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.

MM		89.16 7	89.23 9	88.97 4	90.79 103	73.65 10	92.66 28	91.17 154	86.57 1	87.39 58	94.97 25	71.70 65	97.68 1	92.19 1	95.63 31	95.57 2

fmvsm_s_conf0.5_n_9		87.39 33	87.95 23	85.70 83	89.48 139	67.88 155	88.59 148	89.05 241	80.19 13	90.70 20	95.40 17	74.56 29	93.92 154	91.54 2	92.07 92	95.31 6

fmvsm_s_conf0.5_n_4		85.39 78	85.75 71	84.30 149	86.70 276	65.83 209	88.77 137	89.78 200	75.46 125	88.35 37	93.73 74	69.19 107	93.06 215	91.30 3	88.44 163	94.02 85

fmvsm_s_conf0.5_n_3		86.36 53	87.46 32	83.09 214	87.08 265	65.21 229	89.09 124	90.21 188	79.67 20	89.98 24	95.02 24	73.17 43	91.71 275	91.30 3	91.60 100	92.34 183

fmvsm_s_conf0.5_n_8		86.56 47	87.17 38	84.73 125	87.76 224	65.62 216	89.20 115	92.21 105	79.94 18	89.74 27	94.86 26	68.63 117	94.20 139	90.83 5	91.39 105	94.38 64

MGCNet		87.69 24	87.55 29	88.12 13	89.45 140	71.76 54	91.47 57	89.54 211	82.14 3	86.65 67	94.28 46	68.28 123	97.46 6	90.81 6	95.31 37	95.15 9

fmvsm_s_conf0.5_n_10		86.38 52	86.76 46	85.24 98	87.33 250	67.30 177	89.50 101	90.98 159	76.25 106	90.56 22	94.75 29	68.38 120	94.24 138	90.80 7	92.32 89	94.19 75

test_fmvsmconf_n		85.92 63	86.04 63	85.57 89	85.03 320	69.51 101	89.62 98	90.58 172	73.42 191	87.75 51	94.02 61	72.85 49	93.24 199	90.37 8	90.75 118	93.96 87

test_fmvsmconf0.1_n		85.61 72	85.65 72	85.50 90	82.99 377	69.39 108	89.65 95	90.29 186	73.31 195	87.77 50	94.15 55	71.72 64	93.23 200	90.31 9	90.67 120	93.89 93

test_fmvsmconf0.01_n		84.73 91	84.52 93	85.34 95	80.25 421	69.03 111	89.47 102	89.65 207	73.24 199	86.98 63	94.27 47	66.62 142	93.23 200	90.26 10	89.95 134	93.78 102

fmvsm_l_conf0.5_n_9		85.84 67	86.63 49	83.46 195	87.12 264	66.01 202	88.56 150	89.43 215	75.59 121	89.32 28	94.32 44	72.89 47	91.21 304	90.11 11	92.33 87	93.16 141

fmvsm_s_conf0.5_n_2		84.04 101	84.11 101	83.81 186	86.17 289	65.00 237	86.96 214	87.28 299	74.35 162	88.25 40	94.23 50	61.82 213	92.60 233	89.85 12	88.09 173	93.84 96

fmvsm_s_conf0.5_n_5		85.22 82	85.55 74	84.25 156	86.26 285	67.40 173	89.18 116	89.31 224	72.50 211	88.31 38	93.86 70	69.66 96	91.96 262	89.81 13	91.05 111	93.38 125

fmvsm_s_conf0.1_n_2		83.80 109	83.79 108	83.83 184	85.62 301	64.94 242	87.03 211	86.62 323	74.32 163	87.97 48	94.33 43	60.67 237	92.60 233	89.72 14	87.79 180	93.96 87

MSC_two_6792asdad				89.16 1	94.34 31	75.53 2		92.99 55					97.53 2	89.67 15	96.44 9	94.41 61

No_MVS				89.16 1	94.34 31	75.53 2		92.99 55					97.53 2	89.67 15	96.44 9	94.41 61

MSP-MVS		89.51 5	89.91 6	88.30 10	94.28 34	73.46 17	92.90 21	94.11 10	80.27 11	91.35 16	94.16 54	78.35 14	96.77 28	89.59 17	94.22 65	94.67 42
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
fmvsm_s_conf0.5_n_6		85.55 73	86.20 56	83.60 190	87.32 252	65.13 232	88.86 131	91.63 138	75.41 126	88.23 41	93.45 82	68.56 118	92.47 241	89.52 18	92.78 79	93.20 138

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 31	71.25 65	95.06 1	94.23 6	78.38 39	92.78 4	95.74 8	82.45 3	97.49 4	89.42 19	96.68 2	94.95 15

test_0728_THIRD									78.38 39	92.12 11	95.78 6	81.46 8	97.40 9	89.42 19	96.57 7	94.67 42

APDe-MVS		89.15 8	89.63 7	87.73 31	94.49 22	71.69 55	93.83 4	93.96 17	75.70 119	91.06 19	96.03 1	76.84 18	97.03 20	89.09 21	95.65 30	94.47 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
fmvsm_s_conf0.5_n_11		86.06 57	86.75 47	84.00 177	87.78 221	66.09 199	89.96 86	90.80 167	77.37 59	86.72 66	94.20 52	72.51 53	92.78 229	89.08 22	92.33 87	93.13 145

DVP-MVS		89.60 4	90.35 4	87.33 45	95.27 5	71.25 65	93.49 10	92.73 71	77.33 60	92.12 11	95.78 6	80.98 10	97.40 9	89.08 22	96.41 12	93.33 129
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				87.71 35	95.34 1	71.43 61	93.49 10	94.23 6					97.49 4	89.08 22	96.41 12	94.21 74

SED-MVS		90.08 2	90.85 2	87.77 28	95.30 2	70.98 73	93.57 8	94.06 14	77.24 65	93.10 1	95.72 10	82.99 1	97.44 7	89.07 25	96.63 4	94.88 19

test_241102_TWO								94.06 14	77.24 65	92.78 4	95.72 10	81.26 9	97.44 7	89.07 25	96.58 6	94.26 73

fmvsm_l_conf0.5_n_3		86.02 58	86.32 53	85.14 101	87.20 256	68.54 131	89.57 99	90.44 177	75.31 130	87.49 55	94.39 42	72.86 48	92.72 230	89.04 27	90.56 122	94.16 76

IU-MVS					95.30 2	71.25 65		92.95 61	66.81 335	92.39 6				88.94 28	96.63 4	94.85 24

fmvsm_l_conf0.5_n		84.47 92	84.54 91	84.27 153	85.42 307	68.81 117	88.49 153	87.26 304	68.08 323	88.03 45	93.49 78	72.04 60	91.77 271	88.90 29	89.14 150	92.24 190

fmvsm_s_conf0.5_n		83.80 109	83.71 110	84.07 166	86.69 277	67.31 176	89.46 103	83.07 377	71.09 242	86.96 64	93.70 75	69.02 113	91.47 292	88.79 30	84.62 243	93.44 124

MP-MVS-pluss		87.67 25	87.72 25	87.54 40	93.64 48	72.04 51	89.80 90	93.50 30	75.17 139	86.34 69	95.29 19	70.86 77	96.00 60	88.78 31	96.04 16	94.58 51
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_fmvsmvis_n_1920		84.02 102	83.87 104	84.49 136	84.12 338	69.37 109	88.15 170	87.96 281	70.01 276	83.95 110	93.23 87	68.80 115	91.51 289	88.61 32	89.96 133	92.57 170

SMA-MVS		89.08 9	89.23 9	88.61 6	94.25 35	73.73 9	92.40 29	93.63 26	74.77 152	92.29 7	95.97 2	74.28 34	97.24 15	88.58 33	96.91 1	94.87 21
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
fmvsm_s_conf0.1_n		83.56 121	83.38 119	84.10 160	84.86 322	67.28 178	89.40 109	83.01 378	70.67 255	87.08 61	93.96 67	68.38 120	91.45 293	88.56 34	84.50 244	93.56 118

test_fmvsm_n_1920		85.29 81	85.34 78	85.13 104	86.12 291	69.93 93	88.65 146	90.78 168	69.97 278	88.27 39	93.98 66	71.39 70	91.54 286	88.49 35	90.45 124	93.91 90

CNVR-MVS		88.93 12	89.13 13	88.33 8	94.77 12	73.82 8	90.51 70	93.00 52	80.90 7	88.06 44	94.06 59	76.43 20	96.84 25	88.48 36	95.99 18	94.34 67

fmvsm_l_conf0.5_n_a		84.13 99	84.16 96	84.06 169	85.38 308	68.40 134	88.34 161	86.85 316	67.48 330	87.48 56	93.40 83	70.89 76	91.61 277	88.38 37	89.22 147	92.16 197

fmvsm_s_conf0.5_n_a		83.63 118	83.41 118	84.28 151	86.14 290	68.12 144	89.43 105	82.87 382	70.27 271	87.27 60	93.80 73	69.09 108	91.58 279	88.21 38	83.65 264	93.14 144

MED-MVS test				87.86 27	94.57 17	71.43 61	93.28 12	94.36 3	75.24 131	92.25 9	95.03 22		97.39 11	88.15 39	95.96 19	94.75 35

MED-MVS		89.75 3	90.37 3	87.89 24	94.57 17	71.43 61	93.28 12	94.36 3	77.30 62	92.25 9	95.87 3	81.59 7	97.39 11	88.15 39	95.96 19	94.85 24

ME-MVS		88.98 11	89.39 8	87.75 30	94.54 20	71.43 61	91.61 49	94.25 5	76.30 104	90.62 21	95.03 22	78.06 15	97.07 19	88.15 39	95.96 19	94.75 35

fmvsm_s_conf0.1_n_a		83.32 130	82.99 127	84.28 151	83.79 346	68.07 146	89.34 112	82.85 383	69.80 282	87.36 59	94.06 59	68.34 122	91.56 282	87.95 42	83.46 270	93.21 136

TSAR-MVS + MP.		88.02 21	88.11 20	87.72 33	93.68 47	72.13 48	91.41 58	92.35 90	74.62 156	88.90 33	93.85 71	75.75 24	96.00 60	87.80 43	94.63 53	95.04 12
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMMP_NAP		88.05 20	88.08 21	87.94 19	93.70 45	73.05 22	90.86 65	93.59 28	76.27 105	88.14 42	95.09 21	71.06 75	96.67 33	87.67 44	96.37 14	94.09 81

SD-MVS		88.06 18	88.50 18	86.71 61	92.60 76	72.71 29	91.81 46	93.19 41	77.87 44	90.32 23	94.00 63	74.83 27	93.78 162	87.63 45	94.27 64	93.65 111
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
SteuartSystems-ACMMP		88.72 14	88.86 14	88.32 9	92.14 79	72.96 25	93.73 5	93.67 25	80.19 13	88.10 43	94.80 27	73.76 38	97.11 17	87.51 46	95.82 24	94.90 18
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		89.02 10	89.15 12	88.63 5	95.01 9	76.03 1	92.38 32	92.85 65	80.26 12	87.78 49	94.27 47	75.89 23	96.81 27	87.45 47	96.44 9	93.05 151

DPE-MVS		89.48 6	89.98 5	88.01 16	94.80 11	72.69 31	91.59 51	94.10 12	75.90 112	92.29 7	95.66 12	81.67 6	97.38 13	87.44 48	96.34 15	93.95 89
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SF-MVS		88.46 15	88.74 15	87.64 39	92.78 71	71.95 52	92.40 29	94.74 2	75.71 117	89.16 29	95.10 20	75.65 25	96.19 52	87.07 49	96.01 17	94.79 28

lecture		88.09 17	88.59 16	86.58 63	93.26 56	69.77 97	93.70 6	94.16 8	77.13 70	89.76 26	95.52 16	72.26 55	96.27 49	86.87 50	94.65 51	93.70 105

9.14			88.26 19		92.84 70		91.52 56	94.75 1	73.93 176	88.57 36	94.67 30	75.57 26	95.79 64	86.77 51	95.76 26

MTAPA		87.23 36	87.00 39	87.90 22	94.18 39	74.25 5	86.58 232	92.02 114	79.45 23	85.88 71	94.80 27	68.07 125	96.21 51	86.69 52	95.34 35	93.23 133

fmvsm_s_conf0.5_n_7		83.34 128	84.03 102	81.28 276	85.73 298	65.13 232	85.40 273	89.90 198	74.96 145	82.13 148	93.89 69	66.65 141	87.92 379	86.56 53	91.05 111	90.80 239

reproduce-ours		87.47 27	87.61 27	87.07 51	93.27 54	71.60 56	91.56 54	93.19 41	74.98 143	88.96 30	95.54 14	71.20 73	96.54 41	86.28 54	93.49 70	93.06 149

our_new_method		87.47 27	87.61 27	87.07 51	93.27 54	71.60 56	91.56 54	93.19 41	74.98 143	88.96 30	95.54 14	71.20 73	96.54 41	86.28 54	93.49 70	93.06 149

reproduce_model		87.28 35	87.39 33	86.95 55	93.10 62	71.24 70	91.60 50	93.19 41	74.69 153	88.80 34	95.61 13	70.29 84	96.44 44	86.20 56	93.08 74	93.16 141

TestfortrainingZip a		88.83 13	89.21 11	87.68 37	94.57 17	71.25 65	93.28 12	93.91 19	77.30 62	91.13 18	95.87 3	77.62 16	96.95 22	86.12 57	93.07 75	94.85 24

DeepPCF-MVS	80.84 1	88.10 16	88.56 17	86.73 60	92.24 78	69.03 111	89.57 99	93.39 35	77.53 55	89.79 25	94.12 56	78.98 13	96.58 40	85.66 58	95.72 27	94.58 51

MP-MVS		87.71 23	87.64 26	87.93 21	94.36 30	73.88 6	92.71 27	92.65 77	77.57 51	83.84 112	94.40 41	72.24 56	96.28 48	85.65 59	95.30 38	93.62 114
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
BridgeMVS		86.78 42	86.99 40	86.15 72	91.24 91	67.61 164	90.51 70	92.90 62	77.26 64	87.44 57	91.63 139	71.27 72	96.06 55	85.62 60	95.01 40	94.78 29

ZNCC-MVS		87.94 22	87.85 24	88.20 12	94.39 28	73.33 19	93.03 19	93.81 22	76.81 80	85.24 78	94.32 44	71.76 63	96.93 23	85.53 61	95.79 25	94.32 69

HPM-MVS		87.11 38	86.98 41	87.50 43	93.88 43	72.16 47	92.19 38	93.33 36	76.07 109	83.81 113	93.95 68	69.77 95	96.01 59	85.15 62	94.66 50	94.32 69
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
train_agg		86.43 49	86.20 56	87.13 50	93.26 56	72.96 25	88.75 139	91.89 122	68.69 314	85.00 81	93.10 89	74.43 31	95.41 81	84.97 63	95.71 28	93.02 153

test9_res														84.90 64	95.70 29	92.87 160

NCCC		88.06 18	88.01 22	88.24 11	94.41 26	73.62 11	91.22 62	92.83 66	81.50 5	85.79 73	93.47 81	73.02 46	97.00 21	84.90 64	94.94 43	94.10 80

MCST-MVS		87.37 34	87.25 35	87.73 31	94.53 21	72.46 40	89.82 88	93.82 21	73.07 203	84.86 86	92.89 96	76.22 21	96.33 46	84.89 66	95.13 39	94.40 63

DeepC-MVS	79.81 2	87.08 40	86.88 45	87.69 36	91.16 92	72.32 45	90.31 79	93.94 18	77.12 71	82.82 138	94.23 50	72.13 59	97.09 18	84.83 67	95.37 34	93.65 111
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS		86.73 43	86.67 48	86.91 56	94.11 41	72.11 49	92.37 33	92.56 82	74.50 157	86.84 65	94.65 31	67.31 133	95.77 65	84.80 68	92.85 78	92.84 163

MVSMamba_PlusPlus		85.99 60	85.96 65	86.05 75	91.09 93	67.64 163	89.63 97	92.65 77	72.89 208	84.64 92	91.71 134	71.85 61	96.03 56	84.77 69	94.45 59	94.49 59

ZD-MVS					94.38 29	72.22 46		92.67 74	70.98 247	87.75 51	94.07 58	74.01 37	96.70 31	84.66 70	94.84 47

PC_three_1452									68.21 322	92.02 14	94.00 63	82.09 5	95.98 62	84.58 71	96.68 2	94.95 15

HFP-MVS		87.58 26	87.47 31	87.94 19	94.58 16	73.54 15	93.04 17	93.24 39	76.78 82	84.91 83	94.44 39	70.78 78	96.61 37	84.53 72	94.89 45	93.66 107

ACMMPR		87.44 29	87.23 36	88.08 15	94.64 13	73.59 12	93.04 17	93.20 40	76.78 82	84.66 91	94.52 32	68.81 114	96.65 35	84.53 72	94.90 44	94.00 86

region2R		87.42 31	87.20 37	88.09 14	94.63 14	73.55 13	93.03 19	93.12 46	76.73 85	84.45 96	94.52 32	69.09 108	96.70 31	84.37 74	94.83 48	94.03 84

CANet		86.45 48	86.10 61	87.51 42	90.09 116	70.94 77	89.70 94	92.59 81	81.78 4	81.32 163	91.43 149	70.34 82	97.23 16	84.26 75	93.36 73	94.37 65

APD-MVS		87.44 29	87.52 30	87.19 48	94.24 36	72.39 41	91.86 45	92.83 66	73.01 205	88.58 35	94.52 32	73.36 39	96.49 43	84.26 75	95.01 40	92.70 165
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CS-MVS		86.69 44	86.95 42	85.90 80	90.76 104	67.57 166	92.83 22	93.30 38	79.67 20	84.57 95	92.27 110	71.47 68	95.02 102	84.24 77	93.46 72	95.13 11

CP-MVS		87.11 38	86.92 43	87.68 37	94.20 38	73.86 7	93.98 3	92.82 69	76.62 88	83.68 115	94.46 36	67.93 126	95.95 63	84.20 78	94.39 60	93.23 133

GST-MVS		87.42 31	87.26 34	87.89 24	94.12 40	72.97 24	92.39 31	93.43 33	76.89 78	84.68 88	93.99 65	70.67 80	96.82 26	84.18 79	95.01 40	93.90 92

BP-MVS1		84.32 93	83.71 110	86.17 70	87.84 216	67.85 156	89.38 110	89.64 208	77.73 47	83.98 109	92.12 121	56.89 275	95.43 78	84.03 80	91.75 99	95.24 8

EC-MVSNet		86.01 59	86.38 52	84.91 116	89.31 149	66.27 197	92.32 35	93.63 26	79.37 24	84.17 105	91.88 126	69.04 112	95.43 78	83.93 81	93.77 68	93.01 154

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 61	82.45 3	96.87 24	83.77 82	96.48 8	94.88 19

casdiffmvs_mvg		85.99 60	86.09 62	85.70 83	87.65 232	67.22 182	88.69 144	93.04 47	79.64 22	85.33 77	92.54 106	73.30 40	94.50 127	83.49 83	91.14 110	95.37 3
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
dcpmvs_2		85.63 71	86.15 60	84.06 169	91.71 85	64.94 242	86.47 236	91.87 124	73.63 183	86.60 68	93.02 94	76.57 19	91.87 269	83.36 84	92.15 90	95.35 4

test_prior2							88.85 133		75.41 126	84.91 83	93.54 76	74.28 34		83.31 85	95.86 23

PHI-MVS		86.43 49	86.17 59	87.24 47	90.88 100	70.96 75	92.27 37	94.07 13	72.45 212	85.22 79	91.90 125	69.47 98	96.42 45	83.28 86	95.94 22	94.35 66

XVS		87.18 37	86.91 44	88.00 17	94.42 24	73.33 19	92.78 23	92.99 55	79.14 27	83.67 116	94.17 53	67.45 131	96.60 38	83.06 87	94.50 56	94.07 82

X-MVStestdata		80.37 207	77.83 247	88.00 17	94.42 24	73.33 19	92.78 23	92.99 55	79.14 27	83.67 116	12.47 523	67.45 131	96.60 38	83.06 87	94.50 56	94.07 82

balanced_ft_v1		83.98 105	83.64 113	85.03 107	89.76 129	65.86 208	88.31 163	91.71 134	74.41 161	80.41 187	90.82 172	62.90 195	94.90 106	83.04 89	91.37 106	94.32 69

APD-MVS_3200maxsize		85.97 62	85.88 66	86.22 69	92.69 73	69.53 100	91.93 42	92.99 55	73.54 187	85.94 70	94.51 35	65.80 159	95.61 68	83.04 89	92.51 83	93.53 121

agg_prior2														82.91 91	95.45 32	92.70 165

mPP-MVS		86.67 46	86.32 53	87.72 33	94.41 26	73.55 13	92.74 25	92.22 103	76.87 79	82.81 139	94.25 49	66.44 146	96.24 50	82.88 92	94.28 63	93.38 125

cashybrid2		86.09 56	86.04 63	86.24 67	88.17 197	68.05 148	89.44 104	92.79 70	80.30 10	84.71 87	92.78 103	72.83 50	95.05 100	82.81 93	90.57 121	95.62 1

diffmvs_AUTHOR		82.38 147	82.27 143	82.73 240	83.26 361	63.80 273	83.89 317	89.76 202	73.35 194	82.37 143	90.84 170	66.25 149	90.79 323	82.77 94	87.93 178	93.59 116

SR-MVS-dyc-post		85.77 68	85.61 73	86.23 68	93.06 64	70.63 83	91.88 43	92.27 96	73.53 188	85.69 74	94.45 37	65.00 168	95.56 69	82.75 95	91.87 96	92.50 176

RE-MVS-def			85.48 76		93.06 64	70.63 83	91.88 43	92.27 96	73.53 188	85.69 74	94.45 37	63.87 178		82.75 95	91.87 96	92.50 176

h-mvs33		83.15 133	82.19 144	86.02 78	90.56 106	70.85 80	88.15 170	89.16 235	76.02 110	84.67 89	91.39 150	61.54 218	95.50 74	82.71 97	75.48 377	91.72 210

hse-mvs2		81.72 161	80.94 167	84.07 166	88.72 177	67.68 162	85.87 258	87.26 304	76.02 110	84.67 89	88.22 256	61.54 218	93.48 187	82.71 97	73.44 405	91.06 229

PGM-MVS		86.68 45	86.27 55	87.90 22	94.22 37	73.38 18	90.22 81	93.04 47	75.53 122	83.86 111	94.42 40	67.87 128	96.64 36	82.70 99	94.57 55	93.66 107

ACMMP		85.89 66	85.39 77	87.38 44	93.59 49	72.63 33	92.74 25	93.18 45	76.78 82	80.73 179	93.82 72	64.33 174	96.29 47	82.67 100	90.69 119	93.23 133
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
diffmvs		82.10 152	81.88 153	82.76 238	83.00 373	63.78 275	83.68 322	89.76 202	72.94 206	82.02 150	89.85 200	65.96 158	90.79 323	82.38 101	87.30 190	93.71 104
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
patch_mono-2		83.65 116	84.54 91	80.99 285	90.06 121	65.83 209	84.21 310	88.74 260	71.60 230	85.01 80	92.44 108	74.51 30	83.50 426	82.15 102	92.15 90	93.64 113

SPE-MVS-test		86.29 54	86.48 51	85.71 82	91.02 96	67.21 183	92.36 34	93.78 23	78.97 34	83.51 123	91.20 157	70.65 81	95.15 92	81.96 103	94.89 45	94.77 30

TSAR-MVS + GP.		85.71 70	85.33 79	86.84 57	91.34 89	72.50 36	89.07 125	87.28 299	76.41 96	85.80 72	90.22 195	74.15 36	95.37 86	81.82 104	91.88 95	92.65 169

alignmvs		85.48 74	85.32 80	85.96 79	89.51 136	69.47 103	89.74 92	92.47 83	76.17 107	87.73 53	91.46 148	70.32 83	93.78 162	81.51 105	88.95 151	94.63 48

sasdasda		85.91 64	85.87 68	86.04 76	89.84 126	69.44 106	90.45 76	93.00 52	76.70 86	88.01 46	91.23 153	73.28 41	93.91 155	81.50 106	88.80 154	94.77 30

canonicalmvs		85.91 64	85.87 68	86.04 76	89.84 126	69.44 106	90.45 76	93.00 52	76.70 86	88.01 46	91.23 153	73.28 41	93.91 155	81.50 106	88.80 154	94.77 30

nocashy02		82.38 147	82.11 145	83.19 209	83.30 359	64.26 263	84.62 295	89.16 235	75.24 131	80.97 172	91.10 160	67.12 136	91.63 276	81.36 108	86.13 215	93.67 106

baseline		84.93 88	84.98 85	84.80 122	87.30 254	65.39 222	87.30 204	92.88 63	77.62 49	84.04 108	92.26 111	71.81 62	93.96 147	81.31 109	90.30 126	95.03 13

MGCFI-Net		85.06 87	85.51 75	83.70 188	89.42 141	63.01 298	89.43 105	92.62 80	76.43 95	87.53 54	91.34 151	72.82 51	93.42 192	81.28 110	88.74 157	94.66 45

casdiffmvs		85.11 84	85.14 84	85.01 109	87.20 256	65.77 213	87.75 184	92.83 66	77.84 45	84.36 101	92.38 109	72.15 58	93.93 153	81.27 111	90.48 123	95.33 5
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_111021_HR		85.14 83	84.75 89	86.32 66	91.65 86	72.70 30	85.98 254	90.33 183	76.11 108	82.08 149	91.61 142	71.36 71	94.17 142	81.02 112	92.58 82	92.08 199

HPM-MVS_fast		85.35 80	84.95 87	86.57 64	93.69 46	70.58 85	92.15 40	91.62 139	73.89 177	82.67 142	94.09 57	62.60 197	95.54 71	80.93 113	92.93 77	93.57 117

CPTT-MVS		83.73 113	83.33 121	84.92 115	93.28 53	70.86 79	92.09 41	90.38 179	68.75 313	79.57 197	92.83 98	60.60 241	93.04 218	80.92 114	91.56 103	90.86 238

ETV-MVS		84.90 90	84.67 90	85.59 88	89.39 144	68.66 128	88.74 141	92.64 79	79.97 17	84.10 106	85.71 325	69.32 101	95.38 83	80.82 115	91.37 106	92.72 164

DeepC-MVS_fast	79.65 3	86.91 41	86.62 50	87.76 29	93.52 50	72.37 43	91.26 59	93.04 47	76.62 88	84.22 103	93.36 85	71.44 69	96.76 29	80.82 115	95.33 36	94.16 76
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		83.88 107	83.53 116	84.96 111	86.77 274	69.28 110	90.46 75	92.67 74	74.79 151	82.95 133	91.33 152	72.70 52	93.09 213	80.79 117	79.28 326	92.50 176

NormalMVS		86.29 54	85.88 66	87.52 41	93.26 56	72.47 38	91.65 47	92.19 108	79.31 25	84.39 98	92.18 116	64.64 171	95.53 72	80.70 118	94.65 51	94.56 55

SymmetryMVS		85.38 79	84.81 88	87.07 51	91.47 88	72.47 38	91.65 47	88.06 277	79.31 25	84.39 98	92.18 116	64.64 171	95.53 72	80.70 118	90.91 116	93.21 136

EI-MVSNet-Vis-set		84.19 98	83.81 107	85.31 96	88.18 196	67.85 156	87.66 186	89.73 205	80.05 16	82.95 133	89.59 213	70.74 79	94.82 111	80.66 120	84.72 241	93.28 131

hybridcas		85.11 84	85.18 83	84.90 117	87.47 244	65.68 214	88.53 152	92.38 88	77.91 43	84.27 102	92.48 107	72.19 57	93.88 159	80.37 121	90.97 113	95.15 9

MSLP-MVS++		85.43 76	85.76 70	84.45 137	91.93 82	70.24 86	90.71 67	92.86 64	77.46 57	84.22 103	92.81 100	67.16 135	92.94 220	80.36 122	94.35 62	90.16 268

hybridnocas07		81.44 173	81.13 162	82.37 248	82.13 394	63.11 297	83.45 331	88.74 260	72.54 210	80.71 180	90.73 173	65.14 164	90.74 328	80.35 123	86.41 208	93.27 132

onestephybrid01		82.22 150	81.81 155	83.46 195	83.16 367	64.93 245	84.64 294	89.19 234	73.95 173	81.48 161	90.63 178	66.00 157	91.92 266	80.33 124	86.93 197	93.53 121

MVS_111021_LR		82.61 144	82.11 145	84.11 159	88.82 168	71.58 58	85.15 278	86.16 331	74.69 153	80.47 186	91.04 164	62.29 204	90.55 331	80.33 124	90.08 131	90.20 267

DELS-MVS		85.41 77	85.30 81	85.77 81	88.49 184	67.93 154	85.52 272	93.44 32	78.70 35	83.63 118	89.03 228	74.57 28	95.71 67	80.26 126	94.04 66	93.66 107
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
GDP-MVS		83.52 122	82.64 134	86.16 71	88.14 200	68.45 133	89.13 122	92.69 72	72.82 209	83.71 114	91.86 128	55.69 284	95.35 87	80.03 127	89.74 138	94.69 37

EI-MVSNet-UG-set		83.81 108	83.38 119	85.09 106	87.87 214	67.53 168	87.44 199	89.66 206	79.74 19	82.23 146	89.41 222	70.24 85	94.74 117	79.95 128	83.92 256	92.99 156

CSCG		86.41 51	86.19 58	87.07 51	92.91 67	72.48 37	90.81 66	93.56 29	73.95 173	83.16 130	91.07 163	75.94 22	95.19 90	79.94 129	94.38 61	93.55 119

E5new		84.22 94	84.12 97	84.51 132	87.60 234	65.36 224	87.45 194	92.31 92	76.51 91	83.53 119	92.26 111	69.25 105	93.50 182	79.88 130	88.26 165	94.69 37

E6new		84.22 94	84.12 97	84.52 130	87.60 234	65.36 224	87.45 194	92.30 94	76.51 91	83.53 119	92.26 111	69.26 103	93.49 184	79.88 130	88.26 165	94.69 37

E6		84.22 94	84.12 97	84.52 130	87.60 234	65.36 224	87.45 194	92.30 94	76.51 91	83.53 119	92.26 111	69.26 103	93.49 184	79.88 130	88.26 165	94.69 37

E5		84.22 94	84.12 97	84.51 132	87.60 234	65.36 224	87.45 194	92.31 92	76.51 91	83.53 119	92.26 111	69.25 105	93.50 182	79.88 130	88.26 165	94.69 37

RRT-MVS		82.60 146	82.10 147	84.10 160	87.98 210	62.94 304	87.45 194	91.27 150	77.42 58	79.85 193	90.28 191	56.62 278	94.70 120	79.87 134	88.15 171	94.67 42

E4		84.10 100	83.99 103	84.45 137	87.58 242	64.99 238	86.54 234	92.25 99	76.38 100	83.37 124	92.09 122	69.88 93	93.58 171	79.78 135	88.03 176	94.77 30

AstraMVS		80.81 186	80.14 187	82.80 232	86.05 293	63.96 268	86.46 237	85.90 335	73.71 181	80.85 177	90.56 182	54.06 301	91.57 281	79.72 136	83.97 255	92.86 161

OPM-MVS		83.50 123	82.95 128	85.14 101	88.79 174	70.95 76	89.13 122	91.52 143	77.55 54	80.96 173	91.75 132	60.71 235	94.50 127	79.67 137	86.51 206	89.97 284
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
hybrid		81.05 180	80.66 172	82.22 252	81.97 396	62.99 302	83.42 332	88.68 263	70.76 253	80.56 183	90.40 187	64.49 173	90.48 332	79.57 138	86.06 217	93.19 139

E2		84.00 103	83.87 104	84.39 140	87.70 229	64.95 239	86.40 241	92.23 100	75.85 113	83.21 126	91.78 130	70.09 88	93.55 176	79.52 139	88.05 174	94.66 45

E3		84.00 103	83.87 104	84.39 140	87.70 229	64.95 239	86.40 241	92.23 100	75.85 113	83.21 126	91.78 130	70.09 88	93.55 176	79.52 139	88.05 174	94.66 45

viewcassd2359sk11		83.89 106	83.74 109	84.34 145	87.76 224	64.91 246	86.30 245	92.22 103	75.47 124	83.04 132	91.52 144	70.15 86	93.53 179	79.26 141	87.96 177	94.57 53

E3new		83.78 111	83.60 114	84.31 147	87.76 224	64.89 247	86.24 248	92.20 106	75.15 140	82.87 135	91.23 153	70.11 87	93.52 181	79.05 142	87.79 180	94.51 58

viewmacassd2359aftdt		83.76 112	83.66 112	84.07 166	86.59 280	64.56 252	86.88 219	91.82 127	75.72 116	83.34 125	92.15 120	68.24 124	92.88 223	79.05 142	89.15 149	94.77 30

viewmanbaseed2359cas		83.66 115	83.55 115	84.00 177	86.81 272	64.53 253	86.65 229	91.75 132	74.89 147	83.15 131	91.68 135	68.74 116	92.83 227	79.02 144	89.24 146	94.63 48

LuminaMVS		80.68 194	79.62 203	83.83 184	85.07 319	68.01 150	86.99 213	88.83 251	70.36 266	81.38 162	87.99 264	50.11 355	92.51 240	79.02 144	86.89 200	90.97 234

CDPH-MVS		85.76 69	85.29 82	87.17 49	93.49 51	71.08 71	88.58 149	92.42 87	68.32 321	84.61 93	93.48 79	72.32 54	96.15 54	79.00 146	95.43 33	94.28 72

MVSFormer		82.85 140	82.05 149	85.24 98	87.35 245	70.21 87	90.50 72	90.38 179	68.55 316	81.32 163	89.47 216	61.68 215	93.46 189	78.98 147	90.26 127	92.05 200

test_djsdf		80.30 210	79.32 212	83.27 204	83.98 342	65.37 223	90.50 72	90.38 179	68.55 316	76.19 277	88.70 239	56.44 279	93.46 189	78.98 147	80.14 314	90.97 234

test_vis1_n_1920		75.52 318	75.78 292	74.75 405	79.84 428	57.44 392	83.26 337	85.52 339	62.83 399	79.34 204	86.17 318	45.10 408	79.71 449	78.75 149	81.21 298	87.10 382

HQP_MVS		83.64 117	83.14 122	85.14 101	90.08 117	68.71 124	91.25 60	92.44 84	79.12 29	78.92 209	91.00 167	60.42 243	95.38 83	78.71 150	86.32 209	91.33 221

plane_prior5								92.44 84					95.38 83	78.71 150	86.32 209	91.33 221

LPG-MVS_test		82.08 153	81.27 159	84.50 134	89.23 154	68.76 120	90.22 81	91.94 120	75.37 128	76.64 265	91.51 145	54.29 297	94.91 104	78.44 152	83.78 257	89.83 289

LGP-MVS_train				84.50 134	89.23 154	68.76 120		91.94 120	75.37 128	76.64 265	91.51 145	54.29 297	94.91 104	78.44 152	83.78 257	89.83 289

lupinMVS		81.39 174	80.27 183	84.76 124	87.35 245	70.21 87	85.55 268	86.41 325	62.85 398	81.32 163	88.61 243	61.68 215	92.24 253	78.41 154	90.26 127	91.83 203

jason		81.39 174	80.29 182	84.70 126	86.63 279	69.90 95	85.95 255	86.77 317	63.24 391	81.07 169	89.47 216	61.08 231	92.15 255	78.33 155	90.07 132	92.05 200
jason: jason.
xiu_mvs_v1_base_debu		80.80 189	79.72 200	84.03 174	87.35 245	70.19 89	85.56 265	88.77 254	69.06 304	81.83 151	88.16 257	50.91 343	92.85 224	78.29 156	87.56 184	89.06 309

xiu_mvs_v1_base		80.80 189	79.72 200	84.03 174	87.35 245	70.19 89	85.56 265	88.77 254	69.06 304	81.83 151	88.16 257	50.91 343	92.85 224	78.29 156	87.56 184	89.06 309

xiu_mvs_v1_base_debi		80.80 189	79.72 200	84.03 174	87.35 245	70.19 89	85.56 265	88.77 254	69.06 304	81.83 151	88.16 257	50.91 343	92.85 224	78.29 156	87.56 184	89.06 309

guyue		81.13 178	80.64 173	82.60 243	86.52 281	63.92 271	86.69 228	87.73 289	73.97 172	80.83 178	89.69 207	56.70 276	91.33 298	78.26 159	85.40 233	92.54 172

Effi-MVS+		83.62 119	83.08 123	85.24 98	88.38 190	67.45 170	88.89 130	89.15 237	75.50 123	82.27 145	88.28 253	69.61 97	94.45 130	77.81 160	87.84 179	93.84 96

KinetiMVS		83.31 131	82.61 135	85.39 94	87.08 265	67.56 167	88.06 172	91.65 137	77.80 46	82.21 147	91.79 129	57.27 270	94.07 145	77.77 161	89.89 136	94.56 55

viewdifsd2359ckpt07		82.83 141	82.78 133	82.99 221	86.51 282	62.58 308	85.09 281	90.83 166	75.22 133	82.28 144	91.63 139	69.43 99	92.03 258	77.71 162	86.32 209	94.34 67

PS-MVSNAJss		82.07 154	81.31 158	84.34 145	86.51 282	67.27 179	89.27 113	91.51 144	71.75 225	79.37 202	90.22 195	63.15 188	94.27 134	77.69 163	82.36 285	91.49 217

ACMP	74.13 6	81.51 172	80.57 174	84.36 143	89.42 141	68.69 127	89.97 85	91.50 147	74.46 159	75.04 312	90.41 186	53.82 303	94.54 124	77.56 164	82.91 277	89.86 288
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
BP-MVS														77.47 165

HQP-MVS		82.61 144	82.02 150	84.37 142	89.33 146	66.98 186	89.17 117	92.19 108	76.41 96	77.23 250	90.23 194	60.17 246	95.11 95	77.47 165	85.99 220	91.03 231

MVS_Test		83.15 133	83.06 124	83.41 200	86.86 269	63.21 293	86.11 252	92.00 116	74.31 164	82.87 135	89.44 221	70.03 90	93.21 202	77.39 167	88.50 162	93.81 98

3Dnovator+	77.84 4	85.48 74	84.47 94	88.51 7	91.08 94	73.49 16	93.18 16	93.78 23	80.79 8	76.66 264	93.37 84	60.40 245	96.75 30	77.20 168	93.73 69	95.29 7

anonymousdsp		78.60 252	77.15 267	82.98 223	80.51 419	67.08 184	87.24 206	89.53 212	65.66 356	75.16 307	87.19 286	52.52 312	92.25 252	77.17 169	79.34 325	89.61 296

mmtdpeth		74.16 334	73.01 338	77.60 373	83.72 349	61.13 335	85.10 280	85.10 344	72.06 221	77.21 254	80.33 424	43.84 417	85.75 402	77.14 170	52.61 485	85.91 407

VDD-MVS		83.01 138	82.36 140	84.96 111	91.02 96	66.40 194	88.91 129	88.11 273	77.57 51	84.39 98	93.29 86	52.19 318	93.91 155	77.05 171	88.70 158	94.57 53

XVG-OURS-SEG-HR		80.81 186	79.76 197	83.96 181	85.60 302	68.78 119	83.54 330	90.50 175	70.66 258	76.71 263	91.66 136	60.69 236	91.26 299	76.94 172	81.58 294	91.83 203

Elysia		81.53 168	80.16 185	85.62 86	85.51 304	68.25 140	88.84 134	92.19 108	71.31 235	80.50 184	89.83 201	46.89 386	94.82 111	76.85 173	89.57 140	93.80 100

StellarMVS		81.53 168	80.16 185	85.62 86	85.51 304	68.25 140	88.84 134	92.19 108	71.31 235	80.50 184	89.83 201	46.89 386	94.82 111	76.85 173	89.57 140	93.80 100

jajsoiax		79.29 234	77.96 241	83.27 204	84.68 327	66.57 193	89.25 114	90.16 190	69.20 300	75.46 292	89.49 215	45.75 403	93.13 211	76.84 175	80.80 304	90.11 272

SDMVSNet		80.38 205	80.18 184	80.99 285	89.03 163	64.94 242	80.45 386	89.40 216	75.19 137	76.61 267	89.98 197	60.61 240	87.69 383	76.83 176	83.55 266	90.33 262

viewdifsd2359ckpt11		80.37 207	79.73 198	82.30 250	83.70 350	62.39 312	84.20 311	86.67 319	73.22 200	80.90 174	90.62 179	63.00 193	91.56 282	76.81 177	78.44 333	92.95 158

viewmsd2359difaftdt		80.37 207	79.73 198	82.30 250	83.70 350	62.39 312	84.20 311	86.67 319	73.22 200	80.90 174	90.62 179	63.00 193	91.56 282	76.81 177	78.44 333	92.95 158

mvs_tets		79.13 238	77.77 251	83.22 208	84.70 326	66.37 195	89.17 117	90.19 189	69.38 292	75.40 295	89.46 218	44.17 415	93.15 209	76.78 179	80.70 306	90.14 269

DPM-MVS		84.93 88	84.29 95	86.84 57	90.20 114	73.04 23	87.12 208	93.04 47	69.80 282	82.85 137	91.22 156	73.06 45	96.02 58	76.72 180	94.63 53	91.46 220

test_cas_vis1_n_1920		73.76 340	73.74 329	73.81 416	75.90 461	59.77 361	80.51 384	82.40 387	58.30 443	81.62 159	85.69 326	44.35 414	76.41 467	76.29 181	78.61 329	85.23 419

ET-MVSNet_ETH3D		78.63 251	76.63 282	84.64 127	86.73 275	69.47 103	85.01 283	84.61 350	69.54 289	66.51 429	86.59 304	50.16 354	91.75 272	76.26 182	84.24 252	92.69 167

viewdifsd2359ckpt09		83.34 128	82.55 136	85.70 83	87.64 233	67.72 161	88.43 154	91.68 136	71.91 224	81.65 158	90.68 176	67.10 137	94.75 116	76.17 183	87.70 183	94.62 50

v2v482		80.23 211	79.29 213	83.05 218	83.62 352	64.14 265	87.04 210	89.97 195	73.61 184	78.18 228	87.22 284	61.10 230	93.82 160	76.11 184	76.78 356	91.18 225

test_fmvs1_n		70.86 382	70.24 377	72.73 427	72.51 485	55.28 424	81.27 372	79.71 426	51.49 475	78.73 211	84.87 348	27.54 481	77.02 461	76.06 185	79.97 316	85.88 408

CLD-MVS		82.31 149	81.65 156	84.29 150	88.47 185	67.73 160	85.81 262	92.35 90	75.78 115	78.33 224	86.58 306	64.01 177	94.35 131	76.05 186	87.48 187	90.79 240
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPNet		83.72 114	82.92 129	86.14 74	84.22 336	69.48 102	91.05 64	85.27 341	81.30 6	76.83 259	91.65 137	66.09 153	95.56 69	76.00 187	93.85 67	93.38 125
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewdifsd2359ckpt13		82.91 139	82.29 142	84.77 123	86.96 268	66.90 190	87.47 191	91.62 139	72.19 217	81.68 157	90.71 175	66.92 138	93.28 195	75.90 188	87.15 193	94.12 79

test_fmvs1		70.93 380	70.52 372	72.16 430	73.71 473	55.05 426	80.82 375	78.77 435	51.21 476	78.58 216	84.41 356	31.20 475	76.94 462	75.88 189	80.12 315	84.47 431

XVG-OURS		80.41 203	79.23 215	83.97 180	85.64 300	69.02 113	83.03 346	90.39 178	71.09 242	77.63 241	91.49 147	54.62 296	91.35 296	75.71 190	83.47 269	91.54 214

V42		79.38 232	78.24 237	82.83 229	81.10 413	65.50 219	85.55 268	89.82 199	71.57 231	78.21 226	86.12 319	60.66 238	93.18 208	75.64 191	75.46 379	89.81 291

PS-MVSNAJ		81.69 163	81.02 165	83.70 188	89.51 136	68.21 143	84.28 309	90.09 192	70.79 251	81.26 167	85.62 330	63.15 188	94.29 132	75.62 192	88.87 153	88.59 333

xiu_mvs_v2_base		81.69 163	81.05 164	83.60 190	89.15 157	68.03 149	84.46 301	90.02 193	70.67 255	81.30 166	86.53 309	63.17 187	94.19 141	75.60 193	88.54 160	88.57 334

EIA-MVS		83.31 131	82.80 131	84.82 120	89.59 132	65.59 217	88.21 166	92.68 73	74.66 155	78.96 207	86.42 311	69.06 110	95.26 88	75.54 194	90.09 130	93.62 114

AUN-MVS		79.21 236	77.60 257	84.05 172	88.71 178	67.61 164	85.84 260	87.26 304	69.08 303	77.23 250	88.14 261	53.20 310	93.47 188	75.50 195	73.45 404	91.06 229

mvsmamba		80.60 198	79.38 209	84.27 153	89.74 130	67.24 181	87.47 191	86.95 312	70.02 275	75.38 296	88.93 233	51.24 340	92.56 236	75.47 196	89.22 147	93.00 155

reproduce_monomvs		75.40 322	74.38 320	78.46 354	83.92 344	57.80 385	83.78 319	86.94 313	73.47 190	72.25 353	84.47 354	38.74 450	89.27 355	75.32 197	70.53 424	88.31 339

OMC-MVS		82.69 142	81.97 152	84.85 119	88.75 176	67.42 171	87.98 174	90.87 164	74.92 146	79.72 195	91.65 137	62.19 207	93.96 147	75.26 198	86.42 207	93.16 141

VortexMVS		78.57 254	77.89 245	80.59 294	85.89 294	62.76 306	85.61 263	89.62 209	72.06 221	74.99 313	85.38 336	55.94 283	90.77 326	74.99 199	76.58 357	88.23 342

v1144		80.03 216	79.03 219	83.01 220	83.78 347	64.51 255	87.11 209	90.57 174	71.96 223	78.08 231	86.20 317	61.41 222	93.94 150	74.93 200	77.23 347	90.60 250

MVSTER		79.01 241	77.88 246	82.38 247	83.07 370	64.80 249	84.08 316	88.95 248	69.01 307	78.69 212	87.17 287	54.70 294	92.43 243	74.69 201	80.57 308	89.89 287

viewmambaseed2359dif		80.41 203	79.84 195	82.12 253	82.95 379	62.50 311	83.39 333	88.06 277	67.11 333	80.98 171	90.31 190	66.20 151	91.01 313	74.62 202	84.90 237	92.86 161

test_vis1_n		69.85 399	69.21 385	71.77 433	72.66 484	55.27 425	81.48 366	76.21 455	52.03 472	75.30 303	83.20 388	28.97 478	76.22 469	74.60 203	78.41 337	83.81 439

test_fmvs2		68.35 413	67.48 409	70.98 442	69.50 489	51.95 451	80.05 393	76.38 454	49.33 478	74.65 320	84.38 357	23.30 490	75.40 478	74.51 204	75.17 388	85.60 412

PVSNet_Blended_VisFu		82.62 143	81.83 154	84.96 111	90.80 102	69.76 98	88.74 141	91.70 135	69.39 291	78.96 207	88.46 248	65.47 161	94.87 110	74.42 205	88.57 159	90.24 266

v8		79.97 218	79.02 220	82.80 232	84.09 339	64.50 257	87.96 175	90.29 186	74.13 171	75.24 305	86.81 293	62.88 196	93.89 158	74.39 206	75.40 382	90.00 280

v144192		79.47 226	78.37 233	82.78 236	83.35 357	63.96 268	86.96 214	90.36 182	69.99 277	77.50 242	85.67 328	60.66 238	93.77 164	74.27 207	76.58 357	90.62 248

ACMM	73.20 8	80.78 193	79.84 195	83.58 192	89.31 149	68.37 135	89.99 84	91.60 141	70.28 270	77.25 248	89.66 209	53.37 308	93.53 179	74.24 208	82.85 278	88.85 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
旧先验2							86.56 233		58.10 446	87.04 62			88.98 362	74.07 209

v1192		79.59 223	78.43 232	83.07 217	83.55 354	64.52 254	86.93 217	90.58 172	70.83 250	77.78 238	85.90 321	59.15 252	93.94 150	73.96 210	77.19 349	90.76 242

v10		79.74 220	78.67 225	82.97 224	84.06 340	64.95 239	87.88 181	90.62 171	73.11 202	75.11 309	86.56 307	61.46 221	94.05 146	73.68 211	75.55 375	89.90 286

v1921920		79.22 235	78.03 240	82.80 232	83.30 359	63.94 270	86.80 222	90.33 183	69.91 280	77.48 243	85.53 332	58.44 258	93.75 166	73.60 212	76.85 354	90.71 246

cl22		78.07 266	77.01 269	81.23 278	82.37 392	61.83 325	83.55 328	87.98 279	68.96 310	75.06 311	83.87 370	61.40 223	91.88 268	73.53 213	76.39 362	89.98 283

Effi-MVS+-dtu		80.03 216	78.57 228	84.42 139	85.13 317	68.74 122	88.77 137	88.10 274	74.99 142	74.97 314	83.49 383	57.27 270	93.36 193	73.53 213	80.88 302	91.18 225

c3_l		78.75 247	77.91 243	81.26 277	82.89 380	61.56 329	84.09 315	89.13 239	69.97 278	75.56 288	84.29 360	66.36 147	92.09 257	73.47 215	75.48 377	90.12 271

VDDNet		81.52 170	80.67 171	84.05 172	90.44 109	64.13 266	89.73 93	85.91 334	71.11 241	83.18 129	93.48 79	50.54 350	93.49 184	73.40 216	88.25 169	94.54 57

CANet_DTU		80.61 196	79.87 194	82.83 229	85.60 302	63.17 296	87.36 201	88.65 266	76.37 101	75.88 283	88.44 249	53.51 306	93.07 214	73.30 217	89.74 138	92.25 188

miper_ehance_all_eth		78.59 253	77.76 252	81.08 283	82.66 385	61.56 329	83.65 323	89.15 237	68.87 311	75.55 289	83.79 374	66.49 145	92.03 258	73.25 218	76.39 362	89.64 295

3Dnovator	76.31 5	83.38 127	82.31 141	86.59 62	87.94 211	72.94 28	90.64 68	92.14 113	77.21 67	75.47 290	92.83 98	58.56 257	94.72 118	73.24 219	92.71 81	92.13 198

v1240		78.99 242	77.78 250	82.64 241	83.21 363	63.54 284	86.62 231	90.30 185	69.74 287	77.33 246	85.68 327	57.04 273	93.76 165	73.13 220	76.92 351	90.62 248

casdiffseed414692147		83.62 119	83.02 125	85.40 93	87.31 253	67.50 169	88.70 143	91.72 133	76.97 75	82.77 140	91.72 133	66.85 139	93.71 169	73.06 221	88.12 172	94.98 14

miper_enhance_ethall		77.87 273	76.86 273	80.92 288	81.65 401	61.38 333	82.68 347	88.98 245	65.52 358	75.47 290	82.30 403	65.76 160	92.00 261	72.95 222	76.39 362	89.39 302

MG-MVS		83.41 125	83.45 117	83.28 203	92.74 72	62.28 317	88.17 168	89.50 213	75.22 133	81.49 160	92.74 105	66.75 140	95.11 95	72.85 223	91.58 102	92.45 180

EPP-MVSNet		83.40 126	83.02 125	84.57 128	90.13 115	64.47 258	92.32 35	90.73 169	74.45 160	79.35 203	91.10 160	69.05 111	95.12 93	72.78 224	87.22 191	94.13 78

test_fmvs3		63.36 439	61.82 441	67.98 458	62.51 498	46.96 479	77.37 431	74.03 465	45.24 483	67.50 410	78.79 442	12.16 502	72.98 488	72.77 225	66.02 445	83.99 437

IterMVS-LS		80.06 214	79.38 209	82.11 255	85.89 294	63.20 294	86.79 223	89.34 218	74.19 168	75.45 293	86.72 296	66.62 142	92.39 245	72.58 226	76.86 353	90.75 243
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tt0805		78.73 248	77.83 247	81.43 270	85.17 313	60.30 356	89.41 108	90.90 162	71.21 239	77.17 255	88.73 238	46.38 392	93.21 202	72.57 227	78.96 328	90.79 240

EI-MVSNet		80.52 202	79.98 190	82.12 253	84.28 334	63.19 295	86.41 238	88.95 248	74.18 169	78.69 212	87.54 276	66.62 142	92.43 243	72.57 227	80.57 308	90.74 244

icg_test_0407_2		78.92 245	78.93 222	78.90 342	87.13 259	63.59 280	76.58 436	89.33 219	70.51 261	77.82 235	89.03 228	61.84 211	81.38 442	72.56 229	85.56 229	91.74 206

IMVS_0407		80.61 196	79.90 193	82.75 239	87.13 259	63.59 280	85.33 274	89.33 219	70.51 261	77.82 235	89.03 228	61.84 211	92.91 221	72.56 229	85.56 229	91.74 206

IMVS_0404		77.16 289	76.42 286	79.37 333	87.13 259	63.59 280	77.12 433	89.33 219	70.51 261	66.22 432	89.03 228	50.36 352	82.78 431	72.56 229	85.56 229	91.74 206

IMVS_0403		80.80 189	80.12 188	82.87 228	87.13 259	63.59 280	85.19 275	89.33 219	70.51 261	78.49 219	89.03 228	63.26 184	93.27 197	72.56 229	85.56 229	91.74 206

SSM_0407		81.58 167	80.48 177	84.87 118	88.81 169	67.96 151	87.37 200	89.25 229	71.06 244	79.48 199	90.39 188	59.57 248	94.48 129	72.45 233	85.93 222	92.18 193

SSM_0404		81.91 157	80.84 169	85.13 104	89.24 153	68.26 138	87.84 183	89.25 229	71.06 244	80.62 181	90.39 188	59.57 248	94.65 122	72.45 233	87.19 192	92.47 179

Vis-MVSNet		83.46 124	82.80 131	85.43 92	90.25 113	68.74 122	90.30 80	90.13 191	76.33 103	80.87 176	92.89 96	61.00 232	94.20 139	72.45 233	90.97 113	93.35 128
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
LFMVS		81.82 160	81.23 160	83.57 193	91.89 83	63.43 289	89.84 87	81.85 396	77.04 74	83.21 126	93.10 89	52.26 317	93.43 191	71.98 236	89.95 134	93.85 94

v148		78.72 249	77.80 249	81.47 269	82.73 383	61.96 323	86.30 245	88.08 275	73.26 197	76.18 278	85.47 334	62.46 201	92.36 247	71.92 237	73.82 401	90.09 274

PVSNet_BlendedMVS		80.60 198	80.02 189	82.36 249	88.85 165	65.40 220	86.16 251	92.00 116	69.34 293	78.11 229	86.09 320	66.02 155	94.27 134	71.52 238	82.06 288	87.39 364

PVSNet_Blended		80.98 181	80.34 180	82.90 226	88.85 165	65.40 220	84.43 304	92.00 116	67.62 327	78.11 229	85.05 346	66.02 155	94.27 134	71.52 238	89.50 142	89.01 314

eth_miper_zixun_eth		77.92 271	76.69 280	81.61 267	83.00 373	61.98 322	83.15 339	89.20 233	69.52 290	74.86 316	84.35 359	61.76 214	92.56 236	71.50 240	72.89 409	90.28 265

UA-Net		85.08 86	84.96 86	85.45 91	92.07 80	68.07 146	89.78 91	90.86 165	82.48 2	84.60 94	93.20 88	69.35 100	95.22 89	71.39 241	90.88 117	93.07 148

FA-MVS(test-final)		80.96 182	79.91 192	84.10 160	88.30 193	65.01 236	84.55 298	90.01 194	73.25 198	79.61 196	87.57 273	58.35 259	94.72 118	71.29 242	86.25 212	92.56 171

dtuplus		80.04 215	79.40 208	81.97 259	83.08 369	62.61 307	83.63 326	87.98 279	67.47 331	81.02 170	90.50 185	64.86 169	90.77 326	71.28 243	84.76 240	92.53 173

cl____		77.72 276	76.76 277	80.58 295	82.49 389	60.48 353	83.09 342	87.87 284	69.22 298	74.38 325	85.22 341	62.10 208	91.53 287	71.09 244	75.41 381	89.73 294

DIV-MVS_self_test		77.72 276	76.76 277	80.58 295	82.48 390	60.48 353	83.09 342	87.86 285	69.22 298	74.38 325	85.24 339	62.10 208	91.53 287	71.09 244	75.40 382	89.74 293

MonoMVSNet		76.49 302	75.80 291	78.58 348	81.55 404	58.45 372	86.36 243	86.22 329	74.87 150	74.73 318	83.73 376	51.79 332	88.73 367	70.78 246	72.15 414	88.55 335

test_yl		81.17 176	80.47 178	83.24 206	89.13 158	63.62 276	86.21 249	89.95 196	72.43 215	81.78 155	89.61 211	57.50 267	93.58 171	70.75 247	86.90 198	92.52 174

DCV-MVSNet		81.17 176	80.47 178	83.24 206	89.13 158	63.62 276	86.21 249	89.95 196	72.43 215	81.78 155	89.61 211	57.50 267	93.58 171	70.75 247	86.90 198	92.52 174

VNet		82.21 151	82.41 138	81.62 265	90.82 101	60.93 342	84.47 299	89.78 200	76.36 102	84.07 107	91.88 126	64.71 170	90.26 336	70.68 249	88.89 152	93.66 107

mvs_anonymous		79.42 229	79.11 218	80.34 301	84.45 333	57.97 380	82.59 348	87.62 291	67.40 332	76.17 280	88.56 246	68.47 119	89.59 349	70.65 250	86.05 218	93.47 123

VPA-MVSNet		80.60 198	80.55 175	80.76 291	88.07 205	60.80 345	86.86 220	91.58 142	75.67 120	80.24 189	89.45 220	63.34 181	90.25 337	70.51 251	79.22 327	91.23 224

PAPM_NR		83.02 137	82.41 138	84.82 120	92.47 77	66.37 195	87.93 178	91.80 128	73.82 178	77.32 247	90.66 177	67.90 127	94.90 106	70.37 252	89.48 143	93.19 139

mamba_0408		79.37 233	77.52 259	84.93 114	88.81 169	67.96 151	65.03 490	88.66 264	70.96 248	79.48 199	89.80 203	58.69 254	94.65 122	70.35 253	85.93 222	92.18 193

SSM_04072		77.67 280	77.52 259	78.12 359	88.81 169	67.96 151	65.03 490	88.66 264	70.96 248	79.48 199	89.80 203	58.69 254	74.23 483	70.35 253	85.93 222	92.18 193

thisisatest0530		79.40 230	77.76 252	84.31 147	87.69 231	65.10 235	87.36 201	84.26 357	70.04 274	77.42 244	88.26 255	49.94 358	94.79 115	70.20 255	84.70 242	93.03 152

tttt0517		79.40 230	77.91 243	83.90 183	88.10 203	63.84 272	88.37 160	84.05 359	71.45 233	76.78 261	89.12 225	49.93 360	94.89 108	70.18 256	83.18 275	92.96 157

UniMVSNet_NR-MVSNet		81.88 158	81.54 157	82.92 225	88.46 186	63.46 287	87.13 207	92.37 89	80.19 13	78.38 222	89.14 224	71.66 67	93.05 216	70.05 257	76.46 360	92.25 188

DU-MVS		81.12 179	80.52 176	82.90 226	87.80 218	63.46 287	87.02 212	91.87 124	79.01 32	78.38 222	89.07 226	65.02 166	93.05 216	70.05 257	76.46 360	92.20 191

XVG-ACMP-BASELINE		76.11 310	74.27 322	81.62 265	83.20 364	64.67 251	83.60 327	89.75 204	69.75 285	71.85 357	87.09 289	32.78 470	92.11 256	69.99 259	80.43 310	88.09 346

GeoE		81.71 162	81.01 166	83.80 187	89.51 136	64.45 259	88.97 127	88.73 262	71.27 238	78.63 215	89.76 206	66.32 148	93.20 205	69.89 260	86.02 219	93.74 103

FIs		82.07 154	82.42 137	81.04 284	88.80 173	58.34 374	88.26 165	93.49 31	76.93 77	78.47 221	91.04 164	69.92 92	92.34 249	69.87 261	84.97 236	92.44 181

114514_t		80.68 194	79.51 205	84.20 157	94.09 42	67.27 179	89.64 96	91.11 157	58.75 441	74.08 327	90.72 174	58.10 260	95.04 101	69.70 262	89.42 144	90.30 264

Anonymous20231211		78.97 243	77.69 255	82.81 231	90.54 107	64.29 262	90.11 83	91.51 144	65.01 370	76.16 281	88.13 262	50.56 349	93.03 219	69.68 263	77.56 346	91.11 227

Patchmatch-RL test		70.24 390	67.78 404	77.61 371	77.43 456	59.57 365	71.16 465	70.33 473	62.94 397	68.65 393	72.77 476	50.62 348	85.49 407	69.58 264	66.58 443	87.77 353

UniMVSNet (Re)		81.60 166	81.11 163	83.09 214	88.38 190	64.41 260	87.60 187	93.02 51	78.42 38	78.56 217	88.16 257	69.78 94	93.26 198	69.58 264	76.49 359	91.60 211

IterMVS-SCA-FT		75.43 320	73.87 327	80.11 309	82.69 384	64.85 248	81.57 365	83.47 368	69.16 301	70.49 369	84.15 368	51.95 325	88.15 376	69.23 266	72.14 415	87.34 369

v7n		78.97 243	77.58 258	83.14 212	83.45 356	65.51 218	88.32 162	91.21 152	73.69 182	72.41 350	86.32 314	57.93 261	93.81 161	69.18 267	75.65 373	90.11 272

Anonymous20240529		80.19 213	78.89 223	84.10 160	90.60 105	64.75 250	88.95 128	90.90 162	65.97 353	80.59 182	91.17 159	49.97 357	93.73 168	69.16 268	82.70 282	93.81 98

miper_lstm_enhance		74.11 335	73.11 337	77.13 379	80.11 424	59.62 363	72.23 461	86.92 315	66.76 337	70.40 370	82.92 393	56.93 274	82.92 430	69.06 269	72.63 410	88.87 321

testdata				79.97 313	90.90 99	64.21 264		84.71 348	59.27 434	85.40 76	92.91 95	62.02 210	89.08 360	68.95 270	91.37 106	86.63 394

test1111		79.43 228	79.18 217	80.15 308	89.99 122	53.31 443	87.33 203	77.05 449	75.04 141	80.23 190	92.77 104	48.97 374	92.33 250	68.87 271	92.40 86	94.81 27

GA-MVS		76.87 294	75.17 309	81.97 259	82.75 382	62.58 308	81.44 368	86.35 328	72.16 220	74.74 317	82.89 394	46.20 397	92.02 260	68.85 272	81.09 299	91.30 223

test2506		77.30 287	76.49 283	79.74 323	90.08 117	52.02 449	87.86 182	63.10 493	74.88 148	80.16 191	92.79 101	38.29 454	92.35 248	68.74 273	92.50 84	94.86 22

ECVR-MVS		79.61 221	79.26 214	80.67 293	90.08 117	54.69 430	87.89 180	77.44 445	74.88 148	80.27 188	92.79 101	48.96 375	92.45 242	68.55 274	92.50 84	94.86 22

UGNet		80.83 185	79.59 204	84.54 129	88.04 206	68.09 145	89.42 107	88.16 272	76.95 76	76.22 276	89.46 218	49.30 369	93.94 150	68.48 275	90.31 125	91.60 211
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
FC-MVSNet-test		81.52 170	82.02 150	80.03 310	88.42 189	55.97 414	87.95 176	93.42 34	77.10 72	77.38 245	90.98 169	69.96 91	91.79 270	68.46 276	84.50 244	92.33 184

DP-MVS Recon		83.11 136	82.09 148	86.15 72	94.44 23	70.92 78	88.79 136	92.20 106	70.53 260	79.17 205	91.03 166	64.12 176	96.03 56	68.39 277	90.14 129	91.50 216

UniMVSNet_ETH3D		79.10 239	78.24 237	81.70 264	86.85 270	60.24 357	87.28 205	88.79 253	74.25 167	76.84 258	90.53 184	49.48 364	91.56 282	67.98 278	82.15 286	93.29 130

D2MVS		74.82 327	73.21 335	79.64 328	79.81 429	62.56 310	80.34 388	87.35 298	64.37 378	68.86 391	82.66 398	46.37 393	90.10 339	67.91 279	81.24 297	86.25 397

IS-MVSNet		83.15 133	82.81 130	84.18 158	89.94 124	63.30 291	91.59 51	88.46 270	79.04 31	79.49 198	92.16 118	65.10 165	94.28 133	67.71 280	91.86 98	94.95 15

Fast-Effi-MVS+-dtu		78.02 268	76.49 283	82.62 242	83.16 367	66.96 188	86.94 216	87.45 296	72.45 212	71.49 362	84.17 367	54.79 293	91.58 279	67.61 281	80.31 311	89.30 305

PAPR		81.66 165	80.89 168	83.99 179	90.27 112	64.00 267	86.76 226	91.77 131	68.84 312	77.13 257	89.50 214	67.63 129	94.88 109	67.55 282	88.52 161	93.09 147

cascas		76.72 296	74.64 314	82.99 221	85.78 297	65.88 207	82.33 352	89.21 232	60.85 419	72.74 344	81.02 415	47.28 382	93.75 166	67.48 283	85.02 235	89.34 304

1314		76.53 298	75.30 307	80.21 306	83.93 343	62.32 316	84.66 291	88.81 252	60.23 424	70.16 375	84.07 369	55.30 287	90.73 329	67.37 284	83.21 274	87.59 358

无先验							87.48 190	88.98 245	60.00 427				94.12 143	67.28 285		88.97 317

thisisatest0515		77.33 286	75.38 302	83.18 210	85.27 312	63.80 273	82.11 356	83.27 371	65.06 368	75.91 282	83.84 372	49.54 363	94.27 134	67.24 286	86.19 213	91.48 218

原ACMM1				84.35 144	93.01 66	68.79 118		92.44 84	63.96 386	81.09 168	91.57 143	66.06 154	95.45 76	67.19 287	94.82 49	88.81 324

Baseline_NR-MVSNet		78.15 264	78.33 235	77.61 371	85.79 296	56.21 412	86.78 224	85.76 337	73.60 185	77.93 234	87.57 273	65.02 166	88.99 361	67.14 288	75.33 384	87.63 355

TranMVSNet+NR-MVSNet		80.84 184	80.31 181	82.42 246	87.85 215	62.33 315	87.74 185	91.33 149	80.55 9	77.99 233	89.86 199	65.23 163	92.62 231	67.05 289	75.24 387	92.30 186

Fast-Effi-MVS+		80.81 186	79.92 191	83.47 194	88.85 165	64.51 255	85.53 270	89.39 217	70.79 251	78.49 219	85.06 345	67.54 130	93.58 171	67.03 290	86.58 204	92.32 185

VPNet		78.69 250	78.66 226	78.76 344	88.31 192	55.72 418	84.45 302	86.63 322	76.79 81	78.26 225	90.55 183	59.30 251	89.70 348	66.63 291	77.05 350	90.88 237

PM-MVS		66.41 426	64.14 429	73.20 422	73.92 472	56.45 405	78.97 409	64.96 490	63.88 387	64.72 443	80.24 426	19.84 494	83.44 427	66.24 292	64.52 457	79.71 470

test-LLR		72.94 359	72.43 344	74.48 406	81.35 409	58.04 378	78.38 417	77.46 443	66.66 339	69.95 379	79.00 439	48.06 378	79.24 450	66.13 293	84.83 238	86.15 400

test-mter		71.41 375	70.39 376	74.48 406	81.35 409	58.04 378	78.38 417	77.46 443	60.32 423	69.95 379	79.00 439	36.08 464	79.24 450	66.13 293	84.83 238	86.15 400

MVS		78.19 263	76.99 271	81.78 262	85.66 299	66.99 185	84.66 291	90.47 176	55.08 464	72.02 356	85.27 338	63.83 179	94.11 144	66.10 295	89.80 137	84.24 433

NR-MVSNet		80.23 211	79.38 209	82.78 236	87.80 218	63.34 290	86.31 244	91.09 158	79.01 32	72.17 354	89.07 226	67.20 134	92.81 228	66.08 296	75.65 373	92.20 191

CVMVSNet		72.99 358	72.58 343	74.25 410	84.28 334	50.85 463	86.41 238	83.45 369	44.56 484	73.23 338	87.54 276	49.38 366	85.70 403	65.90 297	78.44 333	86.19 399

IterMVS		74.29 331	72.94 339	78.35 355	81.53 405	63.49 286	81.58 364	82.49 386	68.06 324	69.99 378	83.69 378	51.66 334	85.54 406	65.85 298	71.64 418	86.01 404
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
OurMVSNet-221017-0		74.26 332	72.42 345	79.80 318	83.76 348	59.59 364	85.92 257	86.64 321	66.39 346	66.96 419	87.58 272	39.46 445	91.60 278	65.76 299	69.27 429	88.22 343

tpmrst		72.39 364	72.13 348	73.18 423	80.54 418	49.91 467	79.91 396	79.08 433	63.11 393	71.69 359	79.95 429	55.32 286	82.77 432	65.66 300	73.89 399	86.87 385

MAR-MVS		81.84 159	80.70 170	85.27 97	91.32 90	71.53 59	89.82 88	90.92 161	69.77 284	78.50 218	86.21 316	62.36 203	94.52 126	65.36 301	92.05 93	89.77 292
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
Anonymous202405211		78.25 259	77.01 269	81.99 258	91.03 95	60.67 349	84.77 288	83.90 361	70.65 259	80.00 192	91.20 157	41.08 436	91.43 294	65.21 302	85.26 234	93.85 94

ab-mvs		79.51 224	78.97 221	81.14 281	88.46 186	60.91 343	83.84 318	89.24 231	70.36 266	79.03 206	88.87 236	63.23 186	90.21 338	65.12 303	82.57 283	92.28 187

IB-MVS	68.01 15	75.85 314	73.36 334	83.31 202	84.76 325	66.03 200	83.38 334	85.06 345	70.21 273	69.40 385	81.05 414	45.76 402	94.66 121	65.10 304	75.49 376	89.25 306
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
WR-MVS		79.49 225	79.22 216	80.27 303	88.79 174	58.35 373	85.06 282	88.61 268	78.56 36	77.65 240	88.34 251	63.81 180	90.66 330	64.98 305	77.22 348	91.80 205

CostFormer		75.24 324	73.90 326	79.27 335	82.65 386	58.27 375	80.80 376	82.73 385	61.57 414	75.33 302	83.13 389	55.52 285	91.07 311	64.98 305	78.34 338	88.45 336

API-MVS		81.99 156	81.23 160	84.26 155	90.94 98	70.18 92	91.10 63	89.32 223	71.51 232	78.66 214	88.28 253	65.26 162	95.10 98	64.74 307	91.23 109	87.51 361

新几何1				83.42 198	93.13 60	70.71 81		85.48 340	57.43 453	81.80 154	91.98 123	63.28 182	92.27 251	64.60 308	92.99 76	87.27 372

testing91		76.54 297	75.66 296	79.18 338	88.43 188	55.89 415	81.08 373	83.00 379	73.76 180	75.34 298	84.29 360	46.20 397	90.07 340	64.33 309	84.50 244	91.58 213

testing99		76.09 311	75.12 310	79.00 339	88.16 198	55.50 421	80.79 377	81.40 401	73.30 196	75.17 306	84.27 363	44.48 412	90.02 341	64.28 310	84.22 253	91.48 218

pm-mvs1		77.25 288	76.68 281	78.93 341	84.22 336	58.62 371	86.41 238	88.36 271	71.37 234	73.31 336	88.01 263	61.22 228	89.15 359	64.24 311	73.01 408	89.03 313

TESTMET0.1,1		69.89 398	69.00 387	72.55 428	79.27 439	56.85 398	78.38 417	74.71 463	57.64 449	68.09 401	77.19 454	37.75 456	76.70 463	63.92 312	84.09 254	84.10 436

QAPM		80.88 183	79.50 206	85.03 107	88.01 209	68.97 115	91.59 51	92.00 116	66.63 344	75.15 308	92.16 118	57.70 264	95.45 76	63.52 313	88.76 156	90.66 247

baseline2		75.70 315	73.83 328	81.30 275	83.26 361	61.79 326	82.57 349	80.65 409	66.81 335	66.88 420	83.42 384	57.86 263	92.19 254	63.47 314	79.57 318	89.91 285

LCM-MVSNet-Re		77.05 290	76.94 272	77.36 375	87.20 256	51.60 456	80.06 392	80.46 414	75.20 136	67.69 408	86.72 296	62.48 200	88.98 362	63.44 315	89.25 145	91.51 215

gm-plane-assit					81.40 407	53.83 438			62.72 402		80.94 417		92.39 245	63.40 316

baseline1		76.98 292	76.75 279	77.66 369	88.13 201	55.66 419	85.12 279	81.89 394	73.04 204	76.79 260	88.90 234	62.43 202	87.78 382	63.30 317	71.18 421	89.55 298

blended_shiyan8		73.38 345	71.17 361	80.02 311	78.36 444	61.51 331	82.43 350	87.28 299	65.40 362	68.61 394	77.53 452	51.91 328	91.00 316	63.28 318	65.76 448	87.53 360

blended_shiyan6		73.38 345	71.17 361	80.01 312	78.36 444	61.48 332	82.43 350	87.27 302	65.40 362	68.56 396	77.55 451	51.94 327	91.01 313	63.27 319	65.76 448	87.55 359

usedtu_blend_shiyan5		73.29 351	70.96 365	80.25 304	77.80 451	62.16 319	84.44 303	87.38 297	64.41 376	68.09 401	76.28 461	51.32 336	91.23 301	63.21 320	65.76 448	87.35 366

blend_shiyan4		72.29 368	69.65 381	80.21 306	78.24 447	62.16 319	82.29 353	87.27 302	65.41 361	68.43 400	76.42 460	39.91 443	91.23 301	63.21 320	65.66 453	87.22 373

wanda-best-256-512		72.94 359	70.66 369	79.79 319	77.80 451	61.03 340	81.31 370	87.15 307	65.18 365	68.09 401	76.28 461	51.32 336	90.97 317	63.06 322	65.76 448	87.35 366

FE-blended-shiyan7		72.94 359	70.66 369	79.79 319	77.80 451	61.03 340	81.31 370	87.15 307	65.18 365	68.09 401	76.28 461	51.32 336	90.97 317	63.06 322	65.76 448	87.35 366

AdaColmap		80.58 201	79.42 207	84.06 169	93.09 63	68.91 116	89.36 111	88.97 247	69.27 295	75.70 286	89.69 207	57.20 272	95.77 65	63.06 322	88.41 164	87.50 362

test_vis1_rt		60.28 444	58.42 447	65.84 463	67.25 492	55.60 420	70.44 470	60.94 496	44.33 485	59.00 470	66.64 487	24.91 485	68.67 494	62.80 325	69.48 427	73.25 483

gbinet_0.2-2-1-0.02		73.24 353	70.86 368	80.39 298	78.03 449	61.62 328	83.10 341	86.69 318	65.98 352	69.29 388	76.15 464	49.77 361	91.51 289	62.75 326	66.00 446	88.03 347

GBi-Net		78.40 256	77.40 262	81.40 272	87.60 234	63.01 298	88.39 157	89.28 225	71.63 227	75.34 298	87.28 280	54.80 290	91.11 305	62.72 327	79.57 318	90.09 274

test1		78.40 256	77.40 262	81.40 272	87.60 234	63.01 298	88.39 157	89.28 225	71.63 227	75.34 298	87.28 280	54.80 290	91.11 305	62.72 327	79.57 318	90.09 274

FMVSNet3		77.88 272	76.85 274	80.97 287	86.84 271	62.36 314	86.52 235	88.77 254	71.13 240	75.34 298	86.66 302	54.07 300	91.10 308	62.72 327	79.57 318	89.45 300

CMPMVS	51.72 21	70.19 391	68.16 393	76.28 384	73.15 480	57.55 390	79.47 400	83.92 360	48.02 480	56.48 479	84.81 350	43.13 421	86.42 396	62.67 330	81.81 292	84.89 426
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
sd_testset		77.70 278	77.40 262	78.60 347	89.03 163	60.02 359	79.00 408	85.83 336	75.19 137	76.61 267	89.98 197	54.81 289	85.46 408	62.63 331	83.55 266	90.33 262

0.4-1-1-0.1		70.93 380	67.94 399	79.91 314	79.35 437	61.27 334	78.95 410	82.19 391	63.36 390	67.50 410	69.40 484	39.83 444	91.04 312	62.44 332	68.40 435	87.40 363

usedtu_dtu_shiyan1		76.43 303	75.32 305	79.76 321	83.00 373	60.72 346	81.74 360	88.76 258	68.99 308	72.98 341	84.19 365	56.41 280	90.27 334	62.39 333	79.40 322	88.31 339

FE-MVSNET3		76.43 303	75.32 305	79.76 321	83.00 373	60.72 346	81.74 360	88.76 258	68.99 308	72.98 341	84.19 365	56.41 280	90.27 334	62.39 333	79.40 322	88.31 339

FMVSNet2		78.20 262	77.21 266	81.20 279	87.60 234	62.89 305	87.47 191	89.02 243	71.63 227	75.29 304	87.28 280	54.80 290	91.10 308	62.38 335	79.38 324	89.61 296

testdata2													91.01 313	62.37 336

testing11		75.14 325	74.01 323	78.53 351	88.16 198	56.38 408	80.74 380	80.42 416	70.67 255	72.69 347	83.72 377	43.61 419	89.86 343	62.29 337	83.76 259	89.36 303

CP-MVSNet		78.22 260	78.34 234	77.84 365	87.83 217	54.54 432	87.94 177	91.17 154	77.65 48	73.48 335	88.49 247	62.24 206	88.43 373	62.19 338	74.07 396	90.55 252

XXY-MVS		75.41 321	75.56 297	74.96 400	83.59 353	57.82 384	80.59 383	83.87 362	66.54 345	74.93 315	88.31 252	63.24 185	80.09 448	62.16 339	76.85 354	86.97 384

pmmvs6		74.69 328	73.39 332	78.61 346	81.38 408	57.48 391	86.64 230	87.95 282	64.99 371	70.18 373	86.61 303	50.43 351	89.52 350	62.12 340	70.18 426	88.83 323

1112_ss		77.40 285	76.43 285	80.32 302	89.11 162	60.41 355	83.65 323	87.72 290	62.13 410	73.05 340	86.72 296	62.58 199	89.97 342	62.11 341	80.80 304	90.59 251

0.3-1-1-0.015		70.03 394	66.80 418	79.72 324	78.18 448	61.07 338	77.63 428	82.32 390	62.65 403	65.50 436	67.29 485	37.62 458	90.91 319	61.99 342	68.04 437	87.19 375

PS-CasMVS		78.01 269	78.09 239	77.77 367	87.71 227	54.39 434	88.02 173	91.22 151	77.50 56	73.26 337	88.64 242	60.73 234	88.41 374	61.88 343	73.88 400	90.53 253

CDS-MVSNet		79.07 240	77.70 254	83.17 211	87.60 234	68.23 142	84.40 307	86.20 330	67.49 329	76.36 273	86.54 308	61.54 218	90.79 323	61.86 344	87.33 189	90.49 255
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OpenMVS	72.83 10	79.77 219	78.33 235	84.09 164	85.17 313	69.91 94	90.57 69	90.97 160	66.70 338	72.17 354	91.91 124	54.70 294	93.96 147	61.81 345	90.95 115	88.41 338

0.4-1-1-0.2		70.01 395	66.86 417	79.44 332	77.61 454	60.64 350	76.77 435	82.34 389	62.40 406	65.91 434	66.65 486	40.05 441	90.83 321	61.77 346	68.24 436	86.86 386

K. test v3		71.19 376	68.51 389	79.21 337	83.04 372	57.78 386	84.35 308	76.91 450	72.90 207	62.99 455	82.86 395	39.27 446	91.09 310	61.65 347	52.66 484	88.75 327

CHOSEN 1792x2688		77.63 281	75.69 293	83.44 197	89.98 123	68.58 130	78.70 413	87.50 294	56.38 458	75.80 285	86.84 292	58.67 256	91.40 295	61.58 348	85.75 227	90.34 261

dtuonly		69.95 396	69.98 379	69.85 446	73.09 481	49.46 470	74.55 454	76.40 453	57.56 452	67.82 405	86.31 315	50.89 347	74.23 483	61.46 349	81.71 293	85.86 410

PCF-MVS	73.52 7	80.38 205	78.84 224	85.01 109	87.71 227	68.99 114	83.65 323	91.46 148	63.00 395	77.77 239	90.28 191	66.10 152	95.09 99	61.40 350	88.22 170	90.94 236
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HY-MVS	69.67 12	77.95 270	77.15 267	80.36 300	87.57 243	60.21 358	83.37 335	87.78 288	66.11 348	75.37 297	87.06 291	63.27 183	90.48 332	61.38 351	82.43 284	90.40 259

HyFIR lowres test		77.53 282	75.40 301	83.94 182	89.59 132	66.62 191	80.36 387	88.64 267	56.29 459	76.45 270	85.17 342	57.64 265	93.28 195	61.34 352	83.10 276	91.91 202

PMMVS		69.34 402	68.67 388	71.35 438	75.67 464	62.03 321	75.17 446	73.46 466	50.00 477	68.68 392	79.05 437	52.07 323	78.13 455	61.16 353	82.77 279	73.90 482

FMVSNet1		77.44 283	76.12 290	81.40 272	86.81 272	63.01 298	88.39 157	89.28 225	70.49 265	74.39 324	87.28 280	49.06 373	91.11 305	60.91 354	78.52 331	90.09 274

sss		73.60 342	73.64 330	73.51 418	82.80 381	55.01 427	76.12 438	81.69 397	62.47 405	74.68 319	85.85 324	57.32 269	78.11 456	60.86 355	80.93 300	87.39 364

Test_1112_low_res		76.40 306	75.44 299	79.27 335	89.28 151	58.09 376	81.69 363	87.07 310	59.53 432	72.48 349	86.67 301	61.30 225	89.33 353	60.81 356	80.15 313	90.41 258

sc_t1		72.19 370	69.51 382	80.23 305	84.81 323	61.09 337	84.68 290	80.22 421	60.70 420	71.27 363	83.58 381	36.59 461	89.24 356	60.41 357	63.31 460	90.37 260

BH-untuned		79.47 226	78.60 227	82.05 256	89.19 156	65.91 206	86.07 253	88.52 269	72.18 218	75.42 294	87.69 270	61.15 229	93.54 178	60.38 358	86.83 201	86.70 391

WTY-MVS		75.65 316	75.68 294	75.57 391	86.40 284	56.82 399	77.92 426	82.40 387	65.10 367	76.18 278	87.72 268	63.13 191	80.90 445	60.31 359	81.96 289	89.00 316

pmmvs4		74.03 338	71.91 349	80.39 298	81.96 397	68.32 136	81.45 367	82.14 392	59.32 433	69.87 381	85.13 343	52.40 315	88.13 377	60.21 360	74.74 392	84.73 429

PEN-MVS		77.73 275	77.69 255	77.84 365	87.07 267	53.91 437	87.91 179	91.18 153	77.56 53	73.14 339	88.82 237	61.23 227	89.17 358	59.95 361	72.37 411	90.43 257

CR-MVSNet		73.37 347	71.27 359	79.67 327	81.32 411	65.19 230	75.92 440	80.30 419	59.92 428	72.73 345	81.19 412	52.50 313	86.69 391	59.84 362	77.71 342	87.11 380

mvs5depth		69.45 401	67.45 410	75.46 395	73.93 471	55.83 416	79.19 405	83.23 372	66.89 334	71.63 360	83.32 385	33.69 469	85.09 411	59.81 363	55.34 481	85.46 415

lessismore_v0				78.97 340	81.01 414	57.15 395		65.99 486		61.16 462	82.82 396	39.12 448	91.34 297	59.67 364	46.92 491	88.43 337

CNLPA		78.08 265	76.79 276	81.97 259	90.40 110	71.07 72	87.59 188	84.55 351	66.03 351	72.38 351	89.64 210	57.56 266	86.04 400	59.61 365	83.35 271	88.79 325

BH-RMVSNet		79.61 221	78.44 231	83.14 212	89.38 145	65.93 205	84.95 285	87.15 307	73.56 186	78.19 227	89.79 205	56.67 277	93.36 193	59.53 366	86.74 202	90.13 270

FE-MVSNET2		72.88 362	71.28 358	77.67 368	78.30 446	57.78 386	84.43 304	88.92 250	69.56 288	64.61 444	81.67 410	46.73 390	88.54 372	59.33 367	67.99 438	86.69 392

MS-PatchMatch		73.83 339	72.67 341	77.30 377	83.87 345	66.02 201	81.82 358	84.66 349	61.37 417	68.61 394	82.82 396	47.29 381	88.21 375	59.27 368	84.32 251	77.68 475

test_post1							78.90 412				5.43 531	48.81 377	85.44 409	59.25 369

SCA		74.22 333	72.33 346	79.91 314	84.05 341	62.17 318	79.96 395	79.29 431	66.30 347	72.38 351	80.13 427	51.95 325	88.60 370	59.25 369	77.67 345	88.96 318

FE-MVS		77.78 274	75.68 294	84.08 165	88.09 204	66.00 203	83.13 340	87.79 287	68.42 320	78.01 232	85.23 340	45.50 406	95.12 93	59.11 371	85.83 226	91.11 227

SixPastTwentyTwo		73.37 347	71.26 360	79.70 325	85.08 318	57.89 382	85.57 264	83.56 366	71.03 246	65.66 435	85.88 322	42.10 429	92.57 235	59.11 371	63.34 459	88.65 331

WR-MVS_H		78.51 255	78.49 229	78.56 349	88.02 207	56.38 408	88.43 154	92.67 74	77.14 69	73.89 329	87.55 275	66.25 149	89.24 356	58.92 373	73.55 403	90.06 278

PLC	70.83 11	78.05 267	76.37 288	83.08 216	91.88 84	67.80 158	88.19 167	89.46 214	64.33 379	69.87 381	88.38 250	53.66 304	93.58 171	58.86 374	82.73 280	87.86 351
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
RPSCF		73.23 354	71.46 354	78.54 350	82.50 388	59.85 360	82.18 355	82.84 384	58.96 437	71.15 366	89.41 222	45.48 407	84.77 415	58.82 375	71.83 417	91.02 233

EU-MVSNet		68.53 410	67.61 407	71.31 439	78.51 443	47.01 478	84.47 299	84.27 356	42.27 487	66.44 430	84.79 351	40.44 439	83.76 421	58.76 376	68.54 434	83.17 444

pmmvs-eth3d		70.50 387	67.83 402	78.52 352	77.37 457	66.18 198	81.82 358	81.51 399	58.90 438	63.90 451	80.42 422	42.69 424	86.28 397	58.56 377	65.30 455	83.11 446

TAMVS		78.89 246	77.51 261	83.03 219	87.80 218	67.79 159	84.72 289	85.05 346	67.63 326	76.75 262	87.70 269	62.25 205	90.82 322	58.53 378	87.13 194	90.49 255

WBMVS		73.43 344	72.81 340	75.28 397	87.91 212	50.99 462	78.59 416	81.31 403	65.51 360	74.47 323	84.83 349	46.39 391	86.68 392	58.41 379	77.86 340	88.17 345

ACMH+	68.96 14	76.01 312	74.01 323	82.03 257	88.60 181	65.31 228	88.86 131	87.55 292	70.25 272	67.75 407	87.47 278	41.27 434	93.19 207	58.37 380	75.94 370	87.60 356

tpm		72.37 366	71.71 351	74.35 408	82.19 393	52.00 450	79.22 404	77.29 447	64.56 374	72.95 343	83.68 379	51.35 335	83.26 429	58.33 381	75.80 371	87.81 352

BH-w/o		78.21 261	77.33 265	80.84 289	88.81 169	65.13 232	84.87 286	87.85 286	69.75 285	74.52 322	84.74 352	61.34 224	93.11 212	58.24 382	85.84 225	84.27 432

Vis-MVSNet (Re-imp)		78.36 258	78.45 230	78.07 361	88.64 180	51.78 455	86.70 227	79.63 427	74.14 170	75.11 309	90.83 171	61.29 226	89.75 346	58.10 383	91.60 100	92.69 167

MVP-Stereo		76.12 309	74.46 319	81.13 282	85.37 309	69.79 96	84.42 306	87.95 282	65.03 369	67.46 412	85.33 337	53.28 309	91.73 274	58.01 384	83.27 273	81.85 459
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ambc				75.24 398	73.16 479	50.51 465	63.05 495	87.47 295		64.28 446	77.81 449	17.80 496	89.73 347	57.88 385	60.64 470	85.49 414

TR-MVS		77.44 283	76.18 289	81.20 279	88.24 194	63.24 292	84.61 296	86.40 326	67.55 328	77.81 237	86.48 310	54.10 299	93.15 209	57.75 386	82.72 281	87.20 374

F-COLMAP		76.38 307	74.33 321	82.50 245	89.28 151	66.95 189	88.41 156	89.03 242	64.05 383	66.83 421	88.61 243	46.78 388	92.89 222	57.48 387	78.55 330	87.67 354

EG-PatchMatch MVS		74.04 336	71.82 350	80.71 292	84.92 321	67.42 171	85.86 259	88.08 275	66.04 350	64.22 447	83.85 371	35.10 466	92.56 236	57.44 388	80.83 303	82.16 457

PatchmatchNet		73.12 355	71.33 357	78.49 353	83.18 365	60.85 344	79.63 398	78.57 436	64.13 380	71.73 358	79.81 432	51.20 341	85.97 401	57.40 389	76.36 367	88.66 330
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DTE-MVSNet		76.99 291	76.80 275	77.54 374	86.24 286	53.06 447	87.52 189	90.66 170	77.08 73	72.50 348	88.67 241	60.48 242	89.52 350	57.33 390	70.74 423	90.05 279

UnsupCasMVSNet_eth		67.33 418	65.99 422	71.37 436	73.48 476	51.47 458	75.16 447	85.19 342	65.20 364	60.78 463	80.93 419	42.35 425	77.20 460	57.12 391	53.69 483	85.44 416

pmmvs5		71.55 374	70.20 378	75.61 390	77.83 450	56.39 407	81.74 360	80.89 405	57.76 448	67.46 412	84.49 353	49.26 370	85.32 410	57.08 392	75.29 385	85.11 423

testing3-2		75.12 326	75.19 308	74.91 401	90.40 110	45.09 486	80.29 389	78.42 437	78.37 41	76.54 269	87.75 267	44.36 413	87.28 388	57.04 393	83.49 268	92.37 182

Anonymous20240521		68.80 406	67.22 414	73.55 417	74.33 469	54.11 435	83.18 338	85.61 338	58.15 444	61.68 460	80.94 417	30.71 476	81.27 443	57.00 394	73.34 407	85.28 418

mvsany_test1		62.30 441	61.26 445	65.41 464	69.52 488	54.86 429	66.86 482	49.78 504	46.65 481	68.50 398	83.21 387	49.15 371	66.28 496	56.93 395	60.77 469	75.11 480

TransMVSNet (Re)		75.39 323	74.56 316	77.86 364	85.50 306	57.10 396	86.78 224	86.09 333	72.17 219	71.53 361	87.34 279	63.01 192	89.31 354	56.84 396	61.83 465	87.17 376

tt0320-xc		70.11 392	67.45 410	78.07 361	85.33 310	59.51 366	83.28 336	78.96 434	58.77 439	67.10 418	80.28 425	36.73 460	87.42 386	56.83 397	59.77 473	87.29 371

test_vis3_rt		49.26 461	47.02 463	56.00 476	54.30 504	45.27 485	66.76 484	48.08 505	36.83 494	44.38 493	53.20 503	7.17 509	64.07 498	56.77 398	55.66 478	58.65 495

EPMVS		69.02 404	68.16 393	71.59 434	79.61 433	49.80 469	77.40 430	66.93 484	62.82 400	70.01 376	79.05 437	45.79 401	77.86 458	56.58 399	75.26 386	87.13 379

KD-MVS_self_test		68.81 405	67.59 408	72.46 429	74.29 470	45.45 481	77.93 425	87.00 311	63.12 392	63.99 450	78.99 441	42.32 426	84.77 415	56.55 400	64.09 458	87.16 378

tpm2		73.26 352	71.46 354	78.63 345	83.34 358	56.71 402	80.65 382	80.40 417	56.63 457	73.55 334	82.02 408	51.80 331	91.24 300	56.35 401	78.42 336	87.95 348

LTVRE_ROB	69.57 13	76.25 308	74.54 317	81.41 271	88.60 181	64.38 261	79.24 403	89.12 240	70.76 253	69.79 383	87.86 266	49.09 372	93.20 205	56.21 402	80.16 312	86.65 393
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
ACMH	67.68 16	75.89 313	73.93 325	81.77 263	88.71 178	66.61 192	88.62 147	89.01 244	69.81 281	66.78 422	86.70 300	41.95 431	91.51 289	55.64 403	78.14 339	87.17 376
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		66.51 425	64.71 427	71.90 432	81.45 406	63.52 285	57.98 498	68.95 480	53.57 467	62.59 457	76.70 455	46.22 396	75.29 479	55.25 404	79.68 317	76.88 477

tt0320		70.49 388	68.03 396	77.89 363	84.78 324	59.12 368	83.55 328	80.44 415	58.13 445	67.43 414	80.41 423	39.26 447	87.54 385	55.12 405	63.18 461	86.99 383

dtuonlycased		68.45 412	67.29 413	71.92 431	80.18 423	54.90 428	79.76 397	80.38 418	60.11 426	62.57 458	76.44 459	49.34 367	82.31 434	55.05 406	61.77 466	78.53 473

UBG		73.08 356	72.27 347	75.51 393	88.02 207	51.29 460	78.35 420	77.38 446	65.52 358	73.87 330	82.36 401	45.55 404	86.48 395	55.02 407	84.39 250	88.75 327

EPNet_dtu		75.46 319	74.86 311	77.23 378	82.57 387	54.60 431	86.89 218	83.09 376	71.64 226	66.25 431	85.86 323	55.99 282	88.04 378	54.92 408	86.55 205	89.05 312
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsany_test3		53.99 452	51.45 457	61.61 469	55.51 503	44.74 488	63.52 493	45.41 508	43.69 486	58.11 474	76.45 457	17.99 495	63.76 499	54.77 409	47.59 490	76.34 478

PVSNet	64.34 18	72.08 372	70.87 367	75.69 389	86.21 287	56.44 406	74.37 455	80.73 408	62.06 411	70.17 374	82.23 405	42.86 423	83.31 428	54.77 409	84.45 248	87.32 370

ITE_SJBPF				78.22 356	81.77 400	60.57 351		83.30 370	69.25 297	67.54 409	87.20 285	36.33 463	87.28 388	54.34 411	74.62 393	86.80 388

SSC-MVS3.2		73.35 350	73.39 332	73.23 419	85.30 311	49.01 471	74.58 453	81.57 398	75.21 135	73.68 332	85.58 331	52.53 311	82.05 437	54.33 412	77.69 344	88.63 332

MDTV_nov1_ep13_2view						37.79 500	75.16 447		55.10 463	66.53 426		49.34 367		53.98 413		87.94 349

gg-mvs-nofinetune		69.95 396	67.96 397	75.94 386	83.07 370	54.51 433	77.23 432	70.29 474	63.11 393	70.32 371	62.33 489	43.62 418	88.69 368	53.88 414	87.76 182	84.62 430

PatchMatch-RL		72.38 365	70.90 366	76.80 382	88.60 181	67.38 174	79.53 399	76.17 456	62.75 401	69.36 386	82.00 409	45.51 405	84.89 414	53.62 415	80.58 307	78.12 474

test_f		52.09 457	50.82 458	55.90 477	53.82 506	42.31 495	59.42 497	58.31 500	36.45 495	56.12 482	70.96 481	12.18 501	57.79 503	53.51 416	56.57 477	67.60 488

Patchmtry		70.74 383	69.16 386	75.49 394	80.72 415	54.07 436	74.94 451	80.30 419	58.34 442	70.01 376	81.19 412	52.50 313	86.54 393	53.37 417	71.09 422	85.87 409

USDC		70.33 389	68.37 390	76.21 385	80.60 417	56.23 411	79.19 405	86.49 324	60.89 418	61.29 461	85.47 334	31.78 473	89.47 352	53.37 417	76.21 368	82.94 450

LF4IMVS		64.02 437	62.19 440	69.50 448	70.90 486	53.29 444	76.13 437	77.18 448	52.65 470	58.59 471	80.98 416	23.55 489	76.52 465	53.06 419	66.66 442	78.68 472

PAPM		77.68 279	76.40 287	81.51 268	87.29 255	61.85 324	83.78 319	89.59 210	64.74 372	71.23 364	88.70 239	62.59 198	93.66 170	52.66 420	87.03 196	89.01 314

dmvs_re		71.14 377	70.58 371	72.80 426	81.96 397	59.68 362	75.60 444	79.34 430	68.55 316	69.27 389	80.72 420	49.42 365	76.54 464	52.56 421	77.79 341	82.19 456

CL-MVSNet_self_test		72.37 366	71.46 354	75.09 399	79.49 435	53.53 439	80.76 379	85.01 347	69.12 302	70.51 368	82.05 407	57.92 262	84.13 419	52.27 422	66.00 446	87.60 356

tpm cat1		70.57 385	68.31 391	77.35 376	82.41 391	57.95 381	78.08 422	80.22 421	52.04 471	68.54 397	77.66 450	52.00 324	87.84 381	51.77 423	72.07 416	86.25 397

our_test_3		69.14 403	67.00 415	75.57 391	79.80 430	58.80 369	77.96 424	77.81 440	59.55 431	62.90 456	78.25 446	47.43 380	83.97 420	51.71 424	67.58 440	83.93 438

MDTV_nov1_ep13			69.97 380		83.18 365	53.48 440	77.10 434	80.18 423	60.45 421	69.33 387	80.44 421	48.89 376	86.90 390	51.60 425	78.51 332

myMVS_eth3d28		73.62 341	73.53 331	73.90 415	88.20 195	47.41 476	78.06 423	79.37 429	74.29 166	73.98 328	84.29 360	44.67 409	83.54 425	51.47 426	87.39 188	90.74 244

JIA-IIPM		66.32 427	62.82 439	76.82 381	77.09 458	61.72 327	65.34 488	75.38 457	58.04 447	64.51 445	62.32 490	42.05 430	86.51 394	51.45 427	69.22 430	82.21 455

testing222		74.04 336	72.66 342	78.19 357	87.89 213	55.36 422	81.06 374	79.20 432	71.30 237	74.65 320	83.57 382	39.11 449	88.67 369	51.43 428	85.75 227	90.53 253

MSDG		73.36 349	70.99 364	80.49 297	84.51 332	65.80 211	80.71 381	86.13 332	65.70 355	65.46 437	83.74 375	44.60 410	90.91 319	51.13 429	76.89 352	84.74 428

PatchT		68.46 411	67.85 400	70.29 444	80.70 416	43.93 489	72.47 460	74.88 460	60.15 425	70.55 367	76.57 456	49.94 358	81.59 439	50.58 430	74.83 391	85.34 417

GG-mvs-BLEND				75.38 396	81.59 403	55.80 417	79.32 402	69.63 476		67.19 416	73.67 474	43.24 420	88.90 366	50.41 431	84.50 244	81.45 461

KD-MVS_2432*1600		66.22 428	63.89 431	73.21 420	75.47 467	53.42 441	70.76 468	84.35 353	64.10 381	66.52 427	78.52 443	34.55 467	84.98 412	50.40 432	50.33 488	81.23 462

miper_refine_blended		66.22 428	63.89 431	73.21 420	75.47 467	53.42 441	70.76 468	84.35 353	64.10 381	66.52 427	78.52 443	34.55 467	84.98 412	50.40 432	50.33 488	81.23 462

AllTest		70.96 379	68.09 395	79.58 329	85.15 315	63.62 276	84.58 297	79.83 424	62.31 407	60.32 466	86.73 294	32.02 471	88.96 364	50.28 434	71.57 419	86.15 400

TestCases				79.58 329	85.15 315	63.62 276		79.83 424	62.31 407	60.32 466	86.73 294	32.02 471	88.96 364	50.28 434	71.57 419	86.15 400

TAPA-MVS	73.13 9	79.15 237	77.94 242	82.79 235	89.59 132	62.99 302	88.16 169	91.51 144	65.77 354	77.14 256	91.09 162	60.91 233	93.21 202	50.26 436	87.05 195	92.17 196
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
YYNet1		65.03 432	62.91 437	71.38 435	75.85 463	56.60 404	69.12 476	74.66 464	57.28 454	54.12 483	77.87 448	45.85 400	74.48 481	49.95 437	61.52 468	83.05 447

MDA-MVSNet_test_wron		65.03 432	62.92 436	71.37 436	75.93 460	56.73 400	69.09 477	74.73 462	57.28 454	54.03 484	77.89 447	45.88 399	74.39 482	49.89 438	61.55 467	82.99 449

tpmvs		71.09 378	69.29 384	76.49 383	82.04 395	56.04 413	78.92 411	81.37 402	64.05 383	67.18 417	78.28 445	49.74 362	89.77 345	49.67 439	72.37 411	83.67 440

SD_0403		74.65 329	74.77 313	74.29 409	86.20 288	47.42 475	83.71 321	85.12 343	69.30 294	68.50 398	87.95 265	59.40 250	86.05 399	49.38 440	83.35 271	89.40 301

ppachtmachnet_test		70.04 393	67.34 412	78.14 358	79.80 430	61.13 335	79.19 405	80.59 410	59.16 435	65.27 439	79.29 436	46.75 389	87.29 387	49.33 441	66.72 441	86.00 406

UnsupCasMVSNet_bld		63.70 438	61.53 444	70.21 445	73.69 474	51.39 459	72.82 459	81.89 394	55.63 462	57.81 475	71.80 478	38.67 451	78.61 453	49.26 442	52.21 486	80.63 466

UWE-MVS		72.13 371	71.49 353	74.03 413	86.66 278	47.70 473	81.40 369	76.89 451	63.60 389	75.59 287	84.22 364	39.94 442	85.62 405	48.98 443	86.13 215	88.77 326

dp		66.80 422	65.43 423	70.90 443	79.74 432	48.82 472	75.12 449	74.77 461	59.61 430	64.08 449	77.23 453	42.89 422	80.72 446	48.86 444	66.58 443	83.16 445

FMVSNet5		69.50 400	67.96 397	74.15 411	82.97 378	55.35 423	80.01 394	82.12 393	62.56 404	63.02 453	81.53 411	36.92 459	81.92 438	48.42 445	74.06 397	85.17 422

thres100view900		76.50 299	75.55 298	79.33 334	89.52 135	56.99 397	85.83 261	83.23 372	73.94 175	76.32 274	87.12 288	51.89 329	91.95 263	48.33 446	83.75 260	89.07 307

tfpn200view9		76.42 305	75.37 303	79.55 331	89.13 158	57.65 388	85.17 276	83.60 364	73.41 192	76.45 270	86.39 312	52.12 319	91.95 263	48.33 446	83.75 260	89.07 307

thres400		76.50 299	75.37 303	79.86 316	89.13 158	57.65 388	85.17 276	83.60 364	73.41 192	76.45 270	86.39 312	52.12 319	91.95 263	48.33 446	83.75 260	90.00 280

LCM-MVSNet		54.25 451	49.68 461	67.97 459	53.73 507	45.28 484	66.85 483	80.78 407	35.96 496	39.45 498	62.23 491	8.70 506	78.06 457	48.24 449	51.20 487	80.57 467

RPMNet		73.51 343	70.49 373	82.58 244	81.32 411	65.19 230	75.92 440	92.27 96	57.60 450	72.73 345	76.45 457	52.30 316	95.43 78	48.14 450	77.71 342	87.11 380

thres600view7		76.50 299	75.44 299	79.68 326	89.40 143	57.16 394	85.53 270	83.23 372	73.79 179	76.26 275	87.09 289	51.89 329	91.89 267	48.05 451	83.72 263	90.00 280

TDRefinement		67.49 416	64.34 428	76.92 380	73.47 477	61.07 338	84.86 287	82.98 380	59.77 429	58.30 473	85.13 343	26.06 482	87.89 380	47.92 452	60.59 471	81.81 460

thres200		75.55 317	74.47 318	78.82 343	87.78 221	57.85 383	83.07 344	83.51 367	72.44 214	75.84 284	84.42 355	52.08 322	91.75 272	47.41 453	83.64 265	86.86 386

PVSNet_0	57.27 20	61.67 443	59.27 446	68.85 452	79.61 433	57.44 392	68.01 478	73.44 467	55.93 461	58.54 472	70.41 482	44.58 411	77.55 459	47.01 454	35.91 496	71.55 485

DP-MVS		76.78 295	74.57 315	83.42 198	93.29 52	69.46 105	88.55 151	83.70 363	63.98 385	70.20 372	88.89 235	54.01 302	94.80 114	46.66 455	81.88 291	86.01 404

COLMAP_ROB	66.92 17	73.01 357	70.41 375	80.81 290	87.13 259	65.63 215	88.30 164	84.19 358	62.96 396	63.80 452	87.69 270	38.04 455	92.56 236	46.66 455	74.91 390	84.24 433
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet		70.69 384	69.30 383	74.88 402	84.52 331	56.35 410	75.87 442	79.42 428	64.59 373	67.76 406	82.41 400	41.10 435	81.54 440	46.64 457	81.34 295	86.75 390

LS3D		76.95 293	74.82 312	83.37 201	90.45 108	67.36 175	89.15 121	86.94 313	61.87 413	69.52 384	90.61 181	51.71 333	94.53 125	46.38 458	86.71 203	88.21 344

ETVMVS		72.25 369	71.05 363	75.84 387	87.77 223	51.91 452	79.39 401	74.98 459	69.26 296	73.71 331	82.95 392	40.82 438	86.14 398	46.17 459	84.43 249	89.47 299

MDA-MVSNet-bldmvs		66.68 423	63.66 433	75.75 388	79.28 438	60.56 352	73.92 457	78.35 438	64.43 375	50.13 489	79.87 431	44.02 416	83.67 422	46.10 460	56.86 475	83.03 448

new-patchmatchnet		61.73 442	61.73 442	61.70 468	72.74 483	24.50 513	69.16 475	78.03 439	61.40 415	56.72 478	75.53 469	38.42 452	76.48 466	45.95 461	57.67 474	84.13 435

ArgMatch-SfM		44.04 467	39.87 471	56.58 475	50.92 510	36.22 501	59.86 496	27.68 514	33.67 499	42.15 495	71.07 480	3.10 513	59.10 501	45.79 462	24.54 503	74.41 481

WB-MVSnew		71.96 373	71.65 352	72.89 425	84.67 330	51.88 453	82.29 353	77.57 442	62.31 407	73.67 333	83.00 391	53.49 307	81.10 444	45.75 463	82.13 287	85.70 411

TinyColmap		67.30 419	64.81 426	74.76 404	81.92 399	56.68 403	80.29 389	81.49 400	60.33 422	56.27 481	83.22 386	24.77 486	87.66 384	45.52 464	69.47 428	79.95 469

pmmvs3		57.79 447	54.26 452	68.37 455	64.02 497	56.72 401	75.12 449	65.17 488	40.20 489	52.93 485	69.86 483	20.36 493	75.48 476	45.45 465	55.25 482	72.90 484

OpenMVS_ROB	64.09 19	70.56 386	68.19 392	77.65 370	80.26 420	59.41 367	85.01 283	82.96 381	58.76 440	65.43 438	82.33 402	37.63 457	91.23 301	45.34 466	76.03 369	82.32 454

test0.0.03 1		68.00 415	67.69 405	68.90 451	77.55 455	47.43 474	75.70 443	72.95 470	66.66 339	66.56 425	82.29 404	48.06 378	75.87 473	44.97 467	74.51 394	83.41 442

testgi		66.67 424	66.53 420	67.08 461	75.62 465	41.69 496	75.93 439	76.50 452	66.11 348	65.20 442	86.59 304	35.72 465	74.71 480	43.71 468	73.38 406	84.84 427

Anonymous20231206		68.60 407	67.80 403	71.02 441	80.23 422	50.75 464	78.30 421	80.47 413	56.79 456	66.11 433	82.63 399	46.35 394	78.95 452	43.62 469	75.70 372	83.36 443

FE-MVSNET		67.25 420	65.33 424	73.02 424	75.86 462	52.54 448	80.26 391	80.56 411	63.80 388	60.39 464	79.70 433	41.41 433	84.66 417	43.34 470	62.62 463	81.86 458

tfpnnormal		74.39 330	73.16 336	78.08 360	86.10 292	58.05 377	84.65 293	87.53 293	70.32 269	71.22 365	85.63 329	54.97 288	89.86 343	43.03 471	75.02 389	86.32 396

MIMVSNet1		68.58 408	66.78 419	73.98 414	80.07 425	51.82 454	80.77 378	84.37 352	64.40 377	59.75 469	82.16 406	36.47 462	83.63 423	42.73 472	70.33 425	86.48 395

usedtu_dtu_shiyan2		64.75 435	61.63 443	74.10 412	70.64 487	53.18 446	82.10 357	81.27 404	56.22 460	56.39 480	74.67 471	27.94 480	83.56 424	42.71 473	62.73 462	85.57 413

ttmdpeth		59.91 445	57.10 449	68.34 456	67.13 493	46.65 480	74.64 452	67.41 483	48.30 479	62.52 459	85.04 347	20.40 492	75.93 472	42.55 474	45.90 494	82.44 453

test20.03		67.45 417	66.95 416	68.94 450	75.48 466	44.84 487	77.50 429	77.67 441	66.66 339	63.01 454	83.80 373	47.02 384	78.40 454	42.53 475	68.86 433	83.58 441

ADS-MVSNet2		66.20 430	63.33 434	74.82 403	79.92 426	58.75 370	67.55 480	75.19 458	53.37 468	65.25 440	75.86 466	42.32 426	80.53 447	41.57 476	68.91 431	85.18 420

ADS-MVSNet		64.36 436	62.88 438	68.78 453	79.92 426	47.17 477	67.55 480	71.18 472	53.37 468	65.25 440	75.86 466	42.32 426	73.99 485	41.57 476	68.91 431	85.18 420

Patchmatch-test		64.82 434	63.24 435	69.57 447	79.42 436	49.82 468	63.49 494	69.05 479	51.98 473	59.95 468	80.13 427	50.91 343	70.98 489	40.66 478	73.57 402	87.90 350

MVS-HIRNet		59.14 446	57.67 448	63.57 466	81.65 401	43.50 490	71.73 462	65.06 489	39.59 491	51.43 486	57.73 497	38.34 453	82.58 433	39.53 479	73.95 398	64.62 491

WAC-MVS						42.58 492								39.46 480

myMVS_eth3d		67.02 421	66.29 421	69.21 449	84.68 327	42.58 492	78.62 414	73.08 468	66.65 342	66.74 423	79.46 434	31.53 474	82.30 435	39.43 481	76.38 365	82.75 451

DSMNet-mixed		57.77 448	56.90 450	60.38 470	67.70 491	35.61 502	69.18 474	53.97 502	32.30 501	57.49 476	79.88 430	40.39 440	68.57 495	38.78 482	72.37 411	76.97 476

N_pmnet		52.79 456	53.26 454	51.40 483	78.99 440	7.68 527	69.52 472	3.89 527	51.63 474	57.01 477	74.98 470	40.83 437	65.96 497	37.78 483	64.67 456	80.56 468

testing3		68.56 409	67.67 406	71.22 440	87.33 250	42.87 491	83.06 345	71.54 471	70.36 266	69.08 390	84.38 357	30.33 477	85.69 404	37.50 484	75.45 380	85.09 424

MVStest1		56.63 449	52.76 455	68.25 457	61.67 499	53.25 445	71.67 463	68.90 481	38.59 492	50.59 488	83.05 390	25.08 484	70.66 490	36.76 485	38.56 495	80.83 465

test_0402		72.79 363	70.44 374	79.84 317	88.13 201	65.99 204	85.93 256	84.29 355	65.57 357	67.40 415	85.49 333	46.92 385	92.61 232	35.88 486	74.38 395	80.94 464

new_pmnet		50.91 459	50.29 459	52.78 482	68.58 490	34.94 504	63.71 492	56.63 501	39.73 490	44.95 492	65.47 488	21.93 491	58.48 502	34.98 487	56.62 476	64.92 490

APD_test1		53.31 455	49.93 460	63.42 467	65.68 494	50.13 466	71.59 464	66.90 485	34.43 497	40.58 497	71.56 479	8.65 507	76.27 468	34.64 488	55.36 480	63.86 492

Syy-MVS		68.05 414	67.85 400	68.67 454	84.68 327	40.97 497	78.62 414	73.08 468	66.65 342	66.74 423	79.46 434	52.11 321	82.30 435	32.89 489	76.38 365	82.75 451

dmvs_testset		62.63 440	64.11 430	58.19 472	78.55 442	24.76 512	75.28 445	65.94 487	67.91 325	60.34 465	76.01 465	53.56 305	73.94 486	31.79 490	67.65 439	75.88 479

UWE-MVS-28		65.32 431	64.93 425	66.49 462	78.70 441	38.55 499	77.86 427	64.39 491	62.00 412	64.13 448	83.60 380	41.44 432	76.00 471	31.39 491	80.89 301	84.92 425

ANet_high		50.57 460	46.10 464	63.99 465	48.67 511	39.13 498	70.99 467	80.85 406	61.39 416	31.18 500	57.70 498	17.02 497	73.65 487	31.22 492	15.89 510	79.18 471

EGC-MVSNET		52.07 458	47.05 462	67.14 460	83.51 355	60.71 348	80.50 385	67.75 482	0.07 545	0.43 546	75.85 468	24.26 487	81.54 440	28.82 493	62.25 464	59.16 494

PMMVS2		40.82 468	38.86 472	46.69 484	53.84 505	16.45 520	48.61 501	49.92 503	37.49 493	31.67 499	60.97 492	8.14 508	56.42 504	28.42 494	30.72 500	67.19 489

tmp_tt		18.61 481	21.40 483	10.23 503	4.82 547	10.11 522	34.70 506	30.74 513	1.48 523	23.91 508	26.07 517	28.42 479	13.41 521	27.12 495	15.35 511	7.17 523

test_method		31.52 472	29.28 475	38.23 489	27.03 521	6.50 530	20.94 512	62.21 494	4.05 519	22.35 510	52.50 504	13.33 499	47.58 507	27.04 496	34.04 498	60.62 493

DenseAffine		31.97 470	28.22 476	43.21 487	43.10 513	27.10 507	46.21 502	11.36 518	24.92 504	27.70 503	58.81 496	1.09 517	46.50 510	26.95 497	13.85 513	56.02 497

PDCNetPlus		24.75 478	22.46 482	31.64 495	35.53 516	17.00 519	32.00 509	9.46 519	18.43 509	18.56 514	51.31 505	1.65 515	33.00 515	26.51 498	8.70 518	44.91 506

RoMa-SfM		28.67 475	25.38 479	38.54 488	32.61 518	22.48 514	40.24 503	7.23 522	21.81 507	26.66 505	60.46 495	0.96 518	41.72 511	26.47 499	11.95 514	51.40 501

testf1		45.72 462	41.96 466	57.00 473	56.90 501	45.32 482	66.14 485	59.26 498	26.19 502	30.89 501	60.96 493	4.14 510	70.64 491	26.39 500	46.73 492	55.04 498

APD_test2		45.72 462	41.96 466	57.00 473	56.90 501	45.32 482	66.14 485	59.26 498	26.19 502	30.89 501	60.96 493	4.14 510	70.64 491	26.39 500	46.73 492	55.04 498

FPMVS		53.68 454	51.64 456	59.81 471	65.08 495	51.03 461	69.48 473	69.58 477	41.46 488	40.67 496	72.32 477	16.46 498	70.00 493	24.24 502	65.42 454	58.40 496

DKM		25.67 477	23.01 481	33.64 494	32.08 519	19.25 518	37.50 505	5.52 524	18.67 508	23.58 509	55.44 502	0.64 523	34.02 513	23.95 503	9.73 516	47.66 504

Gipuma		45.18 465	41.86 468	55.16 480	77.03 459	51.52 457	32.50 508	80.52 412	32.46 500	27.12 504	35.02 513	9.52 505	75.50 475	22.31 504	60.21 472	38.45 508
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
dongtai		45.42 464	45.38 465	45.55 485	73.36 478	26.85 510	67.72 479	34.19 510	54.15 466	49.65 490	56.41 501	25.43 483	62.94 500	19.45 505	28.09 501	46.86 505

DeepMVS_CX				27.40 497	40.17 515	26.90 509		24.59 515	17.44 511	23.95 507	48.61 508	9.77 504	26.48 516	18.06 506	24.47 504	28.83 513

WB-MVS		54.94 450	54.72 451	55.60 479	73.50 475	20.90 515	74.27 456	61.19 495	59.16 435	50.61 487	74.15 472	47.19 383	75.78 474	17.31 507	35.07 497	70.12 486

PMVS	37.38 22	44.16 466	40.28 470	55.82 478	40.82 514	42.54 494	65.12 489	63.99 492	34.43 497	24.48 506	57.12 499	3.92 512	76.17 470	17.10 508	55.52 479	48.75 502
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 474	25.89 478	43.81 486	44.55 512	35.46 503	28.87 511	39.07 509	18.20 510	18.58 513	40.18 511	2.68 514	47.37 508	17.07 509	23.78 505	48.60 503
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SSC-MVS		53.88 453	53.59 453	54.75 481	72.87 482	19.59 516	73.84 458	60.53 497	57.58 451	49.18 491	73.45 475	46.34 395	75.47 477	16.20 510	32.28 499	69.20 487

E-PMN		31.77 471	30.64 473	35.15 492	52.87 508	27.67 506	57.09 499	47.86 506	24.64 505	16.40 516	33.05 514	11.23 503	54.90 505	14.46 511	18.15 508	22.87 514

LoFTR		27.52 476	24.27 480	37.29 491	34.75 517	19.27 517	33.78 507	21.60 516	12.42 512	21.61 511	56.59 500	0.91 519	40.37 512	13.94 512	22.80 506	52.22 500

PMatch-SfM		14.15 484	12.67 487	18.59 501	12.84 526	7.03 528	17.41 513	2.28 531	6.63 515	12.96 518	43.56 510	0.09 546	16.11 520	13.90 513	4.38 529	32.63 512

EMVS		30.81 473	29.65 474	34.27 493	50.96 509	25.95 511	56.58 500	46.80 507	24.01 506	15.53 517	30.68 516	12.47 500	54.43 506	12.81 514	17.05 509	22.43 515

kuosan		39.70 469	40.40 469	37.58 490	64.52 496	26.98 508	65.62 487	33.02 511	46.12 482	42.79 494	48.99 506	24.10 488	46.56 509	12.16 515	26.30 502	39.20 507

MASt3R-SfM		13.55 485	13.93 486	12.41 502	10.54 530	5.97 531	16.61 514	6.07 523	4.50 517	16.53 515	48.67 507	0.73 521	9.44 522	11.56 516	10.18 515	21.81 516

wuyk23d		16.82 482	15.94 485	19.46 500	58.74 500	31.45 505	39.22 504	3.74 529	6.84 514	6.04 521	2.70 545	1.27 516	24.29 518	10.54 517	14.40 512	2.63 528

ELoFTR		14.23 483	11.56 488	22.24 498	11.02 527	6.56 529	13.59 517	7.57 521	5.55 516	11.96 520	39.09 512	0.21 534	24.93 517	9.43 518	5.66 523	35.22 510

MatchFormer		22.13 479	19.86 484	28.93 496	28.66 520	15.74 521	31.91 510	17.10 517	7.75 513	18.87 512	47.50 509	0.62 525	33.92 514	7.49 519	18.87 507	37.14 509

GLUNet-SfM		12.90 486	10.00 489	21.62 499	13.58 525	8.30 525	10.19 519	9.30 520	4.31 518	12.18 519	30.90 515	0.50 529	22.76 519	4.89 520	4.14 530	33.79 511

SP-DiffGlue		4.29 495	4.46 498	3.77 511	3.68 548	2.12 538	5.97 524	2.22 532	1.10 524	4.89 524	13.93 522	0.66 522	1.95 532	2.47 521	5.24 524	7.22 522

XFeat-MNN		4.39 494	4.49 497	4.10 507	2.88 549	1.91 544	5.86 525	2.57 530	1.06 525	5.04 523	13.99 521	0.43 532	4.47 526	2.00 522	6.55 521	5.92 526

XFeat-NN		3.78 500	3.96 503	3.23 513	2.65 550	1.53 549	4.99 526	1.92 536	0.81 530	4.77 526	12.37 524	0.38 533	3.39 527	1.64 523	6.13 522	4.77 527

SP-LightGlue		4.27 496	4.41 499	3.86 508	10.99 528	1.99 541	8.19 520	2.06 534	0.98 527	2.37 529	8.29 525	0.56 527	2.10 529	1.27 524	4.99 525	7.48 519

SP-SuperGlue		4.24 497	4.38 500	3.81 510	10.75 529	2.00 540	8.18 521	2.09 533	1.00 526	2.41 528	8.29 525	0.56 527	2.05 531	1.27 524	4.91 526	7.39 520

SP-NN		4.00 499	4.12 502	3.63 512	9.92 532	1.81 546	7.94 523	1.90 537	0.86 528	2.15 531	8.00 528	0.50 529	2.09 530	1.20 526	4.63 528	6.98 524

SP-MNN		4.14 498	4.24 501	3.82 509	10.32 531	1.83 545	8.11 522	1.99 535	0.82 529	2.23 530	8.27 527	0.47 531	2.14 528	1.20 526	4.77 527	7.49 518

ALIKED-LG		8.61 487	8.70 491	8.33 504	20.63 522	8.70 524	15.50 515	4.61 525	2.19 520	5.84 522	18.70 518	0.80 520	8.06 523	1.03 528	8.97 517	8.25 517

ALIKED-MNN		7.86 488	7.83 494	7.97 505	19.40 523	8.86 523	14.48 516	3.90 526	1.59 521	4.74 527	16.49 519	0.59 526	7.65 524	0.91 529	8.34 520	7.39 520

ALIKED-NN		7.51 489	7.61 495	7.21 506	18.26 524	8.10 526	13.45 518	3.88 528	1.50 522	4.87 525	16.47 520	0.64 523	7.00 525	0.88 530	8.50 519	6.52 525

SIFT-NN		2.77 501	2.92 504	2.34 514	8.70 533	3.08 532	4.46 527	1.01 539	0.68 531	1.46 532	5.49 529	0.16 535	1.65 533	0.26 531	4.04 531	2.27 529

SIFT-MNN		2.63 502	2.75 505	2.25 515	8.10 534	2.84 533	4.08 528	1.02 538	0.68 531	1.28 533	5.34 532	0.15 536	1.64 534	0.26 531	3.88 533	2.27 529

testmvs		6.04 492	8.02 493	0.10 529	0.08 551	0.03 554	69.74 471	0.04 552	0.05 546	0.31 547	1.68 546	0.02 551	0.04 547	0.24 533	0.02 545	0.25 544

SIFT-NN-UMatch		2.26 506	2.39 509	1.89 520	6.21 542	2.08 539	3.76 530	0.83 542	0.66 533	1.04 537	5.09 533	0.14 537	1.52 537	0.23 534	3.51 535	2.07 533

SIFT-NN-NCMNet		2.52 503	2.64 506	2.14 516	7.53 536	2.74 534	4.00 529	0.98 540	0.65 534	1.24 535	5.08 535	0.14 537	1.60 535	0.23 534	3.94 532	2.07 533

SIFT-NN-CMatch		2.31 505	2.41 508	2.00 518	6.59 540	2.34 537	3.48 532	0.83 542	0.65 534	1.28 533	5.09 533	0.14 537	1.52 537	0.23 534	3.41 536	2.14 531

SIFT-UMatch		2.16 508	2.30 511	1.72 522	6.99 538	1.97 543	3.32 533	0.70 546	0.64 538	0.91 539	4.86 537	0.12 543	1.49 540	0.22 537	2.97 539	1.72 538

SIFT-ConvMatch		2.25 507	2.37 510	1.90 519	7.29 537	2.37 536	3.21 535	0.75 544	0.65 534	1.03 538	4.91 536	0.12 543	1.51 539	0.22 537	3.13 538	1.81 536

SIFT-NN-PointCN		2.07 509	2.18 512	1.74 521	5.75 543	1.65 548	3.27 534	0.73 545	0.60 541	1.07 536	4.62 539	0.13 540	1.43 541	0.21 539	3.22 537	2.12 532

test123		6.12 491	8.11 492	0.14 528	0.06 552	0.09 553	71.05 466	0.03 553	0.04 547	0.25 548	1.30 547	0.05 550	0.03 548	0.21 539	0.01 546	0.29 543

SIFT-UM-Cal		1.97 511	2.12 514	1.52 524	6.57 541	1.67 547	2.93 536	0.57 549	0.62 540	0.83 542	4.55 540	0.11 545	1.37 543	0.20 541	2.69 541	1.53 541

SIFT-NCM-Cal		2.40 504	2.52 507	2.05 517	7.74 535	2.54 535	3.75 531	0.84 541	0.65 534	0.89 540	4.78 538	0.13 540	1.60 535	0.19 542	3.71 534	2.01 535

SIFT-CM-Cal		2.02 510	2.13 513	1.67 523	6.79 539	1.99 541	2.79 537	0.64 547	0.63 539	0.87 541	4.48 541	0.13 540	1.41 542	0.19 542	2.70 540	1.61 540

SIFT-PCN-Cal		1.72 512	1.82 516	1.39 525	5.64 544	1.19 551	2.39 539	0.53 550	0.55 543	0.72 543	3.90 542	0.09 546	1.22 545	0.17 544	2.42 543	1.76 537

SIFT-PointCN		1.72 512	1.83 515	1.36 526	5.55 545	1.22 550	2.59 538	0.59 548	0.55 543	0.71 544	3.77 543	0.08 548	1.24 544	0.17 544	2.48 542	1.63 539

SIFT-NCMNet		1.44 514	1.56 517	1.08 527	5.14 546	1.07 552	1.97 540	0.32 551	0.56 542	0.64 545	3.23 544	0.07 549	1.01 546	0.14 546	1.95 544	1.15 542

mmdepth		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

monomultidepth		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

test_blank		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

uanet_test		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

DCPMVS		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

cdsmvs_eth3d_5k		19.96 480	26.61 477	0.00 530	0.00 553	0.00 555	0.00 541	89.26 228	0.00 548	0.00 549	88.61 243	61.62 217	0.00 549	0.00 547	0.00 547	0.00 545

pcd_1.5k_mvsjas		5.26 493	7.02 496	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	63.15 188	0.00 549	0.00 547	0.00 547	0.00 545

sosnet-low-res		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

sosnet		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

uncertanet		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

Regformer		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

ab-mvs-re		7.23 490	9.64 490	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	86.72 296	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

uanet		0.00 515	0.00 518	0.00 530	0.00 553	0.00 555	0.00 541	0.00 554	0.00 548	0.00 549	0.00 548	0.00 552	0.00 549	0.00 547	0.00 547	0.00 545

TestfortrainingZip				87.28 46	92.85 68	72.05 50	93.28 12	93.32 37	76.52 90	88.91 32	93.52 77	77.30 17	96.67 33		91.98 94	93.13 145

FOURS1					95.00 10	72.39 41	95.06 1	93.84 20	74.49 158	91.30 17

test_one_0601					95.07 7	71.46 60		94.14 9	78.27 42	92.05 13	95.74 8	80.83 12

eth-test2					0.00 553

eth-test					0.00 553

test_241102_ONE					95.30 2	70.98 73		94.06 14	77.17 68	93.10 1	95.39 18	82.99 1	97.27 14

save fliter					93.80 44	72.35 44	90.47 74	91.17 154	74.31 164

test0726					95.27 5	71.25 65	93.60 7	94.11 10	77.33 60	92.81 3	95.79 5	80.98 10

GSMVS																88.96 318

test_part2					95.06 8	72.65 32				91.80 15

sam_mvs1												51.32 336				88.96 318

sam_mvs												50.01 356

MTGPA								92.02 114

test_post											5.46 530	50.36 352	84.24 418

patchmatchnet-post											74.00 473	51.12 342	88.60 370

MTMP							92.18 39	32.83 512

TEST9					93.26 56	72.96 25	88.75 139	91.89 122	68.44 319	85.00 81	93.10 89	74.36 33	95.41 81

test_8					93.13 60	72.57 35	88.68 145	91.84 126	68.69 314	84.87 85	93.10 89	74.43 31	95.16 91

agg_prior					92.85 68	71.94 53		91.78 130		84.41 97			94.93 103

test_prior4						72.60 34	89.01 126

test_prior				86.33 65	92.61 75	69.59 99		92.97 60					95.48 75			93.91 90

新几何2							86.29 247

旧先验1					91.96 81	65.79 212		86.37 327			93.08 93	69.31 102			92.74 80	88.74 329

原ACMM2							86.86 220

test222					91.50 87	68.26 138	84.16 313	83.20 375	54.63 465	79.74 194	91.63 139	58.97 253			91.42 104	86.77 389

segment_acmp												73.08 44

testdata1							84.14 314		75.71 117

test12				86.80 59	92.63 74	70.70 82		91.79 129		82.71 141		71.67 66	96.16 53		94.50 56	93.54 120

plane_prior7					90.08 117	68.51 132

plane_prior6					89.84 126	68.70 126						60.42 243

plane_prior4											91.00 167

plane_prior3						68.60 129			78.44 37	78.92 209

plane_prior2							91.25 60		79.12 29

plane_prior1					89.90 125

plane_prior						68.71 124	90.38 78		77.62 49						86.16 214

n2								0.00 554

nn								0.00 554

door-mid								69.98 475

test11								92.23 100

door								69.44 478

HQP5-MVS						66.98 186

HQP-NCC					89.33 146		89.17 117		76.41 96	77.23 250

ACMP_Plane					89.33 146		89.17 117		76.41 96	77.23 250

HQP4-MVS										77.24 249			95.11 95			91.03 231

HQP3-MVS								92.19 108							85.99 220

HQP2-MVS												60.17 246

NP-MVS					89.62 131	68.32 136					90.24 193

ACMMP++_ref															81.95 290

ACMMP++															81.25 296

Test By Simon												64.33 174

High-resolution multi-view benchmark