High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

MM		89.16 6	89.23 7	88.97 4	90.79 95	73.65 10	92.66 23	91.17 125	86.57 1	87.39 43	94.97 18	71.70 53	97.68 1	92.19 1	95.63 28	95.57 1

casdiffmvs_mvg		85.99 48	86.09 50	85.70 74	87.65 209	67.22 159	88.69 124	93.04 41	79.64 18	85.33 61	92.54 88	73.30 35	94.50 112	83.49 67	91.14 95	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
dcpmvs_2		85.63 58	86.15 48	84.06 133	91.71 78	64.94 203	86.47 198	91.87 103	73.63 141	86.60 52	93.02 77	76.57 15	91.87 225	83.36 68	92.15 80	95.35 3

casdiffmvs		85.11 67	85.14 67	85.01 90	87.20 223	65.77 185	87.75 157	92.83 60	77.84 37	84.36 82	92.38 90	72.15 46	93.93 134	81.27 92	90.48 102	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
3Dnovator+	77.84 4	85.48 60	84.47 76	88.51 7	91.08 86	73.49 16	93.18 11	93.78 18	80.79 8	76.66 205	93.37 67	60.40 198	96.75 26	77.20 127	93.73 64	95.29 5

BP-MVS1		84.32 75	83.71 83	86.17 61	87.84 199	67.85 138	89.38 98	89.64 171	77.73 38	83.98 89	92.12 95	56.89 222	95.43 70	84.03 64	91.75 87	95.24 6

MVS_0304		87.69 20	87.55 24	88.12 13	89.45 129	71.76 51	91.47 49	89.54 173	82.14 3	86.65 51	94.28 35	68.28 95	97.46 6	90.81 2	95.31 34	95.15 7

CS-MVS		86.69 39	86.95 35	85.90 71	90.76 96	67.57 147	92.83 17	93.30 32	79.67 17	84.57 78	92.27 91	71.47 56	95.02 93	84.24 61	93.46 67	95.13 8

TSAR-MVS + MP.		88.02 17	88.11 16	87.72 30	93.68 43	72.13 46	91.41 50	92.35 82	74.62 119	88.90 22	93.85 57	75.75 20	96.00 54	87.80 30	94.63 48	95.04 9
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
baseline		84.93 70	84.98 68	84.80 100	87.30 221	65.39 193	87.30 171	92.88 57	77.62 40	84.04 88	92.26 92	71.81 50	93.96 128	81.31 90	90.30 105	95.03 10

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 59	95.06 1	94.23 3	78.38 33	92.78 4	95.74 6	82.45 3	97.49 4	89.42 11	96.68 2	94.95 11

PC_three_1452									68.21 256	92.02 12	94.00 51	82.09 5	95.98 56	84.58 55	96.68 2	94.95 11

IS-MVSNet		83.15 99	82.81 98	84.18 123	89.94 115	63.30 239	91.59 43	88.46 213	79.04 25	79.49 145	92.16 93	65.10 128	94.28 117	67.71 221	91.86 86	94.95 11

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 72	72.96 25	93.73 5	93.67 20	80.19 12	88.10 29	94.80 19	73.76 33	97.11 15	87.51 33	95.82 21	94.90 14
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 66	93.57 7	94.06 10	77.24 53	93.10 1	95.72 8	82.99 1	97.44 7	89.07 16	96.63 4	94.88 15

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 49	82.45 3	96.87 20	83.77 66	96.48 8	94.88 15

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 115	92.29 7	95.97 2	74.28 29	97.24 13	88.58 23	96.91 1	94.87 17
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
test2506		77.30 229	76.49 226	79.74 254	90.08 108	52.02 370	87.86 156	63.10 408	74.88 111	80.16 138	92.79 84	38.29 374	92.35 207	68.74 214	92.50 77	94.86 18

ECVR-MVS		79.61 167	79.26 160	80.67 236	90.08 108	54.69 353	87.89 154	77.44 362	74.88 111	80.27 135	92.79 84	48.96 306	92.45 201	68.55 215	92.50 77	94.86 18

IU-MVS					95.30 2	71.25 59		92.95 55	66.81 267	92.39 6				88.94 18	96.63 4	94.85 20

test1111		79.43 174	79.18 163	80.15 246	89.99 113	53.31 366	87.33 170	77.05 366	75.04 106	80.23 137	92.77 86	48.97 305	92.33 209	68.87 212	92.40 79	94.81 21

SF-MVS		88.46 12	88.74 12	87.64 35	92.78 64	71.95 49	92.40 24	94.74 2	75.71 92	89.16 19	95.10 16	75.65 21	96.19 46	87.07 36	96.01 17	94.79 22

balanced_conf03		86.78 37	86.99 33	86.15 63	91.24 83	67.61 145	90.51 62	92.90 56	77.26 52	87.44 42	91.63 107	71.27 60	96.06 49	85.62 44	95.01 37	94.78 23

sasdasda		85.91 52	85.87 54	86.04 67	89.84 117	69.44 98	90.45 68	93.00 46	76.70 72	88.01 32	91.23 119	73.28 36	93.91 135	81.50 88	88.80 128	94.77 24

SPE-MVS-test		86.29 46	86.48 41	85.71 73	91.02 88	67.21 160	92.36 29	93.78 18	78.97 28	83.51 99	91.20 122	70.65 69	95.15 84	81.96 85	94.89 42	94.77 24

canonicalmvs		85.91 52	85.87 54	86.04 67	89.84 117	69.44 98	90.45 68	93.00 46	76.70 72	88.01 32	91.23 119	73.28 36	93.91 135	81.50 88	88.80 128	94.77 24

GDP-MVS		83.52 91	82.64 101	86.16 62	88.14 183	68.45 124	89.13 108	92.69 65	72.82 164	83.71 94	91.86 101	55.69 227	95.35 79	80.03 103	89.74 116	94.69 27

test_0728_THIRD									78.38 33	92.12 9	95.78 4	81.46 7	97.40 9	89.42 11	96.57 7	94.67 28

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 16	94.11 6	80.27 10	91.35 14	94.16 42	78.35 13	96.77 24	89.59 10	94.22 60	94.67 28
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
RRT-MVS		82.60 110	82.10 109	84.10 125	87.98 193	62.94 250	87.45 166	91.27 121	77.42 49	79.85 140	90.28 142	56.62 224	94.70 107	79.87 106	88.15 140	94.67 28

MGCFI-Net		85.06 69	85.51 59	83.70 149	89.42 130	63.01 245	89.43 93	92.62 73	76.43 76	87.53 40	91.34 117	72.82 42	93.42 161	81.28 91	88.74 131	94.66 31

alignmvs		85.48 60	85.32 64	85.96 70	89.51 126	69.47 95	89.74 83	92.47 76	76.17 85	87.73 39	91.46 114	70.32 71	93.78 141	81.51 87	88.95 125	94.63 32

MP-MVS-pluss		87.67 21	87.72 20	87.54 36	93.64 44	72.04 48	89.80 81	93.50 25	75.17 105	86.34 53	95.29 15	70.86 65	96.00 54	88.78 21	96.04 16	94.58 33
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepPCF-MVS	80.84 1	88.10 13	88.56 13	86.73 53	92.24 71	69.03 103	89.57 90	93.39 30	77.53 46	89.79 18	94.12 44	78.98 12	96.58 35	85.66 42	95.72 24	94.58 33

VDD-MVS		83.01 104	82.36 105	84.96 92	91.02 88	66.40 170	88.91 114	88.11 216	77.57 42	84.39 81	93.29 69	52.19 259	93.91 135	77.05 130	88.70 132	94.57 35

VDDNet		81.52 127	80.67 130	84.05 136	90.44 101	64.13 221	89.73 84	85.91 264	71.11 189	83.18 101	93.48 63	50.54 285	93.49 155	73.40 167	88.25 138	94.54 36

MVSMamba_PlusPlus		85.99 48	85.96 52	86.05 66	91.09 85	67.64 144	89.63 88	92.65 70	72.89 163	84.64 75	91.71 103	71.85 49	96.03 50	84.77 53	94.45 54	94.49 37

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 94	91.06 16	96.03 1	76.84 14	97.03 17	89.09 13	95.65 27	94.47 38
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 8	96.44 9	94.41 39

No_MVS				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 8	96.44 9	94.41 39

MCST-MVS		87.37 29	87.25 29	87.73 28	94.53 17	72.46 38	89.82 79	93.82 16	73.07 158	84.86 70	92.89 79	76.22 17	96.33 41	84.89 50	95.13 36	94.40 41

CANet		86.45 42	86.10 49	87.51 37	90.09 107	70.94 70	89.70 85	92.59 74	81.78 4	81.32 123	91.43 115	70.34 70	97.23 14	84.26 59	93.36 68	94.37 42

PHI-MVS		86.43 43	86.17 47	87.24 41	90.88 92	70.96 68	92.27 32	94.07 9	72.45 165	85.22 63	91.90 98	69.47 80	96.42 40	83.28 70	95.94 19	94.35 43

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 62	93.00 46	80.90 7	88.06 30	94.06 47	76.43 16	96.84 21	88.48 26	95.99 18	94.34 44

ZNCC-MVS		87.94 18	87.85 19	88.20 12	94.39 24	73.33 19	93.03 14	93.81 17	76.81 66	85.24 62	94.32 34	71.76 51	96.93 19	85.53 45	95.79 22	94.32 45

HPM-MVS		87.11 33	86.98 34	87.50 38	93.88 39	72.16 45	92.19 33	93.33 31	76.07 87	83.81 93	93.95 56	69.77 78	96.01 53	85.15 46	94.66 47	94.32 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CDPH-MVS		85.76 56	85.29 66	87.17 43	93.49 47	71.08 64	88.58 128	92.42 80	68.32 255	84.61 76	93.48 63	72.32 44	96.15 48	79.00 108	95.43 30	94.28 47

test_241102_TWO								94.06 10	77.24 53	92.78 4	95.72 8	81.26 8	97.44 7	89.07 16	96.58 6	94.26 48

test_0728_SECOND				87.71 32	95.34 1	71.43 58	93.49 9	94.23 3					97.49 4	89.08 14	96.41 12	94.21 49

DeepC-MVS_fast	79.65 3	86.91 36	86.62 40	87.76 27	93.52 46	72.37 41	91.26 51	93.04 41	76.62 74	84.22 83	93.36 68	71.44 57	96.76 25	80.82 96	95.33 33	94.16 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EPP-MVSNet		83.40 95	83.02 94	84.57 104	90.13 106	64.47 214	92.32 30	90.73 137	74.45 123	79.35 147	91.10 125	69.05 87	95.12 85	72.78 174	87.22 151	94.13 51

NCCC		88.06 14	88.01 18	88.24 11	94.41 22	73.62 11	91.22 54	92.83 60	81.50 5	85.79 57	93.47 65	73.02 40	97.00 18	84.90 48	94.94 40	94.10 52

ACMMP_NAP		88.05 16	88.08 17	87.94 19	93.70 41	73.05 22	90.86 57	93.59 23	76.27 84	88.14 28	95.09 17	71.06 63	96.67 29	87.67 31	96.37 14	94.09 53

XVS		87.18 32	86.91 37	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 21	83.67 96	94.17 41	67.45 103	96.60 33	83.06 71	94.50 51	94.07 54

X-MVStestdata		80.37 156	77.83 192	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 21	83.67 96	12.47 422	67.45 103	96.60 33	83.06 71	94.50 51	94.07 54

region2R		87.42 27	87.20 31	88.09 14	94.63 14	73.55 13	93.03 14	93.12 40	76.73 71	84.45 79	94.52 23	69.09 84	96.70 27	84.37 58	94.83 45	94.03 56

ACMMPR		87.44 25	87.23 30	88.08 15	94.64 13	73.59 12	93.04 12	93.20 34	76.78 68	84.66 74	94.52 23	68.81 90	96.65 30	84.53 56	94.90 41	94.00 57

fmvsm_s_conf0.1_n_2		83.80 82	83.79 82	83.83 146	85.62 250	64.94 203	87.03 178	86.62 253	74.32 125	87.97 34	94.33 33	60.67 190	92.60 194	89.72 7	87.79 143	93.96 58

test_fmvsmconf_n		85.92 51	86.04 51	85.57 76	85.03 264	69.51 93	89.62 89	90.58 140	73.42 149	87.75 37	94.02 49	72.85 41	93.24 166	90.37 3	90.75 99	93.96 58

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 43	94.10 8	75.90 90	92.29 7	95.66 10	81.67 6	97.38 11	87.44 35	96.34 15	93.95 60
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_fmvsm_n_1920		85.29 65	85.34 62	85.13 87	86.12 242	69.93 86	88.65 126	90.78 136	69.97 216	88.27 26	93.98 54	71.39 58	91.54 237	88.49 25	90.45 103	93.91 61

test_prior				86.33 57	92.61 68	69.59 91		92.97 54					95.48 67			93.91 61

GST-MVS		87.42 27	87.26 28	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 64	84.68 71	93.99 53	70.67 68	96.82 22	84.18 63	95.01 37	93.90 63

test_fmvsmconf0.1_n		85.61 59	85.65 57	85.50 77	82.99 311	69.39 100	89.65 86	90.29 153	73.31 152	87.77 36	94.15 43	71.72 52	93.23 167	90.31 4	90.67 101	93.89 64

Anonymous202405211		78.25 202	77.01 212	81.99 203	91.03 87	60.67 277	84.77 240	83.90 289	70.65 202	80.00 139	91.20 122	41.08 360	91.43 244	65.21 243	85.26 178	93.85 65

LFMVS		81.82 120	81.23 121	83.57 153	91.89 76	63.43 237	89.84 78	81.85 322	77.04 61	83.21 100	93.10 72	52.26 258	93.43 160	71.98 180	89.95 113	93.85 65

fmvsm_s_conf0.5_n_2		84.04 78	84.11 79	83.81 147	86.17 240	65.00 201	86.96 180	87.28 237	74.35 124	88.25 27	94.23 39	61.82 166	92.60 194	89.85 6	88.09 141	93.84 67

Effi-MVS+		83.62 89	83.08 92	85.24 83	88.38 175	67.45 149	88.89 115	89.15 189	75.50 97	82.27 111	88.28 195	69.61 79	94.45 114	77.81 121	87.84 142	93.84 67

Anonymous20240529		80.19 160	78.89 168	84.10 125	90.60 97	64.75 208	88.95 113	90.90 132	65.97 284	80.59 133	91.17 124	49.97 290	93.73 147	69.16 209	82.70 221	93.81 69

MVS_Test		83.15 99	83.06 93	83.41 158	86.86 227	63.21 241	86.11 209	92.00 95	74.31 126	82.87 105	89.44 167	70.03 74	93.21 169	77.39 126	88.50 136	93.81 69

test_fmvsmconf0.01_n		84.73 73	84.52 75	85.34 80	80.25 352	69.03 103	89.47 91	89.65 170	73.24 156	86.98 48	94.27 36	66.62 109	93.23 167	90.26 5	89.95 113	93.78 71

GeoE		81.71 122	81.01 126	83.80 148	89.51 126	64.45 215	88.97 112	88.73 208	71.27 186	78.63 159	89.76 153	66.32 115	93.20 172	69.89 201	86.02 171	93.74 72

diffmvs		82.10 113	81.88 115	82.76 191	83.00 309	63.78 227	83.68 265	89.76 166	72.94 161	82.02 114	89.85 151	65.96 122	90.79 261	82.38 83	87.30 150	93.71 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HFP-MVS		87.58 22	87.47 26	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 68	84.91 67	94.44 30	70.78 66	96.61 32	84.53 56	94.89 42	93.66 74

VNet		82.21 112	82.41 103	81.62 209	90.82 93	60.93 272	84.47 248	89.78 165	76.36 82	84.07 87	91.88 99	64.71 132	90.26 267	70.68 192	88.89 126	93.66 74

PGM-MVS		86.68 40	86.27 44	87.90 22	94.22 33	73.38 18	90.22 73	93.04 41	75.53 96	83.86 91	94.42 31	67.87 100	96.64 31	82.70 81	94.57 50	93.66 74

DELS-MVS		85.41 63	85.30 65	85.77 72	88.49 169	67.93 137	85.52 228	93.44 27	78.70 29	83.63 98	89.03 174	74.57 24	95.71 61	80.26 102	94.04 61	93.66 74
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
SD-MVS		88.06 14	88.50 14	86.71 54	92.60 69	72.71 29	91.81 41	93.19 35	77.87 36	90.32 17	94.00 51	74.83 23	93.78 141	87.63 32	94.27 59	93.65 78
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
DeepC-MVS	79.81 2	87.08 35	86.88 38	87.69 33	91.16 84	72.32 43	90.31 71	93.94 14	77.12 58	82.82 107	94.23 39	72.13 47	97.09 16	84.83 51	95.37 31	93.65 78
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
patch_mono-2		83.65 86	84.54 73	80.99 228	90.06 112	65.83 182	84.21 257	88.74 207	71.60 180	85.01 64	92.44 89	74.51 25	83.50 347	82.15 84	92.15 80	93.64 80

EIA-MVS		83.31 98	82.80 99	84.82 98	89.59 122	65.59 188	88.21 141	92.68 66	74.66 118	78.96 151	86.42 250	69.06 86	95.26 80	75.54 147	90.09 109	93.62 81

MP-MVS		87.71 19	87.64 21	87.93 21	94.36 26	73.88 6	92.71 22	92.65 70	77.57 42	83.84 92	94.40 32	72.24 45	96.28 43	85.65 43	95.30 35	93.62 81
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		85.35 64	84.95 70	86.57 56	93.69 42	70.58 78	92.15 35	91.62 111	73.89 136	82.67 110	94.09 45	62.60 152	95.54 65	80.93 94	92.93 71	93.57 83

fmvsm_s_conf0.1_n		83.56 90	83.38 88	84.10 125	84.86 266	67.28 155	89.40 97	83.01 306	70.67 198	87.08 46	93.96 55	68.38 93	91.45 243	88.56 24	84.50 186	93.56 84

CSCG		86.41 45	86.19 46	87.07 45	92.91 61	72.48 37	90.81 58	93.56 24	73.95 133	83.16 102	91.07 127	75.94 18	95.19 82	79.94 105	94.38 56	93.55 85

test12				86.80 52	92.63 67	70.70 75		91.79 107		82.71 109		71.67 54	96.16 47		94.50 51	93.54 86

APD-MVS_3200maxsize		85.97 50	85.88 53	86.22 60	92.69 66	69.53 92	91.93 37	92.99 49	73.54 145	85.94 54	94.51 26	65.80 123	95.61 62	83.04 73	92.51 76	93.53 87

mvs_anonymous		79.42 175	79.11 164	80.34 242	84.45 275	57.97 305	82.59 284	87.62 230	67.40 265	76.17 220	88.56 188	68.47 92	89.59 280	70.65 193	86.05 170	93.47 88

fmvsm_s_conf0.5_n		83.80 82	83.71 83	84.07 131	86.69 233	67.31 154	89.46 92	83.07 305	71.09 190	86.96 49	93.70 60	69.02 89	91.47 242	88.79 20	84.62 185	93.44 89

mPP-MVS		86.67 41	86.32 43	87.72 30	94.41 22	73.55 13	92.74 20	92.22 88	76.87 65	82.81 108	94.25 38	66.44 113	96.24 44	82.88 76	94.28 58	93.38 90

EPNet		83.72 85	82.92 97	86.14 65	84.22 278	69.48 94	91.05 56	85.27 270	81.30 6	76.83 200	91.65 105	66.09 118	95.56 63	76.00 141	93.85 62	93.38 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Vis-MVSNet		83.46 93	82.80 99	85.43 79	90.25 104	68.74 114	90.30 72	90.13 157	76.33 83	80.87 131	92.89 79	61.00 185	94.20 122	72.45 179	90.97 96	93.35 92
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 59	93.49 9	92.73 64	77.33 50	92.12 9	95.78 4	80.98 9	97.40 9	89.08 14	96.41 12	93.33 93
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
UniMVSNet_ETH3D		79.10 184	78.24 182	81.70 208	86.85 228	60.24 284	87.28 172	88.79 202	74.25 128	76.84 199	90.53 140	49.48 296	91.56 235	67.98 219	82.15 225	93.29 94

EI-MVSNet-Vis-set		84.19 76	83.81 81	85.31 81	88.18 180	67.85 138	87.66 159	89.73 168	80.05 14	82.95 103	89.59 159	70.74 67	94.82 101	80.66 99	84.72 183	93.28 95

MTAPA		87.23 31	87.00 32	87.90 22	94.18 35	74.25 5	86.58 195	92.02 93	79.45 19	85.88 55	94.80 19	68.07 96	96.21 45	86.69 38	95.34 32	93.23 96

CP-MVS		87.11 33	86.92 36	87.68 34	94.20 34	73.86 7	93.98 3	92.82 63	76.62 74	83.68 95	94.46 27	67.93 98	95.95 57	84.20 62	94.39 55	93.23 96

ACMMP		85.89 54	85.39 61	87.38 39	93.59 45	72.63 33	92.74 20	93.18 39	76.78 68	80.73 132	93.82 58	64.33 133	96.29 42	82.67 82	90.69 100	93.23 96
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_conf0.1_n_a		83.32 97	82.99 95	84.28 117	83.79 288	68.07 134	89.34 100	82.85 311	69.80 220	87.36 44	94.06 47	68.34 94	91.56 235	87.95 29	83.46 210	93.21 99

PAPM_NR		83.02 103	82.41 103	84.82 98	92.47 70	66.37 171	87.93 152	91.80 106	73.82 137	77.32 188	90.66 137	67.90 99	94.90 97	70.37 195	89.48 119	93.19 100

reproduce_model		87.28 30	87.39 27	86.95 48	93.10 56	71.24 63	91.60 42	93.19 35	74.69 116	88.80 23	95.61 11	70.29 72	96.44 39	86.20 41	93.08 69	93.16 101

OMC-MVS		82.69 106	81.97 114	84.85 97	88.75 161	67.42 150	87.98 148	90.87 134	74.92 110	79.72 142	91.65 105	62.19 162	93.96 128	75.26 151	86.42 163	93.16 101

fmvsm_s_conf0.5_n_a		83.63 88	83.41 87	84.28 117	86.14 241	68.12 132	89.43 93	82.87 310	70.27 209	87.27 45	93.80 59	69.09 84	91.58 233	88.21 28	83.65 205	93.14 103

PAPR		81.66 125	80.89 128	83.99 141	90.27 103	64.00 222	86.76 191	91.77 109	68.84 246	77.13 198	89.50 160	67.63 101	94.88 99	67.55 223	88.52 135	93.09 104

UA-Net		85.08 68	84.96 69	85.45 78	92.07 73	68.07 134	89.78 82	90.86 135	82.48 2	84.60 77	93.20 71	69.35 81	95.22 81	71.39 185	90.88 98	93.07 105

reproduce-ours		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 108	88.96 20	95.54 12	71.20 61	96.54 36	86.28 39	93.49 65	93.06 106

our_new_method		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 108	88.96 20	95.54 12	71.20 61	96.54 36	86.28 39	93.49 65	93.06 106

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 27	92.85 59	80.26 11	87.78 35	94.27 36	75.89 19	96.81 23	87.45 34	96.44 9	93.05 108

thisisatest0530		79.40 176	77.76 197	84.31 115	87.69 208	65.10 199	87.36 168	84.26 285	70.04 212	77.42 185	88.26 197	49.94 291	94.79 103	70.20 196	84.70 184	93.03 109

train_agg		86.43 43	86.20 45	87.13 44	93.26 52	72.96 25	88.75 120	91.89 101	68.69 248	85.00 65	93.10 72	74.43 26	95.41 73	84.97 47	95.71 25	93.02 110

EC-MVSNet		86.01 47	86.38 42	84.91 96	89.31 138	66.27 173	92.32 30	93.63 21	79.37 20	84.17 85	91.88 99	69.04 88	95.43 70	83.93 65	93.77 63	93.01 111

mvsmamba		80.60 148	79.38 155	84.27 119	89.74 120	67.24 158	87.47 164	86.95 245	70.02 213	75.38 236	88.93 175	51.24 276	92.56 197	75.47 149	89.22 122	93.00 112

EI-MVSNet-UG-set		83.81 81	83.38 88	85.09 88	87.87 197	67.53 148	87.44 167	89.66 169	79.74 16	82.23 112	89.41 168	70.24 73	94.74 104	79.95 104	83.92 197	92.99 113

tttt0517		79.40 176	77.91 189	83.90 145	88.10 186	63.84 225	88.37 136	84.05 287	71.45 183	76.78 202	89.12 171	49.93 293	94.89 98	70.18 197	83.18 214	92.96 114

test9_res														84.90 48	95.70 26	92.87 115

SR-MVS		86.73 38	86.67 39	86.91 49	94.11 37	72.11 47	92.37 28	92.56 75	74.50 120	86.84 50	94.65 22	67.31 105	95.77 59	84.80 52	92.85 72	92.84 116

ETV-MVS		84.90 72	84.67 72	85.59 75	89.39 133	68.66 120	88.74 122	92.64 72	79.97 15	84.10 86	85.71 263	69.32 82	95.38 75	80.82 96	91.37 92	92.72 117

agg_prior2														82.91 75	95.45 29	92.70 118

APD-MVS		87.44 25	87.52 25	87.19 42	94.24 32	72.39 39	91.86 40	92.83 60	73.01 160	88.58 24	94.52 23	73.36 34	96.49 38	84.26 59	95.01 37	92.70 118
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ET-MVSNet_ETH3D		78.63 195	76.63 225	84.64 103	86.73 232	69.47 95	85.01 235	84.61 278	69.54 226	66.51 352	86.59 243	50.16 288	91.75 228	76.26 137	84.24 194	92.69 120

Vis-MVSNet (Re-imp)		78.36 201	78.45 175	78.07 287	88.64 165	51.78 376	86.70 192	79.63 347	74.14 131	75.11 249	90.83 135	61.29 179	89.75 277	58.10 309	91.60 88	92.69 120

TSAR-MVS + GP.		85.71 57	85.33 63	86.84 50	91.34 81	72.50 36	89.07 110	87.28 237	76.41 77	85.80 56	90.22 146	74.15 31	95.37 78	81.82 86	91.88 83	92.65 122

test_fmvsmvis_n_1920		84.02 79	83.87 80	84.49 108	84.12 280	69.37 101	88.15 145	87.96 221	70.01 214	83.95 90	93.23 70	68.80 91	91.51 240	88.61 22	89.96 112	92.57 123

FA-MVS(test-final)		80.96 136	79.91 144	84.10 125	88.30 178	65.01 200	84.55 247	90.01 160	73.25 155	79.61 143	87.57 212	58.35 207	94.72 105	71.29 186	86.25 166	92.56 124

test_yl		81.17 132	80.47 134	83.24 164	89.13 146	63.62 228	86.21 206	89.95 162	72.43 168	81.78 119	89.61 157	57.50 215	93.58 149	70.75 190	86.90 155	92.52 125

DCV-MVSNet		81.17 132	80.47 134	83.24 164	89.13 146	63.62 228	86.21 206	89.95 162	72.43 168	81.78 119	89.61 157	57.50 215	93.58 149	70.75 190	86.90 155	92.52 125

SR-MVS-dyc-post		85.77 55	85.61 58	86.23 59	93.06 58	70.63 76	91.88 38	92.27 84	73.53 146	85.69 58	94.45 28	65.00 131	95.56 63	82.75 77	91.87 84	92.50 127

RE-MVS-def			85.48 60		93.06 58	70.63 76	91.88 38	92.27 84	73.53 146	85.69 58	94.45 28	63.87 137		82.75 77	91.87 84	92.50 127

nrg030		83.88 80	83.53 85	84.96 92	86.77 231	69.28 102	90.46 67	92.67 67	74.79 114	82.95 103	91.33 118	72.70 43	93.09 180	80.79 98	79.28 261	92.50 127

MG-MVS		83.41 94	83.45 86	83.28 161	92.74 65	62.28 257	88.17 143	89.50 175	75.22 101	81.49 122	92.74 87	66.75 108	95.11 87	72.85 173	91.58 89	92.45 130

FIs		82.07 115	82.42 102	81.04 227	88.80 158	58.34 299	88.26 140	93.49 26	76.93 63	78.47 164	91.04 128	69.92 76	92.34 208	69.87 202	84.97 180	92.44 131

FC-MVSNet-test		81.52 127	82.02 112	80.03 248	88.42 174	55.97 338	87.95 150	93.42 29	77.10 59	77.38 186	90.98 134	69.96 75	91.79 226	68.46 217	84.50 186	92.33 132

Fast-Effi-MVS+		80.81 140	79.92 143	83.47 154	88.85 153	64.51 211	85.53 226	89.39 178	70.79 195	78.49 163	85.06 281	67.54 102	93.58 149	67.03 231	86.58 160	92.32 133

TranMVSNet+NR-MVSNet		80.84 138	80.31 137	82.42 196	87.85 198	62.33 255	87.74 158	91.33 120	80.55 9	77.99 176	89.86 150	65.23 127	92.62 192	67.05 230	75.24 319	92.30 134

ab-mvs		79.51 170	78.97 167	81.14 224	88.46 171	60.91 273	83.84 262	89.24 185	70.36 205	79.03 150	88.87 178	63.23 144	90.21 269	65.12 244	82.57 222	92.28 135

CANet_DTU		80.61 147	79.87 145	82.83 183	85.60 251	63.17 244	87.36 168	88.65 209	76.37 81	75.88 223	88.44 191	53.51 248	93.07 181	73.30 168	89.74 116	92.25 136

UniMVSNet_NR-MVSNet		81.88 118	81.54 118	82.92 180	88.46 171	63.46 235	87.13 174	92.37 81	80.19 12	78.38 165	89.14 170	71.66 55	93.05 182	70.05 198	76.46 292	92.25 136

fmvsm_l_conf0.5_n		84.47 74	84.54 73	84.27 119	85.42 254	68.81 109	88.49 130	87.26 239	68.08 257	88.03 31	93.49 62	72.04 48	91.77 227	88.90 19	89.14 124	92.24 138

DU-MVS		81.12 134	80.52 133	82.90 181	87.80 201	63.46 235	87.02 179	91.87 103	79.01 26	78.38 165	89.07 172	65.02 129	93.05 182	70.05 198	76.46 292	92.20 139

NR-MVSNet		80.23 158	79.38 155	82.78 189	87.80 201	63.34 238	86.31 203	91.09 129	79.01 26	72.17 290	89.07 172	67.20 106	92.81 191	66.08 237	75.65 305	92.20 139

TAPA-MVS	73.13 9	79.15 182	77.94 188	82.79 188	89.59 122	62.99 249	88.16 144	91.51 115	65.77 285	77.14 197	91.09 126	60.91 186	93.21 169	50.26 356	87.05 153	92.17 141
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_l_conf0.5_n_a		84.13 77	84.16 78	84.06 133	85.38 255	68.40 125	88.34 137	86.85 249	67.48 264	87.48 41	93.40 66	70.89 64	91.61 231	88.38 27	89.22 122	92.16 142

3Dnovator	76.31 5	83.38 96	82.31 106	86.59 55	87.94 194	72.94 28	90.64 60	92.14 92	77.21 55	75.47 230	92.83 81	58.56 205	94.72 105	73.24 170	92.71 74	92.13 143

MVS_111021_HR		85.14 66	84.75 71	86.32 58	91.65 79	72.70 30	85.98 211	90.33 150	76.11 86	82.08 113	91.61 109	71.36 59	94.17 124	81.02 93	92.58 75	92.08 144

MVSFormer		82.85 105	82.05 111	85.24 83	87.35 215	70.21 80	90.50 64	90.38 146	68.55 250	81.32 123	89.47 162	61.68 168	93.46 158	78.98 109	90.26 106	92.05 145

jason		81.39 130	80.29 138	84.70 102	86.63 235	69.90 88	85.95 212	86.77 250	63.24 315	81.07 129	89.47 162	61.08 184	92.15 214	78.33 117	90.07 111	92.05 145
jason: jason.
HyFIR lowres test		77.53 224	75.40 243	83.94 144	89.59 122	66.62 167	80.36 315	88.64 210	56.29 375	76.45 210	85.17 278	57.64 213	93.28 164	61.34 280	83.10 215	91.91 147

XVG-OURS-SEG-HR		80.81 140	79.76 147	83.96 143	85.60 251	68.78 111	83.54 271	90.50 143	70.66 201	76.71 204	91.66 104	60.69 189	91.26 248	76.94 131	81.58 232	91.83 148

lupinMVS		81.39 130	80.27 139	84.76 101	87.35 215	70.21 80	85.55 224	86.41 255	62.85 322	81.32 123	88.61 185	61.68 168	92.24 212	78.41 116	90.26 106	91.83 148

WR-MVS		79.49 171	79.22 162	80.27 244	88.79 159	58.35 298	85.06 234	88.61 211	78.56 30	77.65 181	88.34 193	63.81 139	90.66 264	64.98 246	77.22 281	91.80 150

h-mvs33		83.15 99	82.19 107	86.02 69	90.56 98	70.85 73	88.15 145	89.16 188	76.02 88	84.67 72	91.39 116	61.54 171	95.50 66	82.71 79	75.48 309	91.72 151

UniMVSNet (Re)		81.60 126	81.11 123	83.09 171	88.38 175	64.41 216	87.60 160	93.02 45	78.42 32	78.56 161	88.16 199	69.78 77	93.26 165	69.58 205	76.49 291	91.60 152

UGNet		80.83 139	79.59 151	84.54 105	88.04 189	68.09 133	89.42 95	88.16 215	76.95 62	76.22 216	89.46 164	49.30 300	93.94 131	68.48 216	90.31 104	91.60 152
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
testing91		76.54 239	75.66 238	79.18 266	88.43 173	55.89 339	81.08 301	83.00 307	73.76 139	75.34 238	84.29 296	46.20 325	90.07 271	64.33 250	84.50 186	91.58 154

XVG-OURS		80.41 153	79.23 161	83.97 142	85.64 249	69.02 105	83.03 282	90.39 145	71.09 190	77.63 182	91.49 113	54.62 239	91.35 246	75.71 143	83.47 209	91.54 155

LCM-MVSNet-Re		77.05 231	76.94 215	77.36 298	87.20 223	51.60 377	80.06 318	80.46 337	75.20 102	67.69 334	86.72 235	62.48 155	88.98 292	63.44 256	89.25 121	91.51 156

DP-MVS Recon		83.11 102	82.09 110	86.15 63	94.44 19	70.92 71	88.79 118	92.20 89	70.53 203	79.17 149	91.03 130	64.12 135	96.03 50	68.39 218	90.14 108	91.50 157

PS-MVSNAJss		82.07 115	81.31 119	84.34 114	86.51 236	67.27 156	89.27 101	91.51 115	71.75 175	79.37 146	90.22 146	63.15 146	94.27 118	77.69 122	82.36 224	91.49 158

testing99		76.09 251	75.12 249	79.00 267	88.16 181	55.50 345	80.79 305	81.40 326	73.30 153	75.17 246	84.27 298	44.48 339	90.02 272	64.28 251	84.22 195	91.48 159

thisisatest0515		77.33 228	75.38 244	83.18 167	85.27 257	63.80 226	82.11 289	83.27 299	65.06 294	75.91 222	83.84 305	49.54 295	94.27 118	67.24 227	86.19 167	91.48 159

DPM-MVS		84.93 70	84.29 77	86.84 50	90.20 105	73.04 23	87.12 175	93.04 41	69.80 220	82.85 106	91.22 121	73.06 39	96.02 52	76.72 135	94.63 48	91.46 161

HQP_MVS		83.64 87	83.14 91	85.14 85	90.08 108	68.71 116	91.25 52	92.44 77	79.12 23	78.92 153	91.00 132	60.42 196	95.38 75	78.71 112	86.32 164	91.33 162

plane_prior5								92.44 77					95.38 75	78.71 112	86.32 164	91.33 162

GA-MVS		76.87 235	75.17 248	81.97 204	82.75 315	62.58 252	81.44 298	86.35 258	72.16 172	74.74 256	82.89 325	46.20 325	92.02 218	68.85 213	81.09 237	91.30 164

VPA-MVSNet		80.60 148	80.55 132	80.76 234	88.07 188	60.80 275	86.86 185	91.58 113	75.67 95	80.24 136	89.45 166	63.34 140	90.25 268	70.51 194	79.22 262	91.23 165

Effi-MVS+-dtu		80.03 162	78.57 173	84.42 110	85.13 262	68.74 114	88.77 119	88.10 217	74.99 107	74.97 253	83.49 314	57.27 218	93.36 162	73.53 164	80.88 239	91.18 166

v2v482		80.23 158	79.29 159	83.05 174	83.62 292	64.14 220	87.04 177	89.97 161	73.61 142	78.18 171	87.22 223	61.10 183	93.82 139	76.11 138	76.78 289	91.18 166

FE-MVS		77.78 217	75.68 236	84.08 130	88.09 187	66.00 177	83.13 277	87.79 227	68.42 254	78.01 175	85.23 276	45.50 334	95.12 85	59.11 297	85.83 175	91.11 168

Anonymous20231211		78.97 188	77.69 200	82.81 185	90.54 99	64.29 218	90.11 75	91.51 115	65.01 296	76.16 221	88.13 204	50.56 284	93.03 185	69.68 204	77.56 279	91.11 168

hse-mvs2		81.72 121	80.94 127	84.07 131	88.72 162	67.68 143	85.87 215	87.26 239	76.02 88	84.67 72	88.22 198	61.54 171	93.48 156	82.71 79	73.44 337	91.06 170

AUN-MVS		79.21 181	77.60 202	84.05 136	88.71 163	67.61 145	85.84 217	87.26 239	69.08 239	77.23 191	88.14 203	53.20 252	93.47 157	75.50 148	73.45 336	91.06 170

HQP4-MVS										77.24 190			95.11 87			91.03 172

HQP-MVS		82.61 108	82.02 112	84.37 111	89.33 135	66.98 163	89.17 103	92.19 90	76.41 77	77.23 191	90.23 145	60.17 199	95.11 87	77.47 124	85.99 172	91.03 172

RPSCF		73.23 286	71.46 290	78.54 277	82.50 321	59.85 287	82.18 288	82.84 312	58.96 356	71.15 301	89.41 168	45.48 335	84.77 339	58.82 301	71.83 349	91.02 174

test_djsdf		80.30 157	79.32 158	83.27 162	83.98 284	65.37 194	90.50 64	90.38 146	68.55 250	76.19 217	88.70 181	56.44 225	93.46 158	78.98 109	80.14 251	90.97 175

PCF-MVS	73.52 7	80.38 154	78.84 169	85.01 90	87.71 206	68.99 106	83.65 266	91.46 119	63.00 319	77.77 180	90.28 142	66.10 117	95.09 91	61.40 278	88.22 139	90.94 176
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VPNet		78.69 194	78.66 171	78.76 271	88.31 177	55.72 342	84.45 251	86.63 252	76.79 67	78.26 168	90.55 139	59.30 201	89.70 279	66.63 232	77.05 283	90.88 177

CPTT-MVS		83.73 84	83.33 90	84.92 95	93.28 49	70.86 72	92.09 36	90.38 146	68.75 247	79.57 144	92.83 81	60.60 194	93.04 184	80.92 95	91.56 90	90.86 178

tt0805		78.73 192	77.83 192	81.43 214	85.17 258	60.30 283	89.41 96	90.90 132	71.21 187	77.17 196	88.73 180	46.38 320	93.21 169	72.57 177	78.96 263	90.79 179

CLD-MVS		82.31 111	81.65 117	84.29 116	88.47 170	67.73 142	85.81 219	92.35 82	75.78 91	78.33 167	86.58 245	64.01 136	94.35 115	76.05 140	87.48 148	90.79 179
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v1192		79.59 169	78.43 177	83.07 173	83.55 294	64.52 210	86.93 183	90.58 140	70.83 194	77.78 179	85.90 259	59.15 202	93.94 131	73.96 161	77.19 282	90.76 181

IterMVS-LS		80.06 161	79.38 155	82.11 200	85.89 245	63.20 242	86.79 188	89.34 179	74.19 129	75.45 233	86.72 235	66.62 109	92.39 204	72.58 176	76.86 286	90.75 182
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		80.52 152	79.98 142	82.12 199	84.28 276	63.19 243	86.41 199	88.95 199	74.18 130	78.69 156	87.54 215	66.62 109	92.43 202	72.57 177	80.57 245	90.74 183

v1921920		79.22 180	78.03 186	82.80 186	83.30 299	63.94 224	86.80 187	90.33 150	69.91 218	77.48 184	85.53 269	58.44 206	93.75 145	73.60 163	76.85 287	90.71 184

QAPM		80.88 137	79.50 153	85.03 89	88.01 192	68.97 107	91.59 43	92.00 95	66.63 276	75.15 248	92.16 93	57.70 212	95.45 68	63.52 254	88.76 130	90.66 185

v144192		79.47 172	78.37 178	82.78 189	83.35 297	63.96 223	86.96 180	90.36 149	69.99 215	77.50 183	85.67 266	60.66 191	93.77 143	74.27 158	76.58 290	90.62 186

v1240		78.99 187	77.78 195	82.64 192	83.21 301	63.54 232	86.62 194	90.30 152	69.74 225	77.33 187	85.68 265	57.04 220	93.76 144	73.13 171	76.92 284	90.62 186

v1144		80.03 162	79.03 165	83.01 176	83.78 289	64.51 211	87.11 176	90.57 142	71.96 174	78.08 174	86.20 255	61.41 175	93.94 131	74.93 152	77.23 280	90.60 188

1112_ss		77.40 227	76.43 228	80.32 243	89.11 150	60.41 282	83.65 266	87.72 229	62.13 332	73.05 277	86.72 235	62.58 154	89.97 273	62.11 272	80.80 241	90.59 189

CP-MVSNet		78.22 203	78.34 179	77.84 289	87.83 200	54.54 355	87.94 151	91.17 125	77.65 39	73.48 272	88.49 189	62.24 161	88.43 302	62.19 269	74.07 328	90.55 190

testing222		74.04 274	72.66 278	78.19 284	87.89 196	55.36 346	81.06 302	79.20 351	71.30 185	74.65 259	83.57 313	39.11 369	88.67 299	51.43 348	85.75 176	90.53 191

PS-CasMVS		78.01 212	78.09 185	77.77 291	87.71 206	54.39 357	88.02 147	91.22 122	77.50 47	73.26 274	88.64 184	60.73 187	88.41 303	61.88 273	73.88 332	90.53 191

CDS-MVSNet		79.07 185	77.70 199	83.17 168	87.60 210	68.23 130	84.40 254	86.20 260	67.49 263	76.36 213	86.54 247	61.54 171	90.79 261	61.86 274	87.33 149	90.49 193
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		78.89 190	77.51 204	83.03 175	87.80 201	67.79 141	84.72 241	85.05 274	67.63 260	76.75 203	87.70 208	62.25 160	90.82 260	58.53 304	87.13 152	90.49 193

PEN-MVS		77.73 218	77.69 200	77.84 289	87.07 226	53.91 360	87.91 153	91.18 124	77.56 44	73.14 276	88.82 179	61.23 180	89.17 288	59.95 288	72.37 343	90.43 195

Test_1112_low_res		76.40 246	75.44 241	79.27 263	89.28 140	58.09 301	81.69 293	87.07 243	59.53 351	72.48 285	86.67 240	61.30 178	89.33 284	60.81 284	80.15 250	90.41 196

HY-MVS	69.67 12	77.95 213	77.15 210	80.36 241	87.57 214	60.21 285	83.37 273	87.78 228	66.11 280	75.37 237	87.06 230	63.27 142	90.48 266	61.38 279	82.43 223	90.40 197

CHOSEN 1792x2688		77.63 223	75.69 235	83.44 155	89.98 114	68.58 122	78.70 338	87.50 233	56.38 374	75.80 225	86.84 231	58.67 204	91.40 245	61.58 277	85.75 176	90.34 198

SDMVSNet		80.38 154	80.18 140	80.99 228	89.03 151	64.94 203	80.45 314	89.40 177	75.19 103	76.61 208	89.98 148	60.61 193	87.69 311	76.83 133	83.55 207	90.33 199

sd_testset		77.70 221	77.40 205	78.60 274	89.03 151	60.02 286	79.00 333	85.83 265	75.19 103	76.61 208	89.98 148	54.81 232	85.46 332	62.63 265	83.55 207	90.33 199

114514_t		80.68 146	79.51 152	84.20 122	94.09 38	67.27 156	89.64 87	91.11 128	58.75 359	74.08 266	90.72 136	58.10 208	95.04 92	69.70 203	89.42 120	90.30 201

eth_miper_zixun_eth		77.92 214	76.69 223	81.61 211	83.00 309	61.98 260	83.15 276	89.20 187	69.52 227	74.86 255	84.35 295	61.76 167	92.56 197	71.50 184	72.89 341	90.28 202

PVSNet_Blended_VisFu		82.62 107	81.83 116	84.96 92	90.80 94	69.76 90	88.74 122	91.70 110	69.39 228	78.96 151	88.46 190	65.47 125	94.87 100	74.42 156	88.57 133	90.24 203

MVS_111021_LR		82.61 108	82.11 108	84.11 124	88.82 156	71.58 55	85.15 231	86.16 261	74.69 116	80.47 134	91.04 128	62.29 159	90.55 265	80.33 101	90.08 110	90.20 204

MSLP-MVS++		85.43 62	85.76 56	84.45 109	91.93 75	70.24 79	90.71 59	92.86 58	77.46 48	84.22 83	92.81 83	67.16 107	92.94 186	80.36 100	94.35 57	90.16 205

mvs_tets		79.13 183	77.77 196	83.22 166	84.70 268	66.37 171	89.17 103	90.19 155	69.38 229	75.40 235	89.46 164	44.17 341	93.15 176	76.78 134	80.70 243	90.14 206

BH-RMVSNet		79.61 167	78.44 176	83.14 169	89.38 134	65.93 179	84.95 237	87.15 242	73.56 144	78.19 170	89.79 152	56.67 223	93.36 162	59.53 293	86.74 158	90.13 207

c3_l		78.75 191	77.91 189	81.26 220	82.89 313	61.56 266	84.09 260	89.13 191	69.97 216	75.56 228	84.29 296	66.36 114	92.09 216	73.47 166	75.48 309	90.12 208

v7n		78.97 188	77.58 203	83.14 169	83.45 296	65.51 189	88.32 138	91.21 123	73.69 140	72.41 286	86.32 253	57.93 209	93.81 140	69.18 208	75.65 305	90.11 209

jajsoiax		79.29 179	77.96 187	83.27 162	84.68 269	66.57 169	89.25 102	90.16 156	69.20 236	75.46 232	89.49 161	45.75 331	93.13 178	76.84 132	80.80 241	90.11 209

v148		78.72 193	77.80 194	81.47 213	82.73 316	61.96 261	86.30 204	88.08 218	73.26 154	76.18 218	85.47 271	62.46 156	92.36 206	71.92 181	73.82 333	90.09 211

GBi-Net		78.40 199	77.40 205	81.40 216	87.60 210	63.01 245	88.39 133	89.28 181	71.63 177	75.34 238	87.28 219	54.80 233	91.11 251	62.72 261	79.57 255	90.09 211

test1		78.40 199	77.40 205	81.40 216	87.60 210	63.01 245	88.39 133	89.28 181	71.63 177	75.34 238	87.28 219	54.80 233	91.11 251	62.72 261	79.57 255	90.09 211

FMVSNet1		77.44 225	76.12 232	81.40 216	86.81 230	63.01 245	88.39 133	89.28 181	70.49 204	74.39 263	87.28 219	49.06 304	91.11 251	60.91 282	78.52 266	90.09 211

WR-MVS_H		78.51 198	78.49 174	78.56 276	88.02 190	56.38 332	88.43 131	92.67 67	77.14 57	73.89 267	87.55 214	66.25 116	89.24 287	58.92 299	73.55 335	90.06 215

DTE-MVSNet		76.99 232	76.80 218	77.54 297	86.24 238	53.06 369	87.52 162	90.66 138	77.08 60	72.50 284	88.67 183	60.48 195	89.52 281	57.33 316	70.74 355	90.05 216

v8		79.97 164	79.02 166	82.80 186	84.09 281	64.50 213	87.96 149	90.29 153	74.13 132	75.24 245	86.81 232	62.88 151	93.89 138	74.39 157	75.40 314	90.00 217

thres600view7		76.50 241	75.44 241	79.68 256	89.40 132	57.16 318	85.53 226	83.23 300	73.79 138	76.26 215	87.09 228	51.89 268	91.89 223	48.05 370	83.72 204	90.00 217

thres400		76.50 241	75.37 245	79.86 251	89.13 146	57.65 312	85.17 229	83.60 292	73.41 150	76.45 210	86.39 251	52.12 260	91.95 220	48.33 365	83.75 201	90.00 217

cl22		78.07 209	77.01 212	81.23 221	82.37 325	61.83 263	83.55 270	87.98 220	68.96 244	75.06 251	83.87 303	61.40 176	91.88 224	73.53 164	76.39 294	89.98 220

OPM-MVS		83.50 92	82.95 96	85.14 85	88.79 159	70.95 69	89.13 108	91.52 114	77.55 45	80.96 130	91.75 102	60.71 188	94.50 112	79.67 107	86.51 162	89.97 221
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		75.70 255	73.83 266	81.30 219	83.26 300	61.79 264	82.57 285	80.65 333	66.81 267	66.88 343	83.42 315	57.86 211	92.19 213	63.47 255	79.57 255	89.91 222

v10		79.74 166	78.67 170	82.97 179	84.06 282	64.95 202	87.88 155	90.62 139	73.11 157	75.11 249	86.56 246	61.46 174	94.05 127	73.68 162	75.55 307	89.90 223

MVSTER		79.01 186	77.88 191	82.38 197	83.07 306	64.80 207	84.08 261	88.95 199	69.01 243	78.69 156	87.17 226	54.70 237	92.43 202	74.69 153	80.57 245	89.89 224

ACMP	74.13 6	81.51 129	80.57 131	84.36 112	89.42 130	68.69 119	89.97 77	91.50 118	74.46 122	75.04 252	90.41 141	53.82 245	94.54 109	77.56 123	82.91 216	89.86 225
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LPG-MVS_test		82.08 114	81.27 120	84.50 106	89.23 142	68.76 112	90.22 73	91.94 99	75.37 99	76.64 206	91.51 111	54.29 240	94.91 95	78.44 114	83.78 198	89.83 226

LGP-MVS_train				84.50 106	89.23 142	68.76 112		91.94 99	75.37 99	76.64 206	91.51 111	54.29 240	94.91 95	78.44 114	83.78 198	89.83 226

V42		79.38 178	78.24 182	82.83 183	81.10 344	65.50 190	85.55 224	89.82 164	71.57 181	78.21 169	86.12 257	60.66 191	93.18 175	75.64 144	75.46 311	89.81 228

MAR-MVS		81.84 119	80.70 129	85.27 82	91.32 82	71.53 56	89.82 79	90.92 131	69.77 222	78.50 162	86.21 254	62.36 158	94.52 111	65.36 242	92.05 82	89.77 229
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
DIV-MVS_self_test		77.72 219	76.76 220	80.58 237	82.48 323	60.48 280	83.09 278	87.86 225	69.22 234	74.38 264	85.24 275	62.10 163	91.53 238	71.09 187	75.40 314	89.74 230

cl____		77.72 219	76.76 220	80.58 237	82.49 322	60.48 280	83.09 278	87.87 224	69.22 234	74.38 264	85.22 277	62.10 163	91.53 238	71.09 187	75.41 313	89.73 231

miper_ehance_all_eth		78.59 197	77.76 197	81.08 226	82.66 318	61.56 266	83.65 266	89.15 189	68.87 245	75.55 229	83.79 307	66.49 112	92.03 217	73.25 169	76.39 294	89.64 232

anonymousdsp		78.60 196	77.15 210	82.98 178	80.51 350	67.08 161	87.24 173	89.53 174	65.66 287	75.16 247	87.19 225	52.52 253	92.25 211	77.17 128	79.34 260	89.61 233

FMVSNet2		78.20 205	77.21 209	81.20 222	87.60 210	62.89 251	87.47 164	89.02 194	71.63 177	75.29 244	87.28 219	54.80 233	91.10 254	62.38 266	79.38 259	89.61 233

baseline1		76.98 233	76.75 222	77.66 292	88.13 184	55.66 343	85.12 232	81.89 320	73.04 159	76.79 201	88.90 176	62.43 157	87.78 310	63.30 258	71.18 353	89.55 235

ETVMVS		72.25 297	71.05 296	75.84 310	87.77 205	51.91 373	79.39 326	74.98 375	69.26 232	73.71 269	82.95 323	40.82 362	86.14 323	46.17 378	84.43 191	89.47 236

FMVSNet3		77.88 215	76.85 217	80.97 230	86.84 229	62.36 254	86.52 197	88.77 203	71.13 188	75.34 238	86.66 241	54.07 243	91.10 254	62.72 261	79.57 255	89.45 237

miper_enhance_ethall		77.87 216	76.86 216	80.92 231	81.65 332	61.38 268	82.68 283	88.98 196	65.52 289	75.47 230	82.30 334	65.76 124	92.00 219	72.95 172	76.39 294	89.39 238

testing11		75.14 265	74.01 261	78.53 278	88.16 181	56.38 332	80.74 308	80.42 338	70.67 198	72.69 283	83.72 310	43.61 345	89.86 274	62.29 268	83.76 200	89.36 239

cascas		76.72 238	74.64 252	82.99 177	85.78 247	65.88 181	82.33 286	89.21 186	60.85 340	72.74 280	81.02 345	47.28 313	93.75 145	67.48 224	85.02 179	89.34 240

Fast-Effi-MVS+-dtu		78.02 211	76.49 226	82.62 193	83.16 305	66.96 165	86.94 182	87.45 235	72.45 165	71.49 298	84.17 300	54.79 236	91.58 233	67.61 222	80.31 248	89.30 241

IB-MVS	68.01 15	75.85 254	73.36 270	83.31 160	84.76 267	66.03 175	83.38 272	85.06 273	70.21 211	69.40 320	81.05 344	45.76 330	94.66 108	65.10 245	75.49 308	89.25 242
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
thres100view900		76.50 241	75.55 240	79.33 262	89.52 125	56.99 321	85.83 218	83.23 300	73.94 134	76.32 214	87.12 227	51.89 268	91.95 220	48.33 365	83.75 201	89.07 243

tfpn200view9		76.42 245	75.37 245	79.55 261	89.13 146	57.65 312	85.17 229	83.60 292	73.41 150	76.45 210	86.39 251	52.12 260	91.95 220	48.33 365	83.75 201	89.07 243

xiu_mvs_v1_base_debu		80.80 142	79.72 148	84.03 138	87.35 215	70.19 82	85.56 221	88.77 203	69.06 240	81.83 115	88.16 199	50.91 279	92.85 188	78.29 118	87.56 145	89.06 245

xiu_mvs_v1_base		80.80 142	79.72 148	84.03 138	87.35 215	70.19 82	85.56 221	88.77 203	69.06 240	81.83 115	88.16 199	50.91 279	92.85 188	78.29 118	87.56 145	89.06 245

xiu_mvs_v1_base_debi		80.80 142	79.72 148	84.03 138	87.35 215	70.19 82	85.56 221	88.77 203	69.06 240	81.83 115	88.16 199	50.91 279	92.85 188	78.29 118	87.56 145	89.06 245

EPNet_dtu		75.46 259	74.86 250	77.23 301	82.57 320	54.60 354	86.89 184	83.09 304	71.64 176	66.25 354	85.86 261	55.99 226	88.04 307	54.92 330	86.55 161	89.05 248
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pm-mvs1		77.25 230	76.68 224	78.93 269	84.22 278	58.62 296	86.41 199	88.36 214	71.37 184	73.31 273	88.01 205	61.22 181	89.15 289	64.24 252	73.01 340	89.03 249

PVSNet_Blended		80.98 135	80.34 136	82.90 181	88.85 153	65.40 191	84.43 252	92.00 95	67.62 261	78.11 172	85.05 282	66.02 120	94.27 118	71.52 182	89.50 118	89.01 250

PAPM		77.68 222	76.40 229	81.51 212	87.29 222	61.85 262	83.78 263	89.59 172	64.74 298	71.23 299	88.70 181	62.59 153	93.66 148	52.66 341	87.03 154	89.01 250

WTY-MVS		75.65 256	75.68 236	75.57 314	86.40 237	56.82 323	77.92 350	82.40 315	65.10 293	76.18 218	87.72 207	63.13 149	80.90 362	60.31 286	81.96 228	89.00 252

无先验							87.48 163	88.98 196	60.00 346				94.12 125	67.28 226		88.97 253

GSMVS																88.96 254

sam_mvs1												51.32 275				88.96 254

SCA		74.22 271	72.33 282	79.91 250	84.05 283	62.17 258	79.96 321	79.29 350	66.30 279	72.38 287	80.13 355	51.95 266	88.60 300	59.25 295	77.67 278	88.96 254

miper_lstm_enhance		74.11 273	73.11 273	77.13 302	80.11 354	59.62 290	72.23 378	86.92 248	66.76 269	70.40 305	82.92 324	56.93 221	82.92 351	69.06 210	72.63 342	88.87 257

ACMM	73.20 8	80.78 145	79.84 146	83.58 152	89.31 138	68.37 126	89.99 76	91.60 112	70.28 208	77.25 189	89.66 155	53.37 250	93.53 154	74.24 159	82.85 217	88.85 258
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		74.69 267	73.39 269	78.61 273	81.38 339	57.48 315	86.64 193	87.95 222	64.99 297	70.18 308	86.61 242	50.43 286	89.52 281	62.12 271	70.18 358	88.83 259

原ACMM1				84.35 113	93.01 60	68.79 110		92.44 77	63.96 312	81.09 128	91.57 110	66.06 119	95.45 68	67.19 228	94.82 46	88.81 260

CNLPA		78.08 208	76.79 219	81.97 204	90.40 102	71.07 65	87.59 161	84.55 279	66.03 283	72.38 287	89.64 156	57.56 214	86.04 324	59.61 292	83.35 211	88.79 261

UWE-MVS		72.13 298	71.49 289	74.03 333	86.66 234	47.70 392	81.40 299	76.89 368	63.60 314	75.59 227	84.22 299	39.94 365	85.62 329	48.98 362	86.13 169	88.77 262

UBG		73.08 288	72.27 283	75.51 316	88.02 190	51.29 381	78.35 345	77.38 363	65.52 289	73.87 268	82.36 332	45.55 332	86.48 320	55.02 329	84.39 192	88.75 263

K. test v3		71.19 303	68.51 315	79.21 265	83.04 308	57.78 311	84.35 255	76.91 367	72.90 162	62.99 373	82.86 326	39.27 367	91.09 256	61.65 276	52.66 399	88.75 263

旧先验1					91.96 74	65.79 184		86.37 257			93.08 76	69.31 83			92.74 73	88.74 265

PatchmatchNet		73.12 287	71.33 293	78.49 280	83.18 303	60.85 274	79.63 323	78.57 354	64.13 305	71.73 294	79.81 360	51.20 277	85.97 325	57.40 315	76.36 299	88.66 266
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SixPastTwentyTwo		73.37 282	71.26 295	79.70 255	85.08 263	57.89 307	85.57 220	83.56 294	71.03 192	65.66 356	85.88 260	42.10 355	92.57 196	59.11 297	63.34 380	88.65 267

PS-MVSNAJ		81.69 123	81.02 125	83.70 149	89.51 126	68.21 131	84.28 256	90.09 158	70.79 195	81.26 127	85.62 268	63.15 146	94.29 116	75.62 145	88.87 127	88.59 268

xiu_mvs_v2_base		81.69 123	81.05 124	83.60 151	89.15 145	68.03 136	84.46 250	90.02 159	70.67 198	81.30 126	86.53 248	63.17 145	94.19 123	75.60 146	88.54 134	88.57 269

MonoMVSNet		76.49 244	75.80 233	78.58 275	81.55 335	58.45 297	86.36 202	86.22 259	74.87 113	74.73 257	83.73 309	51.79 271	88.73 297	70.78 189	72.15 346	88.55 270

CostFormer		75.24 264	73.90 264	79.27 263	82.65 319	58.27 300	80.80 304	82.73 313	61.57 335	75.33 242	83.13 320	55.52 228	91.07 257	64.98 246	78.34 271	88.45 271

lessismore_v0				78.97 268	81.01 345	57.15 319		65.99 402		61.16 379	82.82 327	39.12 368	91.34 247	59.67 291	46.92 406	88.43 272

OpenMVS	72.83 10	79.77 165	78.33 180	84.09 129	85.17 258	69.91 87	90.57 61	90.97 130	66.70 270	72.17 290	91.91 97	54.70 237	93.96 128	61.81 275	90.95 97	88.41 273

reproduce_monomvs		75.40 262	74.38 258	78.46 281	83.92 286	57.80 310	83.78 263	86.94 246	73.47 148	72.25 289	84.47 290	38.74 370	89.27 286	75.32 150	70.53 356	88.31 274

OurMVSNet-221017-0		74.26 270	72.42 281	79.80 253	83.76 290	59.59 291	85.92 214	86.64 251	66.39 278	66.96 342	87.58 211	39.46 366	91.60 232	65.76 240	69.27 361	88.22 275

LS3D		76.95 234	74.82 251	83.37 159	90.45 100	67.36 153	89.15 107	86.94 246	61.87 334	69.52 319	90.61 138	51.71 272	94.53 110	46.38 377	86.71 159	88.21 276

WBMVS		73.43 281	72.81 276	75.28 320	87.91 195	50.99 383	78.59 341	81.31 328	65.51 291	74.47 262	84.83 285	46.39 319	86.68 317	58.41 305	77.86 274	88.17 277

XVG-ACMP-BASELINE		76.11 250	74.27 260	81.62 209	83.20 302	64.67 209	83.60 269	89.75 167	69.75 223	71.85 293	87.09 228	32.78 387	92.11 215	69.99 200	80.43 247	88.09 278

tpm2		73.26 285	71.46 290	78.63 272	83.34 298	56.71 326	80.65 310	80.40 339	56.63 373	73.55 271	82.02 339	51.80 270	91.24 249	56.35 325	78.42 269	87.95 279

MDTV_nov1_ep13_2view						37.79 415	75.16 366		55.10 378	66.53 349		49.34 299		53.98 334		87.94 280

Patchmatch-test		64.82 352	63.24 353	69.57 363	79.42 366	49.82 389	63.49 409	69.05 395	51.98 388	59.95 384	80.13 355	50.91 279	70.98 403	40.66 394	73.57 334	87.90 281

PLC	70.83 11	78.05 210	76.37 230	83.08 172	91.88 77	67.80 140	88.19 142	89.46 176	64.33 304	69.87 316	88.38 192	53.66 246	93.58 149	58.86 300	82.73 219	87.86 282
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		72.37 295	71.71 287	74.35 330	82.19 326	52.00 371	79.22 329	77.29 364	64.56 300	72.95 279	83.68 312	51.35 274	83.26 350	58.33 307	75.80 303	87.81 283

Patchmatch-RL test		70.24 315	67.78 328	77.61 294	77.43 374	59.57 292	71.16 382	70.33 389	62.94 321	68.65 327	72.77 394	50.62 283	85.49 331	69.58 205	66.58 371	87.77 284

F-COLMAP		76.38 247	74.33 259	82.50 195	89.28 140	66.95 166	88.41 132	89.03 193	64.05 309	66.83 344	88.61 185	46.78 317	92.89 187	57.48 313	78.55 265	87.67 285

Baseline_NR-MVSNet		78.15 207	78.33 180	77.61 294	85.79 246	56.21 336	86.78 189	85.76 266	73.60 143	77.93 177	87.57 212	65.02 129	88.99 291	67.14 229	75.33 316	87.63 286

CL-MVSNet_self_test		72.37 295	71.46 290	75.09 322	79.49 365	53.53 362	80.76 307	85.01 275	69.12 238	70.51 303	82.05 338	57.92 210	84.13 342	52.27 343	66.00 374	87.60 287

ACMH+	68.96 14	76.01 252	74.01 261	82.03 202	88.60 166	65.31 195	88.86 116	87.55 231	70.25 210	67.75 333	87.47 217	41.27 358	93.19 174	58.37 306	75.94 302	87.60 287

1314		76.53 240	75.30 247	80.21 245	83.93 285	62.32 256	84.66 242	88.81 201	60.23 344	70.16 310	84.07 302	55.30 230	90.73 263	67.37 225	83.21 213	87.59 289

API-MVS		81.99 117	81.23 121	84.26 121	90.94 90	70.18 85	91.10 55	89.32 180	71.51 182	78.66 158	88.28 195	65.26 126	95.10 90	64.74 248	91.23 94	87.51 290

AdaColmap		80.58 151	79.42 154	84.06 133	93.09 57	68.91 108	89.36 99	88.97 198	69.27 231	75.70 226	89.69 154	57.20 219	95.77 59	63.06 259	88.41 137	87.50 291

PVSNet_BlendedMVS		80.60 148	80.02 141	82.36 198	88.85 153	65.40 191	86.16 208	92.00 95	69.34 230	78.11 172	86.09 258	66.02 120	94.27 118	71.52 182	82.06 227	87.39 292

sss		73.60 279	73.64 268	73.51 337	82.80 314	55.01 351	76.12 357	81.69 323	62.47 328	74.68 258	85.85 262	57.32 217	78.11 373	60.86 283	80.93 238	87.39 292

IterMVS-SCA-FT		75.43 260	73.87 265	80.11 247	82.69 317	64.85 206	81.57 295	83.47 296	69.16 237	70.49 304	84.15 301	51.95 266	88.15 305	69.23 207	72.14 347	87.34 294

PVSNet	64.34 18	72.08 299	70.87 299	75.69 312	86.21 239	56.44 330	74.37 372	80.73 332	62.06 333	70.17 309	82.23 336	42.86 349	83.31 349	54.77 331	84.45 190	87.32 295

新几何1				83.42 156	93.13 54	70.71 74		85.48 269	57.43 369	81.80 118	91.98 96	63.28 141	92.27 210	64.60 249	92.99 70	87.27 296

TR-MVS		77.44 225	76.18 231	81.20 222	88.24 179	63.24 240	84.61 245	86.40 256	67.55 262	77.81 178	86.48 249	54.10 242	93.15 176	57.75 312	82.72 220	87.20 297

TransMVSNet (Re)		75.39 263	74.56 254	77.86 288	85.50 253	57.10 320	86.78 189	86.09 263	72.17 171	71.53 297	87.34 218	63.01 150	89.31 285	56.84 321	61.83 382	87.17 298

ACMH	67.68 16	75.89 253	73.93 263	81.77 207	88.71 163	66.61 168	88.62 127	89.01 195	69.81 219	66.78 345	86.70 239	41.95 357	91.51 240	55.64 327	78.14 272	87.17 298
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
KD-MVS_self_test		68.81 326	67.59 332	72.46 347	74.29 387	45.45 398	77.93 349	87.00 244	63.12 316	63.99 368	78.99 368	42.32 352	84.77 339	56.55 324	64.09 379	87.16 300

EPMVS		69.02 325	68.16 319	71.59 351	79.61 363	49.80 390	77.40 352	66.93 400	62.82 324	70.01 311	79.05 364	45.79 329	77.86 375	56.58 323	75.26 318	87.13 301

CR-MVSNet		73.37 282	71.27 294	79.67 257	81.32 342	65.19 196	75.92 359	80.30 340	59.92 347	72.73 281	81.19 342	52.50 254	86.69 316	59.84 289	77.71 276	87.11 302

RPMNet		73.51 280	70.49 302	82.58 194	81.32 342	65.19 196	75.92 359	92.27 84	57.60 367	72.73 281	76.45 382	52.30 257	95.43 70	48.14 369	77.71 276	87.11 302

test_vis1_n_1920		75.52 258	75.78 234	74.75 327	79.84 358	57.44 316	83.26 274	85.52 268	62.83 323	79.34 148	86.17 256	45.10 336	79.71 366	78.75 111	81.21 236	87.10 304

XXY-MVS		75.41 261	75.56 239	74.96 323	83.59 293	57.82 309	80.59 311	83.87 290	66.54 277	74.93 254	88.31 194	63.24 143	80.09 365	62.16 270	76.85 287	86.97 305

tpmrst		72.39 293	72.13 284	73.18 341	80.54 349	49.91 388	79.91 322	79.08 352	63.11 317	71.69 295	79.95 357	55.32 229	82.77 352	65.66 241	73.89 331	86.87 306

thres200		75.55 257	74.47 256	78.82 270	87.78 204	57.85 308	83.07 280	83.51 295	72.44 167	75.84 224	84.42 291	52.08 263	91.75 228	47.41 372	83.64 206	86.86 307

ITE_SJBPF				78.22 283	81.77 331	60.57 278		83.30 298	69.25 233	67.54 335	87.20 224	36.33 380	87.28 314	54.34 333	74.62 325	86.80 308

test222					91.50 80	68.26 129	84.16 258	83.20 303	54.63 380	79.74 141	91.63 107	58.97 203			91.42 91	86.77 309

MIMVSNet		70.69 310	69.30 309	74.88 324	84.52 273	56.35 334	75.87 361	79.42 348	64.59 299	67.76 332	82.41 331	41.10 359	81.54 358	46.64 376	81.34 233	86.75 310

BH-untuned		79.47 172	78.60 172	82.05 201	89.19 144	65.91 180	86.07 210	88.52 212	72.18 170	75.42 234	87.69 209	61.15 182	93.54 153	60.38 285	86.83 157	86.70 311

LTVRE_ROB	69.57 13	76.25 248	74.54 255	81.41 215	88.60 166	64.38 217	79.24 328	89.12 192	70.76 197	69.79 318	87.86 206	49.09 303	93.20 172	56.21 326	80.16 249	86.65 312
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
testdata				79.97 249	90.90 91	64.21 219		84.71 276	59.27 353	85.40 60	92.91 78	62.02 165	89.08 290	68.95 211	91.37 92	86.63 313

MIMVSNet1		68.58 329	66.78 339	73.98 334	80.07 355	51.82 375	80.77 306	84.37 280	64.40 302	59.75 385	82.16 337	36.47 379	83.63 346	42.73 389	70.33 357	86.48 314

tfpnnormal		74.39 268	73.16 272	78.08 286	86.10 244	58.05 302	84.65 244	87.53 232	70.32 207	71.22 300	85.63 267	54.97 231	89.86 274	43.03 388	75.02 321	86.32 315

D2MVS		74.82 266	73.21 271	79.64 258	79.81 359	62.56 253	80.34 316	87.35 236	64.37 303	68.86 325	82.66 329	46.37 321	90.10 270	67.91 220	81.24 235	86.25 316

tpm cat1		70.57 311	68.31 317	77.35 299	82.41 324	57.95 306	78.08 347	80.22 342	52.04 386	68.54 329	77.66 377	52.00 265	87.84 309	51.77 344	72.07 348	86.25 316

CVMVSNet		72.99 290	72.58 279	74.25 331	84.28 276	50.85 384	86.41 199	83.45 297	44.56 399	73.23 275	87.54 215	49.38 298	85.70 327	65.90 238	78.44 268	86.19 318

AllTest		70.96 306	68.09 321	79.58 259	85.15 260	63.62 228	84.58 246	79.83 344	62.31 329	60.32 382	86.73 233	32.02 388	88.96 294	50.28 354	71.57 351	86.15 319

TestCases				79.58 259	85.15 260	63.62 228		79.83 344	62.31 329	60.32 382	86.73 233	32.02 388	88.96 294	50.28 354	71.57 351	86.15 319

test-LLR		72.94 291	72.43 280	74.48 328	81.35 340	58.04 303	78.38 342	77.46 360	66.66 271	69.95 314	79.00 366	48.06 309	79.24 367	66.13 234	84.83 181	86.15 319

test-mter		71.41 302	70.39 305	74.48 328	81.35 340	58.04 303	78.38 342	77.46 360	60.32 343	69.95 314	79.00 366	36.08 381	79.24 367	66.13 234	84.83 181	86.15 319

IterMVS		74.29 269	72.94 275	78.35 282	81.53 336	63.49 234	81.58 294	82.49 314	68.06 258	69.99 313	83.69 311	51.66 273	85.54 330	65.85 239	71.64 350	86.01 323
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		76.78 237	74.57 253	83.42 156	93.29 48	69.46 97	88.55 129	83.70 291	63.98 311	70.20 307	88.89 177	54.01 244	94.80 102	46.66 374	81.88 230	86.01 323

ppachtmachnet_test		70.04 317	67.34 335	78.14 285	79.80 360	61.13 269	79.19 330	80.59 334	59.16 354	65.27 359	79.29 363	46.75 318	87.29 313	49.33 360	66.72 369	86.00 325

mmtdpeth		74.16 272	73.01 274	77.60 296	83.72 291	61.13 269	85.10 233	85.10 272	72.06 173	77.21 195	80.33 353	43.84 343	85.75 326	77.14 129	52.61 400	85.91 326

test_fmvs1_n		70.86 308	70.24 306	72.73 344	72.51 401	55.28 348	81.27 300	79.71 346	51.49 390	78.73 155	84.87 284	27.54 397	77.02 378	76.06 139	79.97 253	85.88 327

Patchmtry		70.74 309	69.16 312	75.49 317	80.72 346	54.07 359	74.94 370	80.30 340	58.34 360	70.01 311	81.19 342	52.50 254	86.54 318	53.37 338	71.09 354	85.87 328

WB-MVSnew		71.96 300	71.65 288	72.89 342	84.67 272	51.88 374	82.29 287	77.57 359	62.31 329	73.67 270	83.00 322	53.49 249	81.10 361	45.75 381	82.13 226	85.70 329

test_fmvs2		68.35 333	67.48 333	70.98 359	69.50 404	51.95 372	80.05 319	76.38 370	49.33 393	74.65 259	84.38 293	23.30 406	75.40 394	74.51 155	75.17 320	85.60 330

ambc				75.24 321	73.16 396	50.51 386	63.05 410	87.47 234		64.28 365	77.81 376	17.80 412	89.73 278	57.88 311	60.64 386	85.49 331

mvs5depth		69.45 322	67.45 334	75.46 318	73.93 388	55.83 340	79.19 330	83.23 300	66.89 266	71.63 296	83.32 316	33.69 386	85.09 335	59.81 290	55.34 396	85.46 332

UnsupCasMVSNet_eth		67.33 338	65.99 342	71.37 353	73.48 393	51.47 379	75.16 366	85.19 271	65.20 292	60.78 380	80.93 349	42.35 351	77.20 377	57.12 317	53.69 398	85.44 333

PatchT		68.46 332	67.85 324	70.29 361	80.70 347	43.93 405	72.47 377	74.88 376	60.15 345	70.55 302	76.57 381	49.94 291	81.59 357	50.58 350	74.83 323	85.34 334

Anonymous20240521		68.80 327	67.22 336	73.55 336	74.33 386	54.11 358	83.18 275	85.61 267	58.15 362	61.68 377	80.94 347	30.71 393	81.27 360	57.00 319	73.34 339	85.28 335

test_cas_vis1_n_1920		73.76 278	73.74 267	73.81 335	75.90 379	59.77 288	80.51 312	82.40 315	58.30 361	81.62 121	85.69 264	44.35 340	76.41 384	76.29 136	78.61 264	85.23 336

ADS-MVSNet2		66.20 349	63.33 352	74.82 325	79.92 356	58.75 295	67.55 397	75.19 374	53.37 383	65.25 360	75.86 385	42.32 352	80.53 364	41.57 392	68.91 363	85.18 337

ADS-MVSNet		64.36 353	62.88 356	68.78 369	79.92 356	47.17 394	67.55 397	71.18 388	53.37 383	65.25 360	75.86 385	42.32 352	73.99 399	41.57 392	68.91 363	85.18 337

FMVSNet5		69.50 321	67.96 322	74.15 332	82.97 312	55.35 347	80.01 320	82.12 318	62.56 327	63.02 371	81.53 341	36.92 378	81.92 356	48.42 364	74.06 329	85.17 339

pmmvs5		71.55 301	70.20 307	75.61 313	77.83 372	56.39 331	81.74 292	80.89 329	57.76 365	67.46 337	84.49 289	49.26 301	85.32 334	57.08 318	75.29 317	85.11 340

testing3		68.56 330	67.67 330	71.22 357	87.33 220	42.87 407	83.06 281	71.54 387	70.36 205	69.08 324	84.38 293	30.33 394	85.69 328	37.50 400	75.45 312	85.09 341

CMPMVS	51.72 21	70.19 316	68.16 319	76.28 307	73.15 397	57.55 314	79.47 325	83.92 288	48.02 395	56.48 395	84.81 286	43.13 347	86.42 321	62.67 264	81.81 231	84.89 342
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testgi		66.67 343	66.53 340	67.08 377	75.62 382	41.69 412	75.93 358	76.50 369	66.11 280	65.20 362	86.59 243	35.72 382	74.71 396	43.71 386	73.38 338	84.84 343

MSDG		73.36 284	70.99 297	80.49 239	84.51 274	65.80 183	80.71 309	86.13 262	65.70 286	65.46 357	83.74 308	44.60 337	90.91 259	51.13 349	76.89 285	84.74 344

pmmvs4		74.03 276	71.91 285	80.39 240	81.96 328	68.32 127	81.45 297	82.14 317	59.32 352	69.87 316	85.13 279	52.40 256	88.13 306	60.21 287	74.74 324	84.73 345

gg-mvs-nofinetune		69.95 318	67.96 322	75.94 309	83.07 306	54.51 356	77.23 354	70.29 390	63.11 317	70.32 306	62.33 403	43.62 344	88.69 298	53.88 335	87.76 144	84.62 346

test_fmvs1		70.93 307	70.52 301	72.16 348	73.71 390	55.05 350	80.82 303	78.77 353	51.21 391	78.58 160	84.41 292	31.20 392	76.94 379	75.88 142	80.12 252	84.47 347

BH-w/o		78.21 204	77.33 208	80.84 232	88.81 157	65.13 198	84.87 238	87.85 226	69.75 223	74.52 261	84.74 288	61.34 177	93.11 179	58.24 308	85.84 174	84.27 348

MVS		78.19 206	76.99 214	81.78 206	85.66 248	66.99 162	84.66 242	90.47 144	55.08 379	72.02 292	85.27 274	63.83 138	94.11 126	66.10 236	89.80 115	84.24 349

COLMAP_ROB	66.92 17	73.01 289	70.41 304	80.81 233	87.13 225	65.63 187	88.30 139	84.19 286	62.96 320	63.80 370	87.69 209	38.04 375	92.56 197	46.66 374	74.91 322	84.24 349
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
new-patchmatchnet		61.73 359	61.73 360	61.70 383	72.74 399	24.50 426	69.16 392	78.03 356	61.40 336	56.72 394	75.53 388	38.42 372	76.48 383	45.95 380	57.67 389	84.13 351

TESTMET0.1,1		69.89 319	69.00 313	72.55 345	79.27 368	56.85 322	78.38 342	74.71 379	57.64 366	68.09 331	77.19 379	37.75 376	76.70 380	63.92 253	84.09 196	84.10 352

test_fmvs3		63.36 356	61.82 359	67.98 374	62.51 413	46.96 396	77.37 353	74.03 381	45.24 398	67.50 336	78.79 369	12.16 418	72.98 402	72.77 175	66.02 373	83.99 353

our_test_3		69.14 324	67.00 337	75.57 314	79.80 360	58.80 294	77.96 348	77.81 357	59.55 350	62.90 374	78.25 373	47.43 311	83.97 343	51.71 345	67.58 368	83.93 354

test_vis1_n		69.85 320	69.21 311	71.77 350	72.66 400	55.27 349	81.48 296	76.21 371	52.03 387	75.30 243	83.20 319	28.97 395	76.22 386	74.60 154	78.41 270	83.81 355

mamv4		76.81 236	78.23 184	72.54 346	86.12 242	65.75 186	78.76 337	82.07 319	64.12 306	72.97 278	91.02 131	67.97 97	68.08 410	83.04 73	78.02 273	83.80 356

tpmvs		71.09 305	69.29 310	76.49 306	82.04 327	56.04 337	78.92 335	81.37 327	64.05 309	67.18 341	78.28 372	49.74 294	89.77 276	49.67 359	72.37 343	83.67 357

test20.03		67.45 337	66.95 338	68.94 366	75.48 383	44.84 403	77.50 351	77.67 358	66.66 271	63.01 372	83.80 306	47.02 315	78.40 371	42.53 391	68.86 365	83.58 358

test0.0.03 1		68.00 335	67.69 329	68.90 367	77.55 373	47.43 393	75.70 362	72.95 386	66.66 271	66.56 348	82.29 335	48.06 309	75.87 389	44.97 385	74.51 326	83.41 359

Anonymous20231206		68.60 328	67.80 327	71.02 358	80.23 353	50.75 385	78.30 346	80.47 336	56.79 372	66.11 355	82.63 330	46.35 322	78.95 369	43.62 387	75.70 304	83.36 360

EU-MVSNet		68.53 331	67.61 331	71.31 356	78.51 371	47.01 395	84.47 248	84.27 284	42.27 402	66.44 353	84.79 287	40.44 363	83.76 344	58.76 302	68.54 366	83.17 361

dp		66.80 341	65.43 343	70.90 360	79.74 362	48.82 391	75.12 368	74.77 377	59.61 349	64.08 367	77.23 378	42.89 348	80.72 363	48.86 363	66.58 371	83.16 362

pmmvs-eth3d		70.50 313	67.83 326	78.52 279	77.37 375	66.18 174	81.82 290	81.51 324	58.90 357	63.90 369	80.42 352	42.69 350	86.28 322	58.56 303	65.30 376	83.11 363

YYNet1		65.03 350	62.91 355	71.38 352	75.85 380	56.60 328	69.12 393	74.66 380	57.28 370	54.12 398	77.87 375	45.85 328	74.48 397	49.95 357	61.52 384	83.05 364

MDA-MVSNet-bldmvs		66.68 342	63.66 351	75.75 311	79.28 367	60.56 279	73.92 374	78.35 355	64.43 301	50.13 404	79.87 359	44.02 342	83.67 345	46.10 379	56.86 390	83.03 365

MDA-MVSNet_test_wron		65.03 350	62.92 354	71.37 353	75.93 378	56.73 324	69.09 394	74.73 378	57.28 370	54.03 399	77.89 374	45.88 327	74.39 398	49.89 358	61.55 383	82.99 366

USDC		70.33 314	68.37 316	76.21 308	80.60 348	56.23 335	79.19 330	86.49 254	60.89 339	61.29 378	85.47 271	31.78 390	89.47 283	53.37 338	76.21 300	82.94 367

Syy-MVS		68.05 334	67.85 324	68.67 370	84.68 269	40.97 413	78.62 339	73.08 384	66.65 274	66.74 346	79.46 361	52.11 262	82.30 354	32.89 405	76.38 297	82.75 368

myMVS_eth3d		67.02 340	66.29 341	69.21 365	84.68 269	42.58 408	78.62 339	73.08 384	66.65 274	66.74 346	79.46 361	31.53 391	82.30 354	39.43 397	76.38 297	82.75 368

ttmdpeth		59.91 362	57.10 366	68.34 372	67.13 408	46.65 397	74.64 371	67.41 399	48.30 394	62.52 376	85.04 283	20.40 408	75.93 388	42.55 390	45.90 409	82.44 370

OpenMVS_ROB	64.09 19	70.56 312	68.19 318	77.65 293	80.26 351	59.41 293	85.01 235	82.96 309	58.76 358	65.43 358	82.33 333	37.63 377	91.23 250	45.34 384	76.03 301	82.32 371

JIA-IIPM		66.32 346	62.82 357	76.82 304	77.09 376	61.72 265	65.34 405	75.38 373	58.04 364	64.51 364	62.32 404	42.05 356	86.51 319	51.45 347	69.22 362	82.21 372

dmvs_re		71.14 304	70.58 300	72.80 343	81.96 328	59.68 289	75.60 363	79.34 349	68.55 250	69.27 323	80.72 350	49.42 297	76.54 381	52.56 342	77.79 275	82.19 373

EG-PatchMatch MVS		74.04 274	71.82 286	80.71 235	84.92 265	67.42 150	85.86 216	88.08 218	66.04 282	64.22 366	83.85 304	35.10 383	92.56 197	57.44 314	80.83 240	82.16 374

MVP-Stereo		76.12 249	74.46 257	81.13 225	85.37 256	69.79 89	84.42 253	87.95 222	65.03 295	67.46 337	85.33 273	53.28 251	91.73 230	58.01 310	83.27 212	81.85 375
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TDRefinement		67.49 336	64.34 346	76.92 303	73.47 394	61.07 271	84.86 239	82.98 308	59.77 348	58.30 389	85.13 279	26.06 398	87.89 308	47.92 371	60.59 387	81.81 376

GG-mvs-BLEND				75.38 319	81.59 334	55.80 341	79.32 327	69.63 392		67.19 340	73.67 392	43.24 346	88.90 296	50.41 351	84.50 186	81.45 377

KD-MVS_2432*1600		66.22 347	63.89 349	73.21 338	75.47 384	53.42 364	70.76 385	84.35 281	64.10 307	66.52 350	78.52 370	34.55 384	84.98 336	50.40 352	50.33 403	81.23 378

miper_refine_blended		66.22 347	63.89 349	73.21 338	75.47 384	53.42 364	70.76 385	84.35 281	64.10 307	66.52 350	78.52 370	34.55 384	84.98 336	50.40 352	50.33 403	81.23 378

test_0402		72.79 292	70.44 303	79.84 252	88.13 184	65.99 178	85.93 213	84.29 283	65.57 288	67.40 339	85.49 270	46.92 316	92.61 193	35.88 402	74.38 327	80.94 380

MVStest1		56.63 366	52.76 372	68.25 373	61.67 414	53.25 368	71.67 380	68.90 397	38.59 407	50.59 403	83.05 321	25.08 400	70.66 404	36.76 401	38.56 410	80.83 381

UnsupCasMVSNet_bld		63.70 355	61.53 361	70.21 362	73.69 391	51.39 380	72.82 376	81.89 320	55.63 377	57.81 391	71.80 396	38.67 371	78.61 370	49.26 361	52.21 401	80.63 382

LCM-MVSNet		54.25 368	49.68 378	67.97 375	53.73 422	45.28 401	66.85 400	80.78 331	35.96 411	39.45 412	62.23 405	8.70 422	78.06 374	48.24 368	51.20 402	80.57 383

N_pmnet		52.79 373	53.26 371	51.40 397	78.99 369	7.68 431	69.52 389	3.89 430	51.63 389	57.01 393	74.98 389	40.83 361	65.96 412	37.78 399	64.67 377	80.56 384

TinyColmap		67.30 339	64.81 344	74.76 326	81.92 330	56.68 327	80.29 317	81.49 325	60.33 342	56.27 396	83.22 317	24.77 402	87.66 312	45.52 382	69.47 360	79.95 385

PM-MVS		66.41 345	64.14 347	73.20 340	73.92 389	56.45 329	78.97 334	64.96 406	63.88 313	64.72 363	80.24 354	19.84 410	83.44 348	66.24 233	64.52 378	79.71 386

ANet_high		50.57 377	46.10 381	63.99 380	48.67 425	39.13 414	70.99 384	80.85 330	61.39 337	31.18 414	57.70 410	17.02 413	73.65 401	31.22 407	15.89 422	79.18 387

LF4IMVS		64.02 354	62.19 358	69.50 364	70.90 402	53.29 367	76.13 356	77.18 365	52.65 385	58.59 387	80.98 346	23.55 405	76.52 382	53.06 340	66.66 370	78.68 388

PatchMatch-RL		72.38 294	70.90 298	76.80 305	88.60 166	67.38 152	79.53 324	76.17 372	62.75 325	69.36 321	82.00 340	45.51 333	84.89 338	53.62 336	80.58 244	78.12 389

MS-PatchMatch		73.83 277	72.67 277	77.30 300	83.87 287	66.02 176	81.82 290	84.66 277	61.37 338	68.61 328	82.82 327	47.29 312	88.21 304	59.27 294	84.32 193	77.68 390

DSMNet-mixed		57.77 365	56.90 367	60.38 385	67.70 406	35.61 416	69.18 391	53.97 417	32.30 415	57.49 392	79.88 358	40.39 364	68.57 409	38.78 398	72.37 343	76.97 391

CHOSEN 280x420		66.51 344	64.71 345	71.90 349	81.45 337	63.52 233	57.98 412	68.95 396	53.57 382	62.59 375	76.70 380	46.22 324	75.29 395	55.25 328	79.68 254	76.88 392

mvsany_test3		53.99 369	51.45 374	61.61 384	55.51 418	44.74 404	63.52 408	45.41 423	43.69 401	58.11 390	76.45 382	17.99 411	63.76 414	54.77 331	47.59 405	76.34 393

dmvs_testset		62.63 357	64.11 348	58.19 387	78.55 370	24.76 425	75.28 364	65.94 403	67.91 259	60.34 381	76.01 384	53.56 247	73.94 400	31.79 406	67.65 367	75.88 394

mvsany_test1		62.30 358	61.26 362	65.41 379	69.52 403	54.86 352	66.86 399	49.78 419	46.65 396	68.50 330	83.21 318	49.15 302	66.28 411	56.93 320	60.77 385	75.11 395

PMMVS		69.34 323	68.67 314	71.35 355	75.67 381	62.03 259	75.17 365	73.46 382	50.00 392	68.68 326	79.05 364	52.07 264	78.13 372	61.16 281	82.77 218	73.90 396

test_vis1_rt		60.28 361	58.42 364	65.84 378	67.25 407	55.60 344	70.44 387	60.94 411	44.33 400	59.00 386	66.64 401	24.91 401	68.67 408	62.80 260	69.48 359	73.25 397

pmmvs3		57.79 364	54.26 369	68.37 371	64.02 412	56.72 325	75.12 368	65.17 404	40.20 404	52.93 400	69.86 400	20.36 409	75.48 392	45.45 383	55.25 397	72.90 398

PVSNet_0	57.27 20	61.67 360	59.27 363	68.85 368	79.61 363	57.44 316	68.01 395	73.44 383	55.93 376	58.54 388	70.41 399	44.58 338	77.55 376	47.01 373	35.91 411	71.55 399

WB-MVS		54.94 367	54.72 368	55.60 393	73.50 392	20.90 427	74.27 373	61.19 410	59.16 354	50.61 402	74.15 390	47.19 314	75.78 390	17.31 418	35.07 412	70.12 400

SSC-MVS		53.88 370	53.59 370	54.75 395	72.87 398	19.59 428	73.84 375	60.53 412	57.58 368	49.18 406	73.45 393	46.34 323	75.47 393	16.20 421	32.28 414	69.20 401

test_f		52.09 374	50.82 375	55.90 391	53.82 421	42.31 411	59.42 411	58.31 415	36.45 410	56.12 397	70.96 398	12.18 417	57.79 417	53.51 337	56.57 392	67.60 402

PMMVS2		40.82 384	38.86 388	46.69 398	53.84 420	16.45 429	48.61 415	49.92 418	37.49 408	31.67 413	60.97 406	8.14 424	56.42 418	28.42 409	30.72 415	67.19 403

new_pmnet		50.91 376	50.29 376	52.78 396	68.58 405	34.94 418	63.71 407	56.63 416	39.73 405	44.95 407	65.47 402	21.93 407	58.48 416	34.98 403	56.62 391	64.92 404

MVS-HIRNet		59.14 363	57.67 365	63.57 381	81.65 332	43.50 406	71.73 379	65.06 405	39.59 406	51.43 401	57.73 409	38.34 373	82.58 353	39.53 395	73.95 330	64.62 405

APD_test1		53.31 372	49.93 377	63.42 382	65.68 409	50.13 387	71.59 381	66.90 401	34.43 412	40.58 411	71.56 397	8.65 423	76.27 385	34.64 404	55.36 395	63.86 406

test_method		31.52 387	29.28 391	38.23 401	27.03 429	6.50 432	20.94 420	62.21 409	4.05 423	22.35 421	52.50 414	13.33 415	47.58 421	27.04 411	34.04 413	60.62 407

EGC-MVSNET		52.07 375	47.05 379	67.14 376	83.51 295	60.71 276	80.50 313	67.75 398	0.07 425	0.43 426	75.85 387	24.26 403	81.54 358	28.82 408	62.25 381	59.16 408

test_vis3_rt		49.26 378	47.02 380	56.00 390	54.30 419	45.27 402	66.76 401	48.08 420	36.83 409	44.38 408	53.20 413	7.17 425	64.07 413	56.77 322	55.66 393	58.65 409

FPMVS		53.68 371	51.64 373	59.81 386	65.08 410	51.03 382	69.48 390	69.58 393	41.46 403	40.67 410	72.32 395	16.46 414	70.00 407	24.24 414	65.42 375	58.40 410

testf1		45.72 379	41.96 383	57.00 388	56.90 416	45.32 399	66.14 402	59.26 413	26.19 416	30.89 415	60.96 407	4.14 426	70.64 405	26.39 412	46.73 407	55.04 411

APD_test2		45.72 379	41.96 383	57.00 388	56.90 416	45.32 399	66.14 402	59.26 413	26.19 416	30.89 415	60.96 407	4.14 426	70.64 405	26.39 412	46.73 407	55.04 411

PMVS	37.38 22	44.16 383	40.28 387	55.82 392	40.82 427	42.54 410	65.12 406	63.99 407	34.43 412	24.48 418	57.12 411	3.92 428	76.17 387	17.10 419	55.52 394	48.75 413
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 389	25.89 393	43.81 400	44.55 426	35.46 417	28.87 419	39.07 424	18.20 420	18.58 422	40.18 417	2.68 429	47.37 422	17.07 420	23.78 419	48.60 414
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dongtai		45.42 381	45.38 382	45.55 399	73.36 395	26.85 423	67.72 396	34.19 425	54.15 381	49.65 405	56.41 412	25.43 399	62.94 415	19.45 416	28.09 416	46.86 415

kuosan		39.70 385	40.40 386	37.58 402	64.52 411	26.98 421	65.62 404	33.02 426	46.12 397	42.79 409	48.99 415	24.10 404	46.56 423	12.16 424	26.30 417	39.20 416

Gipuma		45.18 382	41.86 385	55.16 394	77.03 377	51.52 378	32.50 418	80.52 335	32.46 414	27.12 417	35.02 418	9.52 421	75.50 391	22.31 415	60.21 388	38.45 417
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX				27.40 405	40.17 428	26.90 422		24.59 429	17.44 421	23.95 419	48.61 416	9.77 420	26.48 424	18.06 417	24.47 418	28.83 418

E-PMN		31.77 386	30.64 389	35.15 403	52.87 423	27.67 420	57.09 413	47.86 421	24.64 418	16.40 423	33.05 419	11.23 419	54.90 419	14.46 422	18.15 420	22.87 419

EMVS		30.81 388	29.65 390	34.27 404	50.96 424	25.95 424	56.58 414	46.80 422	24.01 419	15.53 424	30.68 420	12.47 416	54.43 420	12.81 423	17.05 421	22.43 420

tmp_tt		18.61 391	21.40 394	10.23 407	4.82 430	10.11 430	34.70 417	30.74 428	1.48 424	23.91 420	26.07 421	28.42 396	13.41 426	27.12 410	15.35 423	7.17 421

wuyk23d		16.82 392	15.94 395	19.46 406	58.74 415	31.45 419	39.22 416	3.74 431	6.84 422	6.04 425	2.70 425	1.27 430	24.29 425	10.54 425	14.40 424	2.63 422

test123		6.12 394	8.11 397	0.14 408	0.06 432	0.09 433	71.05 383	0.03 433	0.04 427	0.25 428	1.30 427	0.05 431	0.03 428	0.21 427	0.01 426	0.29 423

testmvs		6.04 395	8.02 398	0.10 409	0.08 431	0.03 434	69.74 388	0.04 432	0.05 426	0.31 427	1.68 426	0.02 432	0.04 427	0.24 426	0.02 425	0.25 424

mmdepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

monomultidepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

test_blank		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet_test		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

DCPMVS		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

cdsmvs_eth3d_5k		19.96 390	26.61 392	0.00 410	0.00 433	0.00 435	0.00 421	89.26 184	0.00 428	0.00 429	88.61 185	61.62 170	0.00 429	0.00 428	0.00 427	0.00 425

pcd_1.5k_mvsjas		5.26 396	7.02 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	63.15 146	0.00 429	0.00 428	0.00 427	0.00 425

sosnet-low-res		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

sosnet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uncertanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

Regformer		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

ab-mvs-re		7.23 393	9.64 396	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	86.72 235	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

WAC-MVS						42.58 408								39.46 396

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 121	91.30 15

test_one_0601					95.07 7	71.46 57		94.14 5	78.27 35	92.05 11	95.74 6	80.83 11

eth-test2					0.00 433

eth-test					0.00 433

ZD-MVS					94.38 25	72.22 44		92.67 67	70.98 193	87.75 37	94.07 46	74.01 32	96.70 27	84.66 54	94.84 44

test_241102_ONE					95.30 2	70.98 66		94.06 10	77.17 56	93.10 1	95.39 14	82.99 1	97.27 12

9.14			88.26 15		92.84 63		91.52 48	94.75 1	73.93 135	88.57 25	94.67 21	75.57 22	95.79 58	86.77 37	95.76 23

save fliter					93.80 40	72.35 42	90.47 66	91.17 125	74.31 126

test0726					95.27 5	71.25 59	93.60 6	94.11 6	77.33 50	92.81 3	95.79 3	80.98 9

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs												50.01 289

MTGPA								92.02 93

test_post1							78.90 336				5.43 424	48.81 308	85.44 333	59.25 295

test_post											5.46 423	50.36 287	84.24 341

patchmatchnet-post											74.00 391	51.12 278	88.60 300

MTMP							92.18 34	32.83 427

gm-plane-assit					81.40 338	53.83 361			62.72 326		80.94 347		92.39 204	63.40 257

TEST9					93.26 52	72.96 25	88.75 120	91.89 101	68.44 253	85.00 65	93.10 72	74.36 28	95.41 73

test_8					93.13 54	72.57 35	88.68 125	91.84 105	68.69 248	84.87 69	93.10 72	74.43 26	95.16 83

agg_prior					92.85 62	71.94 50		91.78 108		84.41 80			94.93 94

test_prior4						72.60 34	89.01 111

test_prior2							88.85 117		75.41 98	84.91 67	93.54 61	74.28 29		83.31 69	95.86 20

旧先验2							86.56 196		58.10 363	87.04 47			88.98 292	74.07 160

新几何2							86.29 205

原ACMM2							86.86 185

testdata2													91.01 258	62.37 267

segment_acmp												73.08 38

testdata1							84.14 259		75.71 92

plane_prior7					90.08 108	68.51 123

plane_prior6					89.84 117	68.70 118						60.42 196

plane_prior4											91.00 132

plane_prior3						68.60 121			78.44 31	78.92 153

plane_prior2							91.25 52		79.12 23

plane_prior1					89.90 116

plane_prior						68.71 116	90.38 70		77.62 40						86.16 168

n2								0.00 434

nn								0.00 434

door-mid								69.98 391

test11								92.23 87

door								69.44 394

HQP5-MVS						66.98 163

HQP-NCC					89.33 135		89.17 103		76.41 77	77.23 191

ACMP_Plane					89.33 135		89.17 103		76.41 77	77.23 191

BP-MVS														77.47 124

HQP3-MVS								92.19 90							85.99 172

HQP2-MVS												60.17 199

NP-MVS					89.62 121	68.32 127					90.24 144

MDTV_nov1_ep13			69.97 308		83.18 303	53.48 363	77.10 355	80.18 343	60.45 341	69.33 322	80.44 351	48.89 307	86.90 315	51.60 346	78.51 267

ACMMP++_ref															81.95 229

ACMMP++															81.25 234

Test By Simon												64.33 133

High-resolution multi-view benchmark