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 6	89.23 7	88.97 4	90.79 95	73.65 10	92.66 23	91.17 126	86.57 1	87.39 48	94.97 19	71.70 55	97.68 1	92.19 1	95.63 28	95.57 1

fmvsm_s_conf0.5_n_4		85.39 67	85.75 60	84.30 117	86.70 238	65.83 184	88.77 123	89.78 168	75.46 100	88.35 27	93.73 63	69.19 87	93.06 182	91.30 2	88.44 141	94.02 58

fmvsm_s_conf0.5_n_3		86.36 46	87.46 27	83.09 175	87.08 230	65.21 199	89.09 112	90.21 157	79.67 17	89.98 18	95.02 18	73.17 38	91.71 235	91.30 2	91.60 89	92.34 137

MVS_0304		87.69 20	87.55 24	88.12 13	89.45 130	71.76 51	91.47 49	89.54 177	82.14 3	86.65 56	94.28 37	68.28 100	97.46 6	90.81 4	95.31 34	95.15 7

test_fmvsmconf_n		85.92 53	86.04 54	85.57 76	85.03 272	69.51 93	89.62 89	90.58 141	73.42 156	87.75 41	94.02 51	72.85 43	93.24 166	90.37 5	90.75 102	93.96 60

test_fmvsmconf0.1_n		85.61 61	85.65 61	85.50 77	82.99 319	69.39 100	89.65 86	90.29 155	73.31 159	87.77 40	94.15 45	71.72 54	93.23 167	90.31 6	90.67 104	93.89 66

test_fmvsmconf0.01_n		84.73 78	84.52 80	85.34 80	80.25 360	69.03 103	89.47 92	89.65 174	73.24 163	86.98 53	94.27 38	66.62 114	93.23 167	90.26 7	89.95 117	93.78 73

fmvsm_s_conf0.5_n_2		84.04 83	84.11 84	83.81 150	86.17 247	65.00 206	86.96 185	87.28 242	74.35 130	88.25 30	94.23 41	61.82 171	92.60 196	89.85 8	88.09 146	93.84 69

fmvsm_s_conf0.5_n_5		85.22 70	85.55 63	84.25 124	86.26 244	67.40 153	89.18 104	89.31 185	72.50 172	88.31 28	93.86 59	69.66 81	91.96 223	89.81 9	91.05 98	93.38 92

fmvsm_s_conf0.1_n_2		83.80 87	83.79 87	83.83 149	85.62 257	64.94 208	87.03 183	86.62 258	74.32 131	87.97 38	94.33 35	60.67 195	92.60 196	89.72 10	87.79 148	93.96 60

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 11	96.44 9	94.41 39

No_MVS				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 11	96.44 9	94.41 39

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 16	94.11 6	80.27 10	91.35 14	94.16 44	78.35 13	96.77 24	89.59 13	94.22 60	94.67 28
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 62	86.20 47	83.60 154	87.32 223	65.13 202	88.86 119	91.63 111	75.41 101	88.23 31	93.45 70	68.56 96	92.47 203	89.52 14	92.78 73	93.20 103

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 59	95.06 1	94.23 3	78.38 34	92.78 4	95.74 6	82.45 3	97.49 4	89.42 15	96.68 2	94.95 11

test_0728_THIRD									78.38 34	92.12 9	95.78 4	81.46 7	97.40 9	89.42 15	96.57 7	94.67 28

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 96	91.06 16	96.03 1	76.84 14	97.03 17	89.09 17	95.65 27	94.47 38
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 59	93.49 9	92.73 64	77.33 52	92.12 9	95.78 4	80.98 9	97.40 9	89.08 18	96.41 12	93.33 96
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 32	95.34 1	71.43 58	93.49 9	94.23 3					97.49 4	89.08 18	96.41 12	94.21 49

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 66	93.57 7	94.06 10	77.24 55	93.10 1	95.72 8	82.99 1	97.44 7	89.07 20	96.63 4	94.88 15

test_241102_TWO								94.06 10	77.24 55	92.78 4	95.72 8	81.26 8	97.44 7	89.07 20	96.58 6	94.26 48

fmvsm_l_conf0.5_n_3		86.02 48	86.32 44	85.14 85	87.20 226	68.54 123	89.57 90	90.44 146	75.31 105	87.49 45	94.39 34	72.86 42	92.72 193	89.04 22	90.56 105	94.16 50

IU-MVS					95.30 2	71.25 59		92.95 55	66.81 275	92.39 6				88.94 23	96.63 4	94.85 20

fmvsm_l_conf0.5_n		84.47 79	84.54 78	84.27 121	85.42 261	68.81 109	88.49 135	87.26 244	68.08 265	88.03 35	93.49 66	72.04 50	91.77 231	88.90 24	89.14 128	92.24 144

fmvsm_s_conf0.5_n		83.80 87	83.71 88	84.07 134	86.69 239	67.31 156	89.46 93	83.07 310	71.09 198	86.96 54	93.70 64	69.02 93	91.47 247	88.79 25	84.62 191	93.44 91

MP-MVS-pluss		87.67 21	87.72 20	87.54 36	93.64 44	72.04 48	89.80 81	93.50 25	75.17 111	86.34 58	95.29 15	70.86 67	96.00 54	88.78 26	96.04 16	94.58 33
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_fmvsmvis_n_1920		84.02 84	83.87 85	84.49 109	84.12 288	69.37 101	88.15 150	87.96 226	70.01 222	83.95 95	93.23 75	68.80 95	91.51 245	88.61 27	89.96 116	92.57 127

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 121	92.29 7	95.97 2	74.28 29	97.24 13	88.58 28	96.91 1	94.87 17
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 95	83.38 93	84.10 128	84.86 274	67.28 157	89.40 98	83.01 311	70.67 206	87.08 51	93.96 57	68.38 98	91.45 248	88.56 29	84.50 192	93.56 86

test_fmvsm_n_1920		85.29 69	85.34 67	85.13 88	86.12 249	69.93 86	88.65 131	90.78 137	69.97 224	88.27 29	93.98 56	71.39 60	91.54 242	88.49 30	90.45 107	93.91 63

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 62	93.00 46	80.90 7	88.06 34	94.06 49	76.43 16	96.84 21	88.48 31	95.99 18	94.34 44

fmvsm_l_conf0.5_n_a		84.13 82	84.16 83	84.06 136	85.38 262	68.40 126	88.34 142	86.85 254	67.48 272	87.48 46	93.40 71	70.89 66	91.61 236	88.38 32	89.22 126	92.16 148

fmvsm_s_conf0.5_n_a		83.63 93	83.41 92	84.28 119	86.14 248	68.12 133	89.43 94	82.87 315	70.27 217	87.27 50	93.80 62	69.09 88	91.58 238	88.21 33	83.65 211	93.14 107

fmvsm_s_conf0.1_n_a		83.32 102	82.99 100	84.28 119	83.79 296	68.07 135	89.34 101	82.85 316	69.80 228	87.36 49	94.06 49	68.34 99	91.56 240	87.95 34	83.46 217	93.21 102

TSAR-MVS + MP.		88.02 17	88.11 16	87.72 30	93.68 43	72.13 46	91.41 50	92.35 82	74.62 125	88.90 23	93.85 60	75.75 20	96.00 54	87.80 35	94.63 48	95.04 9
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 16	88.08 17	87.94 19	93.70 41	73.05 22	90.86 57	93.59 23	76.27 86	88.14 32	95.09 17	71.06 65	96.67 29	87.67 36	96.37 14	94.09 54

SD-MVS		88.06 14	88.50 14	86.71 54	92.60 69	72.71 29	91.81 41	93.19 35	77.87 38	90.32 17	94.00 53	74.83 23	93.78 141	87.63 37	94.27 59	93.65 80
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 11	88.86 11	88.32 9	92.14 72	72.96 25	93.73 5	93.67 20	80.19 12	88.10 33	94.80 20	73.76 33	97.11 15	87.51 38	95.82 21	94.90 14
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 27	92.85 59	80.26 11	87.78 39	94.27 38	75.89 19	96.81 23	87.45 39	96.44 9	93.05 112

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 43	94.10 8	75.90 92	92.29 7	95.66 10	81.67 6	97.38 11	87.44 40	96.34 15	93.95 62
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SF-MVS		88.46 12	88.74 12	87.64 35	92.78 64	71.95 49	92.40 24	94.74 2	75.71 94	89.16 20	95.10 16	75.65 21	96.19 46	87.07 41	96.01 17	94.79 22

9.14			88.26 15		92.84 63		91.52 48	94.75 1	73.93 142	88.57 26	94.67 22	75.57 22	95.79 58	86.77 42	95.76 23

MTAPA		87.23 31	87.00 33	87.90 22	94.18 35	74.25 5	86.58 200	92.02 93	79.45 20	85.88 60	94.80 20	68.07 101	96.21 45	86.69 43	95.34 32	93.23 99

reproduce-ours		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 114	88.96 21	95.54 12	71.20 63	96.54 36	86.28 44	93.49 65	93.06 110

our_new_method		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 114	88.96 21	95.54 12	71.20 63	96.54 36	86.28 44	93.49 65	93.06 110

reproduce_model		87.28 30	87.39 28	86.95 48	93.10 56	71.24 63	91.60 42	93.19 35	74.69 122	88.80 24	95.61 11	70.29 74	96.44 39	86.20 46	93.08 69	93.16 105

DeepPCF-MVS	80.84 1	88.10 13	88.56 13	86.73 53	92.24 71	69.03 103	89.57 90	93.39 30	77.53 48	89.79 19	94.12 46	78.98 12	96.58 35	85.66 47	95.72 24	94.58 33

MP-MVS		87.71 19	87.64 21	87.93 21	94.36 26	73.88 6	92.71 22	92.65 70	77.57 44	83.84 97	94.40 33	72.24 47	96.28 43	85.65 48	95.30 35	93.62 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
balanced_conf03		86.78 37	86.99 34	86.15 63	91.24 83	67.61 146	90.51 62	92.90 56	77.26 54	87.44 47	91.63 112	71.27 62	96.06 49	85.62 49	95.01 37	94.78 23

ZNCC-MVS		87.94 18	87.85 19	88.20 12	94.39 24	73.33 19	93.03 14	93.81 17	76.81 68	85.24 67	94.32 36	71.76 53	96.93 19	85.53 50	95.79 22	94.32 45

HPM-MVS		87.11 33	86.98 35	87.50 38	93.88 39	72.16 45	92.19 33	93.33 31	76.07 89	83.81 98	93.95 58	69.77 80	96.01 53	85.15 51	94.66 47	94.32 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
train_agg		86.43 43	86.20 47	87.13 44	93.26 52	72.96 25	88.75 125	91.89 101	68.69 256	85.00 70	93.10 77	74.43 26	95.41 73	84.97 52	95.71 25	93.02 114

test9_res														84.90 53	95.70 26	92.87 119

NCCC		88.06 14	88.01 18	88.24 11	94.41 22	73.62 11	91.22 54	92.83 60	81.50 5	85.79 62	93.47 69	73.02 41	97.00 18	84.90 53	94.94 40	94.10 53

MCST-MVS		87.37 29	87.25 30	87.73 28	94.53 17	72.46 38	89.82 79	93.82 16	73.07 165	84.86 75	92.89 84	76.22 17	96.33 41	84.89 55	95.13 36	94.40 41

DeepC-MVS	79.81 2	87.08 35	86.88 39	87.69 33	91.16 84	72.32 43	90.31 71	93.94 14	77.12 60	82.82 112	94.23 41	72.13 49	97.09 16	84.83 56	95.37 31	93.65 80
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 38	86.67 40	86.91 49	94.11 37	72.11 47	92.37 28	92.56 75	74.50 126	86.84 55	94.65 23	67.31 110	95.77 59	84.80 57	92.85 72	92.84 120

MVSMamba_PlusPlus		85.99 50	85.96 55	86.05 66	91.09 85	67.64 145	89.63 88	92.65 70	72.89 170	84.64 80	91.71 108	71.85 51	96.03 50	84.77 58	94.45 54	94.49 37

ZD-MVS					94.38 25	72.22 44		92.67 67	70.98 201	87.75 41	94.07 48	74.01 32	96.70 27	84.66 59	94.84 44

PC_three_1452									68.21 264	92.02 12	94.00 53	82.09 5	95.98 56	84.58 60	96.68 2	94.95 11

HFP-MVS		87.58 22	87.47 26	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 70	84.91 72	94.44 31	70.78 68	96.61 32	84.53 61	94.89 42	93.66 76

ACMMPR		87.44 25	87.23 31	88.08 15	94.64 13	73.59 12	93.04 12	93.20 34	76.78 70	84.66 79	94.52 24	68.81 94	96.65 30	84.53 61	94.90 41	94.00 59

region2R		87.42 27	87.20 32	88.09 14	94.63 14	73.55 13	93.03 14	93.12 40	76.73 73	84.45 84	94.52 24	69.09 88	96.70 27	84.37 63	94.83 45	94.03 57

CANet		86.45 42	86.10 52	87.51 37	90.09 108	70.94 70	89.70 85	92.59 74	81.78 4	81.32 128	91.43 120	70.34 72	97.23 14	84.26 64	93.36 68	94.37 42

APD-MVS		87.44 25	87.52 25	87.19 42	94.24 32	72.39 39	91.86 40	92.83 60	73.01 167	88.58 25	94.52 24	73.36 34	96.49 38	84.26 64	95.01 37	92.70 122
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CS-MVS		86.69 39	86.95 36	85.90 71	90.76 96	67.57 148	92.83 17	93.30 32	79.67 17	84.57 83	92.27 96	71.47 58	95.02 93	84.24 66	93.46 67	95.13 8

CP-MVS		87.11 33	86.92 37	87.68 34	94.20 34	73.86 7	93.98 3	92.82 63	76.62 76	83.68 100	94.46 28	67.93 103	95.95 57	84.20 67	94.39 55	93.23 99

GST-MVS		87.42 27	87.26 29	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 66	84.68 76	93.99 55	70.67 70	96.82 22	84.18 68	95.01 37	93.90 65

BP-MVS1		84.32 80	83.71 88	86.17 61	87.84 201	67.85 139	89.38 99	89.64 175	77.73 40	83.98 94	92.12 100	56.89 227	95.43 70	84.03 69	91.75 88	95.24 6

EC-MVSNet		86.01 49	86.38 43	84.91 97	89.31 139	66.27 175	92.32 30	93.63 21	79.37 21	84.17 90	91.88 104	69.04 92	95.43 70	83.93 70	93.77 63	93.01 115

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 51	82.45 3	96.87 20	83.77 71	96.48 8	94.88 15

casdiffmvs_mvg		85.99 50	86.09 53	85.70 74	87.65 211	67.22 161	88.69 129	93.04 41	79.64 19	85.33 66	92.54 93	73.30 35	94.50 112	83.49 72	91.14 97	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 60	86.15 51	84.06 136	91.71 78	64.94 208	86.47 203	91.87 103	73.63 148	86.60 57	93.02 82	76.57 15	91.87 229	83.36 73	92.15 81	95.35 3

test_prior2							88.85 121		75.41 101	84.91 72	93.54 65	74.28 29		83.31 74	95.86 20

PHI-MVS		86.43 43	86.17 50	87.24 41	90.88 92	70.96 68	92.27 32	94.07 9	72.45 173	85.22 68	91.90 103	69.47 83	96.42 40	83.28 75	95.94 19	94.35 43

XVS		87.18 32	86.91 38	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 101	94.17 43	67.45 108	96.60 33	83.06 76	94.50 51	94.07 55

X-MVStestdata		80.37 161	77.83 197	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 101	12.47 431	67.45 108	96.60 33	83.06 76	94.50 51	94.07 55

mamv4		76.81 241	78.23 189	72.54 354	86.12 249	65.75 189	78.76 343	82.07 324	64.12 314	72.97 286	91.02 136	67.97 102	68.08 419	83.04 78	78.02 281	83.80 365

APD-MVS_3200maxsize		85.97 52	85.88 56	86.22 60	92.69 66	69.53 92	91.93 37	92.99 49	73.54 152	85.94 59	94.51 27	65.80 128	95.61 62	83.04 78	92.51 77	93.53 89

agg_prior2														82.91 80	95.45 29	92.70 122

mPP-MVS		86.67 41	86.32 44	87.72 30	94.41 22	73.55 13	92.74 20	92.22 88	76.87 67	82.81 113	94.25 40	66.44 118	96.24 44	82.88 81	94.28 58	93.38 92

SR-MVS-dyc-post		85.77 57	85.61 62	86.23 59	93.06 58	70.63 76	91.88 38	92.27 84	73.53 153	85.69 63	94.45 29	65.00 136	95.56 63	82.75 82	91.87 85	92.50 131

RE-MVS-def			85.48 65		93.06 58	70.63 76	91.88 38	92.27 84	73.53 153	85.69 63	94.45 29	63.87 142		82.75 82	91.87 85	92.50 131

h-mvs33		83.15 104	82.19 112	86.02 69	90.56 98	70.85 73	88.15 150	89.16 193	76.02 90	84.67 77	91.39 121	61.54 176	95.50 66	82.71 84	75.48 318	91.72 157

hse-mvs2		81.72 126	80.94 132	84.07 134	88.72 163	67.68 144	85.87 220	87.26 244	76.02 90	84.67 77	88.22 203	61.54 176	93.48 156	82.71 84	73.44 346	91.06 176

PGM-MVS		86.68 40	86.27 46	87.90 22	94.22 33	73.38 18	90.22 73	93.04 41	75.53 98	83.86 96	94.42 32	67.87 105	96.64 31	82.70 86	94.57 50	93.66 76

ACMMP		85.89 56	85.39 66	87.38 39	93.59 45	72.63 33	92.74 20	93.18 39	76.78 70	80.73 137	93.82 61	64.33 138	96.29 42	82.67 87	90.69 103	93.23 99
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		82.10 118	81.88 120	82.76 196	83.00 317	63.78 232	83.68 270	89.76 170	72.94 168	82.02 119	89.85 156	65.96 127	90.79 266	82.38 88	87.30 156	93.71 75
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 91	84.54 78	80.99 233	90.06 113	65.83 184	84.21 262	88.74 212	71.60 188	85.01 69	92.44 94	74.51 25	83.50 354	82.15 89	92.15 81	93.64 82

SPE-MVS-test		86.29 47	86.48 42	85.71 73	91.02 88	67.21 162	92.36 29	93.78 18	78.97 29	83.51 104	91.20 127	70.65 71	95.15 84	81.96 90	94.89 42	94.77 24

TSAR-MVS + GP.		85.71 59	85.33 68	86.84 50	91.34 81	72.50 36	89.07 113	87.28 242	76.41 79	85.80 61	90.22 151	74.15 31	95.37 78	81.82 91	91.88 84	92.65 126

alignmvs		85.48 63	85.32 69	85.96 70	89.51 127	69.47 95	89.74 83	92.47 76	76.17 87	87.73 43	91.46 119	70.32 73	93.78 141	81.51 92	88.95 129	94.63 32

sasdasda		85.91 54	85.87 57	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 74	88.01 36	91.23 124	73.28 36	93.91 135	81.50 93	88.80 132	94.77 24

canonicalmvs		85.91 54	85.87 57	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 74	88.01 36	91.23 124	73.28 36	93.91 135	81.50 93	88.80 132	94.77 24

baseline		84.93 75	84.98 73	84.80 101	87.30 224	65.39 196	87.30 176	92.88 57	77.62 42	84.04 93	92.26 97	71.81 52	93.96 128	81.31 95	90.30 109	95.03 10

MGCFI-Net		85.06 74	85.51 64	83.70 152	89.42 131	63.01 250	89.43 94	92.62 73	76.43 78	87.53 44	91.34 122	72.82 44	93.42 161	81.28 96	88.74 135	94.66 31

casdiffmvs		85.11 72	85.14 72	85.01 91	87.20 226	65.77 188	87.75 162	92.83 60	77.84 39	84.36 87	92.38 95	72.15 48	93.93 134	81.27 97	90.48 106	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 71	84.75 76	86.32 58	91.65 79	72.70 30	85.98 216	90.33 152	76.11 88	82.08 118	91.61 114	71.36 61	94.17 124	81.02 98	92.58 76	92.08 150

HPM-MVS_fast		85.35 68	84.95 75	86.57 56	93.69 42	70.58 78	92.15 35	91.62 112	73.89 143	82.67 115	94.09 47	62.60 157	95.54 65	80.93 99	92.93 71	93.57 85

CPTT-MVS		83.73 89	83.33 95	84.92 96	93.28 49	70.86 72	92.09 36	90.38 148	68.75 255	79.57 149	92.83 86	60.60 199	93.04 185	80.92 100	91.56 92	90.86 184

ETV-MVS		84.90 77	84.67 77	85.59 75	89.39 134	68.66 120	88.74 127	92.64 72	79.97 15	84.10 91	85.71 269	69.32 85	95.38 75	80.82 101	91.37 94	92.72 121

DeepC-MVS_fast	79.65 3	86.91 36	86.62 41	87.76 27	93.52 46	72.37 41	91.26 51	93.04 41	76.62 76	84.22 88	93.36 73	71.44 59	96.76 25	80.82 101	95.33 33	94.16 50
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 85	83.53 90	84.96 93	86.77 236	69.28 102	90.46 67	92.67 67	74.79 120	82.95 108	91.33 123	72.70 45	93.09 180	80.79 103	79.28 269	92.50 131

EI-MVSNet-Vis-set		84.19 81	83.81 86	85.31 81	88.18 182	67.85 139	87.66 164	89.73 172	80.05 14	82.95 108	89.59 164	70.74 69	94.82 101	80.66 104	84.72 189	93.28 98

MSLP-MVS++		85.43 65	85.76 59	84.45 110	91.93 75	70.24 79	90.71 59	92.86 58	77.46 50	84.22 88	92.81 88	67.16 112	92.94 187	80.36 105	94.35 57	90.16 212

MVS_111021_LR		82.61 113	82.11 113	84.11 127	88.82 157	71.58 55	85.15 236	86.16 266	74.69 122	80.47 139	91.04 133	62.29 164	90.55 270	80.33 106	90.08 114	90.20 211

DELS-MVS		85.41 66	85.30 70	85.77 72	88.49 170	67.93 138	85.52 233	93.44 27	78.70 30	83.63 103	89.03 179	74.57 24	95.71 61	80.26 107	94.04 61	93.66 76
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 96	82.64 106	86.16 62	88.14 185	68.45 125	89.13 110	92.69 65	72.82 171	83.71 99	91.86 106	55.69 232	95.35 79	80.03 108	89.74 120	94.69 27

EI-MVSNet-UG-set		83.81 86	83.38 93	85.09 89	87.87 199	67.53 149	87.44 172	89.66 173	79.74 16	82.23 117	89.41 173	70.24 75	94.74 104	79.95 109	83.92 203	92.99 117

CSCG		86.41 45	86.19 49	87.07 45	92.91 61	72.48 37	90.81 58	93.56 24	73.95 140	83.16 107	91.07 132	75.94 18	95.19 82	79.94 110	94.38 56	93.55 87

RRT-MVS		82.60 115	82.10 114	84.10 128	87.98 195	62.94 255	87.45 171	91.27 122	77.42 51	79.85 145	90.28 147	56.62 229	94.70 107	79.87 111	88.15 145	94.67 28

OPM-MVS		83.50 97	82.95 101	85.14 85	88.79 160	70.95 69	89.13 110	91.52 115	77.55 47	80.96 135	91.75 107	60.71 193	94.50 112	79.67 112	86.51 168	89.97 228
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CDPH-MVS		85.76 58	85.29 71	87.17 43	93.49 47	71.08 64	88.58 133	92.42 80	68.32 263	84.61 81	93.48 67	72.32 46	96.15 48	79.00 113	95.43 30	94.28 47

MVSFormer		82.85 110	82.05 116	85.24 83	87.35 217	70.21 80	90.50 64	90.38 148	68.55 258	81.32 128	89.47 167	61.68 173	93.46 158	78.98 114	90.26 110	92.05 151

test_djsdf		80.30 162	79.32 163	83.27 166	83.98 292	65.37 197	90.50 64	90.38 148	68.55 258	76.19 223	88.70 186	56.44 230	93.46 158	78.98 114	80.14 259	90.97 181

test_vis1_n_1920		75.52 263	75.78 239	74.75 333	79.84 366	57.44 321	83.26 279	85.52 273	62.83 331	79.34 153	86.17 262	45.10 342	79.71 374	78.75 116	81.21 243	87.10 312

HQP_MVS		83.64 92	83.14 96	85.14 85	90.08 109	68.71 116	91.25 52	92.44 77	79.12 24	78.92 158	91.00 137	60.42 201	95.38 75	78.71 117	86.32 170	91.33 168

plane_prior5								92.44 77					95.38 75	78.71 117	86.32 170	91.33 168

LPG-MVS_test		82.08 119	81.27 125	84.50 107	89.23 143	68.76 112	90.22 73	91.94 99	75.37 103	76.64 211	91.51 116	54.29 245	94.91 95	78.44 119	83.78 204	89.83 233

LGP-MVS_train				84.50 107	89.23 143	68.76 112		91.94 99	75.37 103	76.64 211	91.51 116	54.29 245	94.91 95	78.44 119	83.78 204	89.83 233

lupinMVS		81.39 135	80.27 144	84.76 102	87.35 217	70.21 80	85.55 229	86.41 260	62.85 330	81.32 128	88.61 190	61.68 173	92.24 215	78.41 121	90.26 110	91.83 154

jason		81.39 135	80.29 143	84.70 103	86.63 241	69.90 88	85.95 217	86.77 255	63.24 323	81.07 134	89.47 167	61.08 189	92.15 217	78.33 122	90.07 115	92.05 151
jason: jason.
xiu_mvs_v1_base_debu		80.80 147	79.72 153	84.03 141	87.35 217	70.19 82	85.56 226	88.77 208	69.06 248	81.83 120	88.16 204	50.91 285	92.85 189	78.29 123	87.56 150	89.06 252

xiu_mvs_v1_base		80.80 147	79.72 153	84.03 141	87.35 217	70.19 82	85.56 226	88.77 208	69.06 248	81.83 120	88.16 204	50.91 285	92.85 189	78.29 123	87.56 150	89.06 252

xiu_mvs_v1_base_debi		80.80 147	79.72 153	84.03 141	87.35 217	70.19 82	85.56 226	88.77 208	69.06 248	81.83 120	88.16 204	50.91 285	92.85 189	78.29 123	87.56 150	89.06 252

Effi-MVS+		83.62 94	83.08 97	85.24 83	88.38 176	67.45 150	88.89 118	89.15 194	75.50 99	82.27 116	88.28 200	69.61 82	94.45 114	77.81 126	87.84 147	93.84 69

PS-MVSNAJss		82.07 120	81.31 124	84.34 115	86.51 242	67.27 158	89.27 102	91.51 116	71.75 183	79.37 151	90.22 151	63.15 151	94.27 118	77.69 127	82.36 231	91.49 164

ACMP	74.13 6	81.51 134	80.57 136	84.36 113	89.42 131	68.69 119	89.97 77	91.50 119	74.46 128	75.04 258	90.41 146	53.82 250	94.54 109	77.56 128	82.91 223	89.86 232
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
BP-MVS														77.47 129

HQP-MVS		82.61 113	82.02 117	84.37 112	89.33 136	66.98 165	89.17 105	92.19 90	76.41 79	77.23 196	90.23 150	60.17 204	95.11 87	77.47 129	85.99 178	91.03 178

MVS_Test		83.15 104	83.06 98	83.41 162	86.86 232	63.21 246	86.11 214	92.00 95	74.31 132	82.87 110	89.44 172	70.03 76	93.21 169	77.39 131	88.50 140	93.81 71

3Dnovator+	77.84 4	85.48 63	84.47 81	88.51 7	91.08 86	73.49 16	93.18 11	93.78 18	80.79 8	76.66 210	93.37 72	60.40 203	96.75 26	77.20 132	93.73 64	95.29 5

anonymousdsp		78.60 201	77.15 215	82.98 183	80.51 358	67.08 163	87.24 178	89.53 178	65.66 295	75.16 253	87.19 231	52.52 259	92.25 214	77.17 133	79.34 268	89.61 240

mmtdpeth		74.16 278	73.01 282	77.60 301	83.72 299	61.13 274	85.10 238	85.10 277	72.06 181	77.21 200	80.33 362	43.84 351	85.75 332	77.14 134	52.61 409	85.91 334

VDD-MVS		83.01 109	82.36 110	84.96 93	91.02 88	66.40 172	88.91 117	88.11 221	77.57 44	84.39 86	93.29 74	52.19 265	93.91 135	77.05 135	88.70 136	94.57 35

XVG-OURS-SEG-HR		80.81 145	79.76 152	83.96 146	85.60 258	68.78 111	83.54 276	90.50 144	70.66 209	76.71 209	91.66 109	60.69 194	91.26 253	76.94 136	81.58 239	91.83 154

jajsoiax		79.29 184	77.96 192	83.27 166	84.68 277	66.57 171	89.25 103	90.16 159	69.20 244	75.46 238	89.49 166	45.75 337	93.13 178	76.84 137	80.80 249	90.11 216

SDMVSNet		80.38 159	80.18 145	80.99 233	89.03 152	64.94 208	80.45 319	89.40 181	75.19 109	76.61 213	89.98 153	60.61 198	87.69 316	76.83 138	83.55 213	90.33 206

mvs_tets		79.13 188	77.77 201	83.22 170	84.70 276	66.37 173	89.17 105	90.19 158	69.38 237	75.40 241	89.46 169	44.17 349	93.15 176	76.78 139	80.70 251	90.14 213

DPM-MVS		84.93 75	84.29 82	86.84 50	90.20 106	73.04 23	87.12 180	93.04 41	69.80 228	82.85 111	91.22 126	73.06 40	96.02 52	76.72 140	94.63 48	91.46 167

test_cas_vis1_n_1920		73.76 284	73.74 273	73.81 342	75.90 388	59.77 293	80.51 317	82.40 320	58.30 370	81.62 126	85.69 270	44.35 348	76.41 392	76.29 141	78.61 272	85.23 344

ET-MVSNet_ETH3D		78.63 200	76.63 230	84.64 104	86.73 237	69.47 95	85.01 240	84.61 283	69.54 234	66.51 360	86.59 249	50.16 294	91.75 232	76.26 142	84.24 200	92.69 124

v2v482		80.23 163	79.29 164	83.05 179	83.62 300	64.14 225	87.04 182	89.97 164	73.61 149	78.18 176	87.22 229	61.10 188	93.82 139	76.11 143	76.78 298	91.18 172

test_fmvs1_n		70.86 316	70.24 314	72.73 352	72.51 410	55.28 353	81.27 305	79.71 352	51.49 399	78.73 160	84.87 291	27.54 406	77.02 386	76.06 144	79.97 261	85.88 335

CLD-MVS		82.31 116	81.65 122	84.29 118	88.47 171	67.73 143	85.81 224	92.35 82	75.78 93	78.33 172	86.58 251	64.01 141	94.35 115	76.05 145	87.48 153	90.79 185
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 90	82.92 102	86.14 65	84.22 286	69.48 94	91.05 56	85.27 275	81.30 6	76.83 205	91.65 110	66.09 123	95.56 63	76.00 146	93.85 62	93.38 92
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvs1		70.93 315	70.52 309	72.16 356	73.71 399	55.05 355	80.82 308	78.77 360	51.21 400	78.58 165	84.41 299	31.20 401	76.94 387	75.88 147	80.12 260	84.47 356

XVG-OURS		80.41 158	79.23 166	83.97 145	85.64 256	69.02 105	83.03 287	90.39 147	71.09 198	77.63 187	91.49 118	54.62 244	91.35 251	75.71 148	83.47 216	91.54 161

V42		79.38 183	78.24 187	82.83 188	81.10 352	65.50 193	85.55 229	89.82 167	71.57 189	78.21 174	86.12 263	60.66 196	93.18 175	75.64 149	75.46 320	89.81 235

PS-MVSNAJ		81.69 128	81.02 130	83.70 152	89.51 127	68.21 132	84.28 261	90.09 161	70.79 203	81.26 132	85.62 274	63.15 151	94.29 116	75.62 150	88.87 131	88.59 276

xiu_mvs_v2_base		81.69 128	81.05 129	83.60 154	89.15 146	68.03 137	84.46 255	90.02 162	70.67 206	81.30 131	86.53 254	63.17 150	94.19 123	75.60 151	88.54 138	88.57 277

EIA-MVS		83.31 103	82.80 104	84.82 99	89.59 123	65.59 191	88.21 146	92.68 66	74.66 124	78.96 156	86.42 256	69.06 90	95.26 80	75.54 152	90.09 113	93.62 83

AUN-MVS		79.21 186	77.60 207	84.05 139	88.71 164	67.61 146	85.84 222	87.26 244	69.08 247	77.23 196	88.14 208	53.20 257	93.47 157	75.50 153	73.45 345	91.06 176

mvsmamba		80.60 153	79.38 160	84.27 121	89.74 121	67.24 160	87.47 169	86.95 250	70.02 221	75.38 242	88.93 180	51.24 282	92.56 199	75.47 154	89.22 126	93.00 116

reproduce_monomvs		75.40 267	74.38 264	78.46 286	83.92 294	57.80 315	83.78 268	86.94 251	73.47 155	72.25 297	84.47 297	38.74 379	89.27 291	75.32 155	70.53 365	88.31 282

OMC-MVS		82.69 111	81.97 119	84.85 98	88.75 162	67.42 151	87.98 153	90.87 135	74.92 116	79.72 147	91.65 110	62.19 167	93.96 128	75.26 156	86.42 169	93.16 105

v1144		80.03 167	79.03 170	83.01 181	83.78 297	64.51 216	87.11 181	90.57 143	71.96 182	78.08 179	86.20 261	61.41 180	93.94 131	74.93 157	77.23 289	90.60 195

MVSTER		79.01 191	77.88 196	82.38 202	83.07 314	64.80 212	84.08 266	88.95 204	69.01 251	78.69 161	87.17 232	54.70 242	92.43 205	74.69 158	80.57 253	89.89 231

test_vis1_n		69.85 328	69.21 319	71.77 358	72.66 409	55.27 354	81.48 301	76.21 379	52.03 396	75.30 249	83.20 328	28.97 404	76.22 394	74.60 159	78.41 278	83.81 364

test_fmvs2		68.35 341	67.48 341	70.98 367	69.50 413	51.95 377	80.05 325	76.38 378	49.33 402	74.65 265	84.38 300	23.30 415	75.40 403	74.51 160	75.17 329	85.60 338

PVSNet_Blended_VisFu		82.62 112	81.83 121	84.96 93	90.80 94	69.76 90	88.74 127	91.70 110	69.39 236	78.96 156	88.46 195	65.47 130	94.87 100	74.42 161	88.57 137	90.24 210

v8		79.97 169	79.02 171	82.80 191	84.09 289	64.50 218	87.96 154	90.29 155	74.13 139	75.24 251	86.81 238	62.88 156	93.89 138	74.39 162	75.40 323	90.00 224

v144192		79.47 177	78.37 183	82.78 194	83.35 305	63.96 228	86.96 185	90.36 151	69.99 223	77.50 188	85.67 272	60.66 196	93.77 143	74.27 163	76.58 299	90.62 193

ACMM	73.20 8	80.78 150	79.84 151	83.58 156	89.31 139	68.37 127	89.99 76	91.60 113	70.28 216	77.25 194	89.66 160	53.37 255	93.53 154	74.24 164	82.85 224	88.85 265
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
旧先验2							86.56 201		58.10 372	87.04 52			88.98 297	74.07 165

v1192		79.59 174	78.43 182	83.07 178	83.55 302	64.52 215	86.93 188	90.58 141	70.83 202	77.78 184	85.90 265	59.15 207	93.94 131	73.96 166	77.19 291	90.76 187

v10		79.74 171	78.67 175	82.97 184	84.06 290	64.95 207	87.88 160	90.62 140	73.11 164	75.11 255	86.56 252	61.46 179	94.05 127	73.68 167	75.55 316	89.90 230

v1921920		79.22 185	78.03 191	82.80 191	83.30 307	63.94 229	86.80 192	90.33 152	69.91 226	77.48 189	85.53 276	58.44 211	93.75 145	73.60 168	76.85 296	90.71 191

cl22		78.07 214	77.01 217	81.23 226	82.37 333	61.83 268	83.55 275	87.98 225	68.96 252	75.06 257	83.87 311	61.40 181	91.88 228	73.53 169	76.39 303	89.98 227

Effi-MVS+-dtu		80.03 167	78.57 178	84.42 111	85.13 270	68.74 114	88.77 123	88.10 222	74.99 113	74.97 259	83.49 323	57.27 223	93.36 162	73.53 169	80.88 247	91.18 172

c3_l		78.75 196	77.91 194	81.26 225	82.89 321	61.56 271	84.09 265	89.13 196	69.97 224	75.56 234	84.29 303	66.36 119	92.09 219	73.47 171	75.48 318	90.12 215

VDDNet		81.52 132	80.67 135	84.05 139	90.44 101	64.13 226	89.73 84	85.91 269	71.11 197	83.18 106	93.48 67	50.54 291	93.49 155	73.40 172	88.25 143	94.54 36

CANet_DTU		80.61 152	79.87 150	82.83 188	85.60 258	63.17 249	87.36 173	88.65 214	76.37 83	75.88 229	88.44 196	53.51 253	93.07 181	73.30 173	89.74 120	92.25 142

miper_ehance_all_eth		78.59 202	77.76 202	81.08 231	82.66 326	61.56 271	83.65 271	89.15 194	68.87 253	75.55 235	83.79 315	66.49 117	92.03 220	73.25 174	76.39 303	89.64 239

3Dnovator	76.31 5	83.38 101	82.31 111	86.59 55	87.94 196	72.94 28	90.64 60	92.14 92	77.21 57	75.47 236	92.83 86	58.56 210	94.72 105	73.24 175	92.71 75	92.13 149

v1240		78.99 192	77.78 200	82.64 197	83.21 309	63.54 237	86.62 199	90.30 154	69.74 233	77.33 192	85.68 271	57.04 225	93.76 144	73.13 176	76.92 293	90.62 193

miper_enhance_ethall		77.87 221	76.86 221	80.92 236	81.65 340	61.38 273	82.68 288	88.98 201	65.52 297	75.47 236	82.30 343	65.76 129	92.00 222	72.95 177	76.39 303	89.39 245

MG-MVS		83.41 99	83.45 91	83.28 165	92.74 65	62.28 262	88.17 148	89.50 179	75.22 106	81.49 127	92.74 92	66.75 113	95.11 87	72.85 178	91.58 91	92.45 134

EPP-MVSNet		83.40 100	83.02 99	84.57 105	90.13 107	64.47 219	92.32 30	90.73 138	74.45 129	79.35 152	91.10 130	69.05 91	95.12 85	72.78 179	87.22 157	94.13 52

test_fmvs3		63.36 365	61.82 368	67.98 382	62.51 422	46.96 403	77.37 361	74.03 389	45.24 407	67.50 344	78.79 378	12.16 427	72.98 411	72.77 180	66.02 382	83.99 362

IterMVS-LS		80.06 166	79.38 160	82.11 205	85.89 252	63.20 247	86.79 193	89.34 183	74.19 136	75.45 239	86.72 241	66.62 114	92.39 207	72.58 181	76.86 295	90.75 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tt0805		78.73 197	77.83 197	81.43 219	85.17 266	60.30 288	89.41 97	90.90 133	71.21 195	77.17 201	88.73 185	46.38 326	93.21 169	72.57 182	78.96 271	90.79 185

EI-MVSNet		80.52 157	79.98 147	82.12 204	84.28 284	63.19 248	86.41 204	88.95 204	74.18 137	78.69 161	87.54 221	66.62 114	92.43 205	72.57 182	80.57 253	90.74 189

Vis-MVSNet		83.46 98	82.80 104	85.43 79	90.25 105	68.74 114	90.30 72	90.13 160	76.33 85	80.87 136	92.89 84	61.00 190	94.20 122	72.45 184	90.97 99	93.35 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
LFMVS		81.82 125	81.23 126	83.57 157	91.89 76	63.43 242	89.84 78	81.85 327	77.04 63	83.21 105	93.10 77	52.26 264	93.43 160	71.98 185	89.95 117	93.85 67

v148		78.72 198	77.80 199	81.47 218	82.73 324	61.96 266	86.30 209	88.08 223	73.26 161	76.18 224	85.47 278	62.46 161	92.36 209	71.92 186	73.82 342	90.09 218

PVSNet_BlendedMVS		80.60 153	80.02 146	82.36 203	88.85 154	65.40 194	86.16 213	92.00 95	69.34 238	78.11 177	86.09 264	66.02 125	94.27 118	71.52 187	82.06 234	87.39 300

PVSNet_Blended		80.98 140	80.34 141	82.90 186	88.85 154	65.40 194	84.43 257	92.00 95	67.62 269	78.11 177	85.05 289	66.02 125	94.27 118	71.52 187	89.50 122	89.01 257

eth_miper_zixun_eth		77.92 219	76.69 228	81.61 216	83.00 317	61.98 265	83.15 281	89.20 192	69.52 235	74.86 261	84.35 302	61.76 172	92.56 199	71.50 189	72.89 350	90.28 209

UA-Net		85.08 73	84.96 74	85.45 78	92.07 73	68.07 135	89.78 82	90.86 136	82.48 2	84.60 82	93.20 76	69.35 84	95.22 81	71.39 190	90.88 101	93.07 109

FA-MVS(test-final)		80.96 141	79.91 149	84.10 128	88.30 179	65.01 205	84.55 252	90.01 163	73.25 162	79.61 148	87.57 218	58.35 212	94.72 105	71.29 191	86.25 172	92.56 128

cl____		77.72 224	76.76 225	80.58 242	82.49 330	60.48 285	83.09 283	87.87 229	69.22 242	74.38 270	85.22 284	62.10 168	91.53 243	71.09 192	75.41 322	89.73 238

DIV-MVS_self_test		77.72 224	76.76 225	80.58 242	82.48 331	60.48 285	83.09 283	87.86 230	69.22 242	74.38 270	85.24 282	62.10 168	91.53 243	71.09 192	75.40 323	89.74 237

MonoMVSNet		76.49 249	75.80 238	78.58 280	81.55 343	58.45 302	86.36 207	86.22 264	74.87 119	74.73 263	83.73 317	51.79 277	88.73 302	70.78 194	72.15 355	88.55 278

test_yl		81.17 137	80.47 139	83.24 168	89.13 147	63.62 233	86.21 211	89.95 165	72.43 176	81.78 124	89.61 162	57.50 220	93.58 149	70.75 195	86.90 161	92.52 129

DCV-MVSNet		81.17 137	80.47 139	83.24 168	89.13 147	63.62 233	86.21 211	89.95 165	72.43 176	81.78 124	89.61 162	57.50 220	93.58 149	70.75 195	86.90 161	92.52 129

VNet		82.21 117	82.41 108	81.62 214	90.82 93	60.93 277	84.47 253	89.78 168	76.36 84	84.07 92	91.88 104	64.71 137	90.26 272	70.68 197	88.89 130	93.66 76

mvs_anonymous		79.42 180	79.11 169	80.34 247	84.45 283	57.97 310	82.59 289	87.62 235	67.40 273	76.17 226	88.56 193	68.47 97	89.59 285	70.65 198	86.05 176	93.47 90

VPA-MVSNet		80.60 153	80.55 137	80.76 239	88.07 190	60.80 280	86.86 190	91.58 114	75.67 97	80.24 141	89.45 171	63.34 145	90.25 273	70.51 199	79.22 270	91.23 171

PAPM_NR		83.02 108	82.41 108	84.82 99	92.47 70	66.37 173	87.93 157	91.80 106	73.82 144	77.32 193	90.66 142	67.90 104	94.90 97	70.37 200	89.48 123	93.19 104

thisisatest0530		79.40 181	77.76 202	84.31 116	87.69 210	65.10 204	87.36 173	84.26 290	70.04 220	77.42 190	88.26 202	49.94 297	94.79 103	70.20 201	84.70 190	93.03 113

tttt0517		79.40 181	77.91 194	83.90 148	88.10 188	63.84 230	88.37 141	84.05 292	71.45 191	76.78 207	89.12 176	49.93 299	94.89 98	70.18 202	83.18 221	92.96 118

UniMVSNet_NR-MVSNet		81.88 123	81.54 123	82.92 185	88.46 172	63.46 240	87.13 179	92.37 81	80.19 12	78.38 170	89.14 175	71.66 57	93.05 183	70.05 203	76.46 301	92.25 142

DU-MVS		81.12 139	80.52 138	82.90 186	87.80 203	63.46 240	87.02 184	91.87 103	79.01 27	78.38 170	89.07 177	65.02 134	93.05 183	70.05 203	76.46 301	92.20 145

XVG-ACMP-BASELINE		76.11 255	74.27 266	81.62 214	83.20 310	64.67 214	83.60 274	89.75 171	69.75 231	71.85 301	87.09 234	32.78 396	92.11 218	69.99 205	80.43 255	88.09 286

GeoE		81.71 127	81.01 131	83.80 151	89.51 127	64.45 220	88.97 115	88.73 213	71.27 194	78.63 164	89.76 158	66.32 120	93.20 172	69.89 206	86.02 177	93.74 74

FIs		82.07 120	82.42 107	81.04 232	88.80 159	58.34 304	88.26 145	93.49 26	76.93 65	78.47 169	91.04 133	69.92 78	92.34 211	69.87 207	84.97 186	92.44 135

114514_t		80.68 151	79.51 157	84.20 125	94.09 38	67.27 158	89.64 87	91.11 129	58.75 368	74.08 272	90.72 141	58.10 213	95.04 92	69.70 208	89.42 124	90.30 208

Anonymous20231211		78.97 193	77.69 205	82.81 190	90.54 99	64.29 223	90.11 75	91.51 116	65.01 304	76.16 227	88.13 209	50.56 290	93.03 186	69.68 209	77.56 288	91.11 174

Patchmatch-RL test		70.24 323	67.78 336	77.61 299	77.43 383	59.57 297	71.16 391	70.33 397	62.94 329	68.65 335	72.77 403	50.62 289	85.49 337	69.58 210	66.58 380	87.77 292

UniMVSNet (Re)		81.60 131	81.11 128	83.09 175	88.38 176	64.41 221	87.60 165	93.02 45	78.42 33	78.56 166	88.16 204	69.78 79	93.26 165	69.58 210	76.49 300	91.60 158

IterMVS-SCA-FT		75.43 265	73.87 271	80.11 252	82.69 325	64.85 211	81.57 300	83.47 301	69.16 245	70.49 312	84.15 309	51.95 272	88.15 310	69.23 212	72.14 356	87.34 302

v7n		78.97 193	77.58 208	83.14 173	83.45 304	65.51 192	88.32 143	91.21 124	73.69 147	72.41 294	86.32 259	57.93 214	93.81 140	69.18 213	75.65 314	90.11 216

Anonymous20240529		80.19 165	78.89 173	84.10 128	90.60 97	64.75 213	88.95 116	90.90 133	65.97 292	80.59 138	91.17 129	49.97 296	93.73 147	69.16 214	82.70 228	93.81 71

miper_lstm_enhance		74.11 279	73.11 281	77.13 307	80.11 362	59.62 295	72.23 387	86.92 253	66.76 277	70.40 313	82.92 333	56.93 226	82.92 358	69.06 215	72.63 351	88.87 264

testdata				79.97 254	90.90 91	64.21 224		84.71 281	59.27 362	85.40 65	92.91 83	62.02 170	89.08 295	68.95 216	91.37 94	86.63 321

test1111		79.43 179	79.18 168	80.15 251	89.99 114	53.31 371	87.33 175	77.05 374	75.04 112	80.23 142	92.77 91	48.97 311	92.33 212	68.87 217	92.40 80	94.81 21

GA-MVS		76.87 240	75.17 254	81.97 209	82.75 323	62.58 257	81.44 303	86.35 263	72.16 180	74.74 262	82.89 334	46.20 331	92.02 221	68.85 218	81.09 244	91.30 170

test2506		77.30 234	76.49 231	79.74 259	90.08 109	52.02 375	87.86 161	63.10 417	74.88 117	80.16 143	92.79 89	38.29 383	92.35 210	68.74 219	92.50 78	94.86 18

ECVR-MVS		79.61 172	79.26 165	80.67 241	90.08 109	54.69 358	87.89 159	77.44 370	74.88 117	80.27 140	92.79 89	48.96 312	92.45 204	68.55 220	92.50 78	94.86 18

UGNet		80.83 144	79.59 156	84.54 106	88.04 191	68.09 134	89.42 96	88.16 220	76.95 64	76.22 222	89.46 169	49.30 306	93.94 131	68.48 221	90.31 108	91.60 158
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		81.52 132	82.02 117	80.03 253	88.42 175	55.97 343	87.95 155	93.42 29	77.10 61	77.38 191	90.98 139	69.96 77	91.79 230	68.46 222	84.50 192	92.33 138

DP-MVS Recon		83.11 107	82.09 115	86.15 63	94.44 19	70.92 71	88.79 122	92.20 89	70.53 211	79.17 154	91.03 135	64.12 140	96.03 50	68.39 223	90.14 112	91.50 163

UniMVSNet_ETH3D		79.10 189	78.24 187	81.70 213	86.85 233	60.24 289	87.28 177	88.79 207	74.25 135	76.84 204	90.53 145	49.48 302	91.56 240	67.98 224	82.15 232	93.29 97

D2MVS		74.82 272	73.21 279	79.64 263	79.81 367	62.56 258	80.34 321	87.35 241	64.37 311	68.86 333	82.66 338	46.37 327	90.10 275	67.91 225	81.24 242	86.25 324

IS-MVSNet		83.15 104	82.81 103	84.18 126	89.94 116	63.30 244	91.59 43	88.46 218	79.04 26	79.49 150	92.16 98	65.10 133	94.28 117	67.71 226	91.86 87	94.95 11

Fast-Effi-MVS+-dtu		78.02 216	76.49 231	82.62 198	83.16 313	66.96 167	86.94 187	87.45 240	72.45 173	71.49 306	84.17 308	54.79 241	91.58 238	67.61 227	80.31 256	89.30 248

PAPR		81.66 130	80.89 133	83.99 144	90.27 104	64.00 227	86.76 196	91.77 109	68.84 254	77.13 203	89.50 165	67.63 106	94.88 99	67.55 228	88.52 139	93.09 108

cascas		76.72 243	74.64 258	82.99 182	85.78 254	65.88 183	82.33 291	89.21 191	60.85 349	72.74 288	81.02 354	47.28 319	93.75 145	67.48 229	85.02 185	89.34 247

1314		76.53 245	75.30 252	80.21 250	83.93 293	62.32 261	84.66 247	88.81 206	60.23 353	70.16 318	84.07 310	55.30 235	90.73 268	67.37 230	83.21 220	87.59 297

无先验							87.48 168	88.98 201	60.00 355				94.12 125	67.28 231		88.97 260

thisisatest0515		77.33 233	75.38 249	83.18 171	85.27 265	63.80 231	82.11 294	83.27 304	65.06 302	75.91 228	83.84 313	49.54 301	94.27 118	67.24 232	86.19 173	91.48 165

原ACMM1				84.35 114	93.01 60	68.79 110		92.44 77	63.96 320	81.09 133	91.57 115	66.06 124	95.45 68	67.19 233	94.82 46	88.81 267

Baseline_NR-MVSNet		78.15 212	78.33 185	77.61 299	85.79 253	56.21 341	86.78 194	85.76 271	73.60 150	77.93 182	87.57 218	65.02 134	88.99 296	67.14 234	75.33 325	87.63 294

TranMVSNet+NR-MVSNet		80.84 143	80.31 142	82.42 201	87.85 200	62.33 260	87.74 163	91.33 121	80.55 9	77.99 181	89.86 155	65.23 132	92.62 194	67.05 235	75.24 328	92.30 140

Fast-Effi-MVS+		80.81 145	79.92 148	83.47 158	88.85 154	64.51 216	85.53 231	89.39 182	70.79 203	78.49 168	85.06 288	67.54 107	93.58 149	67.03 236	86.58 166	92.32 139

VPNet		78.69 199	78.66 176	78.76 276	88.31 178	55.72 347	84.45 256	86.63 257	76.79 69	78.26 173	90.55 144	59.30 206	89.70 284	66.63 237	77.05 292	90.88 183

PM-MVS		66.41 353	64.14 356	73.20 348	73.92 398	56.45 334	78.97 340	64.96 414	63.88 321	64.72 371	80.24 363	19.84 419	83.44 355	66.24 238	64.52 387	79.71 395

test-LLR		72.94 299	72.43 288	74.48 334	81.35 348	58.04 308	78.38 348	77.46 368	66.66 279	69.95 322	79.00 375	48.06 315	79.24 375	66.13 239	84.83 187	86.15 327

test-mter		71.41 310	70.39 313	74.48 334	81.35 348	58.04 308	78.38 348	77.46 368	60.32 352	69.95 322	79.00 375	36.08 390	79.24 375	66.13 239	84.83 187	86.15 327

MVS		78.19 211	76.99 219	81.78 211	85.66 255	66.99 164	84.66 247	90.47 145	55.08 388	72.02 300	85.27 281	63.83 143	94.11 126	66.10 241	89.80 119	84.24 358

NR-MVSNet		80.23 163	79.38 160	82.78 194	87.80 203	63.34 243	86.31 208	91.09 130	79.01 27	72.17 298	89.07 177	67.20 111	92.81 192	66.08 242	75.65 314	92.20 145

CVMVSNet		72.99 298	72.58 287	74.25 337	84.28 284	50.85 389	86.41 204	83.45 302	44.56 408	73.23 283	87.54 221	49.38 304	85.70 333	65.90 243	78.44 276	86.19 326

IterMVS		74.29 275	72.94 283	78.35 287	81.53 344	63.49 239	81.58 299	82.49 319	68.06 266	69.99 321	83.69 319	51.66 279	85.54 336	65.85 244	71.64 359	86.01 331
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
OurMVSNet-221017-0		74.26 276	72.42 289	79.80 258	83.76 298	59.59 296	85.92 219	86.64 256	66.39 286	66.96 350	87.58 217	39.46 375	91.60 237	65.76 245	69.27 370	88.22 283

tpmrst		72.39 301	72.13 292	73.18 349	80.54 357	49.91 393	79.91 328	79.08 359	63.11 325	71.69 303	79.95 366	55.32 234	82.77 359	65.66 246	73.89 340	86.87 314

MAR-MVS		81.84 124	80.70 134	85.27 82	91.32 82	71.53 56	89.82 79	90.92 132	69.77 230	78.50 167	86.21 260	62.36 163	94.52 111	65.36 247	92.05 83	89.77 236
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		78.25 207	77.01 217	81.99 208	91.03 87	60.67 282	84.77 245	83.90 294	70.65 210	80.00 144	91.20 127	41.08 369	91.43 249	65.21 248	85.26 184	93.85 67

ab-mvs		79.51 175	78.97 172	81.14 229	88.46 172	60.91 278	83.84 267	89.24 190	70.36 213	79.03 155	88.87 183	63.23 149	90.21 274	65.12 249	82.57 229	92.28 141

IB-MVS	68.01 15	75.85 259	73.36 278	83.31 164	84.76 275	66.03 177	83.38 277	85.06 278	70.21 219	69.40 328	81.05 353	45.76 336	94.66 108	65.10 250	75.49 317	89.25 249
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		79.49 176	79.22 167	80.27 249	88.79 160	58.35 303	85.06 239	88.61 216	78.56 31	77.65 186	88.34 198	63.81 144	90.66 269	64.98 251	77.22 290	91.80 156

CostFormer		75.24 269	73.90 270	79.27 268	82.65 327	58.27 305	80.80 309	82.73 318	61.57 344	75.33 248	83.13 329	55.52 233	91.07 262	64.98 251	78.34 279	88.45 279

API-MVS		81.99 122	81.23 126	84.26 123	90.94 90	70.18 85	91.10 55	89.32 184	71.51 190	78.66 163	88.28 200	65.26 131	95.10 90	64.74 253	91.23 96	87.51 298

新几何1				83.42 160	93.13 54	70.71 74		85.48 274	57.43 378	81.80 123	91.98 101	63.28 146	92.27 213	64.60 254	92.99 70	87.27 304

testing91		76.54 244	75.66 243	79.18 271	88.43 174	55.89 344	81.08 306	83.00 312	73.76 146	75.34 244	84.29 303	46.20 331	90.07 276	64.33 255	84.50 192	91.58 160

testing99		76.09 256	75.12 255	79.00 272	88.16 183	55.50 350	80.79 310	81.40 332	73.30 160	75.17 252	84.27 306	44.48 346	90.02 277	64.28 256	84.22 201	91.48 165

pm-mvs1		77.25 235	76.68 229	78.93 274	84.22 286	58.62 301	86.41 204	88.36 219	71.37 192	73.31 281	88.01 210	61.22 186	89.15 294	64.24 257	73.01 349	89.03 256

TESTMET0.1,1		69.89 327	69.00 321	72.55 353	79.27 376	56.85 327	78.38 348	74.71 387	57.64 375	68.09 339	77.19 388	37.75 385	76.70 388	63.92 258	84.09 202	84.10 361

QAPM		80.88 142	79.50 158	85.03 90	88.01 194	68.97 107	91.59 43	92.00 95	66.63 284	75.15 254	92.16 98	57.70 217	95.45 68	63.52 259	88.76 134	90.66 192

baseline2		75.70 260	73.83 272	81.30 224	83.26 308	61.79 269	82.57 290	80.65 339	66.81 275	66.88 351	83.42 324	57.86 216	92.19 216	63.47 260	79.57 263	89.91 229

LCM-MVSNet-Re		77.05 236	76.94 220	77.36 303	87.20 226	51.60 382	80.06 324	80.46 343	75.20 108	67.69 342	86.72 241	62.48 160	88.98 297	63.44 261	89.25 125	91.51 162

gm-plane-assit					81.40 346	53.83 366			62.72 334		80.94 356		92.39 207	63.40 262

baseline1		76.98 238	76.75 227	77.66 297	88.13 186	55.66 348	85.12 237	81.89 325	73.04 166	76.79 206	88.90 181	62.43 162	87.78 315	63.30 263	71.18 362	89.55 242

AdaColmap		80.58 156	79.42 159	84.06 136	93.09 57	68.91 108	89.36 100	88.97 203	69.27 239	75.70 232	89.69 159	57.20 224	95.77 59	63.06 264	88.41 142	87.50 299

test_vis1_rt		60.28 370	58.42 373	65.84 387	67.25 416	55.60 349	70.44 396	60.94 420	44.33 409	59.00 395	66.64 410	24.91 410	68.67 417	62.80 265	69.48 368	73.25 406

GBi-Net		78.40 204	77.40 210	81.40 221	87.60 212	63.01 250	88.39 138	89.28 186	71.63 185	75.34 244	87.28 225	54.80 238	91.11 256	62.72 266	79.57 263	90.09 218

test1		78.40 204	77.40 210	81.40 221	87.60 212	63.01 250	88.39 138	89.28 186	71.63 185	75.34 244	87.28 225	54.80 238	91.11 256	62.72 266	79.57 263	90.09 218

FMVSNet3		77.88 220	76.85 222	80.97 235	86.84 234	62.36 259	86.52 202	88.77 208	71.13 196	75.34 244	86.66 247	54.07 248	91.10 259	62.72 266	79.57 263	89.45 244

CMPMVS	51.72 21	70.19 324	68.16 327	76.28 312	73.15 406	57.55 319	79.47 331	83.92 293	48.02 404	56.48 404	84.81 293	43.13 355	86.42 327	62.67 269	81.81 238	84.89 351
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
sd_testset		77.70 226	77.40 210	78.60 279	89.03 152	60.02 291	79.00 339	85.83 270	75.19 109	76.61 213	89.98 153	54.81 237	85.46 338	62.63 270	83.55 213	90.33 206

FMVSNet2		78.20 210	77.21 214	81.20 227	87.60 212	62.89 256	87.47 169	89.02 199	71.63 185	75.29 250	87.28 225	54.80 238	91.10 259	62.38 271	79.38 267	89.61 240

testdata2													91.01 263	62.37 272

testing11		75.14 270	74.01 267	78.53 283	88.16 183	56.38 337	80.74 313	80.42 344	70.67 206	72.69 291	83.72 318	43.61 353	89.86 279	62.29 273	83.76 206	89.36 246

CP-MVSNet		78.22 208	78.34 184	77.84 294	87.83 202	54.54 360	87.94 156	91.17 126	77.65 41	73.48 280	88.49 194	62.24 166	88.43 307	62.19 274	74.07 337	90.55 197

XXY-MVS		75.41 266	75.56 244	74.96 328	83.59 301	57.82 314	80.59 316	83.87 295	66.54 285	74.93 260	88.31 199	63.24 148	80.09 373	62.16 275	76.85 296	86.97 313

pmmvs6		74.69 273	73.39 276	78.61 278	81.38 347	57.48 320	86.64 198	87.95 227	64.99 305	70.18 316	86.61 248	50.43 292	89.52 286	62.12 276	70.18 367	88.83 266

1112_ss		77.40 232	76.43 233	80.32 248	89.11 151	60.41 287	83.65 271	87.72 234	62.13 340	73.05 285	86.72 241	62.58 159	89.97 278	62.11 277	80.80 249	90.59 196

PS-CasMVS		78.01 217	78.09 190	77.77 296	87.71 208	54.39 362	88.02 152	91.22 123	77.50 49	73.26 282	88.64 189	60.73 192	88.41 308	61.88 278	73.88 341	90.53 198

CDS-MVSNet		79.07 190	77.70 204	83.17 172	87.60 212	68.23 131	84.40 259	86.20 265	67.49 271	76.36 219	86.54 253	61.54 176	90.79 266	61.86 279	87.33 155	90.49 200
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OpenMVS	72.83 10	79.77 170	78.33 185	84.09 132	85.17 266	69.91 87	90.57 61	90.97 131	66.70 278	72.17 298	91.91 102	54.70 242	93.96 128	61.81 280	90.95 100	88.41 281

K. test v3		71.19 311	68.51 323	79.21 270	83.04 316	57.78 316	84.35 260	76.91 375	72.90 169	62.99 382	82.86 335	39.27 376	91.09 261	61.65 281	52.66 408	88.75 270

CHOSEN 1792x2688		77.63 228	75.69 240	83.44 159	89.98 115	68.58 122	78.70 344	87.50 238	56.38 383	75.80 231	86.84 237	58.67 209	91.40 250	61.58 282	85.75 182	90.34 205

PCF-MVS	73.52 7	80.38 159	78.84 174	85.01 91	87.71 208	68.99 106	83.65 271	91.46 120	63.00 327	77.77 185	90.28 147	66.10 122	95.09 91	61.40 283	88.22 144	90.94 182
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
HY-MVS	69.67 12	77.95 218	77.15 215	80.36 246	87.57 216	60.21 290	83.37 278	87.78 233	66.11 288	75.37 243	87.06 236	63.27 147	90.48 271	61.38 284	82.43 230	90.40 204

HyFIR lowres test		77.53 229	75.40 248	83.94 147	89.59 123	66.62 169	80.36 320	88.64 215	56.29 384	76.45 216	85.17 285	57.64 218	93.28 164	61.34 285	83.10 222	91.91 153

PMMVS		69.34 331	68.67 322	71.35 363	75.67 390	62.03 264	75.17 373	73.46 390	50.00 401	68.68 334	79.05 373	52.07 270	78.13 380	61.16 286	82.77 225	73.90 405

FMVSNet1		77.44 230	76.12 237	81.40 221	86.81 235	63.01 250	88.39 138	89.28 186	70.49 212	74.39 269	87.28 225	49.06 310	91.11 256	60.91 287	78.52 274	90.09 218

sss		73.60 286	73.64 274	73.51 344	82.80 322	55.01 356	76.12 365	81.69 328	62.47 336	74.68 264	85.85 268	57.32 222	78.11 381	60.86 288	80.93 245	87.39 300

Test_1112_low_res		76.40 251	75.44 246	79.27 268	89.28 141	58.09 306	81.69 298	87.07 248	59.53 360	72.48 293	86.67 246	61.30 183	89.33 289	60.81 289	80.15 258	90.41 203

BH-untuned		79.47 177	78.60 177	82.05 206	89.19 145	65.91 182	86.07 215	88.52 217	72.18 178	75.42 240	87.69 215	61.15 187	93.54 153	60.38 290	86.83 163	86.70 319

WTY-MVS		75.65 261	75.68 241	75.57 319	86.40 243	56.82 328	77.92 357	82.40 320	65.10 301	76.18 224	87.72 213	63.13 154	80.90 370	60.31 291	81.96 235	89.00 259

pmmvs4		74.03 282	71.91 293	80.39 245	81.96 336	68.32 128	81.45 302	82.14 322	59.32 361	69.87 324	85.13 286	52.40 262	88.13 311	60.21 292	74.74 333	84.73 354

PEN-MVS		77.73 223	77.69 205	77.84 294	87.07 231	53.91 365	87.91 158	91.18 125	77.56 46	73.14 284	88.82 184	61.23 185	89.17 293	59.95 293	72.37 352	90.43 202

CR-MVSNet		73.37 289	71.27 302	79.67 262	81.32 350	65.19 200	75.92 367	80.30 346	59.92 356	72.73 289	81.19 351	52.50 260	86.69 322	59.84 294	77.71 284	87.11 310

mvs5depth		69.45 330	67.45 342	75.46 323	73.93 397	55.83 345	79.19 336	83.23 305	66.89 274	71.63 304	83.32 325	33.69 395	85.09 341	59.81 295	55.34 405	85.46 340

lessismore_v0				78.97 273	81.01 353	57.15 324		65.99 410		61.16 388	82.82 336	39.12 377	91.34 252	59.67 296	46.92 415	88.43 280

CNLPA		78.08 213	76.79 224	81.97 209	90.40 102	71.07 65	87.59 166	84.55 284	66.03 291	72.38 295	89.64 161	57.56 219	86.04 330	59.61 297	83.35 218	88.79 268

BH-RMVSNet		79.61 172	78.44 181	83.14 173	89.38 135	65.93 181	84.95 242	87.15 247	73.56 151	78.19 175	89.79 157	56.67 228	93.36 162	59.53 298	86.74 164	90.13 214

MS-PatchMatch		73.83 283	72.67 285	77.30 305	83.87 295	66.02 178	81.82 295	84.66 282	61.37 347	68.61 336	82.82 336	47.29 318	88.21 309	59.27 299	84.32 199	77.68 399

test_post1							78.90 342				5.43 433	48.81 314	85.44 339	59.25 300

SCA		74.22 277	72.33 290	79.91 255	84.05 291	62.17 263	79.96 327	79.29 357	66.30 287	72.38 295	80.13 364	51.95 272	88.60 305	59.25 300	77.67 287	88.96 261

FE-MVS		77.78 222	75.68 241	84.08 133	88.09 189	66.00 179	83.13 282	87.79 232	68.42 262	78.01 180	85.23 283	45.50 340	95.12 85	59.11 302	85.83 181	91.11 174

SixPastTwentyTwo		73.37 289	71.26 303	79.70 260	85.08 271	57.89 312	85.57 225	83.56 299	71.03 200	65.66 364	85.88 266	42.10 363	92.57 198	59.11 302	63.34 389	88.65 274

WR-MVS_H		78.51 203	78.49 179	78.56 281	88.02 192	56.38 337	88.43 136	92.67 67	77.14 59	73.89 274	87.55 220	66.25 121	89.24 292	58.92 304	73.55 344	90.06 222

PLC	70.83 11	78.05 215	76.37 235	83.08 177	91.88 77	67.80 141	88.19 147	89.46 180	64.33 312	69.87 324	88.38 197	53.66 251	93.58 149	58.86 305	82.73 226	87.86 290
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
RPSCF		73.23 294	71.46 298	78.54 282	82.50 329	59.85 292	82.18 293	82.84 317	58.96 365	71.15 309	89.41 173	45.48 341	84.77 345	58.82 306	71.83 358	91.02 180

EU-MVSNet		68.53 339	67.61 339	71.31 364	78.51 380	47.01 402	84.47 253	84.27 289	42.27 411	66.44 361	84.79 294	40.44 372	83.76 350	58.76 307	68.54 375	83.17 370

pmmvs-eth3d		70.50 321	67.83 334	78.52 284	77.37 384	66.18 176	81.82 295	81.51 330	58.90 366	63.90 378	80.42 361	42.69 358	86.28 328	58.56 308	65.30 385	83.11 372

TAMVS		78.89 195	77.51 209	83.03 180	87.80 203	67.79 142	84.72 246	85.05 279	67.63 268	76.75 208	87.70 214	62.25 165	90.82 265	58.53 309	87.13 158	90.49 200

WBMVS		73.43 288	72.81 284	75.28 325	87.91 197	50.99 388	78.59 347	81.31 334	65.51 299	74.47 268	84.83 292	46.39 325	86.68 323	58.41 310	77.86 282	88.17 285

ACMH+	68.96 14	76.01 257	74.01 267	82.03 207	88.60 167	65.31 198	88.86 119	87.55 236	70.25 218	67.75 341	87.47 223	41.27 367	93.19 174	58.37 311	75.94 311	87.60 295

tpm		72.37 303	71.71 295	74.35 336	82.19 334	52.00 376	79.22 335	77.29 372	64.56 308	72.95 287	83.68 320	51.35 280	83.26 357	58.33 312	75.80 312	87.81 291

BH-w/o		78.21 209	77.33 213	80.84 237	88.81 158	65.13 202	84.87 243	87.85 231	69.75 231	74.52 267	84.74 295	61.34 182	93.11 179	58.24 313	85.84 180	84.27 357

Vis-MVSNet (Re-imp)		78.36 206	78.45 180	78.07 292	88.64 166	51.78 381	86.70 197	79.63 353	74.14 138	75.11 255	90.83 140	61.29 184	89.75 282	58.10 314	91.60 89	92.69 124

MVP-Stereo		76.12 254	74.46 263	81.13 230	85.37 263	69.79 89	84.42 258	87.95 227	65.03 303	67.46 345	85.33 280	53.28 256	91.73 234	58.01 315	83.27 219	81.85 384
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ambc				75.24 326	73.16 405	50.51 391	63.05 419	87.47 239		64.28 373	77.81 385	17.80 421	89.73 283	57.88 316	60.64 395	85.49 339

TR-MVS		77.44 230	76.18 236	81.20 227	88.24 180	63.24 245	84.61 250	86.40 261	67.55 270	77.81 183	86.48 255	54.10 247	93.15 176	57.75 317	82.72 227	87.20 305

F-COLMAP		76.38 252	74.33 265	82.50 200	89.28 141	66.95 168	88.41 137	89.03 198	64.05 317	66.83 352	88.61 190	46.78 323	92.89 188	57.48 318	78.55 273	87.67 293

EG-PatchMatch MVS		74.04 280	71.82 294	80.71 240	84.92 273	67.42 151	85.86 221	88.08 223	66.04 290	64.22 374	83.85 312	35.10 392	92.56 199	57.44 319	80.83 248	82.16 383

PatchmatchNet		73.12 295	71.33 301	78.49 285	83.18 311	60.85 279	79.63 329	78.57 361	64.13 313	71.73 302	79.81 369	51.20 283	85.97 331	57.40 320	76.36 308	88.66 273
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
DTE-MVSNet		76.99 237	76.80 223	77.54 302	86.24 245	53.06 374	87.52 167	90.66 139	77.08 62	72.50 292	88.67 188	60.48 200	89.52 286	57.33 321	70.74 364	90.05 223

UnsupCasMVSNet_eth		67.33 346	65.99 350	71.37 361	73.48 402	51.47 384	75.16 374	85.19 276	65.20 300	60.78 389	80.93 358	42.35 359	77.20 385	57.12 322	53.69 407	85.44 341

pmmvs5		71.55 309	70.20 315	75.61 318	77.83 381	56.39 336	81.74 297	80.89 335	57.76 374	67.46 345	84.49 296	49.26 307	85.32 340	57.08 323	75.29 326	85.11 348

testing3-2		75.12 271	75.19 253	74.91 329	90.40 102	45.09 410	80.29 322	78.42 362	78.37 36	76.54 215	87.75 212	44.36 347	87.28 319	57.04 324	83.49 215	92.37 136

Anonymous20240521		68.80 335	67.22 344	73.55 343	74.33 395	54.11 363	83.18 280	85.61 272	58.15 371	61.68 386	80.94 356	30.71 402	81.27 368	57.00 325	73.34 348	85.28 343

mvsany_test1		62.30 367	61.26 371	65.41 388	69.52 412	54.86 357	66.86 408	49.78 428	46.65 405	68.50 338	83.21 327	49.15 308	66.28 420	56.93 326	60.77 394	75.11 404

TransMVSNet (Re)		75.39 268	74.56 260	77.86 293	85.50 260	57.10 325	86.78 194	86.09 268	72.17 179	71.53 305	87.34 224	63.01 155	89.31 290	56.84 327	61.83 391	87.17 306

test_vis3_rt		49.26 387	47.02 389	56.00 399	54.30 428	45.27 409	66.76 410	48.08 429	36.83 418	44.38 417	53.20 422	7.17 434	64.07 422	56.77 328	55.66 402	58.65 418

EPMVS		69.02 333	68.16 327	71.59 359	79.61 371	49.80 395	77.40 360	66.93 408	62.82 332	70.01 319	79.05 373	45.79 335	77.86 383	56.58 329	75.26 327	87.13 309

KD-MVS_self_test		68.81 334	67.59 340	72.46 355	74.29 396	45.45 405	77.93 356	87.00 249	63.12 324	63.99 377	78.99 377	42.32 360	84.77 345	56.55 330	64.09 388	87.16 308

tpm2		73.26 293	71.46 298	78.63 277	83.34 306	56.71 331	80.65 315	80.40 345	56.63 382	73.55 279	82.02 348	51.80 276	91.24 254	56.35 331	78.42 277	87.95 287

LTVRE_ROB	69.57 13	76.25 253	74.54 261	81.41 220	88.60 167	64.38 222	79.24 334	89.12 197	70.76 205	69.79 326	87.86 211	49.09 309	93.20 172	56.21 332	80.16 257	86.65 320
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	75.89 258	73.93 269	81.77 212	88.71 164	66.61 170	88.62 132	89.01 200	69.81 227	66.78 353	86.70 245	41.95 365	91.51 245	55.64 333	78.14 280	87.17 306
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 280x420		66.51 352	64.71 354	71.90 357	81.45 345	63.52 238	57.98 421	68.95 404	53.57 391	62.59 384	76.70 389	46.22 330	75.29 404	55.25 334	79.68 262	76.88 401

UBG		73.08 296	72.27 291	75.51 321	88.02 192	51.29 386	78.35 351	77.38 371	65.52 297	73.87 275	82.36 341	45.55 338	86.48 326	55.02 335	84.39 198	88.75 270

EPNet_dtu		75.46 264	74.86 256	77.23 306	82.57 328	54.60 359	86.89 189	83.09 309	71.64 184	66.25 362	85.86 267	55.99 231	88.04 312	54.92 336	86.55 167	89.05 255
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvsany_test3		53.99 378	51.45 383	61.61 393	55.51 427	44.74 412	63.52 417	45.41 432	43.69 410	58.11 399	76.45 391	17.99 420	63.76 423	54.77 337	47.59 414	76.34 402

PVSNet	64.34 18	72.08 307	70.87 307	75.69 317	86.21 246	56.44 335	74.37 381	80.73 338	62.06 341	70.17 317	82.23 345	42.86 357	83.31 356	54.77 337	84.45 196	87.32 303

ITE_SJBPF				78.22 288	81.77 339	60.57 283		83.30 303	69.25 241	67.54 343	87.20 230	36.33 389	87.28 319	54.34 339	74.62 334	86.80 316

SSC-MVS3.2		73.35 292	73.39 276	73.23 345	85.30 264	49.01 396	74.58 380	81.57 329	75.21 107	73.68 277	85.58 275	52.53 258	82.05 363	54.33 340	77.69 286	88.63 275

MDTV_nov1_ep13_2view						37.79 424	75.16 374		55.10 387	66.53 357		49.34 305		53.98 341		87.94 288

gg-mvs-nofinetune		69.95 326	67.96 330	75.94 314	83.07 314	54.51 361	77.23 362	70.29 398	63.11 325	70.32 314	62.33 412	43.62 352	88.69 303	53.88 342	87.76 149	84.62 355

PatchMatch-RL		72.38 302	70.90 306	76.80 310	88.60 167	67.38 154	79.53 330	76.17 380	62.75 333	69.36 329	82.00 349	45.51 339	84.89 344	53.62 343	80.58 252	78.12 398

test_f		52.09 383	50.82 384	55.90 400	53.82 430	42.31 419	59.42 420	58.31 424	36.45 419	56.12 406	70.96 407	12.18 426	57.79 426	53.51 344	56.57 401	67.60 411

Patchmtry		70.74 317	69.16 320	75.49 322	80.72 354	54.07 364	74.94 378	80.30 346	58.34 369	70.01 319	81.19 351	52.50 260	86.54 324	53.37 345	71.09 363	85.87 336

USDC		70.33 322	68.37 324	76.21 313	80.60 356	56.23 340	79.19 336	86.49 259	60.89 348	61.29 387	85.47 278	31.78 399	89.47 288	53.37 345	76.21 309	82.94 376

LF4IMVS		64.02 363	62.19 367	69.50 372	70.90 411	53.29 372	76.13 364	77.18 373	52.65 394	58.59 396	80.98 355	23.55 414	76.52 390	53.06 347	66.66 379	78.68 397

PAPM		77.68 227	76.40 234	81.51 217	87.29 225	61.85 267	83.78 268	89.59 176	64.74 306	71.23 307	88.70 186	62.59 158	93.66 148	52.66 348	87.03 160	89.01 257

dmvs_re		71.14 312	70.58 308	72.80 351	81.96 336	59.68 294	75.60 371	79.34 356	68.55 258	69.27 331	80.72 359	49.42 303	76.54 389	52.56 349	77.79 283	82.19 382

CL-MVSNet_self_test		72.37 303	71.46 298	75.09 327	79.49 373	53.53 367	80.76 312	85.01 280	69.12 246	70.51 311	82.05 347	57.92 215	84.13 348	52.27 350	66.00 383	87.60 295

tpm cat1		70.57 319	68.31 325	77.35 304	82.41 332	57.95 311	78.08 353	80.22 348	52.04 395	68.54 337	77.66 386	52.00 271	87.84 314	51.77 351	72.07 357	86.25 324

our_test_3		69.14 332	67.00 345	75.57 319	79.80 368	58.80 299	77.96 355	77.81 365	59.55 359	62.90 383	78.25 382	47.43 317	83.97 349	51.71 352	67.58 377	83.93 363

MDTV_nov1_ep13			69.97 316		83.18 311	53.48 368	77.10 363	80.18 349	60.45 350	69.33 330	80.44 360	48.89 313	86.90 321	51.60 353	78.51 275

myMVS_eth3d28		73.62 285	73.53 275	73.90 341	88.20 181	47.41 400	78.06 354	79.37 355	74.29 134	73.98 273	84.29 303	44.67 343	83.54 353	51.47 354	87.39 154	90.74 189

JIA-IIPM		66.32 354	62.82 366	76.82 309	77.09 385	61.72 270	65.34 414	75.38 381	58.04 373	64.51 372	62.32 413	42.05 364	86.51 325	51.45 355	69.22 371	82.21 381

testing222		74.04 280	72.66 286	78.19 289	87.89 198	55.36 351	81.06 307	79.20 358	71.30 193	74.65 265	83.57 322	39.11 378	88.67 304	51.43 356	85.75 182	90.53 198

MSDG		73.36 291	70.99 305	80.49 244	84.51 282	65.80 186	80.71 314	86.13 267	65.70 294	65.46 365	83.74 316	44.60 344	90.91 264	51.13 357	76.89 294	84.74 353

PatchT		68.46 340	67.85 332	70.29 369	80.70 355	43.93 413	72.47 386	74.88 384	60.15 354	70.55 310	76.57 390	49.94 297	81.59 365	50.58 358	74.83 332	85.34 342

GG-mvs-BLEND				75.38 324	81.59 342	55.80 346	79.32 333	69.63 400		67.19 348	73.67 401	43.24 354	88.90 301	50.41 359	84.50 192	81.45 386

KD-MVS_2432*1600		66.22 355	63.89 358	73.21 346	75.47 393	53.42 369	70.76 394	84.35 286	64.10 315	66.52 358	78.52 379	34.55 393	84.98 342	50.40 360	50.33 412	81.23 387

miper_refine_blended		66.22 355	63.89 358	73.21 346	75.47 393	53.42 369	70.76 394	84.35 286	64.10 315	66.52 358	78.52 379	34.55 393	84.98 342	50.40 360	50.33 412	81.23 387

AllTest		70.96 314	68.09 329	79.58 264	85.15 268	63.62 233	84.58 251	79.83 350	62.31 337	60.32 391	86.73 239	32.02 397	88.96 299	50.28 362	71.57 360	86.15 327

TestCases				79.58 264	85.15 268	63.62 233		79.83 350	62.31 337	60.32 391	86.73 239	32.02 397	88.96 299	50.28 362	71.57 360	86.15 327

TAPA-MVS	73.13 9	79.15 187	77.94 193	82.79 193	89.59 123	62.99 254	88.16 149	91.51 116	65.77 293	77.14 202	91.09 131	60.91 191	93.21 169	50.26 364	87.05 159	92.17 147
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
YYNet1		65.03 359	62.91 364	71.38 360	75.85 389	56.60 333	69.12 402	74.66 388	57.28 379	54.12 407	77.87 384	45.85 334	74.48 406	49.95 365	61.52 393	83.05 373

MDA-MVSNet_test_wron		65.03 359	62.92 363	71.37 361	75.93 387	56.73 329	69.09 403	74.73 386	57.28 379	54.03 408	77.89 383	45.88 333	74.39 407	49.89 366	61.55 392	82.99 375

tpmvs		71.09 313	69.29 318	76.49 311	82.04 335	56.04 342	78.92 341	81.37 333	64.05 317	67.18 349	78.28 381	49.74 300	89.77 281	49.67 367	72.37 352	83.67 366

ppachtmachnet_test		70.04 325	67.34 343	78.14 290	79.80 368	61.13 274	79.19 336	80.59 340	59.16 363	65.27 367	79.29 372	46.75 324	87.29 318	49.33 368	66.72 378	86.00 333

UnsupCasMVSNet_bld		63.70 364	61.53 370	70.21 370	73.69 400	51.39 385	72.82 385	81.89 325	55.63 386	57.81 400	71.80 405	38.67 380	78.61 378	49.26 369	52.21 410	80.63 391

UWE-MVS		72.13 306	71.49 297	74.03 339	86.66 240	47.70 398	81.40 304	76.89 376	63.60 322	75.59 233	84.22 307	39.94 374	85.62 335	48.98 370	86.13 175	88.77 269

dp		66.80 349	65.43 351	70.90 368	79.74 370	48.82 397	75.12 376	74.77 385	59.61 358	64.08 376	77.23 387	42.89 356	80.72 371	48.86 371	66.58 380	83.16 371

FMVSNet5		69.50 329	67.96 330	74.15 338	82.97 320	55.35 352	80.01 326	82.12 323	62.56 335	63.02 380	81.53 350	36.92 387	81.92 364	48.42 372	74.06 338	85.17 347

thres100view900		76.50 246	75.55 245	79.33 267	89.52 126	56.99 326	85.83 223	83.23 305	73.94 141	76.32 220	87.12 233	51.89 274	91.95 224	48.33 373	83.75 207	89.07 250

tfpn200view9		76.42 250	75.37 250	79.55 266	89.13 147	57.65 317	85.17 234	83.60 297	73.41 157	76.45 216	86.39 257	52.12 266	91.95 224	48.33 373	83.75 207	89.07 250

thres400		76.50 246	75.37 250	79.86 256	89.13 147	57.65 317	85.17 234	83.60 297	73.41 157	76.45 216	86.39 257	52.12 266	91.95 224	48.33 373	83.75 207	90.00 224

LCM-MVSNet		54.25 377	49.68 387	67.97 383	53.73 431	45.28 408	66.85 409	80.78 337	35.96 420	39.45 421	62.23 414	8.70 431	78.06 382	48.24 376	51.20 411	80.57 392

RPMNet		73.51 287	70.49 310	82.58 199	81.32 350	65.19 200	75.92 367	92.27 84	57.60 376	72.73 289	76.45 391	52.30 263	95.43 70	48.14 377	77.71 284	87.11 310

thres600view7		76.50 246	75.44 246	79.68 261	89.40 133	57.16 323	85.53 231	83.23 305	73.79 145	76.26 221	87.09 234	51.89 274	91.89 227	48.05 378	83.72 210	90.00 224

TDRefinement		67.49 344	64.34 355	76.92 308	73.47 403	61.07 276	84.86 244	82.98 313	59.77 357	58.30 398	85.13 286	26.06 407	87.89 313	47.92 379	60.59 396	81.81 385

thres200		75.55 262	74.47 262	78.82 275	87.78 206	57.85 313	83.07 285	83.51 300	72.44 175	75.84 230	84.42 298	52.08 269	91.75 232	47.41 380	83.64 212	86.86 315

PVSNet_0	57.27 20	61.67 369	59.27 372	68.85 376	79.61 371	57.44 321	68.01 404	73.44 391	55.93 385	58.54 397	70.41 408	44.58 345	77.55 384	47.01 381	35.91 420	71.55 408

DP-MVS		76.78 242	74.57 259	83.42 160	93.29 48	69.46 97	88.55 134	83.70 296	63.98 319	70.20 315	88.89 182	54.01 249	94.80 102	46.66 382	81.88 237	86.01 331

COLMAP_ROB	66.92 17	73.01 297	70.41 312	80.81 238	87.13 229	65.63 190	88.30 144	84.19 291	62.96 328	63.80 379	87.69 215	38.04 384	92.56 199	46.66 382	74.91 331	84.24 358
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet		70.69 318	69.30 317	74.88 330	84.52 281	56.35 339	75.87 369	79.42 354	64.59 307	67.76 340	82.41 340	41.10 368	81.54 366	46.64 384	81.34 240	86.75 318

LS3D		76.95 239	74.82 257	83.37 163	90.45 100	67.36 155	89.15 109	86.94 251	61.87 343	69.52 327	90.61 143	51.71 278	94.53 110	46.38 385	86.71 165	88.21 284

ETVMVS		72.25 305	71.05 304	75.84 315	87.77 207	51.91 378	79.39 332	74.98 383	69.26 240	73.71 276	82.95 332	40.82 371	86.14 329	46.17 386	84.43 197	89.47 243

MDA-MVSNet-bldmvs		66.68 350	63.66 360	75.75 316	79.28 375	60.56 284	73.92 383	78.35 363	64.43 309	50.13 413	79.87 368	44.02 350	83.67 351	46.10 387	56.86 399	83.03 374

new-patchmatchnet		61.73 368	61.73 369	61.70 392	72.74 408	24.50 435	69.16 401	78.03 364	61.40 345	56.72 403	75.53 397	38.42 381	76.48 391	45.95 388	57.67 398	84.13 360

WB-MVSnew		71.96 308	71.65 296	72.89 350	84.67 280	51.88 379	82.29 292	77.57 367	62.31 337	73.67 278	83.00 331	53.49 254	81.10 369	45.75 389	82.13 233	85.70 337

TinyColmap		67.30 347	64.81 353	74.76 332	81.92 338	56.68 332	80.29 322	81.49 331	60.33 351	56.27 405	83.22 326	24.77 411	87.66 317	45.52 390	69.47 369	79.95 394

pmmvs3		57.79 373	54.26 378	68.37 379	64.02 421	56.72 330	75.12 376	65.17 412	40.20 413	52.93 409	69.86 409	20.36 418	75.48 401	45.45 391	55.25 406	72.90 407

OpenMVS_ROB	64.09 19	70.56 320	68.19 326	77.65 298	80.26 359	59.41 298	85.01 240	82.96 314	58.76 367	65.43 366	82.33 342	37.63 386	91.23 255	45.34 392	76.03 310	82.32 380

test0.0.03 1		68.00 343	67.69 337	68.90 375	77.55 382	47.43 399	75.70 370	72.95 394	66.66 279	66.56 356	82.29 344	48.06 315	75.87 398	44.97 393	74.51 335	83.41 368

testgi		66.67 351	66.53 348	67.08 385	75.62 391	41.69 420	75.93 366	76.50 377	66.11 288	65.20 370	86.59 249	35.72 391	74.71 405	43.71 394	73.38 347	84.84 352

Anonymous20231206		68.60 336	67.80 335	71.02 366	80.23 361	50.75 390	78.30 352	80.47 342	56.79 381	66.11 363	82.63 339	46.35 328	78.95 377	43.62 395	75.70 313	83.36 369

tfpnnormal		74.39 274	73.16 280	78.08 291	86.10 251	58.05 307	84.65 249	87.53 237	70.32 215	71.22 308	85.63 273	54.97 236	89.86 279	43.03 396	75.02 330	86.32 323

MIMVSNet1		68.58 337	66.78 347	73.98 340	80.07 363	51.82 380	80.77 311	84.37 285	64.40 310	59.75 394	82.16 346	36.47 388	83.63 352	42.73 397	70.33 366	86.48 322

ttmdpeth		59.91 371	57.10 375	68.34 380	67.13 417	46.65 404	74.64 379	67.41 407	48.30 403	62.52 385	85.04 290	20.40 417	75.93 397	42.55 398	45.90 418	82.44 379

test20.03		67.45 345	66.95 346	68.94 374	75.48 392	44.84 411	77.50 359	77.67 366	66.66 279	63.01 381	83.80 314	47.02 321	78.40 379	42.53 399	68.86 374	83.58 367

ADS-MVSNet2		66.20 357	63.33 361	74.82 331	79.92 364	58.75 300	67.55 406	75.19 382	53.37 392	65.25 368	75.86 394	42.32 360	80.53 372	41.57 400	68.91 372	85.18 345

ADS-MVSNet		64.36 362	62.88 365	68.78 377	79.92 364	47.17 401	67.55 406	71.18 396	53.37 392	65.25 368	75.86 394	42.32 360	73.99 408	41.57 400	68.91 372	85.18 345

Patchmatch-test		64.82 361	63.24 362	69.57 371	79.42 374	49.82 394	63.49 418	69.05 403	51.98 397	59.95 393	80.13 364	50.91 285	70.98 412	40.66 402	73.57 343	87.90 289

MVS-HIRNet		59.14 372	57.67 374	63.57 390	81.65 340	43.50 414	71.73 388	65.06 413	39.59 415	51.43 410	57.73 418	38.34 382	82.58 360	39.53 403	73.95 339	64.62 414

WAC-MVS						42.58 416								39.46 404

myMVS_eth3d		67.02 348	66.29 349	69.21 373	84.68 277	42.58 416	78.62 345	73.08 392	66.65 282	66.74 354	79.46 370	31.53 400	82.30 361	39.43 405	76.38 306	82.75 377

DSMNet-mixed		57.77 374	56.90 376	60.38 394	67.70 415	35.61 425	69.18 400	53.97 426	32.30 424	57.49 401	79.88 367	40.39 373	68.57 418	38.78 406	72.37 352	76.97 400

N_pmnet		52.79 382	53.26 380	51.40 406	78.99 377	7.68 440	69.52 398	3.89 439	51.63 398	57.01 402	74.98 398	40.83 370	65.96 421	37.78 407	64.67 386	80.56 393

testing3		68.56 338	67.67 338	71.22 365	87.33 222	42.87 415	83.06 286	71.54 395	70.36 213	69.08 332	84.38 300	30.33 403	85.69 334	37.50 408	75.45 321	85.09 349

MVStest1		56.63 375	52.76 381	68.25 381	61.67 423	53.25 373	71.67 389	68.90 405	38.59 416	50.59 412	83.05 330	25.08 409	70.66 413	36.76 409	38.56 419	80.83 390

test_0402		72.79 300	70.44 311	79.84 257	88.13 186	65.99 180	85.93 218	84.29 288	65.57 296	67.40 347	85.49 277	46.92 322	92.61 195	35.88 410	74.38 336	80.94 389

new_pmnet		50.91 385	50.29 385	52.78 405	68.58 414	34.94 427	63.71 416	56.63 425	39.73 414	44.95 416	65.47 411	21.93 416	58.48 425	34.98 411	56.62 400	64.92 413

APD_test1		53.31 381	49.93 386	63.42 391	65.68 418	50.13 392	71.59 390	66.90 409	34.43 421	40.58 420	71.56 406	8.65 432	76.27 393	34.64 412	55.36 404	63.86 415

Syy-MVS		68.05 342	67.85 332	68.67 378	84.68 277	40.97 421	78.62 345	73.08 392	66.65 282	66.74 354	79.46 370	52.11 268	82.30 361	32.89 413	76.38 306	82.75 377

dmvs_testset		62.63 366	64.11 357	58.19 396	78.55 379	24.76 434	75.28 372	65.94 411	67.91 267	60.34 390	76.01 393	53.56 252	73.94 409	31.79 414	67.65 376	75.88 403

UWE-MVS-28		65.32 358	64.93 352	66.49 386	78.70 378	38.55 423	77.86 358	64.39 415	62.00 342	64.13 375	83.60 321	41.44 366	76.00 396	31.39 415	80.89 246	84.92 350

ANet_high		50.57 386	46.10 390	63.99 389	48.67 434	39.13 422	70.99 393	80.85 336	61.39 346	31.18 423	57.70 419	17.02 422	73.65 410	31.22 416	15.89 431	79.18 396

EGC-MVSNET		52.07 384	47.05 388	67.14 384	83.51 303	60.71 281	80.50 318	67.75 406	0.07 434	0.43 435	75.85 396	24.26 412	81.54 366	28.82 417	62.25 390	59.16 417

PMMVS2		40.82 393	38.86 397	46.69 407	53.84 429	16.45 438	48.61 424	49.92 427	37.49 417	31.67 422	60.97 415	8.14 433	56.42 427	28.42 418	30.72 424	67.19 412

tmp_tt		18.61 400	21.40 403	10.23 416	4.82 439	10.11 439	34.70 426	30.74 437	1.48 433	23.91 429	26.07 430	28.42 405	13.41 435	27.12 419	15.35 432	7.17 430

test_method		31.52 396	29.28 400	38.23 410	27.03 438	6.50 441	20.94 429	62.21 418	4.05 432	22.35 430	52.50 423	13.33 424	47.58 430	27.04 420	34.04 422	60.62 416

testf1		45.72 388	41.96 392	57.00 397	56.90 425	45.32 406	66.14 411	59.26 422	26.19 425	30.89 424	60.96 416	4.14 435	70.64 414	26.39 421	46.73 416	55.04 420

APD_test2		45.72 388	41.96 392	57.00 397	56.90 425	45.32 406	66.14 411	59.26 422	26.19 425	30.89 424	60.96 416	4.14 435	70.64 414	26.39 421	46.73 416	55.04 420

FPMVS		53.68 380	51.64 382	59.81 395	65.08 419	51.03 387	69.48 399	69.58 401	41.46 412	40.67 419	72.32 404	16.46 423	70.00 416	24.24 423	65.42 384	58.40 419

Gipuma		45.18 391	41.86 394	55.16 403	77.03 386	51.52 383	32.50 427	80.52 341	32.46 423	27.12 426	35.02 427	9.52 430	75.50 400	22.31 424	60.21 397	38.45 426
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
dongtai		45.42 390	45.38 391	45.55 408	73.36 404	26.85 432	67.72 405	34.19 434	54.15 390	49.65 414	56.41 421	25.43 408	62.94 424	19.45 425	28.09 425	46.86 424

DeepMVS_CX				27.40 414	40.17 437	26.90 431		24.59 438	17.44 430	23.95 428	48.61 425	9.77 429	26.48 433	18.06 426	24.47 427	28.83 427

WB-MVS		54.94 376	54.72 377	55.60 402	73.50 401	20.90 436	74.27 382	61.19 419	59.16 363	50.61 411	74.15 399	47.19 320	75.78 399	17.31 427	35.07 421	70.12 409

PMVS	37.38 22	44.16 392	40.28 396	55.82 401	40.82 436	42.54 418	65.12 415	63.99 416	34.43 421	24.48 427	57.12 420	3.92 437	76.17 395	17.10 428	55.52 403	48.75 422
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 398	25.89 402	43.81 409	44.55 435	35.46 426	28.87 428	39.07 433	18.20 429	18.58 431	40.18 426	2.68 438	47.37 431	17.07 429	23.78 428	48.60 423
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SSC-MVS		53.88 379	53.59 379	54.75 404	72.87 407	19.59 437	73.84 384	60.53 421	57.58 377	49.18 415	73.45 402	46.34 329	75.47 402	16.20 430	32.28 423	69.20 410

E-PMN		31.77 395	30.64 398	35.15 412	52.87 432	27.67 429	57.09 422	47.86 430	24.64 427	16.40 432	33.05 428	11.23 428	54.90 428	14.46 431	18.15 429	22.87 428

EMVS		30.81 397	29.65 399	34.27 413	50.96 433	25.95 433	56.58 423	46.80 431	24.01 428	15.53 433	30.68 429	12.47 425	54.43 429	12.81 432	17.05 430	22.43 429

kuosan		39.70 394	40.40 395	37.58 411	64.52 420	26.98 430	65.62 413	33.02 435	46.12 406	42.79 418	48.99 424	24.10 413	46.56 432	12.16 433	26.30 426	39.20 425

wuyk23d		16.82 401	15.94 404	19.46 415	58.74 424	31.45 428	39.22 425	3.74 440	6.84 431	6.04 434	2.70 434	1.27 439	24.29 434	10.54 434	14.40 433	2.63 431

testmvs		6.04 404	8.02 407	0.10 418	0.08 440	0.03 443	69.74 397	0.04 441	0.05 435	0.31 436	1.68 435	0.02 441	0.04 436	0.24 435	0.02 434	0.25 433

test123		6.12 403	8.11 406	0.14 417	0.06 441	0.09 442	71.05 392	0.03 442	0.04 436	0.25 437	1.30 436	0.05 440	0.03 437	0.21 436	0.01 435	0.29 432

mmdepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

monomultidepth		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

test_blank		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet_test		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

DCPMVS		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

cdsmvs_eth3d_5k		19.96 399	26.61 401	0.00 419	0.00 442	0.00 444	0.00 430	89.26 189	0.00 437	0.00 438	88.61 190	61.62 175	0.00 438	0.00 437	0.00 436	0.00 434

pcd_1.5k_mvsjas		5.26 405	7.02 408	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	63.15 151	0.00 438	0.00 437	0.00 436	0.00 434

sosnet-low-res		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

sosnet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uncertanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

Regformer		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

ab-mvs-re		7.23 402	9.64 405	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	86.72 241	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

uanet		0.00 406	0.00 409	0.00 419	0.00 442	0.00 444	0.00 430	0.00 443	0.00 437	0.00 438	0.00 437	0.00 442	0.00 438	0.00 437	0.00 436	0.00 434

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 127	91.30 15

test_one_0601					95.07 7	71.46 57		94.14 5	78.27 37	92.05 11	95.74 6	80.83 11

eth-test2					0.00 442

eth-test					0.00 442

test_241102_ONE					95.30 2	70.98 66		94.06 10	77.17 58	93.10 1	95.39 14	82.99 1	97.27 12

save fliter					93.80 40	72.35 42	90.47 66	91.17 126	74.31 132

test0726					95.27 5	71.25 59	93.60 6	94.11 6	77.33 52	92.81 3	95.79 3	80.98 9

GSMVS																88.96 261

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 281				88.96 261

sam_mvs												50.01 295

MTGPA								92.02 93

test_post											5.46 432	50.36 293	84.24 347

patchmatchnet-post											74.00 400	51.12 284	88.60 305

MTMP							92.18 34	32.83 436

TEST9					93.26 52	72.96 25	88.75 125	91.89 101	68.44 261	85.00 70	93.10 77	74.36 28	95.41 73

test_8					93.13 54	72.57 35	88.68 130	91.84 105	68.69 256	84.87 74	93.10 77	74.43 26	95.16 83

agg_prior					92.85 62	71.94 50		91.78 108		84.41 85			94.93 94

test_prior4						72.60 34	89.01 114

test_prior				86.33 57	92.61 68	69.59 91		92.97 54					95.48 67			93.91 63

新几何2							86.29 210

旧先验1					91.96 74	65.79 187		86.37 262			93.08 81	69.31 86			92.74 74	88.74 272

原ACMM2							86.86 190

test222					91.50 80	68.26 130	84.16 263	83.20 308	54.63 389	79.74 146	91.63 112	58.97 208			91.42 93	86.77 317

segment_acmp												73.08 39

testdata1							84.14 264		75.71 94

test12				86.80 52	92.63 67	70.70 75		91.79 107		82.71 114		71.67 56	96.16 47		94.50 51	93.54 88

plane_prior7					90.08 109	68.51 124

plane_prior6					89.84 118	68.70 118						60.42 201

plane_prior4											91.00 137

plane_prior3						68.60 121			78.44 32	78.92 158

plane_prior2							91.25 52		79.12 24

plane_prior1					89.90 117

plane_prior						68.71 116	90.38 70		77.62 42						86.16 174

n2								0.00 443

nn								0.00 443

door-mid								69.98 399

test11								92.23 87

door								69.44 402

HQP5-MVS						66.98 165

HQP-NCC					89.33 136		89.17 105		76.41 79	77.23 196

ACMP_Plane					89.33 136		89.17 105		76.41 79	77.23 196

HQP4-MVS										77.24 195			95.11 87			91.03 178

HQP3-MVS								92.19 90							85.99 178

HQP2-MVS												60.17 204

NP-MVS					89.62 122	68.32 128					90.24 149

ACMMP++_ref															81.95 236

ACMMP++															81.25 241

Test By Simon												64.33 138

High-resolution multi-view benchmark