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 19	95.65 27	94.47 41
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	74.77 128	92.29 7	95.97 2	74.28 30	97.24 13	88.58 30	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 20	96.41 12	93.33 103
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 17	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 17	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 22	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 22	96.58 6	94.26 52

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 42	96.34 15	93.95 66
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	74.69 129	88.80 27	95.61 11	70.29 76	96.44 39	86.20 50	93.08 71	93.16 113

reproduce-ours		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 120	88.96 24	95.54 12	71.20 65	96.54 36	86.28 48	93.49 67	93.06 118

our_new_method		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 120	88.96 24	95.54 12	71.20 65	96.54 36	86.28 48	93.49 67	93.06 118

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 48	96.27 44	86.87 44	94.65 48	93.70 82

fmvsm_s_conf0.5_n_9		87.39 30	87.95 20	85.70 77	89.48 133	67.88 149	88.59 139	89.05 212	80.19 12	90.70 17	95.40 15	74.56 25	93.92 145	91.54 2	92.07 85	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	75.17 117	86.34 61	95.29 17	70.86 69	96.00 55	88.78 28	96.04 16	94.58 34
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 23	95.10 18	75.65 21	96.19 47	87.07 43	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 35	95.09 19	71.06 67	96.67 29	87.67 38	96.37 14	94.09 58

fmvsm_s_conf0.5_n_3		86.36 49	87.46 29	83.09 187	87.08 243	65.21 212	89.09 116	90.21 163	79.67 19	89.98 19	95.02 20	73.17 39	91.71 249	91.30 3	91.60 92	92.34 149

MM		89.16 6	89.23 7	88.97 4	90.79 98	73.65 10	92.66 24	91.17 132	86.57 1	87.39 51	94.97 21	71.70 57	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	65.62 203	89.20 107	92.21 90	79.94 17	89.74 22	94.86 22	68.63 98	94.20 130	90.83 5	91.39 97	94.38 45

MTAPA		87.23 33	87.00 36	87.90 22	94.18 35	74.25 5	86.58 212	92.02 98	79.45 22	85.88 63	94.80 23	68.07 104	96.21 46	86.69 46	95.34 32	93.23 106

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 36	94.80 23	73.76 34	97.11 15	87.51 40	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	73.93 150	88.57 29	94.67 25	75.57 22	95.79 59	86.77 45	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	74.50 133	86.84 58	94.65 26	67.31 113	95.77 60	84.80 61	92.85 74	92.84 130

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 87	94.52 27	69.09 90	96.70 27	84.37 67	94.83 45	94.03 61

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 82	94.52 27	68.81 96	96.65 30	84.53 65	94.90 41	94.00 63

APD-MVS		87.44 26	87.52 27	87.19 43	94.24 32	72.39 41	91.86 41	92.83 61	73.01 176	88.58 28	94.52 27	73.36 35	96.49 38	84.26 68	95.01 37	92.70 132
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
APD-MVS_3200maxsize		85.97 56	85.88 59	86.22 63	92.69 68	69.53 95	91.93 38	92.99 50	73.54 161	85.94 62	94.51 30	65.80 133	95.61 63	83.04 82	92.51 79	93.53 96

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	83.68 105	94.46 31	67.93 106	95.95 58	84.20 71	94.39 57	93.23 106

SR-MVS-dyc-post		85.77 61	85.61 66	86.23 62	93.06 60	70.63 78	91.88 39	92.27 85	73.53 162	85.69 66	94.45 32	65.00 141	95.56 64	82.75 86	91.87 88	92.50 142

RE-MVS-def			85.48 69		93.06 60	70.63 78	91.88 39	92.27 85	73.53 162	85.69 66	94.45 32	63.87 149		82.75 86	91.87 88	92.50 142

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 75	94.44 34	70.78 70	96.61 32	84.53 65	94.89 42	93.66 83

PGM-MVS		86.68 42	86.27 49	87.90 22	94.22 33	73.38 18	90.22 76	93.04 42	75.53 104	83.86 101	94.42 35	67.87 108	96.64 31	82.70 90	94.57 52	93.66 83

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	83.84 102	94.40 36	72.24 49	96.28 43	85.65 52	95.30 35	93.62 90
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 47	85.14 92	87.20 235	68.54 126	89.57 93	90.44 152	75.31 111	87.49 48	94.39 37	72.86 43	92.72 206	89.04 24	90.56 111	94.16 54

fmvsm_s_conf0.1_n_2		83.80 92	83.79 93	83.83 160	85.62 276	64.94 222	87.03 193	86.62 279	74.32 138	87.97 41	94.33 38	60.67 205	92.60 209	89.72 12	87.79 157	93.96 64

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 70	94.32 39	71.76 55	96.93 19	85.53 54	95.79 22	94.32 49

MVS_0304		87.69 21	87.55 26	88.12 13	89.45 134	71.76 53	91.47 52	89.54 185	82.14 3	86.65 59	94.28 40	68.28 103	97.46 6	90.81 6	95.31 34	95.15 8

test_fmvsmconf0.01_n		84.73 83	84.52 85	85.34 87	80.25 386	69.03 106	89.47 95	89.65 181	73.24 172	86.98 56	94.27 41	66.62 118	93.23 179	90.26 9	89.95 123	93.78 79

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 42	94.27 41	75.89 19	96.81 23	87.45 41	96.44 9	93.05 120

mPP-MVS		86.67 43	86.32 47	87.72 30	94.41 22	73.55 13	92.74 21	92.22 89	76.87 73	82.81 118	94.25 43	66.44 122	96.24 45	82.88 85	94.28 60	93.38 99

fmvsm_s_conf0.5_n_2		84.04 88	84.11 89	83.81 162	86.17 263	65.00 220	86.96 196	87.28 263	74.35 137	88.25 33	94.23 44	61.82 181	92.60 209	89.85 10	88.09 155	93.84 73

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	82.82 117	94.23 44	72.13 51	97.09 16	84.83 60	95.37 31	93.65 87
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	83.67 106	94.17 46	67.45 111	96.60 33	83.06 80	94.50 53	94.07 59

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 47	78.35 13	96.77 24	89.59 15	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 65	85.65 65	85.50 83	82.99 344	69.39 103	89.65 89	90.29 161	73.31 168	87.77 43	94.15 48	71.72 56	93.23 179	90.31 8	90.67 110	93.89 70

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 49	78.98 12	96.58 35	85.66 51	95.72 24	94.58 34

HPM-MVS_fast		85.35 73	84.95 79	86.57 59	93.69 42	70.58 80	92.15 36	91.62 118	73.89 151	82.67 120	94.09 50	62.60 165	95.54 66	80.93 103	92.93 73	93.57 92

ZD-MVS					94.38 25	72.22 46		92.67 68	70.98 215	87.75 44	94.07 51	74.01 33	96.70 27	84.66 63	94.84 44

fmvsm_s_conf0.1_n_a		83.32 108	82.99 106	84.28 130	83.79 321	68.07 141	89.34 104	82.85 339	69.80 249	87.36 52	94.06 52	68.34 102	91.56 255	87.95 36	83.46 238	93.21 109

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 37	94.06 52	76.43 16	96.84 21	88.48 33	95.99 18	94.34 48

test_fmvsmconf_n		85.92 57	86.04 57	85.57 82	85.03 295	69.51 96	89.62 92	90.58 147	73.42 165	87.75 44	94.02 54	72.85 44	93.24 178	90.37 7	90.75 108	93.96 64

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 54	82.45 3	96.87 20	83.77 75	96.48 8	94.88 16

PC_three_1452									68.21 286	92.02 12	94.00 56	82.09 5	95.98 57	84.58 64	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 56	74.83 23	93.78 152	87.63 39	94.27 61	93.65 87
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 79	93.99 58	70.67 72	96.82 22	84.18 72	95.01 37	93.90 69

test_fmvsm_n_1920		85.29 74	85.34 71	85.13 95	86.12 265	69.93 88	88.65 137	90.78 143	69.97 245	88.27 32	93.98 59	71.39 62	91.54 257	88.49 32	90.45 113	93.91 67

fmvsm_s_conf0.1_n		83.56 100	83.38 99	84.10 139	84.86 297	67.28 169	89.40 101	83.01 334	70.67 222	87.08 54	93.96 60	68.38 101	91.45 263	88.56 31	84.50 212	93.56 93

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	83.81 103	93.95 61	69.77 82	96.01 54	85.15 55	94.66 47	94.32 49
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		83.34 107	84.03 90	81.28 242	85.73 273	65.13 215	85.40 248	89.90 173	74.96 122	82.13 124	93.89 62	66.65 117	87.92 332	86.56 47	91.05 102	90.80 205

fmvsm_s_conf0.5_n_5		85.22 75	85.55 67	84.25 135	86.26 259	67.40 165	89.18 108	89.31 197	72.50 181	88.31 31	93.86 63	69.66 83	91.96 237	89.81 11	91.05 102	93.38 99

TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 48	91.41 53	92.35 83	74.62 132	88.90 26	93.85 64	75.75 20	96.00 55	87.80 37	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 70	87.38 40	93.59 45	72.63 33	92.74 21	93.18 40	76.78 76	80.73 148	93.82 65	64.33 145	96.29 42	82.67 91	90.69 109	93.23 106
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 98	83.41 98	84.28 130	86.14 264	68.12 139	89.43 97	82.87 338	70.27 238	87.27 53	93.80 66	69.09 90	91.58 252	88.21 35	83.65 232	93.14 115

fmvsm_s_conf0.5_n_4		85.39 71	85.75 64	84.30 128	86.70 252	65.83 196	88.77 129	89.78 175	75.46 106	88.35 30	93.73 67	69.19 89	93.06 194	91.30 3	88.44 150	94.02 62

fmvsm_s_conf0.5_n		83.80 92	83.71 94	84.07 145	86.69 253	67.31 168	89.46 96	83.07 333	71.09 210	86.96 57	93.70 68	69.02 95	91.47 262	88.79 27	84.62 211	93.44 98

test_prior2							88.85 125		75.41 107	84.91 75	93.54 69	74.28 30		83.31 78	95.86 20

fmvsm_l_conf0.5_n		84.47 84	84.54 83	84.27 132	85.42 282	68.81 112	88.49 142	87.26 265	68.08 287	88.03 38	93.49 70	72.04 52	91.77 245	88.90 26	89.14 137	92.24 156

VDDNet		81.52 143	80.67 143	84.05 150	90.44 104	64.13 240	89.73 87	85.91 290	71.11 209	83.18 111	93.48 71	50.54 310	93.49 166	73.40 186	88.25 152	94.54 39

CDPH-MVS		85.76 62	85.29 75	87.17 44	93.49 47	71.08 66	88.58 140	92.42 81	68.32 285	84.61 84	93.48 71	72.32 47	96.15 49	79.00 121	95.43 30	94.28 51

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 65	93.47 73	73.02 42	97.00 18	84.90 57	94.94 40	94.10 57

fmvsm_s_conf0.5_n_6		85.55 66	86.20 50	83.60 166	87.32 232	65.13 215	88.86 123	91.63 117	75.41 107	88.23 34	93.45 74	68.56 99	92.47 217	89.52 16	92.78 75	93.20 111

fmvsm_l_conf0.5_n_a		84.13 87	84.16 88	84.06 147	85.38 283	68.40 129	88.34 149	86.85 275	67.48 294	87.48 49	93.40 75	70.89 68	91.61 250	88.38 34	89.22 135	92.16 163

3Dnovator+	77.84 4	85.48 67	84.47 86	88.51 7	91.08 89	73.49 16	93.18 12	93.78 19	80.79 8	76.66 230	93.37 76	60.40 213	96.75 26	77.20 142	93.73 66	95.29 6

DeepC-MVS_fast	79.65 3	86.91 38	86.62 44	87.76 27	93.52 46	72.37 43	91.26 54	93.04 42	76.62 82	84.22 93	93.36 77	71.44 61	96.76 25	80.82 105	95.33 33	94.16 54
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		83.01 116	82.36 117	84.96 101	91.02 91	66.40 184	88.91 121	88.11 239	77.57 49	84.39 89	93.29 78	52.19 284	93.91 146	77.05 145	88.70 145	94.57 36

test_fmvsmvis_n_1920		84.02 89	83.87 91	84.49 120	84.12 313	69.37 104	88.15 157	87.96 246	70.01 243	83.95 100	93.23 79	68.80 97	91.51 260	88.61 29	89.96 122	92.57 137

UA-Net		85.08 78	84.96 78	85.45 84	92.07 75	68.07 141	89.78 85	90.86 142	82.48 2	84.60 85	93.20 80	69.35 86	95.22 84	71.39 210	90.88 107	93.07 117

TEST9					93.26 52	72.96 25	88.75 131	91.89 106	68.44 283	85.00 73	93.10 81	74.36 29	95.41 76

train_agg		86.43 46	86.20 50	87.13 45	93.26 52	72.96 25	88.75 131	91.89 106	68.69 278	85.00 73	93.10 81	74.43 27	95.41 76	84.97 56	95.71 25	93.02 122

test_8					93.13 56	72.57 35	88.68 136	91.84 110	68.69 278	84.87 77	93.10 81	74.43 27	95.16 86

LFMVS		81.82 133	81.23 133	83.57 169	91.89 78	63.43 262	89.84 81	81.85 350	77.04 69	83.21 110	93.10 81	52.26 283	93.43 171	71.98 205	89.95 123	93.85 71

旧先验1					91.96 76	65.79 199		86.37 283			93.08 85	69.31 88			92.74 76	88.74 295

dcpmvs_2		85.63 64	86.15 54	84.06 147	91.71 80	64.94 222	86.47 215	91.87 108	73.63 157	86.60 60	93.02 86	76.57 15	91.87 243	83.36 77	92.15 83	95.35 3

testdata				79.97 274	90.90 94	64.21 238		84.71 304	59.27 386	85.40 68	92.91 87	62.02 178	89.08 314	68.95 238	91.37 98	86.63 347

MCST-MVS		87.37 31	87.25 32	87.73 28	94.53 17	72.46 40	89.82 82	93.82 17	73.07 174	84.86 78	92.89 88	76.22 17	96.33 41	84.89 59	95.13 36	94.40 44

Vis-MVSNet		83.46 103	82.80 110	85.43 85	90.25 108	68.74 117	90.30 75	90.13 166	76.33 91	80.87 145	92.89 88	61.00 200	94.20 130	72.45 202	90.97 104	93.35 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CPTT-MVS		83.73 94	83.33 101	84.92 105	93.28 49	70.86 74	92.09 37	90.38 154	68.75 277	79.57 163	92.83 90	60.60 209	93.04 197	80.92 104	91.56 95	90.86 204

3Dnovator	76.31 5	83.38 106	82.31 118	86.59 57	87.94 204	72.94 28	90.64 63	92.14 97	77.21 62	75.47 256	92.83 90	58.56 225	94.72 110	73.24 189	92.71 77	92.13 164

MSLP-MVS++		85.43 69	85.76 63	84.45 121	91.93 77	70.24 81	90.71 62	92.86 59	77.46 55	84.22 93	92.81 92	67.16 115	92.94 199	80.36 111	94.35 59	90.16 234

test2506		77.30 255	76.49 252	79.74 279	90.08 112	52.02 400	87.86 169	63.10 443	74.88 124	80.16 157	92.79 93	38.29 407	92.35 224	68.74 241	92.50 80	94.86 19

ECVR-MVS		79.61 189	79.26 182	80.67 259	90.08 112	54.69 383	87.89 167	77.44 396	74.88 124	80.27 154	92.79 93	48.96 333	92.45 218	68.55 242	92.50 80	94.86 19

test1111		79.43 196	79.18 185	80.15 271	89.99 117	53.31 396	87.33 185	77.05 400	75.04 118	80.23 156	92.77 95	48.97 332	92.33 226	68.87 239	92.40 82	94.81 22

MG-MVS		83.41 104	83.45 97	83.28 177	92.74 67	62.28 284	88.17 155	89.50 187	75.22 112	81.49 134	92.74 96	66.75 116	95.11 90	72.85 192	91.58 94	92.45 146

casdiffmvs_mvg		85.99 54	86.09 56	85.70 77	87.65 220	67.22 173	88.69 135	93.04 42	79.64 21	85.33 69	92.54 97	73.30 36	94.50 119	83.49 76	91.14 101	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 96	84.54 83	80.99 251	90.06 116	65.83 196	84.21 280	88.74 228	71.60 198	85.01 72	92.44 98	74.51 26	83.50 377	82.15 93	92.15 83	93.64 89

casdiffmvs		85.11 77	85.14 76	85.01 99	87.20 235	65.77 200	87.75 171	92.83 61	77.84 43	84.36 92	92.38 99	72.15 50	93.93 144	81.27 101	90.48 112	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 86	92.27 100	71.47 60	95.02 96	84.24 70	93.46 69	95.13 9

baseline		84.93 80	84.98 77	84.80 111	87.30 233	65.39 209	87.30 186	92.88 58	77.62 47	84.04 98	92.26 101	71.81 54	93.96 138	81.31 99	90.30 115	95.03 11

NormalMVS		86.29 50	85.88 59	87.52 37	93.26 52	72.47 38	91.65 43	92.19 92	79.31 24	84.39 89	92.18 102	64.64 143	95.53 67	80.70 108	94.65 48	94.56 37

SymmetryMVS		85.38 72	84.81 80	87.07 46	91.47 83	72.47 38	91.65 43	88.06 243	79.31 24	84.39 89	92.18 102	64.64 143	95.53 67	80.70 108	90.91 106	93.21 109

QAPM		80.88 154	79.50 175	85.03 98	88.01 202	68.97 110	91.59 46	92.00 100	66.63 307	75.15 274	92.16 104	57.70 232	95.45 71	63.52 281	88.76 143	90.66 213

IS-MVSNet		83.15 111	82.81 109	84.18 137	89.94 119	63.30 264	91.59 46	88.46 236	79.04 30	79.49 164	92.16 104	65.10 138	94.28 125	67.71 248	91.86 90	94.95 12

BP-MVS1		84.32 85	83.71 94	86.17 64	87.84 209	67.85 150	89.38 102	89.64 182	77.73 45	83.98 99	92.12 106	56.89 243	95.43 73	84.03 73	91.75 91	95.24 7

新几何1				83.42 172	93.13 56	70.71 76		85.48 296	57.43 404	81.80 130	91.98 107	63.28 153	92.27 227	64.60 276	92.99 72	87.27 329

OpenMVS	72.83 10	79.77 187	78.33 203	84.09 143	85.17 288	69.91 89	90.57 64	90.97 137	66.70 301	72.17 319	91.91 108	54.70 260	93.96 138	61.81 302	90.95 105	88.41 304

PHI-MVS		86.43 46	86.17 53	87.24 42	90.88 95	70.96 70	92.27 33	94.07 10	72.45 182	85.22 71	91.90 109	69.47 85	96.42 40	83.28 79	95.94 19	94.35 47

VNet		82.21 124	82.41 115	81.62 231	90.82 96	60.93 300	84.47 271	89.78 175	76.36 90	84.07 97	91.88 110	64.71 142	90.26 290	70.68 217	88.89 139	93.66 83

EC-MVSNet		86.01 53	86.38 46	84.91 106	89.31 143	66.27 187	92.32 31	93.63 22	79.37 23	84.17 95	91.88 110	69.04 94	95.43 73	83.93 74	93.77 65	93.01 123

GDP-MVS		83.52 101	82.64 112	86.16 65	88.14 193	68.45 128	89.13 114	92.69 66	72.82 180	83.71 104	91.86 112	55.69 250	95.35 82	80.03 114	89.74 127	94.69 28

KinetiMVS		83.31 109	82.61 113	85.39 86	87.08 243	67.56 160	88.06 159	91.65 116	77.80 44	82.21 123	91.79 113	57.27 238	94.07 136	77.77 136	89.89 125	94.56 37

OPM-MVS		83.50 102	82.95 107	85.14 92	88.79 168	70.95 71	89.13 114	91.52 121	77.55 52	80.96 144	91.75 114	60.71 203	94.50 119	79.67 119	86.51 179	89.97 250
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MVSMamba_PlusPlus		85.99 54	85.96 58	86.05 69	91.09 88	67.64 156	89.63 91	92.65 71	72.89 179	84.64 83	91.71 115	71.85 53	96.03 51	84.77 62	94.45 56	94.49 40

XVG-OURS-SEG-HR		80.81 157	79.76 168	83.96 157	85.60 277	68.78 114	83.54 296	90.50 150	70.66 225	76.71 229	91.66 116	60.69 204	91.26 269	76.94 146	81.58 261	91.83 169

EPNet		83.72 95	82.92 108	86.14 68	84.22 311	69.48 97	91.05 59	85.27 297	81.30 6	76.83 225	91.65 117	66.09 128	95.56 64	76.00 158	93.85 64	93.38 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		82.69 118	81.97 126	84.85 108	88.75 170	67.42 163	87.98 161	90.87 141	74.92 123	79.72 161	91.65 117	62.19 175	93.96 138	75.26 168	86.42 180	93.16 113

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 50	91.63 119	71.27 64	96.06 50	85.62 53	95.01 37	94.78 24

test222					91.50 82	68.26 133	84.16 281	83.20 331	54.63 415	79.74 160	91.63 119	58.97 221			91.42 96	86.77 343

MVS_111021_HR		85.14 76	84.75 81	86.32 61	91.65 81	72.70 30	85.98 229	90.33 158	76.11 94	82.08 125	91.61 121	71.36 63	94.17 133	81.02 102	92.58 78	92.08 165

原ACMM1				84.35 125	93.01 62	68.79 113		92.44 78	63.96 343	81.09 141	91.57 122	66.06 129	95.45 71	67.19 255	94.82 46	88.81 290

LPG-MVS_test		82.08 126	81.27 132	84.50 118	89.23 148	68.76 115	90.22 76	91.94 104	75.37 109	76.64 231	91.51 123	54.29 263	94.91 98	78.44 127	83.78 225	89.83 255

LGP-MVS_train				84.50 118	89.23 148	68.76 115		91.94 104	75.37 109	76.64 231	91.51 123	54.29 263	94.91 98	78.44 127	83.78 225	89.83 255

XVG-OURS		80.41 174	79.23 183	83.97 156	85.64 275	69.02 108	83.03 309	90.39 153	71.09 210	77.63 207	91.49 125	54.62 262	91.35 266	75.71 160	83.47 237	91.54 180

alignmvs		85.48 67	85.32 73	85.96 73	89.51 130	69.47 98	89.74 86	92.47 77	76.17 93	87.73 46	91.46 126	70.32 75	93.78 152	81.51 96	88.95 138	94.63 33

CANet		86.45 45	86.10 55	87.51 38	90.09 111	70.94 72	89.70 88	92.59 75	81.78 4	81.32 136	91.43 127	70.34 74	97.23 14	84.26 68	93.36 70	94.37 46

h-mvs33		83.15 111	82.19 119	86.02 72	90.56 101	70.85 75	88.15 157	89.16 207	76.02 96	84.67 80	91.39 128	61.54 186	95.50 69	82.71 88	75.48 341	91.72 176

MGCFI-Net		85.06 79	85.51 68	83.70 164	89.42 135	63.01 270	89.43 97	92.62 74	76.43 84	87.53 47	91.34 129	72.82 45	93.42 172	81.28 100	88.74 144	94.66 32

nrg030		83.88 90	83.53 96	84.96 101	86.77 250	69.28 105	90.46 70	92.67 68	74.79 127	82.95 113	91.33 130	72.70 46	93.09 192	80.79 107	79.28 291	92.50 142

sasdasda		85.91 58	85.87 61	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 39	91.23 131	73.28 37	93.91 146	81.50 97	88.80 141	94.77 25

canonicalmvs		85.91 58	85.87 61	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 39	91.23 131	73.28 37	93.91 146	81.50 97	88.80 141	94.77 25

DPM-MVS		84.93 80	84.29 87	86.84 52	90.20 109	73.04 23	87.12 190	93.04 42	69.80 249	82.85 116	91.22 133	73.06 41	96.02 53	76.72 152	94.63 50	91.46 186

Anonymous202405211		78.25 227	77.01 238	81.99 225	91.03 90	60.67 305	84.77 262	83.90 317	70.65 226	80.00 158	91.20 134	41.08 392	91.43 264	65.21 270	85.26 203	93.85 71

SPE-MVS-test		86.29 50	86.48 45	85.71 76	91.02 91	67.21 174	92.36 30	93.78 19	78.97 33	83.51 109	91.20 134	70.65 73	95.15 87	81.96 94	94.89 42	94.77 25

Anonymous20240529		80.19 182	78.89 191	84.10 139	90.60 100	64.75 227	88.95 120	90.90 139	65.97 315	80.59 150	91.17 136	49.97 317	93.73 158	69.16 236	82.70 250	93.81 75

EPP-MVSNet		83.40 105	83.02 105	84.57 116	90.13 110	64.47 233	92.32 31	90.73 144	74.45 136	79.35 169	91.10 137	69.05 93	95.12 88	72.78 193	87.22 166	94.13 56

TAPA-MVS	73.13 9	79.15 205	77.94 211	82.79 207	89.59 126	62.99 274	88.16 156	91.51 122	65.77 316	77.14 222	91.09 138	60.91 201	93.21 181	50.26 389	87.05 169	92.17 162
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CSCG		86.41 48	86.19 52	87.07 46	92.91 63	72.48 37	90.81 61	93.56 25	73.95 148	83.16 112	91.07 139	75.94 18	95.19 85	79.94 116	94.38 58	93.55 94

FIs		82.07 127	82.42 114	81.04 250	88.80 167	58.34 329	88.26 152	93.49 27	76.93 71	78.47 187	91.04 140	69.92 80	92.34 225	69.87 229	84.97 205	92.44 147

MVS_111021_LR		82.61 120	82.11 120	84.11 138	88.82 162	71.58 57	85.15 253	86.16 287	74.69 129	80.47 153	91.04 140	62.29 172	90.55 288	80.33 112	90.08 120	90.20 233

DP-MVS Recon		83.11 114	82.09 122	86.15 66	94.44 19	70.92 73	88.79 128	92.20 91	70.53 227	79.17 171	91.03 142	64.12 147	96.03 51	68.39 245	90.14 118	91.50 182

mamv4		76.81 263	78.23 207	72.54 380	86.12 265	65.75 201	78.76 365	82.07 347	64.12 337	72.97 307	91.02 143	67.97 105	68.08 445	83.04 82	78.02 303	83.80 391

HQP_MVS		83.64 97	83.14 102	85.14 92	90.08 112	68.71 119	91.25 55	92.44 78	79.12 28	78.92 175	91.00 144	60.42 211	95.38 78	78.71 125	86.32 181	91.33 187

plane_prior4											91.00 144

FC-MVSNet-test		81.52 143	82.02 124	80.03 273	88.42 183	55.97 368	87.95 163	93.42 30	77.10 67	77.38 211	90.98 146	69.96 79	91.79 244	68.46 244	84.50 212	92.33 150

Vis-MVSNet (Re-imp)		78.36 226	78.45 198	78.07 315	88.64 174	51.78 406	86.70 208	79.63 378	74.14 145	75.11 275	90.83 147	61.29 194	89.75 300	58.10 337	91.60 92	92.69 134

114514_t		80.68 165	79.51 174	84.20 136	94.09 38	67.27 170	89.64 90	91.11 135	58.75 393	74.08 293	90.72 148	58.10 228	95.04 95	69.70 230	89.42 133	90.30 230

PAPM_NR		83.02 115	82.41 115	84.82 109	92.47 72	66.37 185	87.93 165	91.80 111	73.82 152	77.32 213	90.66 149	67.90 107	94.90 100	70.37 220	89.48 132	93.19 112

LS3D		76.95 261	74.82 279	83.37 175	90.45 103	67.36 167	89.15 113	86.94 272	61.87 366	69.52 349	90.61 150	51.71 297	94.53 117	46.38 411	86.71 176	88.21 308

AstraMVS		80.81 157	80.14 158	82.80 204	86.05 268	63.96 242	86.46 216	85.90 291	73.71 155	80.85 146	90.56 151	54.06 267	91.57 254	79.72 118	83.97 223	92.86 128

VPNet		78.69 218	78.66 194	78.76 298	88.31 186	55.72 372	84.45 274	86.63 278	76.79 75	78.26 191	90.55 152	59.30 219	89.70 302	66.63 259	77.05 314	90.88 203

UniMVSNet_ETH3D		79.10 207	78.24 205	81.70 230	86.85 247	60.24 312	87.28 187	88.79 223	74.25 142	76.84 224	90.53 153	49.48 323	91.56 255	67.98 246	82.15 254	93.29 104

ACMP	74.13 6	81.51 145	80.57 145	84.36 124	89.42 135	68.69 122	89.97 80	91.50 125	74.46 135	75.04 278	90.41 154	53.82 269	94.54 116	77.56 138	82.91 245	89.86 254
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
mamba_test_0407		81.58 140	80.48 148	84.87 107	88.81 163	67.96 145	87.37 182	89.25 202	71.06 212	79.48 165	90.39 155	59.57 216	94.48 121	72.45 202	85.93 191	92.18 159

mamba_0404		81.91 130	80.84 141	85.13 95	89.24 147	68.26 133	87.84 170	89.25 202	71.06 212	80.62 149	90.39 155	59.57 216	94.65 114	72.45 202	87.19 167	92.47 145

viewmambaseed2359dif		80.41 174	79.84 166	82.12 220	82.95 346	62.50 280	83.39 297	88.06 243	67.11 296	80.98 143	90.31 157	66.20 126	91.01 279	74.62 172	84.90 206	92.86 128

RRT-MVS		82.60 122	82.10 121	84.10 139	87.98 203	62.94 275	87.45 180	91.27 128	77.42 56	79.85 159	90.28 158	56.62 246	94.70 112	79.87 117	88.15 154	94.67 29

PCF-MVS	73.52 7	80.38 176	78.84 192	85.01 99	87.71 217	68.99 109	83.65 290	91.46 126	63.00 350	77.77 205	90.28 158	66.10 127	95.09 94	61.40 305	88.22 153	90.94 202
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					90.24 160

HQP-MVS		82.61 120	82.02 124	84.37 123	89.33 140	66.98 177	89.17 109	92.19 92	76.41 85	77.23 216	90.23 161	60.17 214	95.11 90	77.47 139	85.99 189	91.03 197

PS-MVSNAJss		82.07 127	81.31 131	84.34 126	86.51 257	67.27 170	89.27 105	91.51 122	71.75 193	79.37 168	90.22 162	63.15 159	94.27 126	77.69 137	82.36 253	91.49 183

TSAR-MVS + GP.		85.71 63	85.33 72	86.84 52	91.34 84	72.50 36	89.07 117	87.28 263	76.41 85	85.80 64	90.22 162	74.15 32	95.37 81	81.82 95	91.88 87	92.65 136

SDMVSNet		80.38 176	80.18 155	80.99 251	89.03 157	64.94 222	80.45 341	89.40 189	75.19 115	76.61 233	89.98 164	60.61 208	87.69 336	76.83 150	83.55 234	90.33 228

sd_testset		77.70 246	77.40 231	78.60 301	89.03 157	60.02 314	79.00 361	85.83 292	75.19 115	76.61 233	89.98 164	54.81 255	85.46 361	62.63 292	83.55 234	90.33 228

TranMVSNet+NR-MVSNet		80.84 155	80.31 152	82.42 217	87.85 208	62.33 282	87.74 172	91.33 127	80.55 9	77.99 199	89.86 166	65.23 137	92.62 207	67.05 257	75.24 351	92.30 152

diffmvs		82.10 125	81.88 127	82.76 210	83.00 342	63.78 248	83.68 289	89.76 177	72.94 177	82.02 126	89.85 167	65.96 132	90.79 283	82.38 92	87.30 165	93.71 81
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		81.53 141	80.16 156	85.62 79	85.51 279	68.25 135	88.84 126	92.19 92	71.31 203	80.50 151	89.83 168	46.89 344	94.82 104	76.85 147	89.57 129	93.80 77

StellarMVS		81.53 141	80.16 156	85.62 79	85.51 279	68.25 135	88.84 126	92.19 92	71.31 203	80.50 151	89.83 168	46.89 344	94.82 104	76.85 147	89.57 129	93.80 77

mamba_0408		79.37 201	77.52 228	84.93 104	88.81 163	67.96 145	65.03 440	88.66 230	70.96 216	79.48 165	89.80 170	58.69 222	94.65 114	70.35 221	85.93 191	92.18 159

mamba_test_0407_2		77.67 248	77.52 228	78.12 313	88.81 163	67.96 145	65.03 440	88.66 230	70.96 216	79.48 165	89.80 170	58.69 222	74.23 433	70.35 221	85.93 191	92.18 159

BH-RMVSNet		79.61 189	78.44 199	83.14 185	89.38 139	65.93 193	84.95 259	87.15 268	73.56 160	78.19 193	89.79 172	56.67 245	93.36 173	59.53 321	86.74 175	90.13 236

GeoE		81.71 135	81.01 138	83.80 163	89.51 130	64.45 234	88.97 119	88.73 229	71.27 206	78.63 181	89.76 173	66.32 124	93.20 184	69.89 228	86.02 188	93.74 80

guyue		81.13 150	80.64 144	82.60 214	86.52 256	63.92 245	86.69 209	87.73 254	73.97 147	80.83 147	89.69 174	56.70 244	91.33 268	78.26 134	85.40 202	92.54 139

AdaColmap		80.58 172	79.42 176	84.06 147	93.09 59	68.91 111	89.36 103	88.97 218	69.27 261	75.70 252	89.69 174	57.20 240	95.77 60	63.06 286	88.41 151	87.50 323

ACMM	73.20 8	80.78 164	79.84 166	83.58 168	89.31 143	68.37 130	89.99 79	91.60 119	70.28 237	77.25 214	89.66 176	53.37 274	93.53 165	74.24 178	82.85 246	88.85 288
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		78.08 233	76.79 245	81.97 226	90.40 105	71.07 67	87.59 175	84.55 307	66.03 314	72.38 316	89.64 177	57.56 234	86.04 353	59.61 320	83.35 239	88.79 291

test_yl		81.17 148	80.47 149	83.24 180	89.13 152	63.62 249	86.21 224	89.95 171	72.43 185	81.78 131	89.61 178	57.50 235	93.58 160	70.75 215	86.90 171	92.52 140

DCV-MVSNet		81.17 148	80.47 149	83.24 180	89.13 152	63.62 249	86.21 224	89.95 171	72.43 185	81.78 131	89.61 178	57.50 235	93.58 160	70.75 215	86.90 171	92.52 140

EI-MVSNet-Vis-set		84.19 86	83.81 92	85.31 88	88.18 190	67.85 150	87.66 173	89.73 179	80.05 15	82.95 113	89.59 180	70.74 71	94.82 104	80.66 110	84.72 209	93.28 105

PAPR		81.66 138	80.89 140	83.99 155	90.27 107	64.00 241	86.76 207	91.77 114	68.84 276	77.13 223	89.50 181	67.63 109	94.88 102	67.55 250	88.52 148	93.09 116

jajsoiax		79.29 202	77.96 210	83.27 178	84.68 302	66.57 183	89.25 106	90.16 165	69.20 266	75.46 258	89.49 182	45.75 360	93.13 190	76.84 149	80.80 271	90.11 238

MVSFormer		82.85 117	82.05 123	85.24 90	87.35 226	70.21 82	90.50 67	90.38 154	68.55 280	81.32 136	89.47 183	61.68 183	93.46 169	78.98 122	90.26 116	92.05 166

jason		81.39 146	80.29 153	84.70 114	86.63 255	69.90 90	85.95 230	86.77 276	63.24 346	81.07 142	89.47 183	61.08 199	92.15 231	78.33 130	90.07 121	92.05 166
jason: jason.
mvs_tets		79.13 206	77.77 220	83.22 182	84.70 301	66.37 185	89.17 109	90.19 164	69.38 258	75.40 261	89.46 185	44.17 372	93.15 188	76.78 151	80.70 273	90.14 235

UGNet		80.83 156	79.59 173	84.54 117	88.04 199	68.09 140	89.42 99	88.16 238	76.95 70	76.22 242	89.46 185	49.30 327	93.94 141	68.48 243	90.31 114	91.60 177
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		80.60 169	80.55 146	80.76 257	88.07 198	60.80 303	86.86 201	91.58 120	75.67 103	80.24 155	89.45 187	63.34 152	90.25 291	70.51 219	79.22 292	91.23 190

MVS_Test		83.15 111	83.06 104	83.41 174	86.86 246	63.21 266	86.11 227	92.00 100	74.31 139	82.87 115	89.44 188	70.03 78	93.21 181	77.39 141	88.50 149	93.81 75

EI-MVSNet-UG-set		83.81 91	83.38 99	85.09 97	87.87 207	67.53 161	87.44 181	89.66 180	79.74 18	82.23 122	89.41 189	70.24 77	94.74 109	79.95 115	83.92 224	92.99 125

RPSCF		73.23 317	71.46 321	78.54 304	82.50 355	59.85 315	82.18 315	82.84 340	58.96 389	71.15 331	89.41 189	45.48 364	84.77 368	58.82 329	71.83 381	91.02 199

UniMVSNet_NR-MVSNet		81.88 131	81.54 130	82.92 197	88.46 180	63.46 260	87.13 189	92.37 82	80.19 12	78.38 188	89.14 191	71.66 59	93.05 195	70.05 225	76.46 324	92.25 154

tttt0517		79.40 198	77.91 212	83.90 159	88.10 196	63.84 246	88.37 148	84.05 315	71.45 201	76.78 227	89.12 192	49.93 320	94.89 101	70.18 224	83.18 243	92.96 126

DU-MVS		81.12 151	80.52 147	82.90 198	87.80 211	63.46 260	87.02 194	91.87 108	79.01 31	78.38 188	89.07 193	65.02 139	93.05 195	70.05 225	76.46 324	92.20 157

NR-MVSNet		80.23 180	79.38 177	82.78 208	87.80 211	63.34 263	86.31 221	91.09 136	79.01 31	72.17 319	89.07 193	67.20 114	92.81 205	66.08 264	75.65 337	92.20 157

icg_test_0407_2		78.92 213	78.93 190	78.90 296	87.13 238	63.59 253	76.58 387	89.33 192	70.51 228	77.82 201	89.03 195	61.84 179	81.38 392	72.56 198	85.56 198	91.74 172

icg_test_0407		80.61 167	79.90 164	82.75 211	87.13 238	63.59 253	85.33 249	89.33 192	70.51 228	77.82 201	89.03 195	61.84 179	92.91 200	72.56 198	85.56 198	91.74 172

ICG_test_0404		77.16 257	76.42 255	79.37 287	87.13 238	63.59 253	77.12 385	89.33 192	70.51 228	66.22 388	89.03 195	50.36 312	82.78 382	72.56 198	85.56 198	91.74 172

icg_test_0403		80.80 160	80.12 159	82.87 200	87.13 238	63.59 253	85.19 250	89.33 192	70.51 228	78.49 185	89.03 195	63.26 155	93.27 176	72.56 198	85.56 198	91.74 172

DELS-MVS		85.41 70	85.30 74	85.77 75	88.49 178	67.93 148	85.52 247	93.44 28	78.70 34	83.63 108	89.03 195	74.57 24	95.71 62	80.26 113	94.04 63	93.66 83
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		80.60 169	79.38 177	84.27 132	89.74 124	67.24 172	87.47 178	86.95 271	70.02 242	75.38 262	88.93 200	51.24 301	92.56 212	75.47 166	89.22 135	93.00 124

baseline1		76.98 260	76.75 248	77.66 322	88.13 194	55.66 373	85.12 254	81.89 348	73.04 175	76.79 226	88.90 201	62.43 170	87.78 335	63.30 285	71.18 385	89.55 264

DP-MVS		76.78 264	74.57 282	83.42 172	93.29 48	69.46 100	88.55 141	83.70 319	63.98 342	70.20 337	88.89 202	54.01 268	94.80 107	46.66 408	81.88 259	86.01 357

ab-mvs		79.51 192	78.97 189	81.14 247	88.46 180	60.91 301	83.84 285	89.24 204	70.36 233	79.03 172	88.87 203	63.23 157	90.21 292	65.12 271	82.57 251	92.28 153

PEN-MVS		77.73 243	77.69 224	77.84 319	87.07 245	53.91 390	87.91 166	91.18 131	77.56 51	73.14 305	88.82 204	61.23 195	89.17 312	59.95 316	72.37 375	90.43 223

tt0805		78.73 216	77.83 216	81.43 236	85.17 288	60.30 311	89.41 100	90.90 139	71.21 207	77.17 221	88.73 205	46.38 349	93.21 181	72.57 196	78.96 293	90.79 206

test_djsdf		80.30 179	79.32 180	83.27 178	83.98 317	65.37 210	90.50 67	90.38 154	68.55 280	76.19 243	88.70 206	56.44 247	93.46 169	78.98 122	80.14 281	90.97 200

PAPM		77.68 247	76.40 256	81.51 234	87.29 234	61.85 289	83.78 286	89.59 184	64.74 329	71.23 329	88.70 206	62.59 166	93.66 159	52.66 373	87.03 170	89.01 280

DTE-MVSNet		76.99 259	76.80 244	77.54 327	86.24 260	53.06 399	87.52 176	90.66 145	77.08 68	72.50 313	88.67 208	60.48 210	89.52 304	57.33 344	70.74 387	90.05 245

PS-CasMVS		78.01 237	78.09 208	77.77 321	87.71 217	54.39 387	88.02 160	91.22 129	77.50 54	73.26 303	88.64 209	60.73 202	88.41 327	61.88 300	73.88 364	90.53 219

cdsmvs_eth3d_5k		19.96 425	26.61 427	0.00 445	0.00 468	0.00 470	0.00 456	89.26 201	0.00 463	0.00 464	88.61 210	61.62 185	0.00 464	0.00 463	0.00 462	0.00 460

lupinMVS		81.39 146	80.27 154	84.76 112	87.35 226	70.21 82	85.55 243	86.41 281	62.85 353	81.32 136	88.61 210	61.68 183	92.24 229	78.41 129	90.26 116	91.83 169

F-COLMAP		76.38 274	74.33 288	82.50 216	89.28 145	66.95 180	88.41 144	89.03 213	64.05 340	66.83 377	88.61 210	46.78 346	92.89 201	57.48 341	78.55 295	87.67 317

mvs_anonymous		79.42 197	79.11 186	80.34 266	84.45 308	57.97 335	82.59 311	87.62 256	67.40 295	76.17 246	88.56 213	68.47 100	89.59 303	70.65 218	86.05 187	93.47 97

CP-MVSNet		78.22 228	78.34 202	77.84 319	87.83 210	54.54 385	87.94 164	91.17 132	77.65 46	73.48 301	88.49 214	62.24 174	88.43 326	62.19 296	74.07 360	90.55 218

PVSNet_Blended_VisFu		82.62 119	81.83 128	84.96 101	90.80 97	69.76 93	88.74 133	91.70 115	69.39 257	78.96 173	88.46 215	65.47 135	94.87 103	74.42 175	88.57 146	90.24 232

CANet_DTU		80.61 167	79.87 165	82.83 201	85.60 277	63.17 269	87.36 183	88.65 232	76.37 89	75.88 249	88.44 216	53.51 272	93.07 193	73.30 187	89.74 127	92.25 154

PLC	70.83 11	78.05 235	76.37 257	83.08 189	91.88 79	67.80 152	88.19 154	89.46 188	64.33 335	69.87 346	88.38 217	53.66 270	93.58 160	58.86 328	82.73 248	87.86 314
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
WR-MVS		79.49 193	79.22 184	80.27 268	88.79 168	58.35 328	85.06 256	88.61 234	78.56 35	77.65 206	88.34 218	63.81 151	90.66 287	64.98 273	77.22 312	91.80 171

XXY-MVS		75.41 288	75.56 266	74.96 353	83.59 326	57.82 339	80.59 338	83.87 318	66.54 308	74.93 281	88.31 219	63.24 156	80.09 398	62.16 297	76.85 318	86.97 339

Effi-MVS+		83.62 99	83.08 103	85.24 90	88.38 184	67.45 162	88.89 122	89.15 208	75.50 105	82.27 121	88.28 220	69.61 84	94.45 122	77.81 135	87.84 156	93.84 73

API-MVS		81.99 129	81.23 133	84.26 134	90.94 93	70.18 87	91.10 58	89.32 196	71.51 200	78.66 180	88.28 220	65.26 136	95.10 93	64.74 275	91.23 100	87.51 322

thisisatest0530		79.40 198	77.76 221	84.31 127	87.69 219	65.10 218	87.36 183	84.26 313	70.04 241	77.42 210	88.26 222	49.94 318	94.79 108	70.20 223	84.70 210	93.03 121

hse-mvs2		81.72 134	80.94 139	84.07 145	88.72 171	67.68 155	85.87 233	87.26 265	76.02 96	84.67 80	88.22 223	61.54 186	93.48 167	82.71 88	73.44 369	91.06 195

xiu_mvs_v1_base_debu		80.80 160	79.72 169	84.03 152	87.35 226	70.19 84	85.56 240	88.77 224	69.06 270	81.83 127	88.16 224	50.91 304	92.85 202	78.29 131	87.56 159	89.06 275

xiu_mvs_v1_base		80.80 160	79.72 169	84.03 152	87.35 226	70.19 84	85.56 240	88.77 224	69.06 270	81.83 127	88.16 224	50.91 304	92.85 202	78.29 131	87.56 159	89.06 275

xiu_mvs_v1_base_debi		80.80 160	79.72 169	84.03 152	87.35 226	70.19 84	85.56 240	88.77 224	69.06 270	81.83 127	88.16 224	50.91 304	92.85 202	78.29 131	87.56 159	89.06 275

UniMVSNet (Re)		81.60 139	81.11 135	83.09 187	88.38 184	64.41 235	87.60 174	93.02 46	78.42 37	78.56 183	88.16 224	69.78 81	93.26 177	69.58 232	76.49 323	91.60 177

AUN-MVS		79.21 204	77.60 226	84.05 150	88.71 172	67.61 157	85.84 235	87.26 265	69.08 269	77.23 216	88.14 228	53.20 276	93.47 168	75.50 165	73.45 368	91.06 195

Anonymous20231211		78.97 211	77.69 224	82.81 203	90.54 102	64.29 237	90.11 78	91.51 122	65.01 327	76.16 247	88.13 229	50.56 309	93.03 198	69.68 231	77.56 310	91.11 193

pm-mvs1		77.25 256	76.68 250	78.93 295	84.22 311	58.62 326	86.41 217	88.36 237	71.37 202	73.31 302	88.01 230	61.22 196	89.15 313	64.24 279	73.01 372	89.03 279

LuminaMVS		80.68 165	79.62 172	83.83 160	85.07 294	68.01 144	86.99 195	88.83 221	70.36 233	81.38 135	87.99 231	50.11 315	92.51 216	79.02 120	86.89 173	90.97 200

SD_0403		74.65 296	74.77 280	74.29 362	86.20 262	47.42 425	83.71 288	85.12 299	69.30 260	68.50 360	87.95 232	59.40 218	86.05 352	49.38 393	83.35 239	89.40 267

LTVRE_ROB	69.57 13	76.25 275	74.54 284	81.41 237	88.60 175	64.38 236	79.24 356	89.12 211	70.76 221	69.79 348	87.86 233	49.09 330	93.20 184	56.21 356	80.16 279	86.65 346
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		75.12 293	75.19 275	74.91 354	90.40 105	45.09 436	80.29 344	78.42 388	78.37 40	76.54 235	87.75 234	44.36 370	87.28 341	57.04 347	83.49 236	92.37 148

WTY-MVS		75.65 283	75.68 263	75.57 344	86.40 258	56.82 353	77.92 379	82.40 343	65.10 324	76.18 244	87.72 235	63.13 162	80.90 395	60.31 314	81.96 257	89.00 282

TAMVS		78.89 214	77.51 230	83.03 192	87.80 211	67.79 153	84.72 263	85.05 302	67.63 290	76.75 228	87.70 236	62.25 173	90.82 282	58.53 332	87.13 168	90.49 221

BH-untuned		79.47 194	78.60 195	82.05 223	89.19 150	65.91 194	86.07 228	88.52 235	72.18 187	75.42 260	87.69 237	61.15 197	93.54 164	60.38 313	86.83 174	86.70 345

COLMAP_ROB	66.92 17	73.01 320	70.41 335	80.81 256	87.13 238	65.63 202	88.30 151	84.19 314	62.96 351	63.80 405	87.69 237	38.04 408	92.56 212	46.66 408	74.91 354	84.24 384
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		74.26 299	72.42 312	79.80 278	83.76 323	59.59 319	85.92 232	86.64 277	66.39 309	66.96 375	87.58 239	39.46 398	91.60 251	65.76 267	69.27 393	88.22 307

FA-MVS(test-final)		80.96 153	79.91 163	84.10 139	88.30 187	65.01 219	84.55 270	90.01 169	73.25 171	79.61 162	87.57 240	58.35 227	94.72 110	71.29 211	86.25 183	92.56 138

Baseline_NR-MVSNet		78.15 232	78.33 203	77.61 324	85.79 271	56.21 366	86.78 205	85.76 293	73.60 159	77.93 200	87.57 240	65.02 139	88.99 315	67.14 256	75.33 348	87.63 318

WR-MVS_H		78.51 223	78.49 197	78.56 303	88.02 200	56.38 362	88.43 143	92.67 68	77.14 64	73.89 295	87.55 242	66.25 125	89.24 310	58.92 327	73.55 367	90.06 244

EI-MVSNet		80.52 173	79.98 161	82.12 220	84.28 309	63.19 268	86.41 217	88.95 219	74.18 144	78.69 178	87.54 243	66.62 118	92.43 219	72.57 196	80.57 275	90.74 210

CVMVSNet		72.99 321	72.58 310	74.25 363	84.28 309	50.85 414	86.41 217	83.45 325	44.56 434	73.23 304	87.54 243	49.38 325	85.70 356	65.90 265	78.44 298	86.19 352

ACMH+	68.96 14	76.01 279	74.01 290	82.03 224	88.60 175	65.31 211	88.86 123	87.55 257	70.25 239	67.75 364	87.47 245	41.27 390	93.19 186	58.37 334	75.94 334	87.60 319

TransMVSNet (Re)		75.39 290	74.56 283	77.86 318	85.50 281	57.10 350	86.78 205	86.09 289	72.17 188	71.53 326	87.34 246	63.01 163	89.31 308	56.84 350	61.83 416	87.17 331

GBi-Net		78.40 224	77.40 231	81.40 238	87.60 221	63.01 270	88.39 145	89.28 198	71.63 195	75.34 264	87.28 247	54.80 256	91.11 272	62.72 288	79.57 285	90.09 240

test1		78.40 224	77.40 231	81.40 238	87.60 221	63.01 270	88.39 145	89.28 198	71.63 195	75.34 264	87.28 247	54.80 256	91.11 272	62.72 288	79.57 285	90.09 240

FMVSNet2		78.20 230	77.21 235	81.20 245	87.60 221	62.89 276	87.47 178	89.02 214	71.63 195	75.29 270	87.28 247	54.80 256	91.10 275	62.38 293	79.38 289	89.61 262

FMVSNet1		77.44 251	76.12 259	81.40 238	86.81 249	63.01 270	88.39 145	89.28 198	70.49 232	74.39 290	87.28 247	49.06 331	91.11 272	60.91 309	78.52 296	90.09 240

v2v482		80.23 180	79.29 181	83.05 191	83.62 325	64.14 239	87.04 192	89.97 170	73.61 158	78.18 194	87.22 251	61.10 198	93.82 150	76.11 155	76.78 320	91.18 191

ITE_SJBPF				78.22 310	81.77 365	60.57 306		83.30 326	69.25 263	67.54 366	87.20 252	36.33 415	87.28 341	54.34 364	74.62 357	86.80 342

anonymousdsp		78.60 220	77.15 236	82.98 195	80.51 384	67.08 175	87.24 188	89.53 186	65.66 318	75.16 273	87.19 253	52.52 278	92.25 228	77.17 143	79.34 290	89.61 262

MVSTER		79.01 209	77.88 215	82.38 218	83.07 339	64.80 226	84.08 284	88.95 219	69.01 273	78.69 178	87.17 254	54.70 260	92.43 219	74.69 171	80.57 275	89.89 253

thres100view900		76.50 268	75.55 267	79.33 288	89.52 129	56.99 351	85.83 236	83.23 328	73.94 149	76.32 240	87.12 255	51.89 293	91.95 238	48.33 399	83.75 228	89.07 273

thres600view7		76.50 268	75.44 268	79.68 281	89.40 137	57.16 348	85.53 245	83.23 328	73.79 153	76.26 241	87.09 256	51.89 293	91.89 241	48.05 404	83.72 231	90.00 246

XVG-ACMP-BASELINE		76.11 277	74.27 289	81.62 231	83.20 335	64.67 228	83.60 293	89.75 178	69.75 252	71.85 322	87.09 256	32.78 422	92.11 232	69.99 227	80.43 277	88.09 310

HY-MVS	69.67 12	77.95 238	77.15 236	80.36 265	87.57 225	60.21 313	83.37 299	87.78 253	66.11 311	75.37 263	87.06 258	63.27 154	90.48 289	61.38 306	82.43 252	90.40 225

CHOSEN 1792x2688		77.63 249	75.69 262	83.44 171	89.98 118	68.58 125	78.70 366	87.50 259	56.38 409	75.80 251	86.84 259	58.67 224	91.40 265	61.58 304	85.75 196	90.34 227

v8		79.97 186	79.02 188	82.80 204	84.09 314	64.50 232	87.96 162	90.29 161	74.13 146	75.24 271	86.81 260	62.88 164	93.89 149	74.39 176	75.40 346	90.00 246

AllTest		70.96 338	68.09 353	79.58 284	85.15 290	63.62 249	84.58 269	79.83 375	62.31 360	60.32 417	86.73 261	32.02 423	88.96 318	50.28 387	71.57 383	86.15 353

TestCases				79.58 284	85.15 290	63.62 249		79.83 375	62.31 360	60.32 417	86.73 261	32.02 423	88.96 318	50.28 387	71.57 383	86.15 353

LCM-MVSNet-Re		77.05 258	76.94 241	77.36 328	87.20 235	51.60 407	80.06 346	80.46 366	75.20 114	67.69 365	86.72 263	62.48 168	88.98 316	63.44 283	89.25 134	91.51 181

1112_ss		77.40 253	76.43 254	80.32 267	89.11 156	60.41 310	83.65 290	87.72 255	62.13 363	73.05 306	86.72 263	62.58 167	89.97 296	62.11 299	80.80 271	90.59 217

ab-mvs-re		7.23 428	9.64 431	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	86.72 263	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

IterMVS-LS		80.06 183	79.38 177	82.11 222	85.89 269	63.20 267	86.79 204	89.34 191	74.19 143	75.45 259	86.72 263	66.62 118	92.39 221	72.58 195	76.86 317	90.75 209
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	67.68 16	75.89 280	73.93 292	81.77 229	88.71 172	66.61 182	88.62 138	89.01 215	69.81 248	66.78 378	86.70 267	41.95 388	91.51 260	55.64 357	78.14 302	87.17 331
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Test_1112_low_res		76.40 273	75.44 268	79.27 289	89.28 145	58.09 331	81.69 320	87.07 269	59.53 384	72.48 314	86.67 268	61.30 193	89.33 307	60.81 311	80.15 280	90.41 224

FMVSNet3		77.88 240	76.85 243	80.97 253	86.84 248	62.36 281	86.52 214	88.77 224	71.13 208	75.34 264	86.66 269	54.07 266	91.10 275	62.72 288	79.57 285	89.45 266

pmmvs6		74.69 295	73.39 299	78.61 300	81.38 373	57.48 345	86.64 210	87.95 247	64.99 328	70.18 338	86.61 270	50.43 311	89.52 304	62.12 298	70.18 390	88.83 289

ET-MVSNet_ETH3D		78.63 219	76.63 251	84.64 115	86.73 251	69.47 98	85.01 257	84.61 306	69.54 255	66.51 385	86.59 271	50.16 314	91.75 246	76.26 154	84.24 220	92.69 134

testgi		66.67 377	66.53 374	67.08 411	75.62 417	41.69 446	75.93 390	76.50 403	66.11 311	65.20 396	86.59 271	35.72 417	74.71 430	43.71 420	73.38 370	84.84 378

CLD-MVS		82.31 123	81.65 129	84.29 129	88.47 179	67.73 154	85.81 237	92.35 83	75.78 99	78.33 190	86.58 273	64.01 148	94.35 123	76.05 157	87.48 162	90.79 206
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v10		79.74 188	78.67 193	82.97 196	84.06 315	64.95 221	87.88 168	90.62 146	73.11 173	75.11 275	86.56 274	61.46 189	94.05 137	73.68 181	75.55 339	89.90 252

CDS-MVSNet		79.07 208	77.70 223	83.17 184	87.60 221	68.23 137	84.40 277	86.20 286	67.49 293	76.36 239	86.54 275	61.54 186	90.79 283	61.86 301	87.33 164	90.49 221
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
xiu_mvs_v2_base		81.69 136	81.05 136	83.60 166	89.15 151	68.03 143	84.46 273	90.02 168	70.67 222	81.30 139	86.53 276	63.17 158	94.19 132	75.60 163	88.54 147	88.57 300

TR-MVS		77.44 251	76.18 258	81.20 245	88.24 188	63.24 265	84.61 268	86.40 282	67.55 292	77.81 203	86.48 277	54.10 265	93.15 188	57.75 340	82.72 249	87.20 330

EIA-MVS		83.31 109	82.80 110	84.82 109	89.59 126	65.59 204	88.21 153	92.68 67	74.66 131	78.96 173	86.42 278	69.06 92	95.26 83	75.54 164	90.09 119	93.62 90

tfpn200view9		76.42 272	75.37 272	79.55 286	89.13 152	57.65 342	85.17 251	83.60 320	73.41 166	76.45 236	86.39 279	52.12 285	91.95 238	48.33 399	83.75 228	89.07 273

thres400		76.50 268	75.37 272	79.86 276	89.13 152	57.65 342	85.17 251	83.60 320	73.41 166	76.45 236	86.39 279	52.12 285	91.95 238	48.33 399	83.75 228	90.00 246

v7n		78.97 211	77.58 227	83.14 185	83.45 329	65.51 205	88.32 150	91.21 130	73.69 156	72.41 315	86.32 281	57.93 229	93.81 151	69.18 235	75.65 337	90.11 238

MAR-MVS		81.84 132	80.70 142	85.27 89	91.32 85	71.53 58	89.82 82	90.92 138	69.77 251	78.50 184	86.21 282	62.36 171	94.52 118	65.36 269	92.05 86	89.77 258
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		80.03 184	79.03 187	83.01 193	83.78 322	64.51 230	87.11 191	90.57 149	71.96 192	78.08 197	86.20 283	61.41 190	93.94 141	74.93 170	77.23 311	90.60 216

test_vis1_n_1920		75.52 285	75.78 261	74.75 358	79.84 392	57.44 346	83.26 301	85.52 295	62.83 354	79.34 170	86.17 284	45.10 365	79.71 399	78.75 124	81.21 265	87.10 337

V42		79.38 200	78.24 205	82.83 201	81.10 378	65.50 206	85.55 243	89.82 174	71.57 199	78.21 192	86.12 285	60.66 206	93.18 187	75.64 161	75.46 343	89.81 257

PVSNet_BlendedMVS		80.60 169	80.02 160	82.36 219	88.85 159	65.40 207	86.16 226	92.00 100	69.34 259	78.11 195	86.09 286	66.02 130	94.27 126	71.52 207	82.06 256	87.39 324

v1192		79.59 191	78.43 200	83.07 190	83.55 327	64.52 229	86.93 199	90.58 147	70.83 218	77.78 204	85.90 287	59.15 220	93.94 141	73.96 180	77.19 313	90.76 208

SixPastTwentyTwo		73.37 312	71.26 326	79.70 280	85.08 293	57.89 337	85.57 239	83.56 322	71.03 214	65.66 390	85.88 288	42.10 386	92.57 211	59.11 325	63.34 412	88.65 297

EPNet_dtu		75.46 286	74.86 278	77.23 331	82.57 354	54.60 384	86.89 200	83.09 332	71.64 194	66.25 387	85.86 289	55.99 248	88.04 331	54.92 361	86.55 178	89.05 278
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sss		73.60 309	73.64 297	73.51 370	82.80 348	55.01 381	76.12 389	81.69 351	62.47 359	74.68 285	85.85 290	57.32 237	78.11 406	60.86 310	80.93 267	87.39 324

ETV-MVS		84.90 82	84.67 82	85.59 81	89.39 138	68.66 123	88.74 133	92.64 73	79.97 16	84.10 96	85.71 291	69.32 87	95.38 78	80.82 105	91.37 98	92.72 131

test_cas_vis1_n_1920		73.76 307	73.74 296	73.81 368	75.90 414	59.77 316	80.51 339	82.40 343	58.30 395	81.62 133	85.69 292	44.35 371	76.41 417	76.29 153	78.61 294	85.23 370

v1240		78.99 210	77.78 219	82.64 212	83.21 334	63.54 257	86.62 211	90.30 160	69.74 254	77.33 212	85.68 293	57.04 241	93.76 155	73.13 190	76.92 315	90.62 214

v144192		79.47 194	78.37 201	82.78 208	83.35 330	63.96 242	86.96 196	90.36 157	69.99 244	77.50 208	85.67 294	60.66 206	93.77 154	74.27 177	76.58 321	90.62 214

tfpnnormal		74.39 297	73.16 303	78.08 314	86.10 267	58.05 332	84.65 267	87.53 258	70.32 236	71.22 330	85.63 295	54.97 254	89.86 297	43.03 422	75.02 353	86.32 349

PS-MVSNAJ		81.69 136	81.02 137	83.70 164	89.51 130	68.21 138	84.28 279	90.09 167	70.79 219	81.26 140	85.62 296	63.15 159	94.29 124	75.62 162	88.87 140	88.59 299

SSC-MVS3.2		73.35 315	73.39 299	73.23 371	85.30 286	49.01 421	74.58 404	81.57 352	75.21 113	73.68 298	85.58 297	52.53 277	82.05 387	54.33 365	77.69 308	88.63 298

v1921920		79.22 203	78.03 209	82.80 204	83.30 332	63.94 244	86.80 203	90.33 158	69.91 247	77.48 209	85.53 298	58.44 226	93.75 156	73.60 182	76.85 318	90.71 212

test_0402		72.79 323	70.44 334	79.84 277	88.13 194	65.99 192	85.93 231	84.29 311	65.57 319	67.40 371	85.49 299	46.92 343	92.61 208	35.88 436	74.38 359	80.94 415

v148		78.72 217	77.80 218	81.47 235	82.73 350	61.96 288	86.30 222	88.08 241	73.26 170	76.18 244	85.47 300	62.46 169	92.36 223	71.92 206	73.82 365	90.09 240

USDC		70.33 347	68.37 348	76.21 338	80.60 382	56.23 365	79.19 358	86.49 280	60.89 371	61.29 413	85.47 300	31.78 425	89.47 306	53.37 370	76.21 332	82.94 402

VortexMVS		78.57 222	77.89 214	80.59 260	85.89 269	62.76 277	85.61 238	89.62 183	72.06 190	74.99 279	85.38 302	55.94 249	90.77 285	74.99 169	76.58 321	88.23 306

MVP-Stereo		76.12 276	74.46 286	81.13 248	85.37 284	69.79 91	84.42 276	87.95 247	65.03 326	67.46 368	85.33 303	53.28 275	91.73 248	58.01 338	83.27 241	81.85 410
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVS		78.19 231	76.99 240	81.78 228	85.66 274	66.99 176	84.66 265	90.47 151	55.08 414	72.02 321	85.27 304	63.83 150	94.11 135	66.10 263	89.80 126	84.24 384

DIV-MVS_self_test		77.72 244	76.76 246	80.58 261	82.48 357	60.48 308	83.09 305	87.86 250	69.22 264	74.38 291	85.24 305	62.10 176	91.53 258	71.09 212	75.40 346	89.74 259

FE-MVS		77.78 242	75.68 263	84.08 144	88.09 197	66.00 191	83.13 304	87.79 252	68.42 284	78.01 198	85.23 306	45.50 363	95.12 88	59.11 325	85.83 195	91.11 193

cl____		77.72 244	76.76 246	80.58 261	82.49 356	60.48 308	83.09 305	87.87 249	69.22 264	74.38 291	85.22 307	62.10 176	91.53 258	71.09 212	75.41 345	89.73 260

HyFIR lowres test		77.53 250	75.40 270	83.94 158	89.59 126	66.62 181	80.36 342	88.64 233	56.29 410	76.45 236	85.17 308	57.64 233	93.28 175	61.34 307	83.10 244	91.91 168

pmmvs4		74.03 305	71.91 316	80.39 264	81.96 362	68.32 131	81.45 324	82.14 345	59.32 385	69.87 346	85.13 309	52.40 281	88.13 330	60.21 315	74.74 356	84.73 380

TDRefinement		67.49 370	64.34 381	76.92 333	73.47 429	61.07 299	84.86 261	82.98 336	59.77 381	58.30 424	85.13 309	26.06 433	87.89 333	47.92 405	60.59 421	81.81 411

Fast-Effi-MVS+		80.81 157	79.92 162	83.47 170	88.85 159	64.51 230	85.53 245	89.39 190	70.79 219	78.49 185	85.06 311	67.54 110	93.58 160	67.03 258	86.58 177	92.32 151

PVSNet_Blended		80.98 152	80.34 151	82.90 198	88.85 159	65.40 207	84.43 275	92.00 100	67.62 291	78.11 195	85.05 312	66.02 130	94.27 126	71.52 207	89.50 131	89.01 280

ttmdpeth		59.91 397	57.10 401	68.34 406	67.13 443	46.65 430	74.64 403	67.41 433	48.30 429	62.52 411	85.04 313	20.40 443	75.93 422	42.55 424	45.90 444	82.44 405

test_fmvs1_n		70.86 340	70.24 337	72.73 378	72.51 436	55.28 378	81.27 327	79.71 377	51.49 425	78.73 177	84.87 314	27.54 432	77.02 411	76.06 156	79.97 283	85.88 361

WBMVS		73.43 311	72.81 307	75.28 350	87.91 205	50.99 413	78.59 369	81.31 357	65.51 322	74.47 289	84.83 315	46.39 348	86.68 345	58.41 333	77.86 304	88.17 309

CMPMVS	51.72 21	70.19 349	68.16 351	76.28 337	73.15 432	57.55 344	79.47 353	83.92 316	48.02 430	56.48 430	84.81 316	43.13 378	86.42 349	62.67 291	81.81 260	84.89 377
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		68.53 365	67.61 364	71.31 390	78.51 406	47.01 428	84.47 271	84.27 312	42.27 437	66.44 386	84.79 317	40.44 395	83.76 373	58.76 330	68.54 398	83.17 396

BH-w/o		78.21 229	77.33 234	80.84 255	88.81 163	65.13 215	84.87 260	87.85 251	69.75 252	74.52 288	84.74 318	61.34 192	93.11 191	58.24 336	85.84 194	84.27 383

pmmvs5		71.55 333	70.20 338	75.61 343	77.83 407	56.39 361	81.74 319	80.89 358	57.76 400	67.46 368	84.49 319	49.26 328	85.32 363	57.08 346	75.29 349	85.11 374

reproduce_monomvs		75.40 289	74.38 287	78.46 308	83.92 319	57.80 340	83.78 286	86.94 272	73.47 164	72.25 318	84.47 320	38.74 403	89.27 309	75.32 167	70.53 388	88.31 305

thres200		75.55 284	74.47 285	78.82 297	87.78 214	57.85 338	83.07 307	83.51 323	72.44 184	75.84 250	84.42 321	52.08 288	91.75 246	47.41 406	83.64 233	86.86 341

test_fmvs1		70.93 339	70.52 332	72.16 382	73.71 425	55.05 380	80.82 330	78.77 386	51.21 426	78.58 182	84.41 322	31.20 427	76.94 412	75.88 159	80.12 282	84.47 382

testing3		68.56 364	67.67 363	71.22 391	87.33 231	42.87 441	83.06 308	71.54 421	70.36 233	69.08 354	84.38 323	30.33 429	85.69 357	37.50 434	75.45 344	85.09 375

test_fmvs2		68.35 367	67.48 366	70.98 393	69.50 439	51.95 402	80.05 347	76.38 404	49.33 428	74.65 286	84.38 323	23.30 441	75.40 428	74.51 174	75.17 352	85.60 364

eth_miper_zixun_eth		77.92 239	76.69 249	81.61 233	83.00 342	61.98 287	83.15 303	89.20 206	69.52 256	74.86 282	84.35 325	61.76 182	92.56 212	71.50 209	72.89 373	90.28 231

myMVS_eth3d28		73.62 308	73.53 298	73.90 367	88.20 189	47.41 426	78.06 376	79.37 380	74.29 141	73.98 294	84.29 326	44.67 366	83.54 376	51.47 379	87.39 163	90.74 210

testing91		76.54 266	75.66 265	79.18 292	88.43 182	55.89 369	81.08 328	83.00 335	73.76 154	75.34 264	84.29 326	46.20 354	90.07 294	64.33 277	84.50 212	91.58 179

c3_l		78.75 215	77.91 212	81.26 243	82.89 347	61.56 293	84.09 283	89.13 210	69.97 245	75.56 254	84.29 326	66.36 123	92.09 233	73.47 185	75.48 341	90.12 237

testing99		76.09 278	75.12 277	79.00 293	88.16 191	55.50 375	80.79 332	81.40 355	73.30 169	75.17 272	84.27 329	44.48 369	90.02 295	64.28 278	84.22 221	91.48 184

UWE-MVS		72.13 330	71.49 320	74.03 365	86.66 254	47.70 423	81.40 326	76.89 402	63.60 345	75.59 253	84.22 330	39.94 397	85.62 358	48.98 396	86.13 186	88.77 292

Fast-Effi-MVS+-dtu		78.02 236	76.49 252	82.62 213	83.16 338	66.96 179	86.94 198	87.45 261	72.45 182	71.49 327	84.17 331	54.79 259	91.58 252	67.61 249	80.31 278	89.30 271

IterMVS-SCA-FT		75.43 287	73.87 294	80.11 272	82.69 351	64.85 225	81.57 322	83.47 324	69.16 267	70.49 334	84.15 332	51.95 291	88.15 329	69.23 234	72.14 379	87.34 326

1314		76.53 267	75.30 274	80.21 270	83.93 318	62.32 283	84.66 265	88.81 222	60.23 377	70.16 340	84.07 333	55.30 253	90.73 286	67.37 252	83.21 242	87.59 321

cl22		78.07 234	77.01 238	81.23 244	82.37 359	61.83 290	83.55 294	87.98 245	68.96 274	75.06 277	83.87 334	61.40 191	91.88 242	73.53 183	76.39 326	89.98 249

EG-PatchMatch MVS		74.04 303	71.82 317	80.71 258	84.92 296	67.42 163	85.86 234	88.08 241	66.04 313	64.22 400	83.85 335	35.10 418	92.56 212	57.44 342	80.83 270	82.16 409

thisisatest0515		77.33 254	75.38 271	83.18 183	85.27 287	63.80 247	82.11 316	83.27 327	65.06 325	75.91 248	83.84 336	49.54 322	94.27 126	67.24 254	86.19 184	91.48 184

test20.03		67.45 371	66.95 372	68.94 400	75.48 418	44.84 437	77.50 381	77.67 392	66.66 302	63.01 407	83.80 337	47.02 342	78.40 404	42.53 425	68.86 397	83.58 393

miper_ehance_all_eth		78.59 221	77.76 221	81.08 249	82.66 352	61.56 293	83.65 290	89.15 208	68.87 275	75.55 255	83.79 338	66.49 121	92.03 234	73.25 188	76.39 326	89.64 261

MSDG		73.36 314	70.99 328	80.49 263	84.51 307	65.80 198	80.71 336	86.13 288	65.70 317	65.46 391	83.74 339	44.60 367	90.91 281	51.13 382	76.89 316	84.74 379

MonoMVSNet		76.49 271	75.80 260	78.58 302	81.55 369	58.45 327	86.36 220	86.22 285	74.87 126	74.73 284	83.73 340	51.79 296	88.73 321	70.78 214	72.15 378	88.55 301

testing11		75.14 292	74.01 290	78.53 305	88.16 191	56.38 362	80.74 335	80.42 368	70.67 222	72.69 312	83.72 341	43.61 376	89.86 297	62.29 295	83.76 227	89.36 269

IterMVS		74.29 298	72.94 306	78.35 309	81.53 370	63.49 259	81.58 321	82.49 342	68.06 288	69.99 343	83.69 342	51.66 298	85.54 359	65.85 266	71.64 382	86.01 357
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tpm		72.37 326	71.71 318	74.35 361	82.19 360	52.00 401	79.22 357	77.29 398	64.56 331	72.95 308	83.68 343	51.35 299	83.26 380	58.33 335	75.80 335	87.81 315

UWE-MVS-28		65.32 384	64.93 378	66.49 412	78.70 404	38.55 449	77.86 380	64.39 441	62.00 365	64.13 401	83.60 344	41.44 389	76.00 421	31.39 441	80.89 268	84.92 376

sc_t1		72.19 329	69.51 340	80.23 269	84.81 298	61.09 298	84.68 264	80.22 372	60.70 373	71.27 328	83.58 345	36.59 413	89.24 310	60.41 312	63.31 413	90.37 226

testing222		74.04 303	72.66 309	78.19 311	87.89 206	55.36 376	81.06 329	79.20 383	71.30 205	74.65 286	83.57 346	39.11 402	88.67 323	51.43 381	85.75 196	90.53 219

Effi-MVS+-dtu		80.03 184	78.57 196	84.42 122	85.13 292	68.74 117	88.77 129	88.10 240	74.99 119	74.97 280	83.49 347	57.27 238	93.36 173	73.53 183	80.88 269	91.18 191

baseline2		75.70 282	73.83 295	81.30 241	83.26 333	61.79 291	82.57 312	80.65 362	66.81 298	66.88 376	83.42 348	57.86 231	92.19 230	63.47 282	79.57 285	89.91 251

mvs5depth		69.45 356	67.45 367	75.46 348	73.93 423	55.83 370	79.19 358	83.23 328	66.89 297	71.63 325	83.32 349	33.69 421	85.09 364	59.81 318	55.34 431	85.46 366

TinyColmap		67.30 373	64.81 379	74.76 357	81.92 364	56.68 357	80.29 344	81.49 354	60.33 375	56.27 431	83.22 350	24.77 437	87.66 337	45.52 416	69.47 392	79.95 420

mvsany_test1		62.30 393	61.26 397	65.41 414	69.52 438	54.86 382	66.86 432	49.78 454	46.65 431	68.50 360	83.21 351	49.15 329	66.28 446	56.93 349	60.77 419	75.11 430

test_vis1_n		69.85 354	69.21 343	71.77 384	72.66 435	55.27 379	81.48 323	76.21 405	52.03 422	75.30 269	83.20 352	28.97 430	76.22 419	74.60 173	78.41 300	83.81 390

CostFormer		75.24 291	73.90 293	79.27 289	82.65 353	58.27 330	80.80 331	82.73 341	61.57 367	75.33 268	83.13 353	55.52 251	91.07 278	64.98 273	78.34 301	88.45 302

MVStest1		56.63 401	52.76 407	68.25 407	61.67 449	53.25 398	71.67 413	68.90 431	38.59 442	50.59 438	83.05 354	25.08 435	70.66 439	36.76 435	38.56 445	80.83 416

WB-MVSnew		71.96 332	71.65 319	72.89 376	84.67 305	51.88 404	82.29 314	77.57 393	62.31 360	73.67 299	83.00 355	53.49 273	81.10 394	45.75 415	82.13 255	85.70 363

ETVMVS		72.25 328	71.05 327	75.84 340	87.77 215	51.91 403	79.39 354	74.98 409	69.26 262	73.71 297	82.95 356	40.82 394	86.14 351	46.17 412	84.43 217	89.47 265

miper_lstm_enhance		74.11 302	73.11 304	77.13 332	80.11 388	59.62 318	72.23 411	86.92 274	66.76 300	70.40 335	82.92 357	56.93 242	82.92 381	69.06 237	72.63 374	88.87 287

GA-MVS		76.87 262	75.17 276	81.97 226	82.75 349	62.58 278	81.44 325	86.35 284	72.16 189	74.74 283	82.89 358	46.20 354	92.02 235	68.85 240	81.09 266	91.30 189

K. test v3		71.19 335	68.51 347	79.21 291	83.04 341	57.78 341	84.35 278	76.91 401	72.90 178	62.99 408	82.86 359	39.27 399	91.09 277	61.65 303	52.66 434	88.75 293

MS-PatchMatch		73.83 306	72.67 308	77.30 330	83.87 320	66.02 190	81.82 317	84.66 305	61.37 370	68.61 358	82.82 360	47.29 339	88.21 328	59.27 322	84.32 219	77.68 425

lessismore_v0				78.97 294	81.01 379	57.15 349		65.99 436		61.16 414	82.82 360	39.12 401	91.34 267	59.67 319	46.92 441	88.43 303

D2MVS		74.82 294	73.21 302	79.64 283	79.81 393	62.56 279	80.34 343	87.35 262	64.37 334	68.86 355	82.66 362	46.37 350	90.10 293	67.91 247	81.24 264	86.25 350

Anonymous20231206		68.60 362	67.80 360	71.02 392	80.23 387	50.75 415	78.30 374	80.47 365	56.79 407	66.11 389	82.63 363	46.35 351	78.95 402	43.62 421	75.70 336	83.36 395

MIMVSNet		70.69 342	69.30 341	74.88 355	84.52 306	56.35 364	75.87 393	79.42 379	64.59 330	67.76 363	82.41 364	41.10 391	81.54 390	46.64 410	81.34 262	86.75 344

UBG		73.08 319	72.27 314	75.51 346	88.02 200	51.29 411	78.35 373	77.38 397	65.52 320	73.87 296	82.36 365	45.55 361	86.48 348	55.02 360	84.39 218	88.75 293

OpenMVS_ROB	64.09 19	70.56 344	68.19 350	77.65 323	80.26 385	59.41 322	85.01 257	82.96 337	58.76 392	65.43 392	82.33 366	37.63 410	91.23 271	45.34 418	76.03 333	82.32 406

miper_enhance_ethall		77.87 241	76.86 242	80.92 254	81.65 366	61.38 295	82.68 310	88.98 216	65.52 320	75.47 256	82.30 367	65.76 134	92.00 236	72.95 191	76.39 326	89.39 268

test0.0.03 1		68.00 369	67.69 362	68.90 401	77.55 408	47.43 424	75.70 394	72.95 420	66.66 302	66.56 381	82.29 368	48.06 336	75.87 423	44.97 419	74.51 358	83.41 394

PVSNet	64.34 18	72.08 331	70.87 330	75.69 342	86.21 261	56.44 360	74.37 405	80.73 361	62.06 364	70.17 339	82.23 369	42.86 380	83.31 379	54.77 362	84.45 216	87.32 327

MIMVSNet1		68.58 363	66.78 373	73.98 366	80.07 389	51.82 405	80.77 333	84.37 308	64.40 333	59.75 420	82.16 370	36.47 414	83.63 375	42.73 423	70.33 389	86.48 348

CL-MVSNet_self_test		72.37 326	71.46 321	75.09 352	79.49 399	53.53 392	80.76 334	85.01 303	69.12 268	70.51 333	82.05 371	57.92 230	84.13 371	52.27 375	66.00 406	87.60 319

tpm2		73.26 316	71.46 321	78.63 299	83.34 331	56.71 356	80.65 337	80.40 369	56.63 408	73.55 300	82.02 372	51.80 295	91.24 270	56.35 355	78.42 299	87.95 311

PatchMatch-RL		72.38 325	70.90 329	76.80 335	88.60 175	67.38 166	79.53 352	76.17 406	62.75 356	69.36 351	82.00 373	45.51 362	84.89 367	53.62 368	80.58 274	78.12 424

FMVSNet5		69.50 355	67.96 355	74.15 364	82.97 345	55.35 377	80.01 348	82.12 346	62.56 358	63.02 406	81.53 374	36.92 411	81.92 388	48.42 398	74.06 361	85.17 373

CR-MVSNet		73.37 312	71.27 325	79.67 282	81.32 376	65.19 213	75.92 391	80.30 370	59.92 380	72.73 310	81.19 375	52.50 279	86.69 344	59.84 317	77.71 306	87.11 335

Patchmtry		70.74 341	69.16 344	75.49 347	80.72 380	54.07 389	74.94 402	80.30 370	58.34 394	70.01 341	81.19 375	52.50 279	86.54 346	53.37 370	71.09 386	85.87 362

IB-MVS	68.01 15	75.85 281	73.36 301	83.31 176	84.76 300	66.03 189	83.38 298	85.06 301	70.21 240	69.40 350	81.05 377	45.76 359	94.66 113	65.10 272	75.49 340	89.25 272
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		76.72 265	74.64 281	82.99 194	85.78 272	65.88 195	82.33 313	89.21 205	60.85 372	72.74 309	81.02 378	47.28 340	93.75 156	67.48 251	85.02 204	89.34 270

LF4IMVS		64.02 389	62.19 393	69.50 398	70.90 437	53.29 397	76.13 388	77.18 399	52.65 420	58.59 422	80.98 379	23.55 440	76.52 415	53.06 372	66.66 402	78.68 423

Anonymous20240521		68.80 361	67.22 370	73.55 369	74.33 421	54.11 388	83.18 302	85.61 294	58.15 396	61.68 412	80.94 380	30.71 428	81.27 393	57.00 348	73.34 371	85.28 369

gm-plane-assit					81.40 372	53.83 391			62.72 357		80.94 380		92.39 221	63.40 284

UnsupCasMVSNet_eth		67.33 372	65.99 376	71.37 387	73.48 428	51.47 409	75.16 398	85.19 298	65.20 323	60.78 415	80.93 382	42.35 382	77.20 410	57.12 345	53.69 433	85.44 367

dmvs_re		71.14 336	70.58 331	72.80 377	81.96 362	59.68 317	75.60 395	79.34 381	68.55 280	69.27 353	80.72 383	49.42 324	76.54 414	52.56 374	77.79 305	82.19 408

MDTV_nov1_ep13			69.97 339		83.18 336	53.48 393	77.10 386	80.18 374	60.45 374	69.33 352	80.44 384	48.89 334	86.90 343	51.60 378	78.51 297

pmmvs-eth3d		70.50 345	67.83 359	78.52 306	77.37 410	66.18 188	81.82 317	81.51 353	58.90 390	63.90 404	80.42 385	42.69 381	86.28 350	58.56 331	65.30 408	83.11 398

tt0320		70.49 346	68.03 354	77.89 317	84.78 299	59.12 323	83.55 294	80.44 367	58.13 397	67.43 370	80.41 386	39.26 400	87.54 338	55.12 359	63.18 414	86.99 338

mmtdpeth		74.16 301	73.01 305	77.60 326	83.72 324	61.13 296	85.10 255	85.10 300	72.06 190	77.21 220	80.33 387	43.84 374	85.75 355	77.14 144	52.61 435	85.91 360

tt0320-xc		70.11 350	67.45 367	78.07 315	85.33 285	59.51 321	83.28 300	78.96 385	58.77 391	67.10 374	80.28 388	36.73 412	87.42 339	56.83 351	59.77 423	87.29 328

PM-MVS		66.41 379	64.14 382	73.20 374	73.92 424	56.45 359	78.97 362	64.96 440	63.88 344	64.72 397	80.24 389	19.84 445	83.44 378	66.24 260	64.52 410	79.71 421

SCA		74.22 300	72.33 313	79.91 275	84.05 316	62.17 285	79.96 349	79.29 382	66.30 310	72.38 316	80.13 390	51.95 291	88.60 324	59.25 323	77.67 309	88.96 284

Patchmatch-test		64.82 387	63.24 388	69.57 397	79.42 400	49.82 419	63.49 444	69.05 429	51.98 423	59.95 419	80.13 390	50.91 304	70.98 438	40.66 428	73.57 366	87.90 313

tpmrst		72.39 324	72.13 315	73.18 375	80.54 383	49.91 418	79.91 350	79.08 384	63.11 348	71.69 324	79.95 392	55.32 252	82.77 383	65.66 268	73.89 363	86.87 340

DSMNet-mixed		57.77 400	56.90 402	60.38 420	67.70 441	35.61 451	69.18 424	53.97 452	32.30 450	57.49 427	79.88 393	40.39 396	68.57 444	38.78 432	72.37 375	76.97 426

MDA-MVSNet-bldmvs		66.68 376	63.66 386	75.75 341	79.28 401	60.56 307	73.92 407	78.35 389	64.43 332	50.13 439	79.87 394	44.02 373	83.67 374	46.10 413	56.86 425	83.03 400

PatchmatchNet		73.12 318	71.33 324	78.49 307	83.18 336	60.85 302	79.63 351	78.57 387	64.13 336	71.73 323	79.81 395	51.20 302	85.97 354	57.40 343	76.36 331	88.66 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Syy-MVS		68.05 368	67.85 357	68.67 404	84.68 302	40.97 447	78.62 367	73.08 418	66.65 305	66.74 379	79.46 396	52.11 287	82.30 385	32.89 439	76.38 329	82.75 403

myMVS_eth3d		67.02 374	66.29 375	69.21 399	84.68 302	42.58 442	78.62 367	73.08 418	66.65 305	66.74 379	79.46 396	31.53 426	82.30 385	39.43 431	76.38 329	82.75 403

ppachtmachnet_test		70.04 351	67.34 369	78.14 312	79.80 394	61.13 296	79.19 358	80.59 363	59.16 387	65.27 393	79.29 398	46.75 347	87.29 340	49.33 394	66.72 401	86.00 359

EPMVS		69.02 359	68.16 351	71.59 385	79.61 397	49.80 420	77.40 382	66.93 434	62.82 355	70.01 341	79.05 399	45.79 358	77.86 408	56.58 353	75.26 350	87.13 334

PMMVS		69.34 357	68.67 346	71.35 389	75.67 416	62.03 286	75.17 397	73.46 416	50.00 427	68.68 356	79.05 399	52.07 289	78.13 405	61.16 308	82.77 247	73.90 431

test-LLR		72.94 322	72.43 311	74.48 359	81.35 374	58.04 333	78.38 370	77.46 394	66.66 302	69.95 344	79.00 401	48.06 336	79.24 400	66.13 261	84.83 207	86.15 353

test-mter		71.41 334	70.39 336	74.48 359	81.35 374	58.04 333	78.38 370	77.46 394	60.32 376	69.95 344	79.00 401	36.08 416	79.24 400	66.13 261	84.83 207	86.15 353

KD-MVS_self_test		68.81 360	67.59 365	72.46 381	74.29 422	45.45 431	77.93 378	87.00 270	63.12 347	63.99 403	78.99 403	42.32 383	84.77 368	56.55 354	64.09 411	87.16 333

test_fmvs3		63.36 391	61.82 394	67.98 408	62.51 448	46.96 429	77.37 383	74.03 415	45.24 433	67.50 367	78.79 404	12.16 453	72.98 437	72.77 194	66.02 405	83.99 388

KD-MVS_2432*1600		66.22 381	63.89 384	73.21 372	75.47 419	53.42 394	70.76 418	84.35 309	64.10 338	66.52 383	78.52 405	34.55 419	84.98 365	50.40 385	50.33 438	81.23 413

miper_refine_blended		66.22 381	63.89 384	73.21 372	75.47 419	53.42 394	70.76 418	84.35 309	64.10 338	66.52 383	78.52 405	34.55 419	84.98 365	50.40 385	50.33 438	81.23 413

tpmvs		71.09 337	69.29 342	76.49 336	82.04 361	56.04 367	78.92 363	81.37 356	64.05 340	67.18 373	78.28 407	49.74 321	89.77 299	49.67 392	72.37 375	83.67 392

our_test_3		69.14 358	67.00 371	75.57 344	79.80 394	58.80 324	77.96 377	77.81 391	59.55 383	62.90 409	78.25 408	47.43 338	83.97 372	51.71 377	67.58 400	83.93 389

MDA-MVSNet_test_wron		65.03 385	62.92 389	71.37 387	75.93 413	56.73 354	69.09 427	74.73 412	57.28 405	54.03 434	77.89 409	45.88 356	74.39 432	49.89 391	61.55 417	82.99 401

YYNet1		65.03 385	62.91 390	71.38 386	75.85 415	56.60 358	69.12 426	74.66 414	57.28 405	54.12 433	77.87 410	45.85 357	74.48 431	49.95 390	61.52 418	83.05 399

ambc				75.24 351	73.16 431	50.51 416	63.05 445	87.47 260		64.28 399	77.81 411	17.80 447	89.73 301	57.88 339	60.64 420	85.49 365

tpm cat1		70.57 343	68.31 349	77.35 329	82.41 358	57.95 336	78.08 375	80.22 372	52.04 421	68.54 359	77.66 412	52.00 290	87.84 334	51.77 376	72.07 380	86.25 350

dp		66.80 375	65.43 377	70.90 394	79.74 396	48.82 422	75.12 400	74.77 411	59.61 382	64.08 402	77.23 413	42.89 379	80.72 396	48.86 397	66.58 403	83.16 397

TESTMET0.1,1		69.89 353	69.00 345	72.55 379	79.27 402	56.85 352	78.38 370	74.71 413	57.64 401	68.09 362	77.19 414	37.75 409	76.70 413	63.92 280	84.09 222	84.10 387

CHOSEN 280x420		66.51 378	64.71 380	71.90 383	81.45 371	63.52 258	57.98 447	68.95 430	53.57 417	62.59 410	76.70 415	46.22 353	75.29 429	55.25 358	79.68 284	76.88 427

PatchT		68.46 366	67.85 357	70.29 395	80.70 381	43.93 439	72.47 410	74.88 410	60.15 378	70.55 332	76.57 416	49.94 318	81.59 389	50.58 383	74.83 355	85.34 368

mvsany_test3		53.99 404	51.45 409	61.61 419	55.51 453	44.74 438	63.52 443	45.41 458	43.69 436	58.11 425	76.45 417	17.99 446	63.76 449	54.77 362	47.59 440	76.34 428

RPMNet		73.51 310	70.49 333	82.58 215	81.32 376	65.19 213	75.92 391	92.27 85	57.60 402	72.73 310	76.45 417	52.30 282	95.43 73	48.14 403	77.71 306	87.11 335

dmvs_testset		62.63 392	64.11 383	58.19 422	78.55 405	24.76 460	75.28 396	65.94 437	67.91 289	60.34 416	76.01 419	53.56 271	73.94 435	31.79 440	67.65 399	75.88 429

ADS-MVSNet2		66.20 383	63.33 387	74.82 356	79.92 390	58.75 325	67.55 430	75.19 408	53.37 418	65.25 394	75.86 420	42.32 383	80.53 397	41.57 426	68.91 395	85.18 371

ADS-MVSNet		64.36 388	62.88 391	68.78 403	79.92 390	47.17 427	67.55 430	71.18 422	53.37 418	65.25 394	75.86 420	42.32 383	73.99 434	41.57 426	68.91 395	85.18 371

EGC-MVSNET		52.07 410	47.05 414	67.14 410	83.51 328	60.71 304	80.50 340	67.75 432	0.07 460	0.43 461	75.85 422	24.26 438	81.54 390	28.82 443	62.25 415	59.16 443

new-patchmatchnet		61.73 394	61.73 395	61.70 418	72.74 434	24.50 461	69.16 425	78.03 390	61.40 368	56.72 429	75.53 423	38.42 405	76.48 416	45.95 414	57.67 424	84.13 386

N_pmnet		52.79 408	53.26 406	51.40 432	78.99 403	7.68 466	69.52 422	3.89 465	51.63 424	57.01 428	74.98 424	40.83 393	65.96 447	37.78 433	64.67 409	80.56 419

WB-MVS		54.94 402	54.72 403	55.60 428	73.50 427	20.90 462	74.27 406	61.19 445	59.16 387	50.61 437	74.15 425	47.19 341	75.78 424	17.31 453	35.07 447	70.12 435

patchmatchnet-post											74.00 426	51.12 303	88.60 324

GG-mvs-BLEND				75.38 349	81.59 368	55.80 371	79.32 355	69.63 426		67.19 372	73.67 427	43.24 377	88.90 320	50.41 384	84.50 212	81.45 412

SSC-MVS		53.88 405	53.59 405	54.75 430	72.87 433	19.59 463	73.84 408	60.53 447	57.58 403	49.18 441	73.45 428	46.34 352	75.47 427	16.20 456	32.28 449	69.20 436

Patchmatch-RL test		70.24 348	67.78 361	77.61 324	77.43 409	59.57 320	71.16 415	70.33 423	62.94 352	68.65 357	72.77 429	50.62 308	85.49 360	69.58 232	66.58 403	87.77 316

FPMVS		53.68 406	51.64 408	59.81 421	65.08 445	51.03 412	69.48 423	69.58 427	41.46 438	40.67 445	72.32 430	16.46 449	70.00 442	24.24 449	65.42 407	58.40 445

UnsupCasMVSNet_bld		63.70 390	61.53 396	70.21 396	73.69 426	51.39 410	72.82 409	81.89 348	55.63 412	57.81 426	71.80 431	38.67 404	78.61 403	49.26 395	52.21 436	80.63 417

APD_test1		53.31 407	49.93 412	63.42 417	65.68 444	50.13 417	71.59 414	66.90 435	34.43 447	40.58 446	71.56 432	8.65 458	76.27 418	34.64 438	55.36 430	63.86 441

test_f		52.09 409	50.82 410	55.90 426	53.82 456	42.31 445	59.42 446	58.31 450	36.45 445	56.12 432	70.96 433	12.18 452	57.79 452	53.51 369	56.57 427	67.60 437

PVSNet_0	57.27 20	61.67 395	59.27 398	68.85 402	79.61 397	57.44 346	68.01 428	73.44 417	55.93 411	58.54 423	70.41 434	44.58 368	77.55 409	47.01 407	35.91 446	71.55 434

pmmvs3		57.79 399	54.26 404	68.37 405	64.02 447	56.72 355	75.12 400	65.17 438	40.20 439	52.93 435	69.86 435	20.36 444	75.48 426	45.45 417	55.25 432	72.90 433

test_vis1_rt		60.28 396	58.42 399	65.84 413	67.25 442	55.60 374	70.44 420	60.94 446	44.33 435	59.00 421	66.64 436	24.91 436	68.67 443	62.80 287	69.48 391	73.25 432

new_pmnet		50.91 411	50.29 411	52.78 431	68.58 440	34.94 453	63.71 442	56.63 451	39.73 440	44.95 442	65.47 437	21.93 442	58.48 451	34.98 437	56.62 426	64.92 439

gg-mvs-nofinetune		69.95 352	67.96 355	75.94 339	83.07 339	54.51 386	77.23 384	70.29 424	63.11 348	70.32 336	62.33 438	43.62 375	88.69 322	53.88 367	87.76 158	84.62 381

JIA-IIPM		66.32 380	62.82 392	76.82 334	77.09 411	61.72 292	65.34 438	75.38 407	58.04 399	64.51 398	62.32 439	42.05 387	86.51 347	51.45 380	69.22 394	82.21 407

LCM-MVSNet		54.25 403	49.68 413	67.97 409	53.73 457	45.28 434	66.85 433	80.78 360	35.96 446	39.45 447	62.23 440	8.70 457	78.06 407	48.24 402	51.20 437	80.57 418

PMMVS2		40.82 419	38.86 423	46.69 433	53.84 455	16.45 464	48.61 450	49.92 453	37.49 443	31.67 448	60.97 441	8.14 459	56.42 453	28.42 444	30.72 450	67.19 438

testf1		45.72 414	41.96 418	57.00 423	56.90 451	45.32 432	66.14 435	59.26 448	26.19 451	30.89 450	60.96 442	4.14 461	70.64 440	26.39 447	46.73 442	55.04 446

APD_test2		45.72 414	41.96 418	57.00 423	56.90 451	45.32 432	66.14 435	59.26 448	26.19 451	30.89 450	60.96 442	4.14 461	70.64 440	26.39 447	46.73 442	55.04 446

MVS-HIRNet		59.14 398	57.67 400	63.57 416	81.65 366	43.50 440	71.73 412	65.06 439	39.59 441	51.43 436	57.73 444	38.34 406	82.58 384	39.53 429	73.95 362	64.62 440

ANet_high		50.57 412	46.10 416	63.99 415	48.67 460	39.13 448	70.99 417	80.85 359	61.39 369	31.18 449	57.70 445	17.02 448	73.65 436	31.22 442	15.89 457	79.18 422

PMVS	37.38 22	44.16 418	40.28 422	55.82 427	40.82 462	42.54 444	65.12 439	63.99 442	34.43 447	24.48 453	57.12 446	3.92 463	76.17 420	17.10 454	55.52 429	48.75 448
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		45.42 416	45.38 417	45.55 434	73.36 430	26.85 458	67.72 429	34.19 460	54.15 416	49.65 440	56.41 447	25.43 434	62.94 450	19.45 451	28.09 451	46.86 450

test_vis3_rt		49.26 413	47.02 415	56.00 425	54.30 454	45.27 435	66.76 434	48.08 455	36.83 444	44.38 443	53.20 448	7.17 460	64.07 448	56.77 352	55.66 428	58.65 444

test_method		31.52 422	29.28 426	38.23 436	27.03 464	6.50 467	20.94 455	62.21 444	4.05 458	22.35 456	52.50 449	13.33 450	47.58 456	27.04 446	34.04 448	60.62 442

kuosan		39.70 420	40.40 421	37.58 437	64.52 446	26.98 456	65.62 437	33.02 461	46.12 432	42.79 444	48.99 450	24.10 439	46.56 458	12.16 459	26.30 452	39.20 451

DeepMVS_CX				27.40 440	40.17 463	26.90 457		24.59 464	17.44 456	23.95 454	48.61 451	9.77 455	26.48 459	18.06 452	24.47 453	28.83 453

MVE	26.22 23	30.37 424	25.89 428	43.81 435	44.55 461	35.46 452	28.87 454	39.07 459	18.20 455	18.58 457	40.18 452	2.68 464	47.37 457	17.07 455	23.78 454	48.60 449
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		45.18 417	41.86 420	55.16 429	77.03 412	51.52 408	32.50 453	80.52 364	32.46 449	27.12 452	35.02 453	9.52 456	75.50 425	22.31 450	60.21 422	38.45 452
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		31.77 421	30.64 424	35.15 438	52.87 458	27.67 455	57.09 448	47.86 456	24.64 453	16.40 458	33.05 454	11.23 454	54.90 454	14.46 457	18.15 455	22.87 454

EMVS		30.81 423	29.65 425	34.27 439	50.96 459	25.95 459	56.58 449	46.80 457	24.01 454	15.53 459	30.68 455	12.47 451	54.43 455	12.81 458	17.05 456	22.43 455

tmp_tt		18.61 426	21.40 429	10.23 442	4.82 465	10.11 465	34.70 452	30.74 463	1.48 459	23.91 455	26.07 456	28.42 431	13.41 461	27.12 445	15.35 458	7.17 456

X-MVStestdata		80.37 178	77.83 216	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 106	12.47 457	67.45 111	96.60 33	83.06 80	94.50 53	94.07 59

test_post											5.46 458	50.36 312	84.24 370

test_post1							78.90 364				5.43 459	48.81 335	85.44 362	59.25 323

wuyk23d		16.82 427	15.94 430	19.46 441	58.74 450	31.45 454	39.22 451	3.74 466	6.84 457	6.04 460	2.70 460	1.27 465	24.29 460	10.54 460	14.40 459	2.63 457

testmvs		6.04 430	8.02 433	0.10 444	0.08 466	0.03 469	69.74 421	0.04 467	0.05 461	0.31 462	1.68 461	0.02 467	0.04 462	0.24 461	0.02 460	0.25 459

test123		6.12 429	8.11 432	0.14 443	0.06 467	0.09 468	71.05 416	0.03 468	0.04 462	0.25 463	1.30 462	0.05 466	0.03 463	0.21 462	0.01 461	0.29 458

mmdepth		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

monomultidepth		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

test_blank		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uanet_test		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

DCPMVS		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

pcd_1.5k_mvsjas		5.26 431	7.02 434	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	63.15 159	0.00 464	0.00 463	0.00 462	0.00 460

sosnet-low-res		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

sosnet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uncertanet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

Regformer		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

uanet		0.00 432	0.00 435	0.00 445	0.00 468	0.00 470	0.00 456	0.00 469	0.00 463	0.00 464	0.00 463	0.00 468	0.00 464	0.00 463	0.00 462	0.00 460

WAC-MVS						42.58 442								39.46 430

FOURS1					95.00 10	72.39 41	95.06 1	93.84 16	74.49 134	91.30 15

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 13	96.44 9	94.41 42

No_MVS				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 13	96.44 9	94.41 42

eth-test2					0.00 468

eth-test					0.00 468

IU-MVS					95.30 2	71.25 61		92.95 56	66.81 298	92.39 6				88.94 25	96.63 4	94.85 21

save fliter					93.80 40	72.35 44	90.47 69	91.17 132	74.31 139

test_0728_SECOND				87.71 32	95.34 1	71.43 60	93.49 10	94.23 3					97.49 4	89.08 20	96.41 12	94.21 53

GSMVS																88.96 284

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 300				88.96 284

sam_mvs												50.01 316

MTGPA								92.02 98

MTMP							92.18 35	32.83 462

test9_res														84.90 57	95.70 26	92.87 127

agg_prior2														82.91 84	95.45 29	92.70 132

agg_prior					92.85 64	71.94 52		91.78 113		84.41 88			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 67

旧先验2							86.56 213		58.10 398	87.04 55			88.98 316	74.07 179

新几何2							86.29 223

无先验							87.48 177	88.98 216	60.00 379				94.12 134	67.28 253		88.97 283

原ACMM2							86.86 201

testdata2													91.01 279	62.37 294

segment_acmp												73.08 40

testdata1							84.14 282		75.71 100

test12				86.80 54	92.63 69	70.70 77		91.79 112		82.71 119		71.67 58	96.16 48		94.50 53	93.54 95

plane_prior7					90.08 112	68.51 127

plane_prior6					89.84 121	68.70 121						60.42 211

plane_prior5								92.44 78					95.38 78	78.71 125	86.32 181	91.33 187

plane_prior3						68.60 124			78.44 36	78.92 175

plane_prior2							91.25 55		79.12 28

plane_prior1					89.90 120

plane_prior						68.71 119	90.38 73		77.62 47						86.16 185

n2								0.00 469

nn								0.00 469

door-mid								69.98 425

test11								92.23 88

door								69.44 428

HQP5-MVS						66.98 177

HQP-NCC					89.33 140		89.17 109		76.41 85	77.23 216

ACMP_Plane					89.33 140		89.17 109		76.41 85	77.23 216

BP-MVS														77.47 139

HQP4-MVS										77.24 215			95.11 90			91.03 197

HQP3-MVS								92.19 92							85.99 189

HQP2-MVS												60.17 214

MDTV_nov1_ep13_2view						37.79 450	75.16 398		55.10 413	66.53 382		49.34 326		53.98 366		87.94 312

ACMMP++_ref															81.95 258

ACMMP++															81.25 263

Test By Simon												64.33 145

High-resolution multi-view benchmark