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.

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 54	93.83 4	93.96 14	75.70 102	91.06 16	96.03 1	76.84 14	97.03 17	89.09 20	95.65 27	94.47 42
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 25	93.63 22	74.77 130	92.29 7	95.97 2	74.28 30	97.24 13	88.58 31	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
test0726					95.27 5	71.25 61	93.60 7	94.11 7	77.33 57	92.81 3	95.79 3	80.98 9

DVP-MVS		89.60 3	90.35 3	87.33 41	95.27 5	71.25 61	93.49 10	92.73 65	77.33 57	92.12 9	95.78 4	80.98 9	97.40 9	89.08 21	96.41 12	93.33 105
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									78.38 38	92.12 9	95.78 4	81.46 7	97.40 9	89.42 18	96.57 7	94.67 29

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 61	95.06 1	94.23 3	78.38 38	92.78 4	95.74 6	82.45 3	97.49 4	89.42 18	96.68 2	94.95 12

test_one_0601					95.07 7	71.46 59		94.14 6	78.27 41	92.05 11	95.74 6	80.83 11

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 68	93.57 8	94.06 11	77.24 60	93.10 1	95.72 8	82.99 1	97.44 7	89.07 23	96.63 4	94.88 16

test_241102_TWO								94.06 11	77.24 60	92.78 4	95.72 8	81.26 8	97.44 7	89.07 23	96.58 6	94.26 53

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 46	94.10 9	75.90 98	92.29 7	95.66 10	81.67 6	97.38 11	87.44 43	96.34 15	93.95 67
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
reproduce_model		87.28 32	87.39 30	86.95 50	93.10 58	71.24 65	91.60 45	93.19 36	74.69 131	88.80 28	95.61 11	70.29 77	96.44 39	86.20 51	93.08 71	93.16 115

reproduce-ours		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 121	88.96 25	95.54 12	71.20 66	96.54 36	86.28 49	93.49 67	93.06 121

our_new_method		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 121	88.96 25	95.54 12	71.20 66	96.54 36	86.28 49	93.49 67	93.06 121

lecture		88.09 14	88.59 13	86.58 58	93.26 52	69.77 92	93.70 6	94.16 5	77.13 65	89.76 21	95.52 14	72.26 49	96.27 44	86.87 45	94.65 48	93.70 83

fmvsm_s_conf0.5_n_9		87.39 30	87.95 20	85.70 77	89.48 133	67.88 149	88.59 139	89.05 215	80.19 12	90.70 17	95.40 15	74.56 25	93.92 145	91.54 2	92.07 86	95.31 5

test_241102_ONE					95.30 2	70.98 68		94.06 11	77.17 63	93.10 1	95.39 16	82.99 1	97.27 12

MP-MVS-pluss		87.67 22	87.72 22	87.54 36	93.64 44	72.04 50	89.80 84	93.50 26	75.17 118	86.34 62	95.29 17	70.86 70	96.00 55	88.78 29	96.04 16	94.58 35
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SF-MVS		88.46 12	88.74 12	87.64 35	92.78 66	71.95 51	92.40 25	94.74 2	75.71 100	89.16 24	95.10 18	75.65 21	96.19 47	87.07 44	96.01 17	94.79 23

ACMMP_NAP		88.05 17	88.08 18	87.94 19	93.70 41	73.05 22	90.86 60	93.59 24	76.27 92	88.14 36	95.09 19	71.06 68	96.67 29	87.67 39	96.37 14	94.09 59

fmvsm_s_conf0.5_n_3		86.36 49	87.46 29	83.09 189	87.08 244	65.21 213	89.09 116	90.21 164	79.67 19	89.98 19	95.02 20	73.17 39	91.71 250	91.30 3	91.60 93	92.34 152

MM		89.16 6	89.23 7	88.97 4	90.79 98	73.65 10	92.66 24	91.17 133	86.57 1	87.39 52	94.97 21	71.70 58	97.68 1	92.19 1	95.63 28	95.57 1

fmvsm_s_conf0.5_n_8		86.56 44	87.17 35	84.73 113	87.76 216	65.62 204	89.20 107	92.21 90	79.94 17	89.74 22	94.86 22	68.63 100	94.20 130	90.83 5	91.39 98	94.38 46

MTAPA		87.23 33	87.00 36	87.90 22	94.18 35	74.25 5	86.58 214	92.02 98	79.45 22	85.88 64	94.80 23	68.07 106	96.21 46	86.69 47	95.34 32	93.23 108

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 74	72.96 25	93.73 5	93.67 21	80.19 12	88.10 37	94.80 23	73.76 34	97.11 15	87.51 41	95.82 21	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
9.14			88.26 16		92.84 65		91.52 51	94.75 1	73.93 152	88.57 30	94.67 25	75.57 22	95.79 59	86.77 46	95.76 23

SR-MVS		86.73 40	86.67 43	86.91 51	94.11 37	72.11 49	92.37 29	92.56 76	74.50 135	86.84 59	94.65 26	67.31 115	95.77 60	84.80 62	92.85 74	92.84 133

region2R		87.42 28	87.20 34	88.09 14	94.63 14	73.55 13	93.03 15	93.12 41	76.73 79	84.45 88	94.52 27	69.09 91	96.70 27	84.37 68	94.83 45	94.03 62

ACMMPR		87.44 26	87.23 33	88.08 15	94.64 13	73.59 12	93.04 13	93.20 35	76.78 76	84.66 83	94.52 27	68.81 97	96.65 30	84.53 66	94.90 41	94.00 64

APD-MVS		87.44 26	87.52 27	87.19 43	94.24 32	72.39 41	91.86 41	92.83 61	73.01 179	88.58 29	94.52 27	73.36 35	96.49 38	84.26 69	95.01 37	92.70 135
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
APD-MVS_3200maxsize		85.97 56	85.88 60	86.22 63	92.69 68	69.53 95	91.93 38	92.99 50	73.54 163	85.94 63	94.51 30	65.80 136	95.61 63	83.04 83	92.51 79	93.53 98

CP-MVS		87.11 35	86.92 40	87.68 34	94.20 34	73.86 7	93.98 3	92.82 64	76.62 82	83.68 106	94.46 31	67.93 108	95.95 58	84.20 72	94.39 57	93.23 108

SR-MVS-dyc-post		85.77 62	85.61 67	86.23 62	93.06 60	70.63 78	91.88 39	92.27 85	73.53 164	85.69 67	94.45 32	65.00 144	95.56 64	82.75 88	91.87 89	92.50 145

RE-MVS-def			85.48 70		93.06 60	70.63 78	91.88 39	92.27 85	73.53 164	85.69 67	94.45 32	63.87 152		82.75 88	91.87 89	92.50 145

HFP-MVS		87.58 23	87.47 28	87.94 19	94.58 16	73.54 15	93.04 13	93.24 34	76.78 76	84.91 76	94.44 34	70.78 71	96.61 32	84.53 66	94.89 42	93.66 84

PGM-MVS		86.68 42	86.27 50	87.90 22	94.22 33	73.38 18	90.22 76	93.04 42	75.53 105	83.86 102	94.42 35	67.87 110	96.64 31	82.70 92	94.57 52	93.66 84

MP-MVS		87.71 20	87.64 23	87.93 21	94.36 26	73.88 6	92.71 23	92.65 71	77.57 49	83.84 103	94.40 36	72.24 50	96.28 43	85.65 53	95.30 35	93.62 91
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_l_conf0.5_n_3		86.02 52	86.32 48	85.14 92	87.20 235	68.54 126	89.57 93	90.44 153	75.31 112	87.49 49	94.39 37	72.86 44	92.72 207	89.04 25	90.56 112	94.16 55

fmvsm_s_conf0.1_n_2		83.80 93	83.79 94	83.83 161	85.62 278	64.94 223	87.03 194	86.62 282	74.32 140	87.97 42	94.33 38	60.67 208	92.60 210	89.72 13	87.79 160	93.96 65

fmvsm_l_conf0.5_n_9		85.84 61	86.63 44	83.46 172	87.12 243	66.01 191	88.56 141	89.43 191	75.59 104	89.32 23	94.32 39	72.89 43	91.21 273	90.11 10	92.33 83	93.16 115

ZNCC-MVS		87.94 19	87.85 21	88.20 12	94.39 24	73.33 19	93.03 15	93.81 18	76.81 74	85.24 71	94.32 39	71.76 56	96.93 19	85.53 55	95.79 22	94.32 50

MVS_0304		87.69 21	87.55 26	88.12 13	89.45 134	71.76 53	91.47 52	89.54 187	82.14 3	86.65 60	94.28 41	68.28 105	97.46 6	90.81 6	95.31 34	95.15 8

test_fmvsmconf0.01_n		84.73 84	84.52 86	85.34 87	80.25 389	69.03 106	89.47 95	89.65 183	73.24 175	86.98 57	94.27 42	66.62 120	93.23 179	90.26 9	89.95 124	93.78 80

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 28	92.85 60	80.26 11	87.78 43	94.27 42	75.89 19	96.81 23	87.45 42	96.44 9	93.05 123

mPP-MVS		86.67 43	86.32 48	87.72 30	94.41 22	73.55 13	92.74 21	92.22 89	76.87 73	82.81 120	94.25 44	66.44 124	96.24 45	82.88 86	94.28 60	93.38 101

fmvsm_s_conf0.5_n_2		84.04 89	84.11 90	83.81 163	86.17 265	65.00 221	86.96 197	87.28 266	74.35 139	88.25 34	94.23 45	61.82 184	92.60 210	89.85 11	88.09 157	93.84 74

DeepC-MVS	79.81 2	87.08 37	86.88 42	87.69 33	91.16 87	72.32 45	90.31 74	93.94 15	77.12 66	82.82 119	94.23 45	72.13 52	97.09 16	84.83 61	95.37 31	93.65 88
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS		87.18 34	86.91 41	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 107	94.17 47	67.45 113	96.60 33	83.06 81	94.50 53	94.07 60

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 17	94.11 7	80.27 10	91.35 14	94.16 48	78.35 13	96.77 24	89.59 16	94.22 62	94.67 29
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
test_fmvsmconf0.1_n		85.61 66	85.65 66	85.50 83	82.99 347	69.39 103	89.65 89	90.29 162	73.31 171	87.77 44	94.15 49	71.72 57	93.23 179	90.31 8	90.67 111	93.89 71

DeepPCF-MVS	80.84 1	88.10 13	88.56 14	86.73 55	92.24 73	69.03 106	89.57 93	93.39 31	77.53 53	89.79 20	94.12 50	78.98 12	96.58 35	85.66 52	95.72 24	94.58 35

HPM-MVS_fast		85.35 74	84.95 80	86.57 59	93.69 42	70.58 80	92.15 36	91.62 119	73.89 153	82.67 122	94.09 51	62.60 168	95.54 66	80.93 105	92.93 73	93.57 94

ZD-MVS					94.38 25	72.22 46		92.67 68	70.98 218	87.75 45	94.07 52	74.01 33	96.70 27	84.66 64	94.84 44

fmvsm_s_conf0.1_n_a		83.32 110	82.99 108	84.28 130	83.79 323	68.07 141	89.34 104	82.85 342	69.80 252	87.36 53	94.06 53	68.34 104	91.56 256	87.95 37	83.46 241	93.21 111

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 65	93.00 47	80.90 7	88.06 38	94.06 53	76.43 16	96.84 21	88.48 34	95.99 18	94.34 49

test_fmvsmconf_n		85.92 57	86.04 58	85.57 82	85.03 297	69.51 96	89.62 92	90.58 148	73.42 167	87.75 45	94.02 55	72.85 45	93.24 178	90.37 7	90.75 109	93.96 65

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 55	82.45 3	96.87 20	83.77 76	96.48 8	94.88 16

PC_three_1452									68.21 289	92.02 12	94.00 57	82.09 5	95.98 57	84.58 65	96.68 2	94.95 12

SD-MVS		88.06 15	88.50 15	86.71 56	92.60 71	72.71 29	91.81 42	93.19 36	77.87 42	90.32 18	94.00 57	74.83 23	93.78 152	87.63 40	94.27 61	93.65 88
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
GST-MVS		87.42 28	87.26 31	87.89 24	94.12 36	72.97 24	92.39 27	93.43 29	76.89 72	84.68 80	93.99 59	70.67 73	96.82 22	84.18 73	95.01 37	93.90 70

test_fmvsm_n_1920		85.29 75	85.34 72	85.13 95	86.12 267	69.93 88	88.65 137	90.78 144	69.97 248	88.27 33	93.98 60	71.39 63	91.54 258	88.49 33	90.45 114	93.91 68

fmvsm_s_conf0.1_n		83.56 102	83.38 101	84.10 139	84.86 299	67.28 169	89.40 101	83.01 337	70.67 225	87.08 55	93.96 61	68.38 103	91.45 264	88.56 32	84.50 215	93.56 95

HPM-MVS		87.11 35	86.98 38	87.50 39	93.88 39	72.16 47	92.19 34	93.33 32	76.07 95	83.81 104	93.95 62	69.77 83	96.01 54	85.15 56	94.66 47	94.32 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_7		83.34 109	84.03 91	81.28 245	85.73 275	65.13 216	85.40 250	89.90 174	74.96 123	82.13 127	93.89 63	66.65 119	87.92 335	86.56 48	91.05 103	90.80 208

fmvsm_s_conf0.5_n_5		85.22 76	85.55 68	84.25 135	86.26 261	67.40 165	89.18 108	89.31 200	72.50 184	88.31 32	93.86 64	69.66 84	91.96 238	89.81 12	91.05 103	93.38 101

TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 48	91.41 53	92.35 83	74.62 134	88.90 27	93.85 65	75.75 20	96.00 55	87.80 38	94.63 50	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		85.89 60	85.39 71	87.38 40	93.59 45	72.63 33	92.74 21	93.18 40	76.78 76	80.73 151	93.82 66	64.33 148	96.29 42	82.67 93	90.69 110	93.23 108
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
fmvsm_s_conf0.5_n_a		83.63 100	83.41 100	84.28 130	86.14 266	68.12 139	89.43 97	82.87 341	70.27 241	87.27 54	93.80 67	69.09 91	91.58 253	88.21 36	83.65 235	93.14 118

fmvsm_s_conf0.5_n_4		85.39 72	85.75 65	84.30 128	86.70 254	65.83 197	88.77 129	89.78 176	75.46 107	88.35 31	93.73 68	69.19 90	93.06 194	91.30 3	88.44 152	94.02 63

fmvsm_s_conf0.5_n		83.80 93	83.71 95	84.07 145	86.69 255	67.31 168	89.46 96	83.07 336	71.09 213	86.96 58	93.70 69	69.02 96	91.47 263	88.79 28	84.62 214	93.44 100

test_prior2							88.85 125		75.41 108	84.91 76	93.54 70	74.28 30		83.31 79	95.86 20

fmvsm_l_conf0.5_n		84.47 85	84.54 84	84.27 132	85.42 284	68.81 112	88.49 143	87.26 268	68.08 290	88.03 39	93.49 71	72.04 53	91.77 246	88.90 27	89.14 139	92.24 159

VDDNet		81.52 146	80.67 146	84.05 150	90.44 104	64.13 242	89.73 87	85.91 293	71.11 212	83.18 112	93.48 72	50.54 313	93.49 166	73.40 189	88.25 154	94.54 40

CDPH-MVS		85.76 63	85.29 76	87.17 44	93.49 47	71.08 66	88.58 140	92.42 81	68.32 288	84.61 85	93.48 72	72.32 48	96.15 49	79.00 124	95.43 30	94.28 52

NCCC		88.06 15	88.01 19	88.24 11	94.41 22	73.62 11	91.22 57	92.83 61	81.50 5	85.79 66	93.47 74	73.02 42	97.00 18	84.90 58	94.94 40	94.10 58

fmvsm_s_conf0.5_n_6		85.55 67	86.20 51	83.60 167	87.32 232	65.13 216	88.86 123	91.63 118	75.41 108	88.23 35	93.45 75	68.56 101	92.47 218	89.52 17	92.78 75	93.20 113

fmvsm_l_conf0.5_n_a		84.13 88	84.16 89	84.06 147	85.38 285	68.40 129	88.34 150	86.85 278	67.48 297	87.48 50	93.40 76	70.89 69	91.61 251	88.38 35	89.22 137	92.16 166

3Dnovator+	77.84 4	85.48 68	84.47 87	88.51 7	91.08 89	73.49 16	93.18 12	93.78 19	80.79 8	76.66 233	93.37 77	60.40 216	96.75 26	77.20 145	93.73 66	95.29 6

DeepC-MVS_fast	79.65 3	86.91 38	86.62 45	87.76 27	93.52 46	72.37 43	91.26 54	93.04 42	76.62 82	84.22 94	93.36 78	71.44 62	96.76 25	80.82 107	95.33 33	94.16 55
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		83.01 118	82.36 119	84.96 101	91.02 91	66.40 184	88.91 121	88.11 242	77.57 49	84.39 90	93.29 79	52.19 287	93.91 146	77.05 148	88.70 147	94.57 37

test_fmvsmvis_n_1920		84.02 90	83.87 92	84.49 120	84.12 315	69.37 104	88.15 158	87.96 249	70.01 246	83.95 101	93.23 80	68.80 98	91.51 261	88.61 30	89.96 123	92.57 140

UA-Net		85.08 79	84.96 79	85.45 84	92.07 75	68.07 141	89.78 85	90.86 143	82.48 2	84.60 86	93.20 81	69.35 87	95.22 84	71.39 213	90.88 108	93.07 120

TEST9					93.26 52	72.96 25	88.75 131	91.89 106	68.44 286	85.00 74	93.10 82	74.36 29	95.41 76

train_agg		86.43 46	86.20 51	87.13 45	93.26 52	72.96 25	88.75 131	91.89 106	68.69 281	85.00 74	93.10 82	74.43 27	95.41 76	84.97 57	95.71 25	93.02 125

test_8					93.13 56	72.57 35	88.68 136	91.84 110	68.69 281	84.87 78	93.10 82	74.43 27	95.16 86

LFMVS		81.82 136	81.23 136	83.57 170	91.89 78	63.43 265	89.84 81	81.85 353	77.04 69	83.21 111	93.10 82	52.26 286	93.43 171	71.98 208	89.95 124	93.85 72

旧先验1					91.96 76	65.79 200		86.37 286			93.08 86	69.31 89			92.74 76	88.74 298

dcpmvs_2		85.63 65	86.15 55	84.06 147	91.71 80	64.94 223	86.47 217	91.87 108	73.63 159	86.60 61	93.02 87	76.57 15	91.87 244	83.36 78	92.15 84	95.35 3

testdata				79.97 277	90.90 94	64.21 240		84.71 307	59.27 389	85.40 69	92.91 88	62.02 181	89.08 317	68.95 241	91.37 99	86.63 350

MCST-MVS		87.37 31	87.25 32	87.73 28	94.53 17	72.46 40	89.82 82	93.82 17	73.07 177	84.86 79	92.89 89	76.22 17	96.33 41	84.89 60	95.13 36	94.40 45

Vis-MVSNet		83.46 105	82.80 112	85.43 85	90.25 108	68.74 117	90.30 75	90.13 167	76.33 91	80.87 148	92.89 89	61.00 203	94.20 130	72.45 205	90.97 105	93.35 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CPTT-MVS		83.73 95	83.33 103	84.92 105	93.28 49	70.86 74	92.09 37	90.38 155	68.75 280	79.57 166	92.83 91	60.60 212	93.04 197	80.92 106	91.56 96	90.86 207

3Dnovator	76.31 5	83.38 108	82.31 120	86.59 57	87.94 204	72.94 28	90.64 63	92.14 97	77.21 62	75.47 259	92.83 91	58.56 228	94.72 110	73.24 192	92.71 77	92.13 167

MSLP-MVS++		85.43 70	85.76 64	84.45 121	91.93 77	70.24 81	90.71 62	92.86 59	77.46 55	84.22 94	92.81 93	67.16 117	92.94 199	80.36 113	94.35 59	90.16 237

test2506		77.30 258	76.49 255	79.74 282	90.08 112	52.02 403	87.86 170	63.10 446	74.88 126	80.16 160	92.79 94	38.29 410	92.35 225	68.74 244	92.50 80	94.86 19

ECVR-MVS		79.61 192	79.26 185	80.67 262	90.08 112	54.69 386	87.89 168	77.44 399	74.88 126	80.27 157	92.79 94	48.96 336	92.45 219	68.55 245	92.50 80	94.86 19

test1111		79.43 199	79.18 188	80.15 274	89.99 117	53.31 399	87.33 186	77.05 403	75.04 119	80.23 159	92.77 96	48.97 335	92.33 227	68.87 242	92.40 82	94.81 22

MG-MVS		83.41 106	83.45 99	83.28 179	92.74 67	62.28 287	88.17 156	89.50 189	75.22 113	81.49 137	92.74 97	66.75 118	95.11 90	72.85 195	91.58 95	92.45 149

casdiffmvs_mvg		85.99 54	86.09 57	85.70 77	87.65 220	67.22 173	88.69 135	93.04 42	79.64 21	85.33 70	92.54 98	73.30 36	94.50 119	83.49 77	91.14 102	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
patch_mono-2		83.65 98	84.54 84	80.99 254	90.06 116	65.83 197	84.21 282	88.74 231	71.60 201	85.01 73	92.44 99	74.51 26	83.50 380	82.15 95	92.15 84	93.64 90

casdiffmvs		85.11 78	85.14 77	85.01 99	87.20 235	65.77 201	87.75 172	92.83 61	77.84 43	84.36 93	92.38 100	72.15 51	93.93 144	81.27 103	90.48 113	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
CS-MVS		86.69 41	86.95 39	85.90 74	90.76 99	67.57 159	92.83 18	93.30 33	79.67 19	84.57 87	92.27 101	71.47 61	95.02 96	84.24 71	93.46 69	95.13 9

baseline		84.93 81	84.98 78	84.80 111	87.30 233	65.39 210	87.30 187	92.88 58	77.62 47	84.04 99	92.26 102	71.81 55	93.96 138	81.31 101	90.30 116	95.03 11

NormalMVS		86.29 50	85.88 60	87.52 37	93.26 52	72.47 38	91.65 43	92.19 92	79.31 24	84.39 90	92.18 103	64.64 146	95.53 67	80.70 110	94.65 48	94.56 38

SymmetryMVS		85.38 73	84.81 81	87.07 46	91.47 83	72.47 38	91.65 43	88.06 246	79.31 24	84.39 90	92.18 103	64.64 146	95.53 67	80.70 110	90.91 107	93.21 111

QAPM		80.88 157	79.50 178	85.03 98	88.01 202	68.97 110	91.59 46	92.00 100	66.63 310	75.15 277	92.16 105	57.70 235	95.45 71	63.52 284	88.76 145	90.66 216

IS-MVSNet		83.15 113	82.81 111	84.18 137	89.94 119	63.30 267	91.59 46	88.46 239	79.04 30	79.49 167	92.16 105	65.10 141	94.28 125	67.71 251	91.86 91	94.95 12

BP-MVS1		84.32 86	83.71 95	86.17 64	87.84 209	67.85 150	89.38 102	89.64 184	77.73 45	83.98 100	92.12 107	56.89 246	95.43 73	84.03 74	91.75 92	95.24 7

新几何1				83.42 174	93.13 56	70.71 76		85.48 299	57.43 407	81.80 133	91.98 108	63.28 156	92.27 228	64.60 279	92.99 72	87.27 332

OpenMVS	72.83 10	79.77 190	78.33 206	84.09 143	85.17 290	69.91 89	90.57 64	90.97 138	66.70 304	72.17 322	91.91 109	54.70 263	93.96 138	61.81 305	90.95 106	88.41 307

PHI-MVS		86.43 46	86.17 54	87.24 42	90.88 95	70.96 70	92.27 33	94.07 10	72.45 185	85.22 72	91.90 110	69.47 86	96.42 40	83.28 80	95.94 19	94.35 48

VNet		82.21 127	82.41 117	81.62 234	90.82 96	60.93 303	84.47 273	89.78 176	76.36 90	84.07 98	91.88 111	64.71 145	90.26 293	70.68 220	88.89 141	93.66 84

EC-MVSNet		86.01 53	86.38 47	84.91 106	89.31 143	66.27 187	92.32 31	93.63 22	79.37 23	84.17 96	91.88 111	69.04 95	95.43 73	83.93 75	93.77 65	93.01 126

GDP-MVS		83.52 103	82.64 114	86.16 65	88.14 193	68.45 128	89.13 114	92.69 66	72.82 183	83.71 105	91.86 113	55.69 253	95.35 82	80.03 116	89.74 128	94.69 28

KinetiMVS		83.31 111	82.61 115	85.39 86	87.08 244	67.56 160	88.06 160	91.65 117	77.80 44	82.21 126	91.79 114	57.27 241	94.07 136	77.77 139	89.89 126	94.56 38

OPM-MVS		83.50 104	82.95 109	85.14 92	88.79 168	70.95 71	89.13 114	91.52 122	77.55 52	80.96 147	91.75 115	60.71 206	94.50 119	79.67 121	86.51 182	89.97 253
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MVSMamba_PlusPlus		85.99 54	85.96 59	86.05 69	91.09 88	67.64 156	89.63 91	92.65 71	72.89 182	84.64 84	91.71 116	71.85 54	96.03 51	84.77 63	94.45 56	94.49 41

viewmanbaseed2359cas		83.66 97	83.55 97	84.00 155	86.81 250	64.53 230	86.65 211	91.75 115	74.89 125	83.15 114	91.68 117	68.74 99	92.83 205	79.02 122	89.24 136	94.63 33

XVG-OURS-SEG-HR		80.81 160	79.76 171	83.96 158	85.60 279	68.78 114	83.54 299	90.50 151	70.66 228	76.71 232	91.66 118	60.69 207	91.26 270	76.94 149	81.58 264	91.83 172

EPNet		83.72 96	82.92 110	86.14 68	84.22 313	69.48 97	91.05 59	85.27 300	81.30 6	76.83 228	91.65 119	66.09 131	95.56 64	76.00 161	93.85 64	93.38 101
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		82.69 120	81.97 129	84.85 108	88.75 170	67.42 163	87.98 162	90.87 142	74.92 124	79.72 164	91.65 119	62.19 178	93.96 138	75.26 171	86.42 183	93.16 115

balanced_conf03		86.78 39	86.99 37	86.15 66	91.24 86	67.61 157	90.51 65	92.90 57	77.26 59	87.44 51	91.63 121	71.27 65	96.06 50	85.62 54	95.01 37	94.78 24

test222					91.50 82	68.26 133	84.16 283	83.20 334	54.63 418	79.74 163	91.63 121	58.97 224			91.42 97	86.77 346

MVS_111021_HR		85.14 77	84.75 82	86.32 61	91.65 81	72.70 30	85.98 231	90.33 159	76.11 94	82.08 128	91.61 123	71.36 64	94.17 133	81.02 104	92.58 78	92.08 168

原ACMM1				84.35 125	93.01 62	68.79 113		92.44 78	63.96 346	81.09 144	91.57 124	66.06 132	95.45 71	67.19 258	94.82 46	88.81 293

LPG-MVS_test		82.08 129	81.27 135	84.50 118	89.23 148	68.76 115	90.22 76	91.94 104	75.37 110	76.64 234	91.51 125	54.29 266	94.91 98	78.44 130	83.78 228	89.83 258

LGP-MVS_train				84.50 118	89.23 148	68.76 115		91.94 104	75.37 110	76.64 234	91.51 125	54.29 266	94.91 98	78.44 130	83.78 228	89.83 258

XVG-OURS		80.41 177	79.23 186	83.97 157	85.64 277	69.02 108	83.03 312	90.39 154	71.09 213	77.63 210	91.49 127	54.62 265	91.35 267	75.71 163	83.47 240	91.54 183

alignmvs		85.48 68	85.32 74	85.96 73	89.51 130	69.47 98	89.74 86	92.47 77	76.17 93	87.73 47	91.46 128	70.32 76	93.78 152	81.51 98	88.95 140	94.63 33

CANet		86.45 45	86.10 56	87.51 38	90.09 111	70.94 72	89.70 88	92.59 75	81.78 4	81.32 139	91.43 129	70.34 75	97.23 14	84.26 69	93.36 70	94.37 47

h-mvs33		83.15 113	82.19 122	86.02 72	90.56 101	70.85 75	88.15 158	89.16 210	76.02 96	84.67 81	91.39 130	61.54 189	95.50 69	82.71 90	75.48 344	91.72 179

MGCFI-Net		85.06 80	85.51 69	83.70 165	89.42 135	63.01 273	89.43 97	92.62 74	76.43 84	87.53 48	91.34 131	72.82 46	93.42 172	81.28 102	88.74 146	94.66 32

nrg030		83.88 91	83.53 98	84.96 101	86.77 252	69.28 105	90.46 70	92.67 68	74.79 129	82.95 115	91.33 132	72.70 47	93.09 192	80.79 109	79.28 294	92.50 145

sasdasda		85.91 58	85.87 62	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 40	91.23 133	73.28 37	93.91 146	81.50 99	88.80 143	94.77 25

canonicalmvs		85.91 58	85.87 62	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 40	91.23 133	73.28 37	93.91 146	81.50 99	88.80 143	94.77 25

DPM-MVS		84.93 81	84.29 88	86.84 52	90.20 109	73.04 23	87.12 191	93.04 42	69.80 252	82.85 118	91.22 135	73.06 41	96.02 53	76.72 155	94.63 50	91.46 189

Anonymous202405211		78.25 230	77.01 241	81.99 228	91.03 90	60.67 308	84.77 264	83.90 320	70.65 229	80.00 161	91.20 136	41.08 395	91.43 265	65.21 273	85.26 206	93.85 72

SPE-MVS-test		86.29 50	86.48 46	85.71 76	91.02 91	67.21 174	92.36 30	93.78 19	78.97 33	83.51 110	91.20 136	70.65 74	95.15 87	81.96 96	94.89 42	94.77 25

Anonymous20240529		80.19 185	78.89 194	84.10 139	90.60 100	64.75 228	88.95 120	90.90 140	65.97 318	80.59 153	91.17 138	49.97 320	93.73 158	69.16 239	82.70 253	93.81 76

EPP-MVSNet		83.40 107	83.02 107	84.57 116	90.13 110	64.47 235	92.32 31	90.73 145	74.45 138	79.35 172	91.10 139	69.05 94	95.12 88	72.78 196	87.22 169	94.13 57

TAPA-MVS	73.13 9	79.15 208	77.94 214	82.79 209	89.59 126	62.99 277	88.16 157	91.51 123	65.77 319	77.14 225	91.09 140	60.91 204	93.21 181	50.26 392	87.05 172	92.17 165
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CSCG		86.41 48	86.19 53	87.07 46	92.91 63	72.48 37	90.81 61	93.56 25	73.95 150	83.16 113	91.07 141	75.94 18	95.19 85	79.94 118	94.38 58	93.55 96

FIs		82.07 130	82.42 116	81.04 253	88.80 167	58.34 332	88.26 153	93.49 27	76.93 71	78.47 190	91.04 142	69.92 81	92.34 226	69.87 232	84.97 208	92.44 150

MVS_111021_LR		82.61 122	82.11 123	84.11 138	88.82 162	71.58 57	85.15 255	86.16 290	74.69 131	80.47 156	91.04 142	62.29 175	90.55 291	80.33 114	90.08 121	90.20 236

DP-MVS Recon		83.11 116	82.09 125	86.15 66	94.44 19	70.92 73	88.79 128	92.20 91	70.53 230	79.17 174	91.03 144	64.12 150	96.03 51	68.39 248	90.14 119	91.50 185

mamv4		76.81 266	78.23 210	72.54 383	86.12 267	65.75 202	78.76 368	82.07 350	64.12 340	72.97 310	91.02 145	67.97 107	68.08 448	83.04 83	78.02 306	83.80 394

HQP_MVS		83.64 99	83.14 104	85.14 92	90.08 112	68.71 119	91.25 55	92.44 78	79.12 28	78.92 178	91.00 146	60.42 214	95.38 78	78.71 128	86.32 184	91.33 190

plane_prior4											91.00 146

FC-MVSNet-test		81.52 146	82.02 127	80.03 276	88.42 183	55.97 371	87.95 164	93.42 30	77.10 67	77.38 214	90.98 148	69.96 80	91.79 245	68.46 247	84.50 215	92.33 153

diffmvs_AUTHOR		82.38 125	82.27 121	82.73 214	83.26 335	63.80 249	83.89 287	89.76 178	73.35 170	82.37 123	90.84 149	66.25 127	90.79 285	82.77 87	87.93 158	93.59 93

Vis-MVSNet (Re-imp)		78.36 229	78.45 201	78.07 318	88.64 174	51.78 409	86.70 209	79.63 381	74.14 147	75.11 278	90.83 150	61.29 197	89.75 303	58.10 340	91.60 93	92.69 137

114514_t		80.68 168	79.51 177	84.20 136	94.09 38	67.27 170	89.64 90	91.11 136	58.75 396	74.08 296	90.72 151	58.10 231	95.04 95	69.70 233	89.42 134	90.30 233

PAPM_NR		83.02 117	82.41 117	84.82 109	92.47 72	66.37 185	87.93 166	91.80 111	73.82 154	77.32 216	90.66 152	67.90 109	94.90 100	70.37 223	89.48 133	93.19 114

LS3D		76.95 264	74.82 282	83.37 177	90.45 103	67.36 167	89.15 113	86.94 275	61.87 369	69.52 352	90.61 153	51.71 300	94.53 117	46.38 414	86.71 179	88.21 311

AstraMVS		80.81 160	80.14 161	82.80 206	86.05 270	63.96 244	86.46 218	85.90 294	73.71 157	80.85 149	90.56 154	54.06 270	91.57 255	79.72 120	83.97 226	92.86 131

VPNet		78.69 221	78.66 197	78.76 301	88.31 186	55.72 375	84.45 276	86.63 281	76.79 75	78.26 194	90.55 155	59.30 222	89.70 305	66.63 262	77.05 317	90.88 206

UniMVSNet_ETH3D		79.10 210	78.24 208	81.70 233	86.85 248	60.24 315	87.28 188	88.79 226	74.25 144	76.84 227	90.53 156	49.48 326	91.56 256	67.98 249	82.15 257	93.29 106

ACMP	74.13 6	81.51 148	80.57 148	84.36 124	89.42 135	68.69 122	89.97 80	91.50 126	74.46 137	75.04 281	90.41 157	53.82 272	94.54 116	77.56 141	82.91 248	89.86 257
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
SSM_0407		81.58 143	80.48 151	84.87 107	88.81 163	67.96 145	87.37 183	89.25 205	71.06 215	79.48 168	90.39 158	59.57 219	94.48 121	72.45 205	85.93 194	92.18 162

SSM_0404		81.91 133	80.84 144	85.13 95	89.24 147	68.26 133	87.84 171	89.25 205	71.06 215	80.62 152	90.39 158	59.57 219	94.65 114	72.45 205	87.19 170	92.47 148

viewmambaseed2359dif		80.41 177	79.84 169	82.12 223	82.95 349	62.50 283	83.39 300	88.06 246	67.11 299	80.98 146	90.31 160	66.20 129	91.01 281	74.62 175	84.90 209	92.86 131

RRT-MVS		82.60 124	82.10 124	84.10 139	87.98 203	62.94 278	87.45 181	91.27 129	77.42 56	79.85 162	90.28 161	56.62 249	94.70 112	79.87 119	88.15 156	94.67 29

PCF-MVS	73.52 7	80.38 179	78.84 195	85.01 99	87.71 217	68.99 109	83.65 293	91.46 127	63.00 353	77.77 208	90.28 161	66.10 130	95.09 94	61.40 308	88.22 155	90.94 205
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
NP-MVS					89.62 125	68.32 131					90.24 163

HQP-MVS		82.61 122	82.02 127	84.37 123	89.33 140	66.98 177	89.17 109	92.19 92	76.41 85	77.23 219	90.23 164	60.17 217	95.11 90	77.47 142	85.99 192	91.03 200

PS-MVSNAJss		82.07 130	81.31 134	84.34 126	86.51 259	67.27 170	89.27 105	91.51 123	71.75 196	79.37 171	90.22 165	63.15 162	94.27 126	77.69 140	82.36 256	91.49 186

TSAR-MVS + GP.		85.71 64	85.33 73	86.84 52	91.34 84	72.50 36	89.07 117	87.28 266	76.41 85	85.80 65	90.22 165	74.15 32	95.37 81	81.82 97	91.88 88	92.65 139

SDMVSNet		80.38 179	80.18 158	80.99 254	89.03 157	64.94 223	80.45 344	89.40 192	75.19 116	76.61 236	89.98 167	60.61 211	87.69 339	76.83 153	83.55 237	90.33 231

sd_testset		77.70 249	77.40 234	78.60 304	89.03 157	60.02 317	79.00 364	85.83 295	75.19 116	76.61 236	89.98 167	54.81 258	85.46 364	62.63 295	83.55 237	90.33 231

TranMVSNet+NR-MVSNet		80.84 158	80.31 155	82.42 220	87.85 208	62.33 285	87.74 173	91.33 128	80.55 9	77.99 202	89.86 169	65.23 140	92.62 208	67.05 260	75.24 354	92.30 155

diffmvs		82.10 128	81.88 130	82.76 212	83.00 345	63.78 251	83.68 292	89.76 178	72.94 180	82.02 129	89.85 170	65.96 135	90.79 285	82.38 94	87.30 168	93.71 82
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Elysia		81.53 144	80.16 159	85.62 79	85.51 281	68.25 135	88.84 126	92.19 92	71.31 206	80.50 154	89.83 171	46.89 347	94.82 104	76.85 150	89.57 130	93.80 78

StellarMVS		81.53 144	80.16 159	85.62 79	85.51 281	68.25 135	88.84 126	92.19 92	71.31 206	80.50 154	89.83 171	46.89 347	94.82 104	76.85 150	89.57 130	93.80 78

mamba_0408		79.37 204	77.52 231	84.93 104	88.81 163	67.96 145	65.03 443	88.66 233	70.96 219	79.48 168	89.80 173	58.69 225	94.65 114	70.35 224	85.93 194	92.18 162

SSM_04072		77.67 251	77.52 231	78.12 316	88.81 163	67.96 145	65.03 443	88.66 233	70.96 219	79.48 168	89.80 173	58.69 225	74.23 436	70.35 224	85.93 194	92.18 162

BH-RMVSNet		79.61 192	78.44 202	83.14 187	89.38 139	65.93 194	84.95 261	87.15 271	73.56 162	78.19 196	89.79 175	56.67 248	93.36 173	59.53 324	86.74 178	90.13 239

GeoE		81.71 138	81.01 141	83.80 164	89.51 130	64.45 236	88.97 119	88.73 232	71.27 209	78.63 184	89.76 176	66.32 126	93.20 184	69.89 231	86.02 191	93.74 81

guyue		81.13 153	80.64 147	82.60 217	86.52 258	63.92 247	86.69 210	87.73 257	73.97 149	80.83 150	89.69 177	56.70 247	91.33 269	78.26 137	85.40 205	92.54 142

AdaColmap		80.58 175	79.42 179	84.06 147	93.09 59	68.91 111	89.36 103	88.97 221	69.27 264	75.70 255	89.69 177	57.20 243	95.77 60	63.06 289	88.41 153	87.50 326

ACMM	73.20 8	80.78 167	79.84 169	83.58 169	89.31 143	68.37 130	89.99 79	91.60 120	70.28 240	77.25 217	89.66 179	53.37 277	93.53 165	74.24 181	82.85 249	88.85 291
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		78.08 236	76.79 248	81.97 229	90.40 105	71.07 67	87.59 176	84.55 310	66.03 317	72.38 319	89.64 180	57.56 237	86.04 356	59.61 323	83.35 242	88.79 294

test_yl		81.17 151	80.47 152	83.24 182	89.13 152	63.62 252	86.21 226	89.95 172	72.43 188	81.78 134	89.61 181	57.50 238	93.58 160	70.75 218	86.90 174	92.52 143

DCV-MVSNet		81.17 151	80.47 152	83.24 182	89.13 152	63.62 252	86.21 226	89.95 172	72.43 188	81.78 134	89.61 181	57.50 238	93.58 160	70.75 218	86.90 174	92.52 143

EI-MVSNet-Vis-set		84.19 87	83.81 93	85.31 88	88.18 190	67.85 150	87.66 174	89.73 181	80.05 15	82.95 115	89.59 183	70.74 72	94.82 104	80.66 112	84.72 212	93.28 107

PAPR		81.66 141	80.89 143	83.99 156	90.27 107	64.00 243	86.76 208	91.77 114	68.84 279	77.13 226	89.50 184	67.63 111	94.88 102	67.55 253	88.52 150	93.09 119

jajsoiax		79.29 205	77.96 213	83.27 180	84.68 304	66.57 183	89.25 106	90.16 166	69.20 269	75.46 261	89.49 185	45.75 363	93.13 190	76.84 152	80.80 274	90.11 241

MVSFormer		82.85 119	82.05 126	85.24 90	87.35 226	70.21 82	90.50 67	90.38 155	68.55 283	81.32 139	89.47 186	61.68 186	93.46 169	78.98 125	90.26 117	92.05 169

jason		81.39 149	80.29 156	84.70 114	86.63 257	69.90 90	85.95 232	86.77 279	63.24 349	81.07 145	89.47 186	61.08 202	92.15 232	78.33 133	90.07 122	92.05 169
jason: jason.
mvs_tets		79.13 209	77.77 223	83.22 184	84.70 303	66.37 185	89.17 109	90.19 165	69.38 261	75.40 264	89.46 188	44.17 375	93.15 188	76.78 154	80.70 276	90.14 238

UGNet		80.83 159	79.59 176	84.54 117	88.04 199	68.09 140	89.42 99	88.16 241	76.95 70	76.22 245	89.46 188	49.30 330	93.94 141	68.48 246	90.31 115	91.60 180
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
VPA-MVSNet		80.60 172	80.55 149	80.76 260	88.07 198	60.80 306	86.86 202	91.58 121	75.67 103	80.24 158	89.45 190	63.34 155	90.25 294	70.51 222	79.22 295	91.23 193

MVS_Test		83.15 113	83.06 106	83.41 176	86.86 247	63.21 269	86.11 229	92.00 100	74.31 141	82.87 117	89.44 191	70.03 79	93.21 181	77.39 144	88.50 151	93.81 76

EI-MVSNet-UG-set		83.81 92	83.38 101	85.09 97	87.87 207	67.53 161	87.44 182	89.66 182	79.74 18	82.23 125	89.41 192	70.24 78	94.74 109	79.95 117	83.92 227	92.99 128

RPSCF		73.23 320	71.46 324	78.54 307	82.50 358	59.85 318	82.18 318	82.84 343	58.96 392	71.15 334	89.41 192	45.48 367	84.77 371	58.82 332	71.83 384	91.02 202

UniMVSNet_NR-MVSNet		81.88 134	81.54 133	82.92 199	88.46 180	63.46 263	87.13 190	92.37 82	80.19 12	78.38 191	89.14 194	71.66 60	93.05 195	70.05 228	76.46 327	92.25 157

tttt0517		79.40 201	77.91 215	83.90 160	88.10 196	63.84 248	88.37 149	84.05 318	71.45 204	76.78 230	89.12 195	49.93 323	94.89 101	70.18 227	83.18 246	92.96 129

DU-MVS		81.12 154	80.52 150	82.90 200	87.80 211	63.46 263	87.02 195	91.87 108	79.01 31	78.38 191	89.07 196	65.02 142	93.05 195	70.05 228	76.46 327	92.20 160

NR-MVSNet		80.23 183	79.38 180	82.78 210	87.80 211	63.34 266	86.31 223	91.09 137	79.01 31	72.17 322	89.07 196	67.20 116	92.81 206	66.08 267	75.65 340	92.20 160

icg_test_0407_2		78.92 216	78.93 193	78.90 299	87.13 238	63.59 256	76.58 390	89.33 195	70.51 231	77.82 204	89.03 198	61.84 182	81.38 395	72.56 201	85.56 201	91.74 175

IMVS_0407		80.61 170	79.90 167	82.75 213	87.13 238	63.59 256	85.33 251	89.33 195	70.51 231	77.82 204	89.03 198	61.84 182	92.91 200	72.56 201	85.56 201	91.74 175

IMVS_0404		77.16 260	76.42 258	79.37 290	87.13 238	63.59 256	77.12 388	89.33 195	70.51 231	66.22 391	89.03 198	50.36 315	82.78 385	72.56 201	85.56 201	91.74 175

IMVS_0403		80.80 163	80.12 162	82.87 202	87.13 238	63.59 256	85.19 252	89.33 195	70.51 231	78.49 188	89.03 198	63.26 158	93.27 176	72.56 201	85.56 201	91.74 175

DELS-MVS		85.41 71	85.30 75	85.77 75	88.49 178	67.93 148	85.52 249	93.44 28	78.70 34	83.63 109	89.03 198	74.57 24	95.71 62	80.26 115	94.04 63	93.66 84
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
mvsmamba		80.60 172	79.38 180	84.27 132	89.74 124	67.24 172	87.47 179	86.95 274	70.02 245	75.38 265	88.93 203	51.24 304	92.56 213	75.47 169	89.22 137	93.00 127

baseline1		76.98 263	76.75 251	77.66 325	88.13 194	55.66 376	85.12 256	81.89 351	73.04 178	76.79 229	88.90 204	62.43 173	87.78 338	63.30 288	71.18 388	89.55 267

DP-MVS		76.78 267	74.57 285	83.42 174	93.29 48	69.46 100	88.55 142	83.70 322	63.98 345	70.20 340	88.89 205	54.01 271	94.80 107	46.66 411	81.88 262	86.01 360

ab-mvs		79.51 195	78.97 192	81.14 250	88.46 180	60.91 304	83.84 288	89.24 207	70.36 236	79.03 175	88.87 206	63.23 160	90.21 295	65.12 274	82.57 254	92.28 156

PEN-MVS		77.73 246	77.69 227	77.84 322	87.07 246	53.91 393	87.91 167	91.18 132	77.56 51	73.14 308	88.82 207	61.23 198	89.17 315	59.95 319	72.37 378	90.43 226

tt0805		78.73 219	77.83 219	81.43 239	85.17 290	60.30 314	89.41 100	90.90 140	71.21 210	77.17 224	88.73 208	46.38 352	93.21 181	72.57 199	78.96 296	90.79 209

test_djsdf		80.30 182	79.32 183	83.27 180	83.98 319	65.37 211	90.50 67	90.38 155	68.55 283	76.19 246	88.70 209	56.44 250	93.46 169	78.98 125	80.14 284	90.97 203

PAPM		77.68 250	76.40 259	81.51 237	87.29 234	61.85 292	83.78 289	89.59 186	64.74 332	71.23 332	88.70 209	62.59 169	93.66 159	52.66 376	87.03 173	89.01 283

DTE-MVSNet		76.99 262	76.80 247	77.54 330	86.24 262	53.06 402	87.52 177	90.66 146	77.08 68	72.50 316	88.67 211	60.48 213	89.52 307	57.33 347	70.74 390	90.05 248

PS-CasMVS		78.01 240	78.09 211	77.77 324	87.71 217	54.39 390	88.02 161	91.22 130	77.50 54	73.26 306	88.64 212	60.73 205	88.41 330	61.88 303	73.88 367	90.53 222

cdsmvs_eth3d_5k		19.96 428	26.61 430	0.00 448	0.00 471	0.00 473	0.00 459	89.26 204	0.00 466	0.00 467	88.61 213	61.62 188	0.00 467	0.00 466	0.00 465	0.00 463

lupinMVS		81.39 149	80.27 157	84.76 112	87.35 226	70.21 82	85.55 245	86.41 284	62.85 356	81.32 139	88.61 213	61.68 186	92.24 230	78.41 132	90.26 117	91.83 172

F-COLMAP		76.38 277	74.33 291	82.50 219	89.28 145	66.95 180	88.41 145	89.03 216	64.05 343	66.83 380	88.61 213	46.78 349	92.89 201	57.48 344	78.55 298	87.67 320

mvs_anonymous		79.42 200	79.11 189	80.34 269	84.45 310	57.97 338	82.59 314	87.62 259	67.40 298	76.17 249	88.56 216	68.47 102	89.59 306	70.65 221	86.05 190	93.47 99

CP-MVSNet		78.22 231	78.34 205	77.84 322	87.83 210	54.54 388	87.94 165	91.17 133	77.65 46	73.48 304	88.49 217	62.24 177	88.43 329	62.19 299	74.07 363	90.55 221

PVSNet_Blended_VisFu		82.62 121	81.83 131	84.96 101	90.80 97	69.76 93	88.74 133	91.70 116	69.39 260	78.96 176	88.46 218	65.47 138	94.87 103	74.42 178	88.57 148	90.24 235

CANet_DTU		80.61 170	79.87 168	82.83 203	85.60 279	63.17 272	87.36 184	88.65 235	76.37 89	75.88 252	88.44 219	53.51 275	93.07 193	73.30 190	89.74 128	92.25 157

PLC	70.83 11	78.05 238	76.37 260	83.08 191	91.88 79	67.80 152	88.19 155	89.46 190	64.33 338	69.87 349	88.38 220	53.66 273	93.58 160	58.86 331	82.73 251	87.86 317
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
WR-MVS		79.49 196	79.22 187	80.27 271	88.79 168	58.35 331	85.06 258	88.61 237	78.56 35	77.65 209	88.34 221	63.81 154	90.66 290	64.98 276	77.22 315	91.80 174

XXY-MVS		75.41 291	75.56 269	74.96 356	83.59 328	57.82 342	80.59 341	83.87 321	66.54 311	74.93 284	88.31 222	63.24 159	80.09 401	62.16 300	76.85 321	86.97 342

Effi-MVS+		83.62 101	83.08 105	85.24 90	88.38 184	67.45 162	88.89 122	89.15 211	75.50 106	82.27 124	88.28 223	69.61 85	94.45 122	77.81 138	87.84 159	93.84 74

API-MVS		81.99 132	81.23 136	84.26 134	90.94 93	70.18 87	91.10 58	89.32 199	71.51 203	78.66 183	88.28 223	65.26 139	95.10 93	64.74 278	91.23 101	87.51 325

thisisatest0530		79.40 201	77.76 224	84.31 127	87.69 219	65.10 219	87.36 184	84.26 316	70.04 244	77.42 213	88.26 225	49.94 321	94.79 108	70.20 226	84.70 213	93.03 124

hse-mvs2		81.72 137	80.94 142	84.07 145	88.72 171	67.68 155	85.87 235	87.26 268	76.02 96	84.67 81	88.22 226	61.54 189	93.48 167	82.71 90	73.44 372	91.06 198

xiu_mvs_v1_base_debu		80.80 163	79.72 172	84.03 152	87.35 226	70.19 84	85.56 242	88.77 227	69.06 273	81.83 130	88.16 227	50.91 307	92.85 202	78.29 134	87.56 162	89.06 278

xiu_mvs_v1_base		80.80 163	79.72 172	84.03 152	87.35 226	70.19 84	85.56 242	88.77 227	69.06 273	81.83 130	88.16 227	50.91 307	92.85 202	78.29 134	87.56 162	89.06 278

xiu_mvs_v1_base_debi		80.80 163	79.72 172	84.03 152	87.35 226	70.19 84	85.56 242	88.77 227	69.06 273	81.83 130	88.16 227	50.91 307	92.85 202	78.29 134	87.56 162	89.06 278

UniMVSNet (Re)		81.60 142	81.11 138	83.09 189	88.38 184	64.41 237	87.60 175	93.02 46	78.42 37	78.56 186	88.16 227	69.78 82	93.26 177	69.58 235	76.49 326	91.60 180

AUN-MVS		79.21 207	77.60 229	84.05 150	88.71 172	67.61 157	85.84 237	87.26 268	69.08 272	77.23 219	88.14 231	53.20 279	93.47 168	75.50 168	73.45 371	91.06 198

Anonymous20231211		78.97 214	77.69 227	82.81 205	90.54 102	64.29 239	90.11 78	91.51 123	65.01 330	76.16 250	88.13 232	50.56 312	93.03 198	69.68 234	77.56 313	91.11 196

pm-mvs1		77.25 259	76.68 253	78.93 298	84.22 313	58.62 329	86.41 219	88.36 240	71.37 205	73.31 305	88.01 233	61.22 199	89.15 316	64.24 282	73.01 375	89.03 282

LuminaMVS		80.68 168	79.62 175	83.83 161	85.07 296	68.01 144	86.99 196	88.83 224	70.36 236	81.38 138	87.99 234	50.11 318	92.51 217	79.02 122	86.89 176	90.97 203

SD_0403		74.65 299	74.77 283	74.29 365	86.20 264	47.42 428	83.71 291	85.12 302	69.30 263	68.50 363	87.95 235	59.40 221	86.05 355	49.38 396	83.35 242	89.40 270

LTVRE_ROB	69.57 13	76.25 278	74.54 287	81.41 240	88.60 175	64.38 238	79.24 359	89.12 214	70.76 224	69.79 351	87.86 236	49.09 333	93.20 184	56.21 359	80.16 282	86.65 349
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
testing3-2		75.12 296	75.19 278	74.91 357	90.40 105	45.09 439	80.29 347	78.42 391	78.37 40	76.54 238	87.75 237	44.36 373	87.28 344	57.04 350	83.49 239	92.37 151

WTY-MVS		75.65 286	75.68 266	75.57 347	86.40 260	56.82 356	77.92 382	82.40 346	65.10 327	76.18 247	87.72 238	63.13 165	80.90 398	60.31 317	81.96 260	89.00 285

TAMVS		78.89 217	77.51 233	83.03 194	87.80 211	67.79 153	84.72 265	85.05 305	67.63 293	76.75 231	87.70 239	62.25 176	90.82 284	58.53 335	87.13 171	90.49 224

BH-untuned		79.47 197	78.60 198	82.05 226	89.19 150	65.91 195	86.07 230	88.52 238	72.18 190	75.42 263	87.69 240	61.15 200	93.54 164	60.38 316	86.83 177	86.70 348

COLMAP_ROB	66.92 17	73.01 323	70.41 338	80.81 259	87.13 238	65.63 203	88.30 152	84.19 317	62.96 354	63.80 408	87.69 240	38.04 411	92.56 213	46.66 411	74.91 357	84.24 387
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		74.26 302	72.42 315	79.80 281	83.76 325	59.59 322	85.92 234	86.64 280	66.39 312	66.96 378	87.58 242	39.46 401	91.60 252	65.76 270	69.27 396	88.22 310

FA-MVS(test-final)		80.96 156	79.91 166	84.10 139	88.30 187	65.01 220	84.55 272	90.01 170	73.25 174	79.61 165	87.57 243	58.35 230	94.72 110	71.29 214	86.25 186	92.56 141

Baseline_NR-MVSNet		78.15 235	78.33 206	77.61 327	85.79 273	56.21 369	86.78 206	85.76 296	73.60 161	77.93 203	87.57 243	65.02 142	88.99 318	67.14 259	75.33 351	87.63 321

WR-MVS_H		78.51 226	78.49 200	78.56 306	88.02 200	56.38 365	88.43 144	92.67 68	77.14 64	73.89 298	87.55 245	66.25 127	89.24 313	58.92 330	73.55 370	90.06 247

EI-MVSNet		80.52 176	79.98 164	82.12 223	84.28 311	63.19 271	86.41 219	88.95 222	74.18 146	78.69 181	87.54 246	66.62 120	92.43 220	72.57 199	80.57 278	90.74 213

CVMVSNet		72.99 324	72.58 313	74.25 366	84.28 311	50.85 417	86.41 219	83.45 328	44.56 437	73.23 307	87.54 246	49.38 328	85.70 359	65.90 268	78.44 301	86.19 355

ACMH+	68.96 14	76.01 282	74.01 293	82.03 227	88.60 175	65.31 212	88.86 123	87.55 260	70.25 242	67.75 367	87.47 248	41.27 393	93.19 186	58.37 337	75.94 337	87.60 322

TransMVSNet (Re)		75.39 293	74.56 286	77.86 321	85.50 283	57.10 353	86.78 206	86.09 292	72.17 191	71.53 329	87.34 249	63.01 166	89.31 311	56.84 353	61.83 419	87.17 334

GBi-Net		78.40 227	77.40 234	81.40 241	87.60 221	63.01 273	88.39 146	89.28 201	71.63 198	75.34 267	87.28 250	54.80 259	91.11 274	62.72 291	79.57 288	90.09 243

test1		78.40 227	77.40 234	81.40 241	87.60 221	63.01 273	88.39 146	89.28 201	71.63 198	75.34 267	87.28 250	54.80 259	91.11 274	62.72 291	79.57 288	90.09 243

FMVSNet2		78.20 233	77.21 238	81.20 248	87.60 221	62.89 279	87.47 179	89.02 217	71.63 198	75.29 273	87.28 250	54.80 259	91.10 277	62.38 296	79.38 292	89.61 265

FMVSNet1		77.44 254	76.12 262	81.40 241	86.81 250	63.01 273	88.39 146	89.28 201	70.49 235	74.39 293	87.28 250	49.06 334	91.11 274	60.91 312	78.52 299	90.09 243

v2v482		80.23 183	79.29 184	83.05 193	83.62 327	64.14 241	87.04 193	89.97 171	73.61 160	78.18 197	87.22 254	61.10 201	93.82 150	76.11 158	76.78 323	91.18 194

ITE_SJBPF				78.22 313	81.77 368	60.57 309		83.30 329	69.25 266	67.54 369	87.20 255	36.33 418	87.28 344	54.34 367	74.62 360	86.80 345

anonymousdsp		78.60 223	77.15 239	82.98 197	80.51 387	67.08 175	87.24 189	89.53 188	65.66 321	75.16 276	87.19 256	52.52 281	92.25 229	77.17 146	79.34 293	89.61 265

MVSTER		79.01 212	77.88 218	82.38 221	83.07 342	64.80 227	84.08 286	88.95 222	69.01 276	78.69 181	87.17 257	54.70 263	92.43 220	74.69 174	80.57 278	89.89 256

thres100view900		76.50 271	75.55 270	79.33 291	89.52 129	56.99 354	85.83 238	83.23 331	73.94 151	76.32 243	87.12 258	51.89 296	91.95 239	48.33 402	83.75 231	89.07 276

thres600view7		76.50 271	75.44 271	79.68 284	89.40 137	57.16 351	85.53 247	83.23 331	73.79 155	76.26 244	87.09 259	51.89 296	91.89 242	48.05 407	83.72 234	90.00 249

XVG-ACMP-BASELINE		76.11 280	74.27 292	81.62 234	83.20 338	64.67 229	83.60 296	89.75 180	69.75 255	71.85 325	87.09 259	32.78 425	92.11 233	69.99 230	80.43 280	88.09 313

HY-MVS	69.67 12	77.95 241	77.15 239	80.36 268	87.57 225	60.21 316	83.37 302	87.78 256	66.11 314	75.37 266	87.06 261	63.27 157	90.48 292	61.38 309	82.43 255	90.40 228

CHOSEN 1792x2688		77.63 252	75.69 265	83.44 173	89.98 118	68.58 125	78.70 369	87.50 262	56.38 412	75.80 254	86.84 262	58.67 227	91.40 266	61.58 307	85.75 199	90.34 230

v8		79.97 189	79.02 191	82.80 206	84.09 316	64.50 234	87.96 163	90.29 162	74.13 148	75.24 274	86.81 263	62.88 167	93.89 149	74.39 179	75.40 349	90.00 249

AllTest		70.96 341	68.09 356	79.58 287	85.15 292	63.62 252	84.58 271	79.83 378	62.31 363	60.32 420	86.73 264	32.02 426	88.96 321	50.28 390	71.57 386	86.15 356

TestCases				79.58 287	85.15 292	63.62 252		79.83 378	62.31 363	60.32 420	86.73 264	32.02 426	88.96 321	50.28 390	71.57 386	86.15 356

LCM-MVSNet-Re		77.05 261	76.94 244	77.36 331	87.20 235	51.60 410	80.06 349	80.46 369	75.20 115	67.69 368	86.72 266	62.48 171	88.98 319	63.44 286	89.25 135	91.51 184

1112_ss		77.40 256	76.43 257	80.32 270	89.11 156	60.41 313	83.65 293	87.72 258	62.13 366	73.05 309	86.72 266	62.58 170	89.97 299	62.11 302	80.80 274	90.59 220

ab-mvs-re		7.23 431	9.64 434	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	86.72 266	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

IterMVS-LS		80.06 186	79.38 180	82.11 225	85.89 271	63.20 270	86.79 205	89.34 194	74.19 145	75.45 262	86.72 266	66.62 120	92.39 222	72.58 198	76.86 320	90.75 212
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	67.68 16	75.89 283	73.93 295	81.77 232	88.71 172	66.61 182	88.62 138	89.01 218	69.81 251	66.78 381	86.70 270	41.95 391	91.51 261	55.64 360	78.14 305	87.17 334
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Test_1112_low_res		76.40 276	75.44 271	79.27 292	89.28 145	58.09 334	81.69 323	87.07 272	59.53 387	72.48 317	86.67 271	61.30 196	89.33 310	60.81 314	80.15 283	90.41 227

FMVSNet3		77.88 243	76.85 246	80.97 256	86.84 249	62.36 284	86.52 216	88.77 227	71.13 211	75.34 267	86.66 272	54.07 269	91.10 277	62.72 291	79.57 288	89.45 269

pmmvs6		74.69 298	73.39 302	78.61 303	81.38 376	57.48 348	86.64 212	87.95 250	64.99 331	70.18 341	86.61 273	50.43 314	89.52 307	62.12 301	70.18 393	88.83 292

ET-MVSNet_ETH3D		78.63 222	76.63 254	84.64 115	86.73 253	69.47 98	85.01 259	84.61 309	69.54 258	66.51 388	86.59 274	50.16 317	91.75 247	76.26 157	84.24 223	92.69 137

testgi		66.67 380	66.53 377	67.08 414	75.62 420	41.69 449	75.93 393	76.50 406	66.11 314	65.20 399	86.59 274	35.72 420	74.71 433	43.71 423	73.38 373	84.84 381

CLD-MVS		82.31 126	81.65 132	84.29 129	88.47 179	67.73 154	85.81 239	92.35 83	75.78 99	78.33 193	86.58 276	64.01 151	94.35 123	76.05 160	87.48 165	90.79 209
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v10		79.74 191	78.67 196	82.97 198	84.06 317	64.95 222	87.88 169	90.62 147	73.11 176	75.11 278	86.56 277	61.46 192	94.05 137	73.68 184	75.55 342	89.90 255

CDS-MVSNet		79.07 211	77.70 226	83.17 186	87.60 221	68.23 137	84.40 279	86.20 289	67.49 296	76.36 242	86.54 278	61.54 189	90.79 285	61.86 304	87.33 167	90.49 224
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
xiu_mvs_v2_base		81.69 139	81.05 139	83.60 167	89.15 151	68.03 143	84.46 275	90.02 169	70.67 225	81.30 142	86.53 279	63.17 161	94.19 132	75.60 166	88.54 149	88.57 303

TR-MVS		77.44 254	76.18 261	81.20 248	88.24 188	63.24 268	84.61 270	86.40 285	67.55 295	77.81 206	86.48 280	54.10 268	93.15 188	57.75 343	82.72 252	87.20 333

EIA-MVS		83.31 111	82.80 112	84.82 109	89.59 126	65.59 205	88.21 154	92.68 67	74.66 133	78.96 176	86.42 281	69.06 93	95.26 83	75.54 167	90.09 120	93.62 91

tfpn200view9		76.42 275	75.37 275	79.55 289	89.13 152	57.65 345	85.17 253	83.60 323	73.41 168	76.45 239	86.39 282	52.12 288	91.95 239	48.33 402	83.75 231	89.07 276

thres400		76.50 271	75.37 275	79.86 279	89.13 152	57.65 345	85.17 253	83.60 323	73.41 168	76.45 239	86.39 282	52.12 288	91.95 239	48.33 402	83.75 231	90.00 249

v7n		78.97 214	77.58 230	83.14 187	83.45 331	65.51 206	88.32 151	91.21 131	73.69 158	72.41 318	86.32 284	57.93 232	93.81 151	69.18 238	75.65 340	90.11 241

MAR-MVS		81.84 135	80.70 145	85.27 89	91.32 85	71.53 58	89.82 82	90.92 139	69.77 254	78.50 187	86.21 285	62.36 174	94.52 118	65.36 272	92.05 87	89.77 261
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
v1144		80.03 187	79.03 190	83.01 195	83.78 324	64.51 232	87.11 192	90.57 150	71.96 195	78.08 200	86.20 286	61.41 193	93.94 141	74.93 173	77.23 314	90.60 219

test_vis1_n_1920		75.52 288	75.78 264	74.75 361	79.84 395	57.44 349	83.26 304	85.52 298	62.83 357	79.34 173	86.17 287	45.10 368	79.71 402	78.75 127	81.21 268	87.10 340

V42		79.38 203	78.24 208	82.83 203	81.10 381	65.50 207	85.55 245	89.82 175	71.57 202	78.21 195	86.12 288	60.66 209	93.18 187	75.64 164	75.46 346	89.81 260

PVSNet_BlendedMVS		80.60 172	80.02 163	82.36 222	88.85 159	65.40 208	86.16 228	92.00 100	69.34 262	78.11 198	86.09 289	66.02 133	94.27 126	71.52 210	82.06 259	87.39 327

v1192		79.59 194	78.43 203	83.07 192	83.55 329	64.52 231	86.93 200	90.58 148	70.83 221	77.78 207	85.90 290	59.15 223	93.94 141	73.96 183	77.19 316	90.76 211

SixPastTwentyTwo		73.37 315	71.26 329	79.70 283	85.08 295	57.89 340	85.57 241	83.56 325	71.03 217	65.66 393	85.88 291	42.10 389	92.57 212	59.11 328	63.34 415	88.65 300

EPNet_dtu		75.46 289	74.86 281	77.23 334	82.57 357	54.60 387	86.89 201	83.09 335	71.64 197	66.25 390	85.86 292	55.99 251	88.04 334	54.92 364	86.55 181	89.05 281
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		73.60 312	73.64 300	73.51 373	82.80 351	55.01 384	76.12 392	81.69 354	62.47 362	74.68 288	85.85 293	57.32 240	78.11 409	60.86 313	80.93 270	87.39 327

ETV-MVS		84.90 83	84.67 83	85.59 81	89.39 138	68.66 123	88.74 133	92.64 73	79.97 16	84.10 97	85.71 294	69.32 88	95.38 78	80.82 107	91.37 99	92.72 134

test_cas_vis1_n_1920		73.76 310	73.74 299	73.81 371	75.90 417	59.77 319	80.51 342	82.40 346	58.30 398	81.62 136	85.69 295	44.35 374	76.41 420	76.29 156	78.61 297	85.23 373

v1240		78.99 213	77.78 222	82.64 215	83.21 337	63.54 260	86.62 213	90.30 161	69.74 257	77.33 215	85.68 296	57.04 244	93.76 155	73.13 193	76.92 318	90.62 217

v144192		79.47 197	78.37 204	82.78 210	83.35 332	63.96 244	86.96 197	90.36 158	69.99 247	77.50 211	85.67 297	60.66 209	93.77 154	74.27 180	76.58 324	90.62 217

tfpnnormal		74.39 300	73.16 306	78.08 317	86.10 269	58.05 335	84.65 269	87.53 261	70.32 239	71.22 333	85.63 298	54.97 257	89.86 300	43.03 425	75.02 356	86.32 352

PS-MVSNAJ		81.69 139	81.02 140	83.70 165	89.51 130	68.21 138	84.28 281	90.09 168	70.79 222	81.26 143	85.62 299	63.15 162	94.29 124	75.62 165	88.87 142	88.59 302

SSC-MVS3.2		73.35 318	73.39 302	73.23 374	85.30 288	49.01 424	74.58 407	81.57 355	75.21 114	73.68 301	85.58 300	52.53 280	82.05 390	54.33 368	77.69 311	88.63 301

v1921920		79.22 206	78.03 212	82.80 206	83.30 334	63.94 246	86.80 204	90.33 159	69.91 250	77.48 212	85.53 301	58.44 229	93.75 156	73.60 185	76.85 321	90.71 215

test_0402		72.79 326	70.44 337	79.84 280	88.13 194	65.99 193	85.93 233	84.29 314	65.57 322	67.40 374	85.49 302	46.92 346	92.61 209	35.88 439	74.38 362	80.94 418

v148		78.72 220	77.80 221	81.47 238	82.73 353	61.96 291	86.30 224	88.08 244	73.26 173	76.18 247	85.47 303	62.46 172	92.36 224	71.92 209	73.82 368	90.09 243

USDC		70.33 350	68.37 351	76.21 341	80.60 385	56.23 368	79.19 361	86.49 283	60.89 374	61.29 416	85.47 303	31.78 428	89.47 309	53.37 373	76.21 335	82.94 405

VortexMVS		78.57 225	77.89 217	80.59 263	85.89 271	62.76 280	85.61 240	89.62 185	72.06 193	74.99 282	85.38 305	55.94 252	90.77 288	74.99 172	76.58 324	88.23 309

MVP-Stereo		76.12 279	74.46 289	81.13 251	85.37 286	69.79 91	84.42 278	87.95 250	65.03 329	67.46 371	85.33 306	53.28 278	91.73 249	58.01 341	83.27 244	81.85 413
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVS		78.19 234	76.99 243	81.78 231	85.66 276	66.99 176	84.66 267	90.47 152	55.08 417	72.02 324	85.27 307	63.83 153	94.11 135	66.10 266	89.80 127	84.24 387

DIV-MVS_self_test		77.72 247	76.76 249	80.58 264	82.48 360	60.48 311	83.09 308	87.86 253	69.22 267	74.38 294	85.24 308	62.10 179	91.53 259	71.09 215	75.40 349	89.74 262

FE-MVS		77.78 245	75.68 266	84.08 144	88.09 197	66.00 192	83.13 307	87.79 255	68.42 287	78.01 201	85.23 309	45.50 366	95.12 88	59.11 328	85.83 198	91.11 196

cl____		77.72 247	76.76 249	80.58 264	82.49 359	60.48 311	83.09 308	87.87 252	69.22 267	74.38 294	85.22 310	62.10 179	91.53 259	71.09 215	75.41 348	89.73 263

HyFIR lowres test		77.53 253	75.40 273	83.94 159	89.59 126	66.62 181	80.36 345	88.64 236	56.29 413	76.45 239	85.17 311	57.64 236	93.28 175	61.34 310	83.10 247	91.91 171

pmmvs4		74.03 308	71.91 319	80.39 267	81.96 365	68.32 131	81.45 327	82.14 348	59.32 388	69.87 349	85.13 312	52.40 284	88.13 333	60.21 318	74.74 359	84.73 383

TDRefinement		67.49 373	64.34 384	76.92 336	73.47 432	61.07 302	84.86 263	82.98 339	59.77 384	58.30 427	85.13 312	26.06 436	87.89 336	47.92 408	60.59 424	81.81 414

Fast-Effi-MVS+		80.81 160	79.92 165	83.47 171	88.85 159	64.51 232	85.53 247	89.39 193	70.79 222	78.49 188	85.06 314	67.54 112	93.58 160	67.03 261	86.58 180	92.32 154

PVSNet_Blended		80.98 155	80.34 154	82.90 200	88.85 159	65.40 208	84.43 277	92.00 100	67.62 294	78.11 198	85.05 315	66.02 133	94.27 126	71.52 210	89.50 132	89.01 283

ttmdpeth		59.91 400	57.10 404	68.34 409	67.13 446	46.65 433	74.64 406	67.41 436	48.30 432	62.52 414	85.04 316	20.40 446	75.93 425	42.55 427	45.90 447	82.44 408

test_fmvs1_n		70.86 343	70.24 340	72.73 381	72.51 439	55.28 381	81.27 330	79.71 380	51.49 428	78.73 180	84.87 317	27.54 435	77.02 414	76.06 159	79.97 286	85.88 364

WBMVS		73.43 314	72.81 310	75.28 353	87.91 205	50.99 416	78.59 372	81.31 360	65.51 325	74.47 292	84.83 318	46.39 351	86.68 348	58.41 336	77.86 307	88.17 312

CMPMVS	51.72 21	70.19 352	68.16 354	76.28 340	73.15 435	57.55 347	79.47 356	83.92 319	48.02 433	56.48 433	84.81 319	43.13 381	86.42 352	62.67 294	81.81 263	84.89 380
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		68.53 368	67.61 367	71.31 393	78.51 409	47.01 431	84.47 273	84.27 315	42.27 440	66.44 389	84.79 320	40.44 398	83.76 376	58.76 333	68.54 401	83.17 399

BH-w/o		78.21 232	77.33 237	80.84 258	88.81 163	65.13 216	84.87 262	87.85 254	69.75 255	74.52 291	84.74 321	61.34 195	93.11 191	58.24 339	85.84 197	84.27 386

pmmvs5		71.55 336	70.20 341	75.61 346	77.83 410	56.39 364	81.74 322	80.89 361	57.76 403	67.46 371	84.49 322	49.26 331	85.32 366	57.08 349	75.29 352	85.11 377

reproduce_monomvs		75.40 292	74.38 290	78.46 311	83.92 321	57.80 343	83.78 289	86.94 275	73.47 166	72.25 321	84.47 323	38.74 406	89.27 312	75.32 170	70.53 391	88.31 308

thres200		75.55 287	74.47 288	78.82 300	87.78 214	57.85 341	83.07 310	83.51 326	72.44 187	75.84 253	84.42 324	52.08 291	91.75 247	47.41 409	83.64 236	86.86 344

test_fmvs1		70.93 342	70.52 335	72.16 385	73.71 428	55.05 383	80.82 333	78.77 389	51.21 429	78.58 185	84.41 325	31.20 430	76.94 415	75.88 162	80.12 285	84.47 385

testing3		68.56 367	67.67 366	71.22 394	87.33 231	42.87 444	83.06 311	71.54 424	70.36 236	69.08 357	84.38 326	30.33 432	85.69 360	37.50 437	75.45 347	85.09 378

test_fmvs2		68.35 370	67.48 369	70.98 396	69.50 442	51.95 405	80.05 350	76.38 407	49.33 431	74.65 289	84.38 326	23.30 444	75.40 431	74.51 177	75.17 355	85.60 367

eth_miper_zixun_eth		77.92 242	76.69 252	81.61 236	83.00 345	61.98 290	83.15 306	89.20 209	69.52 259	74.86 285	84.35 328	61.76 185	92.56 213	71.50 212	72.89 376	90.28 234

myMVS_eth3d28		73.62 311	73.53 301	73.90 370	88.20 189	47.41 429	78.06 379	79.37 383	74.29 143	73.98 297	84.29 329	44.67 369	83.54 379	51.47 382	87.39 166	90.74 213

testing91		76.54 269	75.66 268	79.18 295	88.43 182	55.89 372	81.08 331	83.00 338	73.76 156	75.34 267	84.29 329	46.20 357	90.07 297	64.33 280	84.50 215	91.58 182

c3_l		78.75 218	77.91 215	81.26 246	82.89 350	61.56 296	84.09 285	89.13 213	69.97 248	75.56 257	84.29 329	66.36 125	92.09 234	73.47 188	75.48 344	90.12 240

testing99		76.09 281	75.12 280	79.00 296	88.16 191	55.50 378	80.79 335	81.40 358	73.30 172	75.17 275	84.27 332	44.48 372	90.02 298	64.28 281	84.22 224	91.48 187

UWE-MVS		72.13 333	71.49 323	74.03 368	86.66 256	47.70 426	81.40 329	76.89 405	63.60 348	75.59 256	84.22 333	39.94 400	85.62 361	48.98 399	86.13 189	88.77 295

Fast-Effi-MVS+-dtu		78.02 239	76.49 255	82.62 216	83.16 341	66.96 179	86.94 199	87.45 264	72.45 185	71.49 330	84.17 334	54.79 262	91.58 253	67.61 252	80.31 281	89.30 274

IterMVS-SCA-FT		75.43 290	73.87 297	80.11 275	82.69 354	64.85 226	81.57 325	83.47 327	69.16 270	70.49 337	84.15 335	51.95 294	88.15 332	69.23 237	72.14 382	87.34 329

1314		76.53 270	75.30 277	80.21 273	83.93 320	62.32 286	84.66 267	88.81 225	60.23 380	70.16 343	84.07 336	55.30 256	90.73 289	67.37 255	83.21 245	87.59 324

cl22		78.07 237	77.01 241	81.23 247	82.37 362	61.83 293	83.55 297	87.98 248	68.96 277	75.06 280	83.87 337	61.40 194	91.88 243	73.53 186	76.39 329	89.98 252

EG-PatchMatch MVS		74.04 306	71.82 320	80.71 261	84.92 298	67.42 163	85.86 236	88.08 244	66.04 316	64.22 403	83.85 338	35.10 421	92.56 213	57.44 345	80.83 273	82.16 412

thisisatest0515		77.33 257	75.38 274	83.18 185	85.27 289	63.80 249	82.11 319	83.27 330	65.06 328	75.91 251	83.84 339	49.54 325	94.27 126	67.24 257	86.19 187	91.48 187

test20.03		67.45 374	66.95 375	68.94 403	75.48 421	44.84 440	77.50 384	77.67 395	66.66 305	63.01 410	83.80 340	47.02 345	78.40 407	42.53 428	68.86 400	83.58 396

miper_ehance_all_eth		78.59 224	77.76 224	81.08 252	82.66 355	61.56 296	83.65 293	89.15 211	68.87 278	75.55 258	83.79 341	66.49 123	92.03 235	73.25 191	76.39 329	89.64 264

MSDG		73.36 317	70.99 331	80.49 266	84.51 309	65.80 199	80.71 339	86.13 291	65.70 320	65.46 394	83.74 342	44.60 370	90.91 283	51.13 385	76.89 319	84.74 382

MonoMVSNet		76.49 274	75.80 263	78.58 305	81.55 372	58.45 330	86.36 222	86.22 288	74.87 128	74.73 287	83.73 343	51.79 299	88.73 324	70.78 217	72.15 381	88.55 304

testing11		75.14 295	74.01 293	78.53 308	88.16 191	56.38 365	80.74 338	80.42 371	70.67 225	72.69 315	83.72 344	43.61 379	89.86 300	62.29 298	83.76 230	89.36 272

IterMVS		74.29 301	72.94 309	78.35 312	81.53 373	63.49 262	81.58 324	82.49 345	68.06 291	69.99 346	83.69 345	51.66 301	85.54 362	65.85 269	71.64 385	86.01 360
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 329	71.71 321	74.35 364	82.19 363	52.00 404	79.22 360	77.29 401	64.56 334	72.95 311	83.68 346	51.35 302	83.26 383	58.33 338	75.80 338	87.81 318

UWE-MVS-28		65.32 387	64.93 381	66.49 415	78.70 407	38.55 452	77.86 383	64.39 444	62.00 368	64.13 404	83.60 347	41.44 392	76.00 424	31.39 444	80.89 271	84.92 379

sc_t1		72.19 332	69.51 343	80.23 272	84.81 300	61.09 301	84.68 266	80.22 375	60.70 376	71.27 331	83.58 348	36.59 416	89.24 313	60.41 315	63.31 416	90.37 229

testing222		74.04 306	72.66 312	78.19 314	87.89 206	55.36 379	81.06 332	79.20 386	71.30 208	74.65 289	83.57 349	39.11 405	88.67 326	51.43 384	85.75 199	90.53 222

Effi-MVS+-dtu		80.03 187	78.57 199	84.42 122	85.13 294	68.74 117	88.77 129	88.10 243	74.99 120	74.97 283	83.49 350	57.27 241	93.36 173	73.53 186	80.88 272	91.18 194

baseline2		75.70 285	73.83 298	81.30 244	83.26 335	61.79 294	82.57 315	80.65 365	66.81 301	66.88 379	83.42 351	57.86 234	92.19 231	63.47 285	79.57 288	89.91 254

mvs5depth		69.45 359	67.45 370	75.46 351	73.93 426	55.83 373	79.19 361	83.23 331	66.89 300	71.63 328	83.32 352	33.69 424	85.09 367	59.81 321	55.34 434	85.46 369

TinyColmap		67.30 376	64.81 382	74.76 360	81.92 367	56.68 360	80.29 347	81.49 357	60.33 378	56.27 434	83.22 353	24.77 440	87.66 340	45.52 419	69.47 395	79.95 423

mvsany_test1		62.30 396	61.26 400	65.41 417	69.52 441	54.86 385	66.86 435	49.78 457	46.65 434	68.50 363	83.21 354	49.15 332	66.28 449	56.93 352	60.77 422	75.11 433

test_vis1_n		69.85 357	69.21 346	71.77 387	72.66 438	55.27 382	81.48 326	76.21 408	52.03 425	75.30 272	83.20 355	28.97 433	76.22 422	74.60 176	78.41 303	83.81 393

CostFormer		75.24 294	73.90 296	79.27 292	82.65 356	58.27 333	80.80 334	82.73 344	61.57 370	75.33 271	83.13 356	55.52 254	91.07 280	64.98 276	78.34 304	88.45 305

MVStest1		56.63 404	52.76 410	68.25 410	61.67 452	53.25 401	71.67 416	68.90 434	38.59 445	50.59 441	83.05 357	25.08 438	70.66 442	36.76 438	38.56 448	80.83 419

WB-MVSnew		71.96 335	71.65 322	72.89 379	84.67 307	51.88 407	82.29 317	77.57 396	62.31 363	73.67 302	83.00 358	53.49 276	81.10 397	45.75 418	82.13 258	85.70 366

ETVMVS		72.25 331	71.05 330	75.84 343	87.77 215	51.91 406	79.39 357	74.98 412	69.26 265	73.71 300	82.95 359	40.82 397	86.14 354	46.17 415	84.43 220	89.47 268

miper_lstm_enhance		74.11 305	73.11 307	77.13 335	80.11 391	59.62 321	72.23 414	86.92 277	66.76 303	70.40 338	82.92 360	56.93 245	82.92 384	69.06 240	72.63 377	88.87 290

GA-MVS		76.87 265	75.17 279	81.97 229	82.75 352	62.58 281	81.44 328	86.35 287	72.16 192	74.74 286	82.89 361	46.20 357	92.02 236	68.85 243	81.09 269	91.30 192

K. test v3		71.19 338	68.51 350	79.21 294	83.04 344	57.78 344	84.35 280	76.91 404	72.90 181	62.99 411	82.86 362	39.27 402	91.09 279	61.65 306	52.66 437	88.75 296

MS-PatchMatch		73.83 309	72.67 311	77.30 333	83.87 322	66.02 190	81.82 320	84.66 308	61.37 373	68.61 361	82.82 363	47.29 342	88.21 331	59.27 325	84.32 222	77.68 428

lessismore_v0				78.97 297	81.01 382	57.15 352		65.99 439		61.16 417	82.82 363	39.12 404	91.34 268	59.67 322	46.92 444	88.43 306

D2MVS		74.82 297	73.21 305	79.64 286	79.81 396	62.56 282	80.34 346	87.35 265	64.37 337	68.86 358	82.66 365	46.37 353	90.10 296	67.91 250	81.24 267	86.25 353

Anonymous20231206		68.60 365	67.80 363	71.02 395	80.23 390	50.75 418	78.30 377	80.47 368	56.79 410	66.11 392	82.63 366	46.35 354	78.95 405	43.62 424	75.70 339	83.36 398

MIMVSNet		70.69 345	69.30 344	74.88 358	84.52 308	56.35 367	75.87 396	79.42 382	64.59 333	67.76 366	82.41 367	41.10 394	81.54 393	46.64 413	81.34 265	86.75 347

UBG		73.08 322	72.27 317	75.51 349	88.02 200	51.29 414	78.35 376	77.38 400	65.52 323	73.87 299	82.36 368	45.55 364	86.48 351	55.02 363	84.39 221	88.75 296

OpenMVS_ROB	64.09 19	70.56 347	68.19 353	77.65 326	80.26 388	59.41 325	85.01 259	82.96 340	58.76 395	65.43 395	82.33 369	37.63 413	91.23 272	45.34 421	76.03 336	82.32 409

miper_enhance_ethall		77.87 244	76.86 245	80.92 257	81.65 369	61.38 298	82.68 313	88.98 219	65.52 323	75.47 259	82.30 370	65.76 137	92.00 237	72.95 194	76.39 329	89.39 271

test0.0.03 1		68.00 372	67.69 365	68.90 404	77.55 411	47.43 427	75.70 397	72.95 423	66.66 305	66.56 384	82.29 371	48.06 339	75.87 426	44.97 422	74.51 361	83.41 397

PVSNet	64.34 18	72.08 334	70.87 333	75.69 345	86.21 263	56.44 363	74.37 408	80.73 364	62.06 367	70.17 342	82.23 372	42.86 383	83.31 382	54.77 365	84.45 219	87.32 330

MIMVSNet1		68.58 366	66.78 376	73.98 369	80.07 392	51.82 408	80.77 336	84.37 311	64.40 336	59.75 423	82.16 373	36.47 417	83.63 378	42.73 426	70.33 392	86.48 351

CL-MVSNet_self_test		72.37 329	71.46 324	75.09 355	79.49 402	53.53 395	80.76 337	85.01 306	69.12 271	70.51 336	82.05 374	57.92 233	84.13 374	52.27 378	66.00 409	87.60 322

tpm2		73.26 319	71.46 324	78.63 302	83.34 333	56.71 359	80.65 340	80.40 372	56.63 411	73.55 303	82.02 375	51.80 298	91.24 271	56.35 358	78.42 302	87.95 314

PatchMatch-RL		72.38 328	70.90 332	76.80 338	88.60 175	67.38 166	79.53 355	76.17 409	62.75 359	69.36 354	82.00 376	45.51 365	84.89 370	53.62 371	80.58 277	78.12 427

FMVSNet5		69.50 358	67.96 358	74.15 367	82.97 348	55.35 380	80.01 351	82.12 349	62.56 361	63.02 409	81.53 377	36.92 414	81.92 391	48.42 401	74.06 364	85.17 376

CR-MVSNet		73.37 315	71.27 328	79.67 285	81.32 379	65.19 214	75.92 394	80.30 373	59.92 383	72.73 313	81.19 378	52.50 282	86.69 347	59.84 320	77.71 309	87.11 338

Patchmtry		70.74 344	69.16 347	75.49 350	80.72 383	54.07 392	74.94 405	80.30 373	58.34 397	70.01 344	81.19 378	52.50 282	86.54 349	53.37 373	71.09 389	85.87 365

IB-MVS	68.01 15	75.85 284	73.36 304	83.31 178	84.76 302	66.03 189	83.38 301	85.06 304	70.21 243	69.40 353	81.05 380	45.76 362	94.66 113	65.10 275	75.49 343	89.25 275
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
cascas		76.72 268	74.64 284	82.99 196	85.78 274	65.88 196	82.33 316	89.21 208	60.85 375	72.74 312	81.02 381	47.28 343	93.75 156	67.48 254	85.02 207	89.34 273

LF4IMVS		64.02 392	62.19 396	69.50 401	70.90 440	53.29 400	76.13 391	77.18 402	52.65 423	58.59 425	80.98 382	23.55 443	76.52 418	53.06 375	66.66 405	78.68 426

Anonymous20240521		68.80 364	67.22 373	73.55 372	74.33 424	54.11 391	83.18 305	85.61 297	58.15 399	61.68 415	80.94 383	30.71 431	81.27 396	57.00 351	73.34 374	85.28 372

gm-plane-assit					81.40 375	53.83 394			62.72 360		80.94 383		92.39 222	63.40 287

UnsupCasMVSNet_eth		67.33 375	65.99 379	71.37 390	73.48 431	51.47 412	75.16 401	85.19 301	65.20 326	60.78 418	80.93 385	42.35 385	77.20 413	57.12 348	53.69 436	85.44 370

dmvs_re		71.14 339	70.58 334	72.80 380	81.96 365	59.68 320	75.60 398	79.34 384	68.55 283	69.27 356	80.72 386	49.42 327	76.54 417	52.56 377	77.79 308	82.19 411

MDTV_nov1_ep13			69.97 342		83.18 339	53.48 396	77.10 389	80.18 377	60.45 377	69.33 355	80.44 387	48.89 337	86.90 346	51.60 381	78.51 300

pmmvs-eth3d		70.50 348	67.83 362	78.52 309	77.37 413	66.18 188	81.82 320	81.51 356	58.90 393	63.90 407	80.42 388	42.69 384	86.28 353	58.56 334	65.30 411	83.11 401

tt0320		70.49 349	68.03 357	77.89 320	84.78 301	59.12 326	83.55 297	80.44 370	58.13 400	67.43 373	80.41 389	39.26 403	87.54 341	55.12 362	63.18 417	86.99 341

mmtdpeth		74.16 304	73.01 308	77.60 329	83.72 326	61.13 299	85.10 257	85.10 303	72.06 193	77.21 223	80.33 390	43.84 377	85.75 358	77.14 147	52.61 438	85.91 363

tt0320-xc		70.11 353	67.45 370	78.07 318	85.33 287	59.51 324	83.28 303	78.96 388	58.77 394	67.10 377	80.28 391	36.73 415	87.42 342	56.83 354	59.77 426	87.29 331

PM-MVS		66.41 382	64.14 385	73.20 377	73.92 427	56.45 362	78.97 365	64.96 443	63.88 347	64.72 400	80.24 392	19.84 448	83.44 381	66.24 263	64.52 413	79.71 424

SCA		74.22 303	72.33 316	79.91 278	84.05 318	62.17 288	79.96 352	79.29 385	66.30 313	72.38 319	80.13 393	51.95 294	88.60 327	59.25 326	77.67 312	88.96 287

Patchmatch-test		64.82 390	63.24 391	69.57 400	79.42 403	49.82 422	63.49 447	69.05 432	51.98 426	59.95 422	80.13 393	50.91 307	70.98 441	40.66 431	73.57 369	87.90 316

tpmrst		72.39 327	72.13 318	73.18 378	80.54 386	49.91 421	79.91 353	79.08 387	63.11 351	71.69 327	79.95 395	55.32 255	82.77 386	65.66 271	73.89 366	86.87 343

DSMNet-mixed		57.77 403	56.90 405	60.38 423	67.70 444	35.61 454	69.18 427	53.97 455	32.30 453	57.49 430	79.88 396	40.39 399	68.57 447	38.78 435	72.37 378	76.97 429

MDA-MVSNet-bldmvs		66.68 379	63.66 389	75.75 344	79.28 404	60.56 310	73.92 410	78.35 392	64.43 335	50.13 442	79.87 397	44.02 376	83.67 377	46.10 416	56.86 428	83.03 403

PatchmatchNet		73.12 321	71.33 327	78.49 310	83.18 339	60.85 305	79.63 354	78.57 390	64.13 339	71.73 326	79.81 398	51.20 305	85.97 357	57.40 346	76.36 334	88.66 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Syy-MVS		68.05 371	67.85 360	68.67 407	84.68 304	40.97 450	78.62 370	73.08 421	66.65 308	66.74 382	79.46 399	52.11 290	82.30 388	32.89 442	76.38 332	82.75 406

myMVS_eth3d		67.02 377	66.29 378	69.21 402	84.68 304	42.58 445	78.62 370	73.08 421	66.65 308	66.74 382	79.46 399	31.53 429	82.30 388	39.43 434	76.38 332	82.75 406

ppachtmachnet_test		70.04 354	67.34 372	78.14 315	79.80 397	61.13 299	79.19 361	80.59 366	59.16 390	65.27 396	79.29 401	46.75 350	87.29 343	49.33 397	66.72 404	86.00 362

EPMVS		69.02 362	68.16 354	71.59 388	79.61 400	49.80 423	77.40 385	66.93 437	62.82 358	70.01 344	79.05 402	45.79 361	77.86 411	56.58 356	75.26 353	87.13 337

PMMVS		69.34 360	68.67 349	71.35 392	75.67 419	62.03 289	75.17 400	73.46 419	50.00 430	68.68 359	79.05 402	52.07 292	78.13 408	61.16 311	82.77 250	73.90 434

test-LLR		72.94 325	72.43 314	74.48 362	81.35 377	58.04 336	78.38 373	77.46 397	66.66 305	69.95 347	79.00 404	48.06 339	79.24 403	66.13 264	84.83 210	86.15 356

test-mter		71.41 337	70.39 339	74.48 362	81.35 377	58.04 336	78.38 373	77.46 397	60.32 379	69.95 347	79.00 404	36.08 419	79.24 403	66.13 264	84.83 210	86.15 356

KD-MVS_self_test		68.81 363	67.59 368	72.46 384	74.29 425	45.45 434	77.93 381	87.00 273	63.12 350	63.99 406	78.99 406	42.32 386	84.77 371	56.55 357	64.09 414	87.16 336

test_fmvs3		63.36 394	61.82 397	67.98 411	62.51 451	46.96 432	77.37 386	74.03 418	45.24 436	67.50 370	78.79 407	12.16 456	72.98 440	72.77 197	66.02 408	83.99 391

KD-MVS_2432*1600		66.22 384	63.89 387	73.21 375	75.47 422	53.42 397	70.76 421	84.35 312	64.10 341	66.52 386	78.52 408	34.55 422	84.98 368	50.40 388	50.33 441	81.23 416

miper_refine_blended		66.22 384	63.89 387	73.21 375	75.47 422	53.42 397	70.76 421	84.35 312	64.10 341	66.52 386	78.52 408	34.55 422	84.98 368	50.40 388	50.33 441	81.23 416

tpmvs		71.09 340	69.29 345	76.49 339	82.04 364	56.04 370	78.92 366	81.37 359	64.05 343	67.18 376	78.28 410	49.74 324	89.77 302	49.67 395	72.37 378	83.67 395

our_test_3		69.14 361	67.00 374	75.57 347	79.80 397	58.80 327	77.96 380	77.81 394	59.55 386	62.90 412	78.25 411	47.43 341	83.97 375	51.71 380	67.58 403	83.93 392

MDA-MVSNet_test_wron		65.03 388	62.92 392	71.37 390	75.93 416	56.73 357	69.09 430	74.73 415	57.28 408	54.03 437	77.89 412	45.88 359	74.39 435	49.89 394	61.55 420	82.99 404

YYNet1		65.03 388	62.91 393	71.38 389	75.85 418	56.60 361	69.12 429	74.66 417	57.28 408	54.12 436	77.87 413	45.85 360	74.48 434	49.95 393	61.52 421	83.05 402

ambc				75.24 354	73.16 434	50.51 419	63.05 448	87.47 263		64.28 402	77.81 414	17.80 450	89.73 304	57.88 342	60.64 423	85.49 368

tpm cat1		70.57 346	68.31 352	77.35 332	82.41 361	57.95 339	78.08 378	80.22 375	52.04 424	68.54 362	77.66 415	52.00 293	87.84 337	51.77 379	72.07 383	86.25 353

dp		66.80 378	65.43 380	70.90 397	79.74 399	48.82 425	75.12 403	74.77 414	59.61 385	64.08 405	77.23 416	42.89 382	80.72 399	48.86 400	66.58 406	83.16 400

TESTMET0.1,1		69.89 356	69.00 348	72.55 382	79.27 405	56.85 355	78.38 373	74.71 416	57.64 404	68.09 365	77.19 417	37.75 412	76.70 416	63.92 283	84.09 225	84.10 390

CHOSEN 280x420		66.51 381	64.71 383	71.90 386	81.45 374	63.52 261	57.98 450	68.95 433	53.57 420	62.59 413	76.70 418	46.22 356	75.29 432	55.25 361	79.68 287	76.88 430

PatchT		68.46 369	67.85 360	70.29 398	80.70 384	43.93 442	72.47 413	74.88 413	60.15 381	70.55 335	76.57 419	49.94 321	81.59 392	50.58 386	74.83 358	85.34 371

mvsany_test3		53.99 407	51.45 412	61.61 422	55.51 456	44.74 441	63.52 446	45.41 461	43.69 439	58.11 428	76.45 420	17.99 449	63.76 452	54.77 365	47.59 443	76.34 431

RPMNet		73.51 313	70.49 336	82.58 218	81.32 379	65.19 214	75.92 394	92.27 85	57.60 405	72.73 313	76.45 420	52.30 285	95.43 73	48.14 406	77.71 309	87.11 338

dmvs_testset		62.63 395	64.11 386	58.19 425	78.55 408	24.76 463	75.28 399	65.94 440	67.91 292	60.34 419	76.01 422	53.56 274	73.94 438	31.79 443	67.65 402	75.88 432

ADS-MVSNet2		66.20 386	63.33 390	74.82 359	79.92 393	58.75 328	67.55 433	75.19 411	53.37 421	65.25 397	75.86 423	42.32 386	80.53 400	41.57 429	68.91 398	85.18 374

ADS-MVSNet		64.36 391	62.88 394	68.78 406	79.92 393	47.17 430	67.55 433	71.18 425	53.37 421	65.25 397	75.86 423	42.32 386	73.99 437	41.57 429	68.91 398	85.18 374

EGC-MVSNET		52.07 413	47.05 417	67.14 413	83.51 330	60.71 307	80.50 343	67.75 435	0.07 463	0.43 464	75.85 425	24.26 441	81.54 393	28.82 446	62.25 418	59.16 446

new-patchmatchnet		61.73 397	61.73 398	61.70 421	72.74 437	24.50 464	69.16 428	78.03 393	61.40 371	56.72 432	75.53 426	38.42 408	76.48 419	45.95 417	57.67 427	84.13 389

N_pmnet		52.79 411	53.26 409	51.40 435	78.99 406	7.68 469	69.52 425	3.89 468	51.63 427	57.01 431	74.98 427	40.83 396	65.96 450	37.78 436	64.67 412	80.56 422

WB-MVS		54.94 405	54.72 406	55.60 431	73.50 430	20.90 465	74.27 409	61.19 448	59.16 390	50.61 440	74.15 428	47.19 344	75.78 427	17.31 456	35.07 450	70.12 438

patchmatchnet-post											74.00 429	51.12 306	88.60 327

GG-mvs-BLEND				75.38 352	81.59 371	55.80 374	79.32 358	69.63 429		67.19 375	73.67 430	43.24 380	88.90 323	50.41 387	84.50 215	81.45 415

SSC-MVS		53.88 408	53.59 408	54.75 433	72.87 436	19.59 466	73.84 411	60.53 450	57.58 406	49.18 444	73.45 431	46.34 355	75.47 430	16.20 459	32.28 452	69.20 439

Patchmatch-RL test		70.24 351	67.78 364	77.61 327	77.43 412	59.57 323	71.16 418	70.33 426	62.94 355	68.65 360	72.77 432	50.62 311	85.49 363	69.58 235	66.58 406	87.77 319

FPMVS		53.68 409	51.64 411	59.81 424	65.08 448	51.03 415	69.48 426	69.58 430	41.46 441	40.67 448	72.32 433	16.46 452	70.00 445	24.24 452	65.42 410	58.40 448

UnsupCasMVSNet_bld		63.70 393	61.53 399	70.21 399	73.69 429	51.39 413	72.82 412	81.89 351	55.63 415	57.81 429	71.80 434	38.67 407	78.61 406	49.26 398	52.21 439	80.63 420

APD_test1		53.31 410	49.93 415	63.42 420	65.68 447	50.13 420	71.59 417	66.90 438	34.43 450	40.58 449	71.56 435	8.65 461	76.27 421	34.64 441	55.36 433	63.86 444

test_f		52.09 412	50.82 413	55.90 429	53.82 459	42.31 448	59.42 449	58.31 453	36.45 448	56.12 435	70.96 436	12.18 455	57.79 455	53.51 372	56.57 430	67.60 440

PVSNet_0	57.27 20	61.67 398	59.27 401	68.85 405	79.61 400	57.44 349	68.01 431	73.44 420	55.93 414	58.54 426	70.41 437	44.58 371	77.55 412	47.01 410	35.91 449	71.55 437

pmmvs3		57.79 402	54.26 407	68.37 408	64.02 450	56.72 358	75.12 403	65.17 441	40.20 442	52.93 438	69.86 438	20.36 447	75.48 429	45.45 420	55.25 435	72.90 436

test_vis1_rt		60.28 399	58.42 402	65.84 416	67.25 445	55.60 377	70.44 423	60.94 449	44.33 438	59.00 424	66.64 439	24.91 439	68.67 446	62.80 290	69.48 394	73.25 435

new_pmnet		50.91 414	50.29 414	52.78 434	68.58 443	34.94 456	63.71 445	56.63 454	39.73 443	44.95 445	65.47 440	21.93 445	58.48 454	34.98 440	56.62 429	64.92 442

gg-mvs-nofinetune		69.95 355	67.96 358	75.94 342	83.07 342	54.51 389	77.23 387	70.29 427	63.11 351	70.32 339	62.33 441	43.62 378	88.69 325	53.88 370	87.76 161	84.62 384

JIA-IIPM		66.32 383	62.82 395	76.82 337	77.09 414	61.72 295	65.34 441	75.38 410	58.04 402	64.51 401	62.32 442	42.05 390	86.51 350	51.45 383	69.22 397	82.21 410

LCM-MVSNet		54.25 406	49.68 416	67.97 412	53.73 460	45.28 437	66.85 436	80.78 363	35.96 449	39.45 450	62.23 443	8.70 460	78.06 410	48.24 405	51.20 440	80.57 421

PMMVS2		40.82 422	38.86 426	46.69 436	53.84 458	16.45 467	48.61 453	49.92 456	37.49 446	31.67 451	60.97 444	8.14 462	56.42 456	28.42 447	30.72 453	67.19 441

testf1		45.72 417	41.96 421	57.00 426	56.90 454	45.32 435	66.14 438	59.26 451	26.19 454	30.89 453	60.96 445	4.14 464	70.64 443	26.39 450	46.73 445	55.04 449

APD_test2		45.72 417	41.96 421	57.00 426	56.90 454	45.32 435	66.14 438	59.26 451	26.19 454	30.89 453	60.96 445	4.14 464	70.64 443	26.39 450	46.73 445	55.04 449

MVS-HIRNet		59.14 401	57.67 403	63.57 419	81.65 369	43.50 443	71.73 415	65.06 442	39.59 444	51.43 439	57.73 447	38.34 409	82.58 387	39.53 432	73.95 365	64.62 443

ANet_high		50.57 415	46.10 419	63.99 418	48.67 463	39.13 451	70.99 420	80.85 362	61.39 372	31.18 452	57.70 448	17.02 451	73.65 439	31.22 445	15.89 460	79.18 425

PMVS	37.38 22	44.16 421	40.28 425	55.82 430	40.82 465	42.54 447	65.12 442	63.99 445	34.43 450	24.48 456	57.12 449	3.92 466	76.17 423	17.10 457	55.52 432	48.75 451
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		45.42 419	45.38 420	45.55 437	73.36 433	26.85 461	67.72 432	34.19 463	54.15 419	49.65 443	56.41 450	25.43 437	62.94 453	19.45 454	28.09 454	46.86 453

test_vis3_rt		49.26 416	47.02 418	56.00 428	54.30 457	45.27 438	66.76 437	48.08 458	36.83 447	44.38 446	53.20 451	7.17 463	64.07 451	56.77 355	55.66 431	58.65 447

test_method		31.52 425	29.28 429	38.23 439	27.03 467	6.50 470	20.94 458	62.21 447	4.05 461	22.35 459	52.50 452	13.33 453	47.58 459	27.04 449	34.04 451	60.62 445

kuosan		39.70 423	40.40 424	37.58 440	64.52 449	26.98 459	65.62 440	33.02 464	46.12 435	42.79 447	48.99 453	24.10 442	46.56 461	12.16 462	26.30 455	39.20 454

DeepMVS_CX				27.40 443	40.17 466	26.90 460		24.59 467	17.44 459	23.95 457	48.61 454	9.77 458	26.48 462	18.06 455	24.47 456	28.83 456

MVE	26.22 23	30.37 427	25.89 431	43.81 438	44.55 464	35.46 455	28.87 457	39.07 462	18.20 458	18.58 460	40.18 455	2.68 467	47.37 460	17.07 458	23.78 457	48.60 452
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		45.18 420	41.86 423	55.16 432	77.03 415	51.52 411	32.50 456	80.52 367	32.46 452	27.12 455	35.02 456	9.52 459	75.50 428	22.31 453	60.21 425	38.45 455
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		31.77 424	30.64 427	35.15 441	52.87 461	27.67 458	57.09 451	47.86 459	24.64 456	16.40 461	33.05 457	11.23 457	54.90 457	14.46 460	18.15 458	22.87 457

EMVS		30.81 426	29.65 428	34.27 442	50.96 462	25.95 462	56.58 452	46.80 460	24.01 457	15.53 462	30.68 458	12.47 454	54.43 458	12.81 461	17.05 459	22.43 458

tmp_tt		18.61 429	21.40 432	10.23 445	4.82 468	10.11 468	34.70 455	30.74 466	1.48 462	23.91 458	26.07 459	28.42 434	13.41 464	27.12 448	15.35 461	7.17 459

X-MVStestdata		80.37 181	77.83 219	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 107	12.47 460	67.45 113	96.60 33	83.06 81	94.50 53	94.07 60

test_post											5.46 461	50.36 315	84.24 373

test_post1							78.90 367				5.43 462	48.81 338	85.44 365	59.25 326

wuyk23d		16.82 430	15.94 433	19.46 444	58.74 453	31.45 457	39.22 454	3.74 469	6.84 460	6.04 463	2.70 463	1.27 468	24.29 463	10.54 463	14.40 462	2.63 460

testmvs		6.04 433	8.02 436	0.10 447	0.08 469	0.03 472	69.74 424	0.04 470	0.05 464	0.31 465	1.68 464	0.02 470	0.04 465	0.24 464	0.02 463	0.25 462

test123		6.12 432	8.11 435	0.14 446	0.06 470	0.09 471	71.05 419	0.03 471	0.04 465	0.25 466	1.30 465	0.05 469	0.03 466	0.21 465	0.01 464	0.29 461

mmdepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

monomultidepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

test_blank		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet_test		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

DCPMVS		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

pcd_1.5k_mvsjas		5.26 434	7.02 437	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	63.15 162	0.00 467	0.00 466	0.00 465	0.00 463

sosnet-low-res		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uncertanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

Regformer		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

WAC-MVS						42.58 445								39.46 433

FOURS1					95.00 10	72.39 41	95.06 1	93.84 16	74.49 136	91.30 15

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 14	96.44 9	94.41 43

No_MVS				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 14	96.44 9	94.41 43

eth-test2					0.00 471

eth-test					0.00 471

IU-MVS					95.30 2	71.25 61		92.95 56	66.81 301	92.39 6				88.94 26	96.63 4	94.85 21

save fliter					93.80 40	72.35 44	90.47 69	91.17 133	74.31 141

test_0728_SECOND				87.71 32	95.34 1	71.43 60	93.49 10	94.23 3					97.49 4	89.08 21	96.41 12	94.21 54

GSMVS																88.96 287

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 303				88.96 287

sam_mvs												50.01 319

MTGPA								92.02 98

MTMP							92.18 35	32.83 465

test9_res														84.90 58	95.70 26	92.87 130

agg_prior2														82.91 85	95.45 29	92.70 135

agg_prior					92.85 64	71.94 52		91.78 113		84.41 89			94.93 97

test_prior4						72.60 34	89.01 118

test_prior				86.33 60	92.61 70	69.59 94		92.97 55					95.48 70			93.91 68

旧先验2							86.56 215		58.10 401	87.04 56			88.98 319	74.07 182

新几何2							86.29 225

无先验							87.48 178	88.98 219	60.00 382				94.12 134	67.28 256		88.97 286

原ACMM2							86.86 202

testdata2													91.01 281	62.37 297

segment_acmp												73.08 40

testdata1							84.14 284		75.71 100

test12				86.80 54	92.63 69	70.70 77		91.79 112		82.71 121		71.67 59	96.16 48		94.50 53	93.54 97

plane_prior7					90.08 112	68.51 127

plane_prior6					89.84 121	68.70 121						60.42 214

plane_prior5								92.44 78					95.38 78	78.71 128	86.32 184	91.33 190

plane_prior3						68.60 124			78.44 36	78.92 178

plane_prior2							91.25 55		79.12 28

plane_prior1					89.90 120

plane_prior						68.71 119	90.38 73		77.62 47						86.16 188

n2								0.00 472

nn								0.00 472

door-mid								69.98 428

test11								92.23 88

door								69.44 431

HQP5-MVS						66.98 177

HQP-NCC					89.33 140		89.17 109		76.41 85	77.23 219

ACMP_Plane					89.33 140		89.17 109		76.41 85	77.23 219

BP-MVS														77.47 142

HQP4-MVS										77.24 218			95.11 90			91.03 200

HQP3-MVS								92.19 92							85.99 192

HQP2-MVS												60.17 217

MDTV_nov1_ep13_2view						37.79 453	75.16 401		55.10 416	66.53 385		49.34 329		53.98 369		87.94 315

ACMMP++_ref															81.95 261

ACMMP++															81.25 266

Test By Simon												64.33 148

High-resolution multi-view benchmark