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 98	73.65 10	92.66 24	91.17 136	86.57 1	87.39 52	94.97 21	71.70 58	97.68 1	92.19 1	95.63 28	95.57 1

casdiffmvs_mvg		85.99 54	86.09 57	85.70 77	87.65 221	67.22 173	88.69 135	93.04 42	79.64 21	85.33 70	92.54 98	73.30 36	94.50 119	83.49 77	91.14 102	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
dcpmvs_2		85.63 65	86.15 55	84.06 150	91.71 80	64.94 224	86.47 219	91.87 109	73.63 161	86.60 61	93.02 87	76.57 15	91.87 247	83.36 78	92.15 84	95.35 3

casdiffmvs		85.11 78	85.14 77	85.01 99	87.20 236	65.77 202	87.75 172	92.83 61	77.84 43	84.36 93	92.38 100	72.15 51	93.93 144	81.27 103	90.48 113	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_9		87.39 30	87.95 20	85.70 77	89.48 133	67.88 149	88.59 139	89.05 218	80.19 12	90.70 17	95.40 15	74.56 25	93.92 145	91.54 2	92.07 86	95.31 5

3Dnovator+	77.84 4	85.48 68	84.47 87	88.51 7	91.08 89	73.49 16	93.18 12	93.78 19	80.79 8	76.66 238	93.37 77	60.40 221	96.75 26	77.20 147	93.73 66	95.29 6

BP-MVS1		84.32 86	83.71 96	86.17 64	87.84 209	67.85 150	89.38 102	89.64 187	77.73 45	83.98 100	92.12 108	56.89 251	95.43 73	84.03 74	91.75 92	95.24 7

MVS_0304		87.69 21	87.55 26	88.12 13	89.45 134	71.76 53	91.47 52	89.54 190	82.14 3	86.65 60	94.28 41	68.28 106	97.46 6	90.81 6	95.31 34	95.15 8

CS-MVS		86.69 41	86.95 39	85.90 74	90.76 99	67.57 159	92.83 18	93.30 33	79.67 19	84.57 87	92.27 101	71.47 61	95.02 96	84.24 71	93.46 69	95.13 9

TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 48	91.41 53	92.35 83	74.62 136	88.90 27	93.85 65	75.75 20	96.00 55	87.80 38	94.63 50	95.04 10
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
baseline		84.93 81	84.98 78	84.80 111	87.30 234	65.39 211	87.30 188	92.88 58	77.62 47	84.04 99	92.26 102	71.81 55	93.96 138	81.31 101	90.30 116	95.03 11

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

PC_three_1452									68.21 294	92.02 12	94.00 57	82.09 5	95.98 57	84.58 65	96.68 2	94.95 12

IS-MVSNet		83.15 115	82.81 113	84.18 139	89.94 119	63.30 270	91.59 46	88.46 242	79.04 30	79.49 172	92.16 105	65.10 144	94.28 125	67.71 256	91.86 91	94.95 12

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 74	72.96 25	93.73 5	93.67 21	80.19 12	88.10 37	94.80 23	73.76 34	97.11 15	87.51 41	95.82 21	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 68	93.57 8	94.06 11	77.24 60	93.10 1	95.72 8	82.99 1	97.44 7	89.07 23	96.63 4	94.88 16

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

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 25	93.63 22	74.77 132	92.29 7	95.97 2	74.28 30	97.24 13	88.58 31	96.91 1	94.87 18
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
test2506		77.30 263	76.49 260	79.74 287	90.08 112	52.02 409	87.86 170	63.10 452	74.88 128	80.16 165	92.79 94	38.29 416	92.35 228	68.74 249	92.50 80	94.86 19

ECVR-MVS		79.61 197	79.26 190	80.67 267	90.08 112	54.69 391	87.89 168	77.44 405	74.88 128	80.27 162	92.79 94	48.96 341	92.45 222	68.55 250	92.50 80	94.86 19

IU-MVS					95.30 2	71.25 61		92.95 56	66.81 306	92.39 6				88.94 26	96.63 4	94.85 21

test1111		79.43 204	79.18 193	80.15 279	89.99 117	53.31 404	87.33 187	77.05 409	75.04 121	80.23 164	92.77 96	48.97 340	92.33 230	68.87 247	92.40 82	94.81 22

SF-MVS		88.46 12	88.74 12	87.64 35	92.78 66	71.95 51	92.40 25	94.74 2	75.71 101	89.16 24	95.10 18	75.65 21	96.19 47	87.07 44	96.01 17	94.79 23

balanced_conf03		86.78 39	86.99 37	86.15 66	91.24 86	67.61 157	90.51 65	92.90 57	77.26 59	87.44 51	91.63 122	71.27 65	96.06 50	85.62 54	95.01 37	94.78 24

viewmacassd2359aftdt		83.76 96	83.66 98	84.07 147	86.59 260	64.56 232	86.88 203	91.82 112	75.72 100	83.34 111	92.15 107	68.24 107	92.88 204	79.05 123	89.15 139	94.77 25

sasdasda		85.91 58	85.87 62	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 40	91.23 135	73.28 37	93.91 146	81.50 99	88.80 144	94.77 25

SPE-MVS-test		86.29 50	86.48 46	85.71 76	91.02 91	67.21 174	92.36 30	93.78 19	78.97 33	83.51 110	91.20 138	70.65 74	95.15 87	81.96 96	94.89 42	94.77 25

canonicalmvs		85.91 58	85.87 62	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 40	91.23 135	73.28 37	93.91 146	81.50 99	88.80 144	94.77 25

GDP-MVS		83.52 105	82.64 116	86.16 65	88.14 193	68.45 128	89.13 114	92.69 66	72.82 187	83.71 105	91.86 114	55.69 258	95.35 82	80.03 116	89.74 128	94.69 29

test_0728_THIRD									78.38 38	92.12 9	95.78 4	81.46 7	97.40 9	89.42 18	96.57 7	94.67 30

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 17	94.11 7	80.27 10	91.35 14	94.16 48	78.35 13	96.77 24	89.59 16	94.22 62	94.67 30
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		82.60 127	82.10 127	84.10 141	87.98 203	62.94 281	87.45 182	91.27 132	77.42 56	79.85 167	90.28 166	56.62 254	94.70 112	79.87 119	88.15 157	94.67 30

MGCFI-Net		85.06 80	85.51 69	83.70 168	89.42 135	63.01 276	89.43 97	92.62 74	76.43 84	87.53 48	91.34 133	72.82 46	93.42 173	81.28 102	88.74 147	94.66 33

viewmanbaseed2359cas		83.66 99	83.55 99	84.00 158	86.81 252	64.53 233	86.65 213	91.75 117	74.89 127	83.15 115	91.68 118	68.74 100	92.83 208	79.02 124	89.24 136	94.63 34

alignmvs		85.48 68	85.32 74	85.96 73	89.51 130	69.47 98	89.74 86	92.47 77	76.17 93	87.73 47	91.46 130	70.32 76	93.78 152	81.51 98	88.95 141	94.63 34

MP-MVS-pluss		87.67 22	87.72 22	87.54 36	93.64 44	72.04 50	89.80 84	93.50 26	75.17 120	86.34 62	95.29 17	70.86 70	96.00 55	88.78 29	96.04 16	94.58 36
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepPCF-MVS	80.84 1	88.10 13	88.56 14	86.73 55	92.24 73	69.03 106	89.57 93	93.39 31	77.53 53	89.79 20	94.12 50	78.98 12	96.58 35	85.66 52	95.72 24	94.58 36

viewcassd2359sk11		83.89 91	83.74 95	84.34 127	87.76 216	64.91 227	86.30 226	92.22 89	75.47 108	83.04 116	91.52 126	70.15 79	93.53 165	79.26 122	87.96 159	94.57 38

VDD-MVS		83.01 120	82.36 121	84.96 101	91.02 91	66.40 185	88.91 121	88.11 245	77.57 49	84.39 90	93.29 79	52.19 292	93.91 146	77.05 150	88.70 148	94.57 38

NormalMVS		86.29 50	85.88 60	87.52 37	93.26 52	72.47 38	91.65 43	92.19 93	79.31 24	84.39 90	92.18 103	64.64 149	95.53 67	80.70 110	94.65 48	94.56 40

KinetiMVS		83.31 113	82.61 117	85.39 86	87.08 245	67.56 160	88.06 160	91.65 119	77.80 44	82.21 128	91.79 115	57.27 246	94.07 136	77.77 141	89.89 126	94.56 40

VDDNet		81.52 149	80.67 149	84.05 153	90.44 104	64.13 245	89.73 87	85.91 298	71.11 217	83.18 113	93.48 72	50.54 318	93.49 167	73.40 194	88.25 155	94.54 42

MVSMamba_PlusPlus		85.99 54	85.96 59	86.05 69	91.09 88	67.64 156	89.63 91	92.65 71	72.89 186	84.64 84	91.71 117	71.85 54	96.03 51	84.77 63	94.45 56	94.49 43

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 54	93.83 4	93.96 14	75.70 103	91.06 16	96.03 1	76.84 14	97.03 17	89.09 20	95.65 27	94.47 44
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 50					97.53 2	89.67 14	96.44 9	94.41 45

No_MVS				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 14	96.44 9	94.41 45

MCST-MVS		87.37 31	87.25 32	87.73 28	94.53 17	72.46 40	89.82 82	93.82 17	73.07 181	84.86 79	92.89 89	76.22 17	96.33 41	84.89 60	95.13 36	94.40 47

fmvsm_s_conf0.5_n_8		86.56 44	87.17 35	84.73 114	87.76 216	65.62 205	89.20 107	92.21 91	79.94 17	89.74 22	94.86 22	68.63 101	94.20 130	90.83 5	91.39 98	94.38 48

CANet		86.45 45	86.10 56	87.51 38	90.09 111	70.94 72	89.70 88	92.59 75	81.78 4	81.32 142	91.43 131	70.34 75	97.23 14	84.26 69	93.36 70	94.37 49

PHI-MVS		86.43 46	86.17 54	87.24 42	90.88 95	70.96 70	92.27 33	94.07 10	72.45 189	85.22 72	91.90 111	69.47 87	96.42 40	83.28 80	95.94 19	94.35 50

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 65	93.00 47	80.90 7	88.06 38	94.06 53	76.43 16	96.84 21	88.48 34	95.99 18	94.34 51

ZNCC-MVS		87.94 19	87.85 21	88.20 12	94.39 24	73.33 19	93.03 15	93.81 18	76.81 74	85.24 71	94.32 39	71.76 56	96.93 19	85.53 55	95.79 22	94.32 52

HPM-MVS		87.11 35	86.98 38	87.50 39	93.88 39	72.16 47	92.19 34	93.33 32	76.07 95	83.81 104	93.95 62	69.77 84	96.01 54	85.15 56	94.66 47	94.32 52
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CDPH-MVS		85.76 63	85.29 76	87.17 44	93.49 47	71.08 66	88.58 140	92.42 81	68.32 293	84.61 85	93.48 72	72.32 48	96.15 49	79.00 126	95.43 30	94.28 54

test_241102_TWO								94.06 11	77.24 60	92.78 4	95.72 8	81.26 8	97.44 7	89.07 23	96.58 6	94.26 55

test_0728_SECOND				87.71 32	95.34 1	71.43 60	93.49 10	94.23 3					97.49 4	89.08 21	96.41 12	94.21 56

fmvsm_l_conf0.5_n_3		86.02 52	86.32 48	85.14 92	87.20 236	68.54 126	89.57 93	90.44 156	75.31 114	87.49 49	94.39 37	72.86 44	92.72 210	89.04 25	90.56 112	94.16 57

DeepC-MVS_fast	79.65 3	86.91 38	86.62 45	87.76 27	93.52 46	72.37 43	91.26 54	93.04 42	76.62 82	84.22 94	93.36 78	71.44 62	96.76 25	80.82 107	95.33 33	94.16 57
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EPP-MVSNet		83.40 109	83.02 109	84.57 117	90.13 110	64.47 238	92.32 31	90.73 148	74.45 140	79.35 177	91.10 141	69.05 95	95.12 88	72.78 201	87.22 171	94.13 59

viewdifsd2359ckpt13		82.91 121	82.29 123	84.77 112	86.96 248	66.90 181	87.47 179	91.62 121	72.19 194	81.68 138	90.71 154	66.92 120	93.28 176	75.90 166	87.15 173	94.12 60

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

ACMMP_NAP		88.05 17	88.08 18	87.94 19	93.70 41	73.05 22	90.86 60	93.59 24	76.27 92	88.14 36	95.09 19	71.06 68	96.67 29	87.67 39	96.37 14	94.09 62

XVS		87.18 34	86.91 41	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 107	94.17 47	67.45 115	96.60 33	83.06 81	94.50 53	94.07 63

X-MVStestdata		80.37 184	77.83 224	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 107	12.47 466	67.45 115	96.60 33	83.06 81	94.50 53	94.07 63

region2R		87.42 28	87.20 34	88.09 14	94.63 14	73.55 13	93.03 15	93.12 41	76.73 79	84.45 88	94.52 27	69.09 92	96.70 27	84.37 68	94.83 45	94.03 65

fmvsm_s_conf0.5_n_4		85.39 72	85.75 65	84.30 130	86.70 256	65.83 198	88.77 129	89.78 179	75.46 109	88.35 31	93.73 68	69.19 91	93.06 196	91.30 3	88.44 153	94.02 66

ACMMPR		87.44 26	87.23 33	88.08 15	94.64 13	73.59 12	93.04 13	93.20 35	76.78 76	84.66 83	94.52 27	68.81 98	96.65 30	84.53 66	94.90 41	94.00 67

fmvsm_s_conf0.1_n_2		83.80 94	83.79 94	83.83 164	85.62 281	64.94 224	87.03 195	86.62 287	74.32 142	87.97 42	94.33 38	60.67 213	92.60 213	89.72 13	87.79 162	93.96 68

test_fmvsmconf_n		85.92 57	86.04 58	85.57 82	85.03 300	69.51 96	89.62 92	90.58 151	73.42 169	87.75 45	94.02 55	72.85 45	93.24 180	90.37 7	90.75 109	93.96 68

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 46	94.10 9	75.90 98	92.29 7	95.66 10	81.67 6	97.38 11	87.44 43	96.34 15	93.95 70
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 75	85.34 72	85.13 95	86.12 270	69.93 88	88.65 137	90.78 147	69.97 253	88.27 33	93.98 60	71.39 63	91.54 263	88.49 33	90.45 114	93.91 71

test_prior				86.33 60	92.61 70	69.59 94		92.97 55					95.48 70			93.91 71

GST-MVS		87.42 28	87.26 31	87.89 24	94.12 36	72.97 24	92.39 27	93.43 29	76.89 72	84.68 80	93.99 59	70.67 73	96.82 22	84.18 73	95.01 37	93.90 73

test_fmvsmconf0.1_n		85.61 66	85.65 66	85.50 83	82.99 352	69.39 103	89.65 89	90.29 165	73.31 173	87.77 44	94.15 49	71.72 57	93.23 181	90.31 8	90.67 111	93.89 74

Anonymous202405211		78.25 235	77.01 246	81.99 233	91.03 90	60.67 313	84.77 267	83.90 325	70.65 234	80.00 166	91.20 138	41.08 401	91.43 270	65.21 278	85.26 209	93.85 75

LFMVS		81.82 139	81.23 139	83.57 173	91.89 78	63.43 268	89.84 81	81.85 358	77.04 69	83.21 112	93.10 82	52.26 291	93.43 172	71.98 213	89.95 124	93.85 75

fmvsm_s_conf0.5_n_2		84.04 89	84.11 90	83.81 166	86.17 268	65.00 222	86.96 198	87.28 269	74.35 141	88.25 34	94.23 45	61.82 189	92.60 213	89.85 11	88.09 158	93.84 77

Effi-MVS+		83.62 103	83.08 107	85.24 90	88.38 184	67.45 162	88.89 122	89.15 214	75.50 107	82.27 126	88.28 228	69.61 86	94.45 122	77.81 140	87.84 161	93.84 77

Anonymous20240529		80.19 190	78.89 199	84.10 141	90.60 100	64.75 230	88.95 120	90.90 143	65.97 323	80.59 158	91.17 140	49.97 325	93.73 158	69.16 244	82.70 256	93.81 79

MVS_Test		83.15 115	83.06 108	83.41 179	86.86 249	63.21 272	86.11 232	92.00 101	74.31 143	82.87 119	89.44 196	70.03 80	93.21 183	77.39 146	88.50 152	93.81 79

Elysia		81.53 147	80.16 162	85.62 79	85.51 284	68.25 135	88.84 126	92.19 93	71.31 211	80.50 159	89.83 176	46.89 352	94.82 104	76.85 152	89.57 130	93.80 81

StellarMVS		81.53 147	80.16 162	85.62 79	85.51 284	68.25 135	88.84 126	92.19 93	71.31 211	80.50 159	89.83 176	46.89 352	94.82 104	76.85 152	89.57 130	93.80 81

test_fmvsmconf0.01_n		84.73 84	84.52 86	85.34 87	80.25 394	69.03 106	89.47 95	89.65 186	73.24 177	86.98 57	94.27 42	66.62 123	93.23 181	90.26 9	89.95 124	93.78 83

GeoE		81.71 141	81.01 144	83.80 167	89.51 130	64.45 239	88.97 119	88.73 235	71.27 214	78.63 189	89.76 181	66.32 129	93.20 186	69.89 236	86.02 194	93.74 84

diffmvs		82.10 131	81.88 133	82.76 215	83.00 350	63.78 254	83.68 297	89.76 181	72.94 184	82.02 131	89.85 175	65.96 138	90.79 290	82.38 94	87.30 170	93.71 85
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
lecture		88.09 14	88.59 13	86.58 58	93.26 52	69.77 92	93.70 6	94.16 5	77.13 65	89.76 21	95.52 14	72.26 49	96.27 44	86.87 45	94.65 48	93.70 86

HFP-MVS		87.58 23	87.47 28	87.94 19	94.58 16	73.54 15	93.04 13	93.24 34	76.78 76	84.91 76	94.44 34	70.78 71	96.61 32	84.53 66	94.89 42	93.66 87

VNet		82.21 130	82.41 119	81.62 239	90.82 96	60.93 308	84.47 276	89.78 179	76.36 90	84.07 98	91.88 112	64.71 148	90.26 298	70.68 225	88.89 142	93.66 87

PGM-MVS		86.68 42	86.27 50	87.90 22	94.22 33	73.38 18	90.22 76	93.04 42	75.53 106	83.86 102	94.42 35	67.87 112	96.64 31	82.70 92	94.57 52	93.66 87

DELS-MVS		85.41 71	85.30 75	85.77 75	88.49 178	67.93 148	85.52 252	93.44 28	78.70 34	83.63 109	89.03 203	74.57 24	95.71 62	80.26 115	94.04 63	93.66 87
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 15	88.50 15	86.71 56	92.60 71	72.71 29	91.81 42	93.19 36	77.87 42	90.32 18	94.00 57	74.83 23	93.78 152	87.63 40	94.27 61	93.65 91
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 37	86.88 42	87.69 33	91.16 87	72.32 45	90.31 74	93.94 15	77.12 66	82.82 121	94.23 45	72.13 52	97.09 16	84.83 61	95.37 31	93.65 91
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		83.65 100	84.54 84	80.99 259	90.06 116	65.83 198	84.21 285	88.74 234	71.60 206	85.01 73	92.44 99	74.51 26	83.50 386	82.15 95	92.15 84	93.64 93

EIA-MVS		83.31 113	82.80 114	84.82 109	89.59 126	65.59 206	88.21 154	92.68 67	74.66 135	78.96 181	86.42 286	69.06 94	95.26 83	75.54 172	90.09 120	93.62 94

MP-MVS		87.71 20	87.64 23	87.93 21	94.36 26	73.88 6	92.71 23	92.65 71	77.57 49	83.84 103	94.40 36	72.24 50	96.28 43	85.65 53	95.30 35	93.62 94
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
diffmvs_AUTHOR		82.38 128	82.27 124	82.73 217	83.26 340	63.80 252	83.89 292	89.76 181	73.35 172	82.37 125	90.84 151	66.25 130	90.79 290	82.77 87	87.93 160	93.59 96

HPM-MVS_fast		85.35 74	84.95 80	86.57 59	93.69 42	70.58 80	92.15 36	91.62 121	73.89 155	82.67 124	94.09 51	62.60 173	95.54 66	80.93 105	92.93 73	93.57 97

fmvsm_s_conf0.1_n		83.56 104	83.38 103	84.10 141	84.86 302	67.28 169	89.40 101	83.01 342	70.67 230	87.08 55	93.96 61	68.38 104	91.45 269	88.56 32	84.50 218	93.56 98

CSCG		86.41 48	86.19 53	87.07 46	92.91 63	72.48 37	90.81 61	93.56 25	73.95 152	83.16 114	91.07 143	75.94 18	95.19 85	79.94 118	94.38 58	93.55 99

test12				86.80 54	92.63 69	70.70 77		91.79 114		82.71 123		71.67 59	96.16 48		94.50 53	93.54 100

APD-MVS_3200maxsize		85.97 56	85.88 60	86.22 63	92.69 68	69.53 95	91.93 38	92.99 50	73.54 165	85.94 63	94.51 30	65.80 139	95.61 63	83.04 83	92.51 79	93.53 101

mvs_anonymous		79.42 205	79.11 194	80.34 274	84.45 313	57.97 343	82.59 319	87.62 262	67.40 303	76.17 254	88.56 221	68.47 103	89.59 311	70.65 226	86.05 193	93.47 102

fmvsm_s_conf0.5_n		83.80 94	83.71 96	84.07 147	86.69 257	67.31 168	89.46 96	83.07 341	71.09 218	86.96 58	93.70 69	69.02 97	91.47 268	88.79 28	84.62 217	93.44 103

fmvsm_s_conf0.5_n_5		85.22 76	85.55 68	84.25 137	86.26 264	67.40 165	89.18 108	89.31 203	72.50 188	88.31 32	93.86 64	69.66 85	91.96 241	89.81 12	91.05 103	93.38 104

mPP-MVS		86.67 43	86.32 48	87.72 30	94.41 22	73.55 13	92.74 21	92.22 89	76.87 73	82.81 122	94.25 44	66.44 127	96.24 45	82.88 86	94.28 60	93.38 104

EPNet		83.72 98	82.92 112	86.14 68	84.22 316	69.48 97	91.05 59	85.27 305	81.30 6	76.83 233	91.65 120	66.09 134	95.56 64	76.00 165	93.85 64	93.38 104
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Vis-MVSNet		83.46 107	82.80 114	85.43 85	90.25 108	68.74 117	90.30 75	90.13 170	76.33 91	80.87 153	92.89 89	61.00 208	94.20 130	72.45 210	90.97 105	93.35 107
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 41	95.27 5	71.25 61	93.49 10	92.73 65	77.33 57	92.12 9	95.78 4	80.98 9	97.40 9	89.08 21	96.41 12	93.33 108
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		79.10 215	78.24 213	81.70 238	86.85 250	60.24 320	87.28 189	88.79 229	74.25 146	76.84 232	90.53 161	49.48 331	91.56 259	67.98 254	82.15 260	93.29 109

EI-MVSNet-Vis-set		84.19 87	83.81 93	85.31 88	88.18 190	67.85 150	87.66 174	89.73 184	80.05 15	82.95 117	89.59 188	70.74 72	94.82 104	80.66 112	84.72 215	93.28 110

MTAPA		87.23 33	87.00 36	87.90 22	94.18 35	74.25 5	86.58 216	92.02 99	79.45 22	85.88 64	94.80 23	68.07 108	96.21 46	86.69 47	95.34 32	93.23 111

CP-MVS		87.11 35	86.92 40	87.68 34	94.20 34	73.86 7	93.98 3	92.82 64	76.62 82	83.68 106	94.46 31	67.93 110	95.95 58	84.20 72	94.39 57	93.23 111

ACMMP		85.89 60	85.39 71	87.38 40	93.59 45	72.63 33	92.74 21	93.18 40	76.78 76	80.73 156	93.82 66	64.33 151	96.29 42	82.67 93	90.69 110	93.23 111
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
SymmetryMVS		85.38 73	84.81 81	87.07 46	91.47 83	72.47 38	91.65 43	88.06 249	79.31 24	84.39 90	92.18 103	64.64 149	95.53 67	80.70 110	90.91 107	93.21 114

fmvsm_s_conf0.1_n_a		83.32 112	82.99 110	84.28 132	83.79 326	68.07 141	89.34 104	82.85 347	69.80 257	87.36 53	94.06 53	68.34 105	91.56 259	87.95 37	83.46 244	93.21 114

fmvsm_s_conf0.5_n_6		85.55 67	86.20 51	83.60 170	87.32 233	65.13 217	88.86 123	91.63 120	75.41 110	88.23 35	93.45 75	68.56 102	92.47 221	89.52 17	92.78 75	93.20 116

PAPM_NR		83.02 119	82.41 119	84.82 109	92.47 72	66.37 186	87.93 166	91.80 113	73.82 156	77.32 221	90.66 155	67.90 111	94.90 100	70.37 228	89.48 133	93.19 117

fmvsm_l_conf0.5_n_9		85.84 61	86.63 44	83.46 175	87.12 244	66.01 192	88.56 141	89.43 194	75.59 105	89.32 23	94.32 39	72.89 43	91.21 278	90.11 10	92.33 83	93.16 118

reproduce_model		87.28 32	87.39 30	86.95 50	93.10 58	71.24 65	91.60 45	93.19 36	74.69 133	88.80 28	95.61 11	70.29 77	96.44 39	86.20 51	93.08 71	93.16 118

OMC-MVS		82.69 123	81.97 132	84.85 108	88.75 170	67.42 163	87.98 162	90.87 145	74.92 126	79.72 169	91.65 120	62.19 183	93.96 138	75.26 176	86.42 186	93.16 118

fmvsm_s_conf0.5_n_a		83.63 102	83.41 102	84.28 132	86.14 269	68.12 139	89.43 97	82.87 346	70.27 246	87.27 54	93.80 67	69.09 92	91.58 256	88.21 36	83.65 238	93.14 121

PAPR		81.66 144	80.89 146	83.99 159	90.27 107	64.00 246	86.76 210	91.77 116	68.84 284	77.13 231	89.50 189	67.63 113	94.88 102	67.55 258	88.52 151	93.09 122

UA-Net		85.08 79	84.96 79	85.45 84	92.07 75	68.07 141	89.78 85	90.86 146	82.48 2	84.60 86	93.20 81	69.35 88	95.22 84	71.39 218	90.88 108	93.07 123

reproduce-ours		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 123	88.96 25	95.54 12	71.20 66	96.54 36	86.28 49	93.49 67	93.06 124

our_new_method		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 123	88.96 25	95.54 12	71.20 66	96.54 36	86.28 49	93.49 67	93.06 124

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 28	92.85 60	80.26 11	87.78 43	94.27 42	75.89 19	96.81 23	87.45 42	96.44 9	93.05 126

thisisatest0530		79.40 206	77.76 229	84.31 129	87.69 220	65.10 220	87.36 185	84.26 321	70.04 249	77.42 218	88.26 230	49.94 326	94.79 108	70.20 231	84.70 216	93.03 127

train_agg		86.43 46	86.20 51	87.13 45	93.26 52	72.96 25	88.75 131	91.89 107	68.69 286	85.00 74	93.10 82	74.43 27	95.41 76	84.97 57	95.71 25	93.02 128

EC-MVSNet		86.01 53	86.38 47	84.91 106	89.31 143	66.27 188	92.32 31	93.63 22	79.37 23	84.17 96	91.88 112	69.04 96	95.43 73	83.93 75	93.77 65	93.01 129

mvsmamba		80.60 175	79.38 185	84.27 134	89.74 124	67.24 172	87.47 179	86.95 277	70.02 250	75.38 270	88.93 208	51.24 309	92.56 216	75.47 174	89.22 137	93.00 130

EI-MVSNet-UG-set		83.81 93	83.38 103	85.09 97	87.87 207	67.53 161	87.44 183	89.66 185	79.74 18	82.23 127	89.41 197	70.24 78	94.74 109	79.95 117	83.92 230	92.99 131

tttt0517		79.40 206	77.91 220	83.90 163	88.10 196	63.84 251	88.37 149	84.05 323	71.45 209	76.78 235	89.12 200	49.93 328	94.89 101	70.18 232	83.18 249	92.96 132

viewdifsd2359ckpt11		80.37 184	79.73 175	82.30 226	83.70 330	62.39 287	84.20 286	86.67 283	73.22 178	80.90 151	90.62 156	63.00 170	91.56 259	76.81 156	78.44 304	92.95 133

viewmsd2359difaftdt		80.37 184	79.73 175	82.30 226	83.70 330	62.39 287	84.20 286	86.67 283	73.22 178	80.90 151	90.62 156	63.00 170	91.56 259	76.81 156	78.44 304	92.95 133

test9_res														84.90 58	95.70 26	92.87 135

viewmambaseed2359dif		80.41 180	79.84 172	82.12 228	82.95 354	62.50 286	83.39 305	88.06 249	67.11 304	80.98 149	90.31 165	66.20 132	91.01 286	74.62 180	84.90 212	92.86 136

AstraMVS		80.81 163	80.14 164	82.80 209	86.05 273	63.96 247	86.46 220	85.90 299	73.71 159	80.85 154	90.56 159	54.06 275	91.57 258	79.72 120	83.97 229	92.86 136

SR-MVS		86.73 40	86.67 43	86.91 51	94.11 37	72.11 49	92.37 29	92.56 76	74.50 137	86.84 59	94.65 26	67.31 117	95.77 60	84.80 62	92.85 74	92.84 138

ETV-MVS		84.90 83	84.67 83	85.59 81	89.39 138	68.66 123	88.74 133	92.64 73	79.97 16	84.10 97	85.71 299	69.32 89	95.38 78	80.82 107	91.37 99	92.72 139

agg_prior2														82.91 85	95.45 29	92.70 140

APD-MVS		87.44 26	87.52 27	87.19 43	94.24 32	72.39 41	91.86 41	92.83 61	73.01 183	88.58 29	94.52 27	73.36 35	96.49 38	84.26 69	95.01 37	92.70 140
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ET-MVSNet_ETH3D		78.63 227	76.63 259	84.64 116	86.73 255	69.47 98	85.01 262	84.61 314	69.54 263	66.51 393	86.59 279	50.16 322	91.75 250	76.26 161	84.24 226	92.69 142

Vis-MVSNet (Re-imp)		78.36 234	78.45 206	78.07 323	88.64 174	51.78 415	86.70 211	79.63 387	74.14 149	75.11 283	90.83 152	61.29 202	89.75 308	58.10 345	91.60 93	92.69 142

TSAR-MVS + GP.		85.71 64	85.33 73	86.84 52	91.34 84	72.50 36	89.07 117	87.28 269	76.41 85	85.80 65	90.22 170	74.15 32	95.37 81	81.82 97	91.88 88	92.65 144

test_fmvsmvis_n_1920		84.02 90	83.87 92	84.49 121	84.12 318	69.37 104	88.15 158	87.96 252	70.01 251	83.95 101	93.23 80	68.80 99	91.51 266	88.61 30	89.96 123	92.57 145

FA-MVS(test-final)		80.96 159	79.91 169	84.10 141	88.30 187	65.01 221	84.55 275	90.01 173	73.25 176	79.61 170	87.57 248	58.35 235	94.72 110	71.29 219	86.25 189	92.56 146

guyue		81.13 156	80.64 150	82.60 220	86.52 261	63.92 250	86.69 212	87.73 260	73.97 151	80.83 155	89.69 182	56.70 252	91.33 274	78.26 139	85.40 208	92.54 147

test_yl		81.17 154	80.47 155	83.24 185	89.13 152	63.62 255	86.21 229	89.95 175	72.43 192	81.78 136	89.61 186	57.50 243	93.58 160	70.75 223	86.90 177	92.52 148

DCV-MVSNet		81.17 154	80.47 155	83.24 185	89.13 152	63.62 255	86.21 229	89.95 175	72.43 192	81.78 136	89.61 186	57.50 243	93.58 160	70.75 223	86.90 177	92.52 148

SR-MVS-dyc-post		85.77 62	85.61 67	86.23 62	93.06 60	70.63 78	91.88 39	92.27 85	73.53 166	85.69 67	94.45 32	65.00 147	95.56 64	82.75 88	91.87 89	92.50 150

RE-MVS-def			85.48 70		93.06 60	70.63 78	91.88 39	92.27 85	73.53 166	85.69 67	94.45 32	63.87 155		82.75 88	91.87 89	92.50 150

nrg030		83.88 92	83.53 100	84.96 101	86.77 254	69.28 105	90.46 70	92.67 68	74.79 131	82.95 117	91.33 134	72.70 47	93.09 194	80.79 109	79.28 297	92.50 150

SSM_0404		81.91 136	80.84 147	85.13 95	89.24 147	68.26 133	87.84 171	89.25 208	71.06 220	80.62 157	90.39 163	59.57 224	94.65 114	72.45 210	87.19 172	92.47 153

MG-MVS		83.41 108	83.45 101	83.28 182	92.74 67	62.28 292	88.17 156	89.50 192	75.22 115	81.49 140	92.74 97	66.75 121	95.11 90	72.85 200	91.58 95	92.45 154

FIs		82.07 133	82.42 118	81.04 258	88.80 167	58.34 337	88.26 153	93.49 27	76.93 71	78.47 195	91.04 144	69.92 82	92.34 229	69.87 237	84.97 211	92.44 155

testing3-2		75.12 301	75.19 283	74.91 362	90.40 105	45.09 445	80.29 352	78.42 397	78.37 40	76.54 243	87.75 242	44.36 378	87.28 349	57.04 355	83.49 242	92.37 156

fmvsm_s_conf0.5_n_3		86.36 49	87.46 29	83.09 192	87.08 245	65.21 214	89.09 116	90.21 167	79.67 19	89.98 19	95.02 20	73.17 39	91.71 253	91.30 3	91.60 93	92.34 157

FC-MVSNet-test		81.52 149	82.02 130	80.03 281	88.42 183	55.97 376	87.95 164	93.42 30	77.10 67	77.38 219	90.98 150	69.96 81	91.79 248	68.46 252	84.50 218	92.33 158

Fast-Effi-MVS+		80.81 163	79.92 168	83.47 174	88.85 159	64.51 235	85.53 250	89.39 196	70.79 227	78.49 193	85.06 319	67.54 114	93.58 160	67.03 266	86.58 183	92.32 159

TranMVSNet+NR-MVSNet		80.84 161	80.31 158	82.42 223	87.85 208	62.33 290	87.74 173	91.33 131	80.55 9	77.99 207	89.86 174	65.23 143	92.62 211	67.05 265	75.24 359	92.30 160

ab-mvs		79.51 200	78.97 197	81.14 255	88.46 180	60.91 309	83.84 293	89.24 210	70.36 241	79.03 180	88.87 211	63.23 163	90.21 300	65.12 279	82.57 257	92.28 161

CANet_DTU		80.61 173	79.87 171	82.83 206	85.60 282	63.17 275	87.36 185	88.65 238	76.37 89	75.88 257	88.44 224	53.51 280	93.07 195	73.30 195	89.74 128	92.25 162

UniMVSNet_NR-MVSNet		81.88 137	81.54 136	82.92 202	88.46 180	63.46 266	87.13 191	92.37 82	80.19 12	78.38 196	89.14 199	71.66 60	93.05 197	70.05 233	76.46 332	92.25 162

fmvsm_l_conf0.5_n		84.47 85	84.54 84	84.27 134	85.42 287	68.81 112	88.49 143	87.26 271	68.08 295	88.03 39	93.49 71	72.04 53	91.77 249	88.90 27	89.14 140	92.24 164

DU-MVS		81.12 157	80.52 153	82.90 203	87.80 211	63.46 266	87.02 196	91.87 109	79.01 31	78.38 196	89.07 201	65.02 145	93.05 197	70.05 233	76.46 332	92.20 165

NR-MVSNet		80.23 188	79.38 185	82.78 213	87.80 211	63.34 269	86.31 225	91.09 140	79.01 31	72.17 327	89.07 201	67.20 118	92.81 209	66.08 272	75.65 345	92.20 165

mamba_0408		79.37 209	77.52 236	84.93 104	88.81 163	67.96 145	65.03 449	88.66 236	70.96 224	79.48 173	89.80 178	58.69 230	94.65 114	70.35 229	85.93 197	92.18 167

SSM_04072		77.67 256	77.52 236	78.12 321	88.81 163	67.96 145	65.03 449	88.66 236	70.96 224	79.48 173	89.80 178	58.69 230	74.23 442	70.35 229	85.93 197	92.18 167

SSM_0407		81.58 146	80.48 154	84.87 107	88.81 163	67.96 145	87.37 184	89.25 208	71.06 220	79.48 173	90.39 163	59.57 224	94.48 121	72.45 210	85.93 197	92.18 167

TAPA-MVS	73.13 9	79.15 213	77.94 219	82.79 212	89.59 126	62.99 280	88.16 157	91.51 126	65.77 324	77.14 230	91.09 142	60.91 209	93.21 183	50.26 397	87.05 175	92.17 170
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_l_conf0.5_n_a		84.13 88	84.16 89	84.06 150	85.38 288	68.40 129	88.34 150	86.85 281	67.48 302	87.48 50	93.40 76	70.89 69	91.61 254	88.38 35	89.22 137	92.16 171

3Dnovator	76.31 5	83.38 110	82.31 122	86.59 57	87.94 204	72.94 28	90.64 63	92.14 98	77.21 62	75.47 264	92.83 91	58.56 233	94.72 110	73.24 197	92.71 77	92.13 172

MVS_111021_HR		85.14 77	84.75 82	86.32 61	91.65 81	72.70 30	85.98 234	90.33 162	76.11 94	82.08 130	91.61 124	71.36 64	94.17 133	81.02 104	92.58 78	92.08 173

MVSFormer		82.85 122	82.05 129	85.24 90	87.35 227	70.21 82	90.50 67	90.38 158	68.55 288	81.32 142	89.47 191	61.68 191	93.46 170	78.98 127	90.26 117	92.05 174

jason		81.39 152	80.29 159	84.70 115	86.63 259	69.90 90	85.95 235	86.77 282	63.24 355	81.07 148	89.47 191	61.08 207	92.15 235	78.33 135	90.07 122	92.05 174
jason: jason.
HyFIR lowres test		77.53 258	75.40 278	83.94 162	89.59 126	66.62 182	80.36 350	88.64 239	56.29 419	76.45 244	85.17 316	57.64 241	93.28 176	61.34 315	83.10 250	91.91 176

XVG-OURS-SEG-HR		80.81 163	79.76 174	83.96 161	85.60 282	68.78 114	83.54 304	90.50 154	70.66 233	76.71 237	91.66 119	60.69 212	91.26 275	76.94 151	81.58 267	91.83 177

lupinMVS		81.39 152	80.27 160	84.76 113	87.35 227	70.21 82	85.55 248	86.41 289	62.85 362	81.32 142	88.61 218	61.68 191	92.24 233	78.41 134	90.26 117	91.83 177

WR-MVS		79.49 201	79.22 192	80.27 276	88.79 168	58.35 336	85.06 261	88.61 240	78.56 35	77.65 214	88.34 226	63.81 157	90.66 295	64.98 281	77.22 320	91.80 179

icg_test_0407_2		78.92 221	78.93 198	78.90 304	87.13 239	63.59 259	76.58 396	89.33 198	70.51 236	77.82 209	89.03 203	61.84 187	81.38 401	72.56 206	85.56 204	91.74 180

IMVS_0407		80.61 173	79.90 170	82.75 216	87.13 239	63.59 259	85.33 254	89.33 198	70.51 236	77.82 209	89.03 203	61.84 187	92.91 202	72.56 206	85.56 204	91.74 180

IMVS_0404		77.16 265	76.42 263	79.37 295	87.13 239	63.59 259	77.12 394	89.33 198	70.51 236	66.22 396	89.03 203	50.36 320	82.78 391	72.56 206	85.56 204	91.74 180

IMVS_0403		80.80 166	80.12 165	82.87 205	87.13 239	63.59 259	85.19 255	89.33 198	70.51 236	78.49 193	89.03 203	63.26 161	93.27 178	72.56 206	85.56 204	91.74 180

h-mvs33		83.15 115	82.19 125	86.02 72	90.56 101	70.85 75	88.15 158	89.16 213	76.02 96	84.67 81	91.39 132	61.54 194	95.50 69	82.71 90	75.48 349	91.72 184

UniMVSNet (Re)		81.60 145	81.11 141	83.09 192	88.38 184	64.41 240	87.60 175	93.02 46	78.42 37	78.56 191	88.16 232	69.78 83	93.26 179	69.58 240	76.49 331	91.60 185

UGNet		80.83 162	79.59 181	84.54 118	88.04 199	68.09 140	89.42 99	88.16 244	76.95 70	76.22 250	89.46 193	49.30 335	93.94 141	68.48 251	90.31 115	91.60 185
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		76.54 274	75.66 273	79.18 300	88.43 182	55.89 377	81.08 336	83.00 343	73.76 158	75.34 272	84.29 334	46.20 362	90.07 302	64.33 285	84.50 218	91.58 187

XVG-OURS		80.41 180	79.23 191	83.97 160	85.64 280	69.02 108	83.03 317	90.39 157	71.09 218	77.63 215	91.49 129	54.62 270	91.35 272	75.71 168	83.47 243	91.54 188

LCM-MVSNet-Re		77.05 266	76.94 249	77.36 336	87.20 236	51.60 416	80.06 355	80.46 375	75.20 117	67.69 373	86.72 271	62.48 176	88.98 324	63.44 291	89.25 135	91.51 189

DP-MVS Recon		83.11 118	82.09 128	86.15 66	94.44 19	70.92 73	88.79 128	92.20 92	70.53 235	79.17 179	91.03 146	64.12 153	96.03 51	68.39 253	90.14 119	91.50 190

PS-MVSNAJss		82.07 133	81.31 137	84.34 127	86.51 262	67.27 170	89.27 105	91.51 126	71.75 201	79.37 176	90.22 170	63.15 165	94.27 126	77.69 142	82.36 259	91.49 191

testing99		76.09 286	75.12 285	79.00 301	88.16 191	55.50 383	80.79 340	81.40 363	73.30 174	75.17 280	84.27 337	44.48 377	90.02 303	64.28 286	84.22 227	91.48 192

thisisatest0515		77.33 262	75.38 279	83.18 188	85.27 292	63.80 252	82.11 324	83.27 335	65.06 333	75.91 256	83.84 344	49.54 330	94.27 126	67.24 262	86.19 190	91.48 192

DPM-MVS		84.93 81	84.29 88	86.84 52	90.20 109	73.04 23	87.12 192	93.04 42	69.80 257	82.85 120	91.22 137	73.06 41	96.02 53	76.72 159	94.63 50	91.46 194

HQP_MVS		83.64 101	83.14 106	85.14 92	90.08 112	68.71 119	91.25 55	92.44 78	79.12 28	78.92 183	91.00 148	60.42 219	95.38 78	78.71 130	86.32 187	91.33 195

plane_prior5								92.44 78					95.38 78	78.71 130	86.32 187	91.33 195

GA-MVS		76.87 270	75.17 284	81.97 234	82.75 357	62.58 284	81.44 333	86.35 292	72.16 197	74.74 291	82.89 366	46.20 362	92.02 239	68.85 248	81.09 272	91.30 197

VPA-MVSNet		80.60 175	80.55 152	80.76 265	88.07 198	60.80 311	86.86 204	91.58 124	75.67 104	80.24 163	89.45 195	63.34 158	90.25 299	70.51 227	79.22 298	91.23 198

Effi-MVS+-dtu		80.03 192	78.57 204	84.42 123	85.13 297	68.74 117	88.77 129	88.10 246	74.99 122	74.97 288	83.49 355	57.27 246	93.36 174	73.53 191	80.88 275	91.18 199

v2v482		80.23 188	79.29 189	83.05 196	83.62 332	64.14 244	87.04 194	89.97 174	73.61 162	78.18 202	87.22 259	61.10 206	93.82 150	76.11 162	76.78 328	91.18 199

FE-MVS		77.78 250	75.68 271	84.08 146	88.09 197	66.00 193	83.13 312	87.79 258	68.42 292	78.01 206	85.23 314	45.50 371	95.12 88	59.11 333	85.83 201	91.11 201

Anonymous20231211		78.97 219	77.69 232	82.81 208	90.54 102	64.29 242	90.11 78	91.51 126	65.01 335	76.16 255	88.13 237	50.56 317	93.03 200	69.68 239	77.56 318	91.11 201

hse-mvs2		81.72 140	80.94 145	84.07 147	88.72 171	67.68 155	85.87 238	87.26 271	76.02 96	84.67 81	88.22 231	61.54 194	93.48 168	82.71 90	73.44 377	91.06 203

AUN-MVS		79.21 212	77.60 234	84.05 153	88.71 172	67.61 157	85.84 240	87.26 271	69.08 277	77.23 224	88.14 236	53.20 284	93.47 169	75.50 173	73.45 376	91.06 203

HQP4-MVS										77.24 223			95.11 90			91.03 205

HQP-MVS		82.61 125	82.02 130	84.37 124	89.33 140	66.98 177	89.17 109	92.19 93	76.41 85	77.23 224	90.23 169	60.17 222	95.11 90	77.47 144	85.99 195	91.03 205

RPSCF		73.23 325	71.46 329	78.54 312	82.50 363	59.85 323	82.18 323	82.84 348	58.96 398	71.15 339	89.41 197	45.48 372	84.77 376	58.82 337	71.83 389	91.02 207

LuminaMVS		80.68 171	79.62 180	83.83 164	85.07 299	68.01 144	86.99 197	88.83 227	70.36 241	81.38 141	87.99 239	50.11 323	92.51 220	79.02 124	86.89 179	90.97 208

test_djsdf		80.30 187	79.32 188	83.27 183	83.98 322	65.37 212	90.50 67	90.38 158	68.55 288	76.19 251	88.70 214	56.44 255	93.46 170	78.98 127	80.14 287	90.97 208

PCF-MVS	73.52 7	80.38 182	78.84 200	85.01 99	87.71 218	68.99 109	83.65 298	91.46 130	63.00 359	77.77 213	90.28 166	66.10 133	95.09 94	61.40 313	88.22 156	90.94 210
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VPNet		78.69 226	78.66 202	78.76 306	88.31 186	55.72 380	84.45 279	86.63 286	76.79 75	78.26 199	90.55 160	59.30 227	89.70 310	66.63 267	77.05 322	90.88 211

CPTT-MVS		83.73 97	83.33 105	84.92 105	93.28 49	70.86 74	92.09 37	90.38 158	68.75 285	79.57 171	92.83 91	60.60 217	93.04 199	80.92 106	91.56 96	90.86 212

fmvsm_s_conf0.5_n_7		83.34 111	84.03 91	81.28 250	85.73 278	65.13 217	85.40 253	89.90 177	74.96 125	82.13 129	93.89 63	66.65 122	87.92 340	86.56 48	91.05 103	90.80 213

tt0805		78.73 224	77.83 224	81.43 244	85.17 293	60.30 319	89.41 100	90.90 143	71.21 215	77.17 229	88.73 213	46.38 357	93.21 183	72.57 204	78.96 299	90.79 214

CLD-MVS		82.31 129	81.65 135	84.29 131	88.47 179	67.73 154	85.81 242	92.35 83	75.78 99	78.33 198	86.58 281	64.01 154	94.35 123	76.05 164	87.48 167	90.79 214
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
v1192		79.59 199	78.43 208	83.07 195	83.55 334	64.52 234	86.93 201	90.58 151	70.83 226	77.78 212	85.90 295	59.15 228	93.94 141	73.96 188	77.19 321	90.76 216

IterMVS-LS		80.06 191	79.38 185	82.11 230	85.89 274	63.20 273	86.79 207	89.34 197	74.19 147	75.45 267	86.72 271	66.62 123	92.39 225	72.58 203	76.86 325	90.75 217
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
myMVS_eth3d28		73.62 316	73.53 306	73.90 375	88.20 189	47.41 435	78.06 385	79.37 389	74.29 145	73.98 302	84.29 334	44.67 374	83.54 385	51.47 387	87.39 168	90.74 218

EI-MVSNet		80.52 179	79.98 167	82.12 228	84.28 314	63.19 274	86.41 221	88.95 225	74.18 148	78.69 186	87.54 251	66.62 123	92.43 223	72.57 204	80.57 281	90.74 218

v1921920		79.22 211	78.03 217	82.80 209	83.30 339	63.94 249	86.80 206	90.33 162	69.91 255	77.48 217	85.53 306	58.44 234	93.75 156	73.60 190	76.85 326	90.71 220

QAPM		80.88 160	79.50 183	85.03 98	88.01 202	68.97 110	91.59 46	92.00 101	66.63 315	75.15 282	92.16 105	57.70 240	95.45 71	63.52 289	88.76 146	90.66 221

v144192		79.47 202	78.37 209	82.78 213	83.35 337	63.96 247	86.96 198	90.36 161	69.99 252	77.50 216	85.67 302	60.66 214	93.77 154	74.27 185	76.58 329	90.62 222

v1240		78.99 218	77.78 227	82.64 218	83.21 342	63.54 263	86.62 215	90.30 164	69.74 262	77.33 220	85.68 301	57.04 249	93.76 155	73.13 198	76.92 323	90.62 222

v1144		80.03 192	79.03 195	83.01 198	83.78 327	64.51 235	87.11 193	90.57 153	71.96 200	78.08 205	86.20 291	61.41 198	93.94 141	74.93 178	77.23 319	90.60 224

1112_ss		77.40 261	76.43 262	80.32 275	89.11 156	60.41 318	83.65 298	87.72 261	62.13 372	73.05 314	86.72 271	62.58 175	89.97 304	62.11 307	80.80 277	90.59 225

CP-MVSNet		78.22 236	78.34 210	77.84 327	87.83 210	54.54 393	87.94 165	91.17 136	77.65 46	73.48 309	88.49 222	62.24 182	88.43 334	62.19 304	74.07 368	90.55 226

testing222		74.04 311	72.66 317	78.19 319	87.89 206	55.36 384	81.06 337	79.20 392	71.30 213	74.65 294	83.57 354	39.11 411	88.67 331	51.43 389	85.75 202	90.53 227

PS-CasMVS		78.01 245	78.09 216	77.77 329	87.71 218	54.39 395	88.02 161	91.22 133	77.50 54	73.26 311	88.64 217	60.73 210	88.41 335	61.88 308	73.88 372	90.53 227

CDS-MVSNet		79.07 216	77.70 231	83.17 189	87.60 222	68.23 137	84.40 282	86.20 294	67.49 301	76.36 247	86.54 283	61.54 194	90.79 290	61.86 309	87.33 169	90.49 229
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		78.89 222	77.51 238	83.03 197	87.80 211	67.79 153	84.72 268	85.05 310	67.63 298	76.75 236	87.70 244	62.25 181	90.82 289	58.53 340	87.13 174	90.49 229

PEN-MVS		77.73 251	77.69 232	77.84 327	87.07 247	53.91 398	87.91 167	91.18 135	77.56 51	73.14 313	88.82 212	61.23 203	89.17 320	59.95 324	72.37 383	90.43 231

Test_1112_low_res		76.40 281	75.44 276	79.27 297	89.28 145	58.09 339	81.69 328	87.07 275	59.53 393	72.48 322	86.67 276	61.30 201	89.33 315	60.81 319	80.15 286	90.41 232

HY-MVS	69.67 12	77.95 246	77.15 244	80.36 273	87.57 226	60.21 321	83.37 307	87.78 259	66.11 319	75.37 271	87.06 266	63.27 160	90.48 297	61.38 314	82.43 258	90.40 233

sc_t1		72.19 337	69.51 348	80.23 277	84.81 303	61.09 306	84.68 269	80.22 381	60.70 382	71.27 336	83.58 353	36.59 422	89.24 318	60.41 320	63.31 421	90.37 234

CHOSEN 1792x2688		77.63 257	75.69 270	83.44 176	89.98 118	68.58 125	78.70 375	87.50 265	56.38 418	75.80 259	86.84 267	58.67 232	91.40 271	61.58 312	85.75 202	90.34 235

SDMVSNet		80.38 182	80.18 161	80.99 259	89.03 157	64.94 224	80.45 349	89.40 195	75.19 118	76.61 241	89.98 172	60.61 216	87.69 344	76.83 155	83.55 240	90.33 236

sd_testset		77.70 254	77.40 239	78.60 309	89.03 157	60.02 322	79.00 370	85.83 300	75.19 118	76.61 241	89.98 172	54.81 263	85.46 369	62.63 300	83.55 240	90.33 236

114514_t		80.68 171	79.51 182	84.20 138	94.09 38	67.27 170	89.64 90	91.11 139	58.75 402	74.08 301	90.72 153	58.10 236	95.04 95	69.70 238	89.42 134	90.30 238

eth_miper_zixun_eth		77.92 247	76.69 257	81.61 241	83.00 350	61.98 295	83.15 311	89.20 212	69.52 264	74.86 290	84.35 333	61.76 190	92.56 216	71.50 217	72.89 381	90.28 239

PVSNet_Blended_VisFu		82.62 124	81.83 134	84.96 101	90.80 97	69.76 93	88.74 133	91.70 118	69.39 265	78.96 181	88.46 223	65.47 141	94.87 103	74.42 183	88.57 149	90.24 240

MVS_111021_LR		82.61 125	82.11 126	84.11 140	88.82 162	71.58 57	85.15 258	86.16 295	74.69 133	80.47 161	91.04 144	62.29 180	90.55 296	80.33 114	90.08 121	90.20 241

MSLP-MVS++		85.43 70	85.76 64	84.45 122	91.93 77	70.24 81	90.71 62	92.86 59	77.46 55	84.22 94	92.81 93	67.16 119	92.94 201	80.36 113	94.35 59	90.16 242

mvs_tets		79.13 214	77.77 228	83.22 187	84.70 306	66.37 186	89.17 109	90.19 168	69.38 266	75.40 269	89.46 193	44.17 380	93.15 190	76.78 158	80.70 279	90.14 243

BH-RMVSNet		79.61 197	78.44 207	83.14 190	89.38 139	65.93 195	84.95 264	87.15 274	73.56 164	78.19 201	89.79 180	56.67 253	93.36 174	59.53 329	86.74 181	90.13 244

c3_l		78.75 223	77.91 220	81.26 251	82.89 355	61.56 301	84.09 290	89.13 216	69.97 253	75.56 262	84.29 334	66.36 128	92.09 237	73.47 193	75.48 349	90.12 245

v7n		78.97 219	77.58 235	83.14 190	83.45 336	65.51 207	88.32 151	91.21 134	73.69 160	72.41 323	86.32 289	57.93 237	93.81 151	69.18 243	75.65 345	90.11 246

jajsoiax		79.29 210	77.96 218	83.27 183	84.68 307	66.57 184	89.25 106	90.16 169	69.20 274	75.46 266	89.49 190	45.75 368	93.13 192	76.84 154	80.80 277	90.11 246

v148		78.72 225	77.80 226	81.47 243	82.73 358	61.96 296	86.30 226	88.08 247	73.26 175	76.18 252	85.47 308	62.46 177	92.36 227	71.92 214	73.82 373	90.09 248

GBi-Net		78.40 232	77.40 239	81.40 246	87.60 222	63.01 276	88.39 146	89.28 204	71.63 203	75.34 272	87.28 255	54.80 264	91.11 279	62.72 296	79.57 291	90.09 248

test1		78.40 232	77.40 239	81.40 246	87.60 222	63.01 276	88.39 146	89.28 204	71.63 203	75.34 272	87.28 255	54.80 264	91.11 279	62.72 296	79.57 291	90.09 248

FMVSNet1		77.44 259	76.12 267	81.40 246	86.81 252	63.01 276	88.39 146	89.28 204	70.49 240	74.39 298	87.28 255	49.06 339	91.11 279	60.91 317	78.52 302	90.09 248

WR-MVS_H		78.51 231	78.49 205	78.56 311	88.02 200	56.38 370	88.43 144	92.67 68	77.14 64	73.89 303	87.55 250	66.25 130	89.24 318	58.92 335	73.55 375	90.06 252

DTE-MVSNet		76.99 267	76.80 252	77.54 335	86.24 265	53.06 407	87.52 177	90.66 149	77.08 68	72.50 321	88.67 216	60.48 218	89.52 312	57.33 352	70.74 395	90.05 253

v8		79.97 194	79.02 196	82.80 209	84.09 319	64.50 237	87.96 163	90.29 165	74.13 150	75.24 279	86.81 268	62.88 172	93.89 149	74.39 184	75.40 354	90.00 254

thres600view7		76.50 276	75.44 276	79.68 289	89.40 137	57.16 356	85.53 250	83.23 336	73.79 157	76.26 249	87.09 264	51.89 301	91.89 245	48.05 412	83.72 237	90.00 254

thres400		76.50 276	75.37 280	79.86 284	89.13 152	57.65 350	85.17 256	83.60 328	73.41 170	76.45 244	86.39 287	52.12 293	91.95 242	48.33 407	83.75 234	90.00 254

cl22		78.07 242	77.01 246	81.23 252	82.37 367	61.83 298	83.55 302	87.98 251	68.96 282	75.06 285	83.87 342	61.40 199	91.88 246	73.53 191	76.39 334	89.98 257

OPM-MVS		83.50 106	82.95 111	85.14 92	88.79 168	70.95 71	89.13 114	91.52 125	77.55 52	80.96 150	91.75 116	60.71 211	94.50 119	79.67 121	86.51 185	89.97 258
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		75.70 290	73.83 303	81.30 249	83.26 340	61.79 299	82.57 320	80.65 370	66.81 306	66.88 384	83.42 356	57.86 239	92.19 234	63.47 290	79.57 291	89.91 259

v10		79.74 196	78.67 201	82.97 201	84.06 320	64.95 223	87.88 169	90.62 150	73.11 180	75.11 283	86.56 282	61.46 197	94.05 137	73.68 189	75.55 347	89.90 260

MVSTER		79.01 217	77.88 223	82.38 224	83.07 347	64.80 229	84.08 291	88.95 225	69.01 281	78.69 186	87.17 262	54.70 268	92.43 223	74.69 179	80.57 281	89.89 261

ACMP	74.13 6	81.51 151	80.57 151	84.36 125	89.42 135	68.69 122	89.97 80	91.50 129	74.46 139	75.04 286	90.41 162	53.82 277	94.54 116	77.56 143	82.91 251	89.86 262
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LPG-MVS_test		82.08 132	81.27 138	84.50 119	89.23 148	68.76 115	90.22 76	91.94 105	75.37 112	76.64 239	91.51 127	54.29 271	94.91 98	78.44 132	83.78 231	89.83 263

LGP-MVS_train				84.50 119	89.23 148	68.76 115		91.94 105	75.37 112	76.64 239	91.51 127	54.29 271	94.91 98	78.44 132	83.78 231	89.83 263

V42		79.38 208	78.24 213	82.83 206	81.10 386	65.50 208	85.55 248	89.82 178	71.57 207	78.21 200	86.12 293	60.66 214	93.18 189	75.64 169	75.46 351	89.81 265

MAR-MVS		81.84 138	80.70 148	85.27 89	91.32 85	71.53 58	89.82 82	90.92 142	69.77 259	78.50 192	86.21 290	62.36 179	94.52 118	65.36 277	92.05 87	89.77 266
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		77.72 252	76.76 254	80.58 269	82.48 365	60.48 316	83.09 313	87.86 256	69.22 272	74.38 299	85.24 313	62.10 184	91.53 264	71.09 220	75.40 354	89.74 267

cl____		77.72 252	76.76 254	80.58 269	82.49 364	60.48 316	83.09 313	87.87 255	69.22 272	74.38 299	85.22 315	62.10 184	91.53 264	71.09 220	75.41 353	89.73 268

miper_ehance_all_eth		78.59 229	77.76 229	81.08 257	82.66 360	61.56 301	83.65 298	89.15 214	68.87 283	75.55 263	83.79 346	66.49 126	92.03 238	73.25 196	76.39 334	89.64 269

anonymousdsp		78.60 228	77.15 244	82.98 200	80.51 392	67.08 175	87.24 190	89.53 191	65.66 326	75.16 281	87.19 261	52.52 286	92.25 232	77.17 148	79.34 296	89.61 270

FMVSNet2		78.20 238	77.21 243	81.20 253	87.60 222	62.89 282	87.47 179	89.02 220	71.63 203	75.29 278	87.28 255	54.80 264	91.10 282	62.38 301	79.38 295	89.61 270

baseline1		76.98 268	76.75 256	77.66 330	88.13 194	55.66 381	85.12 259	81.89 356	73.04 182	76.79 234	88.90 209	62.43 178	87.78 343	63.30 293	71.18 393	89.55 272

ETVMVS		72.25 336	71.05 335	75.84 348	87.77 215	51.91 412	79.39 363	74.98 418	69.26 270	73.71 305	82.95 364	40.82 403	86.14 359	46.17 420	84.43 223	89.47 273

FMVSNet3		77.88 248	76.85 251	80.97 261	86.84 251	62.36 289	86.52 218	88.77 230	71.13 216	75.34 272	86.66 277	54.07 274	91.10 282	62.72 296	79.57 291	89.45 274

SD_0403		74.65 304	74.77 288	74.29 370	86.20 267	47.42 434	83.71 296	85.12 307	69.30 268	68.50 368	87.95 240	59.40 226	86.05 360	49.38 401	83.35 245	89.40 275

miper_enhance_ethall		77.87 249	76.86 250	80.92 262	81.65 374	61.38 303	82.68 318	88.98 222	65.52 328	75.47 264	82.30 375	65.76 140	92.00 240	72.95 199	76.39 334	89.39 276

testing11		75.14 300	74.01 298	78.53 313	88.16 191	56.38 370	80.74 343	80.42 377	70.67 230	72.69 320	83.72 349	43.61 384	89.86 305	62.29 303	83.76 233	89.36 277

cascas		76.72 273	74.64 289	82.99 199	85.78 277	65.88 197	82.33 321	89.21 211	60.85 381	72.74 317	81.02 386	47.28 348	93.75 156	67.48 259	85.02 210	89.34 278

Fast-Effi-MVS+-dtu		78.02 244	76.49 260	82.62 219	83.16 346	66.96 179	86.94 200	87.45 267	72.45 189	71.49 335	84.17 339	54.79 267	91.58 256	67.61 257	80.31 284	89.30 279

IB-MVS	68.01 15	75.85 289	73.36 309	83.31 181	84.76 305	66.03 190	83.38 306	85.06 309	70.21 248	69.40 358	81.05 385	45.76 367	94.66 113	65.10 280	75.49 348	89.25 280
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		76.50 276	75.55 275	79.33 296	89.52 129	56.99 359	85.83 241	83.23 336	73.94 153	76.32 248	87.12 263	51.89 301	91.95 242	48.33 407	83.75 234	89.07 281

tfpn200view9		76.42 280	75.37 280	79.55 294	89.13 152	57.65 350	85.17 256	83.60 328	73.41 170	76.45 244	86.39 287	52.12 293	91.95 242	48.33 407	83.75 234	89.07 281

xiu_mvs_v1_base_debu		80.80 166	79.72 177	84.03 155	87.35 227	70.19 84	85.56 245	88.77 230	69.06 278	81.83 132	88.16 232	50.91 312	92.85 205	78.29 136	87.56 164	89.06 283

xiu_mvs_v1_base		80.80 166	79.72 177	84.03 155	87.35 227	70.19 84	85.56 245	88.77 230	69.06 278	81.83 132	88.16 232	50.91 312	92.85 205	78.29 136	87.56 164	89.06 283

xiu_mvs_v1_base_debi		80.80 166	79.72 177	84.03 155	87.35 227	70.19 84	85.56 245	88.77 230	69.06 278	81.83 132	88.16 232	50.91 312	92.85 205	78.29 136	87.56 164	89.06 283

EPNet_dtu		75.46 294	74.86 286	77.23 339	82.57 362	54.60 392	86.89 202	83.09 340	71.64 202	66.25 395	85.86 297	55.99 256	88.04 339	54.92 369	86.55 184	89.05 286
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pm-mvs1		77.25 264	76.68 258	78.93 303	84.22 316	58.62 334	86.41 221	88.36 243	71.37 210	73.31 310	88.01 238	61.22 204	89.15 321	64.24 287	73.01 380	89.03 287

PVSNet_Blended		80.98 158	80.34 157	82.90 203	88.85 159	65.40 209	84.43 280	92.00 101	67.62 299	78.11 203	85.05 320	66.02 136	94.27 126	71.52 215	89.50 132	89.01 288

PAPM		77.68 255	76.40 264	81.51 242	87.29 235	61.85 297	83.78 294	89.59 189	64.74 337	71.23 337	88.70 214	62.59 174	93.66 159	52.66 381	87.03 176	89.01 288

WTY-MVS		75.65 291	75.68 271	75.57 352	86.40 263	56.82 361	77.92 388	82.40 351	65.10 332	76.18 252	87.72 243	63.13 168	80.90 404	60.31 322	81.96 263	89.00 290

无先验							87.48 178	88.98 222	60.00 388				94.12 134	67.28 261		88.97 291

GSMVS																88.96 292

sam_mvs1												51.32 308				88.96 292

SCA		74.22 308	72.33 321	79.91 283	84.05 321	62.17 293	79.96 358	79.29 391	66.30 318	72.38 324	80.13 398	51.95 299	88.60 332	59.25 331	77.67 317	88.96 292

miper_lstm_enhance		74.11 310	73.11 312	77.13 340	80.11 396	59.62 326	72.23 420	86.92 280	66.76 308	70.40 343	82.92 365	56.93 250	82.92 390	69.06 245	72.63 382	88.87 295

ACMM	73.20 8	80.78 170	79.84 172	83.58 172	89.31 143	68.37 130	89.99 79	91.60 123	70.28 245	77.25 222	89.66 184	53.37 282	93.53 165	74.24 186	82.85 252	88.85 296
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs6		74.69 303	73.39 307	78.61 308	81.38 381	57.48 353	86.64 214	87.95 253	64.99 336	70.18 346	86.61 278	50.43 319	89.52 312	62.12 306	70.18 398	88.83 297

原ACMM1				84.35 126	93.01 62	68.79 113		92.44 78	63.96 351	81.09 147	91.57 125	66.06 135	95.45 71	67.19 263	94.82 46	88.81 298

CNLPA		78.08 241	76.79 253	81.97 234	90.40 105	71.07 67	87.59 176	84.55 315	66.03 322	72.38 324	89.64 185	57.56 242	86.04 361	59.61 328	83.35 245	88.79 299

UWE-MVS		72.13 338	71.49 328	74.03 373	86.66 258	47.70 432	81.40 334	76.89 411	63.60 354	75.59 261	84.22 338	39.94 406	85.62 366	48.98 404	86.13 192	88.77 300

UBG		73.08 327	72.27 322	75.51 354	88.02 200	51.29 420	78.35 382	77.38 406	65.52 328	73.87 304	82.36 373	45.55 369	86.48 356	55.02 368	84.39 224	88.75 301

K. test v3		71.19 343	68.51 355	79.21 299	83.04 349	57.78 349	84.35 283	76.91 410	72.90 185	62.99 416	82.86 367	39.27 408	91.09 284	61.65 311	52.66 443	88.75 301

旧先验1					91.96 76	65.79 201		86.37 291			93.08 86	69.31 90			92.74 76	88.74 303

PatchmatchNet		73.12 326	71.33 332	78.49 315	83.18 344	60.85 310	79.63 360	78.57 396	64.13 344	71.73 331	79.81 403	51.20 310	85.97 362	57.40 351	76.36 339	88.66 304
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SixPastTwentyTwo		73.37 320	71.26 334	79.70 288	85.08 298	57.89 345	85.57 244	83.56 330	71.03 222	65.66 398	85.88 296	42.10 394	92.57 215	59.11 333	63.34 420	88.65 305

SSC-MVS3.2		73.35 323	73.39 307	73.23 379	85.30 291	49.01 430	74.58 413	81.57 360	75.21 116	73.68 306	85.58 305	52.53 285	82.05 396	54.33 373	77.69 316	88.63 306

PS-MVSNAJ		81.69 142	81.02 143	83.70 168	89.51 130	68.21 138	84.28 284	90.09 171	70.79 227	81.26 146	85.62 304	63.15 165	94.29 124	75.62 170	88.87 143	88.59 307

xiu_mvs_v2_base		81.69 142	81.05 142	83.60 170	89.15 151	68.03 143	84.46 278	90.02 172	70.67 230	81.30 145	86.53 284	63.17 164	94.19 132	75.60 171	88.54 150	88.57 308

MonoMVSNet		76.49 279	75.80 268	78.58 310	81.55 377	58.45 335	86.36 224	86.22 293	74.87 130	74.73 292	83.73 348	51.79 304	88.73 329	70.78 222	72.15 386	88.55 309

CostFormer		75.24 299	73.90 301	79.27 297	82.65 361	58.27 338	80.80 339	82.73 349	61.57 376	75.33 276	83.13 361	55.52 259	91.07 285	64.98 281	78.34 309	88.45 310

lessismore_v0				78.97 302	81.01 387	57.15 357		65.99 445		61.16 422	82.82 368	39.12 410	91.34 273	59.67 327	46.92 450	88.43 311

OpenMVS	72.83 10	79.77 195	78.33 211	84.09 145	85.17 293	69.91 89	90.57 64	90.97 141	66.70 309	72.17 327	91.91 110	54.70 268	93.96 138	61.81 310	90.95 106	88.41 312

reproduce_monomvs		75.40 297	74.38 295	78.46 316	83.92 324	57.80 348	83.78 294	86.94 278	73.47 168	72.25 326	84.47 328	38.74 412	89.27 317	75.32 175	70.53 396	88.31 313

VortexMVS		78.57 230	77.89 222	80.59 268	85.89 274	62.76 283	85.61 243	89.62 188	72.06 198	74.99 287	85.38 310	55.94 257	90.77 293	74.99 177	76.58 329	88.23 314

OurMVSNet-221017-0		74.26 307	72.42 320	79.80 286	83.76 328	59.59 327	85.92 237	86.64 285	66.39 317	66.96 383	87.58 247	39.46 407	91.60 255	65.76 275	69.27 401	88.22 315

LS3D		76.95 269	74.82 287	83.37 180	90.45 103	67.36 167	89.15 113	86.94 278	61.87 375	69.52 357	90.61 158	51.71 305	94.53 117	46.38 419	86.71 182	88.21 316

WBMVS		73.43 319	72.81 315	75.28 358	87.91 205	50.99 422	78.59 378	81.31 365	65.51 330	74.47 297	84.83 323	46.39 356	86.68 353	58.41 341	77.86 312	88.17 317

XVG-ACMP-BASELINE		76.11 285	74.27 297	81.62 239	83.20 343	64.67 231	83.60 301	89.75 183	69.75 260	71.85 330	87.09 264	32.78 431	92.11 236	69.99 235	80.43 283	88.09 318

tpm2		73.26 324	71.46 329	78.63 307	83.34 338	56.71 364	80.65 345	80.40 378	56.63 417	73.55 308	82.02 380	51.80 303	91.24 276	56.35 363	78.42 307	87.95 319

MDTV_nov1_ep13_2view						37.79 459	75.16 407		55.10 422	66.53 390		49.34 334		53.98 374		87.94 320

Patchmatch-test		64.82 396	63.24 397	69.57 406	79.42 408	49.82 428	63.49 453	69.05 438	51.98 432	59.95 428	80.13 398	50.91 312	70.98 447	40.66 437	73.57 374	87.90 321

PLC	70.83 11	78.05 243	76.37 265	83.08 194	91.88 79	67.80 152	88.19 155	89.46 193	64.33 343	69.87 354	88.38 225	53.66 278	93.58 160	58.86 336	82.73 254	87.86 322
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		72.37 334	71.71 326	74.35 369	82.19 368	52.00 410	79.22 366	77.29 407	64.56 339	72.95 316	83.68 351	51.35 307	83.26 389	58.33 343	75.80 343	87.81 323

Patchmatch-RL test		70.24 356	67.78 369	77.61 332	77.43 417	59.57 328	71.16 424	70.33 432	62.94 361	68.65 365	72.77 438	50.62 316	85.49 368	69.58 240	66.58 411	87.77 324

F-COLMAP		76.38 282	74.33 296	82.50 222	89.28 145	66.95 180	88.41 145	89.03 219	64.05 348	66.83 385	88.61 218	46.78 354	92.89 203	57.48 349	78.55 301	87.67 325

Baseline_NR-MVSNet		78.15 240	78.33 211	77.61 332	85.79 276	56.21 374	86.78 208	85.76 301	73.60 163	77.93 208	87.57 248	65.02 145	88.99 323	67.14 264	75.33 356	87.63 326

CL-MVSNet_self_test		72.37 334	71.46 329	75.09 360	79.49 407	53.53 400	80.76 342	85.01 311	69.12 276	70.51 341	82.05 379	57.92 238	84.13 380	52.27 383	66.00 414	87.60 327

ACMH+	68.96 14	76.01 287	74.01 298	82.03 232	88.60 175	65.31 213	88.86 123	87.55 263	70.25 247	67.75 372	87.47 253	41.27 399	93.19 188	58.37 342	75.94 342	87.60 327

1314		76.53 275	75.30 282	80.21 278	83.93 323	62.32 291	84.66 270	88.81 228	60.23 386	70.16 348	84.07 341	55.30 261	90.73 294	67.37 260	83.21 248	87.59 329

API-MVS		81.99 135	81.23 139	84.26 136	90.94 93	70.18 87	91.10 58	89.32 202	71.51 208	78.66 188	88.28 228	65.26 142	95.10 93	64.74 283	91.23 101	87.51 330

AdaColmap		80.58 178	79.42 184	84.06 150	93.09 59	68.91 111	89.36 103	88.97 224	69.27 269	75.70 260	89.69 182	57.20 248	95.77 60	63.06 294	88.41 154	87.50 331

PVSNet_BlendedMVS		80.60 175	80.02 166	82.36 225	88.85 159	65.40 209	86.16 231	92.00 101	69.34 267	78.11 203	86.09 294	66.02 136	94.27 126	71.52 215	82.06 262	87.39 332

sss		73.60 317	73.64 305	73.51 378	82.80 356	55.01 389	76.12 398	81.69 359	62.47 368	74.68 293	85.85 298	57.32 245	78.11 415	60.86 318	80.93 273	87.39 332

IterMVS-SCA-FT		75.43 295	73.87 302	80.11 280	82.69 359	64.85 228	81.57 330	83.47 332	69.16 275	70.49 342	84.15 340	51.95 299	88.15 337	69.23 242	72.14 387	87.34 334

PVSNet	64.34 18	72.08 339	70.87 338	75.69 350	86.21 266	56.44 368	74.37 414	80.73 369	62.06 373	70.17 347	82.23 377	42.86 388	83.31 388	54.77 370	84.45 222	87.32 335

tt0320-xc		70.11 358	67.45 375	78.07 323	85.33 290	59.51 329	83.28 308	78.96 394	58.77 400	67.10 382	80.28 396	36.73 421	87.42 347	56.83 359	59.77 432	87.29 336

新几何1				83.42 177	93.13 56	70.71 76		85.48 304	57.43 413	81.80 135	91.98 109	63.28 159	92.27 231	64.60 284	92.99 72	87.27 337

TR-MVS		77.44 259	76.18 266	81.20 253	88.24 188	63.24 271	84.61 273	86.40 290	67.55 300	77.81 211	86.48 285	54.10 273	93.15 190	57.75 348	82.72 255	87.20 338

TransMVSNet (Re)		75.39 298	74.56 291	77.86 326	85.50 286	57.10 358	86.78 208	86.09 297	72.17 196	71.53 334	87.34 254	63.01 169	89.31 316	56.84 358	61.83 425	87.17 339

ACMH	67.68 16	75.89 288	73.93 300	81.77 237	88.71 172	66.61 183	88.62 138	89.01 221	69.81 256	66.78 386	86.70 275	41.95 396	91.51 266	55.64 365	78.14 310	87.17 339
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
KD-MVS_self_test		68.81 368	67.59 373	72.46 390	74.29 431	45.45 440	77.93 387	87.00 276	63.12 356	63.99 411	78.99 412	42.32 391	84.77 376	56.55 362	64.09 419	87.16 341

EPMVS		69.02 367	68.16 359	71.59 394	79.61 405	49.80 429	77.40 391	66.93 443	62.82 364	70.01 349	79.05 408	45.79 366	77.86 417	56.58 361	75.26 358	87.13 342

CR-MVSNet		73.37 320	71.27 333	79.67 290	81.32 384	65.19 215	75.92 400	80.30 379	59.92 389	72.73 318	81.19 383	52.50 287	86.69 352	59.84 325	77.71 314	87.11 343

RPMNet		73.51 318	70.49 341	82.58 221	81.32 384	65.19 215	75.92 400	92.27 85	57.60 411	72.73 318	76.45 426	52.30 290	95.43 73	48.14 411	77.71 314	87.11 343

test_vis1_n_1920		75.52 293	75.78 269	74.75 366	79.84 400	57.44 354	83.26 309	85.52 303	62.83 363	79.34 178	86.17 292	45.10 373	79.71 408	78.75 129	81.21 271	87.10 345

tt0320		70.49 354	68.03 362	77.89 325	84.78 304	59.12 331	83.55 302	80.44 376	58.13 406	67.43 378	80.41 394	39.26 409	87.54 346	55.12 367	63.18 422	86.99 346

XXY-MVS		75.41 296	75.56 274	74.96 361	83.59 333	57.82 347	80.59 346	83.87 326	66.54 316	74.93 289	88.31 227	63.24 162	80.09 407	62.16 305	76.85 326	86.97 347

tpmrst		72.39 332	72.13 323	73.18 383	80.54 391	49.91 427	79.91 359	79.08 393	63.11 357	71.69 332	79.95 400	55.32 260	82.77 392	65.66 276	73.89 371	86.87 348

thres200		75.55 292	74.47 293	78.82 305	87.78 214	57.85 346	83.07 315	83.51 331	72.44 191	75.84 258	84.42 329	52.08 296	91.75 250	47.41 414	83.64 239	86.86 349

ITE_SJBPF				78.22 318	81.77 373	60.57 314		83.30 334	69.25 271	67.54 374	87.20 260	36.33 424	87.28 349	54.34 372	74.62 365	86.80 350

test222					91.50 82	68.26 133	84.16 288	83.20 339	54.63 424	79.74 168	91.63 122	58.97 229			91.42 97	86.77 351

MIMVSNet		70.69 350	69.30 349	74.88 363	84.52 311	56.35 372	75.87 402	79.42 388	64.59 338	67.76 371	82.41 372	41.10 400	81.54 399	46.64 418	81.34 268	86.75 352

BH-untuned		79.47 202	78.60 203	82.05 231	89.19 150	65.91 196	86.07 233	88.52 241	72.18 195	75.42 268	87.69 245	61.15 205	93.54 164	60.38 321	86.83 180	86.70 353

LTVRE_ROB	69.57 13	76.25 283	74.54 292	81.41 245	88.60 175	64.38 241	79.24 365	89.12 217	70.76 229	69.79 356	87.86 241	49.09 338	93.20 186	56.21 364	80.16 285	86.65 354
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				79.97 282	90.90 94	64.21 243		84.71 312	59.27 395	85.40 69	92.91 88	62.02 186	89.08 322	68.95 246	91.37 99	86.63 355

MIMVSNet1		68.58 371	66.78 381	73.98 374	80.07 397	51.82 414	80.77 341	84.37 316	64.40 341	59.75 429	82.16 378	36.47 423	83.63 384	42.73 432	70.33 397	86.48 356

tfpnnormal		74.39 305	73.16 311	78.08 322	86.10 272	58.05 340	84.65 272	87.53 264	70.32 244	71.22 338	85.63 303	54.97 262	89.86 305	43.03 431	75.02 361	86.32 357

D2MVS		74.82 302	73.21 310	79.64 291	79.81 401	62.56 285	80.34 351	87.35 268	64.37 342	68.86 363	82.66 370	46.37 358	90.10 301	67.91 255	81.24 270	86.25 358

tpm cat1		70.57 351	68.31 357	77.35 337	82.41 366	57.95 344	78.08 384	80.22 381	52.04 430	68.54 367	77.66 421	52.00 298	87.84 342	51.77 384	72.07 388	86.25 358

CVMVSNet		72.99 329	72.58 318	74.25 371	84.28 314	50.85 423	86.41 221	83.45 333	44.56 443	73.23 312	87.54 251	49.38 333	85.70 364	65.90 273	78.44 304	86.19 360

AllTest		70.96 346	68.09 361	79.58 292	85.15 295	63.62 255	84.58 274	79.83 384	62.31 369	60.32 426	86.73 269	32.02 432	88.96 326	50.28 395	71.57 391	86.15 361

TestCases				79.58 292	85.15 295	63.62 255		79.83 384	62.31 369	60.32 426	86.73 269	32.02 432	88.96 326	50.28 395	71.57 391	86.15 361

test-LLR		72.94 330	72.43 319	74.48 367	81.35 382	58.04 341	78.38 379	77.46 403	66.66 310	69.95 352	79.00 410	48.06 344	79.24 409	66.13 269	84.83 213	86.15 361

test-mter		71.41 342	70.39 344	74.48 367	81.35 382	58.04 341	78.38 379	77.46 403	60.32 385	69.95 352	79.00 410	36.08 425	79.24 409	66.13 269	84.83 213	86.15 361

IterMVS		74.29 306	72.94 314	78.35 317	81.53 378	63.49 265	81.58 329	82.49 350	68.06 296	69.99 351	83.69 350	51.66 306	85.54 367	65.85 274	71.64 390	86.01 365
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		76.78 272	74.57 290	83.42 177	93.29 48	69.46 100	88.55 142	83.70 327	63.98 350	70.20 345	88.89 210	54.01 276	94.80 107	46.66 416	81.88 265	86.01 365

ppachtmachnet_test		70.04 359	67.34 377	78.14 320	79.80 402	61.13 304	79.19 367	80.59 371	59.16 396	65.27 401	79.29 407	46.75 355	87.29 348	49.33 402	66.72 409	86.00 367

mmtdpeth		74.16 309	73.01 313	77.60 334	83.72 329	61.13 304	85.10 260	85.10 308	72.06 198	77.21 228	80.33 395	43.84 382	85.75 363	77.14 149	52.61 444	85.91 368

test_fmvs1_n		70.86 348	70.24 345	72.73 387	72.51 445	55.28 386	81.27 335	79.71 386	51.49 434	78.73 185	84.87 322	27.54 441	77.02 420	76.06 163	79.97 289	85.88 369

Patchmtry		70.74 349	69.16 352	75.49 355	80.72 388	54.07 397	74.94 411	80.30 379	58.34 403	70.01 349	81.19 383	52.50 287	86.54 354	53.37 378	71.09 394	85.87 370

WB-MVSnew		71.96 340	71.65 327	72.89 385	84.67 310	51.88 413	82.29 322	77.57 402	62.31 369	73.67 307	83.00 363	53.49 281	81.10 403	45.75 423	82.13 261	85.70 371

test_fmvs2		68.35 375	67.48 374	70.98 402	69.50 448	51.95 411	80.05 356	76.38 413	49.33 437	74.65 294	84.38 331	23.30 450	75.40 437	74.51 182	75.17 360	85.60 372

ambc				75.24 359	73.16 440	50.51 425	63.05 454	87.47 266		64.28 407	77.81 420	17.80 456	89.73 309	57.88 347	60.64 429	85.49 373

mvs5depth		69.45 364	67.45 375	75.46 356	73.93 432	55.83 378	79.19 367	83.23 336	66.89 305	71.63 333	83.32 357	33.69 430	85.09 372	59.81 326	55.34 440	85.46 374

UnsupCasMVSNet_eth		67.33 380	65.99 384	71.37 396	73.48 437	51.47 418	75.16 407	85.19 306	65.20 331	60.78 423	80.93 390	42.35 390	77.20 419	57.12 353	53.69 442	85.44 375

PatchT		68.46 374	67.85 365	70.29 404	80.70 389	43.93 448	72.47 419	74.88 419	60.15 387	70.55 340	76.57 425	49.94 326	81.59 398	50.58 391	74.83 363	85.34 376

Anonymous20240521		68.80 369	67.22 378	73.55 377	74.33 430	54.11 396	83.18 310	85.61 302	58.15 405	61.68 420	80.94 388	30.71 437	81.27 402	57.00 356	73.34 379	85.28 377

test_cas_vis1_n_1920		73.76 315	73.74 304	73.81 376	75.90 422	59.77 324	80.51 347	82.40 351	58.30 404	81.62 139	85.69 300	44.35 379	76.41 426	76.29 160	78.61 300	85.23 378

ADS-MVSNet2		66.20 392	63.33 396	74.82 364	79.92 398	58.75 333	67.55 439	75.19 417	53.37 427	65.25 402	75.86 429	42.32 391	80.53 406	41.57 435	68.91 403	85.18 379

ADS-MVSNet		64.36 397	62.88 400	68.78 412	79.92 398	47.17 436	67.55 439	71.18 431	53.37 427	65.25 402	75.86 429	42.32 391	73.99 443	41.57 435	68.91 403	85.18 379

FMVSNet5		69.50 363	67.96 363	74.15 372	82.97 353	55.35 385	80.01 357	82.12 354	62.56 367	63.02 414	81.53 382	36.92 420	81.92 397	48.42 406	74.06 369	85.17 381

pmmvs5		71.55 341	70.20 346	75.61 351	77.83 415	56.39 369	81.74 327	80.89 366	57.76 409	67.46 376	84.49 327	49.26 336	85.32 371	57.08 354	75.29 357	85.11 382

testing3		68.56 372	67.67 371	71.22 400	87.33 232	42.87 450	83.06 316	71.54 430	70.36 241	69.08 362	84.38 331	30.33 438	85.69 365	37.50 443	75.45 352	85.09 383

UWE-MVS-28		65.32 393	64.93 387	66.49 421	78.70 412	38.55 458	77.86 389	64.39 450	62.00 374	64.13 409	83.60 352	41.44 397	76.00 430	31.39 450	80.89 274	84.92 384

CMPMVS	51.72 21	70.19 357	68.16 359	76.28 345	73.15 441	57.55 352	79.47 362	83.92 324	48.02 439	56.48 439	84.81 324	43.13 386	86.42 357	62.67 299	81.81 266	84.89 385
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testgi		66.67 386	66.53 382	67.08 420	75.62 426	41.69 455	75.93 399	76.50 412	66.11 319	65.20 404	86.59 279	35.72 426	74.71 439	43.71 428	73.38 378	84.84 386

MSDG		73.36 322	70.99 336	80.49 271	84.51 312	65.80 200	80.71 344	86.13 296	65.70 325	65.46 399	83.74 347	44.60 375	90.91 288	51.13 390	76.89 324	84.74 387

pmmvs4		74.03 313	71.91 324	80.39 272	81.96 370	68.32 131	81.45 332	82.14 353	59.32 394	69.87 354	85.13 317	52.40 289	88.13 338	60.21 323	74.74 364	84.73 388

gg-mvs-nofinetune		69.95 360	67.96 363	75.94 347	83.07 347	54.51 394	77.23 393	70.29 433	63.11 357	70.32 344	62.33 447	43.62 383	88.69 330	53.88 375	87.76 163	84.62 389

test_fmvs1		70.93 347	70.52 340	72.16 391	73.71 434	55.05 388	80.82 338	78.77 395	51.21 435	78.58 190	84.41 330	31.20 436	76.94 421	75.88 167	80.12 288	84.47 390

BH-w/o		78.21 237	77.33 242	80.84 263	88.81 163	65.13 217	84.87 265	87.85 257	69.75 260	74.52 296	84.74 326	61.34 200	93.11 193	58.24 344	85.84 200	84.27 391

MVS		78.19 239	76.99 248	81.78 236	85.66 279	66.99 176	84.66 270	90.47 155	55.08 423	72.02 329	85.27 312	63.83 156	94.11 135	66.10 271	89.80 127	84.24 392

COLMAP_ROB	66.92 17	73.01 328	70.41 343	80.81 264	87.13 239	65.63 204	88.30 152	84.19 322	62.96 360	63.80 413	87.69 245	38.04 417	92.56 216	46.66 416	74.91 362	84.24 392
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
new-patchmatchnet		61.73 403	61.73 404	61.70 427	72.74 443	24.50 470	69.16 434	78.03 399	61.40 377	56.72 438	75.53 432	38.42 414	76.48 425	45.95 422	57.67 433	84.13 394

TESTMET0.1,1		69.89 361	69.00 353	72.55 388	79.27 410	56.85 360	78.38 379	74.71 422	57.64 410	68.09 370	77.19 423	37.75 418	76.70 422	63.92 288	84.09 228	84.10 395

test_fmvs3		63.36 400	61.82 403	67.98 417	62.51 457	46.96 438	77.37 392	74.03 424	45.24 442	67.50 375	78.79 413	12.16 462	72.98 446	72.77 202	66.02 413	83.99 396

our_test_3		69.14 366	67.00 379	75.57 352	79.80 402	58.80 332	77.96 386	77.81 400	59.55 392	62.90 417	78.25 417	47.43 346	83.97 381	51.71 385	67.58 408	83.93 397

test_vis1_n		69.85 362	69.21 351	71.77 393	72.66 444	55.27 387	81.48 331	76.21 414	52.03 431	75.30 277	83.20 360	28.97 439	76.22 428	74.60 181	78.41 308	83.81 398

mamv4		76.81 271	78.23 215	72.54 389	86.12 270	65.75 203	78.76 374	82.07 355	64.12 345	72.97 315	91.02 147	67.97 109	68.08 454	83.04 83	78.02 311	83.80 399

tpmvs		71.09 345	69.29 350	76.49 344	82.04 369	56.04 375	78.92 372	81.37 364	64.05 348	67.18 381	78.28 416	49.74 329	89.77 307	49.67 400	72.37 383	83.67 400

test20.03		67.45 379	66.95 380	68.94 409	75.48 427	44.84 446	77.50 390	77.67 401	66.66 310	63.01 415	83.80 345	47.02 350	78.40 413	42.53 434	68.86 405	83.58 401

test0.0.03 1		68.00 377	67.69 370	68.90 410	77.55 416	47.43 433	75.70 403	72.95 429	66.66 310	66.56 389	82.29 376	48.06 344	75.87 432	44.97 427	74.51 366	83.41 402

Anonymous20231206		68.60 370	67.80 368	71.02 401	80.23 395	50.75 424	78.30 383	80.47 374	56.79 416	66.11 397	82.63 371	46.35 359	78.95 411	43.62 429	75.70 344	83.36 403

EU-MVSNet		68.53 373	67.61 372	71.31 399	78.51 414	47.01 437	84.47 276	84.27 320	42.27 446	66.44 394	84.79 325	40.44 404	83.76 382	58.76 338	68.54 406	83.17 404

dp		66.80 384	65.43 385	70.90 403	79.74 404	48.82 431	75.12 409	74.77 420	59.61 391	64.08 410	77.23 422	42.89 387	80.72 405	48.86 405	66.58 411	83.16 405

pmmvs-eth3d		70.50 353	67.83 367	78.52 314	77.37 418	66.18 189	81.82 325	81.51 361	58.90 399	63.90 412	80.42 393	42.69 389	86.28 358	58.56 339	65.30 416	83.11 406

YYNet1		65.03 394	62.91 399	71.38 395	75.85 424	56.60 366	69.12 435	74.66 423	57.28 414	54.12 442	77.87 419	45.85 365	74.48 440	49.95 398	61.52 427	83.05 407

MDA-MVSNet-bldmvs		66.68 385	63.66 395	75.75 349	79.28 409	60.56 315	73.92 416	78.35 398	64.43 340	50.13 448	79.87 402	44.02 381	83.67 383	46.10 421	56.86 434	83.03 408

MDA-MVSNet_test_wron		65.03 394	62.92 398	71.37 396	75.93 421	56.73 362	69.09 436	74.73 421	57.28 414	54.03 443	77.89 418	45.88 364	74.39 441	49.89 399	61.55 426	82.99 409

USDC		70.33 355	68.37 356	76.21 346	80.60 390	56.23 373	79.19 367	86.49 288	60.89 380	61.29 421	85.47 308	31.78 434	89.47 314	53.37 378	76.21 340	82.94 410

Syy-MVS		68.05 376	67.85 365	68.67 413	84.68 307	40.97 456	78.62 376	73.08 427	66.65 313	66.74 387	79.46 405	52.11 295	82.30 394	32.89 448	76.38 337	82.75 411

myMVS_eth3d		67.02 383	66.29 383	69.21 408	84.68 307	42.58 451	78.62 376	73.08 427	66.65 313	66.74 387	79.46 405	31.53 435	82.30 394	39.43 440	76.38 337	82.75 411

ttmdpeth		59.91 406	57.10 410	68.34 415	67.13 452	46.65 439	74.64 412	67.41 442	48.30 438	62.52 419	85.04 321	20.40 452	75.93 431	42.55 433	45.90 453	82.44 413

OpenMVS_ROB	64.09 19	70.56 352	68.19 358	77.65 331	80.26 393	59.41 330	85.01 262	82.96 345	58.76 401	65.43 400	82.33 374	37.63 419	91.23 277	45.34 426	76.03 341	82.32 414

JIA-IIPM		66.32 389	62.82 401	76.82 342	77.09 419	61.72 300	65.34 447	75.38 416	58.04 408	64.51 406	62.32 448	42.05 395	86.51 355	51.45 388	69.22 402	82.21 415

dmvs_re		71.14 344	70.58 339	72.80 386	81.96 370	59.68 325	75.60 404	79.34 390	68.55 288	69.27 361	80.72 391	49.42 332	76.54 423	52.56 382	77.79 313	82.19 416

EG-PatchMatch MVS		74.04 311	71.82 325	80.71 266	84.92 301	67.42 163	85.86 239	88.08 247	66.04 321	64.22 408	83.85 343	35.10 427	92.56 216	57.44 350	80.83 276	82.16 417

FE-MVSNET		67.25 382	65.33 386	73.02 384	75.86 423	52.54 408	80.26 354	80.56 372	63.80 353	60.39 424	79.70 404	41.41 398	84.66 378	43.34 430	62.62 423	81.86 418

MVP-Stereo		76.12 284	74.46 294	81.13 256	85.37 289	69.79 91	84.42 281	87.95 253	65.03 334	67.46 376	85.33 311	53.28 283	91.73 252	58.01 346	83.27 247	81.85 419
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TDRefinement		67.49 378	64.34 390	76.92 341	73.47 438	61.07 307	84.86 266	82.98 344	59.77 390	58.30 433	85.13 317	26.06 442	87.89 341	47.92 413	60.59 430	81.81 420

GG-mvs-BLEND				75.38 357	81.59 376	55.80 379	79.32 364	69.63 435		67.19 380	73.67 436	43.24 385	88.90 328	50.41 392	84.50 218	81.45 421

KD-MVS_2432*1600		66.22 390	63.89 393	73.21 380	75.47 428	53.42 402	70.76 427	84.35 317	64.10 346	66.52 391	78.52 414	34.55 428	84.98 373	50.40 393	50.33 447	81.23 422

miper_refine_blended		66.22 390	63.89 393	73.21 380	75.47 428	53.42 402	70.76 427	84.35 317	64.10 346	66.52 391	78.52 414	34.55 428	84.98 373	50.40 393	50.33 447	81.23 422

test_0402		72.79 331	70.44 342	79.84 285	88.13 194	65.99 194	85.93 236	84.29 319	65.57 327	67.40 379	85.49 307	46.92 351	92.61 212	35.88 445	74.38 367	80.94 424

MVStest1		56.63 410	52.76 416	68.25 416	61.67 458	53.25 406	71.67 422	68.90 440	38.59 451	50.59 447	83.05 362	25.08 444	70.66 448	36.76 444	38.56 454	80.83 425

UnsupCasMVSNet_bld		63.70 399	61.53 405	70.21 405	73.69 435	51.39 419	72.82 418	81.89 356	55.63 421	57.81 435	71.80 440	38.67 413	78.61 412	49.26 403	52.21 445	80.63 426

LCM-MVSNet		54.25 412	49.68 422	67.97 418	53.73 466	45.28 443	66.85 442	80.78 368	35.96 455	39.45 456	62.23 449	8.70 466	78.06 416	48.24 410	51.20 446	80.57 427

N_pmnet		52.79 417	53.26 415	51.40 441	78.99 411	7.68 475	69.52 431	3.89 474	51.63 433	57.01 437	74.98 433	40.83 402	65.96 456	37.78 442	64.67 417	80.56 428

TinyColmap		67.30 381	64.81 388	74.76 365	81.92 372	56.68 365	80.29 352	81.49 362	60.33 384	56.27 440	83.22 358	24.77 446	87.66 345	45.52 424	69.47 400	79.95 429

PM-MVS		66.41 388	64.14 391	73.20 382	73.92 433	56.45 367	78.97 371	64.96 449	63.88 352	64.72 405	80.24 397	19.84 454	83.44 387	66.24 268	64.52 418	79.71 430

ANet_high		50.57 421	46.10 425	63.99 424	48.67 469	39.13 457	70.99 426	80.85 367	61.39 378	31.18 458	57.70 454	17.02 457	73.65 445	31.22 451	15.89 466	79.18 431

LF4IMVS		64.02 398	62.19 402	69.50 407	70.90 446	53.29 405	76.13 397	77.18 408	52.65 429	58.59 431	80.98 387	23.55 449	76.52 424	53.06 380	66.66 410	78.68 432

PatchMatch-RL		72.38 333	70.90 337	76.80 343	88.60 175	67.38 166	79.53 361	76.17 415	62.75 365	69.36 359	82.00 381	45.51 370	84.89 375	53.62 376	80.58 280	78.12 433

MS-PatchMatch		73.83 314	72.67 316	77.30 338	83.87 325	66.02 191	81.82 325	84.66 313	61.37 379	68.61 366	82.82 368	47.29 347	88.21 336	59.27 330	84.32 225	77.68 434

DSMNet-mixed		57.77 409	56.90 411	60.38 429	67.70 450	35.61 460	69.18 433	53.97 461	32.30 459	57.49 436	79.88 401	40.39 405	68.57 453	38.78 441	72.37 383	76.97 435

CHOSEN 280x420		66.51 387	64.71 389	71.90 392	81.45 379	63.52 264	57.98 456	68.95 439	53.57 426	62.59 418	76.70 424	46.22 361	75.29 438	55.25 366	79.68 290	76.88 436

mvsany_test3		53.99 413	51.45 418	61.61 428	55.51 462	44.74 447	63.52 452	45.41 467	43.69 445	58.11 434	76.45 426	17.99 455	63.76 458	54.77 370	47.59 449	76.34 437

dmvs_testset		62.63 401	64.11 392	58.19 431	78.55 413	24.76 469	75.28 405	65.94 446	67.91 297	60.34 425	76.01 428	53.56 279	73.94 444	31.79 449	67.65 407	75.88 438

mvsany_test1		62.30 402	61.26 406	65.41 423	69.52 447	54.86 390	66.86 441	49.78 463	46.65 440	68.50 368	83.21 359	49.15 337	66.28 455	56.93 357	60.77 428	75.11 439

PMMVS		69.34 365	68.67 354	71.35 398	75.67 425	62.03 294	75.17 406	73.46 425	50.00 436	68.68 364	79.05 408	52.07 297	78.13 414	61.16 316	82.77 253	73.90 440

test_vis1_rt		60.28 405	58.42 408	65.84 422	67.25 451	55.60 382	70.44 429	60.94 455	44.33 444	59.00 430	66.64 445	24.91 445	68.67 452	62.80 295	69.48 399	73.25 441

pmmvs3		57.79 408	54.26 413	68.37 414	64.02 456	56.72 363	75.12 409	65.17 447	40.20 448	52.93 444	69.86 444	20.36 453	75.48 435	45.45 425	55.25 441	72.90 442

PVSNet_0	57.27 20	61.67 404	59.27 407	68.85 411	79.61 405	57.44 354	68.01 437	73.44 426	55.93 420	58.54 432	70.41 443	44.58 376	77.55 418	47.01 415	35.91 455	71.55 443

WB-MVS		54.94 411	54.72 412	55.60 437	73.50 436	20.90 471	74.27 415	61.19 454	59.16 396	50.61 446	74.15 434	47.19 349	75.78 433	17.31 462	35.07 456	70.12 444

SSC-MVS		53.88 414	53.59 414	54.75 439	72.87 442	19.59 472	73.84 417	60.53 456	57.58 412	49.18 450	73.45 437	46.34 360	75.47 436	16.20 465	32.28 458	69.20 445

test_f		52.09 418	50.82 419	55.90 435	53.82 465	42.31 454	59.42 455	58.31 459	36.45 454	56.12 441	70.96 442	12.18 461	57.79 461	53.51 377	56.57 436	67.60 446

PMMVS2		40.82 428	38.86 432	46.69 442	53.84 464	16.45 473	48.61 459	49.92 462	37.49 452	31.67 457	60.97 450	8.14 468	56.42 462	28.42 453	30.72 459	67.19 447

new_pmnet		50.91 420	50.29 420	52.78 440	68.58 449	34.94 462	63.71 451	56.63 460	39.73 449	44.95 451	65.47 446	21.93 451	58.48 460	34.98 446	56.62 435	64.92 448

MVS-HIRNet		59.14 407	57.67 409	63.57 425	81.65 374	43.50 449	71.73 421	65.06 448	39.59 450	51.43 445	57.73 453	38.34 415	82.58 393	39.53 438	73.95 370	64.62 449

APD_test1		53.31 416	49.93 421	63.42 426	65.68 453	50.13 426	71.59 423	66.90 444	34.43 456	40.58 455	71.56 441	8.65 467	76.27 427	34.64 447	55.36 439	63.86 450

test_method		31.52 431	29.28 435	38.23 445	27.03 473	6.50 476	20.94 464	62.21 453	4.05 467	22.35 465	52.50 458	13.33 459	47.58 465	27.04 455	34.04 457	60.62 451

EGC-MVSNET		52.07 419	47.05 423	67.14 419	83.51 335	60.71 312	80.50 348	67.75 441	0.07 469	0.43 470	75.85 431	24.26 447	81.54 399	28.82 452	62.25 424	59.16 452

test_vis3_rt		49.26 422	47.02 424	56.00 434	54.30 463	45.27 444	66.76 443	48.08 464	36.83 453	44.38 452	53.20 457	7.17 469	64.07 457	56.77 360	55.66 437	58.65 453

FPMVS		53.68 415	51.64 417	59.81 430	65.08 454	51.03 421	69.48 432	69.58 436	41.46 447	40.67 454	72.32 439	16.46 458	70.00 451	24.24 458	65.42 415	58.40 454

testf1		45.72 423	41.96 427	57.00 432	56.90 460	45.32 441	66.14 444	59.26 457	26.19 460	30.89 459	60.96 451	4.14 470	70.64 449	26.39 456	46.73 451	55.04 455

APD_test2		45.72 423	41.96 427	57.00 432	56.90 460	45.32 441	66.14 444	59.26 457	26.19 460	30.89 459	60.96 451	4.14 470	70.64 449	26.39 456	46.73 451	55.04 455

PMVS	37.38 22	44.16 427	40.28 431	55.82 436	40.82 471	42.54 453	65.12 448	63.99 451	34.43 456	24.48 462	57.12 455	3.92 472	76.17 429	17.10 463	55.52 438	48.75 457
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	26.22 23	30.37 433	25.89 437	43.81 444	44.55 470	35.46 461	28.87 463	39.07 468	18.20 464	18.58 466	40.18 461	2.68 473	47.37 466	17.07 464	23.78 463	48.60 458
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
dongtai		45.42 425	45.38 426	45.55 443	73.36 439	26.85 467	67.72 438	34.19 469	54.15 425	49.65 449	56.41 456	25.43 443	62.94 459	19.45 460	28.09 460	46.86 459

kuosan		39.70 429	40.40 430	37.58 446	64.52 455	26.98 465	65.62 446	33.02 470	46.12 441	42.79 453	48.99 459	24.10 448	46.56 467	12.16 468	26.30 461	39.20 460

Gipuma		45.18 426	41.86 429	55.16 438	77.03 420	51.52 417	32.50 462	80.52 373	32.46 458	27.12 461	35.02 462	9.52 465	75.50 434	22.31 459	60.21 431	38.45 461
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX				27.40 449	40.17 472	26.90 466		24.59 473	17.44 465	23.95 463	48.61 460	9.77 464	26.48 468	18.06 461	24.47 462	28.83 462

E-PMN		31.77 430	30.64 433	35.15 447	52.87 467	27.67 464	57.09 457	47.86 465	24.64 462	16.40 467	33.05 463	11.23 463	54.90 463	14.46 466	18.15 464	22.87 463

EMVS		30.81 432	29.65 434	34.27 448	50.96 468	25.95 468	56.58 458	46.80 466	24.01 463	15.53 468	30.68 464	12.47 460	54.43 464	12.81 467	17.05 465	22.43 464

tmp_tt		18.61 435	21.40 438	10.23 451	4.82 474	10.11 474	34.70 461	30.74 472	1.48 468	23.91 464	26.07 465	28.42 440	13.41 470	27.12 454	15.35 467	7.17 465

wuyk23d		16.82 436	15.94 439	19.46 450	58.74 459	31.45 463	39.22 460	3.74 475	6.84 466	6.04 469	2.70 469	1.27 474	24.29 469	10.54 469	14.40 468	2.63 466

test123		6.12 438	8.11 441	0.14 452	0.06 476	0.09 477	71.05 425	0.03 477	0.04 471	0.25 472	1.30 471	0.05 475	0.03 472	0.21 471	0.01 470	0.29 467

testmvs		6.04 439	8.02 442	0.10 453	0.08 475	0.03 478	69.74 430	0.04 476	0.05 470	0.31 471	1.68 470	0.02 476	0.04 471	0.24 470	0.02 469	0.25 468

mmdepth		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

monomultidepth		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

test_blank		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet_test		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

DCPMVS		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

cdsmvs_eth3d_5k		19.96 434	26.61 436	0.00 454	0.00 477	0.00 479	0.00 465	89.26 207	0.00 472	0.00 473	88.61 218	61.62 193	0.00 473	0.00 472	0.00 471	0.00 469

pcd_1.5k_mvsjas		5.26 440	7.02 443	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	63.15 165	0.00 473	0.00 472	0.00 471	0.00 469

sosnet-low-res		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

sosnet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uncertanet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

Regformer		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

ab-mvs-re		7.23 437	9.64 440	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	86.72 271	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

WAC-MVS						42.58 451								39.46 439

FOURS1					95.00 10	72.39 41	95.06 1	93.84 16	74.49 138	91.30 15

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

eth-test2					0.00 477

eth-test					0.00 477

ZD-MVS					94.38 25	72.22 46		92.67 68	70.98 223	87.75 45	94.07 52	74.01 33	96.70 27	84.66 64	94.84 44

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

9.14			88.26 16		92.84 65		91.52 51	94.75 1	73.93 154	88.57 30	94.67 25	75.57 22	95.79 59	86.77 46	95.76 23

save fliter					93.80 40	72.35 44	90.47 69	91.17 136	74.31 143

test0726					95.27 5	71.25 61	93.60 7	94.11 7	77.33 57	92.81 3	95.79 3	80.98 9

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs												50.01 324

MTGPA								92.02 99

test_post1							78.90 373				5.43 468	48.81 343	85.44 370	59.25 331

test_post											5.46 467	50.36 320	84.24 379

patchmatchnet-post											74.00 435	51.12 311	88.60 332

MTMP							92.18 35	32.83 471

gm-plane-assit					81.40 380	53.83 399			62.72 366		80.94 388		92.39 225	63.40 292

TEST9					93.26 52	72.96 25	88.75 131	91.89 107	68.44 291	85.00 74	93.10 82	74.36 29	95.41 76

test_8					93.13 56	72.57 35	88.68 136	91.84 111	68.69 286	84.87 78	93.10 82	74.43 27	95.16 86

agg_prior					92.85 64	71.94 52		91.78 115		84.41 89			94.93 97

test_prior4						72.60 34	89.01 118

test_prior2							88.85 125		75.41 110	84.91 76	93.54 70	74.28 30		83.31 79	95.86 20

旧先验2							86.56 217		58.10 407	87.04 56			88.98 324	74.07 187

新几何2							86.29 228

原ACMM2							86.86 204

testdata2													91.01 286	62.37 302

segment_acmp												73.08 40

testdata1							84.14 289		75.71 101

plane_prior7					90.08 112	68.51 127

plane_prior6					89.84 121	68.70 121						60.42 219

plane_prior4											91.00 148

plane_prior3						68.60 124			78.44 36	78.92 183

plane_prior2							91.25 55		79.12 28

plane_prior1					89.90 120

plane_prior						68.71 119	90.38 73		77.62 47						86.16 191

n2								0.00 478

nn								0.00 478

door-mid								69.98 434

test11								92.23 88

door								69.44 437

HQP5-MVS						66.98 177

HQP-NCC					89.33 140		89.17 109		76.41 85	77.23 224

ACMP_Plane					89.33 140		89.17 109		76.41 85	77.23 224

BP-MVS														77.47 144

HQP3-MVS								92.19 93							85.99 195

HQP2-MVS												60.17 222

NP-MVS					89.62 125	68.32 131					90.24 168

MDTV_nov1_ep13			69.97 347		83.18 344	53.48 401	77.10 395	80.18 383	60.45 383	69.33 360	80.44 392	48.89 342	86.90 351	51.60 386	78.51 303

ACMMP++_ref															81.95 264

ACMMP++															81.25 269

Test By Simon												64.33 151

High-resolution multi-view benchmark