MVS		96.00 75	95.82 83	96.54 115	99.47 53	90.13 188	99.36 101	97.41 178	90.64 164	95.49 145	98.95 93	85.51 153	99.98 14	96.00 127	99.59 56	99.52 92
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing3-2		95.17 113	94.78 117	96.33 130	97.35 151	92.35 120	99.85 13	98.43 28	90.60 165	92.84 208	97.00 239	90.89 47	98.89 183	95.95 128	90.12 312	97.76 259

MGCFI-Net		94.89 121	93.84 151	98.06 32	97.49 144	95.55 24	98.64 203	96.10 299	91.60 134	95.75 138	98.46 143	79.31 264	98.98 180	95.95 128	91.24 303	99.65 76

TestfortrainingZip a		97.38 22	97.10 28	98.24 23	99.75 9	94.82 47	99.65 53	97.86 72	94.03 67	99.04 30	99.49 13	90.76 53	99.99 9	95.87 130	97.45 156	99.90 23

h-mvs33		92.47 224	91.95 221	94.05 272	97.13 170	85.01 365	98.36 262	98.08 49	93.85 77	96.27 123	96.73 263	83.19 198	99.43 147	95.81 131	68.09 456	97.70 265

hse-mvs2		91.67 245	91.51 232	92.15 323	96.22 213	82.61 403	97.74 324	97.53 153	93.85 77	96.27 123	96.15 284	83.19 198	97.44 318	95.81 131	66.86 464	96.40 315

HFP-MVS		96.42 61	96.26 62	96.90 90	99.69 15	90.96 160	99.47 80	97.81 85	90.54 170	96.88 100	99.05 77	87.57 103	99.96 35	95.65 133	99.72 35	99.78 47

XVS		96.47 59	96.37 59	96.77 96	99.62 29	90.66 169	99.43 91	97.58 143	92.41 114	96.86 101	98.96 90	87.37 108	99.87 78	95.65 133	99.43 67	99.78 47

X-MVStestdata		90.69 271	88.66 303	96.77 96	99.62 29	90.66 169	99.43 91	97.58 143	92.41 114	96.86 101	29.59 546	87.37 108	99.87 78	95.65 133	99.43 67	99.78 47

ACMMPR		96.28 66	96.14 74	96.73 100	99.68 16	90.47 175	99.47 80	97.80 87	90.54 170	96.83 105	99.03 79	86.51 136	99.95 39	95.65 133	99.72 35	99.75 55

HPM-MVS		95.41 106	95.22 105	95.99 156	99.29 62	89.14 226	99.17 124	97.09 219	87.28 304	95.40 146	98.48 140	84.93 167	99.38 153	95.64 137	99.65 43	99.47 101
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
BP-MVS1		96.59 53	96.36 60	97.29 66	95.05 287	94.72 51	99.44 87	97.45 170	92.71 106	96.41 119	98.50 133	94.11 17	98.50 205	95.61 138	97.97 140	98.66 203

test_yl		95.27 110	94.60 120	97.28 68	98.53 102	92.98 101	99.05 149	98.70 18	86.76 319	94.65 163	97.74 173	87.78 99	99.44 144	95.57 139	92.61 259	99.44 104

DCV-MVSNet		95.27 110	94.60 120	97.28 68	98.53 102	92.98 101	99.05 149	98.70 18	86.76 319	94.65 163	97.74 173	87.78 99	99.44 144	95.57 139	92.61 259	99.44 104

hybridnocas07		93.98 157	93.52 160	95.36 189	95.01 290	89.37 217	98.63 205	95.64 369	90.79 158	94.69 161	97.31 207	79.01 267	98.11 240	95.54 141	95.07 211	98.61 206

hybrid		93.89 164	93.41 166	95.33 195	94.98 293	89.30 219	98.58 222	95.70 359	89.70 205	94.76 158	97.54 190	78.98 268	98.07 252	95.52 142	94.92 214	98.61 206

region2R		96.30 65	96.17 70	96.70 103	99.70 14	90.31 179	99.46 84	97.66 118	90.55 169	97.07 96	99.07 72	86.85 122	99.97 27	95.43 143	99.74 32	99.81 40

EI-MVSNet-Vis-set		95.76 93	95.63 95	96.17 142	99.14 73	90.33 178	98.49 235	97.82 81	91.92 126	94.75 159	98.88 104	87.06 118	99.48 141	95.40 144	97.17 164	98.70 194

MonoMVSNet		90.69 271	89.78 269	93.45 291	91.78 399	84.97 367	96.51 382	94.44 430	90.56 168	85.96 318	90.97 399	78.61 281	96.27 379	95.35 145	83.79 352	99.11 137

EPNet		96.82 41	96.68 49	97.25 70	98.65 99	93.10 96	99.48 78	98.76 14	96.54 24	97.84 78	98.22 151	87.49 105	99.66 119	95.35 145	97.78 146	99.00 148
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MG-MVS		97.24 25	96.83 41	98.47 17	99.79 7	95.71 22	99.07 145	99.06 10	94.45 59	96.42 118	98.70 119	88.81 82	99.74 113	95.35 145	99.86 12	99.97 8

HY-MVS	88.56 7	95.29 109	94.23 128	98.48 16	97.72 128	96.41 15	94.03 440	98.74 15	92.42 113	95.65 142	94.76 317	86.52 135	99.49 137	95.29 148	92.97 254	99.53 91

testing11		95.33 108	94.98 115	96.37 126	97.20 162	92.31 121	99.29 107	97.68 112	90.59 166	94.43 165	97.20 217	90.79 52	98.60 202	95.25 149	92.38 271	98.18 243

mPP-MVS		95.90 84	95.75 88	96.38 125	99.58 37	89.41 216	99.26 113	97.41 178	90.66 161	94.82 156	98.95 93	86.15 144	99.98 14	95.24 150	99.64 45	99.74 56

viewmamba		93.88 165	93.59 159	94.78 229	94.82 306	87.68 279	98.41 248	95.60 372	91.61 131	94.17 173	97.93 160	79.65 256	98.01 265	95.20 151	94.87 216	98.66 203

ZNCC-MVS		96.09 72	95.81 85	96.95 87	99.42 54	91.19 149	99.55 68	97.53 153	89.72 204	95.86 133	98.94 96	86.59 131	99.97 27	95.13 152	99.56 57	99.68 68

GG-mvs-BLEND				96.98 84	96.53 196	94.81 48	87.20 486	97.74 97		93.91 180	96.40 276	96.56 2	96.94 338	95.08 153	98.95 97	99.20 128

EIA-MVS		95.11 115	95.27 103	94.64 238	96.34 208	86.51 316	99.59 64	96.62 249	92.51 109	94.08 175	98.64 123	86.05 145	98.24 223	95.07 154	98.50 126	99.18 129

DeepC-MVS	91.02 4	94.56 140	93.92 145	96.46 118	97.16 168	90.76 165	98.39 258	97.11 215	93.92 71	88.66 294	98.33 146	78.14 286	99.85 88	95.02 155	98.57 123	98.78 179
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
casdiffmvs_mvg		94.00 155	93.33 170	96.03 151	95.22 265	90.90 163	99.09 142	95.99 310	90.58 167	91.55 240	97.37 201	79.91 253	98.06 255	95.01 156	95.22 207	99.13 134
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		94.19 150	93.78 154	95.43 186	95.81 235	89.44 215	98.80 176	96.11 298	90.24 182	93.85 182	97.75 170	80.94 246	98.14 233	95.00 157	95.48 203	98.72 191

WTY-MVS		95.97 78	95.11 110	98.54 15	97.62 133	96.65 11	99.44 87	98.74 15	92.25 120	95.21 149	98.46 143	86.56 133	99.46 143	95.00 157	92.69 258	99.50 97

CSCG		94.87 125	94.71 118	95.36 189	99.54 43	86.49 317	99.34 104	98.15 43	82.71 400	90.15 270	99.25 34	89.48 73	99.86 84	94.97 159	98.82 104	99.72 60

EI-MVSNet-UG-set		95.43 104	95.29 102	95.86 163	99.07 79	89.87 199	98.43 243	97.80 87	91.78 128	94.11 174	98.77 109	86.25 142	99.48 141	94.95 160	96.45 177	98.22 239

LuminaMVS		93.16 200	92.30 205	95.76 167	92.26 386	92.64 114	97.60 337	96.21 286	90.30 180	93.06 199	95.59 300	76.00 309	97.89 273	94.93 161	94.70 218	96.76 297

CPTT-MVS		94.60 137	94.43 124	95.09 213	99.66 19	86.85 310	99.44 87	97.47 167	83.22 387	94.34 170	98.96 90	82.50 216	99.55 131	94.81 162	99.50 60	98.88 164

PVSNet_0	83.28 16	87.31 344	85.16 361	93.74 285	94.78 307	84.59 371	98.91 165	98.69 20	89.81 201	78.59 422	93.23 349	61.95 432	99.34 159	94.75 163	55.72 499	97.30 280

CLD-MVS		91.06 262	90.71 255	92.10 324	94.05 341	86.10 337	99.55 68	96.29 282	94.16 64	84.70 328	97.17 221	69.62 372	97.82 280	94.74 164	86.08 333	92.39 349
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
casdiffmvs		93.98 157	93.43 164	95.61 179	95.07 286	89.86 200	98.80 176	95.84 343	90.98 150	92.74 210	97.66 180	79.71 255	98.10 243	94.72 165	95.37 204	98.87 167
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
VDDNet		90.08 292	88.54 309	94.69 235	94.41 322	87.68 279	98.21 279	96.40 270	76.21 453	93.33 195	97.75 170	54.93 461	98.77 189	94.71 166	90.96 304	97.61 271

viewcassd2359sk11		93.95 159	93.48 163	95.36 189	95.48 251	89.25 221	98.74 185	96.10 299	90.10 190	93.48 191	97.55 189	80.05 251	98.14 233	94.66 167	95.16 208	98.69 195

CDPH-MVS		96.56 57	96.18 67	97.70 46	99.59 35	93.92 70	99.13 138	97.44 174	89.02 235	97.90 77	99.22 39	88.90 81	99.49 137	94.63 168	99.79 28	99.68 68

GST-MVS		95.97 78	95.66 91	96.90 90	99.49 52	91.22 147	99.45 86	97.48 165	89.69 206	95.89 130	98.72 115	86.37 139	99.95 39	94.62 169	99.22 80	99.52 92

Effi-MVS+		93.87 166	93.15 176	96.02 152	95.79 236	90.76 165	96.70 376	95.78 348	86.98 312	95.71 139	97.17 221	79.58 257	98.01 265	94.57 170	96.09 189	99.31 117

LFMVS		92.23 231	90.84 251	96.42 121	98.24 109	91.08 156	98.24 276	96.22 285	83.39 385	94.74 160	98.31 147	61.12 436	98.85 185	94.45 171	92.82 255	99.32 116

viewmanbaseed2359cas		93.90 162	93.34 169	95.56 181	95.39 257	89.72 206	98.58 222	96.00 309	90.32 179	93.58 189	97.78 167	78.71 278	98.07 252	94.43 172	95.29 205	98.88 164

NormalMVS		95.87 85	95.83 81	95.99 156	99.27 64	90.37 176	99.14 133	96.39 271	94.92 47	96.30 121	97.98 158	85.33 161	99.23 163	94.35 173	98.82 104	98.37 227

SymmetryMVS		95.49 102	95.27 103	96.17 142	97.13 170	90.37 176	99.14 133	98.59 23	94.92 47	96.30 121	97.98 158	85.33 161	99.23 163	94.35 173	93.67 244	98.92 161

ET-MVSNet_ETH3D		92.56 222	91.45 233	95.88 162	96.39 206	94.13 68	99.46 84	96.97 230	92.18 122	66.94 485	98.29 149	94.65 15	94.28 447	94.34 175	83.82 351	99.24 123

baseline		93.91 161	93.30 171	95.72 169	95.10 284	90.07 190	97.48 339	95.91 333	91.03 149	93.54 190	97.68 178	79.58 257	98.02 264	94.27 176	95.14 209	99.08 143

SDMVSNet		91.09 259	89.91 267	94.65 236	96.80 187	90.54 173	97.78 318	97.81 85	88.34 266	85.73 319	95.26 310	66.44 406	98.26 221	94.25 177	86.75 325	95.14 328

E2		93.62 177	93.07 177	95.26 203	95.00 291	88.99 236	98.63 205	96.09 304	89.84 198	93.02 200	97.36 202	78.88 270	98.11 240	94.23 178	94.60 220	98.67 198

E3		93.62 177	93.07 177	95.26 203	94.98 293	89.00 235	98.63 205	96.09 304	89.83 199	93.01 202	97.35 204	78.90 269	98.11 240	94.23 178	94.60 220	98.67 198

reproduce_monomvs		92.11 235	91.82 225	92.98 300	98.25 107	90.55 172	98.38 260	97.93 67	94.81 49	80.46 393	92.37 365	96.46 3	97.17 327	94.06 180	73.61 422	91.23 404

PAPR		96.35 62	95.82 83	97.94 36	99.63 25	94.19 67	99.42 93	97.55 148	92.43 111	93.82 185	99.12 65	87.30 113	99.91 59	94.02 181	99.06 88	99.74 56

PGM-MVS		95.85 87	95.65 93	96.45 119	99.50 49	89.77 205	98.22 277	98.90 13	89.19 226	96.74 111	98.95 93	85.91 148	99.92 51	93.94 182	99.46 62	99.66 72

Casviewmamba		93.63 176	93.20 174	94.94 221	95.12 275	87.64 283	98.76 183	95.91 333	90.44 173	92.12 226	97.90 161	79.15 266	98.16 232	93.89 183	95.52 200	99.00 148

gg-mvs-nofinetune		90.00 293	87.71 321	96.89 94	96.15 219	94.69 53	85.15 493	97.74 97	68.32 489	92.97 204	60.16 522	96.10 4	96.84 341	93.89 183	98.87 102	99.14 132

MVS		93.92 160	92.28 206	98.83 8	95.69 240	96.82 9	96.22 396	98.17 39	84.89 357	84.34 333	98.61 127	79.32 263	99.83 94	93.88 185	99.43 67	99.86 34

旧先验2							98.67 199		85.75 342	98.96 34			98.97 181	93.84 186

ACMMP		94.67 134	94.30 126	95.79 166	99.25 66	88.13 267	98.41 248	98.67 21	90.38 177	91.43 242	98.72 115	82.22 225	99.95 39	93.83 187	95.76 194	99.29 119
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
BP-MVS														93.82 188

HQP-MVS		91.50 247	91.23 238	92.29 318	93.95 342	86.39 321	99.16 125	96.37 275	93.92 71	87.57 302	96.67 267	73.34 337	97.77 286	93.82 188	86.29 328	92.72 344

nomal-1		93.28 194	92.96 185	94.27 257	96.12 225	87.08 307	98.16 284	97.23 199	88.41 262	88.79 291	94.03 325	87.66 102	97.86 278	93.72 190	92.50 266	97.86 258

DP-MVS Recon		95.85 87	95.15 107	97.95 35	99.87 2	94.38 61	99.60 63	97.48 165	86.58 322	94.42 166	99.13 62	87.36 111	99.98 14	93.64 191	98.33 132	99.48 99

CHOSEN 1792x2688		94.35 144	93.82 152	95.95 159	97.40 147	88.74 250	98.41 248	98.27 33	92.18 122	91.43 242	96.40 276	78.88 270	99.81 100	93.59 192	97.81 143	99.30 118

E4		93.15 202	92.50 200	95.09 213	94.41 322	88.61 252	98.48 237	95.99 310	89.40 222	92.22 223	97.13 223	77.43 292	98.10 243	93.58 193	93.90 235	98.56 211

testing91		94.88 123	94.44 123	96.21 137	97.19 164	91.90 131	99.23 115	97.66 118	89.91 196	93.66 187	97.05 237	90.21 65	98.50 205	93.52 194	91.53 295	98.25 235

testing99		94.88 123	94.45 122	96.17 142	97.20 162	91.91 130	99.20 117	97.66 118	89.95 195	93.68 186	97.06 235	90.28 64	98.50 205	93.52 194	91.54 292	98.12 250

cascas		90.93 266	89.33 283	95.76 167	95.69 240	93.03 99	98.99 156	96.59 254	80.49 429	86.79 314	94.45 320	65.23 416	98.60 202	93.52 194	92.18 278	95.66 327

viewmambaseed2359dif		93.05 206	92.64 195	94.25 260	94.94 298	86.53 315	98.38 260	95.69 362	87.03 308	93.38 193	97.74 173	78.79 276	98.08 247	93.49 197	94.35 227	98.15 245

HQP_MVS		91.26 254	90.95 247	92.16 322	93.84 350	86.07 340	99.02 152	96.30 279	93.38 91	86.99 309	96.52 270	72.92 344	97.75 293	93.46 198	86.17 331	92.67 346

plane_prior5								96.30 279					97.75 293	93.46 198	86.17 331	92.67 346

PVSNet_Blended_VisFu		94.67 134	94.11 134	96.34 128	97.14 169	91.10 154	99.32 106	97.43 176	92.10 125	91.53 241	96.38 279	83.29 194	99.68 117	93.42 200	96.37 179	98.25 235

viewdifsd2359ckpt09		93.54 180	92.91 187	95.44 185	95.57 245	89.48 213	98.68 196	95.66 368	89.52 216	92.50 216	97.75 170	78.46 282	98.03 262	93.32 201	94.69 219	98.81 173

AdaColmap		93.82 168	93.06 179	96.10 147	99.88 1	89.07 229	98.33 264	97.55 148	86.81 317	90.39 265	98.65 122	75.09 320	99.98 14	93.32 201	97.53 153	99.26 122

viewdifsd2359ckpt13		93.45 182	92.86 189	95.21 206	95.45 252	88.91 244	98.59 219	95.92 327	89.39 223	92.67 213	97.33 206	78.02 288	98.03 262	93.27 203	95.12 210	98.69 195

E5new		92.80 209	92.19 209	94.62 240	94.34 325	87.64 283	98.08 297	95.97 313	89.15 228	92.01 227	97.08 232	76.37 304	98.08 247	93.25 204	93.46 246	98.15 245

E6new		92.80 209	92.19 209	94.62 240	94.31 333	87.64 283	98.08 297	95.97 313	89.15 228	92.01 227	97.10 226	76.38 302	98.08 247	93.25 204	93.45 248	98.15 245

E6		92.80 209	92.19 209	94.62 240	94.31 333	87.64 283	98.08 297	95.97 313	89.15 228	92.01 227	97.10 226	76.38 302	98.08 247	93.25 204	93.45 248	98.15 245

E5		92.80 209	92.19 209	94.62 240	94.34 325	87.64 283	98.08 297	95.97 313	89.15 228	92.01 227	97.08 232	76.37 304	98.08 247	93.25 204	93.46 246	98.15 245

HyFIR lowres test		93.68 173	93.29 172	94.87 224	97.57 139	88.04 269	98.18 281	98.47 26	87.57 297	91.24 247	95.05 313	85.49 154	97.46 316	93.22 208	92.82 255	99.10 138

viewdifsd2359ckpt07		92.71 215	92.19 209	94.28 256	94.96 296	86.26 325	98.29 271	95.80 347	88.71 250	90.81 252	97.34 205	76.57 301	98.19 228	93.16 209	94.05 232	98.39 223

HPM-MVS_fast		94.89 121	94.62 119	95.70 170	99.11 75	88.44 259	99.14 133	97.11 215	85.82 339	95.69 140	98.47 141	83.46 189	99.32 160	93.16 209	99.63 50	99.35 113

PMMVS		93.62 177	93.90 148	92.79 306	96.79 189	81.40 415	98.85 169	96.81 237	91.25 145	96.82 107	98.15 155	77.02 298	98.13 236	93.15 211	96.30 182	98.83 171

dtuplus		92.78 213	92.35 203	94.07 269	94.70 310	85.91 344	98.47 240	95.59 374	87.50 300	92.88 205	97.66 180	77.24 295	98.12 239	93.01 212	94.15 229	98.20 241

LCM-MVSNet-Re		88.59 325	88.61 304	88.51 414	95.53 249	72.68 479	96.85 368	88.43 499	88.45 258	73.14 456	90.63 411	75.82 313	94.38 446	92.95 213	95.71 196	98.48 217

viewmacassd2359aftdt		93.16 200	92.44 202	95.31 197	94.34 325	89.19 223	98.40 253	95.84 343	89.62 210	92.87 207	97.31 207	76.07 308	98.00 267	92.93 214	94.58 222	98.75 184

EPP-MVSNet		93.75 170	93.67 157	94.01 274	95.86 233	85.70 351	98.67 199	97.66 118	84.46 367	91.36 245	97.18 220	91.16 39	97.79 284	92.93 214	93.75 241	98.53 213

CostFormer		92.89 208	92.48 201	94.12 267	94.99 292	85.89 346	92.89 453	97.00 228	86.98 312	95.00 155	90.78 403	90.05 67	97.51 314	92.92 216	91.73 287	98.96 153

XVG-OURS-SEG-HR		90.95 265	90.66 258	91.83 329	95.18 271	81.14 422	95.92 405	95.92 327	88.40 263	90.33 266	97.85 162	70.66 366	99.38 153	92.83 217	88.83 317	94.98 331

sss		94.85 126	93.94 144	97.58 50	96.43 201	94.09 69	98.93 161	99.16 8	89.50 217	95.27 148	97.85 162	81.50 235	99.65 123	92.79 218	94.02 233	98.99 150

hybridcas		93.44 183	92.82 191	95.31 197	94.91 301	89.08 228	98.82 172	95.84 343	90.28 181	91.22 248	97.65 182	78.39 284	98.06 255	92.71 219	95.55 199	98.79 176

test_vis1_rt		81.31 420	80.05 423	85.11 447	91.29 408	70.66 485	98.98 158	77.39 518	85.76 341	68.80 476	82.40 484	36.56 499	99.44 144	92.67 220	86.55 327	85.24 488

MAR-MVS		94.43 143	94.09 135	95.45 183	99.10 77	87.47 294	98.39 258	97.79 89	88.37 264	94.02 177	99.17 52	78.64 280	99.91 59	92.48 221	98.85 103	98.96 153
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
viewdifsd2359ckpt11		90.42 279	89.65 271	92.73 311	93.71 357	82.67 399	98.09 294	95.27 399	89.80 202	90.10 272	97.40 199	69.43 374	98.18 230	92.46 222	80.61 373	97.34 277

viewmsd2359difaftdt		90.43 278	89.65 271	92.74 309	93.72 356	82.67 399	98.09 294	95.27 399	89.80 202	90.12 271	97.40 199	69.43 374	98.20 227	92.45 223	80.62 372	97.34 277

API-MVS		94.78 128	94.18 132	96.59 111	99.21 70	90.06 193	98.80 176	97.78 92	83.59 382	93.85 182	99.21 42	83.79 184	99.97 27	92.37 224	99.00 92	99.74 56

nrg030		90.23 285	88.87 297	94.32 255	91.53 404	93.54 85	98.79 181	95.89 337	88.12 274	84.55 330	94.61 319	78.80 275	96.88 340	92.35 225	75.21 404	92.53 348

OMC-MVS		93.90 162	93.62 158	94.73 233	98.63 100	87.00 308	98.04 303	96.56 258	92.19 121	92.46 218	98.73 113	79.49 262	99.14 172	92.16 226	94.34 228	98.03 252

0.3-1-1-0.015		91.27 253	89.64 273	96.15 146	92.69 379	91.62 139	99.74 37	97.35 188	84.68 363	92.71 211	93.18 350	85.31 163	97.75 293	92.11 227	68.98 452	99.09 139

0.4-1-1-0.2		91.19 258	89.53 276	96.20 138	92.78 378	91.76 136	99.76 33	97.34 189	84.77 359	92.54 215	93.05 354	84.51 175	97.74 296	92.01 228	68.98 452	99.09 139

VortexMVS		90.18 288	89.28 284	92.89 304	95.58 244	90.94 162	97.82 315	95.94 322	90.90 152	82.11 370	91.48 387	78.75 277	96.08 388	91.99 229	78.97 381	91.65 374

testing222		94.48 142	94.00 138	95.95 159	97.30 155	92.27 122	98.82 172	97.92 68	89.20 225	94.82 156	97.26 211	87.13 115	97.32 324	91.95 230	91.56 290	98.25 235

1314		93.44 183	91.98 219	97.84 38	95.24 263	94.38 61	96.22 396	97.92 68	90.18 186	82.28 363	97.71 177	77.63 291	99.80 102	91.94 231	98.67 116	99.34 115

0.4-1-1-0.1		91.07 260	89.43 280	96.01 154	92.48 382	91.23 146	99.69 49	97.34 189	84.50 366	92.49 217	92.98 358	84.53 173	97.72 298	91.87 232	68.97 454	99.08 143

DPM-MVS		97.86 10	97.25 27	99.68 1	98.25 107	99.10 1	99.76 33	97.78 92	96.61 23	98.15 65	99.53 9	93.62 19	100.00 1	91.79 233	99.80 27	99.94 19

GDP-MVS		96.05 74	95.63 95	97.31 65	95.37 259	94.65 54	99.36 101	96.42 269	92.14 124	97.07 96	98.53 129	93.33 21	98.50 205	91.76 234	96.66 175	98.78 179

FBQ-MVS		94.65 136	94.17 133	96.09 148	97.22 160	90.65 171	98.93 161	97.78 92	90.19 185	95.02 154	96.47 274	87.80 98	98.41 213	91.72 235	92.45 268	99.21 127

mvs_anonymous		92.50 223	91.65 229	95.06 216	96.60 193	89.64 209	97.06 360	96.44 268	86.64 321	84.14 334	93.93 331	82.49 217	96.17 384	91.47 236	96.08 190	99.35 113

baseline2		94.04 154	93.80 153	94.74 232	93.07 374	90.25 180	98.12 288	98.16 42	89.86 197	86.53 315	96.95 242	95.56 6	98.05 259	91.44 237	94.53 223	95.93 323

IB-MVS	89.43 6	92.12 233	90.83 253	95.98 158	95.40 256	90.78 164	99.81 21	98.06 52	91.23 147	85.63 322	93.66 339	90.63 54	98.78 188	91.22 238	71.85 441	98.36 230
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
ab-mvs		91.05 263	89.17 286	96.69 104	95.96 230	91.72 137	92.62 457	97.23 199	85.61 343	89.74 280	93.89 333	68.55 380	99.42 148	91.09 239	87.84 320	98.92 161

XVG-OURS		90.83 267	90.49 260	91.86 328	95.23 264	81.25 419	95.79 413	95.92 327	88.96 237	90.02 274	98.03 157	71.60 359	99.35 158	91.06 240	87.78 321	94.98 331

3Dnovator	87.35 11	93.17 199	91.77 227	97.37 62	95.41 255	93.07 97	98.82 172	97.85 74	91.53 135	82.56 356	97.58 187	71.97 354	99.82 97	91.01 241	99.23 79	99.22 126

VPA-MVSNet		89.10 308	87.66 322	93.45 291	92.56 380	91.02 158	97.97 308	98.32 32	86.92 314	86.03 317	92.01 371	68.84 379	97.10 332	90.92 242	75.34 403	92.23 356

PAPM_NR		95.43 104	95.05 112	96.57 114	99.42 54	90.14 186	98.58 222	97.51 159	90.65 163	92.44 219	98.90 100	87.77 101	99.90 64	90.88 243	99.32 72	99.68 68

3Dnovator+	87.72 8	93.43 185	91.84 224	98.17 26	95.73 239	95.08 38	98.92 164	97.04 222	91.42 140	81.48 383	97.60 185	74.60 323	99.79 106	90.84 244	98.97 94	99.64 78

test_fmvs2		85.10 381	85.45 358	84.02 455	89.85 425	65.63 496	98.49 235	92.59 461	90.45 172	85.43 325	93.32 345	43.94 487	96.59 351	90.81 245	84.19 346	89.85 440

gm-plane-assit					94.69 311	88.14 266			88.22 271		97.20 217		98.29 219	90.79 246

MVSTER		92.71 215	92.32 204	93.86 279	97.29 156	92.95 104	99.01 154	96.59 254	90.09 191	85.51 323	94.00 328	94.61 16	96.56 353	90.77 247	83.03 358	92.08 364

ETVMVS		94.50 141	93.90 148	96.31 131	97.48 145	92.98 101	99.07 145	97.86 72	88.09 275	94.40 167	96.90 249	88.35 88	97.28 325	90.72 248	92.25 277	98.66 203

ACMP	87.39 10	88.71 321	88.24 313	90.12 379	93.91 348	81.06 423	98.50 233	95.67 365	89.43 220	80.37 394	95.55 301	65.67 409	97.83 279	90.55 249	84.51 342	91.47 386
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ECVR-MVS		92.29 228	91.33 235	95.15 210	96.41 204	87.84 275	98.10 291	94.84 418	90.82 156	91.42 244	97.28 209	65.61 411	98.49 209	90.33 250	97.19 162	99.12 135

testdata				95.26 203	98.20 110	87.28 301		97.60 137	85.21 348	98.48 54	99.15 57	88.15 93	98.72 197	90.29 251	99.45 65	99.78 47

LPG-MVS_test		88.86 313	88.47 310	90.06 380	93.35 367	80.95 424	98.22 277	95.94 322	87.73 293	83.17 345	96.11 286	66.28 407	97.77 286	90.19 252	85.19 338	91.46 387

LGP-MVS_train				90.06 380	93.35 367	80.95 424		95.94 322	87.73 293	83.17 345	96.11 286	66.28 407	97.77 286	90.19 252	85.19 338	91.46 387

MVSFormer		94.71 133	94.08 136	96.61 109	95.05 287	94.87 42	97.77 320	96.17 294	86.84 315	98.04 72	98.52 131	85.52 151	95.99 392	89.83 254	98.97 94	98.96 153

test_djsdf		88.26 330	87.73 320	89.84 387	88.05 451	82.21 405	97.77 320	96.17 294	86.84 315	82.41 361	91.95 375	72.07 353	95.99 392	89.83 254	84.50 343	91.32 399

test2506		94.80 127	94.21 129	96.58 112	96.41 204	92.18 125	98.01 305	98.96 11	90.82 156	93.46 192	97.28 209	85.92 146	98.45 211	89.82 256	97.19 162	99.12 135

tpmrst		92.78 213	92.16 214	94.65 236	96.27 211	87.45 295	91.83 464	97.10 218	89.10 234	94.68 162	90.69 407	88.22 90	97.73 297	89.78 257	91.80 285	98.77 181

PLC	91.07 3	94.23 148	94.01 137	94.87 224	99.17 72	87.49 293	99.25 114	96.55 259	88.43 261	91.26 246	98.21 153	85.92 146	99.86 84	89.77 258	97.57 150	97.24 283
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test1111		92.12 233	91.19 239	94.94 221	96.15 219	87.36 298	98.12 288	94.84 418	90.85 155	90.97 250	97.26 211	65.60 412	98.37 215	89.74 259	97.14 165	99.07 146

CDS-MVSNet		93.47 181	93.04 181	94.76 230	94.75 309	89.45 214	98.82 172	97.03 224	87.91 282	90.97 250	96.48 273	89.06 76	96.36 366	89.50 260	92.81 257	98.49 216
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		89.97 294	90.68 257	87.81 420	95.15 272	71.98 481	97.87 313	95.40 393	91.92 126	87.57 302	91.44 388	74.27 329	96.84 341	89.45 261	93.10 253	94.60 334

jajsoiax		87.35 343	86.51 342	89.87 385	87.75 458	81.74 410	97.03 361	95.98 312	88.47 255	80.15 397	93.80 335	61.47 433	96.36 366	89.44 262	84.47 344	91.50 384

mvs_tets		87.09 346	86.22 345	89.71 391	87.87 454	81.39 416	96.73 375	95.90 335	88.19 272	79.99 399	93.61 340	59.96 440	96.31 374	89.40 263	84.34 345	91.43 389

PS-MVSNAJss		89.54 302	89.05 292	91.00 354	88.77 441	84.36 374	97.39 342	95.97 313	88.47 255	81.88 375	93.80 335	82.48 218	96.50 357	89.34 264	83.34 357	92.15 361

VPNet		88.30 328	86.57 340	93.49 289	91.95 394	91.35 145	98.18 281	97.20 206	88.61 252	84.52 331	94.89 314	62.21 431	96.76 346	89.34 264	72.26 438	92.36 350

114514_t		94.06 153	93.05 180	97.06 77	99.08 78	92.26 123	98.97 159	97.01 227	82.58 402	92.57 214	98.22 151	80.68 247	99.30 161	89.34 264	99.02 91	99.63 81

OPM-MVS		89.76 298	89.15 290	91.57 344	90.53 416	85.58 353	98.11 290	95.93 326	92.88 104	86.05 316	96.47 274	67.06 396	97.87 276	89.29 267	86.08 333	91.26 402
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SSM_0407		92.04 238	91.03 244	95.07 215	95.12 275	89.81 202	97.18 356	95.49 384	86.17 331	89.50 283	97.13 223	75.65 315	97.68 299	89.26 268	93.79 238	97.73 261

SSM_0404		92.33 226	91.33 235	95.33 195	95.35 260	90.54 173	97.45 340	95.49 384	86.17 331	90.26 267	97.13 223	75.65 315	97.82 280	89.26 268	95.26 206	97.63 269

MVS_Test		93.67 174	92.67 194	96.69 104	96.72 191	92.66 111	97.22 353	96.03 308	87.69 295	95.12 152	94.03 325	81.55 233	98.28 220	89.17 270	96.46 176	99.14 132

BH-w/o		92.32 227	91.79 226	93.91 278	96.85 184	86.18 334	99.11 141	95.74 353	88.13 273	84.81 327	97.00 239	77.26 294	97.91 271	89.16 271	98.03 138	97.64 266

TAMVS		92.62 219	92.09 217	94.20 264	94.10 337	87.68 279	98.41 248	96.97 230	87.53 299	89.74 280	96.04 289	84.77 172	96.49 359	88.97 272	92.31 274	98.42 219

WBMVS		91.35 252	90.49 260	93.94 276	96.97 180	93.40 89	99.27 112	96.71 243	87.40 302	83.10 348	91.76 379	92.38 33	96.23 380	88.95 273	77.89 387	92.17 360

CNLPA		93.64 175	92.74 192	96.36 127	98.96 85	90.01 196	99.19 118	95.89 337	86.22 330	89.40 286	98.85 105	80.66 248	99.84 90	88.57 274	96.92 169	99.24 123

baseline1		92.61 220	91.28 237	96.58 112	97.05 177	94.63 55	97.72 325	96.20 287	89.82 200	88.56 295	96.85 254	86.85 122	97.82 280	88.42 275	80.10 377	97.30 280

CANet_DTU		94.31 145	93.35 168	97.20 72	97.03 179	94.71 52	98.62 209	95.54 377	95.61 38	97.21 92	98.47 141	71.88 355	99.84 90	88.38 276	97.46 155	97.04 290

thisisatest0515		94.75 129	94.19 130	96.43 120	96.13 224	92.64 114	99.47 80	97.60 137	87.55 298	93.17 196	97.59 186	94.71 13	98.42 212	88.28 277	93.20 251	98.24 238

原ACMM1				96.18 140	99.03 80	90.08 189		97.63 131	88.98 236	97.00 98	98.97 85	88.14 94	99.71 115	88.23 278	99.62 51	98.76 183

UGNet		91.91 240	90.85 250	95.10 212	97.06 175	88.69 251	98.01 305	98.24 36	92.41 114	92.39 221	93.61 340	60.52 438	99.68 117	88.14 279	97.25 160	96.92 294
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
AUN-MVS		90.17 289	89.50 277	92.19 321	96.21 214	82.67 399	97.76 323	97.53 153	88.05 276	91.67 235	96.15 284	83.10 200	97.47 315	88.11 280	66.91 463	96.43 314

Vis-MVSNet (Re-imp)		93.26 196	93.00 184	94.06 271	96.14 221	86.71 313	98.68 196	96.70 244	88.30 268	89.71 282	97.64 183	85.43 157	96.39 364	88.06 281	96.32 180	99.08 143

PVSNet	87.13 12	93.69 171	92.83 190	96.28 133	97.99 119	90.22 183	99.38 97	98.93 12	91.42 140	93.66 187	97.68 178	71.29 362	99.64 125	87.94 282	97.20 161	98.98 151

FIs		90.70 270	89.87 268	93.18 296	92.29 385	91.12 152	98.17 283	98.25 34	89.11 233	83.44 339	94.82 316	82.26 224	96.17 384	87.76 283	82.76 360	92.25 354

tpm2		91.77 243	91.09 241	93.82 281	94.83 305	85.56 354	92.51 458	97.16 210	84.00 373	93.83 184	90.66 409	87.54 104	97.17 327	87.73 284	91.55 291	98.72 191

无先验							98.52 229	97.82 81	87.20 306				99.90 64	87.64 285		99.85 35

Anonymous202405211		88.84 314	87.03 335	94.27 257	98.14 114	84.18 377	98.44 242	95.58 375	76.79 451	89.34 287	96.88 252	53.42 467	99.54 133	87.53 286	87.12 324	99.09 139

mamba_0408		90.65 273	89.16 287	95.12 211	95.12 275	89.81 202	83.02 503	95.17 411	85.95 336	89.50 283	96.85 254	75.85 311	97.82 280	87.19 287	93.79 238	97.73 261

SSM_04072		90.31 283	89.16 287	93.74 285	95.12 275	89.81 202	83.02 503	95.17 411	85.95 336	89.50 283	96.85 254	75.85 311	93.69 454	87.19 287	93.79 238	97.73 261

IS-MVSNet		93.00 207	92.51 199	94.49 246	96.14 221	87.36 298	98.31 267	95.70 359	88.58 254	90.17 269	97.50 192	83.02 202	97.22 326	87.06 289	96.07 191	98.90 163

MDTV_nov1_ep13_2view						91.17 151	91.38 472		87.45 301	93.08 198		86.67 129		87.02 290		98.95 157

Anonymous20240529		87.66 340	85.58 355	93.92 277	97.59 137	85.01 365	98.13 286	97.13 213	66.69 494	88.47 296	96.01 290	55.09 459	99.51 135	87.00 291	84.12 347	97.23 284

UniMVSNet_NR-MVSNet		89.60 300	88.55 308	92.75 308	92.17 389	90.07 190	98.74 185	98.15 43	88.37 264	83.21 343	93.98 329	82.86 204	95.93 396	86.95 292	72.47 435	92.25 354

DU-MVS		88.83 316	87.51 325	92.79 306	91.46 405	90.07 190	98.71 189	97.62 133	88.87 242	83.21 343	93.68 337	74.63 321	95.93 396	86.95 292	72.47 435	92.36 350

FA-MVS(test-final)		92.22 232	91.08 242	95.64 174	96.05 227	88.98 237	91.60 468	97.25 195	86.99 309	91.84 231	92.12 367	83.03 201	99.00 178	86.91 294	93.91 234	98.93 159

ACMM	86.95 13	88.77 319	88.22 314	90.43 371	93.61 358	81.34 417	98.50 233	95.92 327	87.88 283	83.85 337	95.20 312	67.20 394	97.89 273	86.90 295	84.90 340	92.06 365
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet (Re)		89.50 303	88.32 312	93.03 298	92.21 388	90.96 160	98.90 167	98.39 29	89.13 232	83.22 342	92.03 369	81.69 232	96.34 372	86.79 296	72.53 434	91.81 371

BH-untuned		91.46 249	90.84 251	93.33 294	96.51 198	84.83 369	98.84 171	95.50 383	86.44 329	83.50 338	96.70 265	75.49 319	97.77 286	86.78 297	97.81 143	97.40 275

KinetiMVS		93.07 205	91.98 219	96.34 128	94.84 304	91.78 133	98.73 188	97.18 207	91.25 145	94.01 178	97.09 230	71.02 363	98.86 184	86.77 298	96.89 170	98.37 227

icg_test_0407_2		91.56 246	90.90 249	93.54 288	94.61 315	86.22 328	95.71 416	95.72 354	88.78 244	89.76 278	96.93 245	77.24 295	95.65 416	86.73 299	92.59 261	98.74 185

IMVS_0407		91.79 242	90.98 245	94.24 262	94.61 315	86.22 328	96.45 384	95.72 354	88.78 244	89.76 278	96.93 245	77.24 295	97.77 286	86.73 299	92.59 261	98.74 185

IMVS_0404		89.79 297	88.57 307	93.47 290	94.61 315	86.22 328	94.45 429	95.72 354	88.78 244	81.88 375	96.93 245	65.39 415	95.47 422	86.73 299	92.59 261	98.74 185

IMVS_0403		91.93 239	91.13 240	94.34 253	94.61 315	86.22 328	96.70 376	95.72 354	88.78 244	90.00 275	96.93 245	78.07 287	98.07 252	86.73 299	92.59 261	98.74 185

mvsany_test3		75.85 451	74.52 451	79.83 472	73.53 510	60.64 502	91.73 466	87.87 502	83.91 376	70.55 468	82.52 483	31.12 501	93.66 455	86.66 303	62.83 473	85.19 489

miper_enhance_ethall		90.33 282	89.70 270	92.22 319	97.12 172	88.93 242	98.35 263	95.96 319	88.60 253	83.14 347	92.33 366	87.38 107	96.18 382	86.49 304	77.89 387	91.55 383

casdiffseed414692147		91.84 241	90.69 256	95.28 201	94.50 320	89.32 218	98.31 267	95.67 365	87.82 287	90.22 268	96.63 269	74.27 329	97.94 270	86.37 305	92.43 269	98.59 210

thisisatest0530		94.00 155	93.52 160	95.43 186	95.76 238	90.02 195	98.99 156	97.60 137	86.58 322	91.74 233	97.36 202	94.78 12	98.34 216	86.37 305	92.48 267	97.94 256

UWE-MVS		93.18 197	93.40 167	92.50 316	96.56 194	83.55 385	98.09 294	97.84 76	89.50 217	91.72 234	96.23 282	91.08 42	96.70 347	86.28 307	93.33 250	97.26 282

TESTMET0.1,1		93.82 168	93.26 173	95.49 182	95.21 267	90.25 180	99.15 130	97.54 152	89.18 227	91.79 232	94.87 315	89.13 75	97.63 304	86.21 308	96.29 184	98.60 208

anonymousdsp		86.69 353	85.75 353	89.53 396	86.46 467	82.94 392	96.39 386	95.71 358	83.97 374	79.63 404	90.70 406	68.85 378	95.94 395	86.01 309	84.02 348	89.72 442

F-COLMAP		92.07 236	91.75 228	93.02 299	98.16 113	82.89 395	98.79 181	95.97 313	86.54 324	87.92 299	97.80 165	78.69 279	99.65 123	85.97 310	95.93 193	96.53 309

cl22		89.57 301	88.79 300	91.91 327	97.94 121	87.62 288	97.98 307	96.51 261	85.03 353	82.37 362	91.79 376	83.65 185	96.50 357	85.96 311	77.89 387	91.61 380

test-LLR		93.11 203	92.68 193	94.40 250	94.94 298	87.27 302	99.15 130	97.25 195	90.21 183	91.57 237	94.04 323	84.89 168	97.58 310	85.94 312	96.13 187	98.36 230

test-mter		93.27 195	92.89 188	94.40 250	94.94 298	87.27 302	99.15 130	97.25 195	88.95 238	91.57 237	94.04 323	88.03 96	97.58 310	85.94 312	96.13 187	98.36 230

FC-MVSNet-test		90.22 286	89.40 281	92.67 314	91.78 399	89.86 200	97.89 310	98.22 37	88.81 243	82.96 349	94.66 318	81.90 231	95.96 394	85.89 314	82.52 363	92.20 359

Vis-MVSNet		92.64 218	91.85 223	95.03 219	95.12 275	88.23 264	98.48 237	96.81 237	91.61 131	92.16 225	97.22 216	71.58 360	98.00 267	85.85 315	97.81 143	98.88 164
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sd_testset		89.23 304	88.05 318	92.74 309	96.80 187	85.33 358	95.85 411	97.03 224	88.34 266	85.73 319	95.26 310	61.12 436	97.76 292	85.61 316	86.75 325	95.14 328

test_fmvs3		75.09 454	75.19 446	74.81 480	77.45 504	54.08 509	95.93 404	90.64 485	82.51 405	73.29 454	81.19 492	22.29 509	86.29 506	85.50 317	67.89 458	84.06 492

WR-MVS		88.54 326	87.22 332	92.52 315	91.93 396	89.50 212	98.56 225	97.84 76	86.99 309	81.87 377	93.81 334	74.25 331	95.92 398	85.29 318	74.43 413	92.12 362

XXY-MVS		87.75 336	86.02 348	92.95 303	90.46 418	89.70 208	97.71 327	95.90 335	84.02 372	80.95 386	94.05 322	67.51 392	97.10 332	85.16 319	78.41 384	92.04 366

thres200		93.69 171	92.59 198	96.97 85	97.76 126	94.74 50	99.35 103	99.36 2	89.23 224	91.21 249	96.97 241	83.42 191	98.77 189	85.08 320	90.96 304	97.39 276

tttt0517		93.30 192	93.01 182	94.17 265	95.57 245	86.47 318	98.51 232	97.60 137	85.99 335	90.55 260	97.19 219	94.80 11	98.31 217	85.06 321	91.86 283	97.74 260

XVG-ACMP-BASELINE		85.86 369	84.95 365	88.57 413	89.90 423	77.12 456	94.30 434	95.60 372	87.40 302	82.12 366	92.99 357	53.42 467	97.66 301	85.02 322	83.83 349	90.92 412

dmvs_re		88.69 322	88.06 317	90.59 365	93.83 352	78.68 442	95.75 414	96.18 292	87.99 279	84.48 332	96.32 280	67.52 391	96.94 338	84.98 323	85.49 337	96.14 318

新几何1				97.40 60	98.92 90	92.51 118		97.77 95	85.52 344	96.69 113	99.06 75	88.08 95	99.89 72	84.88 324	99.62 51	99.79 44

1112_ss		92.71 215	91.55 231	96.20 138	95.56 247	91.12 152	98.48 237	94.69 425	88.29 269	86.89 312	98.50 133	87.02 119	98.66 200	84.75 325	89.77 315	98.81 173

miper_ehance_all_eth		88.94 311	88.12 316	91.40 345	95.32 261	86.93 309	97.85 314	95.55 376	84.19 370	81.97 373	91.50 386	84.16 180	95.91 401	84.69 326	77.89 387	91.36 396

Test_1112_low_res		92.27 230	90.97 246	96.18 140	95.53 249	91.10 154	98.47 240	94.66 426	88.28 270	86.83 313	93.50 344	87.00 120	98.65 201	84.69 326	89.74 316	98.80 175

UWE-MVS-28		90.99 264	91.93 222	88.15 416	95.12 275	77.87 452	97.18 356	97.79 89	88.72 249	88.69 293	96.52 270	86.54 134	90.75 484	84.64 328	92.16 281	95.83 325

TR-MVS		90.77 268	89.44 279	94.76 230	96.31 209	88.02 270	97.92 309	95.96 319	85.52 344	88.22 298	97.23 215	66.80 400	98.09 245	84.58 329	92.38 271	98.17 244

tt0805		86.50 359	84.79 369	91.63 343	91.97 392	81.49 412	96.49 383	97.38 182	82.24 409	82.44 358	95.82 297	51.22 473	98.25 222	84.55 330	80.96 371	95.13 330

OpenMVS	85.28 14	90.75 269	88.84 298	96.48 117	93.58 359	93.51 86	98.80 176	97.41 178	82.59 401	78.62 417	97.49 193	68.00 387	99.82 97	84.52 331	98.55 125	96.11 319

UniMVSNet_ETH3D		85.65 376	83.79 386	91.21 349	90.41 419	80.75 427	95.36 419	95.78 348	78.76 439	81.83 380	94.33 321	49.86 479	96.66 348	84.30 332	83.52 355	96.22 317

NR-MVSNet		87.74 339	86.00 349	92.96 302	91.46 405	90.68 168	96.65 378	97.42 177	88.02 278	73.42 453	93.68 337	77.31 293	95.83 404	84.26 333	71.82 442	92.36 350

D2MVS		87.96 332	87.39 327	89.70 392	91.84 398	83.40 387	98.31 267	98.49 24	88.04 277	78.23 427	90.26 423	73.57 335	96.79 345	84.21 334	83.53 354	88.90 456

testdata2													99.88 74	84.16 335

Baseline_NR-MVSNet		85.83 370	84.82 368	88.87 412	88.73 442	83.34 388	98.63 205	91.66 475	80.41 432	82.44 358	91.35 390	74.63 321	95.42 425	84.13 336	71.39 444	87.84 462

thres100view900		93.34 191	92.15 215	96.90 90	97.62 133	94.84 44	99.06 148	99.36 2	87.96 280	90.47 263	96.78 260	83.29 194	98.75 193	84.11 337	90.69 306	97.12 285

tfpn200view9		93.43 185	92.27 207	96.90 90	97.68 130	94.84 44	99.18 121	99.36 2	88.45 258	90.79 253	96.90 249	83.31 192	98.75 193	84.11 337	90.69 306	97.12 285

thres400		93.39 187	92.27 207	96.73 100	97.68 130	94.84 44	99.18 121	99.36 2	88.45 258	90.79 253	96.90 249	83.31 192	98.75 193	84.11 337	90.69 306	96.61 304

c3_l		88.19 331	87.23 331	91.06 352	94.97 295	86.17 335	97.72 325	95.38 394	83.43 384	81.68 381	91.37 389	82.81 207	95.72 411	84.04 340	73.70 421	91.29 401

usedtu_blend_shiyan5		82.04 414	78.78 428	91.80 332	82.91 484	88.24 260	94.33 432	92.37 464	66.55 495	78.60 419	86.54 466	66.93 398	95.77 406	83.97 341	56.84 492	91.38 392

blend_shiyan4		86.02 365	84.08 381	91.83 329	83.24 482	88.24 260	98.42 246	95.51 379	75.55 463	79.43 407	86.84 463	84.51 175	95.77 406	83.97 341	69.26 449	91.48 385

UA-Net		93.30 192	92.62 197	95.34 193	96.27 211	88.53 257	95.88 408	96.97 230	90.90 152	95.37 147	97.07 234	82.38 223	99.10 174	83.91 343	94.86 217	98.38 224

IterMVS-LS		88.34 327	87.44 326	91.04 353	94.10 337	85.85 348	98.10 291	95.48 387	85.12 349	82.03 371	91.21 394	81.35 240	95.63 418	83.86 344	75.73 401	91.63 376
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.87 295	89.38 282	91.36 348	94.32 329	85.87 347	97.61 335	96.59 254	85.10 350	85.51 323	97.10 226	81.30 241	96.56 353	83.85 345	83.03 358	91.64 375

Elysia		90.62 275	88.95 294	95.64 174	93.08 372	91.94 128	97.65 332	96.39 271	84.72 361	90.59 258	95.95 292	62.22 429	98.23 224	83.69 346	96.23 185	96.74 298

StellarMVS		90.62 275	88.95 294	95.64 174	93.08 372	91.94 128	97.65 332	96.39 271	84.72 361	90.59 258	95.95 292	62.22 429	98.23 224	83.69 346	96.23 185	96.74 298

tpm		89.67 299	88.95 294	91.82 331	92.54 381	81.43 414	92.95 452	95.92 327	87.81 288	90.50 262	89.44 438	84.99 166	95.65 416	83.67 348	82.71 361	98.38 224

dtuonly		89.80 296	89.16 287	91.70 341	90.49 417	81.48 413	96.58 379	93.12 455	87.21 305	88.72 292	96.87 253	72.09 352	97.59 308	83.52 349	93.84 236	96.03 321

eth_miper_zixun_eth		87.76 335	87.00 336	90.06 380	94.67 312	82.65 402	97.02 363	95.37 395	84.19 370	81.86 379	91.58 383	81.47 237	95.90 402	83.24 350	73.61 422	91.61 380

Fast-Effi-MVS+		91.72 244	90.79 254	94.49 246	95.89 231	87.40 297	99.54 73	95.70 359	85.01 355	89.28 288	95.68 299	77.75 290	97.57 313	83.22 351	95.06 212	98.51 214

test_post1							90.74 480				41.37 539	85.38 159	96.36 366	83.16 352

SCA		90.64 274	89.25 285	94.83 228	94.95 297	88.83 245	96.26 393	97.21 202	90.06 194	90.03 273	90.62 412	66.61 403	96.81 343	83.16 352	94.36 226	98.84 168

TranMVSNet+NR-MVSNet		87.75 336	86.31 344	92.07 325	90.81 413	88.56 254	98.33 264	97.18 207	87.76 290	81.87 377	93.90 332	72.45 348	95.43 424	83.13 354	71.30 445	92.23 356

CMPMVS	58.40 21	80.48 423	80.11 422	81.59 469	85.10 474	59.56 503	94.14 438	95.95 321	68.54 488	60.71 497	93.31 346	55.35 458	97.87 276	83.06 355	84.85 341	87.33 469
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
thres600view7		93.18 197	92.00 218	96.75 98	97.62 133	94.92 39	99.07 145	99.36 2	87.96 280	90.47 263	96.78 260	83.29 194	98.71 198	82.93 356	90.47 310	96.61 304

usedtu_dtu_shiyan1		89.12 306	87.56 323	93.78 282	89.74 427	93.60 80	98.70 192	96.60 251	87.85 284	83.43 340	91.56 384	76.34 306	95.92 398	82.75 357	81.08 368	91.82 369

FE-MVSNET3		89.12 306	87.56 323	93.78 282	89.74 427	93.60 80	98.70 192	96.60 251	87.85 284	83.43 340	91.56 384	76.34 306	95.92 398	82.75 357	81.08 368	91.82 369

pmmvs4		87.58 342	86.17 347	91.80 332	89.58 431	88.92 243	97.25 350	95.28 398	82.54 403	80.49 391	93.17 352	75.62 317	96.05 390	82.75 357	78.90 382	90.42 427

CVMVSNet		90.30 284	90.91 248	88.46 415	94.32 329	73.58 473	97.61 335	97.59 141	90.16 189	88.43 297	97.10 226	76.83 299	92.86 463	82.64 360	93.54 245	98.93 159

Anonymous20231211		84.72 385	82.65 398	90.91 356	97.71 129	84.55 372	97.28 348	96.67 245	66.88 493	79.18 412	90.87 402	58.47 444	96.60 350	82.60 361	74.20 417	91.59 382

GA-MVS		90.10 291	88.69 302	94.33 254	92.44 383	87.97 272	99.08 143	96.26 283	89.65 207	86.92 311	93.11 353	68.09 385	96.96 336	82.54 362	90.15 311	98.05 251

blended_shiyan8		83.22 406	80.40 419	91.71 340	82.77 490	88.01 271	98.25 275	95.49 384	75.64 460	78.68 415	86.55 464	66.76 401	95.75 408	82.50 363	56.93 491	91.36 396

wanda-best-256-512		83.28 404	80.44 416	91.78 337	82.91 484	88.24 260	98.43 243	95.51 379	75.76 457	78.60 419	86.54 466	66.95 397	95.71 412	82.44 364	56.84 492	91.38 392

FE-blended-shiyan7		83.27 405	80.44 416	91.78 337	82.91 484	88.24 260	98.43 243	95.51 379	75.76 457	78.60 419	86.54 466	66.93 398	95.71 412	82.44 364	56.84 492	91.38 392

blended_shiyan6		83.17 407	80.34 420	91.67 342	82.80 489	87.93 273	98.29 271	95.51 379	75.63 461	78.46 423	86.48 469	66.74 402	95.70 414	82.33 366	56.84 492	91.37 395

QAPM		91.41 250	89.49 278	97.17 74	95.66 242	93.42 88	98.60 216	97.51 159	80.92 427	81.39 384	97.41 198	72.89 346	99.87 78	82.33 366	98.68 115	98.21 240

Patchmatch-RL test		81.90 417	80.13 421	87.23 427	80.71 494	70.12 488	84.07 499	88.19 500	83.16 389	70.57 467	82.18 486	87.18 114	92.59 468	82.28 368	62.78 474	98.98 151

v2v482		87.27 345	85.76 352	91.78 337	89.59 430	87.58 290	98.56 225	95.54 377	84.53 365	82.51 357	91.78 377	73.11 341	96.47 360	82.07 369	74.14 419	91.30 400

Fast-Effi-MVS+-dtu		88.84 314	88.59 306	89.58 395	93.44 365	78.18 446	98.65 201	94.62 427	88.46 257	84.12 335	95.37 308	68.91 377	96.52 356	82.06 370	91.70 288	94.06 335

pmmvs5		85.87 368	84.40 379	90.30 376	88.53 445	84.23 375	98.60 216	93.71 447	81.53 417	80.29 395	92.02 370	64.51 418	95.52 420	82.04 371	78.34 385	91.15 406

V42		87.00 347	85.68 354	90.98 355	89.91 422	86.08 338	98.32 266	95.61 371	83.67 381	82.72 351	90.67 408	74.00 333	96.53 355	81.94 372	74.28 416	90.32 429

gbinet_0.2-2-1-0.02		83.16 408	80.42 418	91.39 347	83.70 480	87.60 289	98.62 209	95.77 350	75.83 456	79.33 409	87.92 447	64.07 420	95.34 427	81.87 373	56.67 496	91.25 403

EPMVS		92.59 221	91.59 230	95.59 180	97.22 160	90.03 194	91.78 465	98.04 56	90.42 175	91.66 236	90.65 410	86.49 137	97.46 316	81.78 374	96.31 181	99.28 120

DIV-MVS_self_test		87.82 333	86.81 338	90.87 359	94.87 303	85.39 357	97.81 316	95.22 409	82.92 397	80.76 388	91.31 392	81.99 228	95.81 405	81.36 375	75.04 406	91.42 390

cl____		87.82 333	86.79 339	90.89 358	94.88 302	85.43 355	97.81 316	95.24 404	82.91 398	80.71 389	91.22 393	81.97 230	95.84 403	81.34 376	75.06 405	91.40 391

RPSCF		85.33 378	85.55 356	84.67 452	94.63 314	62.28 500	93.73 442	93.76 445	74.38 469	85.23 326	97.06 235	64.09 419	98.31 217	80.98 377	86.08 333	93.41 340

OurMVSNet-221017-0		84.13 397	83.59 387	85.77 444	87.81 455	70.24 486	94.89 425	93.65 449	86.08 333	76.53 432	93.27 348	61.41 434	96.14 386	80.95 378	77.69 393	90.93 411

v148		86.38 361	85.06 362	90.37 375	89.47 435	84.10 378	98.52 229	95.48 387	83.80 377	80.93 387	90.22 427	74.60 323	96.31 374	80.92 379	71.55 443	90.69 422

PatchMatch-RL		91.47 248	90.54 259	94.26 259	98.20 110	86.36 323	96.94 364	97.14 211	87.75 291	88.98 289	95.75 298	71.80 357	99.40 152	80.92 379	97.39 158	97.02 291

FE-MVS		91.38 251	90.16 265	95.05 218	96.46 200	87.53 292	89.69 483	97.84 76	82.97 393	92.18 224	92.00 373	84.07 182	98.93 182	80.71 381	95.52 200	98.68 197

miper_lstm_enhance		86.90 348	86.20 346	89.00 409	94.53 319	81.19 420	96.74 374	95.24 404	82.33 408	80.15 397	90.51 419	81.99 228	94.68 443	80.71 381	73.58 424	91.12 407

PCF-MVS	89.78 5	91.26 254	89.63 274	96.16 145	95.44 253	91.58 143	95.29 421	96.10 299	85.07 352	82.75 350	97.45 196	78.28 285	99.78 109	80.60 383	95.65 198	97.12 285
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
BH-RMVSNet		91.25 256	89.99 266	95.03 219	96.75 190	88.55 255	98.65 201	94.95 415	87.74 292	87.74 301	97.80 165	68.27 383	98.14 233	80.53 384	97.49 154	98.41 220

GeoE		90.60 277	89.56 275	93.72 287	95.10 284	85.43 355	99.41 94	94.94 416	83.96 375	87.21 308	96.83 259	74.37 327	97.05 334	80.50 385	93.73 243	98.67 198

CP-MVSNet		86.54 357	85.45 358	89.79 389	91.02 412	82.78 398	97.38 344	97.56 147	85.37 346	79.53 406	93.03 355	71.86 356	95.25 430	79.92 386	73.43 429	91.34 398

PatchmatchNet		92.05 237	91.04 243	95.06 216	96.17 218	89.04 230	91.26 474	97.26 194	89.56 214	90.64 257	90.56 416	88.35 88	97.11 330	79.53 387	96.07 191	99.03 147
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v1144		86.83 350	85.31 360	91.40 345	89.75 426	87.21 306	98.31 267	95.45 389	83.22 387	82.70 352	90.78 403	73.36 336	96.36 366	79.49 388	74.69 410	90.63 424

IterMVS		85.81 371	84.67 372	89.22 403	93.51 361	83.67 384	96.32 390	94.80 421	85.09 351	78.69 414	90.17 430	66.57 405	93.17 462	79.48 389	77.42 394	90.81 414
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		85.73 374	84.64 373	89.00 409	93.46 364	82.90 394	96.27 391	94.70 424	85.02 354	78.62 417	90.35 421	66.61 403	93.33 458	79.38 390	77.36 395	90.76 418

GBi-Net		86.67 354	84.96 363	91.80 332	95.11 281	88.81 246	96.77 370	95.25 401	82.94 394	82.12 366	90.25 424	62.89 426	94.97 434	79.04 391	80.24 374	91.62 377

test1		86.67 354	84.96 363	91.80 332	95.11 281	88.81 246	96.77 370	95.25 401	82.94 394	82.12 366	90.25 424	62.89 426	94.97 434	79.04 391	80.24 374	91.62 377

FMVSNet3		88.81 318	87.08 333	93.99 275	96.52 197	94.59 56	98.08 297	96.20 287	85.85 338	82.12 366	91.60 382	74.05 332	95.40 426	79.04 391	80.24 374	91.99 367

LF4IMVS		81.94 416	81.17 410	84.25 454	87.23 462	68.87 492	93.35 448	91.93 472	83.35 386	75.40 442	93.00 356	49.25 483	96.65 349	78.88 394	78.11 386	87.22 471

v8		86.11 364	84.45 376	91.10 351	89.99 421	86.85 310	97.24 351	95.36 396	81.99 412	79.89 401	89.86 433	74.53 325	96.39 364	78.83 395	72.32 437	90.05 436

pm-mvs1		84.68 386	82.78 395	90.40 372	89.58 431	85.18 361	97.31 346	94.73 423	81.93 414	76.05 436	92.01 371	65.48 413	96.11 387	78.75 396	69.14 450	89.91 439

test_f		71.94 460	70.82 462	75.30 479	72.77 512	53.28 510	91.62 467	89.66 494	75.44 464	64.47 492	78.31 503	20.48 510	89.56 492	78.63 397	66.02 466	83.05 498

v144192		86.40 360	84.89 366	90.91 356	89.48 434	85.59 352	98.21 279	95.43 392	82.45 406	82.62 355	90.58 415	72.79 347	96.36 366	78.45 398	74.04 420	90.79 416

PS-CasMVS		85.81 371	84.58 374	89.49 399	90.77 414	82.11 406	97.20 354	97.36 186	84.83 358	79.12 413	92.84 359	67.42 393	95.16 432	78.39 399	73.25 430	91.21 405

tmp_tt		53.66 481	52.86 482	56.05 504	32.75 560	41.97 528	73.42 519	76.12 519	21.91 530	39.68 521	96.39 278	42.59 490	65.10 529	78.00 400	14.92 547	61.08 522

JIA-IIPM		85.97 367	84.85 367	89.33 402	93.23 369	73.68 472	85.05 494	97.13 213	69.62 485	91.56 239	68.03 518	88.03 96	96.96 336	77.89 401	93.12 252	97.34 277

MDTV_nov1_ep13			90.47 262		96.14 221	88.55 255	91.34 473	97.51 159	89.58 212	92.24 222	90.50 420	86.99 121	97.61 306	77.64 402	92.34 273

v1192		86.32 362	84.71 371	91.17 350	89.53 433	86.40 320	98.13 286	95.44 391	82.52 404	82.42 360	90.62 412	71.58 360	96.33 373	77.23 403	74.88 407	90.79 416

FMVSNet2		86.90 348	84.79 369	93.24 295	95.11 281	92.54 117	97.67 330	95.86 341	82.94 394	80.55 390	91.17 395	62.89 426	95.29 429	77.23 403	79.71 380	91.90 368

MVP-Stereo		86.61 356	85.83 351	88.93 411	88.70 443	83.85 382	96.07 402	94.41 435	82.15 411	75.64 441	91.96 374	67.65 390	96.45 362	77.20 405	98.72 113	86.51 476
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		88.89 312	87.27 330	93.76 284	95.79 236	85.32 359	90.76 479	97.09 219	76.14 454	85.72 321	88.59 444	82.92 203	98.04 261	76.96 406	91.43 297	97.90 257

v10		85.73 374	84.01 383	90.87 359	90.03 420	86.73 312	97.20 354	95.22 409	81.25 420	79.85 402	89.75 434	73.30 339	96.28 378	76.87 407	72.64 433	89.61 444

v1921920		86.02 365	84.44 377	90.77 362	89.32 436	85.20 360	98.10 291	95.35 397	82.19 410	82.25 364	90.71 405	70.73 364	96.30 377	76.85 408	74.49 412	90.80 415

MS-PatchMatch		86.75 352	85.92 350	89.22 403	91.97 392	82.47 404	96.91 365	96.14 296	83.74 378	77.73 429	93.53 343	58.19 445	97.37 323	76.75 409	98.35 131	87.84 462

K. test v3		81.04 421	79.77 424	84.83 450	87.41 459	70.23 487	95.60 417	93.93 443	83.70 380	67.51 483	89.35 440	55.76 453	93.58 457	76.67 410	68.03 457	90.67 423

PM-MVS		74.88 456	72.85 458	80.98 470	78.98 499	64.75 497	90.81 478	85.77 505	80.95 426	68.23 480	82.81 482	29.08 505	92.84 464	76.54 411	62.46 476	85.36 486

SSC-MVS3.2		85.22 379	83.90 385	89.17 405	91.87 397	79.84 431	97.66 331	96.63 248	86.81 317	81.99 372	91.35 390	55.80 452	96.00 391	76.52 412	76.53 398	91.67 373

WR-MVS_H		86.53 358	85.49 357	89.66 394	91.04 411	83.31 389	97.53 338	98.20 38	84.95 356	79.64 403	90.90 401	78.01 289	95.33 428	76.29 413	72.81 431	90.35 428

ACMH+	83.78 15	84.21 394	82.56 401	89.15 406	93.73 355	79.16 437	96.43 385	94.28 437	81.09 423	74.00 449	94.03 325	54.58 462	97.67 300	76.10 414	78.81 383	90.63 424

PEN-MVS		85.21 380	83.93 384	89.07 408	89.89 424	81.31 418	97.09 359	97.24 198	84.45 368	78.66 416	92.68 362	68.44 382	94.87 437	75.98 415	70.92 446	91.04 409

USDC		84.74 384	82.93 391	90.16 378	91.73 401	83.54 386	95.00 424	93.30 454	88.77 248	73.19 455	93.30 347	53.62 466	97.65 303	75.88 416	81.54 367	89.30 447

EU-MVSNet		84.19 395	84.42 378	83.52 460	88.64 444	67.37 494	96.04 403	95.76 352	85.29 347	78.44 424	93.18 350	70.67 365	91.48 481	75.79 417	75.98 399	91.70 372

v1240		85.77 373	84.11 380	90.73 363	89.26 437	85.15 363	97.88 312	95.23 408	81.89 415	82.16 365	90.55 417	69.60 373	96.31 374	75.59 418	74.87 408	90.72 421

ITE_SJBPF				87.93 418	92.26 386	76.44 460		93.47 453	87.67 296	79.95 400	95.49 305	56.50 451	97.38 321	75.24 419	82.33 364	89.98 438

dp		90.16 290	88.83 299	94.14 266	96.38 207	86.42 319	91.57 469	97.06 221	84.76 360	88.81 290	90.19 429	84.29 179	97.43 319	75.05 420	91.35 301	98.56 211

LS3D		90.19 287	88.72 301	94.59 244	98.97 82	86.33 324	96.90 366	96.60 251	74.96 466	84.06 336	98.74 112	75.78 314	99.83 94	74.93 421	97.57 150	97.62 270

TDRefinement		78.01 441	75.31 445	86.10 439	70.06 516	73.84 471	93.59 445	91.58 478	74.51 468	73.08 458	91.04 396	49.63 481	97.12 329	74.88 422	59.47 484	87.33 469

tpmvs		89.16 305	87.76 319	93.35 293	97.19 164	84.75 370	90.58 481	97.36 186	81.99 412	84.56 329	89.31 441	83.98 183	98.17 231	74.85 423	90.00 314	97.12 285

pmmvs6		79.90 426	77.31 435	87.67 421	84.17 477	78.13 448	95.86 410	93.68 448	67.94 490	72.67 461	89.62 436	50.98 475	95.75 408	74.80 424	66.04 465	89.14 450

SixPastTwentyTwo		82.63 411	81.58 405	85.79 443	88.12 450	71.01 484	95.17 422	92.54 462	84.33 369	72.93 460	92.08 368	60.41 439	95.61 419	74.47 425	74.15 418	90.75 419

ACMH	83.09 17	84.60 387	82.61 399	90.57 366	93.18 370	82.94 392	96.27 391	94.92 417	81.01 425	72.61 462	93.61 340	56.54 450	97.79 284	74.31 426	81.07 370	90.99 410
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis3_rt		61.29 469	58.75 473	68.92 489	67.41 520	52.84 512	91.18 476	59.23 529	66.96 492	41.96 519	58.44 525	11.37 526	94.72 442	74.25 427	57.97 488	59.20 523

ADS-MVSNet2		87.62 341	86.88 337	89.86 386	96.21 214	79.14 438	87.15 487	92.99 456	83.01 391	89.91 276	87.27 456	78.87 272	92.80 466	74.20 428	92.27 275	97.64 266

ADS-MVSNet		88.99 309	87.30 329	94.07 269	96.21 214	87.56 291	87.15 487	96.78 240	83.01 391	89.91 276	87.27 456	78.87 272	97.01 335	74.20 428	92.27 275	97.64 266

sc_t1		78.53 437	74.87 449	89.48 400	87.92 453	77.36 455	94.80 426	90.61 488	57.65 501	76.28 433	89.59 437	38.25 496	96.18 382	74.04 430	64.72 470	94.91 333

lessismore_v0				85.08 448	85.59 473	69.28 489		90.56 489		67.68 482	90.21 428	54.21 464	95.46 423	73.88 431	62.64 475	90.50 426

MIMVSNet		84.48 390	81.83 403	92.42 317	91.73 401	87.36 298	85.52 490	94.42 434	81.40 418	81.91 374	87.58 450	51.92 470	92.81 465	73.84 432	88.15 319	97.08 289

v7n		84.42 392	82.75 396	89.43 401	88.15 449	81.86 409	96.75 373	95.67 365	80.53 428	78.38 425	89.43 439	69.89 368	96.35 371	73.83 433	72.13 439	90.07 434

ambc				79.60 474	72.76 513	56.61 505	76.20 515	92.01 471		68.25 479	80.23 496	23.34 508	94.73 441	73.78 434	60.81 481	87.48 466

pmmvs-eth3d		78.71 435	76.16 441	86.38 435	80.25 497	81.19 420	94.17 437	92.13 469	77.97 443	66.90 486	82.31 485	55.76 453	92.56 469	73.63 435	62.31 477	85.38 485

ArgMatch-Sym		75.37 452	74.07 452	79.27 475	86.10 471	64.15 498	92.14 461	85.97 504	78.66 440	71.15 464	91.00 397	29.88 504	86.45 505	73.44 436	58.34 487	87.22 471

FMVSNet1		83.94 399	81.32 409	91.80 332	91.94 395	88.81 246	96.77 370	95.25 401	77.98 442	78.25 426	90.25 424	50.37 478	94.97 434	73.27 437	77.81 392	91.62 377

MSDG		88.29 329	86.37 343	94.04 273	96.90 182	86.15 336	96.52 381	94.36 436	77.89 446	79.22 411	96.95 242	69.72 370	99.59 129	73.20 438	92.58 265	96.37 316

test0.0.03 1		88.96 310	88.61 304	90.03 384	91.09 410	84.43 373	98.97 159	97.02 226	90.21 183	80.29 395	96.31 281	84.89 168	91.93 478	72.98 439	85.70 336	93.73 336

ArgMatch-SfM		75.24 453	73.75 453	79.70 473	85.92 472	63.67 499	91.51 470	85.16 507	79.74 433	70.70 466	90.27 422	30.46 503	87.73 501	72.95 440	57.08 490	87.70 465

UnsupCasMVSNet_eth		78.90 433	76.67 439	85.58 445	82.81 488	74.94 467	91.98 463	96.31 278	84.64 364	65.84 491	87.71 449	51.33 472	92.23 473	72.89 441	56.50 498	89.56 445

WB-MVSnew		88.69 322	88.34 311	89.77 390	94.30 335	85.99 343	98.14 285	97.31 193	87.15 307	87.85 300	96.07 288	69.91 367	95.52 420	72.83 442	91.47 296	87.80 464

DTE-MVSNet		84.14 396	82.80 393	88.14 417	88.95 440	79.87 430	96.81 369	96.24 284	83.50 383	77.60 430	92.52 364	67.89 389	94.24 448	72.64 443	69.05 451	90.32 429

SD_0403		86.82 351	87.08 333	86.04 440	93.55 360	69.09 490	94.11 439	95.02 413	87.84 286	80.48 392	95.86 296	73.05 342	91.04 483	72.53 444	91.26 302	97.99 255

ttmdpeth		79.80 428	77.91 432	85.47 446	83.34 481	75.75 462	95.32 420	91.45 480	76.84 450	74.81 445	91.71 380	53.98 465	94.13 449	72.42 445	61.29 478	86.51 476

EPNet_dtu		92.28 229	92.15 215	92.70 312	97.29 156	84.84 368	98.64 203	97.82 81	92.91 102	93.02 200	97.02 238	85.48 156	95.70 414	72.25 446	94.89 215	97.55 272
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FE-MVSNET2		78.42 439	75.71 443	86.55 434	78.55 501	81.99 408	95.40 418	93.86 444	81.11 421	66.27 488	81.89 487	49.29 482	91.80 479	72.03 447	63.02 472	85.86 480

dtuonlycased		79.10 431	78.53 429	80.81 471	86.63 465	72.95 476	96.33 389	90.81 484	81.09 423	68.85 475	87.27 456	56.94 449	87.84 500	71.57 448	67.30 462	81.65 499

AllTest		84.97 383	83.12 390	90.52 369	96.82 185	78.84 440	95.89 406	92.17 467	77.96 444	75.94 437	95.50 303	55.48 455	99.18 166	71.15 449	87.14 322	93.55 338

TestCases				90.52 369	96.82 185	78.84 440		92.17 467	77.96 444	75.94 437	95.50 303	55.48 455	99.18 166	71.15 449	87.14 322	93.55 338

DP-MVS		88.75 320	86.56 341	95.34 193	98.92 90	87.45 295	97.64 334	93.52 452	70.55 480	81.49 382	97.25 213	74.43 326	99.88 74	71.14 451	94.09 231	98.67 198

CR-MVSNet		88.83 316	87.38 328	93.16 297	93.47 362	86.24 326	84.97 495	94.20 439	88.92 241	90.76 255	86.88 461	84.43 177	94.82 439	70.64 452	92.17 279	98.41 220

KD-MVS_2432*1600		82.98 409	80.52 414	90.38 373	94.32 329	88.98 237	92.87 454	95.87 339	80.46 430	73.79 450	87.49 453	82.76 210	93.29 460	70.56 453	46.53 512	88.87 457

miper_refine_blended		82.98 409	80.52 414	90.38 373	94.32 329	88.98 237	92.87 454	95.87 339	80.46 430	73.79 450	87.49 453	82.76 210	93.29 460	70.56 453	46.53 512	88.87 457

test_method		70.10 462	68.66 466	74.41 482	86.30 469	55.84 507	94.47 428	89.82 492	35.18 523	66.15 489	84.75 478	30.54 502	77.96 518	70.40 455	60.33 482	89.44 446

tt0320-xc		75.92 449	72.23 461	87.01 429	88.40 446	78.15 447	93.57 446	89.15 497	55.46 502	69.66 472	85.79 474	38.20 497	93.85 451	69.72 456	60.08 483	89.03 451

LTVRE_ROB	81.71 19	84.59 388	82.72 397	90.18 377	92.89 376	83.18 390	93.15 449	94.74 422	78.99 436	75.14 444	92.69 361	65.64 410	97.63 304	69.46 457	81.82 366	89.74 441
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
myMVS_eth3d		88.68 324	89.07 291	87.50 424	95.14 273	79.74 432	97.68 328	96.66 246	86.52 325	82.63 353	96.84 257	85.22 165	89.89 489	69.43 458	91.54 292	92.87 342

mvs5depth		78.17 440	75.56 444	85.97 441	80.43 496	76.44 460	85.46 491	89.24 496	76.39 452	78.17 428	88.26 445	51.73 471	95.73 410	69.31 459	61.09 479	85.73 482

FMVSNet5		82.29 412	80.54 413	87.52 423	93.79 354	84.01 379	93.73 442	92.47 463	76.92 449	74.27 447	86.15 471	63.69 424	89.24 495	69.07 460	74.79 409	89.29 448

tt0320		76.58 446	73.16 457	86.86 432	88.03 452	77.60 453	93.55 447	90.63 486	55.37 503	70.93 465	84.98 475	41.57 491	94.01 450	69.02 461	64.32 471	88.97 453

our_test_3		84.47 391	82.80 393	89.50 397	89.01 438	83.90 381	97.03 361	94.56 428	81.33 419	75.36 443	90.52 418	71.69 358	94.54 445	68.81 462	76.84 396	90.07 434

UnsupCasMVSNet_bld		73.85 458	70.14 463	84.99 449	79.44 498	75.73 463	88.53 484	95.24 404	70.12 483	61.94 495	74.81 510	41.41 493	93.62 456	68.65 463	51.13 507	85.62 483

Patchmtry		83.61 403	81.64 404	89.50 397	93.36 366	82.84 397	84.10 498	94.20 439	69.47 486	79.57 405	86.88 461	84.43 177	94.78 440	68.48 464	74.30 415	90.88 413

KD-MVS_self_test		77.47 444	75.88 442	82.24 463	81.59 491	68.93 491	92.83 456	94.02 442	77.03 448	73.14 456	83.39 480	55.44 457	90.42 486	67.95 465	57.53 489	87.38 467

WAC-MVS						79.74 432								67.75 466

TransMVSNet (Re)		81.97 415	79.61 425	89.08 407	89.70 429	84.01 379	97.26 349	91.85 473	78.84 437	73.07 459	91.62 381	67.17 395	95.21 431	67.50 467	59.46 485	88.02 461

COLMAP_ROB	82.69 18	84.54 389	82.82 392	89.70 392	96.72 191	78.85 439	95.89 406	92.83 459	71.55 476	77.54 431	95.89 295	59.40 442	99.14 172	67.26 468	88.26 318	91.11 408
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EG-PatchMatch MVS		79.92 425	77.59 433	86.90 431	87.06 463	77.90 451	96.20 398	94.06 441	74.61 467	66.53 487	88.76 443	40.40 495	96.20 381	67.02 469	83.66 353	86.61 474

DSMNet-mixed		81.60 418	81.43 407	82.10 466	84.36 476	60.79 501	93.63 444	86.74 503	79.00 435	79.32 410	87.15 459	63.87 422	89.78 491	66.89 470	91.92 282	95.73 326

testgi		82.29 412	81.00 411	86.17 438	87.24 461	74.84 468	97.39 342	91.62 477	88.63 251	75.85 440	95.42 306	46.07 486	91.55 480	66.87 471	79.94 378	92.12 362

MDA-MVSNet_test_wron		79.65 429	77.05 436	87.45 425	87.79 457	80.13 428	96.25 394	94.44 430	73.87 470	51.80 505	87.47 455	68.04 386	92.12 476	66.02 472	67.79 459	90.09 432

YYNet1		79.64 430	77.04 437	87.43 426	87.80 456	79.98 429	96.23 395	94.44 430	73.83 471	51.83 504	87.53 451	67.96 388	92.07 477	66.00 473	67.75 460	90.23 431

DeepMVS_CX				76.08 477	90.74 415	51.65 514		90.84 483	86.47 328	57.89 501	87.98 446	35.88 500	92.60 467	65.77 474	65.06 468	83.97 493

MASt3R-SfM		60.79 471	59.91 472	63.44 499	62.41 527	35.46 531	75.76 518	71.46 523	54.67 504	58.30 500	86.10 472	14.86 518	74.25 522	65.44 475	50.18 509	80.59 501

Anonymous20240521		78.63 436	76.90 438	83.82 456	82.82 487	72.86 477	95.72 415	93.57 451	73.55 473	72.17 463	84.79 477	49.69 480	92.51 470	65.29 476	74.50 411	86.09 479

TinyColmap		80.42 424	77.94 431	87.85 419	92.09 390	78.58 443	93.74 441	89.94 491	74.99 465	69.77 471	91.78 377	46.09 485	97.58 310	65.17 477	77.89 387	87.38 467

kuosan		84.40 393	83.34 388	87.60 422	95.87 232	79.21 436	92.39 459	96.87 234	76.12 455	73.79 450	93.98 329	81.51 234	90.63 485	64.13 478	75.42 402	92.95 341

MVS-HIRNet		79.01 432	75.13 447	90.66 364	93.82 353	81.69 411	85.16 492	93.75 446	54.54 505	74.17 448	59.15 524	57.46 447	96.58 352	63.74 479	94.38 225	93.72 337

ppachtmachnet_test		83.63 402	81.57 406	89.80 388	89.01 438	85.09 364	97.13 358	94.50 429	78.84 437	76.14 435	91.00 397	69.78 369	94.61 444	63.40 480	74.36 414	89.71 443

CL-MVSNet_self_test		79.89 427	78.34 430	84.54 453	81.56 492	75.01 466	96.88 367	95.62 370	81.10 422	75.86 439	85.81 473	68.49 381	90.26 487	63.21 481	56.51 497	88.35 459

Patchmatch-test		86.25 363	84.06 382	92.82 305	94.42 321	82.88 396	82.88 505	94.23 438	71.58 475	79.39 408	90.62 412	89.00 78	96.42 363	63.03 482	91.37 300	99.16 130

pmmvs3		72.86 459	69.76 465	82.17 464	73.86 509	74.19 470	94.20 436	89.01 498	64.23 498	67.72 481	80.91 495	41.48 492	88.65 498	62.40 483	54.02 501	83.68 495

new_pmnet		76.02 448	73.71 454	82.95 461	83.88 478	72.85 478	91.26 474	92.26 466	70.44 481	62.60 494	81.37 491	47.64 484	92.32 472	61.85 484	72.10 440	83.68 495

tfpnnormal		83.65 401	81.35 408	90.56 368	91.37 407	88.06 268	97.29 347	97.87 71	78.51 441	76.20 434	90.91 400	64.78 417	96.47 360	61.71 485	73.50 425	87.13 473

testing3		87.75 336	88.22 314	86.36 436	94.66 313	77.41 454	99.52 74	97.95 63	86.05 334	81.12 385	96.69 266	86.18 143	89.31 494	61.65 486	90.12 312	92.35 353

MDA-MVSNet-bldmvs		77.82 443	74.75 450	87.03 428	88.33 447	78.52 444	96.34 388	92.85 458	75.57 462	48.87 507	87.89 448	57.32 448	92.49 471	60.79 487	64.80 469	90.08 433

Anonymous20231206		80.76 422	79.42 426	84.79 451	84.78 475	72.98 475	96.53 380	92.97 457	79.56 434	74.33 446	88.83 442	61.27 435	92.15 474	60.59 488	75.92 400	89.24 449

new-patchmatchnet		74.80 457	72.40 459	81.99 467	78.36 502	72.20 480	94.44 430	92.36 465	77.06 447	63.47 493	79.98 497	51.04 474	88.85 496	60.53 489	54.35 500	84.92 490

LCM-MVSNet		60.07 473	56.37 476	71.18 486	54.81 536	48.67 517	82.17 508	89.48 495	37.95 520	49.13 506	69.12 516	13.75 520	81.76 508	59.28 490	51.63 506	83.10 497

MVStest1		76.56 447	73.43 455	85.96 442	86.30 469	80.88 426	94.26 435	91.74 474	61.98 499	58.53 499	89.96 431	69.30 376	91.47 482	59.26 491	49.56 510	85.52 484

TAPA-MVS	87.50 9	90.35 281	89.05 292	94.25 260	98.48 104	85.17 362	98.41 248	96.58 257	82.44 407	87.24 307	98.53 129	82.77 208	98.84 186	59.09 492	97.88 142	98.72 191
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test20.03		78.51 438	77.48 434	81.62 468	83.07 483	71.03 483	96.11 400	92.83 459	81.66 416	69.31 474	89.68 435	57.53 446	87.29 503	58.65 493	68.47 455	86.53 475

PatchT		85.44 377	83.19 389	92.22 319	93.13 371	83.00 391	83.80 501	96.37 275	70.62 478	90.55 260	79.63 498	84.81 170	94.87 437	58.18 494	91.59 289	98.79 176

usedtu_dtu_shiyan2		69.89 463	65.80 469	82.15 465	69.90 517	68.09 493	93.09 450	90.63 486	58.33 500	61.56 496	79.31 500	28.96 506	89.43 493	57.76 495	52.68 505	88.92 455

APD_test1		68.93 464	66.98 467	74.77 481	80.62 495	53.15 511	87.97 485	85.01 508	53.76 506	59.26 498	87.52 452	25.19 507	89.95 488	56.20 496	67.33 461	81.19 500

MIMVSNet1		75.92 449	73.30 456	83.81 457	81.29 493	75.57 464	92.26 460	92.05 470	73.09 474	67.48 484	86.18 470	40.87 494	87.64 502	55.78 497	70.68 447	88.21 460

FE-MVSNET		75.08 455	72.25 460	83.56 459	77.93 503	76.96 458	94.36 431	87.96 501	75.72 459	66.01 490	81.60 490	50.48 477	88.85 496	55.38 498	60.82 480	84.86 491

OpenMVS_ROB	73.86 20	77.99 442	75.06 448	86.77 433	83.81 479	77.94 450	96.38 387	91.53 479	67.54 491	68.38 478	87.13 460	43.94 487	96.08 388	55.03 499	81.83 365	86.29 478

RPMNet		85.07 382	81.88 402	94.64 238	93.47 362	86.24 326	84.97 495	97.21 202	64.85 497	90.76 255	78.80 502	80.95 245	99.27 162	53.76 500	92.17 279	98.41 220

N_pmnet		70.19 461	69.87 464	71.12 487	88.24 448	30.63 540	95.85 411	28.70 540	70.18 482	68.73 477	86.55 464	64.04 421	93.81 452	53.12 501	73.46 426	88.94 454

PatchmatchNet1														52.97 502	73.44 427	88.99 452
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
dmvs_testset		77.17 445	78.99 427	71.71 485	87.25 460	38.55 530	91.44 471	81.76 513	85.77 340	69.49 473	95.94 294	69.71 371	84.37 507	52.71 503	76.82 397	92.21 358

PDCNetPlus		48.73 485	46.34 488	55.88 505	64.17 525	41.40 529	76.11 517	34.96 536	50.17 510	35.24 524	71.04 513	15.41 516	67.33 527	52.41 504	17.59 542	58.93 524

dongtai		81.36 419	80.61 412	83.62 458	94.25 336	73.32 474	95.15 423	96.81 237	73.56 472	69.79 470	92.81 360	81.00 244	86.80 504	52.08 505	70.06 448	90.75 419

DenseAffine		61.07 470	57.33 474	72.29 483	78.74 500	56.29 506	83.24 502	69.15 524	53.26 507	47.82 509	79.48 499	13.61 521	80.66 513	51.15 506	39.51 517	79.92 502

PMMVS2		58.97 474	55.07 478	70.69 488	62.72 526	55.37 508	85.97 489	80.52 514	49.48 511	45.94 511	68.31 517	15.73 515	80.78 512	49.79 507	37.12 520	75.91 506

VLMVS_CLIP		40.95 491	42.04 492	37.71 513	32.13 561	14.08 561	54.07 532	58.90 530	13.80 535	44.01 513	74.81 510	9.85 531	48.39 534	49.70 508	41.06 516	50.67 529

DKM		55.59 479	51.49 485	67.89 491	72.36 514	48.29 518	80.45 512	52.05 532	47.86 512	42.54 517	77.08 506	9.06 536	77.32 520	48.87 509	33.13 522	78.05 503

VLMVS		38.17 494	38.75 496	36.45 516	35.35 556	13.53 563	50.05 535	33.90 537	9.30 543	47.14 510	77.14 505	12.39 525	32.34 538	47.77 510	35.68 521	63.48 520

RoMa-SfM		58.43 475	54.99 479	68.74 490	74.29 507	50.87 515	82.37 506	58.12 531	50.53 509	48.40 508	81.78 488	12.70 523	78.25 517	47.71 511	39.01 518	77.09 505

test_0402		78.81 434	76.33 440	86.26 437	91.18 409	78.44 445	95.88 408	91.34 481	68.55 487	70.51 469	89.91 432	52.65 469	94.99 433	47.14 512	79.78 379	85.34 487

Syy-MVS		84.10 398	84.53 375	82.83 462	95.14 273	65.71 495	97.68 328	96.66 246	86.52 325	82.63 353	96.84 257	68.15 384	89.89 489	45.62 513	91.54 292	92.87 342

LoFTR		61.59 467	56.89 475	75.68 478	76.61 505	50.06 516	82.20 507	79.57 515	52.13 508	39.02 523	75.71 507	14.90 517	93.30 459	45.35 514	46.48 514	83.69 494

DKM-HiRes		50.92 483	46.71 487	63.56 498	66.42 521	42.72 525	76.47 513	41.46 535	42.47 515	39.40 522	73.35 512	7.13 542	72.77 524	44.18 515	29.50 524	75.19 509

MVS_clip		35.38 496	36.65 498	31.56 518	48.77 540	16.48 555	41.99 537	8.97 563	9.90 542	45.60 512	78.84 501	13.61 521	15.85 558	44.08 516	38.09 519	62.37 521

RoMa-HiRes		51.04 482	47.47 486	61.73 501	65.35 522	42.38 527	76.31 514	41.57 534	42.69 514	42.32 518	77.75 504	9.33 533	73.10 523	42.68 517	29.24 525	69.72 516

FPMVS		61.57 468	60.32 471	65.34 494	60.14 532	42.44 526	91.02 477	89.72 493	44.15 513	42.63 516	80.93 493	19.02 511	80.59 514	42.50 518	72.76 432	73.00 512

PMatch-SfM		44.26 488	39.30 495	59.12 503	52.80 537	33.36 533	66.34 520	29.85 538	36.60 521	30.58 526	70.53 514	2.50 560	68.49 525	42.14 519	22.39 535	75.51 507

testf1		56.38 477	53.73 480	64.31 496	64.84 523	45.11 520	80.50 510	75.94 521	38.87 518	42.74 514	75.07 508	11.26 527	81.19 510	41.11 520	53.27 502	66.63 517

APD_test2		56.38 477	53.73 480	64.31 496	64.84 523	45.11 520	80.50 510	75.94 521	38.87 518	42.74 514	75.07 508	11.26 527	81.19 510	41.11 520	53.27 502	66.63 517

EGC-MVSNET		60.70 472	55.37 477	76.72 476	86.35 468	71.08 482	89.96 482	84.44 510	0.38 561	1.50 563	84.09 479	37.30 498	88.10 499	40.85 522	73.44 427	70.97 515

ELoFTR		47.00 486	42.41 491	60.77 502	51.54 538	32.77 534	63.82 523	61.24 528	39.04 517	29.94 527	67.31 519	4.83 544	75.52 521	39.39 523	24.54 533	74.03 511

PMatch-Up-SfM		39.29 493	34.48 499	53.73 508	46.70 542	28.02 541	58.71 524	21.05 550	31.53 524	27.94 528	66.24 520	1.99 563	61.38 531	38.41 524	17.72 540	71.80 514

ANet_high		50.71 484	46.17 489	64.33 495	44.27 544	52.30 513	76.13 516	78.73 516	64.95 496	27.37 530	55.23 527	14.61 519	67.74 526	36.01 525	18.23 539	72.95 513

MatchFormer		56.78 476	51.80 484	71.74 484	73.47 511	45.39 519	81.84 509	76.12 519	40.41 516	35.13 525	69.22 515	12.67 524	92.15 474	35.57 526	41.74 515	77.67 504

Gipuma		54.77 480	52.22 483	62.40 500	86.50 466	59.37 504	50.20 534	90.35 490	36.52 522	41.20 520	49.49 530	18.33 513	81.29 509	32.10 527	65.34 467	46.54 533
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	41.42 23	45.67 487	42.50 490	55.17 506	34.28 558	32.37 535	66.24 521	78.71 517	30.72 525	22.04 536	59.59 523	4.59 545	77.85 519	27.49 528	58.84 486	55.29 525
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GLUNet-SfM		37.11 495	32.05 501	52.28 509	44.07 546	25.94 542	52.38 533	46.25 533	24.11 529	21.50 537	55.60 526	6.32 543	66.20 528	27.48 529	10.71 553	64.70 519

MVE	44.00 22	41.70 489	37.64 497	53.90 507	49.46 539	43.37 524	65.09 522	66.66 525	26.19 528	25.77 533	48.53 531	3.58 548	63.35 530	26.15 530	27.28 530	54.97 526
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		66.44 465	66.29 468	66.89 492	74.84 506	44.93 522	93.00 451	84.09 511	71.15 477	55.82 502	81.63 489	63.79 423	80.31 515	21.85 531	50.47 508	75.43 508

SP-DiffGlue		29.92 502	29.42 507	31.40 520	32.10 562	20.02 544	47.81 536	27.27 543	14.91 534	26.24 531	54.34 528	10.53 530	24.46 545	21.49 532	30.15 523	49.71 532

SSC-MVS		65.42 466	65.20 470	66.06 493	73.96 508	43.83 523	92.08 462	83.54 512	69.77 484	54.73 503	80.92 494	63.30 425	79.92 516	20.48 533	48.02 511	74.44 510

E-PMN		41.02 490	40.93 493	41.29 510	61.97 528	33.83 532	84.00 500	65.17 526	27.17 526	27.56 529	46.72 534	17.63 514	60.41 532	19.32 534	18.82 536	29.61 537

EMVS		39.96 492	39.88 494	40.18 511	59.57 534	32.12 537	84.79 497	64.57 527	26.27 527	26.14 532	44.18 538	18.73 512	59.29 533	17.03 535	17.67 541	29.12 538

wuyk23d		16.71 512	16.73 517	16.65 526	60.15 531	25.22 543	41.24 538	5.17 566	6.56 555	5.48 559	3.61 561	3.64 547	22.72 546	15.20 536	9.52 555	1.99 558

testmvs		18.81 508	23.05 510	6.10 542	4.48 566	2.29 569	97.78 318	3.00 567	3.27 559	18.60 543	62.71 521	1.53 565	2.49 563	14.26 537	1.80 561	13.50 543

XFeat-MNN		22.62 505	22.31 511	23.56 523	28.01 563	15.00 559	39.69 539	25.09 547	11.81 540	17.88 545	39.92 544	7.77 540	29.38 539	13.26 538	17.33 545	26.31 540

XFeat-NN		22.06 507	22.11 512	21.91 524	27.57 564	14.27 560	38.62 540	22.62 549	11.16 541	18.84 542	41.23 540	7.46 541	26.91 540	13.19 539	18.30 538	24.56 541

SP-SuperGlue		30.18 501	29.74 506	31.50 519	60.57 530	18.71 547	57.45 525	26.07 544	13.70 536	20.25 539	39.95 542	9.22 535	25.03 544	11.85 540	28.64 528	50.78 528

SP-LightGlue		30.23 500	29.76 505	31.66 517	60.90 529	18.79 546	57.25 526	25.88 545	13.65 537	20.11 540	39.95 542	9.29 534	25.08 543	11.83 541	28.96 526	51.11 527

SP-NN		29.64 503	29.14 508	31.16 522	59.77 533	18.23 548	56.90 528	24.71 548	12.64 538	18.99 541	40.64 541	8.48 537	25.23 542	11.37 542	28.74 527	50.01 531

test123		16.58 513	19.47 513	7.91 541	3.59 567	5.37 568	94.32 433	1.39 568	2.49 560	13.98 547	44.60 537	2.91 556	2.65 562	11.35 543	0.57 562	15.70 542

SP-MNN		29.29 504	28.62 509	31.29 521	59.13 535	18.03 551	56.77 529	25.19 546	11.83 539	18.01 544	39.35 545	8.35 538	25.39 541	10.99 544	27.91 529	50.47 530

ALIKED-NN		33.05 498	31.67 502	37.18 515	69.89 518	31.76 538	55.83 531	28.14 541	16.92 532	23.23 534	47.45 532	9.65 532	45.41 537	8.80 545	25.13 532	34.38 536

MVS_baseline		11.50 524	12.32 528	9.06 540	13.94 565	0.55 570	4.75 555	1.33 569	0.26 562	16.85 546	50.28 529	1.45 566	0.03 564	8.71 546	13.26 549	26.61 539

ALIKED-LG		33.96 497	32.42 500	38.57 512	70.35 515	32.25 536	57.19 527	29.49 539	19.94 531	22.96 535	46.96 533	10.85 529	47.42 535	8.53 547	25.49 531	36.04 534

ALIKED-MNN		32.26 499	30.45 503	37.68 514	69.07 519	31.55 539	56.28 530	27.56 542	16.30 533	21.15 538	44.78 536	8.12 539	46.74 536	8.19 548	22.59 534	34.76 535

SIFT-NN		18.10 509	18.53 514	16.83 525	48.67 541	18.97 545	33.34 541	14.35 551	7.78 544	10.98 548	25.86 547	3.78 546	19.51 547	3.23 549	18.78 537	12.02 544

SIFT-MNN		17.20 510	17.47 515	16.41 527	45.38 543	18.16 549	31.28 543	14.20 552	7.60 545	9.54 549	25.18 548	3.39 549	19.18 548	3.18 550	17.44 543	11.88 545

SIFT-NN-NCMNet		16.94 511	17.19 516	16.19 528	43.53 547	18.04 550	31.30 542	14.18 553	7.55 547	9.51 550	24.88 549	3.32 550	18.84 549	3.08 551	17.35 544	11.70 547

SIFT-NN-UMatch		15.49 516	15.62 520	15.11 532	38.08 553	15.93 556	29.97 544	13.04 554	7.57 546	7.22 554	24.84 551	3.26 551	18.03 552	3.02 552	13.56 548	11.37 548

SIFT-NN-CMatch		15.72 515	15.77 519	15.60 530	39.99 551	16.99 554	28.08 546	12.85 556	7.52 548	9.34 551	24.86 550	3.24 552	18.08 551	2.99 553	13.01 550	11.71 546

SIFT-UMatch		14.73 518	14.79 522	14.57 533	40.58 550	15.36 558	27.70 547	11.21 559	7.28 551	6.62 556	24.07 553	2.81 558	17.91 554	2.87 554	9.94 554	10.45 551

SIFT-NN-PointCN		14.43 519	14.70 523	13.64 535	36.13 554	12.94 564	27.63 548	11.82 558	7.03 554	8.24 552	23.49 556	3.21 553	16.75 556	2.85 555	11.89 551	11.22 549

SIFT-ConvMatch		15.12 517	15.10 521	15.19 531	42.19 548	17.16 553	26.33 549	12.02 557	7.39 549	7.26 553	24.08 552	2.92 555	17.97 553	2.85 555	10.90 552	10.43 552

SIFT-NCM-Cal		16.07 514	16.20 518	15.69 529	44.16 545	17.32 552	29.83 545	12.88 555	7.33 550	6.22 557	23.59 555	3.00 554	18.75 550	2.74 557	16.09 546	10.99 550

SIFT-UM-Cal		13.73 521	13.86 525	13.34 536	39.95 552	13.63 562	25.68 550	9.21 562	7.19 553	5.57 558	23.60 554	2.66 559	16.67 557	2.70 558	8.18 558	9.73 554

SIFT-CM-Cal		14.12 520	14.09 524	14.22 534	40.92 549	15.56 557	23.80 551	10.18 560	7.20 552	6.72 555	23.20 557	2.86 557	16.98 555	2.67 559	9.24 557	10.13 553

SIFT-PCN-Cal		12.09 523	12.36 527	11.26 538	35.43 555	9.79 566	22.24 553	8.83 564	6.37 557	5.43 560	20.44 558	2.34 561	14.88 559	2.35 560	7.87 559	9.13 556

SIFT-PointCN		12.37 522	12.72 526	11.33 537	35.33 557	10.01 565	23.72 552	9.79 561	6.45 556	5.30 561	20.10 559	2.22 562	14.67 560	2.33 561	9.26 556	9.30 555

SIFT-NCMNet		10.41 525	10.63 530	9.76 539	33.41 559	9.03 567	18.23 554	5.49 565	6.29 558	4.60 562	17.58 560	1.84 564	12.74 561	2.03 562	6.21 560	7.52 557

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	0.00 565	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	0.00 565	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	0.00 565	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	0.00 565	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	0.00 565	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		22.52 506	30.03 504	0.00 543	0.00 568	0.00 571	0.00 556	97.17 209	0.00 563	0.00 564	98.77 109	74.35 328	0.00 565	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		6.87 527	9.16 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	82.48 218	0.00 565	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	0.00 565	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	0.00 565	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	0.00 565	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	0.00 565	0.00 563	0.00 563	0.00 559

ab-mvs-re		8.21 526	10.94 529	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	98.50 133	0.00 567	0.00 565	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	0.00 565	0.00 563	0.00 563	0.00 559

Meshroom													0.00 565
: In preparation.
AliceVision / Meshro													0.00 565
: In preparation.
AliceVision_Meshroom													0.00 565
: In preparation.
PatchmatchNet2					0.00 568	79.25 435	96.11 400	93.62 450	70.56 479
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													93.74 453
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip				99.33 5	99.87 2	97.98 5	99.65 53	98.06 52	92.29 118	99.91 1	99.64 2	95.49 8	100.00 1		98.29 135	100.00 1

FOURS1					99.50 49	88.94 240	99.55 68	97.47 167	91.32 143	98.12 68

test_one_0601					99.59 35	94.89 40		97.64 127	93.14 95	98.93 35	99.45 20	93.45 20

eth-test2					0.00 568

eth-test					0.00 568

test_241102_ONE					99.63 25	95.24 30		97.72 101	94.16 64	99.30 19	99.49 13	93.32 22	99.98 14

save fliter					99.34 57	93.85 72	99.65 53	97.63 131	95.69 35

test0726					99.66 19	95.20 35	99.77 30	97.70 106	93.95 69	99.35 17	99.54 5	93.18 26

GSMVS																98.84 168

test_part2					99.54 43	95.42 25				98.13 66

sam_mvs1												88.39 87				98.84 168

sam_mvs												87.08 117

MTGPA								97.45 170

test_post											46.00 535	87.37 108	97.11 330

patchmatchnet-post											84.86 476	88.73 83	96.81 343

MTMP							99.21 116	91.09 482

TEST9					99.57 40	93.17 94	99.38 97	97.66 118	89.57 213	98.39 57	99.18 50	90.88 48	99.66 119

test_8					99.55 42	93.07 97	99.37 100	97.64 127	90.18 186	98.36 59	99.19 47	90.94 44	99.63 126

agg_prior					99.54 43	92.66 111		97.64 127		97.98 75			99.61 127

test_prior4						92.00 127	99.41 94

test_prior				97.01 79	99.58 37	91.77 134		97.57 146					99.49 137			99.79 44

新几何2							98.26 273

旧先验1					98.97 82	92.90 107		97.74 97			99.15 57	91.05 43			99.33 71	99.60 84

原ACMM2							98.69 195

test222					98.32 105	91.21 148	98.08 297	97.58 143	83.74 378	95.87 132	99.02 81	86.74 125			99.64 45	99.81 40

segment_acmp												90.56 56

testdata1							97.89 310		92.43 111

test12				97.83 41	99.33 60	94.45 58		97.55 148		97.56 82		88.60 85	99.50 136		99.71 39	99.55 89

plane_prior7					93.84 350	85.73 350

plane_prior6					93.92 347	86.02 342						72.92 344

plane_prior4											96.52 270

plane_prior3						85.91 344			93.65 84	86.99 309

plane_prior2							99.02 152		93.38 91

plane_prior1					93.90 349

plane_prior						86.07 340	99.14 133		93.81 80						86.26 330

n2								0.00 570

nn								0.00 570

door-mid								84.90 509

test11								97.68 112

door								85.30 506

HQP5-MVS						86.39 321

HQP-NCC					93.95 342		99.16 125		93.92 71	87.57 302

ACMP_Plane					93.95 342		99.16 125		93.92 71	87.57 302

HQP4-MVS										87.57 302			97.77 286			92.72 344

HQP3-MVS								96.37 275							86.29 328

HQP2-MVS												73.34 337

NP-MVS					93.94 345	86.22 328					96.67 267

ACMMP++_ref															82.64 362

ACMMP++															83.83 349

Test By Simon												83.62 186

High-resolution multi-view benchmark