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 44	94.97 19	71.70 54	97.68 1	92.19 1	95.63 28	95.57 1

casdiffmvs_mvg		85.99 49	86.09 51	85.70 74	87.65 209	67.22 159	88.69 125	93.04 41	79.64 19	85.33 62	92.54 89	73.30 35	94.50 112	83.49 68	91.14 96	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 59	86.15 49	84.06 133	91.71 78	64.94 204	86.47 199	91.87 103	73.63 142	86.60 53	93.02 78	76.57 15	91.87 225	83.36 69	92.15 80	95.35 3

casdiffmvs		85.11 68	85.14 68	85.01 90	87.20 223	65.77 185	87.75 158	92.83 60	77.84 38	84.36 83	92.38 91	72.15 47	93.93 134	81.27 93	90.48 103	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 61	84.47 77	88.51 7	91.08 86	73.49 16	93.18 11	93.78 18	80.79 8	76.66 206	93.37 68	60.40 199	96.75 26	77.20 128	93.73 64	95.29 5

BP-MVS1		84.32 76	83.71 84	86.17 61	87.84 199	67.85 138	89.38 98	89.64 172	77.73 39	83.98 90	92.12 96	56.89 223	95.43 70	84.03 65	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	89.54 174	82.14 3	86.65 52	94.28 36	68.28 96	97.46 6	90.81 3	95.31 34	95.15 7

CS-MVS		86.69 39	86.95 36	85.90 71	90.76 96	67.57 147	92.83 17	93.30 32	79.67 17	84.57 79	92.27 92	71.47 57	95.02 93	84.24 62	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	74.62 120	88.90 23	93.85 58	75.75 20	96.00 54	87.80 31	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 71	84.98 69	84.80 100	87.30 221	65.39 193	87.30 172	92.88 57	77.62 41	84.04 89	92.26 93	71.81 51	93.96 128	81.31 91	90.30 106	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 34	92.78 4	95.74 6	82.45 3	97.49 4	89.42 12	96.68 2	94.95 11

PC_three_1452									68.21 257	92.02 12	94.00 52	82.09 5	95.98 56	84.58 56	96.68 2	94.95 11

IS-MVSNet		83.15 100	82.81 99	84.18 123	89.94 115	63.30 240	91.59 43	88.46 214	79.04 26	79.49 146	92.16 94	65.10 129	94.28 117	67.71 222	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 30	94.80 20	73.76 33	97.11 15	87.51 34	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 54	93.10 1	95.72 8	82.99 1	97.44 7	89.07 17	96.63 4	94.88 15

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 50	82.45 3	96.87 20	83.77 67	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	74.77 116	92.29 7	95.97 2	74.28 29	97.24 13	88.58 24	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		77.30 230	76.49 227	79.74 255	90.08 108	52.02 371	87.86 157	63.10 409	74.88 112	80.16 139	92.79 85	38.29 375	92.35 207	68.74 215	92.50 77	94.86 18

ECVR-MVS		79.61 168	79.26 161	80.67 237	90.08 108	54.69 354	87.89 155	77.44 363	74.88 112	80.27 136	92.79 85	48.96 307	92.45 201	68.55 216	92.50 77	94.86 18

IU-MVS					95.30 2	71.25 59		92.95 55	66.81 268	92.39 6				88.94 19	96.63 4	94.85 20

test1111		79.43 175	79.18 164	80.15 247	89.99 113	53.31 367	87.33 171	77.05 367	75.04 107	80.23 138	92.77 87	48.97 306	92.33 209	68.87 213	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 93	89.16 20	95.10 16	75.65 21	96.19 46	87.07 37	96.01 17	94.79 22

balanced_conf03		86.78 37	86.99 34	86.15 63	91.24 83	67.61 145	90.51 62	92.90 56	77.26 53	87.44 43	91.63 108	71.27 61	96.06 49	85.62 45	95.01 37	94.78 23

sasdasda		85.91 53	85.87 55	86.04 67	89.84 117	69.44 98	90.45 68	93.00 46	76.70 73	88.01 33	91.23 120	73.28 36	93.91 135	81.50 89	88.80 129	94.77 24

SPE-MVS-test		86.29 47	86.48 42	85.71 73	91.02 88	67.21 160	92.36 29	93.78 18	78.97 29	83.51 100	91.20 123	70.65 70	95.15 84	81.96 86	94.89 42	94.77 24

canonicalmvs		85.91 53	85.87 55	86.04 67	89.84 117	69.44 98	90.45 68	93.00 46	76.70 73	88.01 33	91.23 120	73.28 36	93.91 135	81.50 89	88.80 129	94.77 24

GDP-MVS		83.52 92	82.64 102	86.16 62	88.14 183	68.45 124	89.13 108	92.69 65	72.82 165	83.71 95	91.86 102	55.69 228	95.35 79	80.03 104	89.74 117	94.69 27

test_0728_THIRD									78.38 34	92.12 9	95.78 4	81.46 7	97.40 9	89.42 12	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 43	78.35 13	96.77 24	89.59 11	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		82.60 111	82.10 110	84.10 125	87.98 193	62.94 251	87.45 167	91.27 121	77.42 50	79.85 141	90.28 143	56.62 225	94.70 107	79.87 107	88.15 141	94.67 28

MGCFI-Net		85.06 70	85.51 60	83.70 149	89.42 130	63.01 246	89.43 93	92.62 73	76.43 77	87.53 41	91.34 118	72.82 43	93.42 161	81.28 92	88.74 132	94.66 31

alignmvs		85.48 61	85.32 65	85.96 70	89.51 126	69.47 95	89.74 83	92.47 76	76.17 86	87.73 40	91.46 115	70.32 72	93.78 141	81.51 88	88.95 126	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	75.17 106	86.34 54	95.29 15	70.86 66	96.00 54	88.78 22	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 47	89.79 19	94.12 45	78.98 12	96.58 35	85.66 43	95.72 24	94.58 33

VDD-MVS		83.01 105	82.36 106	84.96 92	91.02 88	66.40 170	88.91 115	88.11 217	77.57 43	84.39 82	93.29 70	52.19 260	93.91 135	77.05 131	88.70 133	94.57 35

VDDNet		81.52 128	80.67 131	84.05 136	90.44 101	64.13 222	89.73 84	85.91 265	71.11 190	83.18 102	93.48 64	50.54 286	93.49 155	73.40 168	88.25 139	94.54 36

MVSMamba_PlusPlus		85.99 49	85.96 53	86.05 66	91.09 85	67.64 144	89.63 88	92.65 70	72.89 164	84.64 76	91.71 104	71.85 50	96.03 50	84.77 54	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 95	91.06 16	96.03 1	76.84 14	97.03 17	89.09 14	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 9	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 9	96.44 9	94.41 39

MCST-MVS		87.37 29	87.25 30	87.73 28	94.53 17	72.46 38	89.82 79	93.82 16	73.07 159	84.86 71	92.89 80	76.22 17	96.33 41	84.89 51	95.13 36	94.40 41

CANet		86.45 42	86.10 50	87.51 37	90.09 107	70.94 70	89.70 85	92.59 74	81.78 4	81.32 124	91.43 116	70.34 71	97.23 14	84.26 60	93.36 68	94.37 42

PHI-MVS		86.43 43	86.17 48	87.24 41	90.88 92	70.96 68	92.27 32	94.07 9	72.45 166	85.22 64	91.90 99	69.47 81	96.42 40	83.28 71	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 31	94.06 48	76.43 16	96.84 21	88.48 27	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 67	85.24 63	94.32 35	71.76 52	96.93 19	85.53 46	95.79 22	94.32 45

HPM-MVS		87.11 33	86.98 35	87.50 38	93.88 39	72.16 45	92.19 33	93.33 31	76.07 88	83.81 94	93.95 57	69.77 79	96.01 53	85.15 47	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 57	85.29 67	87.17 43	93.49 47	71.08 64	88.58 129	92.42 80	68.32 256	84.61 77	93.48 64	72.32 45	96.15 48	79.00 109	95.43 30	94.28 47

test_241102_TWO								94.06 10	77.24 54	92.78 4	95.72 8	81.26 8	97.44 7	89.07 17	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 15	96.41 12	94.21 49

DeepC-MVS_fast	79.65 3	86.91 36	86.62 41	87.76 27	93.52 46	72.37 41	91.26 51	93.04 41	76.62 75	84.22 84	93.36 69	71.44 58	96.76 25	80.82 97	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 96	83.02 95	84.57 104	90.13 106	64.47 215	92.32 30	90.73 137	74.45 124	79.35 148	91.10 126	69.05 88	95.12 85	72.78 175	87.22 152	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 58	93.47 66	73.02 41	97.00 18	84.90 49	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 85	88.14 29	95.09 17	71.06 64	96.67 29	87.67 32	96.37 14	94.09 53

XVS		87.18 32	86.91 38	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 97	94.17 42	67.45 104	96.60 33	83.06 72	94.50 51	94.07 54

X-MVStestdata		80.37 157	77.83 193	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 97	12.47 423	67.45 104	96.60 33	83.06 72	94.50 51	94.07 54

region2R		87.42 27	87.20 32	88.09 14	94.63 14	73.55 13	93.03 14	93.12 40	76.73 72	84.45 80	94.52 24	69.09 85	96.70 27	84.37 59	94.83 45	94.03 56

ACMMPR		87.44 25	87.23 31	88.08 15	94.64 13	73.59 12	93.04 12	93.20 34	76.78 69	84.66 75	94.52 24	68.81 91	96.65 30	84.53 57	94.90 41	94.00 57

fmvsm_s_conf0.1_n_2		83.80 83	83.79 83	83.83 146	85.62 251	64.94 204	87.03 179	86.62 254	74.32 126	87.97 35	94.33 34	60.67 191	92.60 194	89.72 8	87.79 144	93.96 58

test_fmvsmconf_n		85.92 52	86.04 52	85.57 76	85.03 265	69.51 93	89.62 89	90.58 140	73.42 150	87.75 38	94.02 50	72.85 42	93.24 166	90.37 4	90.75 100	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 91	92.29 7	95.66 10	81.67 6	97.38 11	87.44 36	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 66	85.34 63	85.13 87	86.12 243	69.93 86	88.65 127	90.78 136	69.97 217	88.27 27	93.98 55	71.39 59	91.54 238	88.49 26	90.45 104	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 29	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 65	84.68 72	93.99 54	70.67 69	96.82 22	84.18 64	95.01 37	93.90 63

test_fmvsmconf0.1_n		85.61 60	85.65 58	85.50 77	82.99 312	69.39 100	89.65 86	90.29 153	73.31 153	87.77 37	94.15 44	71.72 53	93.23 167	90.31 5	90.67 102	93.89 64

Anonymous202405211		78.25 203	77.01 213	81.99 204	91.03 87	60.67 278	84.77 241	83.90 290	70.65 203	80.00 140	91.20 123	41.08 361	91.43 245	65.21 244	85.26 179	93.85 65

LFMVS		81.82 121	81.23 122	83.57 153	91.89 76	63.43 238	89.84 78	81.85 323	77.04 62	83.21 101	93.10 73	52.26 259	93.43 160	71.98 181	89.95 114	93.85 65

fmvsm_s_conf0.5_n_2		84.04 79	84.11 80	83.81 147	86.17 241	65.00 202	86.96 181	87.28 238	74.35 125	88.25 28	94.23 40	61.82 167	92.60 194	89.85 7	88.09 142	93.84 67

Effi-MVS+		83.62 90	83.08 93	85.24 83	88.38 175	67.45 149	88.89 116	89.15 190	75.50 98	82.27 112	88.28 196	69.61 80	94.45 114	77.81 122	87.84 143	93.84 67

Anonymous20240529		80.19 161	78.89 169	84.10 125	90.60 97	64.75 209	88.95 114	90.90 132	65.97 285	80.59 134	91.17 125	49.97 291	93.73 147	69.16 210	82.70 222	93.81 69

MVS_Test		83.15 100	83.06 94	83.41 158	86.86 228	63.21 242	86.11 210	92.00 95	74.31 127	82.87 106	89.44 168	70.03 75	93.21 169	77.39 127	88.50 137	93.81 69

test_fmvsmconf0.01_n		84.73 74	84.52 76	85.34 80	80.25 353	69.03 103	89.47 91	89.65 171	73.24 157	86.98 49	94.27 37	66.62 110	93.23 167	90.26 6	89.95 114	93.78 71

GeoE		81.71 123	81.01 127	83.80 148	89.51 126	64.45 216	88.97 113	88.73 209	71.27 187	78.63 160	89.76 154	66.32 116	93.20 172	69.89 202	86.02 172	93.74 72

diffmvs		82.10 114	81.88 116	82.76 192	83.00 310	63.78 228	83.68 266	89.76 167	72.94 162	82.02 115	89.85 152	65.96 123	90.79 262	82.38 84	87.30 151	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 69	84.91 68	94.44 31	70.78 67	96.61 32	84.53 57	94.89 42	93.66 74

VNet		82.21 113	82.41 104	81.62 210	90.82 93	60.93 273	84.47 249	89.78 166	76.36 83	84.07 88	91.88 100	64.71 133	90.26 268	70.68 193	88.89 127	93.66 74

PGM-MVS		86.68 40	86.27 45	87.90 22	94.22 33	73.38 18	90.22 73	93.04 41	75.53 97	83.86 92	94.42 32	67.87 101	96.64 31	82.70 82	94.57 50	93.66 74

DELS-MVS		85.41 64	85.30 66	85.77 72	88.49 169	67.93 137	85.52 229	93.44 27	78.70 30	83.63 99	89.03 175	74.57 24	95.71 61	80.26 103	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 37	90.32 17	94.00 52	74.83 23	93.78 141	87.63 33	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 39	87.69 33	91.16 84	72.32 43	90.31 71	93.94 14	77.12 59	82.82 108	94.23 40	72.13 48	97.09 16	84.83 52	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 87	84.54 74	80.99 229	90.06 112	65.83 182	84.21 258	88.74 208	71.60 181	85.01 65	92.44 90	74.51 25	83.50 348	82.15 85	92.15 80	93.64 80

EIA-MVS		83.31 99	82.80 100	84.82 98	89.59 122	65.59 188	88.21 142	92.68 66	74.66 119	78.96 152	86.42 251	69.06 87	95.26 80	75.54 148	90.09 110	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 43	83.84 93	94.40 33	72.24 46	96.28 43	85.65 44	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 65	84.95 71	86.57 56	93.69 42	70.58 78	92.15 35	91.62 111	73.89 137	82.67 111	94.09 46	62.60 153	95.54 65	80.93 95	92.93 71	93.57 83

fmvsm_s_conf0.1_n		83.56 91	83.38 89	84.10 125	84.86 267	67.28 155	89.40 97	83.01 307	70.67 199	87.08 47	93.96 56	68.38 94	91.45 244	88.56 25	84.50 187	93.56 84

CSCG		86.41 45	86.19 47	87.07 45	92.91 61	72.48 37	90.81 58	93.56 24	73.95 134	83.16 103	91.07 128	75.94 18	95.19 82	79.94 106	94.38 56	93.55 85

test12				86.80 52	92.63 67	70.70 75		91.79 107		82.71 110		71.67 55	96.16 47		94.50 51	93.54 86

APD-MVS_3200maxsize		85.97 51	85.88 54	86.22 60	92.69 66	69.53 92	91.93 37	92.99 49	73.54 146	85.94 55	94.51 27	65.80 124	95.61 62	83.04 74	92.51 76	93.53 87

mvs_anonymous		79.42 176	79.11 165	80.34 243	84.45 276	57.97 306	82.59 285	87.62 231	67.40 266	76.17 221	88.56 189	68.47 93	89.59 281	70.65 194	86.05 171	93.47 88

fmvsm_s_conf0.5_n		83.80 83	83.71 84	84.07 131	86.69 234	67.31 154	89.46 92	83.07 306	71.09 191	86.96 50	93.70 61	69.02 90	91.47 243	88.79 21	84.62 186	93.44 89

mPP-MVS		86.67 41	86.32 44	87.72 30	94.41 22	73.55 13	92.74 20	92.22 88	76.87 66	82.81 109	94.25 39	66.44 114	96.24 44	82.88 77	94.28 58	93.38 90

EPNet		83.72 86	82.92 98	86.14 65	84.22 279	69.48 94	91.05 56	85.27 271	81.30 6	76.83 201	91.65 106	66.09 119	95.56 63	76.00 142	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 94	82.80 100	85.43 79	90.25 104	68.74 114	90.30 72	90.13 158	76.33 84	80.87 132	92.89 80	61.00 186	94.20 122	72.45 180	90.97 97	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 51	92.12 9	95.78 4	80.98 9	97.40 9	89.08 15	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		79.10 185	78.24 183	81.70 209	86.85 229	60.24 285	87.28 173	88.79 203	74.25 129	76.84 200	90.53 141	49.48 297	91.56 236	67.98 220	82.15 226	93.29 94

EI-MVSNet-Vis-set		84.19 77	83.81 82	85.31 81	88.18 180	67.85 138	87.66 160	89.73 169	80.05 14	82.95 104	89.59 160	70.74 68	94.82 101	80.66 100	84.72 184	93.28 95

MTAPA		87.23 31	87.00 33	87.90 22	94.18 35	74.25 5	86.58 196	92.02 93	79.45 20	85.88 56	94.80 20	68.07 97	96.21 45	86.69 39	95.34 32	93.23 96

CP-MVS		87.11 33	86.92 37	87.68 34	94.20 34	73.86 7	93.98 3	92.82 63	76.62 75	83.68 96	94.46 28	67.93 99	95.95 57	84.20 63	94.39 55	93.23 96

ACMMP		85.89 55	85.39 62	87.38 39	93.59 45	72.63 33	92.74 20	93.18 39	76.78 69	80.73 133	93.82 59	64.33 134	96.29 42	82.67 83	90.69 101	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 98	82.99 96	84.28 117	83.79 289	68.07 134	89.34 100	82.85 312	69.80 221	87.36 45	94.06 48	68.34 95	91.56 236	87.95 30	83.46 211	93.21 99

PAPM_NR		83.02 104	82.41 104	84.82 98	92.47 70	66.37 171	87.93 153	91.80 106	73.82 138	77.32 189	90.66 138	67.90 100	94.90 97	70.37 196	89.48 120	93.19 100

reproduce_model		87.28 30	87.39 28	86.95 48	93.10 56	71.24 63	91.60 42	93.19 35	74.69 117	88.80 24	95.61 11	70.29 73	96.44 39	86.20 42	93.08 69	93.16 101

OMC-MVS		82.69 107	81.97 115	84.85 97	88.75 161	67.42 150	87.98 149	90.87 134	74.92 111	79.72 143	91.65 106	62.19 163	93.96 128	75.26 152	86.42 164	93.16 101

fmvsm_s_conf0.5_n_a		83.63 89	83.41 88	84.28 117	86.14 242	68.12 132	89.43 93	82.87 311	70.27 210	87.27 46	93.80 60	69.09 85	91.58 234	88.21 29	83.65 206	93.14 103

PAPR		81.66 126	80.89 129	83.99 141	90.27 103	64.00 223	86.76 192	91.77 109	68.84 247	77.13 199	89.50 161	67.63 102	94.88 99	67.55 224	88.52 136	93.09 104

UA-Net		85.08 69	84.96 70	85.45 78	92.07 73	68.07 134	89.78 82	90.86 135	82.48 2	84.60 78	93.20 72	69.35 82	95.22 81	71.39 186	90.88 99	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	74.98 109	88.96 21	95.54 12	71.20 62	96.54 36	86.28 40	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	74.98 109	88.96 21	95.54 12	71.20 62	96.54 36	86.28 40	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 36	94.27 37	75.89 19	96.81 23	87.45 35	96.44 9	93.05 108

thisisatest0530		79.40 177	77.76 198	84.31 115	87.69 208	65.10 200	87.36 169	84.26 286	70.04 213	77.42 186	88.26 198	49.94 292	94.79 103	70.20 197	84.70 185	93.03 109

train_agg		86.43 43	86.20 46	87.13 44	93.26 52	72.96 25	88.75 121	91.89 101	68.69 249	85.00 66	93.10 73	74.43 26	95.41 73	84.97 48	95.71 25	93.02 110

EC-MVSNet		86.01 48	86.38 43	84.91 96	89.31 138	66.27 173	92.32 30	93.63 21	79.37 21	84.17 86	91.88 100	69.04 89	95.43 70	83.93 66	93.77 63	93.01 111

mvsmamba		80.60 149	79.38 156	84.27 119	89.74 120	67.24 158	87.47 165	86.95 246	70.02 214	75.38 237	88.93 176	51.24 277	92.56 197	75.47 150	89.22 123	93.00 112

EI-MVSNet-UG-set		83.81 82	83.38 89	85.09 88	87.87 197	67.53 148	87.44 168	89.66 170	79.74 16	82.23 113	89.41 169	70.24 74	94.74 104	79.95 105	83.92 198	92.99 113

tttt0517		79.40 177	77.91 190	83.90 145	88.10 186	63.84 226	88.37 137	84.05 288	71.45 184	76.78 203	89.12 172	49.93 294	94.89 98	70.18 198	83.18 215	92.96 114

test9_res														84.90 49	95.70 26	92.87 115

SR-MVS		86.73 38	86.67 40	86.91 49	94.11 37	72.11 47	92.37 28	92.56 75	74.50 121	86.84 51	94.65 23	67.31 106	95.77 59	84.80 53	92.85 72	92.84 116

ETV-MVS		84.90 73	84.67 73	85.59 75	89.39 133	68.66 120	88.74 123	92.64 72	79.97 15	84.10 87	85.71 264	69.32 83	95.38 75	80.82 97	91.37 93	92.72 117

agg_prior2														82.91 76	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	73.01 161	88.58 25	94.52 24	73.36 34	96.49 38	84.26 60	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		78.63 196	76.63 226	84.64 103	86.73 233	69.47 95	85.01 236	84.61 279	69.54 227	66.51 353	86.59 244	50.16 289	91.75 228	76.26 138	84.24 195	92.69 120

Vis-MVSNet (Re-imp)		78.36 202	78.45 176	78.07 288	88.64 165	51.78 377	86.70 193	79.63 348	74.14 132	75.11 250	90.83 136	61.29 180	89.75 278	58.10 310	91.60 88	92.69 120

TSAR-MVS + GP.		85.71 58	85.33 64	86.84 50	91.34 81	72.50 36	89.07 111	87.28 238	76.41 78	85.80 57	90.22 147	74.15 31	95.37 78	81.82 87	91.88 83	92.65 122

test_fmvsmvis_n_1920		84.02 80	83.87 81	84.49 108	84.12 281	69.37 101	88.15 146	87.96 222	70.01 215	83.95 91	93.23 71	68.80 92	91.51 241	88.61 23	89.96 113	92.57 123

FA-MVS(test-final)		80.96 137	79.91 145	84.10 125	88.30 178	65.01 201	84.55 248	90.01 161	73.25 156	79.61 144	87.57 213	58.35 208	94.72 105	71.29 187	86.25 167	92.56 124

test_yl		81.17 133	80.47 135	83.24 164	89.13 146	63.62 229	86.21 207	89.95 163	72.43 169	81.78 120	89.61 158	57.50 216	93.58 149	70.75 191	86.90 156	92.52 125

DCV-MVSNet		81.17 133	80.47 135	83.24 164	89.13 146	63.62 229	86.21 207	89.95 163	72.43 169	81.78 120	89.61 158	57.50 216	93.58 149	70.75 191	86.90 156	92.52 125

SR-MVS-dyc-post		85.77 56	85.61 59	86.23 59	93.06 58	70.63 76	91.88 38	92.27 84	73.53 147	85.69 59	94.45 29	65.00 132	95.56 63	82.75 78	91.87 84	92.50 127

RE-MVS-def			85.48 61		93.06 58	70.63 76	91.88 38	92.27 84	73.53 147	85.69 59	94.45 29	63.87 138		82.75 78	91.87 84	92.50 127

nrg030		83.88 81	83.53 86	84.96 92	86.77 232	69.28 102	90.46 67	92.67 67	74.79 115	82.95 104	91.33 119	72.70 44	93.09 180	80.79 99	79.28 262	92.50 127

MG-MVS		83.41 95	83.45 87	83.28 161	92.74 65	62.28 258	88.17 144	89.50 176	75.22 102	81.49 123	92.74 88	66.75 109	95.11 87	72.85 174	91.58 90	92.45 130

FIs		82.07 116	82.42 103	81.04 228	88.80 158	58.34 300	88.26 141	93.49 26	76.93 64	78.47 165	91.04 129	69.92 77	92.34 208	69.87 203	84.97 181	92.44 131

fmvsm_s_conf0.5_n_3		86.36 46	87.46 27	83.09 171	87.08 226	65.21 196	89.09 110	90.21 155	79.67 17	89.98 18	95.02 18	73.17 38	91.71 231	91.30 2	91.60 88	92.34 132

FC-MVSNet-test		81.52 128	82.02 113	80.03 249	88.42 174	55.97 339	87.95 151	93.42 29	77.10 60	77.38 187	90.98 135	69.96 76	91.79 226	68.46 218	84.50 187	92.33 133

Fast-Effi-MVS+		80.81 141	79.92 144	83.47 154	88.85 153	64.51 212	85.53 227	89.39 179	70.79 196	78.49 164	85.06 282	67.54 103	93.58 149	67.03 232	86.58 161	92.32 134

TranMVSNet+NR-MVSNet		80.84 139	80.31 138	82.42 197	87.85 198	62.33 256	87.74 159	91.33 120	80.55 9	77.99 177	89.86 151	65.23 128	92.62 192	67.05 231	75.24 320	92.30 135

ab-mvs		79.51 171	78.97 168	81.14 225	88.46 171	60.91 274	83.84 263	89.24 186	70.36 206	79.03 151	88.87 179	63.23 145	90.21 270	65.12 245	82.57 223	92.28 136

CANet_DTU		80.61 148	79.87 146	82.83 184	85.60 252	63.17 245	87.36 169	88.65 210	76.37 82	75.88 224	88.44 192	53.51 249	93.07 181	73.30 169	89.74 117	92.25 137

UniMVSNet_NR-MVSNet		81.88 119	81.54 119	82.92 181	88.46 171	63.46 236	87.13 175	92.37 81	80.19 12	78.38 166	89.14 171	71.66 56	93.05 182	70.05 199	76.46 293	92.25 137

fmvsm_l_conf0.5_n		84.47 75	84.54 74	84.27 119	85.42 255	68.81 109	88.49 131	87.26 240	68.08 258	88.03 32	93.49 63	72.04 49	91.77 227	88.90 20	89.14 125	92.24 139

DU-MVS		81.12 135	80.52 134	82.90 182	87.80 201	63.46 236	87.02 180	91.87 103	79.01 27	78.38 166	89.07 173	65.02 130	93.05 182	70.05 199	76.46 293	92.20 140

NR-MVSNet		80.23 159	79.38 156	82.78 190	87.80 201	63.34 239	86.31 204	91.09 129	79.01 27	72.17 291	89.07 173	67.20 107	92.81 191	66.08 238	75.65 306	92.20 140

TAPA-MVS	73.13 9	79.15 183	77.94 189	82.79 189	89.59 122	62.99 250	88.16 145	91.51 115	65.77 286	77.14 198	91.09 127	60.91 187	93.21 169	50.26 357	87.05 154	92.17 142
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_l_conf0.5_n_a		84.13 78	84.16 79	84.06 133	85.38 256	68.40 125	88.34 138	86.85 250	67.48 265	87.48 42	93.40 67	70.89 65	91.61 232	88.38 28	89.22 123	92.16 143

3Dnovator	76.31 5	83.38 97	82.31 107	86.59 55	87.94 194	72.94 28	90.64 60	92.14 92	77.21 56	75.47 231	92.83 82	58.56 206	94.72 105	73.24 171	92.71 74	92.13 144

MVS_111021_HR		85.14 67	84.75 72	86.32 58	91.65 79	72.70 30	85.98 212	90.33 150	76.11 87	82.08 114	91.61 110	71.36 60	94.17 124	81.02 94	92.58 75	92.08 145

MVSFormer		82.85 106	82.05 112	85.24 83	87.35 215	70.21 80	90.50 64	90.38 146	68.55 251	81.32 124	89.47 163	61.68 169	93.46 158	78.98 110	90.26 107	92.05 146

jason		81.39 131	80.29 139	84.70 102	86.63 236	69.90 88	85.95 213	86.77 251	63.24 316	81.07 130	89.47 163	61.08 185	92.15 214	78.33 118	90.07 112	92.05 146
jason: jason.
HyFIR lowres test		77.53 225	75.40 244	83.94 144	89.59 122	66.62 167	80.36 316	88.64 211	56.29 376	76.45 211	85.17 279	57.64 214	93.28 164	61.34 281	83.10 216	91.91 148

XVG-OURS-SEG-HR		80.81 141	79.76 148	83.96 143	85.60 252	68.78 111	83.54 272	90.50 143	70.66 202	76.71 205	91.66 105	60.69 190	91.26 249	76.94 132	81.58 233	91.83 149

lupinMVS		81.39 131	80.27 140	84.76 101	87.35 215	70.21 80	85.55 225	86.41 256	62.85 323	81.32 124	88.61 186	61.68 169	92.24 212	78.41 117	90.26 107	91.83 149

WR-MVS		79.49 172	79.22 163	80.27 245	88.79 159	58.35 299	85.06 235	88.61 212	78.56 31	77.65 182	88.34 194	63.81 140	90.66 265	64.98 247	77.22 282	91.80 151

h-mvs33		83.15 100	82.19 108	86.02 69	90.56 98	70.85 73	88.15 146	89.16 189	76.02 89	84.67 73	91.39 117	61.54 172	95.50 66	82.71 80	75.48 310	91.72 152

UniMVSNet (Re)		81.60 127	81.11 124	83.09 171	88.38 175	64.41 217	87.60 161	93.02 45	78.42 33	78.56 162	88.16 200	69.78 78	93.26 165	69.58 206	76.49 292	91.60 153

UGNet		80.83 140	79.59 152	84.54 105	88.04 189	68.09 133	89.42 95	88.16 216	76.95 63	76.22 217	89.46 165	49.30 301	93.94 131	68.48 217	90.31 105	91.60 153
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		76.54 240	75.66 239	79.18 267	88.43 173	55.89 340	81.08 302	83.00 308	73.76 140	75.34 239	84.29 297	46.20 326	90.07 272	64.33 251	84.50 187	91.58 155

XVG-OURS		80.41 154	79.23 162	83.97 142	85.64 250	69.02 105	83.03 283	90.39 145	71.09 191	77.63 183	91.49 114	54.62 240	91.35 247	75.71 144	83.47 210	91.54 156

LCM-MVSNet-Re		77.05 232	76.94 216	77.36 299	87.20 223	51.60 378	80.06 319	80.46 338	75.20 103	67.69 335	86.72 236	62.48 156	88.98 293	63.44 257	89.25 122	91.51 157

DP-MVS Recon		83.11 103	82.09 111	86.15 63	94.44 19	70.92 71	88.79 119	92.20 89	70.53 204	79.17 150	91.03 131	64.12 136	96.03 50	68.39 219	90.14 109	91.50 158

PS-MVSNAJss		82.07 116	81.31 120	84.34 114	86.51 237	67.27 156	89.27 101	91.51 115	71.75 176	79.37 147	90.22 147	63.15 147	94.27 118	77.69 123	82.36 225	91.49 159

testing99		76.09 252	75.12 250	79.00 268	88.16 181	55.50 346	80.79 306	81.40 327	73.30 154	75.17 247	84.27 299	44.48 340	90.02 273	64.28 252	84.22 196	91.48 160

thisisatest0515		77.33 229	75.38 245	83.18 167	85.27 258	63.80 227	82.11 290	83.27 300	65.06 295	75.91 223	83.84 306	49.54 296	94.27 118	67.24 228	86.19 168	91.48 160

DPM-MVS		84.93 71	84.29 78	86.84 50	90.20 105	73.04 23	87.12 176	93.04 41	69.80 221	82.85 107	91.22 122	73.06 40	96.02 52	76.72 136	94.63 48	91.46 162

HQP_MVS		83.64 88	83.14 92	85.14 85	90.08 108	68.71 116	91.25 52	92.44 77	79.12 24	78.92 154	91.00 133	60.42 197	95.38 75	78.71 113	86.32 165	91.33 163

plane_prior5								92.44 77					95.38 75	78.71 113	86.32 165	91.33 163

GA-MVS		76.87 236	75.17 249	81.97 205	82.75 316	62.58 253	81.44 299	86.35 259	72.16 173	74.74 257	82.89 326	46.20 326	92.02 218	68.85 214	81.09 238	91.30 165

VPA-MVSNet		80.60 149	80.55 133	80.76 235	88.07 188	60.80 276	86.86 186	91.58 113	75.67 96	80.24 137	89.45 167	63.34 141	90.25 269	70.51 195	79.22 263	91.23 166

Effi-MVS+-dtu		80.03 163	78.57 174	84.42 110	85.13 263	68.74 114	88.77 120	88.10 218	74.99 108	74.97 254	83.49 315	57.27 219	93.36 162	73.53 165	80.88 240	91.18 167

v2v482		80.23 159	79.29 160	83.05 175	83.62 293	64.14 221	87.04 178	89.97 162	73.61 143	78.18 172	87.22 224	61.10 184	93.82 139	76.11 139	76.78 290	91.18 167

FE-MVS		77.78 218	75.68 237	84.08 130	88.09 187	66.00 177	83.13 278	87.79 228	68.42 255	78.01 176	85.23 277	45.50 335	95.12 85	59.11 298	85.83 176	91.11 169

Anonymous20231211		78.97 189	77.69 201	82.81 186	90.54 99	64.29 219	90.11 75	91.51 115	65.01 297	76.16 222	88.13 205	50.56 285	93.03 185	69.68 205	77.56 280	91.11 169

hse-mvs2		81.72 122	80.94 128	84.07 131	88.72 162	67.68 143	85.87 216	87.26 240	76.02 89	84.67 73	88.22 199	61.54 172	93.48 156	82.71 80	73.44 338	91.06 171

AUN-MVS		79.21 182	77.60 203	84.05 136	88.71 163	67.61 145	85.84 218	87.26 240	69.08 240	77.23 192	88.14 204	53.20 253	93.47 157	75.50 149	73.45 337	91.06 171

HQP4-MVS										77.24 191			95.11 87			91.03 173

HQP-MVS		82.61 109	82.02 113	84.37 111	89.33 135	66.98 163	89.17 103	92.19 90	76.41 78	77.23 192	90.23 146	60.17 200	95.11 87	77.47 125	85.99 173	91.03 173

RPSCF		73.23 287	71.46 291	78.54 278	82.50 322	59.85 288	82.18 289	82.84 313	58.96 357	71.15 302	89.41 169	45.48 336	84.77 340	58.82 302	71.83 350	91.02 175

test_djsdf		80.30 158	79.32 159	83.27 162	83.98 285	65.37 194	90.50 64	90.38 146	68.55 251	76.19 218	88.70 182	56.44 226	93.46 158	78.98 110	80.14 252	90.97 176

PCF-MVS	73.52 7	80.38 155	78.84 170	85.01 90	87.71 206	68.99 106	83.65 267	91.46 119	63.00 320	77.77 181	90.28 143	66.10 118	95.09 91	61.40 279	88.22 140	90.94 177
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VPNet		78.69 195	78.66 172	78.76 272	88.31 177	55.72 343	84.45 252	86.63 253	76.79 68	78.26 169	90.55 140	59.30 202	89.70 280	66.63 233	77.05 284	90.88 178

CPTT-MVS		83.73 85	83.33 91	84.92 95	93.28 49	70.86 72	92.09 36	90.38 146	68.75 248	79.57 145	92.83 82	60.60 195	93.04 184	80.92 96	91.56 91	90.86 179

tt0805		78.73 193	77.83 193	81.43 215	85.17 259	60.30 284	89.41 96	90.90 132	71.21 188	77.17 197	88.73 181	46.38 321	93.21 169	72.57 178	78.96 264	90.79 180

CLD-MVS		82.31 112	81.65 118	84.29 116	88.47 170	67.73 142	85.81 220	92.35 82	75.78 92	78.33 168	86.58 246	64.01 137	94.35 115	76.05 141	87.48 149	90.79 180
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v1192		79.59 170	78.43 178	83.07 174	83.55 295	64.52 211	86.93 184	90.58 140	70.83 195	77.78 180	85.90 260	59.15 203	93.94 131	73.96 162	77.19 283	90.76 182

IterMVS-LS		80.06 162	79.38 156	82.11 201	85.89 246	63.20 243	86.79 189	89.34 180	74.19 130	75.45 234	86.72 236	66.62 110	92.39 204	72.58 177	76.86 287	90.75 183
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		80.52 153	79.98 143	82.12 200	84.28 277	63.19 244	86.41 200	88.95 200	74.18 131	78.69 157	87.54 216	66.62 110	92.43 202	72.57 178	80.57 246	90.74 184

v1921920		79.22 181	78.03 187	82.80 187	83.30 300	63.94 225	86.80 188	90.33 150	69.91 219	77.48 185	85.53 270	58.44 207	93.75 145	73.60 164	76.85 288	90.71 185

QAPM		80.88 138	79.50 154	85.03 89	88.01 192	68.97 107	91.59 43	92.00 95	66.63 277	75.15 249	92.16 94	57.70 213	95.45 68	63.52 255	88.76 131	90.66 186

v144192		79.47 173	78.37 179	82.78 190	83.35 298	63.96 224	86.96 181	90.36 149	69.99 216	77.50 184	85.67 267	60.66 192	93.77 143	74.27 159	76.58 291	90.62 187

v1240		78.99 188	77.78 196	82.64 193	83.21 302	63.54 233	86.62 195	90.30 152	69.74 226	77.33 188	85.68 266	57.04 221	93.76 144	73.13 172	76.92 285	90.62 187

v1144		80.03 163	79.03 166	83.01 177	83.78 290	64.51 212	87.11 177	90.57 142	71.96 175	78.08 175	86.20 256	61.41 176	93.94 131	74.93 153	77.23 281	90.60 189

1112_ss		77.40 228	76.43 229	80.32 244	89.11 150	60.41 283	83.65 267	87.72 230	62.13 333	73.05 278	86.72 236	62.58 155	89.97 274	62.11 273	80.80 242	90.59 190

CP-MVSNet		78.22 204	78.34 180	77.84 290	87.83 200	54.54 356	87.94 152	91.17 125	77.65 40	73.48 273	88.49 190	62.24 162	88.43 303	62.19 270	74.07 329	90.55 191

testing222		74.04 275	72.66 279	78.19 285	87.89 196	55.36 347	81.06 303	79.20 352	71.30 186	74.65 260	83.57 314	39.11 370	88.67 300	51.43 349	85.75 177	90.53 192

PS-CasMVS		78.01 213	78.09 186	77.77 292	87.71 206	54.39 358	88.02 148	91.22 122	77.50 48	73.26 275	88.64 185	60.73 188	88.41 304	61.88 274	73.88 333	90.53 192

CDS-MVSNet		79.07 186	77.70 200	83.17 168	87.60 210	68.23 130	84.40 255	86.20 261	67.49 264	76.36 214	86.54 248	61.54 172	90.79 262	61.86 275	87.33 150	90.49 194
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		78.89 191	77.51 205	83.03 176	87.80 201	67.79 141	84.72 242	85.05 275	67.63 261	76.75 204	87.70 209	62.25 161	90.82 261	58.53 305	87.13 153	90.49 194

PEN-MVS		77.73 219	77.69 201	77.84 290	87.07 227	53.91 361	87.91 154	91.18 124	77.56 45	73.14 277	88.82 180	61.23 181	89.17 289	59.95 289	72.37 344	90.43 196

Test_1112_low_res		76.40 247	75.44 242	79.27 264	89.28 140	58.09 302	81.69 294	87.07 244	59.53 352	72.48 286	86.67 241	61.30 179	89.33 285	60.81 285	80.15 251	90.41 197

HY-MVS	69.67 12	77.95 214	77.15 211	80.36 242	87.57 214	60.21 286	83.37 274	87.78 229	66.11 281	75.37 238	87.06 231	63.27 143	90.48 267	61.38 280	82.43 224	90.40 198

CHOSEN 1792x2688		77.63 224	75.69 236	83.44 155	89.98 114	68.58 122	78.70 339	87.50 234	56.38 375	75.80 226	86.84 232	58.67 205	91.40 246	61.58 278	85.75 177	90.34 199

SDMVSNet		80.38 155	80.18 141	80.99 229	89.03 151	64.94 204	80.45 315	89.40 178	75.19 104	76.61 209	89.98 149	60.61 194	87.69 312	76.83 134	83.55 208	90.33 200

sd_testset		77.70 222	77.40 206	78.60 275	89.03 151	60.02 287	79.00 334	85.83 266	75.19 104	76.61 209	89.98 149	54.81 233	85.46 333	62.63 266	83.55 208	90.33 200

114514_t		80.68 147	79.51 153	84.20 122	94.09 38	67.27 156	89.64 87	91.11 128	58.75 360	74.08 267	90.72 137	58.10 209	95.04 92	69.70 204	89.42 121	90.30 202

eth_miper_zixun_eth		77.92 215	76.69 224	81.61 212	83.00 310	61.98 261	83.15 277	89.20 188	69.52 228	74.86 256	84.35 296	61.76 168	92.56 197	71.50 185	72.89 342	90.28 203

PVSNet_Blended_VisFu		82.62 108	81.83 117	84.96 92	90.80 94	69.76 90	88.74 123	91.70 110	69.39 229	78.96 152	88.46 191	65.47 126	94.87 100	74.42 157	88.57 134	90.24 204

MVS_111021_LR		82.61 109	82.11 109	84.11 124	88.82 156	71.58 55	85.15 232	86.16 262	74.69 117	80.47 135	91.04 129	62.29 160	90.55 266	80.33 102	90.08 111	90.20 205

MSLP-MVS++		85.43 63	85.76 57	84.45 109	91.93 75	70.24 79	90.71 59	92.86 58	77.46 49	84.22 84	92.81 84	67.16 108	92.94 186	80.36 101	94.35 57	90.16 206

mvs_tets		79.13 184	77.77 197	83.22 166	84.70 269	66.37 171	89.17 103	90.19 156	69.38 230	75.40 236	89.46 165	44.17 342	93.15 176	76.78 135	80.70 244	90.14 207

BH-RMVSNet		79.61 168	78.44 177	83.14 169	89.38 134	65.93 179	84.95 238	87.15 243	73.56 145	78.19 171	89.79 153	56.67 224	93.36 162	59.53 294	86.74 159	90.13 208

c3_l		78.75 192	77.91 190	81.26 221	82.89 314	61.56 267	84.09 261	89.13 192	69.97 217	75.56 229	84.29 297	66.36 115	92.09 216	73.47 167	75.48 310	90.12 209

v7n		78.97 189	77.58 204	83.14 169	83.45 297	65.51 189	88.32 139	91.21 123	73.69 141	72.41 287	86.32 254	57.93 210	93.81 140	69.18 209	75.65 306	90.11 210

jajsoiax		79.29 180	77.96 188	83.27 162	84.68 270	66.57 169	89.25 102	90.16 157	69.20 237	75.46 233	89.49 162	45.75 332	93.13 178	76.84 133	80.80 242	90.11 210

v148		78.72 194	77.80 195	81.47 214	82.73 317	61.96 262	86.30 205	88.08 219	73.26 155	76.18 219	85.47 272	62.46 157	92.36 206	71.92 182	73.82 334	90.09 212

GBi-Net		78.40 200	77.40 206	81.40 217	87.60 210	63.01 246	88.39 134	89.28 182	71.63 178	75.34 239	87.28 220	54.80 234	91.11 252	62.72 262	79.57 256	90.09 212

test1		78.40 200	77.40 206	81.40 217	87.60 210	63.01 246	88.39 134	89.28 182	71.63 178	75.34 239	87.28 220	54.80 234	91.11 252	62.72 262	79.57 256	90.09 212

FMVSNet1		77.44 226	76.12 233	81.40 217	86.81 231	63.01 246	88.39 134	89.28 182	70.49 205	74.39 264	87.28 220	49.06 305	91.11 252	60.91 283	78.52 267	90.09 212

WR-MVS_H		78.51 199	78.49 175	78.56 277	88.02 190	56.38 333	88.43 132	92.67 67	77.14 58	73.89 268	87.55 215	66.25 117	89.24 288	58.92 300	73.55 336	90.06 216

DTE-MVSNet		76.99 233	76.80 219	77.54 298	86.24 239	53.06 370	87.52 163	90.66 138	77.08 61	72.50 285	88.67 184	60.48 196	89.52 282	57.33 317	70.74 356	90.05 217

v8		79.97 165	79.02 167	82.80 187	84.09 282	64.50 214	87.96 150	90.29 153	74.13 133	75.24 246	86.81 233	62.88 152	93.89 138	74.39 158	75.40 315	90.00 218

thres600view7		76.50 242	75.44 242	79.68 257	89.40 132	57.16 319	85.53 227	83.23 301	73.79 139	76.26 216	87.09 229	51.89 269	91.89 223	48.05 371	83.72 205	90.00 218

thres400		76.50 242	75.37 246	79.86 252	89.13 146	57.65 313	85.17 230	83.60 293	73.41 151	76.45 211	86.39 252	52.12 261	91.95 220	48.33 366	83.75 202	90.00 218

cl22		78.07 210	77.01 213	81.23 222	82.37 326	61.83 264	83.55 271	87.98 221	68.96 245	75.06 252	83.87 304	61.40 177	91.88 224	73.53 165	76.39 295	89.98 221

OPM-MVS		83.50 93	82.95 97	85.14 85	88.79 159	70.95 69	89.13 108	91.52 114	77.55 46	80.96 131	91.75 103	60.71 189	94.50 112	79.67 108	86.51 163	89.97 222
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		75.70 256	73.83 267	81.30 220	83.26 301	61.79 265	82.57 286	80.65 334	66.81 268	66.88 344	83.42 316	57.86 212	92.19 213	63.47 256	79.57 256	89.91 223

v10		79.74 167	78.67 171	82.97 180	84.06 283	64.95 203	87.88 156	90.62 139	73.11 158	75.11 250	86.56 247	61.46 175	94.05 127	73.68 163	75.55 308	89.90 224

MVSTER		79.01 187	77.88 192	82.38 198	83.07 307	64.80 208	84.08 262	88.95 200	69.01 244	78.69 157	87.17 227	54.70 238	92.43 202	74.69 154	80.57 246	89.89 225

ACMP	74.13 6	81.51 130	80.57 132	84.36 112	89.42 130	68.69 119	89.97 77	91.50 118	74.46 123	75.04 253	90.41 142	53.82 246	94.54 109	77.56 124	82.91 217	89.86 226
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LPG-MVS_test		82.08 115	81.27 121	84.50 106	89.23 142	68.76 112	90.22 73	91.94 99	75.37 100	76.64 207	91.51 112	54.29 241	94.91 95	78.44 115	83.78 199	89.83 227

LGP-MVS_train				84.50 106	89.23 142	68.76 112		91.94 99	75.37 100	76.64 207	91.51 112	54.29 241	94.91 95	78.44 115	83.78 199	89.83 227

V42		79.38 179	78.24 183	82.83 184	81.10 345	65.50 190	85.55 225	89.82 165	71.57 182	78.21 170	86.12 258	60.66 192	93.18 175	75.64 145	75.46 312	89.81 229

MAR-MVS		81.84 120	80.70 130	85.27 82	91.32 82	71.53 56	89.82 79	90.92 131	69.77 223	78.50 163	86.21 255	62.36 159	94.52 111	65.36 243	92.05 82	89.77 230
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		77.72 220	76.76 221	80.58 238	82.48 324	60.48 281	83.09 279	87.86 226	69.22 235	74.38 265	85.24 276	62.10 164	91.53 239	71.09 188	75.40 315	89.74 231

cl____		77.72 220	76.76 221	80.58 238	82.49 323	60.48 281	83.09 279	87.87 225	69.22 235	74.38 265	85.22 278	62.10 164	91.53 239	71.09 188	75.41 314	89.73 232

miper_ehance_all_eth		78.59 198	77.76 198	81.08 227	82.66 319	61.56 267	83.65 267	89.15 190	68.87 246	75.55 230	83.79 308	66.49 113	92.03 217	73.25 170	76.39 295	89.64 233

anonymousdsp		78.60 197	77.15 211	82.98 179	80.51 351	67.08 161	87.24 174	89.53 175	65.66 288	75.16 248	87.19 226	52.52 254	92.25 211	77.17 129	79.34 261	89.61 234

FMVSNet2		78.20 206	77.21 210	81.20 223	87.60 210	62.89 252	87.47 165	89.02 195	71.63 178	75.29 245	87.28 220	54.80 234	91.10 255	62.38 267	79.38 260	89.61 234

baseline1		76.98 234	76.75 223	77.66 293	88.13 184	55.66 344	85.12 233	81.89 321	73.04 160	76.79 202	88.90 177	62.43 158	87.78 311	63.30 259	71.18 354	89.55 236

ETVMVS		72.25 298	71.05 297	75.84 311	87.77 205	51.91 374	79.39 327	74.98 376	69.26 233	73.71 270	82.95 324	40.82 363	86.14 324	46.17 379	84.43 192	89.47 237

FMVSNet3		77.88 216	76.85 218	80.97 231	86.84 230	62.36 255	86.52 198	88.77 204	71.13 189	75.34 239	86.66 242	54.07 244	91.10 255	62.72 262	79.57 256	89.45 238

miper_enhance_ethall		77.87 217	76.86 217	80.92 232	81.65 333	61.38 269	82.68 284	88.98 197	65.52 290	75.47 231	82.30 335	65.76 125	92.00 219	72.95 173	76.39 295	89.39 239

testing11		75.14 266	74.01 262	78.53 279	88.16 181	56.38 333	80.74 309	80.42 339	70.67 199	72.69 284	83.72 311	43.61 346	89.86 275	62.29 269	83.76 201	89.36 240

cascas		76.72 239	74.64 253	82.99 178	85.78 248	65.88 181	82.33 287	89.21 187	60.85 341	72.74 281	81.02 346	47.28 314	93.75 145	67.48 225	85.02 180	89.34 241

Fast-Effi-MVS+-dtu		78.02 212	76.49 227	82.62 194	83.16 306	66.96 165	86.94 183	87.45 236	72.45 166	71.49 299	84.17 301	54.79 237	91.58 234	67.61 223	80.31 249	89.30 242

IB-MVS	68.01 15	75.85 255	73.36 271	83.31 160	84.76 268	66.03 175	83.38 273	85.06 274	70.21 212	69.40 321	81.05 345	45.76 331	94.66 108	65.10 246	75.49 309	89.25 243
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		76.50 242	75.55 241	79.33 263	89.52 125	56.99 322	85.83 219	83.23 301	73.94 135	76.32 215	87.12 228	51.89 269	91.95 220	48.33 366	83.75 202	89.07 244

tfpn200view9		76.42 246	75.37 246	79.55 262	89.13 146	57.65 313	85.17 230	83.60 293	73.41 151	76.45 211	86.39 252	52.12 261	91.95 220	48.33 366	83.75 202	89.07 244

xiu_mvs_v1_base_debu		80.80 143	79.72 149	84.03 138	87.35 215	70.19 82	85.56 222	88.77 204	69.06 241	81.83 116	88.16 200	50.91 280	92.85 188	78.29 119	87.56 146	89.06 246

xiu_mvs_v1_base		80.80 143	79.72 149	84.03 138	87.35 215	70.19 82	85.56 222	88.77 204	69.06 241	81.83 116	88.16 200	50.91 280	92.85 188	78.29 119	87.56 146	89.06 246

xiu_mvs_v1_base_debi		80.80 143	79.72 149	84.03 138	87.35 215	70.19 82	85.56 222	88.77 204	69.06 241	81.83 116	88.16 200	50.91 280	92.85 188	78.29 119	87.56 146	89.06 246

EPNet_dtu		75.46 260	74.86 251	77.23 302	82.57 321	54.60 355	86.89 185	83.09 305	71.64 177	66.25 355	85.86 262	55.99 227	88.04 308	54.92 331	86.55 162	89.05 249
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pm-mvs1		77.25 231	76.68 225	78.93 270	84.22 279	58.62 297	86.41 200	88.36 215	71.37 185	73.31 274	88.01 206	61.22 182	89.15 290	64.24 253	73.01 341	89.03 250

PVSNet_Blended		80.98 136	80.34 137	82.90 182	88.85 153	65.40 191	84.43 253	92.00 95	67.62 262	78.11 173	85.05 283	66.02 121	94.27 118	71.52 183	89.50 119	89.01 251

PAPM		77.68 223	76.40 230	81.51 213	87.29 222	61.85 263	83.78 264	89.59 173	64.74 299	71.23 300	88.70 182	62.59 154	93.66 148	52.66 342	87.03 155	89.01 251

WTY-MVS		75.65 257	75.68 237	75.57 315	86.40 238	56.82 324	77.92 351	82.40 316	65.10 294	76.18 219	87.72 208	63.13 150	80.90 363	60.31 287	81.96 229	89.00 253

无先验							87.48 164	88.98 197	60.00 347				94.12 125	67.28 227		88.97 254

GSMVS																88.96 255

sam_mvs1												51.32 276				88.96 255

SCA		74.22 272	72.33 283	79.91 251	84.05 284	62.17 259	79.96 322	79.29 351	66.30 280	72.38 288	80.13 356	51.95 267	88.60 301	59.25 296	77.67 279	88.96 255

miper_lstm_enhance		74.11 274	73.11 274	77.13 303	80.11 355	59.62 291	72.23 379	86.92 249	66.76 270	70.40 306	82.92 325	56.93 222	82.92 352	69.06 211	72.63 343	88.87 258

ACMM	73.20 8	80.78 146	79.84 147	83.58 152	89.31 138	68.37 126	89.99 76	91.60 112	70.28 209	77.25 190	89.66 156	53.37 251	93.53 154	74.24 160	82.85 218	88.85 259
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		74.69 268	73.39 270	78.61 274	81.38 340	57.48 316	86.64 194	87.95 223	64.99 298	70.18 309	86.61 243	50.43 287	89.52 282	62.12 272	70.18 359	88.83 260

原ACMM1				84.35 113	93.01 60	68.79 110		92.44 77	63.96 313	81.09 129	91.57 111	66.06 120	95.45 68	67.19 229	94.82 46	88.81 261

CNLPA		78.08 209	76.79 220	81.97 205	90.40 102	71.07 65	87.59 162	84.55 280	66.03 284	72.38 288	89.64 157	57.56 215	86.04 325	59.61 293	83.35 212	88.79 262

UWE-MVS		72.13 299	71.49 290	74.03 334	86.66 235	47.70 393	81.40 300	76.89 369	63.60 315	75.59 228	84.22 300	39.94 366	85.62 330	48.98 363	86.13 170	88.77 263

UBG		73.08 289	72.27 284	75.51 317	88.02 190	51.29 382	78.35 346	77.38 364	65.52 290	73.87 269	82.36 333	45.55 333	86.48 321	55.02 330	84.39 193	88.75 264

K. test v3		71.19 304	68.51 316	79.21 266	83.04 309	57.78 312	84.35 256	76.91 368	72.90 163	62.99 374	82.86 327	39.27 368	91.09 257	61.65 277	52.66 400	88.75 264

旧先验1					91.96 74	65.79 184		86.37 258			93.08 77	69.31 84			92.74 73	88.74 266

PatchmatchNet		73.12 288	71.33 294	78.49 281	83.18 304	60.85 275	79.63 324	78.57 355	64.13 306	71.73 295	79.81 361	51.20 278	85.97 326	57.40 316	76.36 300	88.66 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SixPastTwentyTwo		73.37 283	71.26 296	79.70 256	85.08 264	57.89 308	85.57 221	83.56 295	71.03 193	65.66 357	85.88 261	42.10 356	92.57 196	59.11 298	63.34 381	88.65 268

PS-MVSNAJ		81.69 124	81.02 126	83.70 149	89.51 126	68.21 131	84.28 257	90.09 159	70.79 196	81.26 128	85.62 269	63.15 147	94.29 116	75.62 146	88.87 128	88.59 269

xiu_mvs_v2_base		81.69 124	81.05 125	83.60 151	89.15 145	68.03 136	84.46 251	90.02 160	70.67 199	81.30 127	86.53 249	63.17 146	94.19 123	75.60 147	88.54 135	88.57 270

MonoMVSNet		76.49 245	75.80 234	78.58 276	81.55 336	58.45 298	86.36 203	86.22 260	74.87 114	74.73 258	83.73 310	51.79 272	88.73 298	70.78 190	72.15 347	88.55 271

CostFormer		75.24 265	73.90 265	79.27 264	82.65 320	58.27 301	80.80 305	82.73 314	61.57 336	75.33 243	83.13 321	55.52 229	91.07 258	64.98 247	78.34 272	88.45 272

lessismore_v0				78.97 269	81.01 346	57.15 320		65.99 403		61.16 380	82.82 328	39.12 369	91.34 248	59.67 292	46.92 407	88.43 273

OpenMVS	72.83 10	79.77 166	78.33 181	84.09 129	85.17 259	69.91 87	90.57 61	90.97 130	66.70 271	72.17 291	91.91 98	54.70 238	93.96 128	61.81 276	90.95 98	88.41 274

reproduce_monomvs		75.40 263	74.38 259	78.46 282	83.92 287	57.80 311	83.78 264	86.94 247	73.47 149	72.25 290	84.47 291	38.74 371	89.27 287	75.32 151	70.53 357	88.31 275

OurMVSNet-221017-0		74.26 271	72.42 282	79.80 254	83.76 291	59.59 292	85.92 215	86.64 252	66.39 279	66.96 343	87.58 212	39.46 367	91.60 233	65.76 241	69.27 362	88.22 276

LS3D		76.95 235	74.82 252	83.37 159	90.45 100	67.36 153	89.15 107	86.94 247	61.87 335	69.52 320	90.61 139	51.71 273	94.53 110	46.38 378	86.71 160	88.21 277

WBMVS		73.43 282	72.81 277	75.28 321	87.91 195	50.99 384	78.59 342	81.31 329	65.51 292	74.47 263	84.83 286	46.39 320	86.68 318	58.41 306	77.86 275	88.17 278

XVG-ACMP-BASELINE		76.11 251	74.27 261	81.62 210	83.20 303	64.67 210	83.60 270	89.75 168	69.75 224	71.85 294	87.09 229	32.78 388	92.11 215	69.99 201	80.43 248	88.09 279

tpm2		73.26 286	71.46 291	78.63 273	83.34 299	56.71 327	80.65 311	80.40 340	56.63 374	73.55 272	82.02 340	51.80 271	91.24 250	56.35 326	78.42 270	87.95 280

MDTV_nov1_ep13_2view						37.79 416	75.16 367		55.10 379	66.53 350		49.34 300		53.98 335		87.94 281

Patchmatch-test		64.82 353	63.24 354	69.57 364	79.42 367	49.82 390	63.49 410	69.05 396	51.98 389	59.95 385	80.13 356	50.91 280	70.98 404	40.66 395	73.57 335	87.90 282

PLC	70.83 11	78.05 211	76.37 231	83.08 173	91.88 77	67.80 140	88.19 143	89.46 177	64.33 305	69.87 317	88.38 193	53.66 247	93.58 149	58.86 301	82.73 220	87.86 283
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		72.37 296	71.71 288	74.35 331	82.19 327	52.00 372	79.22 330	77.29 365	64.56 301	72.95 280	83.68 313	51.35 275	83.26 351	58.33 308	75.80 304	87.81 284

Patchmatch-RL test		70.24 316	67.78 329	77.61 295	77.43 375	59.57 293	71.16 383	70.33 390	62.94 322	68.65 328	72.77 395	50.62 284	85.49 332	69.58 206	66.58 372	87.77 285

F-COLMAP		76.38 248	74.33 260	82.50 196	89.28 140	66.95 166	88.41 133	89.03 194	64.05 310	66.83 345	88.61 186	46.78 318	92.89 187	57.48 314	78.55 266	87.67 286

Baseline_NR-MVSNet		78.15 208	78.33 181	77.61 295	85.79 247	56.21 337	86.78 190	85.76 267	73.60 144	77.93 178	87.57 213	65.02 130	88.99 292	67.14 230	75.33 317	87.63 287

CL-MVSNet_self_test		72.37 296	71.46 291	75.09 323	79.49 366	53.53 363	80.76 308	85.01 276	69.12 239	70.51 304	82.05 339	57.92 211	84.13 343	52.27 344	66.00 375	87.60 288

ACMH+	68.96 14	76.01 253	74.01 262	82.03 203	88.60 166	65.31 195	88.86 117	87.55 232	70.25 211	67.75 334	87.47 218	41.27 359	93.19 174	58.37 307	75.94 303	87.60 288

1314		76.53 241	75.30 248	80.21 246	83.93 286	62.32 257	84.66 243	88.81 202	60.23 345	70.16 311	84.07 303	55.30 231	90.73 264	67.37 226	83.21 214	87.59 290

API-MVS		81.99 118	81.23 122	84.26 121	90.94 90	70.18 85	91.10 55	89.32 181	71.51 183	78.66 159	88.28 196	65.26 127	95.10 90	64.74 249	91.23 95	87.51 291

AdaColmap		80.58 152	79.42 155	84.06 133	93.09 57	68.91 108	89.36 99	88.97 199	69.27 232	75.70 227	89.69 155	57.20 220	95.77 59	63.06 260	88.41 138	87.50 292

PVSNet_BlendedMVS		80.60 149	80.02 142	82.36 199	88.85 153	65.40 191	86.16 209	92.00 95	69.34 231	78.11 173	86.09 259	66.02 121	94.27 118	71.52 183	82.06 228	87.39 293

sss		73.60 280	73.64 269	73.51 338	82.80 315	55.01 352	76.12 358	81.69 324	62.47 329	74.68 259	85.85 263	57.32 218	78.11 374	60.86 284	80.93 239	87.39 293

IterMVS-SCA-FT		75.43 261	73.87 266	80.11 248	82.69 318	64.85 207	81.57 296	83.47 297	69.16 238	70.49 305	84.15 302	51.95 267	88.15 306	69.23 208	72.14 348	87.34 295

PVSNet	64.34 18	72.08 300	70.87 300	75.69 313	86.21 240	56.44 331	74.37 373	80.73 333	62.06 334	70.17 310	82.23 337	42.86 350	83.31 350	54.77 332	84.45 191	87.32 296

新几何1				83.42 156	93.13 54	70.71 74		85.48 270	57.43 370	81.80 119	91.98 97	63.28 142	92.27 210	64.60 250	92.99 70	87.27 297

TR-MVS		77.44 226	76.18 232	81.20 223	88.24 179	63.24 241	84.61 246	86.40 257	67.55 263	77.81 179	86.48 250	54.10 243	93.15 176	57.75 313	82.72 221	87.20 298

TransMVSNet (Re)		75.39 264	74.56 255	77.86 289	85.50 254	57.10 321	86.78 190	86.09 264	72.17 172	71.53 298	87.34 219	63.01 151	89.31 286	56.84 322	61.83 383	87.17 299

ACMH	67.68 16	75.89 254	73.93 264	81.77 208	88.71 163	66.61 168	88.62 128	89.01 196	69.81 220	66.78 346	86.70 240	41.95 358	91.51 241	55.64 328	78.14 273	87.17 299
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
KD-MVS_self_test		68.81 327	67.59 333	72.46 348	74.29 388	45.45 399	77.93 350	87.00 245	63.12 317	63.99 369	78.99 369	42.32 353	84.77 340	56.55 325	64.09 380	87.16 301

EPMVS		69.02 326	68.16 320	71.59 352	79.61 364	49.80 391	77.40 353	66.93 401	62.82 325	70.01 312	79.05 365	45.79 330	77.86 376	56.58 324	75.26 319	87.13 302

CR-MVSNet		73.37 283	71.27 295	79.67 258	81.32 343	65.19 197	75.92 360	80.30 341	59.92 348	72.73 282	81.19 343	52.50 255	86.69 317	59.84 290	77.71 277	87.11 303

RPMNet		73.51 281	70.49 303	82.58 195	81.32 343	65.19 197	75.92 360	92.27 84	57.60 368	72.73 282	76.45 383	52.30 258	95.43 70	48.14 370	77.71 277	87.11 303

test_vis1_n_1920		75.52 259	75.78 235	74.75 328	79.84 359	57.44 317	83.26 275	85.52 269	62.83 324	79.34 149	86.17 257	45.10 337	79.71 367	78.75 112	81.21 237	87.10 305

XXY-MVS		75.41 262	75.56 240	74.96 324	83.59 294	57.82 310	80.59 312	83.87 291	66.54 278	74.93 255	88.31 195	63.24 144	80.09 366	62.16 271	76.85 288	86.97 306

tpmrst		72.39 294	72.13 285	73.18 342	80.54 350	49.91 389	79.91 323	79.08 353	63.11 318	71.69 296	79.95 358	55.32 230	82.77 353	65.66 242	73.89 332	86.87 307

thres200		75.55 258	74.47 257	78.82 271	87.78 204	57.85 309	83.07 281	83.51 296	72.44 168	75.84 225	84.42 292	52.08 264	91.75 228	47.41 373	83.64 207	86.86 308

ITE_SJBPF				78.22 284	81.77 332	60.57 279		83.30 299	69.25 234	67.54 336	87.20 225	36.33 381	87.28 315	54.34 334	74.62 326	86.80 309

test222					91.50 80	68.26 129	84.16 259	83.20 304	54.63 381	79.74 142	91.63 108	58.97 204			91.42 92	86.77 310

MIMVSNet		70.69 311	69.30 310	74.88 325	84.52 274	56.35 335	75.87 362	79.42 349	64.59 300	67.76 333	82.41 332	41.10 360	81.54 359	46.64 377	81.34 234	86.75 311

BH-untuned		79.47 173	78.60 173	82.05 202	89.19 144	65.91 180	86.07 211	88.52 213	72.18 171	75.42 235	87.69 210	61.15 183	93.54 153	60.38 286	86.83 158	86.70 312

LTVRE_ROB	69.57 13	76.25 249	74.54 256	81.41 216	88.60 166	64.38 218	79.24 329	89.12 193	70.76 198	69.79 319	87.86 207	49.09 304	93.20 172	56.21 327	80.16 250	86.65 313
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				79.97 250	90.90 91	64.21 220		84.71 277	59.27 354	85.40 61	92.91 79	62.02 166	89.08 291	68.95 212	91.37 93	86.63 314

MIMVSNet1		68.58 330	66.78 340	73.98 335	80.07 356	51.82 376	80.77 307	84.37 281	64.40 303	59.75 386	82.16 338	36.47 380	83.63 347	42.73 390	70.33 358	86.48 315

tfpnnormal		74.39 269	73.16 273	78.08 287	86.10 245	58.05 303	84.65 245	87.53 233	70.32 208	71.22 301	85.63 268	54.97 232	89.86 275	43.03 389	75.02 322	86.32 316

D2MVS		74.82 267	73.21 272	79.64 259	79.81 360	62.56 254	80.34 317	87.35 237	64.37 304	68.86 326	82.66 330	46.37 322	90.10 271	67.91 221	81.24 236	86.25 317

tpm cat1		70.57 312	68.31 318	77.35 300	82.41 325	57.95 307	78.08 348	80.22 343	52.04 387	68.54 330	77.66 378	52.00 266	87.84 310	51.77 345	72.07 349	86.25 317

CVMVSNet		72.99 291	72.58 280	74.25 332	84.28 277	50.85 385	86.41 200	83.45 298	44.56 400	73.23 276	87.54 216	49.38 299	85.70 328	65.90 239	78.44 269	86.19 319

AllTest		70.96 307	68.09 322	79.58 260	85.15 261	63.62 229	84.58 247	79.83 345	62.31 330	60.32 383	86.73 234	32.02 389	88.96 295	50.28 355	71.57 352	86.15 320

TestCases				79.58 260	85.15 261	63.62 229		79.83 345	62.31 330	60.32 383	86.73 234	32.02 389	88.96 295	50.28 355	71.57 352	86.15 320

test-LLR		72.94 292	72.43 281	74.48 329	81.35 341	58.04 304	78.38 343	77.46 361	66.66 272	69.95 315	79.00 367	48.06 310	79.24 368	66.13 235	84.83 182	86.15 320

test-mter		71.41 303	70.39 306	74.48 329	81.35 341	58.04 304	78.38 343	77.46 361	60.32 344	69.95 315	79.00 367	36.08 382	79.24 368	66.13 235	84.83 182	86.15 320

IterMVS		74.29 270	72.94 276	78.35 283	81.53 337	63.49 235	81.58 295	82.49 315	68.06 259	69.99 314	83.69 312	51.66 274	85.54 331	65.85 240	71.64 351	86.01 324
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		76.78 238	74.57 254	83.42 156	93.29 48	69.46 97	88.55 130	83.70 292	63.98 312	70.20 308	88.89 178	54.01 245	94.80 102	46.66 375	81.88 231	86.01 324

ppachtmachnet_test		70.04 318	67.34 336	78.14 286	79.80 361	61.13 270	79.19 331	80.59 335	59.16 355	65.27 360	79.29 364	46.75 319	87.29 314	49.33 361	66.72 370	86.00 326

mmtdpeth		74.16 273	73.01 275	77.60 297	83.72 292	61.13 270	85.10 234	85.10 273	72.06 174	77.21 196	80.33 354	43.84 344	85.75 327	77.14 130	52.61 401	85.91 327

test_fmvs1_n		70.86 309	70.24 307	72.73 345	72.51 402	55.28 349	81.27 301	79.71 347	51.49 391	78.73 156	84.87 285	27.54 398	77.02 379	76.06 140	79.97 254	85.88 328

Patchmtry		70.74 310	69.16 313	75.49 318	80.72 347	54.07 360	74.94 371	80.30 341	58.34 361	70.01 312	81.19 343	52.50 255	86.54 319	53.37 339	71.09 355	85.87 329

WB-MVSnew		71.96 301	71.65 289	72.89 343	84.67 273	51.88 375	82.29 288	77.57 360	62.31 330	73.67 271	83.00 323	53.49 250	81.10 362	45.75 382	82.13 227	85.70 330

test_fmvs2		68.35 334	67.48 334	70.98 360	69.50 405	51.95 373	80.05 320	76.38 371	49.33 394	74.65 260	84.38 294	23.30 407	75.40 395	74.51 156	75.17 321	85.60 331

ambc				75.24 322	73.16 397	50.51 387	63.05 411	87.47 235		64.28 366	77.81 377	17.80 413	89.73 279	57.88 312	60.64 387	85.49 332

mvs5depth		69.45 323	67.45 335	75.46 319	73.93 389	55.83 341	79.19 331	83.23 301	66.89 267	71.63 297	83.32 317	33.69 387	85.09 336	59.81 291	55.34 397	85.46 333

UnsupCasMVSNet_eth		67.33 339	65.99 343	71.37 354	73.48 394	51.47 380	75.16 367	85.19 272	65.20 293	60.78 381	80.93 350	42.35 352	77.20 378	57.12 318	53.69 399	85.44 334

PatchT		68.46 333	67.85 325	70.29 362	80.70 348	43.93 406	72.47 378	74.88 377	60.15 346	70.55 303	76.57 382	49.94 292	81.59 358	50.58 351	74.83 324	85.34 335

Anonymous20240521		68.80 328	67.22 337	73.55 337	74.33 387	54.11 359	83.18 276	85.61 268	58.15 363	61.68 378	80.94 348	30.71 394	81.27 361	57.00 320	73.34 340	85.28 336

test_cas_vis1_n_1920		73.76 279	73.74 268	73.81 336	75.90 380	59.77 289	80.51 313	82.40 316	58.30 362	81.62 122	85.69 265	44.35 341	76.41 385	76.29 137	78.61 265	85.23 337

ADS-MVSNet2		66.20 350	63.33 353	74.82 326	79.92 357	58.75 296	67.55 398	75.19 375	53.37 384	65.25 361	75.86 386	42.32 353	80.53 365	41.57 393	68.91 364	85.18 338

ADS-MVSNet		64.36 354	62.88 357	68.78 370	79.92 357	47.17 395	67.55 398	71.18 389	53.37 384	65.25 361	75.86 386	42.32 353	73.99 400	41.57 393	68.91 364	85.18 338

FMVSNet5		69.50 322	67.96 323	74.15 333	82.97 313	55.35 348	80.01 321	82.12 319	62.56 328	63.02 372	81.53 342	36.92 379	81.92 357	48.42 365	74.06 330	85.17 340

pmmvs5		71.55 302	70.20 308	75.61 314	77.83 373	56.39 332	81.74 293	80.89 330	57.76 366	67.46 338	84.49 290	49.26 302	85.32 335	57.08 319	75.29 318	85.11 341

testing3		68.56 331	67.67 331	71.22 358	87.33 220	42.87 408	83.06 282	71.54 388	70.36 206	69.08 325	84.38 294	30.33 395	85.69 329	37.50 401	75.45 313	85.09 342

CMPMVS	51.72 21	70.19 317	68.16 320	76.28 308	73.15 398	57.55 315	79.47 326	83.92 289	48.02 396	56.48 396	84.81 287	43.13 348	86.42 322	62.67 265	81.81 232	84.89 343
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testgi		66.67 344	66.53 341	67.08 378	75.62 383	41.69 413	75.93 359	76.50 370	66.11 281	65.20 363	86.59 244	35.72 383	74.71 397	43.71 387	73.38 339	84.84 344

MSDG		73.36 285	70.99 298	80.49 240	84.51 275	65.80 183	80.71 310	86.13 263	65.70 287	65.46 358	83.74 309	44.60 338	90.91 260	51.13 350	76.89 286	84.74 345

pmmvs4		74.03 277	71.91 286	80.39 241	81.96 329	68.32 127	81.45 298	82.14 318	59.32 353	69.87 317	85.13 280	52.40 257	88.13 307	60.21 288	74.74 325	84.73 346

gg-mvs-nofinetune		69.95 319	67.96 323	75.94 310	83.07 307	54.51 357	77.23 355	70.29 391	63.11 318	70.32 307	62.33 404	43.62 345	88.69 299	53.88 336	87.76 145	84.62 347

test_fmvs1		70.93 308	70.52 302	72.16 349	73.71 391	55.05 351	80.82 304	78.77 354	51.21 392	78.58 161	84.41 293	31.20 393	76.94 380	75.88 143	80.12 253	84.47 348

BH-w/o		78.21 205	77.33 209	80.84 233	88.81 157	65.13 199	84.87 239	87.85 227	69.75 224	74.52 262	84.74 289	61.34 178	93.11 179	58.24 309	85.84 175	84.27 349

MVS		78.19 207	76.99 215	81.78 207	85.66 249	66.99 162	84.66 243	90.47 144	55.08 380	72.02 293	85.27 275	63.83 139	94.11 126	66.10 237	89.80 116	84.24 350

COLMAP_ROB	66.92 17	73.01 290	70.41 305	80.81 234	87.13 225	65.63 187	88.30 140	84.19 287	62.96 321	63.80 371	87.69 210	38.04 376	92.56 197	46.66 375	74.91 323	84.24 350
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
new-patchmatchnet		61.73 360	61.73 361	61.70 384	72.74 400	24.50 427	69.16 393	78.03 357	61.40 337	56.72 395	75.53 389	38.42 373	76.48 384	45.95 381	57.67 390	84.13 352

TESTMET0.1,1		69.89 320	69.00 314	72.55 346	79.27 369	56.85 323	78.38 343	74.71 380	57.64 367	68.09 332	77.19 380	37.75 377	76.70 381	63.92 254	84.09 197	84.10 353

test_fmvs3		63.36 357	61.82 360	67.98 375	62.51 414	46.96 397	77.37 354	74.03 382	45.24 399	67.50 337	78.79 370	12.16 419	72.98 403	72.77 176	66.02 374	83.99 354

our_test_3		69.14 325	67.00 338	75.57 315	79.80 361	58.80 295	77.96 349	77.81 358	59.55 351	62.90 375	78.25 374	47.43 312	83.97 344	51.71 346	67.58 369	83.93 355

test_vis1_n		69.85 321	69.21 312	71.77 351	72.66 401	55.27 350	81.48 297	76.21 372	52.03 388	75.30 244	83.20 320	28.97 396	76.22 387	74.60 155	78.41 271	83.81 356

mamv4		76.81 237	78.23 185	72.54 347	86.12 243	65.75 186	78.76 338	82.07 320	64.12 307	72.97 279	91.02 132	67.97 98	68.08 411	83.04 74	78.02 274	83.80 357

tpmvs		71.09 306	69.29 311	76.49 307	82.04 328	56.04 338	78.92 336	81.37 328	64.05 310	67.18 342	78.28 373	49.74 295	89.77 277	49.67 360	72.37 344	83.67 358

test20.03		67.45 338	66.95 339	68.94 367	75.48 384	44.84 404	77.50 352	77.67 359	66.66 272	63.01 373	83.80 307	47.02 316	78.40 372	42.53 392	68.86 366	83.58 359

test0.0.03 1		68.00 336	67.69 330	68.90 368	77.55 374	47.43 394	75.70 363	72.95 387	66.66 272	66.56 349	82.29 336	48.06 310	75.87 390	44.97 386	74.51 327	83.41 360

Anonymous20231206		68.60 329	67.80 328	71.02 359	80.23 354	50.75 386	78.30 347	80.47 337	56.79 373	66.11 356	82.63 331	46.35 323	78.95 370	43.62 388	75.70 305	83.36 361

EU-MVSNet		68.53 332	67.61 332	71.31 357	78.51 372	47.01 396	84.47 249	84.27 285	42.27 403	66.44 354	84.79 288	40.44 364	83.76 345	58.76 303	68.54 367	83.17 362

dp		66.80 342	65.43 344	70.90 361	79.74 363	48.82 392	75.12 369	74.77 378	59.61 350	64.08 368	77.23 379	42.89 349	80.72 364	48.86 364	66.58 372	83.16 363

pmmvs-eth3d		70.50 314	67.83 327	78.52 280	77.37 376	66.18 174	81.82 291	81.51 325	58.90 358	63.90 370	80.42 353	42.69 351	86.28 323	58.56 304	65.30 377	83.11 364

YYNet1		65.03 351	62.91 356	71.38 353	75.85 381	56.60 329	69.12 394	74.66 381	57.28 371	54.12 399	77.87 376	45.85 329	74.48 398	49.95 358	61.52 385	83.05 365

MDA-MVSNet-bldmvs		66.68 343	63.66 352	75.75 312	79.28 368	60.56 280	73.92 375	78.35 356	64.43 302	50.13 405	79.87 360	44.02 343	83.67 346	46.10 380	56.86 391	83.03 366

MDA-MVSNet_test_wron		65.03 351	62.92 355	71.37 354	75.93 379	56.73 325	69.09 395	74.73 379	57.28 371	54.03 400	77.89 375	45.88 328	74.39 399	49.89 359	61.55 384	82.99 367

USDC		70.33 315	68.37 317	76.21 309	80.60 349	56.23 336	79.19 331	86.49 255	60.89 340	61.29 379	85.47 272	31.78 391	89.47 284	53.37 339	76.21 301	82.94 368

Syy-MVS		68.05 335	67.85 325	68.67 371	84.68 270	40.97 414	78.62 340	73.08 385	66.65 275	66.74 347	79.46 362	52.11 263	82.30 355	32.89 406	76.38 298	82.75 369

myMVS_eth3d		67.02 341	66.29 342	69.21 366	84.68 270	42.58 409	78.62 340	73.08 385	66.65 275	66.74 347	79.46 362	31.53 392	82.30 355	39.43 398	76.38 298	82.75 369

ttmdpeth		59.91 363	57.10 367	68.34 373	67.13 409	46.65 398	74.64 372	67.41 400	48.30 395	62.52 377	85.04 284	20.40 409	75.93 389	42.55 391	45.90 410	82.44 371

OpenMVS_ROB	64.09 19	70.56 313	68.19 319	77.65 294	80.26 352	59.41 294	85.01 236	82.96 310	58.76 359	65.43 359	82.33 334	37.63 378	91.23 251	45.34 385	76.03 302	82.32 372

JIA-IIPM		66.32 347	62.82 358	76.82 305	77.09 377	61.72 266	65.34 406	75.38 374	58.04 365	64.51 365	62.32 405	42.05 357	86.51 320	51.45 348	69.22 363	82.21 373

dmvs_re		71.14 305	70.58 301	72.80 344	81.96 329	59.68 290	75.60 364	79.34 350	68.55 251	69.27 324	80.72 351	49.42 298	76.54 382	52.56 343	77.79 276	82.19 374

EG-PatchMatch MVS		74.04 275	71.82 287	80.71 236	84.92 266	67.42 150	85.86 217	88.08 219	66.04 283	64.22 367	83.85 305	35.10 384	92.56 197	57.44 315	80.83 241	82.16 375

MVP-Stereo		76.12 250	74.46 258	81.13 226	85.37 257	69.79 89	84.42 254	87.95 223	65.03 296	67.46 338	85.33 274	53.28 252	91.73 230	58.01 311	83.27 213	81.85 376
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TDRefinement		67.49 337	64.34 347	76.92 304	73.47 395	61.07 272	84.86 240	82.98 309	59.77 349	58.30 390	85.13 280	26.06 399	87.89 309	47.92 372	60.59 388	81.81 377

GG-mvs-BLEND				75.38 320	81.59 335	55.80 342	79.32 328	69.63 393		67.19 341	73.67 393	43.24 347	88.90 297	50.41 352	84.50 187	81.45 378

KD-MVS_2432*1600		66.22 348	63.89 350	73.21 339	75.47 385	53.42 365	70.76 386	84.35 282	64.10 308	66.52 351	78.52 371	34.55 385	84.98 337	50.40 353	50.33 404	81.23 379

miper_refine_blended		66.22 348	63.89 350	73.21 339	75.47 385	53.42 365	70.76 386	84.35 282	64.10 308	66.52 351	78.52 371	34.55 385	84.98 337	50.40 353	50.33 404	81.23 379

test_0402		72.79 293	70.44 304	79.84 253	88.13 184	65.99 178	85.93 214	84.29 284	65.57 289	67.40 340	85.49 271	46.92 317	92.61 193	35.88 403	74.38 328	80.94 381

MVStest1		56.63 367	52.76 373	68.25 374	61.67 415	53.25 369	71.67 381	68.90 398	38.59 408	50.59 404	83.05 322	25.08 401	70.66 405	36.76 402	38.56 411	80.83 382

UnsupCasMVSNet_bld		63.70 356	61.53 362	70.21 363	73.69 392	51.39 381	72.82 377	81.89 321	55.63 378	57.81 392	71.80 397	38.67 372	78.61 371	49.26 362	52.21 402	80.63 383

LCM-MVSNet		54.25 369	49.68 379	67.97 376	53.73 423	45.28 402	66.85 401	80.78 332	35.96 412	39.45 413	62.23 406	8.70 423	78.06 375	48.24 369	51.20 403	80.57 384

N_pmnet		52.79 374	53.26 372	51.40 398	78.99 370	7.68 432	69.52 390	3.89 431	51.63 390	57.01 394	74.98 390	40.83 362	65.96 413	37.78 400	64.67 378	80.56 385

TinyColmap		67.30 340	64.81 345	74.76 327	81.92 331	56.68 328	80.29 318	81.49 326	60.33 343	56.27 397	83.22 318	24.77 403	87.66 313	45.52 383	69.47 361	79.95 386

PM-MVS		66.41 346	64.14 348	73.20 341	73.92 390	56.45 330	78.97 335	64.96 407	63.88 314	64.72 364	80.24 355	19.84 411	83.44 349	66.24 234	64.52 379	79.71 387

ANet_high		50.57 378	46.10 382	63.99 381	48.67 426	39.13 415	70.99 385	80.85 331	61.39 338	31.18 415	57.70 411	17.02 414	73.65 402	31.22 408	15.89 423	79.18 388

LF4IMVS		64.02 355	62.19 359	69.50 365	70.90 403	53.29 368	76.13 357	77.18 366	52.65 386	58.59 388	80.98 347	23.55 406	76.52 383	53.06 341	66.66 371	78.68 389

PatchMatch-RL		72.38 295	70.90 299	76.80 306	88.60 166	67.38 152	79.53 325	76.17 373	62.75 326	69.36 322	82.00 341	45.51 334	84.89 339	53.62 337	80.58 245	78.12 390

MS-PatchMatch		73.83 278	72.67 278	77.30 301	83.87 288	66.02 176	81.82 291	84.66 278	61.37 339	68.61 329	82.82 328	47.29 313	88.21 305	59.27 295	84.32 194	77.68 391

DSMNet-mixed		57.77 366	56.90 368	60.38 386	67.70 407	35.61 417	69.18 392	53.97 418	32.30 416	57.49 393	79.88 359	40.39 365	68.57 410	38.78 399	72.37 344	76.97 392

CHOSEN 280x420		66.51 345	64.71 346	71.90 350	81.45 338	63.52 234	57.98 413	68.95 397	53.57 383	62.59 376	76.70 381	46.22 325	75.29 396	55.25 329	79.68 255	76.88 393

mvsany_test3		53.99 370	51.45 375	61.61 385	55.51 419	44.74 405	63.52 409	45.41 424	43.69 402	58.11 391	76.45 383	17.99 412	63.76 415	54.77 332	47.59 406	76.34 394

dmvs_testset		62.63 358	64.11 349	58.19 388	78.55 371	24.76 426	75.28 365	65.94 404	67.91 260	60.34 382	76.01 385	53.56 248	73.94 401	31.79 407	67.65 368	75.88 395

mvsany_test1		62.30 359	61.26 363	65.41 380	69.52 404	54.86 353	66.86 400	49.78 420	46.65 397	68.50 331	83.21 319	49.15 303	66.28 412	56.93 321	60.77 386	75.11 396

PMMVS		69.34 324	68.67 315	71.35 356	75.67 382	62.03 260	75.17 366	73.46 383	50.00 393	68.68 327	79.05 365	52.07 265	78.13 373	61.16 282	82.77 219	73.90 397

test_vis1_rt		60.28 362	58.42 365	65.84 379	67.25 408	55.60 345	70.44 388	60.94 412	44.33 401	59.00 387	66.64 402	24.91 402	68.67 409	62.80 261	69.48 360	73.25 398

pmmvs3		57.79 365	54.26 370	68.37 372	64.02 413	56.72 326	75.12 369	65.17 405	40.20 405	52.93 401	69.86 401	20.36 410	75.48 393	45.45 384	55.25 398	72.90 399

PVSNet_0	57.27 20	61.67 361	59.27 364	68.85 369	79.61 364	57.44 317	68.01 396	73.44 384	55.93 377	58.54 389	70.41 400	44.58 339	77.55 377	47.01 374	35.91 412	71.55 400

WB-MVS		54.94 368	54.72 369	55.60 394	73.50 393	20.90 428	74.27 374	61.19 411	59.16 355	50.61 403	74.15 391	47.19 315	75.78 391	17.31 419	35.07 413	70.12 401

SSC-MVS		53.88 371	53.59 371	54.75 396	72.87 399	19.59 429	73.84 376	60.53 413	57.58 369	49.18 407	73.45 394	46.34 324	75.47 394	16.20 422	32.28 415	69.20 402

test_f		52.09 375	50.82 376	55.90 392	53.82 422	42.31 412	59.42 412	58.31 416	36.45 411	56.12 398	70.96 399	12.18 418	57.79 418	53.51 338	56.57 393	67.60 403

PMMVS2		40.82 385	38.86 389	46.69 399	53.84 421	16.45 430	48.61 416	49.92 419	37.49 409	31.67 414	60.97 407	8.14 425	56.42 419	28.42 410	30.72 416	67.19 404

new_pmnet		50.91 377	50.29 377	52.78 397	68.58 406	34.94 419	63.71 408	56.63 417	39.73 406	44.95 408	65.47 403	21.93 408	58.48 417	34.98 404	56.62 392	64.92 405

MVS-HIRNet		59.14 364	57.67 366	63.57 382	81.65 333	43.50 407	71.73 380	65.06 406	39.59 407	51.43 402	57.73 410	38.34 374	82.58 354	39.53 396	73.95 331	64.62 406

APD_test1		53.31 373	49.93 378	63.42 383	65.68 410	50.13 388	71.59 382	66.90 402	34.43 413	40.58 412	71.56 398	8.65 424	76.27 386	34.64 405	55.36 396	63.86 407

test_method		31.52 388	29.28 392	38.23 402	27.03 430	6.50 433	20.94 421	62.21 410	4.05 424	22.35 422	52.50 415	13.33 416	47.58 422	27.04 412	34.04 414	60.62 408

EGC-MVSNET		52.07 376	47.05 380	67.14 377	83.51 296	60.71 277	80.50 314	67.75 399	0.07 426	0.43 427	75.85 388	24.26 404	81.54 359	28.82 409	62.25 382	59.16 409

test_vis3_rt		49.26 379	47.02 381	56.00 391	54.30 420	45.27 403	66.76 402	48.08 421	36.83 410	44.38 409	53.20 414	7.17 426	64.07 414	56.77 323	55.66 394	58.65 410

FPMVS		53.68 372	51.64 374	59.81 387	65.08 411	51.03 383	69.48 391	69.58 394	41.46 404	40.67 411	72.32 396	16.46 415	70.00 408	24.24 415	65.42 376	58.40 411

testf1		45.72 380	41.96 384	57.00 389	56.90 417	45.32 400	66.14 403	59.26 414	26.19 417	30.89 416	60.96 408	4.14 427	70.64 406	26.39 413	46.73 408	55.04 412

APD_test2		45.72 380	41.96 384	57.00 389	56.90 417	45.32 400	66.14 403	59.26 414	26.19 417	30.89 416	60.96 408	4.14 427	70.64 406	26.39 413	46.73 408	55.04 412

PMVS	37.38 22	44.16 384	40.28 388	55.82 393	40.82 428	42.54 411	65.12 407	63.99 408	34.43 413	24.48 419	57.12 412	3.92 429	76.17 388	17.10 420	55.52 395	48.75 414
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 390	25.89 394	43.81 401	44.55 427	35.46 418	28.87 420	39.07 425	18.20 421	18.58 423	40.18 418	2.68 430	47.37 423	17.07 421	23.78 420	48.60 415
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dongtai		45.42 382	45.38 383	45.55 400	73.36 396	26.85 424	67.72 397	34.19 426	54.15 382	49.65 406	56.41 413	25.43 400	62.94 416	19.45 417	28.09 417	46.86 416

kuosan		39.70 386	40.40 387	37.58 403	64.52 412	26.98 422	65.62 405	33.02 427	46.12 398	42.79 410	48.99 416	24.10 405	46.56 424	12.16 425	26.30 418	39.20 417

Gipuma		45.18 383	41.86 386	55.16 395	77.03 378	51.52 379	32.50 419	80.52 336	32.46 415	27.12 418	35.02 419	9.52 422	75.50 392	22.31 416	60.21 389	38.45 418
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX				27.40 406	40.17 429	26.90 423		24.59 430	17.44 422	23.95 420	48.61 417	9.77 421	26.48 425	18.06 418	24.47 419	28.83 419

E-PMN		31.77 387	30.64 390	35.15 404	52.87 424	27.67 421	57.09 414	47.86 422	24.64 419	16.40 424	33.05 420	11.23 420	54.90 420	14.46 423	18.15 421	22.87 420

EMVS		30.81 389	29.65 391	34.27 405	50.96 425	25.95 425	56.58 415	46.80 423	24.01 420	15.53 425	30.68 421	12.47 417	54.43 421	12.81 424	17.05 422	22.43 421

tmp_tt		18.61 392	21.40 395	10.23 408	4.82 431	10.11 431	34.70 418	30.74 429	1.48 425	23.91 421	26.07 422	28.42 397	13.41 427	27.12 411	15.35 424	7.17 422

wuyk23d		16.82 393	15.94 396	19.46 407	58.74 416	31.45 420	39.22 417	3.74 432	6.84 423	6.04 426	2.70 426	1.27 431	24.29 426	10.54 426	14.40 425	2.63 423

test123		6.12 395	8.11 398	0.14 409	0.06 433	0.09 434	71.05 384	0.03 434	0.04 428	0.25 429	1.30 428	0.05 432	0.03 429	0.21 428	0.01 427	0.29 424

testmvs		6.04 396	8.02 399	0.10 410	0.08 432	0.03 435	69.74 389	0.04 433	0.05 427	0.31 428	1.68 427	0.02 433	0.04 428	0.24 427	0.02 426	0.25 425

mmdepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

monomultidepth		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

test_blank		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet_test		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

DCPMVS		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

cdsmvs_eth3d_5k		19.96 391	26.61 393	0.00 411	0.00 434	0.00 436	0.00 422	89.26 185	0.00 429	0.00 430	88.61 186	61.62 171	0.00 430	0.00 429	0.00 428	0.00 426

pcd_1.5k_mvsjas		5.26 397	7.02 400	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	63.15 147	0.00 430	0.00 429	0.00 428	0.00 426

sosnet-low-res		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

sosnet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uncertanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

Regformer		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

ab-mvs-re		7.23 394	9.64 397	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	86.72 236	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

uanet		0.00 398	0.00 401	0.00 411	0.00 434	0.00 436	0.00 422	0.00 435	0.00 429	0.00 430	0.00 429	0.00 434	0.00 430	0.00 429	0.00 428	0.00 426

WAC-MVS						42.58 409								39.46 397

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 122	91.30 15

test_one_0601					95.07 7	71.46 57		94.14 5	78.27 36	92.05 11	95.74 6	80.83 11

eth-test2					0.00 434

eth-test					0.00 434

ZD-MVS					94.38 25	72.22 44		92.67 67	70.98 194	87.75 38	94.07 47	74.01 32	96.70 27	84.66 55	94.84 44

test_241102_ONE					95.30 2	70.98 66		94.06 10	77.17 57	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	73.93 136	88.57 26	94.67 22	75.57 22	95.79 58	86.77 38	95.76 23

save fliter					93.80 40	72.35 42	90.47 66	91.17 125	74.31 127

test0726					95.27 5	71.25 59	93.60 6	94.11 6	77.33 51	92.81 3	95.79 3	80.98 9

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs												50.01 290

MTGPA								92.02 93

test_post1							78.90 337				5.43 425	48.81 309	85.44 334	59.25 296

test_post											5.46 424	50.36 288	84.24 342

patchmatchnet-post											74.00 392	51.12 279	88.60 301

MTMP							92.18 34	32.83 428

gm-plane-assit					81.40 339	53.83 362			62.72 327		80.94 348		92.39 204	63.40 258

TEST9					93.26 52	72.96 25	88.75 121	91.89 101	68.44 254	85.00 66	93.10 73	74.36 28	95.41 73

test_8					93.13 54	72.57 35	88.68 126	91.84 105	68.69 249	84.87 70	93.10 73	74.43 26	95.16 83

agg_prior					92.85 62	71.94 50		91.78 108		84.41 81			94.93 94

test_prior4						72.60 34	89.01 112

test_prior2							88.85 118		75.41 99	84.91 68	93.54 62	74.28 29		83.31 70	95.86 20

旧先验2							86.56 197		58.10 364	87.04 48			88.98 293	74.07 161

新几何2							86.29 206

原ACMM2							86.86 186

testdata2													91.01 259	62.37 268

segment_acmp												73.08 39

testdata1							84.14 260		75.71 93

plane_prior7					90.08 108	68.51 123

plane_prior6					89.84 117	68.70 118						60.42 197

plane_prior4											91.00 133

plane_prior3						68.60 121			78.44 32	78.92 154

plane_prior2							91.25 52		79.12 24

plane_prior1					89.90 116

plane_prior						68.71 116	90.38 70		77.62 41						86.16 169

n2								0.00 435

nn								0.00 435

door-mid								69.98 392

test11								92.23 87

door								69.44 395

HQP5-MVS						66.98 163

HQP-NCC					89.33 135		89.17 103		76.41 78	77.23 192

ACMP_Plane					89.33 135		89.17 103		76.41 78	77.23 192

BP-MVS														77.47 125

HQP3-MVS								92.19 90							85.99 173

HQP2-MVS												60.17 200

NP-MVS					89.62 121	68.32 127					90.24 145

MDTV_nov1_ep13			69.97 309		83.18 304	53.48 364	77.10 356	80.18 344	60.45 342	69.33 323	80.44 352	48.89 308	86.90 316	51.60 347	78.51 268

ACMMP++_ref															81.95 230

ACMMP++															81.25 235

Test By Simon												64.33 134

High-resolution multi-view benchmark