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 8	89.23 10	88.97 4	90.79 102	73.65 10	92.66 28	91.17 150	86.57 1	87.39 57	94.97 25	71.70 62	97.68 1	92.19 1	95.63 32	95.57 1

fmvsm_s_conf0.5_n_9		87.39 33	87.95 23	85.70 81	89.48 138	67.88 153	88.59 146	89.05 235	80.19 12	90.70 20	95.40 15	74.56 28	93.92 152	91.54 2	92.07 92	95.31 5

fmvsm_s_conf0.5_n_4		85.39 77	85.75 70	84.30 145	86.70 272	65.83 206	88.77 136	89.78 196	75.46 120	88.35 36	93.73 74	69.19 104	93.06 211	91.30 3	88.44 160	94.02 82

fmvsm_s_conf0.5_n_3		86.36 53	87.46 32	83.09 208	87.08 261	65.21 225	89.09 123	90.21 184	79.67 19	89.98 24	95.02 24	73.17 42	91.71 270	91.30 3	91.60 99	92.34 174

fmvsm_s_conf0.5_n_8		86.56 47	87.17 38	84.73 121	87.76 222	65.62 212	89.20 114	92.21 102	79.94 17	89.74 27	94.86 26	68.63 114	94.20 137	90.83 5	91.39 104	94.38 61

MGCNet		87.69 24	87.55 29	88.12 13	89.45 139	71.76 53	91.47 57	89.54 207	82.14 3	86.65 66	94.28 46	68.28 120	97.46 6	90.81 6	95.31 38	95.15 8

fmvsm_s_conf0.5_n_10		86.38 52	86.76 46	85.24 95	87.33 247	67.30 174	89.50 101	90.98 155	76.25 101	90.56 22	94.75 29	68.38 117	94.24 136	90.80 7	92.32 89	94.19 72

test_fmvsmconf_n		85.92 62	86.04 63	85.57 87	85.03 316	69.51 100	89.62 98	90.58 168	73.42 185	87.75 50	94.02 61	72.85 48	93.24 195	90.37 8	90.75 116	93.96 84

test_fmvsmconf0.1_n		85.61 71	85.65 71	85.50 88	82.99 370	69.39 107	89.65 95	90.29 182	73.31 189	87.77 49	94.15 55	71.72 61	93.23 196	90.31 9	90.67 118	93.89 90

test_fmvsmconf0.01_n		84.73 89	84.52 91	85.34 92	80.25 412	69.03 110	89.47 102	89.65 203	73.24 193	86.98 62	94.27 47	66.62 137	93.23 196	90.26 10	89.95 131	93.78 99

fmvsm_l_conf0.5_n_9		85.84 66	86.63 49	83.46 191	87.12 260	66.01 199	88.56 148	89.43 211	75.59 116	89.32 28	94.32 44	72.89 46	91.21 298	90.11 11	92.33 87	93.16 134

fmvsm_s_conf0.5_n_2		84.04 99	84.11 99	83.81 182	86.17 285	65.00 233	86.96 211	87.28 290	74.35 157	88.25 39	94.23 50	61.82 204	92.60 229	89.85 12	88.09 169	93.84 93

fmvsm_s_conf0.5_n_5		85.22 81	85.55 73	84.25 152	86.26 281	67.40 170	89.18 115	89.31 220	72.50 204	88.31 37	93.86 70	69.66 93	91.96 258	89.81 13	91.05 110	93.38 120

fmvsm_s_conf0.1_n_2		83.80 107	83.79 106	83.83 180	85.62 297	64.94 238	87.03 208	86.62 314	74.32 158	87.97 47	94.33 43	60.67 228	92.60 229	89.72 14	87.79 176	93.96 84

MSC_two_6792asdad				89.16 1	94.34 31	75.53 2		92.99 54					97.53 2	89.67 15	96.44 9	94.41 58

No_MVS				89.16 1	94.34 31	75.53 2		92.99 54					97.53 2	89.67 15	96.44 9	94.41 58

MSP-MVS		89.51 5	89.91 6	88.30 10	94.28 34	73.46 17	92.90 21	94.11 11	80.27 10	91.35 17	94.16 54	78.35 15	96.77 28	89.59 17	94.22 66	94.67 38
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 72	86.20 56	83.60 186	87.32 249	65.13 228	88.86 130	91.63 134	75.41 121	88.23 40	93.45 81	68.56 115	92.47 237	89.52 18	92.78 79	93.20 132

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 31	71.25 64	95.06 1	94.23 7	78.38 38	92.78 4	95.74 6	82.45 3	97.49 4	89.42 19	96.68 2	94.95 12

test_0728_THIRD									78.38 38	92.12 12	95.78 4	81.46 9	97.40 9	89.42 19	96.57 7	94.67 38

APDe-MVS		89.15 9	89.63 8	87.73 31	94.49 22	71.69 54	93.83 4	93.96 18	75.70 114	91.06 19	96.03 1	76.84 17	97.03 21	89.09 21	95.65 31	94.47 57
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 56	86.75 47	84.00 173	87.78 219	66.09 196	89.96 86	90.80 163	77.37 57	86.72 65	94.20 52	72.51 51	92.78 225	89.08 22	92.33 87	93.13 138

DVP-MVS		89.60 3	90.35 3	87.33 45	95.27 5	71.25 64	93.49 10	92.73 69	77.33 58	92.12 12	95.78 4	80.98 11	97.40 9	89.08 22	96.41 12	93.33 124
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 60	93.49 10	94.23 7					97.49 4	89.08 22	96.41 12	94.21 71

SED-MVS		90.08 2	90.85 2	87.77 28	95.30 2	70.98 71	93.57 8	94.06 15	77.24 61	93.10 1	95.72 8	82.99 1	97.44 7	89.07 25	96.63 4	94.88 16

test_241102_TWO								94.06 15	77.24 61	92.78 4	95.72 8	81.26 10	97.44 7	89.07 25	96.58 6	94.26 70

fmvsm_l_conf0.5_n_3		86.02 57	86.32 53	85.14 98	87.20 252	68.54 130	89.57 99	90.44 173	75.31 125	87.49 54	94.39 42	72.86 47	92.72 226	89.04 27	90.56 119	94.16 73

IU-MVS					95.30 2	71.25 64		92.95 60	66.81 326	92.39 6				88.94 28	96.63 4	94.85 21

fmvsm_l_conf0.5_n		84.47 90	84.54 89	84.27 149	85.42 303	68.81 116	88.49 150	87.26 295	68.08 315	88.03 44	93.49 77	72.04 57	91.77 266	88.90 29	89.14 147	92.24 181

fmvsm_s_conf0.5_n		83.80 107	83.71 108	84.07 162	86.69 273	67.31 173	89.46 103	83.07 368	71.09 235	86.96 63	93.70 75	69.02 110	91.47 286	88.79 30	84.62 234	93.44 119

MP-MVS-pluss		87.67 25	87.72 25	87.54 40	93.64 48	72.04 50	89.80 90	93.50 30	75.17 134	86.34 68	95.29 17	70.86 74	96.00 59	88.78 31	96.04 16	94.58 47
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_fmvsmvis_n_1920		84.02 100	83.87 102	84.49 132	84.12 334	69.37 108	88.15 167	87.96 272	70.01 268	83.95 107	93.23 86	68.80 112	91.51 283	88.61 32	89.96 130	92.57 162

SMA-MVS		89.08 10	89.23 10	88.61 6	94.25 35	73.73 9	92.40 29	93.63 26	74.77 147	92.29 7	95.97 2	74.28 33	97.24 16	88.58 33	96.91 1	94.87 18
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
fmvsm_s_conf0.1_n		83.56 118	83.38 117	84.10 156	84.86 318	67.28 175	89.40 108	83.01 369	70.67 247	87.08 60	93.96 67	68.38 117	91.45 287	88.56 34	84.50 235	93.56 114

test_fmvsm_n_1920		85.29 80	85.34 77	85.13 101	86.12 287	69.93 92	88.65 144	90.78 164	69.97 270	88.27 38	93.98 66	71.39 67	91.54 280	88.49 35	90.45 121	93.91 87

CNVR-MVS		88.93 13	89.13 13	88.33 8	94.77 12	73.82 8	90.51 70	93.00 51	80.90 7	88.06 43	94.06 59	76.43 19	96.84 25	88.48 36	95.99 18	94.34 64

fmvsm_l_conf0.5_n_a		84.13 97	84.16 94	84.06 165	85.38 304	68.40 133	88.34 158	86.85 307	67.48 322	87.48 55	93.40 82	70.89 73	91.61 271	88.38 37	89.22 144	92.16 188

fmvsm_s_conf0.5_n_a		83.63 116	83.41 116	84.28 147	86.14 286	68.12 143	89.43 104	82.87 373	70.27 263	87.27 59	93.80 73	69.09 105	91.58 273	88.21 38	83.65 255	93.14 137

MED-MVS test				87.86 26	94.57 17	71.43 60	93.28 12	94.36 3	75.24 126	92.25 9	95.03 20		97.39 11	88.15 39	95.96 19	94.75 30

MED-MVS		89.59 4	90.16 4	87.86 26	94.57 17	71.43 60	93.28 12	94.36 3	76.30 98	92.25 9	95.03 20	81.59 7	97.39 11	88.15 39	95.96 19	94.75 30

ME-MVS		88.98 12	89.39 9	87.75 30	94.54 20	71.43 60	91.61 49	94.25 6	76.30 98	90.62 21	95.03 20	78.06 16	97.07 20	88.15 39	95.96 19	94.75 30

fmvsm_s_conf0.1_n_a		83.32 127	82.99 124	84.28 147	83.79 342	68.07 145	89.34 111	82.85 374	69.80 274	87.36 58	94.06 59	68.34 119	91.56 276	87.95 42	83.46 261	93.21 130

TSAR-MVS + MP.		88.02 21	88.11 20	87.72 33	93.68 47	72.13 48	91.41 58	92.35 87	74.62 151	88.90 32	93.85 71	75.75 23	96.00 59	87.80 43	94.63 54	95.04 10
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	76.27 100	88.14 41	95.09 19	71.06 72	96.67 33	87.67 44	96.37 14	94.09 78

SD-MVS		88.06 18	88.50 18	86.71 60	92.60 75	72.71 29	91.81 46	93.19 40	77.87 42	90.32 23	94.00 63	74.83 26	93.78 159	87.63 45	94.27 65	93.65 107
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 78	72.96 25	93.73 5	93.67 25	80.19 12	88.10 42	94.80 27	73.76 37	97.11 18	87.51 46	95.82 25	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		89.02 11	89.15 12	88.63 5	95.01 9	76.03 1	92.38 32	92.85 64	80.26 11	87.78 48	94.27 47	75.89 22	96.81 27	87.45 47	96.44 9	93.05 143

DPE-MVS		89.48 6	89.98 5	88.01 16	94.80 11	72.69 31	91.59 51	94.10 13	75.90 107	92.29 7	95.66 10	81.67 6	97.38 14	87.44 48	96.34 15	93.95 86
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 38	92.78 70	71.95 51	92.40 29	94.74 2	75.71 112	89.16 29	95.10 18	75.65 24	96.19 51	87.07 49	96.01 17	94.79 23

lecture		88.09 17	88.59 16	86.58 62	93.26 56	69.77 96	93.70 6	94.16 9	77.13 66	89.76 26	95.52 14	72.26 53	96.27 48	86.87 50	94.65 52	93.70 102

9.14			88.26 19		92.84 69		91.52 56	94.75 1	73.93 170	88.57 35	94.67 30	75.57 25	95.79 63	86.77 51	95.76 27

MTAPA		87.23 36	87.00 39	87.90 22	94.18 39	74.25 5	86.58 229	92.02 111	79.45 22	85.88 70	94.80 27	68.07 122	96.21 50	86.69 52	95.34 36	93.23 127

fmvsm_s_conf0.5_n_7		83.34 125	84.03 100	81.28 267	85.73 294	65.13 228	85.40 270	89.90 194	74.96 140	82.13 144	93.89 69	66.65 136	87.92 370	86.56 53	91.05 110	90.80 230

reproduce-ours		87.47 27	87.61 27	87.07 50	93.27 54	71.60 55	91.56 54	93.19 40	74.98 138	88.96 30	95.54 12	71.20 70	96.54 40	86.28 54	93.49 71	93.06 141

our_new_method		87.47 27	87.61 27	87.07 50	93.27 54	71.60 55	91.56 54	93.19 40	74.98 138	88.96 30	95.54 12	71.20 70	96.54 40	86.28 54	93.49 71	93.06 141

reproduce_model		87.28 35	87.39 33	86.95 54	93.10 62	71.24 68	91.60 50	93.19 40	74.69 148	88.80 33	95.61 11	70.29 81	96.44 43	86.20 56	93.08 75	93.16 134

TestfortrainingZip a		89.27 7	89.82 7	87.60 39	94.57 17	70.90 77	93.28 12	94.36 3	75.24 126	92.25 9	95.03 20	81.59 7	97.39 11	86.12 57	95.96 19	94.52 54

DeepPCF-MVS	80.84 1	88.10 16	88.56 17	86.73 59	92.24 77	69.03 110	89.57 99	93.39 35	77.53 53	89.79 25	94.12 56	78.98 14	96.58 39	85.66 58	95.72 28	94.58 47

MP-MVS		87.71 23	87.64 26	87.93 21	94.36 30	73.88 6	92.71 27	92.65 75	77.57 49	83.84 109	94.40 41	72.24 54	96.28 47	85.65 59	95.30 39	93.62 110
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
balanced_conf03		86.78 42	86.99 40	86.15 70	91.24 90	67.61 162	90.51 70	92.90 61	77.26 60	87.44 56	91.63 135	71.27 69	96.06 54	85.62 60	95.01 41	94.78 24

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 75	85.24 77	94.32 44	71.76 60	96.93 23	85.53 61	95.79 26	94.32 66

HPM-MVS		87.11 38	86.98 41	87.50 43	93.88 43	72.16 47	92.19 38	93.33 36	76.07 104	83.81 110	93.95 68	69.77 92	96.01 58	85.15 62	94.66 51	94.32 66
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 49	93.26 56	72.96 25	88.75 138	91.89 119	68.69 306	85.00 80	93.10 88	74.43 30	95.41 80	84.97 63	95.71 29	93.02 145

test9_res														84.90 64	95.70 30	92.87 152

NCCC		88.06 18	88.01 22	88.24 11	94.41 26	73.62 11	91.22 62	92.83 65	81.50 5	85.79 72	93.47 80	73.02 45	97.00 22	84.90 64	94.94 44	94.10 77

MCST-MVS		87.37 34	87.25 35	87.73 31	94.53 21	72.46 40	89.82 88	93.82 21	73.07 197	84.86 85	92.89 95	76.22 20	96.33 45	84.89 66	95.13 40	94.40 60

DeepC-MVS	79.81 2	87.08 40	86.88 45	87.69 36	91.16 91	72.32 45	90.31 79	93.94 19	77.12 67	82.82 135	94.23 50	72.13 56	97.09 19	84.83 67	95.37 35	93.65 107
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 55	94.11 41	72.11 49	92.37 33	92.56 80	74.50 152	86.84 64	94.65 31	67.31 130	95.77 64	84.80 68	92.85 78	92.84 155

MVSMamba_PlusPlus		85.99 59	85.96 64	86.05 73	91.09 92	67.64 161	89.63 97	92.65 75	72.89 202	84.64 90	91.71 130	71.85 58	96.03 55	84.77 69	94.45 60	94.49 56

ZD-MVS					94.38 29	72.22 46		92.67 72	70.98 240	87.75 50	94.07 58	74.01 36	96.70 31	84.66 70	94.84 48

PC_three_1452									68.21 314	92.02 15	94.00 63	82.09 5	95.98 61	84.58 71	96.68 2	94.95 12

HFP-MVS		87.58 26	87.47 31	87.94 19	94.58 16	73.54 15	93.04 17	93.24 38	76.78 77	84.91 82	94.44 39	70.78 75	96.61 36	84.53 72	94.89 46	93.66 103

ACMMPR		87.44 29	87.23 36	88.08 15	94.64 13	73.59 12	93.04 17	93.20 39	76.78 77	84.66 89	94.52 32	68.81 111	96.65 34	84.53 72	94.90 45	94.00 83

region2R		87.42 31	87.20 37	88.09 14	94.63 14	73.55 13	93.03 19	93.12 45	76.73 80	84.45 94	94.52 32	69.09 105	96.70 31	84.37 74	94.83 49	94.03 81

CANet		86.45 48	86.10 61	87.51 42	90.09 115	70.94 75	89.70 94	92.59 79	81.78 4	81.32 158	91.43 145	70.34 79	97.23 17	84.26 75	93.36 74	94.37 62

APD-MVS		87.44 29	87.52 30	87.19 47	94.24 36	72.39 41	91.86 45	92.83 65	73.01 199	88.58 34	94.52 32	73.36 38	96.49 42	84.26 75	95.01 41	92.70 157
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 78	90.76 103	67.57 164	92.83 22	93.30 37	79.67 19	84.57 93	92.27 107	71.47 65	95.02 100	84.24 77	93.46 73	95.13 9

CP-MVS		87.11 38	86.92 43	87.68 37	94.20 38	73.86 7	93.98 3	92.82 68	76.62 83	83.68 112	94.46 36	67.93 123	95.95 62	84.20 78	94.39 61	93.23 127

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 73	84.68 86	93.99 65	70.67 77	96.82 26	84.18 79	95.01 41	93.90 89

BP-MVS1		84.32 91	83.71 108	86.17 68	87.84 214	67.85 154	89.38 109	89.64 204	77.73 45	83.98 106	92.12 118	56.89 266	95.43 77	84.03 80	91.75 98	95.24 7

EC-MVSNet		86.01 58	86.38 52	84.91 113	89.31 148	66.27 194	92.32 35	93.63 26	79.37 23	84.17 102	91.88 123	69.04 109	95.43 77	83.93 81	93.77 69	93.01 146

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 16

casdiffmvs_mvg		85.99 59	86.09 62	85.70 81	87.65 230	67.22 179	88.69 142	93.04 46	79.64 21	85.33 76	92.54 104	73.30 39	94.50 125	83.49 83	91.14 109	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
dcpmvs_2		85.63 70	86.15 60	84.06 165	91.71 84	64.94 238	86.47 233	91.87 121	73.63 177	86.60 67	93.02 93	76.57 18	91.87 264	83.36 84	92.15 90	95.35 3

test_prior2							88.85 132		75.41 121	84.91 82	93.54 76	74.28 33		83.31 85	95.86 24

PHI-MVS		86.43 49	86.17 59	87.24 46	90.88 99	70.96 73	92.27 37	94.07 14	72.45 205	85.22 78	91.90 122	69.47 95	96.42 44	83.28 86	95.94 23	94.35 63

XVS		87.18 37	86.91 44	88.00 17	94.42 24	73.33 19	92.78 23	92.99 54	79.14 26	83.67 113	94.17 53	67.45 128	96.60 37	83.06 87	94.50 57	94.07 79

X-MVStestdata		80.37 200	77.83 239	88.00 17	94.42 24	73.33 19	92.78 23	92.99 54	79.14 26	83.67 113	12.47 496	67.45 128	96.60 37	83.06 87	94.50 57	94.07 79

balanced_ft_v1		83.98 103	83.64 111	85.03 104	89.76 128	65.86 205	88.31 160	91.71 130	74.41 156	80.41 178	90.82 167	62.90 186	94.90 104	83.04 89	91.37 105	94.32 66

APD-MVS_3200maxsize		85.97 61	85.88 65	86.22 67	92.69 72	69.53 99	91.93 42	92.99 54	73.54 181	85.94 69	94.51 35	65.80 153	95.61 67	83.04 89	92.51 83	93.53 117

agg_prior2														82.91 91	95.45 33	92.70 157

mPP-MVS		86.67 46	86.32 53	87.72 33	94.41 26	73.55 13	92.74 25	92.22 100	76.87 74	82.81 136	94.25 49	66.44 141	96.24 49	82.88 92	94.28 64	93.38 120

diffmvs_AUTHOR		82.38 144	82.27 140	82.73 234	83.26 356	63.80 267	83.89 312	89.76 198	73.35 188	82.37 139	90.84 165	66.25 144	90.79 317	82.77 93	87.93 174	93.59 112

SR-MVS-dyc-post		85.77 67	85.61 72	86.23 66	93.06 64	70.63 82	91.88 43	92.27 93	73.53 182	85.69 73	94.45 37	65.00 161	95.56 68	82.75 94	91.87 95	92.50 167

RE-MVS-def			85.48 75		93.06 64	70.63 82	91.88 43	92.27 93	73.53 182	85.69 73	94.45 37	63.87 169		82.75 94	91.87 95	92.50 167

h-mvs33		83.15 130	82.19 141	86.02 76	90.56 105	70.85 79	88.15 167	89.16 230	76.02 105	84.67 87	91.39 146	61.54 209	95.50 73	82.71 96	75.48 367	91.72 201

hse-mvs2		81.72 156	80.94 161	84.07 162	88.72 176	67.68 160	85.87 255	87.26 295	76.02 105	84.67 87	88.22 247	61.54 209	93.48 183	82.71 96	73.44 395	91.06 220

PGM-MVS		86.68 45	86.27 55	87.90 22	94.22 37	73.38 18	90.22 81	93.04 46	75.53 117	83.86 108	94.42 40	67.87 125	96.64 35	82.70 98	94.57 56	93.66 103

ACMMP		85.89 65	85.39 76	87.38 44	93.59 49	72.63 33	92.74 25	93.18 44	76.78 77	80.73 172	93.82 72	64.33 165	96.29 46	82.67 99	90.69 117	93.23 127
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		82.10 147	81.88 149	82.76 232	83.00 366	63.78 269	83.68 317	89.76 198	72.94 200	82.02 146	89.85 191	65.96 152	90.79 317	82.38 100	87.30 186	93.71 101
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		83.65 114	84.54 89	80.99 276	90.06 120	65.83 206	84.21 305	88.74 254	71.60 223	85.01 79	92.44 105	74.51 29	83.50 417	82.15 101	92.15 90	93.64 109

SPE-MVS-test		86.29 54	86.48 51	85.71 80	91.02 95	67.21 180	92.36 34	93.78 23	78.97 33	83.51 120	91.20 153	70.65 78	95.15 91	81.96 102	94.89 46	94.77 25

TSAR-MVS + GP.		85.71 69	85.33 78	86.84 56	91.34 88	72.50 36	89.07 124	87.28 290	76.41 90	85.80 71	90.22 186	74.15 35	95.37 85	81.82 103	91.88 94	92.65 161

alignmvs		85.48 73	85.32 79	85.96 77	89.51 135	69.47 102	89.74 92	92.47 81	76.17 102	87.73 52	91.46 144	70.32 80	93.78 159	81.51 104	88.95 148	94.63 44

sasdasda		85.91 63	85.87 67	86.04 74	89.84 125	69.44 105	90.45 76	93.00 51	76.70 81	88.01 45	91.23 149	73.28 40	93.91 153	81.50 105	88.80 151	94.77 25

canonicalmvs		85.91 63	85.87 67	86.04 74	89.84 125	69.44 105	90.45 76	93.00 51	76.70 81	88.01 45	91.23 149	73.28 40	93.91 153	81.50 105	88.80 151	94.77 25

baseline		84.93 86	84.98 83	84.80 118	87.30 250	65.39 218	87.30 201	92.88 62	77.62 47	84.04 105	92.26 108	71.81 59	93.96 145	81.31 107	90.30 123	95.03 11

MGCFI-Net		85.06 85	85.51 74	83.70 184	89.42 140	63.01 291	89.43 104	92.62 78	76.43 89	87.53 53	91.34 147	72.82 49	93.42 188	81.28 108	88.74 154	94.66 41

casdiffmvs		85.11 83	85.14 82	85.01 106	87.20 252	65.77 210	87.75 181	92.83 65	77.84 43	84.36 99	92.38 106	72.15 55	93.93 151	81.27 109	90.48 120	95.33 4
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 82	84.75 87	86.32 65	91.65 85	72.70 30	85.98 251	90.33 179	76.11 103	82.08 145	91.61 138	71.36 68	94.17 140	81.02 110	92.58 82	92.08 190

HPM-MVS_fast		85.35 79	84.95 85	86.57 63	93.69 46	70.58 84	92.15 40	91.62 135	73.89 171	82.67 138	94.09 57	62.60 188	95.54 70	80.93 111	92.93 77	93.57 113

CPTT-MVS		83.73 111	83.33 119	84.92 112	93.28 53	70.86 78	92.09 41	90.38 175	68.75 305	79.57 188	92.83 97	60.60 232	93.04 214	80.92 112	91.56 102	90.86 229

ETV-MVS		84.90 88	84.67 88	85.59 86	89.39 143	68.66 127	88.74 140	92.64 77	79.97 16	84.10 103	85.71 315	69.32 98	95.38 82	80.82 113	91.37 105	92.72 156

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 46	76.62 83	84.22 100	93.36 84	71.44 66	96.76 29	80.82 113	95.33 37	94.16 73
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
nrg030		83.88 105	83.53 114	84.96 108	86.77 270	69.28 109	90.46 75	92.67 72	74.79 146	82.95 130	91.33 148	72.70 50	93.09 209	80.79 115	79.28 316	92.50 167

NormalMVS		86.29 54	85.88 65	87.52 41	93.26 56	72.47 38	91.65 47	92.19 105	79.31 24	84.39 96	92.18 113	64.64 163	95.53 71	80.70 116	94.65 52	94.56 51

SymmetryMVS		85.38 78	84.81 86	87.07 50	91.47 87	72.47 38	91.65 47	88.06 269	79.31 24	84.39 96	92.18 113	64.64 163	95.53 71	80.70 116	90.91 114	93.21 130

EI-MVSNet-Vis-set		84.19 96	83.81 105	85.31 93	88.18 195	67.85 154	87.66 183	89.73 201	80.05 15	82.95 130	89.59 204	70.74 76	94.82 109	80.66 118	84.72 232	93.28 126

MSLP-MVS++		85.43 75	85.76 69	84.45 133	91.93 81	70.24 85	90.71 67	92.86 63	77.46 55	84.22 100	92.81 99	67.16 132	92.94 216	80.36 119	94.35 63	90.16 259

MVS_111021_LR		82.61 141	82.11 142	84.11 155	88.82 167	71.58 57	85.15 275	86.16 322	74.69 148	80.47 177	91.04 159	62.29 195	90.55 323	80.33 120	90.08 128	90.20 258

DELS-MVS		85.41 76	85.30 80	85.77 79	88.49 183	67.93 152	85.52 269	93.44 32	78.70 34	83.63 115	89.03 219	74.57 27	95.71 66	80.26 121	94.04 67	93.66 103
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		83.52 119	82.64 131	86.16 69	88.14 198	68.45 132	89.13 121	92.69 70	72.82 203	83.71 111	91.86 125	55.69 275	95.35 86	80.03 122	89.74 135	94.69 33

EI-MVSNet-UG-set		83.81 106	83.38 117	85.09 103	87.87 212	67.53 166	87.44 196	89.66 202	79.74 18	82.23 142	89.41 213	70.24 82	94.74 115	79.95 123	83.92 247	92.99 148

CSCG		86.41 51	86.19 58	87.07 50	92.91 67	72.48 37	90.81 66	93.56 29	73.95 168	83.16 127	91.07 158	75.94 21	95.19 89	79.94 124	94.38 62	93.55 115

E5new		84.22 92	84.12 95	84.51 128	87.60 232	65.36 220	87.45 191	92.31 89	76.51 85	83.53 116	92.26 108	69.25 102	93.50 178	79.88 125	88.26 162	94.69 33

E6new		84.22 92	84.12 95	84.52 126	87.60 232	65.36 220	87.45 191	92.30 91	76.51 85	83.53 116	92.26 108	69.26 100	93.49 180	79.88 125	88.26 162	94.69 33

E6		84.22 92	84.12 95	84.52 126	87.60 232	65.36 220	87.45 191	92.30 91	76.51 85	83.53 116	92.26 108	69.26 100	93.49 180	79.88 125	88.26 162	94.69 33

E5		84.22 92	84.12 95	84.51 128	87.60 232	65.36 220	87.45 191	92.31 89	76.51 85	83.53 116	92.26 108	69.25 102	93.50 178	79.88 125	88.26 162	94.69 33

RRT-MVS		82.60 143	82.10 143	84.10 156	87.98 208	62.94 296	87.45 191	91.27 146	77.42 56	79.85 184	90.28 182	56.62 269	94.70 118	79.87 129	88.15 168	94.67 38

E4		84.10 98	83.99 101	84.45 133	87.58 240	64.99 234	86.54 231	92.25 96	76.38 94	83.37 121	92.09 119	69.88 90	93.58 167	79.78 130	88.03 172	94.77 25

AstraMVS		80.81 179	80.14 180	82.80 226	86.05 289	63.96 262	86.46 234	85.90 326	73.71 175	80.85 170	90.56 175	54.06 292	91.57 275	79.72 131	83.97 246	92.86 153

OPM-MVS		83.50 120	82.95 125	85.14 98	88.79 173	70.95 74	89.13 121	91.52 139	77.55 52	80.96 166	91.75 129	60.71 226	94.50 125	79.67 132	86.51 201	89.97 275
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
E2		84.00 101	83.87 102	84.39 136	87.70 227	64.95 235	86.40 238	92.23 97	75.85 108	83.21 123	91.78 127	70.09 85	93.55 172	79.52 133	88.05 170	94.66 41

E3		84.00 101	83.87 102	84.39 136	87.70 227	64.95 235	86.40 238	92.23 97	75.85 108	83.21 123	91.78 127	70.09 85	93.55 172	79.52 133	88.05 170	94.66 41

viewcassd2359sk11		83.89 104	83.74 107	84.34 141	87.76 222	64.91 241	86.30 242	92.22 100	75.47 119	83.04 129	91.52 140	70.15 83	93.53 175	79.26 135	87.96 173	94.57 49

E3new		83.78 109	83.60 112	84.31 143	87.76 222	64.89 242	86.24 245	92.20 103	75.15 135	82.87 132	91.23 149	70.11 84	93.52 177	79.05 136	87.79 176	94.51 55

viewmacassd2359aftdt		83.76 110	83.66 110	84.07 162	86.59 276	64.56 247	86.88 216	91.82 124	75.72 111	83.34 122	92.15 117	68.24 121	92.88 219	79.05 136	89.15 146	94.77 25

viewmanbaseed2359cas		83.66 113	83.55 113	84.00 173	86.81 268	64.53 248	86.65 226	91.75 129	74.89 142	83.15 128	91.68 131	68.74 113	92.83 223	79.02 138	89.24 143	94.63 44

LuminaMVS		80.68 187	79.62 196	83.83 180	85.07 315	68.01 148	86.99 210	88.83 245	70.36 258	81.38 157	87.99 255	50.11 345	92.51 236	79.02 138	86.89 195	90.97 225

CDPH-MVS		85.76 68	85.29 81	87.17 48	93.49 51	71.08 69	88.58 147	92.42 85	68.32 313	84.61 91	93.48 78	72.32 52	96.15 53	79.00 140	95.43 34	94.28 69

MVSFormer		82.85 137	82.05 145	85.24 95	87.35 242	70.21 86	90.50 72	90.38 175	68.55 308	81.32 158	89.47 207	61.68 206	93.46 185	78.98 141	90.26 124	92.05 191

test_djsdf		80.30 203	79.32 204	83.27 199	83.98 338	65.37 219	90.50 72	90.38 175	68.55 308	76.19 268	88.70 230	56.44 270	93.46 185	78.98 141	80.14 304	90.97 225

test_vis1_n_1920		75.52 310	75.78 284	74.75 396	79.84 418	57.44 383	83.26 329	85.52 330	62.83 390	79.34 195	86.17 308	45.10 397	79.71 439	78.75 143	81.21 288	87.10 373

HQP_MVS		83.64 115	83.14 120	85.14 98	90.08 116	68.71 123	91.25 60	92.44 82	79.12 28	78.92 200	91.00 162	60.42 234	95.38 82	78.71 144	86.32 203	91.33 212

plane_prior5								92.44 82					95.38 82	78.71 144	86.32 203	91.33 212

LPG-MVS_test		82.08 148	81.27 154	84.50 130	89.23 153	68.76 119	90.22 81	91.94 117	75.37 123	76.64 256	91.51 141	54.29 288	94.91 102	78.44 146	83.78 248	89.83 280

LGP-MVS_train				84.50 130	89.23 153	68.76 119		91.94 117	75.37 123	76.64 256	91.51 141	54.29 288	94.91 102	78.44 146	83.78 248	89.83 280

lupinMVS		81.39 168	80.27 176	84.76 120	87.35 242	70.21 86	85.55 265	86.41 316	62.85 389	81.32 158	88.61 234	61.68 206	92.24 249	78.41 148	90.26 124	91.83 194

jason		81.39 168	80.29 175	84.70 122	86.63 275	69.90 94	85.95 252	86.77 308	63.24 382	81.07 164	89.47 207	61.08 222	92.15 251	78.33 149	90.07 129	92.05 191
jason: jason.
xiu_mvs_v1_base_debu		80.80 182	79.72 193	84.03 170	87.35 242	70.19 88	85.56 262	88.77 248	69.06 296	81.83 147	88.16 248	50.91 334	92.85 220	78.29 150	87.56 180	89.06 300

xiu_mvs_v1_base		80.80 182	79.72 193	84.03 170	87.35 242	70.19 88	85.56 262	88.77 248	69.06 296	81.83 147	88.16 248	50.91 334	92.85 220	78.29 150	87.56 180	89.06 300

xiu_mvs_v1_base_debi		80.80 182	79.72 193	84.03 170	87.35 242	70.19 88	85.56 262	88.77 248	69.06 296	81.83 147	88.16 248	50.91 334	92.85 220	78.29 150	87.56 180	89.06 300

guyue		81.13 172	80.64 166	82.60 237	86.52 277	63.92 265	86.69 225	87.73 280	73.97 167	80.83 171	89.69 198	56.70 267	91.33 292	78.26 153	85.40 225	92.54 164

Effi-MVS+		83.62 117	83.08 121	85.24 95	88.38 189	67.45 167	88.89 129	89.15 231	75.50 118	82.27 141	88.28 244	69.61 94	94.45 128	77.81 154	87.84 175	93.84 93

KinetiMVS		83.31 128	82.61 132	85.39 91	87.08 261	67.56 165	88.06 169	91.65 133	77.80 44	82.21 143	91.79 126	57.27 261	94.07 143	77.77 155	89.89 133	94.56 51

viewdifsd2359ckpt07		82.83 138	82.78 130	82.99 215	86.51 278	62.58 299	85.09 278	90.83 162	75.22 128	82.28 140	91.63 135	69.43 96	92.03 254	77.71 156	86.32 203	94.34 64

PS-MVSNAJss		82.07 149	81.31 153	84.34 141	86.51 278	67.27 176	89.27 112	91.51 140	71.75 218	79.37 193	90.22 186	63.15 179	94.27 132	77.69 157	82.36 276	91.49 208

ACMP	74.13 6	81.51 167	80.57 167	84.36 139	89.42 140	68.69 126	89.97 85	91.50 143	74.46 154	75.04 303	90.41 178	53.82 294	94.54 122	77.56 158	82.91 268	89.86 279
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
BP-MVS														77.47 159

HQP-MVS		82.61 141	82.02 146	84.37 138	89.33 145	66.98 183	89.17 116	92.19 105	76.41 90	77.23 241	90.23 185	60.17 237	95.11 94	77.47 159	85.99 212	91.03 222

MVS_Test		83.15 130	83.06 122	83.41 195	86.86 265	63.21 287	86.11 249	92.00 113	74.31 159	82.87 132	89.44 212	70.03 87	93.21 198	77.39 161	88.50 159	93.81 95

3Dnovator+	77.84 4	85.48 73	84.47 92	88.51 7	91.08 93	73.49 16	93.18 16	93.78 23	80.79 8	76.66 255	93.37 83	60.40 236	96.75 30	77.20 162	93.73 70	95.29 6

anonymousdsp		78.60 244	77.15 259	82.98 217	80.51 410	67.08 181	87.24 203	89.53 208	65.66 347	75.16 298	87.19 277	52.52 303	92.25 248	77.17 163	79.34 315	89.61 287

mmtdpeth		74.16 326	73.01 330	77.60 364	83.72 345	61.13 326	85.10 277	85.10 335	72.06 214	77.21 245	80.33 414	43.84 406	85.75 393	77.14 164	52.61 474	85.91 398

VDD-MVS		83.01 135	82.36 137	84.96 108	91.02 95	66.40 191	88.91 128	88.11 265	77.57 49	84.39 96	93.29 85	52.19 309	93.91 153	77.05 165	88.70 155	94.57 49

XVG-OURS-SEG-HR		80.81 179	79.76 190	83.96 177	85.60 298	68.78 118	83.54 324	90.50 171	70.66 250	76.71 254	91.66 132	60.69 227	91.26 293	76.94 166	81.58 284	91.83 194

Elysia		81.53 163	80.16 178	85.62 84	85.51 300	68.25 139	88.84 133	92.19 105	71.31 228	80.50 175	89.83 192	46.89 375	94.82 109	76.85 167	89.57 137	93.80 97

StellarMVS		81.53 163	80.16 178	85.62 84	85.51 300	68.25 139	88.84 133	92.19 105	71.31 228	80.50 175	89.83 192	46.89 375	94.82 109	76.85 167	89.57 137	93.80 97

jajsoiax		79.29 226	77.96 233	83.27 199	84.68 323	66.57 190	89.25 113	90.16 186	69.20 292	75.46 283	89.49 206	45.75 392	93.13 207	76.84 169	80.80 294	90.11 263

SDMVSNet		80.38 198	80.18 177	80.99 276	89.03 162	64.94 238	80.45 378	89.40 212	75.19 132	76.61 258	89.98 188	60.61 231	87.69 374	76.83 170	83.55 257	90.33 253

viewdifsd2359ckpt11		80.37 200	79.73 191	82.30 243	83.70 346	62.39 303	84.20 306	86.67 310	73.22 194	80.90 167	90.62 172	63.00 184	91.56 276	76.81 171	78.44 323	92.95 150

viewmsd2359difaftdt		80.37 200	79.73 191	82.30 243	83.70 346	62.39 303	84.20 306	86.67 310	73.22 194	80.90 167	90.62 172	63.00 184	91.56 276	76.81 171	78.44 323	92.95 150

mvs_tets		79.13 230	77.77 243	83.22 203	84.70 322	66.37 192	89.17 116	90.19 185	69.38 284	75.40 286	89.46 209	44.17 404	93.15 205	76.78 173	80.70 296	90.14 260

DPM-MVS		84.93 86	84.29 93	86.84 56	90.20 113	73.04 23	87.12 205	93.04 46	69.80 274	82.85 134	91.22 152	73.06 44	96.02 57	76.72 174	94.63 54	91.46 211

test_cas_vis1_n_1920		73.76 332	73.74 321	73.81 407	75.90 451	59.77 352	80.51 376	82.40 378	58.30 433	81.62 155	85.69 316	44.35 403	76.41 457	76.29 175	78.61 319	85.23 409

ET-MVSNet_ETH3D		78.63 243	76.63 274	84.64 123	86.73 271	69.47 102	85.01 280	84.61 341	69.54 281	66.51 419	86.59 295	50.16 344	91.75 267	76.26 176	84.24 243	92.69 159

viewdifsd2359ckpt09		83.34 125	82.55 133	85.70 81	87.64 231	67.72 159	88.43 151	91.68 132	71.91 217	81.65 154	90.68 170	67.10 133	94.75 114	76.17 177	87.70 179	94.62 46

v2v482		80.23 204	79.29 205	83.05 212	83.62 348	64.14 259	87.04 207	89.97 191	73.61 178	78.18 219	87.22 275	61.10 221	93.82 157	76.11 178	76.78 346	91.18 216

test_fmvs1_n		70.86 374	70.24 369	72.73 418	72.51 474	55.28 415	81.27 364	79.71 416	51.49 464	78.73 202	84.87 338	27.54 470	77.02 451	76.06 179	79.97 306	85.88 399

CLD-MVS		82.31 145	81.65 151	84.29 146	88.47 184	67.73 158	85.81 259	92.35 87	75.78 110	78.33 215	86.58 297	64.01 168	94.35 129	76.05 180	87.48 183	90.79 231
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPNet		83.72 112	82.92 126	86.14 72	84.22 332	69.48 101	91.05 64	85.27 332	81.30 6	76.83 250	91.65 133	66.09 148	95.56 68	76.00 181	93.85 68	93.38 120
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewdifsd2359ckpt13		82.91 136	82.29 139	84.77 119	86.96 264	66.90 187	87.47 188	91.62 135	72.19 210	81.68 153	90.71 169	66.92 134	93.28 191	75.90 182	87.15 189	94.12 76

test_fmvs1		70.93 372	70.52 364	72.16 421	73.71 463	55.05 417	80.82 367	78.77 425	51.21 465	78.58 207	84.41 346	31.20 464	76.94 452	75.88 183	80.12 305	84.47 421

XVG-OURS		80.41 196	79.23 207	83.97 176	85.64 296	69.02 112	83.03 338	90.39 174	71.09 235	77.63 232	91.49 143	54.62 287	91.35 290	75.71 184	83.47 260	91.54 205

V42		79.38 224	78.24 229	82.83 223	81.10 404	65.50 215	85.55 265	89.82 195	71.57 224	78.21 217	86.12 309	60.66 229	93.18 204	75.64 185	75.46 369	89.81 282

PS-MVSNAJ		81.69 158	81.02 159	83.70 184	89.51 135	68.21 142	84.28 304	90.09 188	70.79 244	81.26 162	85.62 320	63.15 179	94.29 130	75.62 186	88.87 150	88.59 324

xiu_mvs_v2_base		81.69 158	81.05 158	83.60 186	89.15 156	68.03 147	84.46 296	90.02 189	70.67 247	81.30 161	86.53 300	63.17 178	94.19 139	75.60 187	88.54 157	88.57 325

EIA-MVS		83.31 128	82.80 128	84.82 116	89.59 131	65.59 213	88.21 163	92.68 71	74.66 150	78.96 198	86.42 302	69.06 107	95.26 87	75.54 188	90.09 127	93.62 110

AUN-MVS		79.21 228	77.60 249	84.05 168	88.71 177	67.61 162	85.84 257	87.26 295	69.08 295	77.23 241	88.14 252	53.20 301	93.47 184	75.50 189	73.45 394	91.06 220

mvsmamba		80.60 191	79.38 201	84.27 149	89.74 129	67.24 178	87.47 188	86.95 303	70.02 267	75.38 287	88.93 224	51.24 331	92.56 232	75.47 190	89.22 144	93.00 147

reproduce_monomvs		75.40 314	74.38 312	78.46 345	83.92 340	57.80 376	83.78 314	86.94 304	73.47 184	72.25 344	84.47 344	38.74 439	89.27 346	75.32 191	70.53 414	88.31 330

OMC-MVS		82.69 139	81.97 148	84.85 115	88.75 175	67.42 168	87.98 171	90.87 160	74.92 141	79.72 186	91.65 133	62.19 198	93.96 145	75.26 192	86.42 202	93.16 134

VortexMVS		78.57 246	77.89 237	80.59 285	85.89 290	62.76 298	85.61 260	89.62 205	72.06 214	74.99 304	85.38 326	55.94 274	90.77 320	74.99 193	76.58 347	88.23 333

v1144		80.03 208	79.03 211	83.01 214	83.78 343	64.51 250	87.11 206	90.57 170	71.96 216	78.08 222	86.20 307	61.41 213	93.94 148	74.93 194	77.23 337	90.60 241

MVSTER		79.01 233	77.88 238	82.38 241	83.07 363	64.80 244	84.08 311	88.95 242	69.01 299	78.69 203	87.17 278	54.70 285	92.43 239	74.69 195	80.57 298	89.89 278

viewmambaseed2359dif		80.41 196	79.84 188	82.12 245	82.95 372	62.50 302	83.39 325	88.06 269	67.11 324	80.98 165	90.31 181	66.20 146	91.01 307	74.62 196	84.90 229	92.86 153

test_vis1_n		69.85 390	69.21 376	71.77 423	72.66 473	55.27 416	81.48 358	76.21 444	52.03 461	75.30 294	83.20 378	28.97 467	76.22 459	74.60 197	78.41 327	83.81 429

test_fmvs2		68.35 403	67.48 400	70.98 432	69.50 478	51.95 441	80.05 385	76.38 443	49.33 467	74.65 311	84.38 347	23.30 479	75.40 468	74.51 198	75.17 378	85.60 402

PVSNet_Blended_VisFu		82.62 140	81.83 150	84.96 108	90.80 101	69.76 97	88.74 140	91.70 131	69.39 283	78.96 198	88.46 239	65.47 155	94.87 108	74.42 199	88.57 156	90.24 257

v8		79.97 210	79.02 212	82.80 226	84.09 335	64.50 252	87.96 172	90.29 182	74.13 166	75.24 296	86.81 284	62.88 187	93.89 156	74.39 200	75.40 372	90.00 271

v144192		79.47 218	78.37 225	82.78 230	83.35 353	63.96 262	86.96 211	90.36 178	69.99 269	77.50 233	85.67 318	60.66 229	93.77 161	74.27 201	76.58 347	90.62 239

ACMM	73.20 8	80.78 186	79.84 188	83.58 188	89.31 148	68.37 134	89.99 84	91.60 137	70.28 262	77.25 239	89.66 200	53.37 299	93.53 175	74.24 202	82.85 269	88.85 313
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
旧先验2							86.56 230		58.10 436	87.04 61			88.98 353	74.07 203

v1192		79.59 215	78.43 224	83.07 211	83.55 350	64.52 249	86.93 214	90.58 168	70.83 243	77.78 229	85.90 311	59.15 243	93.94 148	73.96 204	77.19 339	90.76 233

v10		79.74 212	78.67 217	82.97 218	84.06 336	64.95 235	87.88 178	90.62 167	73.11 196	75.11 300	86.56 298	61.46 212	94.05 144	73.68 205	75.55 365	89.90 277

v1921920		79.22 227	78.03 232	82.80 226	83.30 355	63.94 264	86.80 219	90.33 179	69.91 272	77.48 234	85.53 322	58.44 249	93.75 163	73.60 206	76.85 344	90.71 237

cl22		78.07 258	77.01 261	81.23 269	82.37 385	61.83 316	83.55 322	87.98 271	68.96 302	75.06 302	83.87 360	61.40 214	91.88 263	73.53 207	76.39 352	89.98 274

Effi-MVS+-dtu		80.03 208	78.57 220	84.42 135	85.13 313	68.74 121	88.77 136	88.10 266	74.99 137	74.97 305	83.49 373	57.27 261	93.36 189	73.53 207	80.88 292	91.18 216

c3_l		78.75 239	77.91 235	81.26 268	82.89 373	61.56 320	84.09 310	89.13 233	69.97 270	75.56 279	84.29 350	66.36 142	92.09 253	73.47 209	75.48 367	90.12 262

VDDNet		81.52 165	80.67 165	84.05 168	90.44 108	64.13 260	89.73 93	85.91 325	71.11 234	83.18 126	93.48 78	50.54 340	93.49 180	73.40 210	88.25 166	94.54 53

CANet_DTU		80.61 189	79.87 187	82.83 223	85.60 298	63.17 290	87.36 198	88.65 258	76.37 95	75.88 274	88.44 240	53.51 297	93.07 210	73.30 211	89.74 135	92.25 179

miper_ehance_all_eth		78.59 245	77.76 244	81.08 274	82.66 378	61.56 320	83.65 318	89.15 231	68.87 303	75.55 280	83.79 364	66.49 140	92.03 254	73.25 212	76.39 352	89.64 286

3Dnovator	76.31 5	83.38 124	82.31 138	86.59 61	87.94 209	72.94 28	90.64 68	92.14 110	77.21 63	75.47 281	92.83 97	58.56 248	94.72 116	73.24 213	92.71 81	92.13 189

v1240		78.99 234	77.78 242	82.64 235	83.21 358	63.54 278	86.62 228	90.30 181	69.74 279	77.33 237	85.68 317	57.04 264	93.76 162	73.13 214	76.92 341	90.62 239

miper_enhance_ethall		77.87 265	76.86 265	80.92 279	81.65 392	61.38 324	82.68 339	88.98 239	65.52 349	75.47 281	82.30 393	65.76 154	92.00 257	72.95 215	76.39 352	89.39 293

MG-MVS		83.41 122	83.45 115	83.28 198	92.74 71	62.28 308	88.17 165	89.50 209	75.22 128	81.49 156	92.74 103	66.75 135	95.11 94	72.85 216	91.58 101	92.45 171

EPP-MVSNet		83.40 123	83.02 123	84.57 124	90.13 114	64.47 253	92.32 35	90.73 165	74.45 155	79.35 194	91.10 156	69.05 108	95.12 92	72.78 217	87.22 187	94.13 75

test_fmvs3		63.36 429	61.82 431	67.98 447	62.51 487	46.96 468	77.37 422	74.03 454	45.24 472	67.50 400	78.79 432	12.16 491	72.98 477	72.77 218	66.02 435	83.99 427

IterMVS-LS		80.06 207	79.38 201	82.11 247	85.89 290	63.20 288	86.79 220	89.34 214	74.19 163	75.45 284	86.72 287	66.62 137	92.39 241	72.58 219	76.86 343	90.75 234
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tt0805		78.73 240	77.83 239	81.43 261	85.17 309	60.30 347	89.41 107	90.90 158	71.21 232	77.17 246	88.73 229	46.38 381	93.21 198	72.57 220	78.96 318	90.79 231

EI-MVSNet		80.52 195	79.98 183	82.12 245	84.28 330	63.19 289	86.41 235	88.95 242	74.18 164	78.69 203	87.54 267	66.62 137	92.43 239	72.57 220	80.57 298	90.74 235

icg_test_0407_2		78.92 237	78.93 214	78.90 333	87.13 255	63.59 274	76.58 427	89.33 215	70.51 253	77.82 226	89.03 219	61.84 202	81.38 432	72.56 222	85.56 221	91.74 197

IMVS_0407		80.61 189	79.90 186	82.75 233	87.13 255	63.59 274	85.33 271	89.33 215	70.51 253	77.82 226	89.03 219	61.84 202	92.91 217	72.56 222	85.56 221	91.74 197

IMVS_0404		77.16 281	76.42 278	79.37 324	87.13 255	63.59 274	77.12 424	89.33 215	70.51 253	66.22 422	89.03 219	50.36 342	82.78 422	72.56 222	85.56 221	91.74 197

IMVS_0403		80.80 182	80.12 181	82.87 222	87.13 255	63.59 274	85.19 272	89.33 215	70.51 253	78.49 210	89.03 219	63.26 175	93.27 193	72.56 222	85.56 221	91.74 197

SSM_0407		81.58 162	80.48 170	84.87 114	88.81 168	67.96 149	87.37 197	89.25 225	71.06 237	79.48 190	90.39 179	59.57 239	94.48 127	72.45 226	85.93 214	92.18 184

SSM_0404		81.91 152	80.84 163	85.13 101	89.24 152	68.26 137	87.84 180	89.25 225	71.06 237	80.62 173	90.39 179	59.57 239	94.65 120	72.45 226	87.19 188	92.47 170

Vis-MVSNet		83.46 121	82.80 128	85.43 90	90.25 112	68.74 121	90.30 80	90.13 187	76.33 97	80.87 169	92.89 95	61.00 223	94.20 137	72.45 226	90.97 112	93.35 123
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
LFMVS		81.82 155	81.23 155	83.57 189	91.89 82	63.43 283	89.84 87	81.85 387	77.04 70	83.21 123	93.10 88	52.26 308	93.43 187	71.98 229	89.95 131	93.85 91

v148		78.72 241	77.80 241	81.47 260	82.73 376	61.96 314	86.30 242	88.08 267	73.26 191	76.18 269	85.47 324	62.46 192	92.36 243	71.92 230	73.82 391	90.09 265

PVSNet_BlendedMVS		80.60 191	80.02 182	82.36 242	88.85 164	65.40 216	86.16 248	92.00 113	69.34 285	78.11 220	86.09 310	66.02 150	94.27 132	71.52 231	82.06 279	87.39 355

PVSNet_Blended		80.98 174	80.34 173	82.90 220	88.85 164	65.40 216	84.43 299	92.00 113	67.62 319	78.11 220	85.05 336	66.02 150	94.27 132	71.52 231	89.50 139	89.01 305

eth_miper_zixun_eth		77.92 263	76.69 272	81.61 258	83.00 366	61.98 313	83.15 331	89.20 229	69.52 282	74.86 307	84.35 349	61.76 205	92.56 232	71.50 233	72.89 399	90.28 256

UA-Net		85.08 84	84.96 84	85.45 89	92.07 79	68.07 145	89.78 91	90.86 161	82.48 2	84.60 92	93.20 87	69.35 97	95.22 88	71.39 234	90.88 115	93.07 140

FA-MVS(test-final)		80.96 175	79.91 185	84.10 156	88.30 192	65.01 232	84.55 293	90.01 190	73.25 192	79.61 187	87.57 264	58.35 250	94.72 116	71.29 235	86.25 206	92.56 163

cl____		77.72 268	76.76 269	80.58 286	82.49 382	60.48 344	83.09 334	87.87 275	69.22 290	74.38 316	85.22 331	62.10 199	91.53 281	71.09 236	75.41 371	89.73 285

DIV-MVS_self_test		77.72 268	76.76 269	80.58 286	82.48 383	60.48 344	83.09 334	87.86 276	69.22 290	74.38 316	85.24 329	62.10 199	91.53 281	71.09 236	75.40 372	89.74 284

MonoMVSNet		76.49 294	75.80 283	78.58 339	81.55 395	58.45 363	86.36 240	86.22 320	74.87 145	74.73 309	83.73 366	51.79 323	88.73 358	70.78 238	72.15 404	88.55 326

test_yl		81.17 170	80.47 171	83.24 201	89.13 157	63.62 270	86.21 246	89.95 192	72.43 208	81.78 151	89.61 202	57.50 258	93.58 167	70.75 239	86.90 193	92.52 165

DCV-MVSNet		81.17 170	80.47 171	83.24 201	89.13 157	63.62 270	86.21 246	89.95 192	72.43 208	81.78 151	89.61 202	57.50 258	93.58 167	70.75 239	86.90 193	92.52 165

VNet		82.21 146	82.41 135	81.62 256	90.82 100	60.93 333	84.47 294	89.78 196	76.36 96	84.07 104	91.88 123	64.71 162	90.26 327	70.68 241	88.89 149	93.66 103

mvs_anonymous		79.42 221	79.11 210	80.34 292	84.45 329	57.97 371	82.59 340	87.62 282	67.40 323	76.17 271	88.56 237	68.47 116	89.59 340	70.65 242	86.05 210	93.47 118

VPA-MVSNet		80.60 191	80.55 168	80.76 282	88.07 203	60.80 336	86.86 217	91.58 138	75.67 115	80.24 180	89.45 211	63.34 172	90.25 328	70.51 243	79.22 317	91.23 215

PAPM_NR		83.02 134	82.41 135	84.82 116	92.47 76	66.37 192	87.93 175	91.80 125	73.82 172	77.32 238	90.66 171	67.90 124	94.90 104	70.37 244	89.48 140	93.19 133

mamba_0408		79.37 225	77.52 251	84.93 111	88.81 168	67.96 149	65.03 480	88.66 256	70.96 241	79.48 190	89.80 194	58.69 245	94.65 120	70.35 245	85.93 214	92.18 184

SSM_04072		77.67 272	77.52 251	78.12 350	88.81 168	67.96 149	65.03 480	88.66 256	70.96 241	79.48 190	89.80 194	58.69 245	74.23 473	70.35 245	85.93 214	92.18 184

thisisatest0530		79.40 222	77.76 244	84.31 143	87.69 229	65.10 231	87.36 198	84.26 348	70.04 266	77.42 235	88.26 246	49.94 348	94.79 113	70.20 247	84.70 233	93.03 144

tttt0517		79.40 222	77.91 235	83.90 179	88.10 201	63.84 266	88.37 157	84.05 350	71.45 226	76.78 252	89.12 216	49.93 350	94.89 106	70.18 248	83.18 266	92.96 149

UniMVSNet_NR-MVSNet		81.88 153	81.54 152	82.92 219	88.46 185	63.46 281	87.13 204	92.37 86	80.19 12	78.38 213	89.14 215	71.66 64	93.05 212	70.05 249	76.46 350	92.25 179

DU-MVS		81.12 173	80.52 169	82.90 220	87.80 216	63.46 281	87.02 209	91.87 121	79.01 31	78.38 213	89.07 217	65.02 159	93.05 212	70.05 249	76.46 350	92.20 182

XVG-ACMP-BASELINE		76.11 302	74.27 314	81.62 256	83.20 359	64.67 246	83.60 321	89.75 200	69.75 277	71.85 348	87.09 280	32.78 459	92.11 252	69.99 251	80.43 300	88.09 337

GeoE		81.71 157	81.01 160	83.80 183	89.51 135	64.45 254	88.97 126	88.73 255	71.27 231	78.63 206	89.76 197	66.32 143	93.20 201	69.89 252	86.02 211	93.74 100

FIs		82.07 149	82.42 134	81.04 275	88.80 172	58.34 365	88.26 162	93.49 31	76.93 72	78.47 212	91.04 159	69.92 89	92.34 245	69.87 253	84.97 228	92.44 172

114514_t		80.68 187	79.51 198	84.20 153	94.09 42	67.27 176	89.64 96	91.11 153	58.75 431	74.08 318	90.72 168	58.10 251	95.04 99	69.70 254	89.42 141	90.30 255

Anonymous20231211		78.97 235	77.69 247	82.81 225	90.54 106	64.29 257	90.11 83	91.51 140	65.01 361	76.16 272	88.13 253	50.56 339	93.03 215	69.68 255	77.56 336	91.11 218

Patchmatch-RL test		70.24 382	67.78 395	77.61 362	77.43 446	59.57 356	71.16 455	70.33 462	62.94 388	68.65 384	72.77 465	50.62 338	85.49 398	69.58 256	66.58 433	87.77 344

UniMVSNet (Re)		81.60 161	81.11 157	83.09 208	88.38 189	64.41 255	87.60 184	93.02 50	78.42 37	78.56 208	88.16 248	69.78 91	93.26 194	69.58 256	76.49 349	91.60 202

IterMVS-SCA-FT		75.43 312	73.87 319	80.11 300	82.69 377	64.85 243	81.57 357	83.47 359	69.16 293	70.49 360	84.15 358	51.95 316	88.15 367	69.23 258	72.14 405	87.34 360

v7n		78.97 235	77.58 250	83.14 206	83.45 352	65.51 214	88.32 159	91.21 148	73.69 176	72.41 341	86.32 305	57.93 252	93.81 158	69.18 259	75.65 363	90.11 263

Anonymous20240529		80.19 206	78.89 215	84.10 156	90.60 104	64.75 245	88.95 127	90.90 158	65.97 344	80.59 174	91.17 155	49.97 347	93.73 165	69.16 260	82.70 273	93.81 95

miper_lstm_enhance		74.11 327	73.11 329	77.13 370	80.11 414	59.62 354	72.23 451	86.92 306	66.76 328	70.40 361	82.92 383	56.93 265	82.92 421	69.06 261	72.63 400	88.87 312

testdata				79.97 304	90.90 98	64.21 258		84.71 339	59.27 424	85.40 75	92.91 94	62.02 201	89.08 351	68.95 262	91.37 105	86.63 385

test1111		79.43 220	79.18 209	80.15 299	89.99 121	53.31 433	87.33 200	77.05 439	75.04 136	80.23 181	92.77 102	48.97 363	92.33 246	68.87 263	92.40 86	94.81 22

GA-MVS		76.87 286	75.17 301	81.97 251	82.75 375	62.58 299	81.44 360	86.35 319	72.16 213	74.74 308	82.89 384	46.20 386	92.02 256	68.85 264	81.09 289	91.30 214

test2506		77.30 279	76.49 275	79.74 314	90.08 116	52.02 439	87.86 179	63.10 482	74.88 143	80.16 182	92.79 100	38.29 443	92.35 244	68.74 265	92.50 84	94.86 19

ECVR-MVS		79.61 213	79.26 206	80.67 284	90.08 116	54.69 420	87.89 177	77.44 435	74.88 143	80.27 179	92.79 100	48.96 364	92.45 238	68.55 266	92.50 84	94.86 19

UGNet		80.83 178	79.59 197	84.54 125	88.04 204	68.09 144	89.42 106	88.16 264	76.95 71	76.22 267	89.46 209	49.30 358	93.94 148	68.48 267	90.31 122	91.60 202
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		81.52 165	82.02 146	80.03 301	88.42 188	55.97 405	87.95 173	93.42 34	77.10 68	77.38 236	90.98 164	69.96 88	91.79 265	68.46 268	84.50 235	92.33 175

DP-MVS Recon		83.11 133	82.09 144	86.15 70	94.44 23	70.92 76	88.79 135	92.20 103	70.53 252	79.17 196	91.03 161	64.12 167	96.03 55	68.39 269	90.14 126	91.50 207

UniMVSNet_ETH3D		79.10 231	78.24 229	81.70 255	86.85 266	60.24 348	87.28 202	88.79 247	74.25 162	76.84 249	90.53 177	49.48 354	91.56 276	67.98 270	82.15 277	93.29 125

D2MVS		74.82 319	73.21 327	79.64 319	79.81 419	62.56 301	80.34 380	87.35 289	64.37 369	68.86 382	82.66 388	46.37 382	90.10 330	67.91 271	81.24 287	86.25 388

IS-MVSNet		83.15 130	82.81 127	84.18 154	89.94 123	63.30 285	91.59 51	88.46 262	79.04 30	79.49 189	92.16 115	65.10 158	94.28 131	67.71 272	91.86 97	94.95 12

Fast-Effi-MVS+-dtu		78.02 260	76.49 275	82.62 236	83.16 362	66.96 185	86.94 213	87.45 287	72.45 205	71.49 353	84.17 357	54.79 284	91.58 273	67.61 273	80.31 301	89.30 296

PAPR		81.66 160	80.89 162	83.99 175	90.27 111	64.00 261	86.76 223	91.77 128	68.84 304	77.13 248	89.50 205	67.63 126	94.88 107	67.55 274	88.52 158	93.09 139

cascas		76.72 288	74.64 306	82.99 215	85.78 293	65.88 204	82.33 344	89.21 228	60.85 410	72.74 335	81.02 405	47.28 371	93.75 163	67.48 275	85.02 227	89.34 295

1314		76.53 290	75.30 299	80.21 297	83.93 339	62.32 307	84.66 288	88.81 246	60.23 415	70.16 366	84.07 359	55.30 278	90.73 321	67.37 276	83.21 265	87.59 349

无先验							87.48 187	88.98 239	60.00 417				94.12 141	67.28 277		88.97 308

thisisatest0515		77.33 278	75.38 294	83.18 204	85.27 308	63.80 267	82.11 348	83.27 362	65.06 359	75.91 273	83.84 362	49.54 353	94.27 132	67.24 278	86.19 207	91.48 209

原ACMM1				84.35 140	93.01 66	68.79 117		92.44 82	63.96 377	81.09 163	91.57 139	66.06 149	95.45 75	67.19 279	94.82 50	88.81 315

Baseline_NR-MVSNet		78.15 256	78.33 227	77.61 362	85.79 292	56.21 403	86.78 221	85.76 328	73.60 179	77.93 225	87.57 264	65.02 159	88.99 352	67.14 280	75.33 374	87.63 346

TranMVSNet+NR-MVSNet		80.84 177	80.31 174	82.42 240	87.85 213	62.33 306	87.74 182	91.33 145	80.55 9	77.99 224	89.86 190	65.23 157	92.62 227	67.05 281	75.24 377	92.30 177

Fast-Effi-MVS+		80.81 179	79.92 184	83.47 190	88.85 164	64.51 250	85.53 267	89.39 213	70.79 244	78.49 210	85.06 335	67.54 127	93.58 167	67.03 282	86.58 199	92.32 176

VPNet		78.69 242	78.66 218	78.76 335	88.31 191	55.72 409	84.45 297	86.63 313	76.79 76	78.26 216	90.55 176	59.30 242	89.70 339	66.63 283	77.05 340	90.88 228

PM-MVS		66.41 416	64.14 419	73.20 413	73.92 462	56.45 396	78.97 400	64.96 479	63.88 378	64.72 433	80.24 416	19.84 483	83.44 418	66.24 284	64.52 447	79.71 460

test-LLR		72.94 351	72.43 336	74.48 397	81.35 400	58.04 369	78.38 408	77.46 433	66.66 330	69.95 370	79.00 429	48.06 367	79.24 440	66.13 285	84.83 230	86.15 391

test-mter		71.41 367	70.39 368	74.48 397	81.35 400	58.04 369	78.38 408	77.46 433	60.32 414	69.95 370	79.00 429	36.08 453	79.24 440	66.13 285	84.83 230	86.15 391

MVS		78.19 255	76.99 263	81.78 253	85.66 295	66.99 182	84.66 288	90.47 172	55.08 453	72.02 347	85.27 328	63.83 170	94.11 142	66.10 287	89.80 134	84.24 423

NR-MVSNet		80.23 204	79.38 201	82.78 230	87.80 216	63.34 284	86.31 241	91.09 154	79.01 31	72.17 345	89.07 217	67.20 131	92.81 224	66.08 288	75.65 363	92.20 182

CVMVSNet		72.99 350	72.58 335	74.25 401	84.28 330	50.85 453	86.41 235	83.45 360	44.56 473	73.23 329	87.54 267	49.38 356	85.70 394	65.90 289	78.44 323	86.19 390

IterMVS		74.29 323	72.94 331	78.35 346	81.53 396	63.49 280	81.58 356	82.49 377	68.06 316	69.99 369	83.69 368	51.66 325	85.54 397	65.85 290	71.64 408	86.01 395
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
OurMVSNet-221017-0		74.26 324	72.42 337	79.80 309	83.76 344	59.59 355	85.92 254	86.64 312	66.39 337	66.96 409	87.58 263	39.46 434	91.60 272	65.76 291	69.27 419	88.22 334

tpmrst		72.39 356	72.13 340	73.18 414	80.54 409	49.91 457	79.91 388	79.08 423	63.11 384	71.69 350	79.95 419	55.32 277	82.77 423	65.66 292	73.89 389	86.87 376

MAR-MVS		81.84 154	80.70 164	85.27 94	91.32 89	71.53 58	89.82 88	90.92 157	69.77 276	78.50 209	86.21 306	62.36 194	94.52 124	65.36 293	92.05 93	89.77 283
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		78.25 251	77.01 261	81.99 250	91.03 94	60.67 340	84.77 285	83.90 352	70.65 251	80.00 183	91.20 153	41.08 425	91.43 288	65.21 294	85.26 226	93.85 91

ab-mvs		79.51 216	78.97 213	81.14 272	88.46 185	60.91 334	83.84 313	89.24 227	70.36 258	79.03 197	88.87 227	63.23 177	90.21 329	65.12 295	82.57 274	92.28 178

IB-MVS	68.01 15	75.85 306	73.36 326	83.31 197	84.76 321	66.03 197	83.38 326	85.06 336	70.21 265	69.40 376	81.05 404	45.76 391	94.66 119	65.10 296	75.49 366	89.25 297
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		79.49 217	79.22 208	80.27 294	88.79 173	58.35 364	85.06 279	88.61 260	78.56 35	77.65 231	88.34 242	63.81 171	90.66 322	64.98 297	77.22 338	91.80 196

CostFormer		75.24 316	73.90 318	79.27 326	82.65 379	58.27 366	80.80 368	82.73 376	61.57 405	75.33 293	83.13 379	55.52 276	91.07 305	64.98 297	78.34 328	88.45 327

API-MVS		81.99 151	81.23 155	84.26 151	90.94 97	70.18 91	91.10 63	89.32 219	71.51 225	78.66 205	88.28 244	65.26 156	95.10 97	64.74 299	91.23 108	87.51 352

新几何1				83.42 193	93.13 60	70.71 80		85.48 331	57.43 442	81.80 150	91.98 120	63.28 173	92.27 247	64.60 300	92.99 76	87.27 363

testing91		76.54 289	75.66 288	79.18 329	88.43 187	55.89 406	81.08 365	83.00 370	73.76 174	75.34 289	84.29 350	46.20 386	90.07 331	64.33 301	84.50 235	91.58 204

testing99		76.09 303	75.12 302	79.00 330	88.16 196	55.50 412	80.79 369	81.40 392	73.30 190	75.17 297	84.27 353	44.48 401	90.02 332	64.28 302	84.22 244	91.48 209

pm-mvs1		77.25 280	76.68 273	78.93 332	84.22 332	58.62 362	86.41 235	88.36 263	71.37 227	73.31 327	88.01 254	61.22 219	89.15 350	64.24 303	73.01 398	89.03 304

TESTMET0.1,1		69.89 389	69.00 378	72.55 419	79.27 429	56.85 389	78.38 408	74.71 452	57.64 439	68.09 392	77.19 444	37.75 445	76.70 453	63.92 304	84.09 245	84.10 426

QAPM		80.88 176	79.50 199	85.03 104	88.01 207	68.97 114	91.59 51	92.00 113	66.63 335	75.15 299	92.16 115	57.70 255	95.45 75	63.52 305	88.76 153	90.66 238

baseline2		75.70 307	73.83 320	81.30 266	83.26 356	61.79 317	82.57 341	80.65 400	66.81 326	66.88 410	83.42 374	57.86 254	92.19 250	63.47 306	79.57 308	89.91 276

LCM-MVSNet-Re		77.05 282	76.94 264	77.36 366	87.20 252	51.60 446	80.06 384	80.46 405	75.20 131	67.69 398	86.72 287	62.48 191	88.98 353	63.44 307	89.25 142	91.51 206

gm-plane-assit					81.40 398	53.83 428			62.72 393		80.94 407		92.39 241	63.40 308

baseline1		76.98 284	76.75 271	77.66 360	88.13 199	55.66 410	85.12 276	81.89 385	73.04 198	76.79 251	88.90 225	62.43 193	87.78 373	63.30 309	71.18 411	89.55 289

blended_shiyan8		73.38 337	71.17 353	80.02 302	78.36 434	61.51 322	82.43 342	87.28 290	65.40 353	68.61 385	77.53 442	51.91 319	91.00 310	63.28 310	65.76 438	87.53 351

blended_shiyan6		73.38 337	71.17 353	80.01 303	78.36 434	61.48 323	82.43 342	87.27 293	65.40 353	68.56 387	77.55 441	51.94 318	91.01 307	63.27 311	65.76 438	87.55 350

usedtu_blend_shiyan5		73.29 343	70.96 357	80.25 295	77.80 441	62.16 310	84.44 298	87.38 288	64.41 367	68.09 392	76.28 450	51.32 327	91.23 295	63.21 312	65.76 438	87.35 357

blend_shiyan4		72.29 360	69.65 372	80.21 297	78.24 437	62.16 310	82.29 345	87.27 293	65.41 352	68.43 391	76.42 449	39.91 432	91.23 295	63.21 312	65.66 443	87.22 364

wanda-best-256-512		72.94 351	70.66 361	79.79 310	77.80 441	61.03 331	81.31 362	87.15 298	65.18 356	68.09 392	76.28 450	51.32 327	90.97 311	63.06 314	65.76 438	87.35 357

FE-blended-shiyan7		72.94 351	70.66 361	79.79 310	77.80 441	61.03 331	81.31 362	87.15 298	65.18 356	68.09 392	76.28 450	51.32 327	90.97 311	63.06 314	65.76 438	87.35 357

AdaColmap		80.58 194	79.42 200	84.06 165	93.09 63	68.91 115	89.36 110	88.97 241	69.27 287	75.70 277	89.69 198	57.20 263	95.77 64	63.06 314	88.41 161	87.50 353

test_vis1_rt		60.28 434	58.42 437	65.84 452	67.25 481	55.60 411	70.44 460	60.94 485	44.33 474	59.00 459	66.64 475	24.91 474	68.67 483	62.80 317	69.48 417	73.25 471

gbinet_0.2-2-1-0.02		73.24 345	70.86 360	80.39 289	78.03 439	61.62 319	83.10 333	86.69 309	65.98 343	69.29 379	76.15 453	49.77 351	91.51 283	62.75 318	66.00 436	88.03 338

GBi-Net		78.40 248	77.40 254	81.40 263	87.60 232	63.01 291	88.39 154	89.28 221	71.63 220	75.34 289	87.28 271	54.80 281	91.11 299	62.72 319	79.57 308	90.09 265

test1		78.40 248	77.40 254	81.40 263	87.60 232	63.01 291	88.39 154	89.28 221	71.63 220	75.34 289	87.28 271	54.80 281	91.11 299	62.72 319	79.57 308	90.09 265

FMVSNet3		77.88 264	76.85 266	80.97 278	86.84 267	62.36 305	86.52 232	88.77 248	71.13 233	75.34 289	86.66 293	54.07 291	91.10 302	62.72 319	79.57 308	89.45 291

CMPMVS	51.72 21	70.19 383	68.16 384	76.28 375	73.15 470	57.55 381	79.47 391	83.92 351	48.02 469	56.48 468	84.81 340	43.13 410	86.42 387	62.67 322	81.81 283	84.89 416
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
sd_testset		77.70 270	77.40 254	78.60 338	89.03 162	60.02 350	79.00 399	85.83 327	75.19 132	76.61 258	89.98 188	54.81 280	85.46 399	62.63 323	83.55 257	90.33 253

0.4-1-1-0.1		70.93 372	67.94 390	79.91 305	79.35 427	61.27 325	78.95 401	82.19 382	63.36 381	67.50 400	69.40 472	39.83 433	91.04 306	62.44 324	68.40 425	87.40 354

usedtu_dtu_shiyan1		76.43 295	75.32 297	79.76 312	83.00 366	60.72 337	81.74 352	88.76 252	68.99 300	72.98 332	84.19 355	56.41 271	90.27 325	62.39 325	79.40 312	88.31 330

FE-MVSNET3		76.43 295	75.32 297	79.76 312	83.00 366	60.72 337	81.74 352	88.76 252	68.99 300	72.98 332	84.19 355	56.41 271	90.27 325	62.39 325	79.40 312	88.31 330

FMVSNet2		78.20 254	77.21 258	81.20 270	87.60 232	62.89 297	87.47 188	89.02 237	71.63 220	75.29 295	87.28 271	54.80 281	91.10 302	62.38 327	79.38 314	89.61 287

testdata2													91.01 307	62.37 328

testing11		75.14 317	74.01 315	78.53 342	88.16 196	56.38 399	80.74 372	80.42 407	70.67 247	72.69 338	83.72 367	43.61 408	89.86 334	62.29 329	83.76 250	89.36 294

CP-MVSNet		78.22 252	78.34 226	77.84 356	87.83 215	54.54 422	87.94 174	91.17 150	77.65 46	73.48 326	88.49 238	62.24 197	88.43 364	62.19 330	74.07 386	90.55 243

XXY-MVS		75.41 313	75.56 289	74.96 391	83.59 349	57.82 375	80.59 375	83.87 353	66.54 336	74.93 306	88.31 243	63.24 176	80.09 438	62.16 331	76.85 344	86.97 375

pmmvs6		74.69 320	73.39 324	78.61 337	81.38 399	57.48 382	86.64 227	87.95 273	64.99 362	70.18 364	86.61 294	50.43 341	89.52 341	62.12 332	70.18 416	88.83 314

1112_ss		77.40 277	76.43 277	80.32 293	89.11 161	60.41 346	83.65 318	87.72 281	62.13 401	73.05 331	86.72 287	62.58 190	89.97 333	62.11 333	80.80 294	90.59 242

0.3-1-1-0.015		70.03 386	66.80 408	79.72 315	78.18 438	61.07 329	77.63 419	82.32 381	62.65 394	65.50 426	67.29 473	37.62 447	90.91 313	61.99 334	68.04 427	87.19 366

PS-CasMVS		78.01 261	78.09 231	77.77 358	87.71 225	54.39 424	88.02 170	91.22 147	77.50 54	73.26 328	88.64 233	60.73 225	88.41 365	61.88 335	73.88 390	90.53 244

CDS-MVSNet		79.07 232	77.70 246	83.17 205	87.60 232	68.23 141	84.40 302	86.20 321	67.49 321	76.36 264	86.54 299	61.54 209	90.79 317	61.86 336	87.33 185	90.49 246
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OpenMVS	72.83 10	79.77 211	78.33 227	84.09 160	85.17 309	69.91 93	90.57 69	90.97 156	66.70 329	72.17 345	91.91 121	54.70 285	93.96 145	61.81 337	90.95 113	88.41 329

0.4-1-1-0.2		70.01 387	66.86 407	79.44 323	77.61 444	60.64 341	76.77 426	82.34 380	62.40 397	65.91 424	66.65 474	40.05 430	90.83 315	61.77 338	68.24 426	86.86 377

K. test v3		71.19 368	68.51 380	79.21 328	83.04 365	57.78 377	84.35 303	76.91 440	72.90 201	62.99 445	82.86 385	39.27 435	91.09 304	61.65 339	52.66 473	88.75 318

CHOSEN 1792x2688		77.63 273	75.69 285	83.44 192	89.98 122	68.58 129	78.70 404	87.50 285	56.38 447	75.80 276	86.84 283	58.67 247	91.40 289	61.58 340	85.75 219	90.34 252

PCF-MVS	73.52 7	80.38 198	78.84 216	85.01 106	87.71 225	68.99 113	83.65 318	91.46 144	63.00 386	77.77 230	90.28 182	66.10 147	95.09 98	61.40 341	88.22 167	90.94 227
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HY-MVS	69.67 12	77.95 262	77.15 259	80.36 291	87.57 241	60.21 349	83.37 327	87.78 279	66.11 339	75.37 288	87.06 282	63.27 174	90.48 324	61.38 342	82.43 275	90.40 250

HyFIR lowres test		77.53 274	75.40 293	83.94 178	89.59 131	66.62 188	80.36 379	88.64 259	56.29 448	76.45 261	85.17 332	57.64 256	93.28 191	61.34 343	83.10 267	91.91 193

PMMVS		69.34 393	68.67 379	71.35 428	75.67 454	62.03 312	75.17 437	73.46 455	50.00 466	68.68 383	79.05 427	52.07 314	78.13 445	61.16 344	82.77 270	73.90 470

FMVSNet1		77.44 275	76.12 282	81.40 263	86.81 268	63.01 291	88.39 154	89.28 221	70.49 257	74.39 315	87.28 271	49.06 362	91.11 299	60.91 345	78.52 321	90.09 265

sss		73.60 334	73.64 322	73.51 409	82.80 374	55.01 418	76.12 429	81.69 388	62.47 396	74.68 310	85.85 314	57.32 260	78.11 446	60.86 346	80.93 290	87.39 355

Test_1112_low_res		76.40 298	75.44 291	79.27 326	89.28 150	58.09 367	81.69 355	87.07 301	59.53 422	72.48 340	86.67 292	61.30 216	89.33 344	60.81 347	80.15 303	90.41 249

sc_t1		72.19 362	69.51 373	80.23 296	84.81 319	61.09 328	84.68 287	80.22 411	60.70 411	71.27 354	83.58 371	36.59 450	89.24 347	60.41 348	63.31 450	90.37 251

BH-untuned		79.47 218	78.60 219	82.05 248	89.19 155	65.91 203	86.07 250	88.52 261	72.18 211	75.42 285	87.69 261	61.15 220	93.54 174	60.38 349	86.83 196	86.70 382

WTY-MVS		75.65 308	75.68 286	75.57 382	86.40 280	56.82 390	77.92 417	82.40 378	65.10 358	76.18 269	87.72 259	63.13 182	80.90 435	60.31 350	81.96 280	89.00 307

pmmvs4		74.03 330	71.91 341	80.39 289	81.96 388	68.32 135	81.45 359	82.14 383	59.32 423	69.87 372	85.13 333	52.40 306	88.13 368	60.21 351	74.74 382	84.73 419

PEN-MVS		77.73 267	77.69 247	77.84 356	87.07 263	53.91 427	87.91 176	91.18 149	77.56 51	73.14 330	88.82 228	61.23 218	89.17 349	59.95 352	72.37 401	90.43 248

CR-MVSNet		73.37 339	71.27 351	79.67 318	81.32 402	65.19 226	75.92 431	80.30 409	59.92 418	72.73 336	81.19 402	52.50 304	86.69 382	59.84 353	77.71 332	87.11 371

mvs5depth		69.45 392	67.45 401	75.46 386	73.93 461	55.83 407	79.19 396	83.23 363	66.89 325	71.63 351	83.32 375	33.69 458	85.09 402	59.81 354	55.34 470	85.46 405

lessismore_v0				78.97 331	81.01 405	57.15 386		65.99 475		61.16 451	82.82 386	39.12 437	91.34 291	59.67 355	46.92 480	88.43 328

CNLPA		78.08 257	76.79 268	81.97 251	90.40 109	71.07 70	87.59 185	84.55 342	66.03 342	72.38 342	89.64 201	57.56 257	86.04 391	59.61 356	83.35 262	88.79 316

BH-RMVSNet		79.61 213	78.44 223	83.14 206	89.38 144	65.93 202	84.95 282	87.15 298	73.56 180	78.19 218	89.79 196	56.67 268	93.36 189	59.53 357	86.74 197	90.13 261

FE-MVSNET2		72.88 354	71.28 350	77.67 359	78.30 436	57.78 377	84.43 299	88.92 244	69.56 280	64.61 434	81.67 400	46.73 379	88.54 363	59.33 358	67.99 428	86.69 383

MS-PatchMatch		73.83 331	72.67 333	77.30 368	83.87 341	66.02 198	81.82 350	84.66 340	61.37 408	68.61 385	82.82 386	47.29 370	88.21 366	59.27 359	84.32 242	77.68 464

test_post1							78.90 403				5.43 498	48.81 366	85.44 400	59.25 360

SCA		74.22 325	72.33 338	79.91 305	84.05 337	62.17 309	79.96 387	79.29 421	66.30 338	72.38 342	80.13 417	51.95 316	88.60 361	59.25 360	77.67 335	88.96 309

FE-MVS		77.78 266	75.68 286	84.08 161	88.09 202	66.00 200	83.13 332	87.79 278	68.42 312	78.01 223	85.23 330	45.50 395	95.12 92	59.11 362	85.83 218	91.11 218

SixPastTwentyTwo		73.37 339	71.26 352	79.70 316	85.08 314	57.89 373	85.57 261	83.56 357	71.03 239	65.66 425	85.88 312	42.10 418	92.57 231	59.11 362	63.34 449	88.65 322

WR-MVS_H		78.51 247	78.49 221	78.56 340	88.02 205	56.38 399	88.43 151	92.67 72	77.14 65	73.89 320	87.55 266	66.25 144	89.24 347	58.92 364	73.55 393	90.06 269

PLC	70.83 11	78.05 259	76.37 280	83.08 210	91.88 83	67.80 156	88.19 164	89.46 210	64.33 370	69.87 372	88.38 241	53.66 295	93.58 167	58.86 365	82.73 271	87.86 342
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
RPSCF		73.23 346	71.46 346	78.54 341	82.50 381	59.85 351	82.18 347	82.84 375	58.96 427	71.15 357	89.41 213	45.48 396	84.77 406	58.82 366	71.83 407	91.02 224

EU-MVSNet		68.53 401	67.61 398	71.31 429	78.51 433	47.01 467	84.47 294	84.27 347	42.27 476	66.44 420	84.79 341	40.44 428	83.76 412	58.76 367	68.54 424	83.17 434

pmmvs-eth3d		70.50 379	67.83 393	78.52 343	77.37 447	66.18 195	81.82 350	81.51 390	58.90 428	63.90 441	80.42 412	42.69 413	86.28 388	58.56 368	65.30 445	83.11 436

TAMVS		78.89 238	77.51 253	83.03 213	87.80 216	67.79 157	84.72 286	85.05 337	67.63 318	76.75 253	87.70 260	62.25 196	90.82 316	58.53 369	87.13 190	90.49 246

WBMVS		73.43 336	72.81 332	75.28 388	87.91 210	50.99 452	78.59 407	81.31 394	65.51 351	74.47 314	84.83 339	46.39 380	86.68 383	58.41 370	77.86 330	88.17 336

ACMH+	68.96 14	76.01 304	74.01 315	82.03 249	88.60 180	65.31 224	88.86 130	87.55 283	70.25 264	67.75 397	87.47 269	41.27 423	93.19 203	58.37 371	75.94 360	87.60 347

tpm		72.37 358	71.71 343	74.35 399	82.19 386	52.00 440	79.22 395	77.29 437	64.56 365	72.95 334	83.68 369	51.35 326	83.26 420	58.33 372	75.80 361	87.81 343

BH-w/o		78.21 253	77.33 257	80.84 280	88.81 168	65.13 228	84.87 283	87.85 277	69.75 277	74.52 313	84.74 342	61.34 215	93.11 208	58.24 373	85.84 217	84.27 422

Vis-MVSNet (Re-imp)		78.36 250	78.45 222	78.07 352	88.64 179	51.78 445	86.70 224	79.63 417	74.14 165	75.11 300	90.83 166	61.29 217	89.75 337	58.10 374	91.60 99	92.69 159

MVP-Stereo		76.12 301	74.46 311	81.13 273	85.37 305	69.79 95	84.42 301	87.95 273	65.03 360	67.46 402	85.33 327	53.28 300	91.73 269	58.01 375	83.27 264	81.85 449
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ambc				75.24 389	73.16 469	50.51 455	63.05 485	87.47 286		64.28 436	77.81 439	17.80 485	89.73 338	57.88 376	60.64 459	85.49 404

TR-MVS		77.44 275	76.18 281	81.20 270	88.24 193	63.24 286	84.61 291	86.40 317	67.55 320	77.81 228	86.48 301	54.10 290	93.15 205	57.75 377	82.72 272	87.20 365

F-COLMAP		76.38 299	74.33 313	82.50 239	89.28 150	66.95 186	88.41 153	89.03 236	64.05 374	66.83 411	88.61 234	46.78 377	92.89 218	57.48 378	78.55 320	87.67 345

EG-PatchMatch MVS		74.04 328	71.82 342	80.71 283	84.92 317	67.42 168	85.86 256	88.08 267	66.04 341	64.22 437	83.85 361	35.10 455	92.56 232	57.44 379	80.83 293	82.16 447

PatchmatchNet		73.12 347	71.33 349	78.49 344	83.18 360	60.85 335	79.63 389	78.57 426	64.13 371	71.73 349	79.81 422	51.20 332	85.97 392	57.40 380	76.36 357	88.66 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DTE-MVSNet		76.99 283	76.80 267	77.54 365	86.24 282	53.06 437	87.52 186	90.66 166	77.08 69	72.50 339	88.67 232	60.48 233	89.52 341	57.33 381	70.74 413	90.05 270

UnsupCasMVSNet_eth		67.33 408	65.99 412	71.37 426	73.48 466	51.47 448	75.16 438	85.19 333	65.20 355	60.78 452	80.93 409	42.35 414	77.20 450	57.12 382	53.69 472	85.44 406

pmmvs5		71.55 366	70.20 370	75.61 381	77.83 440	56.39 398	81.74 352	80.89 396	57.76 438	67.46 402	84.49 343	49.26 359	85.32 401	57.08 383	75.29 375	85.11 413

testing3-2		75.12 318	75.19 300	74.91 392	90.40 109	45.09 475	80.29 381	78.42 427	78.37 40	76.54 260	87.75 258	44.36 402	87.28 379	57.04 384	83.49 259	92.37 173

Anonymous20240521		68.80 397	67.22 404	73.55 408	74.33 459	54.11 425	83.18 330	85.61 329	58.15 434	61.68 449	80.94 407	30.71 465	81.27 433	57.00 385	73.34 397	85.28 408

mvsany_test1		62.30 431	61.26 435	65.41 453	69.52 477	54.86 419	66.86 472	49.78 493	46.65 470	68.50 389	83.21 377	49.15 360	66.28 485	56.93 386	60.77 458	75.11 469

TransMVSNet (Re)		75.39 315	74.56 308	77.86 355	85.50 302	57.10 387	86.78 221	86.09 324	72.17 212	71.53 352	87.34 270	63.01 183	89.31 345	56.84 387	61.83 455	87.17 367

tt0320-xc		70.11 384	67.45 401	78.07 352	85.33 306	59.51 357	83.28 328	78.96 424	58.77 429	67.10 408	80.28 415	36.73 449	87.42 377	56.83 388	59.77 462	87.29 362

test_vis3_rt		49.26 451	47.02 453	56.00 464	54.30 493	45.27 474	66.76 474	48.08 494	36.83 483	44.38 482	53.20 487	7.17 498	64.07 487	56.77 389	55.66 467	58.65 483

EPMVS		69.02 395	68.16 384	71.59 424	79.61 423	49.80 459	77.40 421	66.93 473	62.82 391	70.01 367	79.05 427	45.79 390	77.86 448	56.58 390	75.26 376	87.13 370

KD-MVS_self_test		68.81 396	67.59 399	72.46 420	74.29 460	45.45 470	77.93 416	87.00 302	63.12 383	63.99 440	78.99 431	42.32 415	84.77 406	56.55 391	64.09 448	87.16 369

tpm2		73.26 344	71.46 346	78.63 336	83.34 354	56.71 393	80.65 374	80.40 408	56.63 446	73.55 325	82.02 398	51.80 322	91.24 294	56.35 392	78.42 326	87.95 339

LTVRE_ROB	69.57 13	76.25 300	74.54 309	81.41 262	88.60 180	64.38 256	79.24 394	89.12 234	70.76 246	69.79 374	87.86 257	49.09 361	93.20 201	56.21 393	80.16 302	86.65 384
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	75.89 305	73.93 317	81.77 254	88.71 177	66.61 189	88.62 145	89.01 238	69.81 273	66.78 412	86.70 291	41.95 420	91.51 283	55.64 394	78.14 329	87.17 367
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		66.51 415	64.71 417	71.90 422	81.45 397	63.52 279	57.98 487	68.95 469	53.57 456	62.59 447	76.70 445	46.22 385	75.29 469	55.25 395	79.68 307	76.88 466

tt0320		70.49 380	68.03 387	77.89 354	84.78 320	59.12 359	83.55 322	80.44 406	58.13 435	67.43 404	80.41 413	39.26 436	87.54 376	55.12 396	63.18 451	86.99 374

UBG		73.08 348	72.27 339	75.51 384	88.02 205	51.29 450	78.35 411	77.38 436	65.52 349	73.87 321	82.36 391	45.55 393	86.48 386	55.02 397	84.39 241	88.75 318

EPNet_dtu		75.46 311	74.86 303	77.23 369	82.57 380	54.60 421	86.89 215	83.09 367	71.64 219	66.25 421	85.86 313	55.99 273	88.04 369	54.92 398	86.55 200	89.05 303
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsany_test3		53.99 442	51.45 447	61.61 458	55.51 492	44.74 477	63.52 483	45.41 497	43.69 475	58.11 463	76.45 447	17.99 484	63.76 488	54.77 399	47.59 479	76.34 467

PVSNet	64.34 18	72.08 364	70.87 359	75.69 380	86.21 283	56.44 397	74.37 445	80.73 399	62.06 402	70.17 365	82.23 395	42.86 412	83.31 419	54.77 399	84.45 239	87.32 361

ITE_SJBPF				78.22 347	81.77 391	60.57 342		83.30 361	69.25 289	67.54 399	87.20 276	36.33 452	87.28 379	54.34 401	74.62 383	86.80 379

SSC-MVS3.2		73.35 342	73.39 324	73.23 410	85.30 307	49.01 460	74.58 444	81.57 389	75.21 130	73.68 323	85.58 321	52.53 302	82.05 427	54.33 402	77.69 334	88.63 323

MDTV_nov1_ep13_2view						37.79 489	75.16 438		55.10 452	66.53 416		49.34 357		53.98 403		87.94 340

gg-mvs-nofinetune		69.95 388	67.96 388	75.94 377	83.07 363	54.51 423	77.23 423	70.29 463	63.11 384	70.32 362	62.33 477	43.62 407	88.69 359	53.88 404	87.76 178	84.62 420

PatchMatch-RL		72.38 357	70.90 358	76.80 373	88.60 180	67.38 171	79.53 390	76.17 445	62.75 392	69.36 377	82.00 399	45.51 394	84.89 405	53.62 405	80.58 297	78.12 463

test_f		52.09 447	50.82 448	55.90 465	53.82 495	42.31 484	59.42 486	58.31 489	36.45 484	56.12 471	70.96 469	12.18 490	57.79 491	53.51 406	56.57 466	67.60 476

Patchmtry		70.74 375	69.16 377	75.49 385	80.72 406	54.07 426	74.94 442	80.30 409	58.34 432	70.01 367	81.19 402	52.50 304	86.54 384	53.37 407	71.09 412	85.87 400

USDC		70.33 381	68.37 381	76.21 376	80.60 408	56.23 402	79.19 396	86.49 315	60.89 409	61.29 450	85.47 324	31.78 462	89.47 343	53.37 407	76.21 358	82.94 440

LF4IMVS		64.02 427	62.19 430	69.50 437	70.90 475	53.29 434	76.13 428	77.18 438	52.65 459	58.59 460	80.98 406	23.55 478	76.52 455	53.06 409	66.66 432	78.68 462

PAPM		77.68 271	76.40 279	81.51 259	87.29 251	61.85 315	83.78 314	89.59 206	64.74 363	71.23 355	88.70 230	62.59 189	93.66 166	52.66 410	87.03 192	89.01 305

dmvs_re		71.14 369	70.58 363	72.80 417	81.96 388	59.68 353	75.60 435	79.34 420	68.55 308	69.27 380	80.72 410	49.42 355	76.54 454	52.56 411	77.79 331	82.19 446

CL-MVSNet_self_test		72.37 358	71.46 346	75.09 390	79.49 425	53.53 429	80.76 371	85.01 338	69.12 294	70.51 359	82.05 397	57.92 253	84.13 410	52.27 412	66.00 436	87.60 347

tpm cat1		70.57 377	68.31 382	77.35 367	82.41 384	57.95 372	78.08 413	80.22 411	52.04 460	68.54 388	77.66 440	52.00 315	87.84 372	51.77 413	72.07 406	86.25 388

our_test_3		69.14 394	67.00 405	75.57 382	79.80 420	58.80 360	77.96 415	77.81 430	59.55 421	62.90 446	78.25 436	47.43 369	83.97 411	51.71 414	67.58 430	83.93 428

MDTV_nov1_ep13			69.97 371		83.18 360	53.48 430	77.10 425	80.18 413	60.45 412	69.33 378	80.44 411	48.89 365	86.90 381	51.60 415	78.51 322

myMVS_eth3d28		73.62 333	73.53 323	73.90 406	88.20 194	47.41 465	78.06 414	79.37 419	74.29 161	73.98 319	84.29 350	44.67 398	83.54 416	51.47 416	87.39 184	90.74 235

JIA-IIPM		66.32 417	62.82 429	76.82 372	77.09 448	61.72 318	65.34 478	75.38 446	58.04 437	64.51 435	62.32 478	42.05 419	86.51 385	51.45 417	69.22 420	82.21 445

testing222		74.04 328	72.66 334	78.19 348	87.89 211	55.36 413	81.06 366	79.20 422	71.30 230	74.65 311	83.57 372	39.11 438	88.67 360	51.43 418	85.75 219	90.53 244

MSDG		73.36 341	70.99 356	80.49 288	84.51 328	65.80 208	80.71 373	86.13 323	65.70 346	65.46 427	83.74 365	44.60 399	90.91 313	51.13 419	76.89 342	84.74 418

PatchT		68.46 402	67.85 391	70.29 434	80.70 407	43.93 478	72.47 450	74.88 449	60.15 416	70.55 358	76.57 446	49.94 348	81.59 429	50.58 420	74.83 381	85.34 407

GG-mvs-BLEND				75.38 387	81.59 394	55.80 408	79.32 393	69.63 465		67.19 406	73.67 463	43.24 409	88.90 357	50.41 421	84.50 235	81.45 451

KD-MVS_2432*1600		66.22 418	63.89 421	73.21 411	75.47 457	53.42 431	70.76 458	84.35 344	64.10 372	66.52 417	78.52 433	34.55 456	84.98 403	50.40 422	50.33 477	81.23 452

miper_refine_blended		66.22 418	63.89 421	73.21 411	75.47 457	53.42 431	70.76 458	84.35 344	64.10 372	66.52 417	78.52 433	34.55 456	84.98 403	50.40 422	50.33 477	81.23 452

AllTest		70.96 371	68.09 386	79.58 320	85.15 311	63.62 270	84.58 292	79.83 414	62.31 398	60.32 455	86.73 285	32.02 460	88.96 355	50.28 424	71.57 409	86.15 391

TestCases				79.58 320	85.15 311	63.62 270		79.83 414	62.31 398	60.32 455	86.73 285	32.02 460	88.96 355	50.28 424	71.57 409	86.15 391

TAPA-MVS	73.13 9	79.15 229	77.94 234	82.79 229	89.59 131	62.99 295	88.16 166	91.51 140	65.77 345	77.14 247	91.09 157	60.91 224	93.21 198	50.26 426	87.05 191	92.17 187
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
YYNet1		65.03 422	62.91 427	71.38 425	75.85 453	56.60 395	69.12 466	74.66 453	57.28 443	54.12 472	77.87 438	45.85 389	74.48 471	49.95 427	61.52 457	83.05 437

MDA-MVSNet_test_wron		65.03 422	62.92 426	71.37 426	75.93 450	56.73 391	69.09 467	74.73 451	57.28 443	54.03 473	77.89 437	45.88 388	74.39 472	49.89 428	61.55 456	82.99 439

tpmvs		71.09 370	69.29 375	76.49 374	82.04 387	56.04 404	78.92 402	81.37 393	64.05 374	67.18 407	78.28 435	49.74 352	89.77 336	49.67 429	72.37 401	83.67 430

SD_0403		74.65 321	74.77 305	74.29 400	86.20 284	47.42 464	83.71 316	85.12 334	69.30 286	68.50 389	87.95 256	59.40 241	86.05 390	49.38 430	83.35 262	89.40 292

ppachtmachnet_test		70.04 385	67.34 403	78.14 349	79.80 420	61.13 326	79.19 396	80.59 401	59.16 425	65.27 429	79.29 426	46.75 378	87.29 378	49.33 431	66.72 431	86.00 397

UnsupCasMVSNet_bld		63.70 428	61.53 434	70.21 435	73.69 464	51.39 449	72.82 449	81.89 385	55.63 451	57.81 464	71.80 467	38.67 440	78.61 443	49.26 432	52.21 475	80.63 456

UWE-MVS		72.13 363	71.49 345	74.03 404	86.66 274	47.70 462	81.40 361	76.89 441	63.60 380	75.59 278	84.22 354	39.94 431	85.62 396	48.98 433	86.13 209	88.77 317

dp		66.80 412	65.43 413	70.90 433	79.74 422	48.82 461	75.12 440	74.77 450	59.61 420	64.08 439	77.23 443	42.89 411	80.72 436	48.86 434	66.58 433	83.16 435

FMVSNet5		69.50 391	67.96 388	74.15 402	82.97 371	55.35 414	80.01 386	82.12 384	62.56 395	63.02 443	81.53 401	36.92 448	81.92 428	48.42 435	74.06 387	85.17 412

thres100view900		76.50 291	75.55 290	79.33 325	89.52 134	56.99 388	85.83 258	83.23 363	73.94 169	76.32 265	87.12 279	51.89 320	91.95 259	48.33 436	83.75 251	89.07 298

tfpn200view9		76.42 297	75.37 295	79.55 322	89.13 157	57.65 379	85.17 273	83.60 355	73.41 186	76.45 261	86.39 303	52.12 310	91.95 259	48.33 436	83.75 251	89.07 298

thres400		76.50 291	75.37 295	79.86 307	89.13 157	57.65 379	85.17 273	83.60 355	73.41 186	76.45 261	86.39 303	52.12 310	91.95 259	48.33 436	83.75 251	90.00 271

LCM-MVSNet		54.25 441	49.68 451	67.97 448	53.73 496	45.28 473	66.85 473	80.78 398	35.96 485	39.45 486	62.23 479	8.70 495	78.06 447	48.24 439	51.20 476	80.57 457

RPMNet		73.51 335	70.49 365	82.58 238	81.32 402	65.19 226	75.92 431	92.27 93	57.60 440	72.73 336	76.45 447	52.30 307	95.43 77	48.14 440	77.71 332	87.11 371

thres600view7		76.50 291	75.44 291	79.68 317	89.40 142	57.16 385	85.53 267	83.23 363	73.79 173	76.26 266	87.09 280	51.89 320	91.89 262	48.05 441	83.72 254	90.00 271

TDRefinement		67.49 406	64.34 418	76.92 371	73.47 467	61.07 329	84.86 284	82.98 371	59.77 419	58.30 462	85.13 333	26.06 471	87.89 371	47.92 442	60.59 460	81.81 450

thres200		75.55 309	74.47 310	78.82 334	87.78 219	57.85 374	83.07 336	83.51 358	72.44 207	75.84 275	84.42 345	52.08 313	91.75 267	47.41 443	83.64 256	86.86 377

PVSNet_0	57.27 20	61.67 433	59.27 436	68.85 441	79.61 423	57.44 383	68.01 468	73.44 456	55.93 450	58.54 461	70.41 470	44.58 400	77.55 449	47.01 444	35.91 485	71.55 473

DP-MVS		76.78 287	74.57 307	83.42 193	93.29 52	69.46 104	88.55 149	83.70 354	63.98 376	70.20 363	88.89 226	54.01 293	94.80 112	46.66 445	81.88 282	86.01 395

COLMAP_ROB	66.92 17	73.01 349	70.41 367	80.81 281	87.13 255	65.63 211	88.30 161	84.19 349	62.96 387	63.80 442	87.69 261	38.04 444	92.56 232	46.66 445	74.91 380	84.24 423
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet		70.69 376	69.30 374	74.88 393	84.52 327	56.35 401	75.87 433	79.42 418	64.59 364	67.76 396	82.41 390	41.10 424	81.54 430	46.64 447	81.34 285	86.75 381

LS3D		76.95 285	74.82 304	83.37 196	90.45 107	67.36 172	89.15 120	86.94 304	61.87 404	69.52 375	90.61 174	51.71 324	94.53 123	46.38 448	86.71 198	88.21 335

ETVMVS		72.25 361	71.05 355	75.84 378	87.77 221	51.91 442	79.39 392	74.98 448	69.26 288	73.71 322	82.95 382	40.82 427	86.14 389	46.17 449	84.43 240	89.47 290

MDA-MVSNet-bldmvs		66.68 413	63.66 423	75.75 379	79.28 428	60.56 343	73.92 447	78.35 428	64.43 366	50.13 478	79.87 421	44.02 405	83.67 413	46.10 450	56.86 464	83.03 438

new-patchmatchnet		61.73 432	61.73 432	61.70 457	72.74 472	24.50 500	69.16 465	78.03 429	61.40 406	56.72 467	75.53 458	38.42 441	76.48 456	45.95 451	57.67 463	84.13 425

WB-MVSnew		71.96 365	71.65 344	72.89 416	84.67 326	51.88 443	82.29 345	77.57 432	62.31 398	73.67 324	83.00 381	53.49 298	81.10 434	45.75 452	82.13 278	85.70 401

TinyColmap		67.30 409	64.81 416	74.76 395	81.92 390	56.68 394	80.29 381	81.49 391	60.33 413	56.27 470	83.22 376	24.77 475	87.66 375	45.52 453	69.47 418	79.95 459

pmmvs3		57.79 437	54.26 442	68.37 444	64.02 486	56.72 392	75.12 440	65.17 477	40.20 478	52.93 474	69.86 471	20.36 482	75.48 466	45.45 454	55.25 471	72.90 472

OpenMVS_ROB	64.09 19	70.56 378	68.19 383	77.65 361	80.26 411	59.41 358	85.01 280	82.96 372	58.76 430	65.43 428	82.33 392	37.63 446	91.23 295	45.34 455	76.03 359	82.32 444

test0.0.03 1		68.00 405	67.69 396	68.90 440	77.55 445	47.43 463	75.70 434	72.95 459	66.66 330	66.56 415	82.29 394	48.06 367	75.87 463	44.97 456	74.51 384	83.41 432

testgi		66.67 414	66.53 410	67.08 450	75.62 455	41.69 485	75.93 430	76.50 442	66.11 339	65.20 432	86.59 295	35.72 454	74.71 470	43.71 457	73.38 396	84.84 417

Anonymous20231206		68.60 398	67.80 394	71.02 431	80.23 413	50.75 454	78.30 412	80.47 404	56.79 445	66.11 423	82.63 389	46.35 383	78.95 442	43.62 458	75.70 362	83.36 433

FE-MVSNET		67.25 410	65.33 414	73.02 415	75.86 452	52.54 438	80.26 383	80.56 402	63.80 379	60.39 453	79.70 423	41.41 422	84.66 408	43.34 459	62.62 453	81.86 448

tfpnnormal		74.39 322	73.16 328	78.08 351	86.10 288	58.05 368	84.65 290	87.53 284	70.32 261	71.22 356	85.63 319	54.97 279	89.86 334	43.03 460	75.02 379	86.32 387

MIMVSNet1		68.58 399	66.78 409	73.98 405	80.07 415	51.82 444	80.77 370	84.37 343	64.40 368	59.75 458	82.16 396	36.47 451	83.63 414	42.73 461	70.33 415	86.48 386

usedtu_dtu_shiyan2		64.75 425	61.63 433	74.10 403	70.64 476	53.18 436	82.10 349	81.27 395	56.22 449	56.39 469	74.67 460	27.94 469	83.56 415	42.71 462	62.73 452	85.57 403

ttmdpeth		59.91 435	57.10 439	68.34 445	67.13 482	46.65 469	74.64 443	67.41 472	48.30 468	62.52 448	85.04 337	20.40 481	75.93 462	42.55 463	45.90 483	82.44 443

test20.03		67.45 407	66.95 406	68.94 439	75.48 456	44.84 476	77.50 420	77.67 431	66.66 330	63.01 444	83.80 363	47.02 373	78.40 444	42.53 464	68.86 423	83.58 431

ADS-MVSNet2		66.20 420	63.33 424	74.82 394	79.92 416	58.75 361	67.55 470	75.19 447	53.37 457	65.25 430	75.86 455	42.32 415	80.53 437	41.57 465	68.91 421	85.18 410

ADS-MVSNet		64.36 426	62.88 428	68.78 442	79.92 416	47.17 466	67.55 470	71.18 461	53.37 457	65.25 430	75.86 455	42.32 415	73.99 474	41.57 465	68.91 421	85.18 410

Patchmatch-test		64.82 424	63.24 425	69.57 436	79.42 426	49.82 458	63.49 484	69.05 468	51.98 462	59.95 457	80.13 417	50.91 334	70.98 478	40.66 467	73.57 392	87.90 341

MVS-HIRNet		59.14 436	57.67 438	63.57 455	81.65 392	43.50 479	71.73 452	65.06 478	39.59 480	51.43 475	57.73 483	38.34 442	82.58 424	39.53 468	73.95 388	64.62 479

WAC-MVS						42.58 481								39.46 469

myMVS_eth3d		67.02 411	66.29 411	69.21 438	84.68 323	42.58 481	78.62 405	73.08 457	66.65 333	66.74 413	79.46 424	31.53 463	82.30 425	39.43 470	76.38 355	82.75 441

DSMNet-mixed		57.77 438	56.90 440	60.38 459	67.70 480	35.61 490	69.18 464	53.97 491	32.30 489	57.49 465	79.88 420	40.39 429	68.57 484	38.78 471	72.37 401	76.97 465

N_pmnet		52.79 446	53.26 444	51.40 471	78.99 430	7.68 505	69.52 462	3.89 504	51.63 463	57.01 466	74.98 459	40.83 426	65.96 486	37.78 472	64.67 446	80.56 458

testing3		68.56 400	67.67 397	71.22 430	87.33 247	42.87 480	83.06 337	71.54 460	70.36 258	69.08 381	84.38 347	30.33 466	85.69 395	37.50 473	75.45 370	85.09 414

MVStest1		56.63 439	52.76 445	68.25 446	61.67 488	53.25 435	71.67 453	68.90 470	38.59 481	50.59 477	83.05 380	25.08 473	70.66 479	36.76 474	38.56 484	80.83 455

test_0402		72.79 355	70.44 366	79.84 308	88.13 199	65.99 201	85.93 253	84.29 346	65.57 348	67.40 405	85.49 323	46.92 374	92.61 228	35.88 475	74.38 385	80.94 454

new_pmnet		50.91 449	50.29 449	52.78 470	68.58 479	34.94 492	63.71 482	56.63 490	39.73 479	44.95 481	65.47 476	21.93 480	58.48 490	34.98 476	56.62 465	64.92 478

APD_test1		53.31 445	49.93 450	63.42 456	65.68 483	50.13 456	71.59 454	66.90 474	34.43 486	40.58 485	71.56 468	8.65 496	76.27 458	34.64 477	55.36 469	63.86 480

Syy-MVS		68.05 404	67.85 391	68.67 443	84.68 323	40.97 486	78.62 405	73.08 457	66.65 333	66.74 413	79.46 424	52.11 312	82.30 425	32.89 478	76.38 355	82.75 441

dmvs_testset		62.63 430	64.11 420	58.19 461	78.55 432	24.76 499	75.28 436	65.94 476	67.91 317	60.34 454	76.01 454	53.56 296	73.94 475	31.79 479	67.65 429	75.88 468

UWE-MVS-28		65.32 421	64.93 415	66.49 451	78.70 431	38.55 488	77.86 418	64.39 480	62.00 403	64.13 438	83.60 370	41.44 421	76.00 461	31.39 480	80.89 291	84.92 415

ANet_high		50.57 450	46.10 454	63.99 454	48.67 499	39.13 487	70.99 457	80.85 397	61.39 407	31.18 488	57.70 484	17.02 486	73.65 476	31.22 481	15.89 496	79.18 461

EGC-MVSNET		52.07 448	47.05 452	67.14 449	83.51 351	60.71 339	80.50 377	67.75 471	0.07 499	0.43 500	75.85 457	24.26 476	81.54 430	28.82 482	62.25 454	59.16 482

PMMVS2		40.82 457	38.86 461	46.69 472	53.84 494	16.45 503	48.61 490	49.92 492	37.49 482	31.67 487	60.97 480	8.14 497	56.42 492	28.42 483	30.72 489	67.19 477

tmp_tt		18.61 464	21.40 467	10.23 481	4.82 504	10.11 504	34.70 492	30.74 502	1.48 498	23.91 494	26.07 495	28.42 468	13.41 500	27.12 484	15.35 497	7.17 495

test_method		31.52 460	29.28 464	38.23 475	27.03 503	6.50 506	20.94 495	62.21 483	4.05 497	22.35 495	52.50 488	13.33 488	47.58 495	27.04 485	34.04 487	60.62 481

testf1		45.72 452	41.96 456	57.00 462	56.90 490	45.32 471	66.14 475	59.26 487	26.19 490	30.89 489	60.96 481	4.14 499	70.64 480	26.39 486	46.73 481	55.04 485

APD_test2		45.72 452	41.96 456	57.00 462	56.90 490	45.32 471	66.14 475	59.26 487	26.19 490	30.89 489	60.96 481	4.14 499	70.64 480	26.39 486	46.73 481	55.04 485

FPMVS		53.68 444	51.64 446	59.81 460	65.08 484	51.03 451	69.48 463	69.58 466	41.46 477	40.67 484	72.32 466	16.46 487	70.00 482	24.24 488	65.42 444	58.40 484

Gipuma		45.18 455	41.86 458	55.16 468	77.03 449	51.52 447	32.50 493	80.52 403	32.46 488	27.12 491	35.02 492	9.52 494	75.50 465	22.31 489	60.21 461	38.45 491
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
dongtai		45.42 454	45.38 455	45.55 473	73.36 468	26.85 497	67.72 469	34.19 499	54.15 455	49.65 479	56.41 486	25.43 472	62.94 489	19.45 490	28.09 490	46.86 489

DeepMVS_CX				27.40 479	40.17 502	26.90 496		24.59 503	17.44 495	23.95 493	48.61 490	9.77 493	26.48 498	18.06 491	24.47 492	28.83 492

WB-MVS		54.94 440	54.72 441	55.60 467	73.50 465	20.90 501	74.27 446	61.19 484	59.16 425	50.61 476	74.15 461	47.19 372	75.78 464	17.31 492	35.07 486	70.12 474

PMVS	37.38 22	44.16 456	40.28 460	55.82 466	40.82 501	42.54 483	65.12 479	63.99 481	34.43 486	24.48 492	57.12 485	3.92 501	76.17 460	17.10 493	55.52 468	48.75 487
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 462	25.89 466	43.81 474	44.55 500	35.46 491	28.87 494	39.07 498	18.20 494	18.58 496	40.18 491	2.68 502	47.37 496	17.07 494	23.78 493	48.60 488
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SSC-MVS		53.88 443	53.59 443	54.75 469	72.87 471	19.59 502	73.84 448	60.53 486	57.58 441	49.18 480	73.45 464	46.34 384	75.47 467	16.20 495	32.28 488	69.20 475

E-PMN		31.77 459	30.64 462	35.15 477	52.87 497	27.67 494	57.09 488	47.86 495	24.64 492	16.40 497	33.05 493	11.23 492	54.90 493	14.46 496	18.15 494	22.87 493

EMVS		30.81 461	29.65 463	34.27 478	50.96 498	25.95 498	56.58 489	46.80 496	24.01 493	15.53 498	30.68 494	12.47 489	54.43 494	12.81 497	17.05 495	22.43 494

kuosan		39.70 458	40.40 459	37.58 476	64.52 485	26.98 495	65.62 477	33.02 500	46.12 471	42.79 483	48.99 489	24.10 477	46.56 497	12.16 498	26.30 491	39.20 490

wuyk23d		16.82 465	15.94 468	19.46 480	58.74 489	31.45 493	39.22 491	3.74 505	6.84 496	6.04 499	2.70 499	1.27 503	24.29 499	10.54 499	14.40 498	2.63 496

testmvs		6.04 468	8.02 471	0.10 483	0.08 505	0.03 508	69.74 461	0.04 506	0.05 500	0.31 501	1.68 500	0.02 505	0.04 501	0.24 500	0.02 499	0.25 498

test123		6.12 467	8.11 470	0.14 482	0.06 506	0.09 507	71.05 456	0.03 507	0.04 501	0.25 502	1.30 501	0.05 504	0.03 502	0.21 501	0.01 500	0.29 497

mmdepth		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

monomultidepth		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

test_blank		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

uanet_test		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

DCPMVS		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

cdsmvs_eth3d_5k		19.96 463	26.61 465	0.00 484	0.00 507	0.00 509	0.00 496	89.26 224	0.00 502	0.00 503	88.61 234	61.62 208	0.00 503	0.00 502	0.00 501	0.00 499

pcd_1.5k_mvsjas		5.26 469	7.02 472	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	63.15 179	0.00 503	0.00 502	0.00 501	0.00 499

sosnet-low-res		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

sosnet		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

uncertanet		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

Regformer		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

ab-mvs-re		7.23 466	9.64 469	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	86.72 287	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

uanet		0.00 470	0.00 473	0.00 484	0.00 507	0.00 509	0.00 496	0.00 508	0.00 502	0.00 503	0.00 502	0.00 506	0.00 503	0.00 502	0.00 501	0.00 499

TestfortrainingZip							93.28 12

FOURS1					95.00 10	72.39 41	95.06 1	93.84 20	74.49 153	91.30 18

test_one_0601					95.07 7	71.46 59		94.14 10	78.27 41	92.05 14	95.74 6	80.83 13

eth-test2					0.00 507

eth-test					0.00 507

test_241102_ONE					95.30 2	70.98 71		94.06 15	77.17 64	93.10 1	95.39 16	82.99 1	97.27 15

save fliter					93.80 44	72.35 44	90.47 74	91.17 150	74.31 159

test0726					95.27 5	71.25 64	93.60 7	94.11 11	77.33 58	92.81 3	95.79 3	80.98 11

GSMVS																88.96 309

test_part2					95.06 8	72.65 32				91.80 16

sam_mvs1												51.32 327				88.96 309

sam_mvs												50.01 346

MTGPA								92.02 111

test_post											5.46 497	50.36 342	84.24 409

patchmatchnet-post											74.00 462	51.12 333	88.60 361

MTMP							92.18 39	32.83 501

TEST9					93.26 56	72.96 25	88.75 138	91.89 119	68.44 311	85.00 80	93.10 88	74.36 32	95.41 80

test_8					93.13 60	72.57 35	88.68 143	91.84 123	68.69 306	84.87 84	93.10 88	74.43 30	95.16 90

agg_prior					92.85 68	71.94 52		91.78 127		84.41 95			94.93 101

test_prior4						72.60 34	89.01 125

test_prior				86.33 64	92.61 74	69.59 98		92.97 59					95.48 74			93.91 87

新几何2							86.29 244

旧先验1					91.96 80	65.79 209		86.37 318			93.08 92	69.31 99			92.74 80	88.74 320

原ACMM2							86.86 217

test222					91.50 86	68.26 137	84.16 308	83.20 366	54.63 454	79.74 185	91.63 135	58.97 244			91.42 103	86.77 380

segment_acmp												73.08 43

testdata1							84.14 309		75.71 112

test12				86.80 58	92.63 73	70.70 81		91.79 126		82.71 137		71.67 63	96.16 52		94.50 57	93.54 116

plane_prior7					90.08 116	68.51 131

plane_prior6					89.84 125	68.70 125						60.42 234

plane_prior4											91.00 162

plane_prior3						68.60 128			78.44 36	78.92 200

plane_prior2							91.25 60		79.12 28

plane_prior1					89.90 124

plane_prior						68.71 123	90.38 78		77.62 47						86.16 208

n2								0.00 508

nn								0.00 508

door-mid								69.98 464

test11								92.23 97

door								69.44 467

HQP5-MVS						66.98 183

HQP-NCC					89.33 145		89.17 116		76.41 90	77.23 241

ACMP_Plane					89.33 145		89.17 116		76.41 90	77.23 241

HQP4-MVS										77.24 240			95.11 94			91.03 222

HQP3-MVS								92.19 105							85.99 212

HQP2-MVS												60.17 237

NP-MVS					89.62 130	68.32 135					90.24 184

ACMMP++_ref															81.95 281

ACMMP++															81.25 286

Test By Simon												64.33 165

High-resolution multi-view benchmark