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.

DeepPCF-MVS	93.56 1	96.55 40	97.84 10	92.68 226	98.71 85	78.11 348	99.70 27	97.71 85	98.18 1	97.36 63	99.76 1	90.37 48	99.94 34	99.27 16	99.54 53	99.99 1

CNVR-MVS		98.46 1	98.38 1	98.72 9	99.80 4	96.19 15	99.80 16	97.99 52	97.05 6	99.41 4	99.59 2	92.89 24	100.00 1	98.99 25	99.90 7	99.96 10

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 25	99.77 18	97.72 81	94.17 45	99.30 9	99.54 3	93.32 18	99.98 9	99.70 4	99.81 23	99.99 1

test_241102_TWO								97.72 81	94.17 45	99.23 11	99.54 3	93.14 23	99.98 9	99.70 4	99.82 19	99.99 1

test0726					99.66 12	95.20 30	99.77 18	97.70 86	93.95 50	99.35 7	99.54 3	93.18 21

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 21	99.29 82	97.72 81	94.50 39	98.64 29	99.54 3	93.32 18	99.97 21	99.58 10	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DPM-MVS		97.86 8	97.25 21	99.68 1	98.25 94	99.10 1	99.76 21	97.78 73	96.61 12	98.15 42	99.53 7	93.62 16	100.00 1	91.79 162	99.80 26	99.94 18

SMA-MVS		97.24 20	96.99 24	98.00 29	99.30 54	94.20 55	99.16 97	97.65 102	89.55 158	99.22 13	99.52 8	90.34 49	99.99 5	98.32 43	99.83 15	99.82 32
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
test_241102_ONE					99.63 18	95.24 25		97.72 81	94.16 47	99.30 9	99.49 9	93.32 18	99.98 9

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 30	99.72 24	97.47 141	93.95 50	99.07 16	99.46 10	93.18 21	99.97 21	99.64 7	99.82 19	99.69 55
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									93.01 72	99.07 16	99.46 10	94.66 13	99.97 21	99.25 18	99.82 19	99.95 15

MSLP-MVS++		97.50 17	97.45 17	97.63 38	99.65 16	93.21 72	99.70 27	98.13 42	94.61 37	97.78 56	99.46 10	89.85 54	99.81 79	97.97 52	99.91 6	99.88 26

NCCC		98.12 5	98.11 3	98.13 24	99.76 6	94.46 48	99.81 12	97.88 57	96.54 13	98.84 25	99.46 10	92.55 26	99.98 9	98.25 46	99.93 1	99.94 18

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 22	99.55 45	97.68 90	93.01 72	99.23 11	99.45 14	95.12 8	99.98 9	99.25 18	99.92 3	99.97 7

test_one_0601					99.59 28	94.89 34		97.64 103	93.14 71	98.93 22	99.45 14	93.45 17

9.14			96.87 27		99.34 50		99.50 52	97.49 138	89.41 162	98.59 31	99.43 16	89.78 55	99.69 91	98.69 30	99.62 45

SF-MVS		97.22 22	96.92 25	98.12 26	99.11 66	94.88 35	99.44 63	97.45 144	89.60 154	98.70 27	99.42 17	90.42 46	99.72 89	98.47 38	99.65 38	99.77 43

DeepC-MVS_fast	93.52 2	97.16 24	96.84 29	98.13 24	99.61 24	94.45 49	98.85 136	97.64 103	96.51 16	95.88 98	99.39 18	87.35 91	99.99 5	96.61 79	99.69 36	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 27	97.98 53	97.18 3	95.96 95	99.33 19	92.62 25	100.00 1	98.99 25	99.93 1	99.98 6

HPM-MVS++		97.72 11	97.59 13	98.14 23	99.53 40	94.76 42	99.19 91	97.75 76	95.66 24	98.21 41	99.29 20	91.10 32	99.99 5	97.68 57	99.87 9	99.68 56

fmvsm_l_conf0.5_n_a		97.70 12	97.80 11	97.42 45	97.59 117	92.91 83	99.86 5	98.04 48	96.70 10	99.58 2	99.26 21	90.90 37	99.94 34	99.57 11	98.66 99	99.40 87

SteuartSystems-ACMMP		97.25 19	97.34 20	97.01 60	97.38 126	91.46 106	99.75 22	97.66 95	94.14 49	98.13 43	99.26 21	92.16 28	99.66 94	97.91 54	99.64 40	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
MP-MVS-pluss		95.80 64	95.30 72	97.29 50	98.95 76	92.66 86	98.59 168	97.14 175	88.95 174	93.12 148	99.25 23	85.62 127	99.94 34	96.56 81	99.48 55	99.28 99
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CSCG		94.87 90	94.71 85	95.36 142	99.54 36	86.49 230	99.34 78	98.15 40	82.71 309	90.15 194	99.25 23	89.48 57	99.86 63	94.97 114	98.82 91	99.72 50

MTAPA		96.09 51	95.80 61	96.96 67	99.29 55	91.19 111	97.23 267	97.45 144	92.58 81	94.39 128	99.24 25	86.43 115	99.99 5	96.22 85	99.40 63	99.71 51

fmvsm_l_conf0.5_n		97.65 13	97.72 12	97.41 46	97.51 121	92.78 85	99.85 8	98.05 46	96.78 8	99.60 1	99.23 26	90.42 46	99.92 40	99.55 12	98.50 104	99.55 72

iter_conf05_11		94.23 110	93.49 119	96.46 94	97.51 121	91.32 108	99.96 1	94.31 335	95.62 26	99.32 8	99.22 27	57.79 345	98.59 170	98.00 50	99.64 40	99.46 81

CDPH-MVS		96.56 39	96.18 45	97.70 36	99.59 28	93.92 60	99.13 109	97.44 147	89.02 171	97.90 54	99.22 27	88.90 63	99.49 112	94.63 122	99.79 27	99.68 56

API-MVS		94.78 93	94.18 98	96.59 87	99.21 61	90.06 149	98.80 142	97.78 73	83.59 293	93.85 137	99.21 29	83.79 153	99.97 21	92.37 157	99.00 80	99.74 47

bld_raw_dy_0_64		91.37 181	89.75 195	96.23 107	97.51 121	90.58 132	99.16 97	88.98 387	95.64 25	87.18 222	99.20 30	57.19 349	98.66 165	98.00 50	84.86 258	99.46 81

PHI-MVS		96.65 37	96.46 38	97.21 54	99.34 50	91.77 99	99.70 27	98.05 46	86.48 247	98.05 48	99.20 30	89.33 58	99.96 28	98.38 39	99.62 45	99.90 22

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 18				99.19 32	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

MSP-MVS		97.77 9	98.18 2	96.53 92	99.54 36	90.14 142	99.41 69	97.70 86	95.46 30	98.60 30	99.19 32	95.71 4	99.49 112	98.15 48	99.85 13	99.95 15
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
test_8					99.55 35	93.07 76	99.37 75	97.64 103	90.18 136	98.36 38	99.19 32	90.94 35	99.64 100

TEST9					99.57 33	93.17 73	99.38 72	97.66 95	89.57 156	98.39 36	99.18 35	90.88 38	99.66 94

train_agg		97.20 23	97.08 23	97.57 42	99.57 33	93.17 73	99.38 72	97.66 95	90.18 136	98.39 36	99.18 35	90.94 35	99.66 94	98.58 36	99.85 13	99.88 26

MAR-MVS		94.43 107	94.09 100	95.45 139	99.10 68	87.47 210	98.39 195	97.79 72	88.37 193	94.02 134	99.17 37	78.64 221	99.91 45	92.48 156	98.85 90	98.96 125
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
fmvsm_s_conf0.5_n_a		95.97 56	96.19 43	95.31 145	96.51 165	89.01 172	99.81 12	98.39 27	95.46 30	99.19 14	99.16 38	81.44 199	99.91 45	98.83 28	96.97 137	97.01 216

ZD-MVS					99.67 10	93.28 71		97.61 110	87.78 214	97.41 61	99.16 38	90.15 52	99.56 105	98.35 41	99.70 35

CP-MVS		96.22 48	96.15 51	96.42 98	99.67 10	89.62 160	99.70 27	97.61 110	90.07 142	96.00 94	99.16 38	87.43 85	99.92 40	96.03 90	99.72 31	99.70 52

fmvsm_s_conf0.5_n		96.19 49	96.49 36	95.30 146	97.37 127	89.16 166	99.86 5	98.47 25	95.68 23	98.87 23	99.15 41	82.44 185	99.92 40	99.14 21	97.43 128	96.83 220

旧先验1					98.97 73	92.90 84		97.74 77			99.15 41	91.05 34			99.33 64	99.60 67

testdata				95.26 148	98.20 96	87.28 217		97.60 112	85.21 264	98.48 34	99.15 41	88.15 74	98.72 162	90.29 179	99.45 58	99.78 38

ACMMP_NAP		96.59 38	96.18 45	97.81 34	98.82 81	93.55 66	98.88 135	97.59 116	90.66 120	97.98 52	99.14 44	86.59 109	100.00 1	96.47 83	99.46 56	99.89 25

PS-MVSNAJ		96.87 31	96.40 39	98.29 19	97.35 128	97.29 5	99.03 120	97.11 179	95.83 20	98.97 20	99.14 44	82.48 181	99.60 103	98.60 33	99.08 74	98.00 187

test_fmvsm_n_1920		97.08 27	97.55 14	95.67 133	97.94 105	89.61 161	99.93 2	98.48 24	97.08 5	99.08 15	99.13 46	88.17 72	99.93 38	99.11 23	99.06 76	97.47 200

DP-MVS Recon		95.85 62	95.15 77	97.95 30	99.87 2	94.38 52	99.60 39	97.48 139	86.58 242	94.42 126	99.13 46	87.36 90	99.98 9	93.64 137	98.33 108	99.48 79

PC_three_1452									94.60 38	99.41 4	99.12 48	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

SR-MVS		96.13 50	96.16 50	96.07 116	99.42 47	89.04 170	98.59 168	97.33 158	90.44 130	96.84 77	99.12 48	86.75 104	99.41 126	97.47 60	99.44 59	99.76 45

APDe-MVS		97.53 14	97.47 15	97.70 36	99.58 30	93.63 64	99.56 44	97.52 131	93.59 65	98.01 51	99.12 48	90.80 40	99.55 106	99.26 17	99.79 27	99.93 20
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PAPR		96.35 43	95.82 58	97.94 31	99.63 18	94.19 56	99.42 68	97.55 123	92.43 84	93.82 139	99.12 48	87.30 92	99.91 45	94.02 129	99.06 76	99.74 47

xiu_mvs_v2_base		96.66 36	96.17 48	98.11 27	97.11 145	96.96 6	99.01 123	97.04 186	95.51 29	98.86 24	99.11 52	82.19 189	99.36 130	98.59 35	98.14 112	98.00 187

region2R		96.30 46	96.17 48	96.70 81	99.70 7	90.31 136	99.46 60	97.66 95	90.55 126	97.07 72	99.07 53	86.85 102	99.97 21	95.43 101	99.74 29	99.81 33

APD-MVS		96.95 29	96.72 32	97.63 38	99.51 41	93.58 65	99.16 97	97.44 147	90.08 141	98.59 31	99.07 53	89.06 60	99.42 123	97.92 53	99.66 37	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
新几何1				97.40 47	98.92 77	92.51 91		97.77 75	85.52 260	96.69 84	99.06 55	88.08 76	99.89 53	84.88 241	99.62 45	99.79 36

CS-MVS-test		95.98 55	96.34 41	94.90 160	98.06 102	87.66 204	99.69 34	96.10 242	93.66 62	98.35 39	99.05 56	86.28 117	97.66 220	96.96 71	98.90 88	99.37 90

HFP-MVS		96.42 42	96.26 42	96.90 69	99.69 8	90.96 122	99.47 56	97.81 68	90.54 127	96.88 74	99.05 56	87.57 82	99.96 28	95.65 94	99.72 31	99.78 38

fmvsm_s_conf0.1_n		95.56 72	95.68 65	95.20 149	94.35 250	89.10 168	99.50 52	97.67 94	94.76 36	98.68 28	99.03 58	81.13 202	99.86 63	98.63 32	97.36 130	96.63 223

ACMMPR		96.28 47	96.14 52	96.73 78	99.68 9	90.47 134	99.47 56	97.80 70	90.54 127	96.83 79	99.03 58	86.51 113	99.95 31	95.65 94	99.72 31	99.75 46

test222					98.32 92	91.21 110	98.08 224	97.58 118	83.74 289	95.87 99	99.02 60	86.74 105			99.64 40	99.81 33

SD-MVS		97.51 16	97.40 18	97.81 34	99.01 72	93.79 63	99.33 79	97.38 154	93.73 61	98.83 26	99.02 60	90.87 39	99.88 54	98.69 30	99.74 29	99.77 43
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
fmvsm_s_conf0.1_n_a		95.16 82	95.15 77	95.18 150	92.06 300	88.94 176	99.29 82	97.53 127	94.46 40	98.98 19	98.99 62	79.99 207	99.85 67	98.24 47	96.86 139	96.73 221

APD-MVS_3200maxsize		95.64 71	95.65 68	95.62 135	99.24 58	87.80 200	98.42 186	97.22 166	88.93 176	96.64 87	98.98 63	85.49 131	99.36 130	96.68 76	99.27 69	99.70 52

SR-MVS-dyc-post		95.75 68	95.86 57	95.41 141	99.22 59	87.26 220	98.40 191	97.21 167	89.63 152	96.67 85	98.97 64	86.73 106	99.36 130	96.62 77	99.31 66	99.60 67

RE-MVS-def			95.70 64		99.22 59	87.26 220	98.40 191	97.21 167	89.63 152	96.67 85	98.97 64	85.24 137		96.62 77	99.31 66	99.60 67

test_prior2							99.57 43		91.43 106	98.12 45	98.97 64	90.43 45		98.33 42	99.81 23

原ACMM1				96.18 110	99.03 71	90.08 145		97.63 107	88.98 172	97.00 73	98.97 64	88.14 75	99.71 90	88.23 203	99.62 45	98.76 149

MM		97.76 10	97.39 19	98.86 5	98.30 93	96.83 7	99.81 12	99.13 9	97.66 2	98.29 40	98.96 68	85.84 126	99.90 50	99.72 3	98.80 92	99.85 30

XVS		96.47 41	96.37 40	96.77 74	99.62 22	90.66 130	99.43 66	97.58 118	92.41 87	96.86 75	98.96 68	87.37 87	99.87 58	95.65 94	99.43 60	99.78 38

CPTT-MVS		94.60 101	94.43 91	95.09 153	99.66 12	86.85 225	99.44 63	97.47 141	83.22 298	94.34 129	98.96 68	82.50 179	99.55 106	94.81 116	99.50 54	98.88 135

MP-MVS		96.00 53	95.82 58	96.54 91	99.47 46	90.13 144	99.36 76	97.41 151	90.64 123	95.49 108	98.95 71	85.51 130	99.98 9	96.00 91	99.59 50	99.52 75
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		95.85 62	95.65 68	96.45 96	99.50 42	89.77 157	98.22 207	98.90 13	89.19 166	96.74 82	98.95 71	85.91 125	99.92 40	93.94 130	99.46 56	99.66 60

mPP-MVS		95.90 61	95.75 63	96.38 101	99.58 30	89.41 164	99.26 86	97.41 151	90.66 120	94.82 118	98.95 71	86.15 121	99.98 9	95.24 107	99.64 40	99.74 47

ZNCC-MVS		96.09 51	95.81 60	96.95 68	99.42 47	91.19 111	99.55 45	97.53 127	89.72 149	95.86 100	98.94 74	86.59 109	99.97 21	95.13 108	99.56 51	99.68 56

MVS_0304		97.53 14	97.15 22	98.67 11	97.30 130	96.52 12	99.60 39	98.88 14	97.14 4	97.21 67	98.94 74	86.89 101	99.91 45	99.43 15	98.91 87	99.59 71

test_fmvsmconf_n		96.78 34	96.84 29	96.61 85	95.99 190	90.25 137	99.90 3	98.13 42	96.68 11	98.42 35	98.92 76	85.34 136	99.88 54	99.12 22	99.08 74	99.70 52

patch_mono-2		97.10 26	97.97 8	94.49 175	99.21 61	83.73 290	99.62 38	98.25 32	95.28 32	99.38 6	98.91 77	92.28 27	99.94 34	99.61 9	99.22 71	99.78 38

CANet		97.00 28	96.49 36	98.55 12	98.86 80	96.10 16	99.83 10	97.52 131	95.90 19	97.21 67	98.90 78	82.66 178	99.93 38	98.71 29	98.80 92	99.63 64

PAPM_NR		95.43 74	95.05 81	96.57 90	99.42 47	90.14 142	98.58 170	97.51 133	90.65 122	92.44 156	98.90 78	87.77 81	99.90 50	90.88 170	99.32 65	99.68 56

test_fmvsmvis_n_1920		95.47 73	95.40 71	95.70 131	94.33 251	90.22 140	99.70 27	96.98 193	96.80 7	92.75 152	98.89 80	82.46 184	99.92 40	98.36 40	98.33 108	96.97 217

CS-MVS		95.75 68	96.19 43	94.40 179	97.88 107	86.22 241	99.66 35	96.12 241	92.69 80	98.07 47	98.89 80	87.09 95	97.59 226	96.71 74	98.62 100	99.39 89

EI-MVSNet-Vis-set		95.76 67	95.63 70	96.17 112	99.14 64	90.33 135	98.49 179	97.82 65	91.92 96	94.75 120	98.88 82	87.06 97	99.48 116	95.40 102	97.17 135	98.70 152

CNLPA		93.64 130	92.74 139	96.36 103	98.96 75	90.01 152	99.19 91	95.89 267	86.22 250	89.40 202	98.85 83	80.66 205	99.84 69	88.57 199	96.92 138	99.24 102

xiu_mvs_v1_base_debu		94.73 95	93.98 104	96.99 62	95.19 217	95.24 25	98.62 162	96.50 216	92.99 74	97.52 58	98.83 84	72.37 262	99.15 141	97.03 67	96.74 140	96.58 226

xiu_mvs_v1_base		94.73 95	93.98 104	96.99 62	95.19 217	95.24 25	98.62 162	96.50 216	92.99 74	97.52 58	98.83 84	72.37 262	99.15 141	97.03 67	96.74 140	96.58 226

xiu_mvs_v1_base_debi		94.73 95	93.98 104	96.99 62	95.19 217	95.24 25	98.62 162	96.50 216	92.99 74	97.52 58	98.83 84	72.37 262	99.15 141	97.03 67	96.74 140	96.58 226

cdsmvs_eth3d_5k		22.52 372	30.03 375	0.00 391	0.00 414	0.00 416	0.00 402	97.17 173	0.00 409	0.00 410	98.77 87	74.35 244	0.00 410	0.00 409	0.00 408	0.00 406

EI-MVSNet-UG-set		95.43 74	95.29 73	95.86 126	99.07 70	89.87 154	98.43 185	97.80 70	91.78 98	94.11 132	98.77 87	86.25 119	99.48 116	94.95 115	96.45 144	98.22 179

lupinMVS		96.32 45	95.94 54	97.44 44	95.05 231	94.87 36	99.86 5	96.50 216	93.82 59	98.04 49	98.77 87	85.52 128	98.09 190	96.98 70	98.97 82	99.37 90

LS3D		90.19 205	88.72 217	94.59 174	98.97 73	86.33 238	96.90 279	96.60 207	74.96 361	84.06 251	98.74 90	75.78 233	99.83 73	74.93 324	97.57 122	97.62 197

MVS_111021_HR		96.69 35	96.69 33	96.72 80	98.58 88	91.00 121	99.14 106	99.45 1	93.86 56	95.15 114	98.73 91	88.48 67	99.76 86	97.23 65	99.56 51	99.40 87

OMC-MVS		93.90 120	93.62 116	94.73 168	98.63 87	87.00 223	98.04 227	96.56 212	92.19 92	92.46 155	98.73 91	79.49 213	99.14 145	92.16 159	94.34 173	98.03 186

GST-MVS		95.97 56	95.66 66	96.90 69	99.49 45	91.22 109	99.45 62	97.48 139	89.69 150	95.89 97	98.72 93	86.37 116	99.95 31	94.62 123	99.22 71	99.52 75

PAPM		96.35 43	95.94 54	97.58 40	94.10 257	95.25 24	98.93 130	98.17 37	94.26 44	93.94 135	98.72 93	89.68 56	97.88 202	96.36 84	99.29 68	99.62 66

ACMMP		94.67 99	94.30 92	95.79 128	99.25 57	88.13 194	98.41 188	98.67 22	90.38 132	91.43 172	98.72 93	82.22 188	99.95 31	93.83 134	95.76 158	99.29 98
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
mvsany_test1		94.57 103	95.09 80	92.98 217	95.84 194	82.07 312	98.76 148	95.24 306	92.87 79	96.45 88	98.71 96	84.81 143	99.15 141	97.68 57	95.49 163	97.73 192

MG-MVS		97.24 20	96.83 31	98.47 15	99.79 5	95.71 18	99.07 114	99.06 10	94.45 42	96.42 89	98.70 97	88.81 64	99.74 88	95.35 103	99.86 12	99.97 7

MVS_111021_LR		95.78 65	95.94 54	95.28 147	98.19 98	87.69 201	98.80 142	99.26 7	93.39 67	95.04 116	98.69 98	84.09 150	99.76 86	96.96 71	99.06 76	98.38 168

test_fmvsmconf0.1_n		95.94 59	95.79 62	96.40 100	92.42 294	89.92 153	99.79 17	96.85 197	96.53 15	97.22 66	98.67 99	82.71 177	99.84 69	98.92 27	98.98 81	99.43 86

AdaColmap		93.82 123	93.06 131	96.10 115	99.88 1	89.07 169	98.33 199	97.55 123	86.81 238	90.39 191	98.65 100	75.09 236	99.98 9	93.32 145	97.53 125	99.26 101

EIA-MVS		95.11 83	95.27 74	94.64 172	96.34 173	86.51 229	99.59 41	96.62 205	92.51 82	94.08 133	98.64 101	86.05 122	98.24 184	95.07 110	98.50 104	99.18 107

TSAR-MVS + MP.		97.44 18	97.46 16	97.39 48	99.12 65	93.49 69	98.52 173	97.50 136	94.46 40	98.99 18	98.64 101	91.58 29	99.08 148	98.49 37	99.83 15	99.60 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
dcpmvs_2		95.67 70	96.18 45	94.12 192	98.82 81	84.22 283	97.37 260	95.45 293	90.70 119	95.77 102	98.63 103	90.47 44	98.68 164	99.20 20	99.22 71	99.45 83

TSAR-MVS + GP.		96.95 29	96.91 26	97.07 57	98.88 79	91.62 102	99.58 42	96.54 214	95.09 34	96.84 77	98.63 103	91.16 30	99.77 85	99.04 24	96.42 145	99.81 33

alignmvs		95.77 66	95.00 82	98.06 28	97.35 128	95.68 19	99.71 26	97.50 136	91.50 103	96.16 93	98.61 105	86.28 117	99.00 150	96.19 86	91.74 207	99.51 77

MVS		93.92 118	92.28 147	98.83 7	95.69 199	96.82 8	96.22 304	98.17 37	84.89 273	84.34 248	98.61 105	79.32 214	99.83 73	93.88 132	99.43 60	99.86 29

TAPA-MVS	87.50 9	90.35 200	89.05 210	94.25 187	98.48 91	85.17 270	98.42 186	96.58 211	82.44 316	87.24 220	98.53 107	82.77 173	98.84 155	59.09 382	97.88 115	98.72 150
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVSFormer		94.71 98	94.08 101	96.61 85	95.05 231	94.87 36	97.77 242	96.17 238	86.84 236	98.04 49	98.52 108	85.52 128	95.99 306	89.83 182	98.97 82	98.96 125

jason		95.40 77	94.86 84	97.03 59	92.91 289	94.23 54	99.70 27	96.30 227	93.56 66	96.73 83	98.52 108	81.46 198	97.91 199	96.08 89	98.47 106	98.96 125
jason: jason.
1112_ss		92.71 152	91.55 164	96.20 109	95.56 203	91.12 114	98.48 181	94.69 324	88.29 198	86.89 226	98.50 110	87.02 98	98.66 165	84.75 242	89.77 232	98.81 143

ab-mvs-re		8.21 376	10.94 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	98.50 110	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

test_fmvsmconf0.01_n		94.14 112	93.51 118	96.04 117	86.79 367	89.19 165	99.28 85	95.94 255	95.70 21	95.50 107	98.49 112	73.27 254	99.79 82	98.28 45	98.32 110	99.15 109

canonicalmvs		95.02 86	93.96 107	98.20 21	97.53 120	95.92 17	98.71 150	96.19 236	91.78 98	95.86 100	98.49 112	79.53 212	99.03 149	96.12 87	91.42 219	99.66 60

HPM-MVS		95.41 76	95.22 75	95.99 121	99.29 55	89.14 167	99.17 96	97.09 183	87.28 227	95.40 109	98.48 114	84.93 140	99.38 128	95.64 98	99.65 38	99.47 80
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CANet_DTU		94.31 109	93.35 123	97.20 55	97.03 149	94.71 44	98.62 162	95.54 288	95.61 27	97.21 67	98.47 115	71.88 267	99.84 69	88.38 201	97.46 127	97.04 214

HPM-MVS_fast		94.89 87	94.62 86	95.70 131	99.11 66	88.44 190	99.14 106	97.11 179	85.82 255	95.69 104	98.47 115	83.46 158	99.32 135	93.16 147	99.63 44	99.35 92

WTY-MVS		95.97 56	95.11 79	98.54 13	97.62 114	96.65 9	99.44 63	98.74 16	92.25 91	95.21 112	98.46 117	86.56 111	99.46 118	95.00 113	92.69 188	99.50 78

EC-MVSNet		95.09 84	95.17 76	94.84 163	95.42 208	88.17 192	99.48 54	95.92 259	91.47 104	97.34 64	98.36 118	82.77 173	97.41 237	97.24 64	98.58 101	98.94 130

DeepC-MVS	91.02 4	94.56 104	93.92 109	96.46 94	97.16 140	90.76 126	98.39 195	97.11 179	93.92 52	88.66 207	98.33 119	78.14 223	99.85 67	95.02 111	98.57 102	98.78 147
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LFMVS		92.23 166	90.84 179	96.42 98	98.24 95	91.08 118	98.24 206	96.22 233	83.39 296	94.74 121	98.31 120	61.12 335	98.85 154	94.45 125	92.82 185	99.32 95

ETV-MVS		96.00 53	96.00 53	96.00 120	96.56 161	91.05 119	99.63 37	96.61 206	93.26 70	97.39 62	98.30 121	86.62 108	98.13 187	98.07 49	97.57 122	98.82 142

ET-MVSNet_ETH3D		92.56 158	91.45 166	95.88 125	96.39 171	94.13 58	99.46 60	96.97 194	92.18 93	66.94 376	98.29 122	94.65 14	94.28 349	94.34 126	83.82 271	99.24 102

DELS-MVS		97.12 25	96.60 35	98.68 10	98.03 103	96.57 11	99.84 9	97.84 61	96.36 18	95.20 113	98.24 123	88.17 72	99.83 73	96.11 88	99.60 49	99.64 62
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
EPNet		96.82 32	96.68 34	97.25 53	98.65 86	93.10 75	99.48 54	98.76 15	96.54 13	97.84 55	98.22 124	87.49 84	99.66 94	95.35 103	97.78 119	99.00 121
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		94.06 113	93.05 132	97.06 58	99.08 69	92.26 94	98.97 128	97.01 191	82.58 311	92.57 154	98.22 124	80.68 204	99.30 136	89.34 192	99.02 79	99.63 64

PLC	91.07 3	94.23 110	94.01 102	94.87 161	99.17 63	87.49 209	99.25 87	96.55 213	88.43 191	91.26 176	98.21 126	85.92 123	99.86 63	89.77 186	97.57 122	97.24 207
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VDD-MVS		91.24 185	90.18 190	94.45 178	97.08 146	85.84 257	98.40 191	96.10 242	86.99 230	93.36 145	98.16 127	54.27 361	99.20 138	96.59 80	90.63 227	98.31 174

PMMVS		93.62 131	93.90 110	92.79 221	96.79 156	81.40 319	98.85 136	96.81 198	91.25 110	96.82 80	98.15 128	77.02 229	98.13 187	93.15 148	96.30 149	98.83 141

test_vis1_n_1920		93.08 148	93.42 121	92.04 239	96.31 174	79.36 336	99.83 10	96.06 246	96.72 9	98.53 33	98.10 129	58.57 342	99.91 45	97.86 55	98.79 95	96.85 219

XVG-OURS		90.83 192	90.49 187	91.86 241	95.23 214	81.25 323	95.79 319	95.92 259	88.96 173	90.02 196	98.03 130	71.60 271	99.35 133	91.06 167	87.78 238	94.98 245

XVG-OURS-SEG-HR		90.95 190	90.66 185	91.83 242	95.18 220	81.14 326	95.92 311	95.92 259	88.40 192	90.33 192	97.85 131	70.66 277	99.38 128	92.83 152	88.83 234	94.98 245

sss		94.85 91	93.94 108	97.58 40	96.43 168	94.09 59	98.93 130	99.16 8	89.50 159	95.27 111	97.85 131	81.50 196	99.65 98	92.79 154	94.02 175	98.99 122

diffmvs		94.59 102	94.19 96	95.81 127	95.54 204	90.69 128	98.70 152	95.68 280	91.61 100	95.96 95	97.81 133	80.11 206	98.06 192	96.52 82	95.76 158	98.67 154
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-RMVSNet		91.25 184	89.99 192	95.03 157	96.75 157	88.55 187	98.65 158	94.95 314	87.74 217	87.74 214	97.80 134	68.27 291	98.14 186	80.53 288	97.49 126	98.41 165

F-COLMAP		92.07 170	91.75 161	93.02 216	98.16 99	82.89 302	98.79 146	95.97 250	86.54 244	87.92 212	97.80 134	78.69 220	99.65 98	85.97 227	95.93 157	96.53 229

test_cas_vis1_n_1920		93.86 122	93.74 114	94.22 188	95.39 211	86.08 247	99.73 23	96.07 245	96.38 17	97.19 70	97.78 136	65.46 317	99.86 63	96.71 74	98.92 86	96.73 221

PVSNet_Blended		95.94 59	95.66 66	96.75 76	98.77 83	91.61 103	99.88 4	98.04 48	93.64 64	94.21 130	97.76 137	83.50 156	99.87 58	97.41 61	97.75 120	98.79 145

VDDNet		90.08 209	88.54 225	94.69 169	94.41 249	87.68 202	98.21 209	96.40 221	76.21 356	93.33 146	97.75 138	54.93 359	98.77 157	94.71 120	90.96 222	97.61 198

test_yl		95.27 80	94.60 87	97.28 51	98.53 89	92.98 79	99.05 118	98.70 19	86.76 239	94.65 123	97.74 139	87.78 79	99.44 119	95.57 99	92.61 189	99.44 84

DCV-MVSNet		95.27 80	94.60 87	97.28 51	98.53 89	92.98 79	99.05 118	98.70 19	86.76 239	94.65 123	97.74 139	87.78 79	99.44 119	95.57 99	92.61 189	99.44 84

1314		93.44 134	91.98 155	97.84 32	95.24 213	94.38 52	96.22 304	97.92 55	90.18 136	82.28 276	97.71 141	77.63 226	99.80 81	91.94 161	98.67 98	99.34 94

baseline		93.91 119	93.30 125	95.72 130	95.10 228	90.07 146	97.48 256	95.91 264	91.03 112	93.54 143	97.68 142	79.58 210	98.02 196	94.27 127	95.14 166	99.08 117

PVSNet	87.13 12	93.69 126	92.83 138	96.28 106	97.99 104	90.22 140	99.38 72	98.93 12	91.42 107	93.66 141	97.68 142	71.29 274	99.64 100	87.94 207	97.20 132	98.98 123

casdiffmvs		93.98 117	93.43 120	95.61 136	95.07 230	89.86 155	98.80 142	95.84 272	90.98 114	92.74 153	97.66 144	79.71 209	98.10 189	94.72 119	95.37 164	98.87 137
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Vis-MVSNet (Re-imp)		93.26 143	93.00 135	94.06 195	96.14 185	86.71 228	98.68 154	96.70 201	88.30 197	89.71 201	97.64 145	85.43 134	96.39 282	88.06 206	96.32 147	99.08 117

3Dnovator+	87.72 8	93.43 135	91.84 158	98.17 22	95.73 198	95.08 32	98.92 132	97.04 186	91.42 107	81.48 293	97.60 146	74.60 239	99.79 82	90.84 171	98.97 82	99.64 62

thisisatest0515		94.75 94	94.19 96	96.43 97	96.13 188	92.64 89	99.47 56	97.60 112	87.55 223	93.17 147	97.59 147	94.71 12	98.42 175	88.28 202	93.20 181	98.24 178

3Dnovator	87.35 11	93.17 146	91.77 160	97.37 49	95.41 209	93.07 76	98.82 139	97.85 60	91.53 102	82.56 268	97.58 148	71.97 266	99.82 76	91.01 168	99.23 70	99.22 105

test_fmvs1		92.35 161	92.94 136	90.57 272	97.19 137	75.43 357	99.55 45	94.97 313	95.20 33	96.82 80	97.57 149	59.59 340	99.84 69	97.30 63	98.29 111	96.46 231

CHOSEN 280x420		96.80 33	96.85 28	96.66 84	97.85 108	94.42 51	94.76 328	98.36 29	92.50 83	95.62 106	97.52 150	97.92 1	97.38 238	98.31 44	98.80 92	98.20 181

IS-MVSNet		93.00 149	92.51 144	94.49 175	96.14 185	87.36 214	98.31 202	95.70 278	88.58 184	90.17 193	97.50 151	83.02 169	97.22 243	87.06 212	96.07 155	98.90 134

OpenMVS	85.28 14	90.75 194	88.84 214	96.48 93	93.58 276	93.51 68	98.80 142	97.41 151	82.59 310	78.62 322	97.49 152	68.00 295	99.82 76	84.52 247	98.55 103	96.11 237

test_fmvs1_n		91.07 187	91.41 167	90.06 286	94.10 257	74.31 361	99.18 93	94.84 317	94.81 35	96.37 90	97.46 153	50.86 372	99.82 76	97.14 66	97.90 114	96.04 238

PCF-MVS	89.78 5	91.26 182	89.63 197	96.16 114	95.44 207	91.58 105	95.29 324	96.10 242	85.07 268	82.75 262	97.45 154	78.28 222	99.78 84	80.60 287	95.65 161	97.12 209
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
VNet		95.08 85	94.26 93	97.55 43	98.07 101	93.88 61	98.68 154	98.73 18	90.33 133	97.16 71	97.43 155	79.19 215	99.53 109	96.91 73	91.85 205	99.24 102

QAPM		91.41 179	89.49 200	97.17 56	95.66 201	93.42 70	98.60 166	97.51 133	80.92 334	81.39 294	97.41 156	72.89 259	99.87 58	82.33 272	98.68 97	98.21 180

casdiffmvs_mvg		94.00 115	93.33 124	96.03 118	95.22 215	90.90 124	99.09 112	95.99 248	90.58 125	91.55 170	97.37 157	79.91 208	98.06 192	95.01 112	95.22 165	99.13 112
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
thisisatest0530		94.00 115	93.52 117	95.43 140	95.76 197	90.02 151	98.99 125	97.60 112	86.58 242	91.74 163	97.36 158	94.78 11	98.34 177	86.37 223	92.48 192	97.94 189

test2506		94.80 92	94.21 95	96.58 88	96.41 169	92.18 95	98.01 228	98.96 11	90.82 117	93.46 144	97.28 159	85.92 123	98.45 174	89.82 184	97.19 133	99.12 113

ECVR-MVS		92.29 163	91.33 168	95.15 151	96.41 169	87.84 199	98.10 220	94.84 317	90.82 117	91.42 174	97.28 159	65.61 314	98.49 173	90.33 178	97.19 133	99.12 113

testing222		94.48 106	94.00 103	95.95 123	97.30 130	92.27 93	98.82 139	97.92 55	89.20 165	94.82 118	97.26 161	87.13 94	97.32 241	91.95 160	91.56 211	98.25 175

test1111		92.12 168	91.19 171	94.94 159	96.15 183	87.36 214	98.12 217	94.84 317	90.85 116	90.97 179	97.26 161	65.60 315	98.37 176	89.74 187	97.14 136	99.07 119

DP-MVS		88.75 235	86.56 254	95.34 143	98.92 77	87.45 211	97.64 252	93.52 349	70.55 373	81.49 292	97.25 163	74.43 242	99.88 54	71.14 347	94.09 174	98.67 154

TR-MVS		90.77 193	89.44 201	94.76 165	96.31 174	88.02 197	97.92 232	95.96 252	85.52 260	88.22 211	97.23 164	66.80 305	98.09 190	84.58 245	92.38 193	98.17 183

Vis-MVSNet		92.64 154	91.85 157	95.03 157	95.12 224	88.23 191	98.48 181	96.81 198	91.61 100	92.16 160	97.22 165	71.58 272	98.00 198	85.85 232	97.81 116	98.88 135
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
testing11		95.33 78	94.98 83	96.37 102	97.20 135	92.31 92	99.29 82	97.68 90	90.59 124	94.43 125	97.20 166	90.79 41	98.60 168	95.25 106	92.38 193	98.18 182

gm-plane-assit					94.69 243	88.14 193			88.22 200		97.20 166		98.29 180	90.79 173

tttt0517		93.30 140	93.01 134	94.17 190	95.57 202	86.47 231	98.51 176	97.60 112	85.99 253	90.55 186	97.19 168	94.80 10	98.31 178	85.06 238	91.86 204	97.74 191

EPP-MVSNet		93.75 125	93.67 115	94.01 198	95.86 193	85.70 259	98.67 156	97.66 95	84.46 278	91.36 175	97.18 169	91.16 30	97.79 208	92.93 150	93.75 177	98.53 160

Effi-MVS+		93.87 121	93.15 130	96.02 119	95.79 195	90.76 126	96.70 289	95.78 273	86.98 233	95.71 103	97.17 170	79.58 210	98.01 197	94.57 124	96.09 153	99.31 96

CLD-MVS		91.06 188	90.71 183	92.10 237	94.05 261	86.10 246	99.55 45	96.29 230	94.16 47	84.70 243	97.17 170	69.62 283	97.82 206	94.74 118	86.08 250	92.39 261
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EI-MVSNet		89.87 213	89.38 204	91.36 254	94.32 252	85.87 255	97.61 253	96.59 208	85.10 266	85.51 237	97.10 172	81.30 201	96.56 270	83.85 259	83.03 277	91.64 285

CVMVSNet		90.30 202	90.91 177	88.46 320	94.32 252	73.58 365	97.61 253	97.59 116	90.16 139	88.43 210	97.10 172	76.83 230	92.86 359	82.64 269	93.54 179	98.93 131

UA-Net		93.30 140	92.62 142	95.34 143	96.27 176	88.53 189	95.88 314	96.97 194	90.90 115	95.37 110	97.07 174	82.38 186	99.10 147	83.91 257	94.86 169	98.38 168

testing99		94.88 88	94.45 89	96.17 112	97.20 135	91.91 97	99.20 90	97.66 95	89.95 144	93.68 140	97.06 175	90.28 50	98.50 171	93.52 139	91.54 213	98.12 184

RPSCF		85.33 291	85.55 269	84.67 347	94.63 246	62.28 386	93.73 338	93.76 343	74.38 364	85.23 240	97.06 175	64.09 321	98.31 178	80.98 281	86.08 250	93.41 253

testing91		94.88 88	94.44 90	96.21 108	97.19 137	91.90 98	99.23 88	97.66 95	89.91 145	93.66 141	97.05 177	90.21 51	98.50 171	93.52 139	91.53 216	98.25 175

EPNet_dtu		92.28 164	92.15 151	92.70 225	97.29 132	84.84 275	98.64 160	97.82 65	92.91 77	93.02 150	97.02 178	85.48 133	95.70 320	72.25 344	94.89 168	97.55 199
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-w/o		92.32 162	91.79 159	93.91 201	96.85 151	86.18 243	99.11 111	95.74 276	88.13 202	84.81 241	97.00 179	77.26 228	97.91 199	89.16 197	98.03 113	97.64 194

thres200		93.69 126	92.59 143	96.97 66	97.76 109	94.74 43	99.35 77	99.36 2	89.23 164	91.21 178	96.97 180	83.42 159	98.77 157	85.08 237	90.96 222	97.39 202

test_vis1_n		90.40 199	90.27 189	90.79 267	91.55 310	76.48 353	99.12 110	94.44 329	94.31 43	97.34 64	96.95 181	43.60 383	99.42 123	97.57 59	97.60 121	96.47 230

baseline2		94.04 114	93.80 113	94.74 167	93.07 288	90.25 137	98.12 217	98.16 39	89.86 146	86.53 230	96.95 181	95.56 6	98.05 194	91.44 164	94.53 170	95.93 239

MSDG		88.29 244	86.37 256	94.04 197	96.90 150	86.15 245	96.52 292	94.36 334	77.89 351	79.22 317	96.95 181	69.72 281	99.59 104	73.20 339	92.58 191	96.37 234

ETVMVS		94.50 105	93.90 110	96.31 105	97.48 124	92.98 79	99.07 114	97.86 59	88.09 204	94.40 127	96.90 184	88.35 69	97.28 242	90.72 175	92.25 199	98.66 157

tfpn200view9		93.43 135	92.27 148	96.90 69	97.68 112	94.84 38	99.18 93	99.36 2	88.45 188	90.79 181	96.90 184	83.31 160	98.75 159	84.11 253	90.69 224	97.12 209

thres400		93.39 137	92.27 148	96.73 78	97.68 112	94.84 38	99.18 93	99.36 2	88.45 188	90.79 181	96.90 184	83.31 160	98.75 159	84.11 253	90.69 224	96.61 224

Anonymous202405211		88.84 229	87.03 248	94.27 185	98.14 100	84.18 284	98.44 184	95.58 286	76.79 355	89.34 203	96.88 187	53.42 364	99.54 108	87.53 211	87.12 241	99.09 116

baseline1		92.61 156	91.28 169	96.58 88	97.05 148	94.63 46	97.72 246	96.20 234	89.82 147	88.56 208	96.85 188	86.85 102	97.82 206	88.42 200	80.10 293	97.30 204

Syy-MVS		84.10 309	84.53 288	82.83 355	95.14 222	65.71 383	97.68 249	96.66 203	86.52 245	82.63 265	96.84 189	68.15 292	89.89 379	45.62 393	91.54 213	92.87 254

myMVS_eth3d		88.68 239	89.07 209	87.50 327	95.14 222	79.74 334	97.68 249	96.66 203	86.52 245	82.63 265	96.84 189	85.22 138	89.89 379	69.43 353	91.54 213	92.87 254

GeoE		90.60 198	89.56 198	93.72 207	95.10 228	85.43 263	99.41 69	94.94 315	83.96 286	87.21 221	96.83 191	74.37 243	97.05 250	80.50 289	93.73 178	98.67 154

thres100view900		93.34 139	92.15 151	96.90 69	97.62 114	94.84 38	99.06 117	99.36 2	87.96 209	90.47 189	96.78 192	83.29 162	98.75 159	84.11 253	90.69 224	97.12 209

thres600view7		93.18 144	92.00 154	96.75 76	97.62 114	94.92 33	99.07 114	99.36 2	87.96 209	90.47 189	96.78 192	83.29 162	98.71 163	82.93 267	90.47 228	96.61 224

h-mvs33		92.47 160	91.95 156	94.05 196	97.13 143	85.01 273	98.36 197	98.08 44	93.85 57	96.27 91	96.73 194	83.19 165	99.43 122	95.81 92	68.09 361	97.70 193

BH-untuned		91.46 178	90.84 179	93.33 211	96.51 165	84.83 276	98.84 138	95.50 290	86.44 249	83.50 253	96.70 195	75.49 235	97.77 210	86.78 220	97.81 116	97.40 201

testing3		87.75 251	88.22 230	86.36 335	94.66 245	77.41 351	99.52 51	97.95 54	86.05 252	81.12 295	96.69 196	86.18 120	89.31 383	61.65 377	90.12 230	92.35 266

NP-MVS					93.94 265	86.22 241					96.67 197

HQP-MVS		91.50 176	91.23 170	92.29 231	93.95 262	86.39 234	99.16 97	96.37 223	93.92 52	87.57 215	96.67 197	73.34 251	97.77 210	93.82 135	86.29 245	92.72 256

HQP_MVS		91.26 182	90.95 176	92.16 235	93.84 269	86.07 249	99.02 121	96.30 227	93.38 68	86.99 223	96.52 199	72.92 257	97.75 216	93.46 142	86.17 248	92.67 258

plane_prior4											96.52 199

CDS-MVSNet		93.47 133	93.04 133	94.76 165	94.75 242	89.45 163	98.82 139	97.03 188	87.91 211	90.97 179	96.48 201	89.06 60	96.36 284	89.50 188	92.81 187	98.49 162
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
OPM-MVS		89.76 214	89.15 208	91.57 251	90.53 324	85.58 261	98.11 219	95.93 258	92.88 78	86.05 231	96.47 202	67.06 304	97.87 203	89.29 195	86.08 250	91.26 306
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
GG-mvs-BLEND				96.98 65	96.53 163	94.81 41	87.20 376	97.74 77		93.91 136	96.40 203	96.56 2	96.94 254	95.08 109	98.95 85	99.20 106

CHOSEN 1792x2688		94.35 108	93.82 112	95.95 123	97.40 125	88.74 184	98.41 188	98.27 31	92.18 93	91.43 172	96.40 203	78.88 216	99.81 79	93.59 138	97.81 116	99.30 97

tmp_tt		53.66 366	52.86 368	56.05 383	32.75 411	41.97 407	73.42 397	76.12 404	21.91 404	39.68 400	96.39 205	42.59 384	65.10 403	78.00 304	14.92 404	61.08 396

PVSNet_Blended_VisFu		94.67 99	94.11 99	96.34 104	97.14 142	91.10 116	99.32 80	97.43 149	92.10 95	91.53 171	96.38 206	83.29 162	99.68 92	93.42 144	96.37 146	98.25 175

dmvs_re		88.69 237	88.06 233	90.59 271	93.83 271	78.68 342	95.75 320	96.18 237	87.99 208	84.48 247	96.32 207	67.52 299	96.94 254	84.98 240	85.49 254	96.14 236

test0.0.03 1		88.96 224	88.61 220	90.03 290	91.09 317	84.43 280	98.97 128	97.02 190	90.21 134	80.29 303	96.31 208	84.89 141	91.93 373	72.98 340	85.70 253	93.73 249

UWE-MVS		93.18 144	93.40 122	92.50 229	96.56 161	83.55 292	98.09 223	97.84 61	89.50 159	91.72 164	96.23 209	91.08 33	96.70 263	86.28 224	93.33 180	97.26 206

hse-mvs2		91.67 175	91.51 165	92.15 236	96.22 178	82.61 308	97.74 245	97.53 127	93.85 57	96.27 91	96.15 210	83.19 165	97.44 235	95.81 92	66.86 368	96.40 233

AUN-MVS		90.17 206	89.50 199	92.19 234	96.21 179	82.67 306	97.76 244	97.53 127	88.05 205	91.67 165	96.15 210	83.10 167	97.47 232	88.11 205	66.91 367	96.43 232

LPG-MVS_test		88.86 228	88.47 226	90.06 286	93.35 283	80.95 328	98.22 207	95.94 255	87.73 218	83.17 258	96.11 212	66.28 310	97.77 210	90.19 180	85.19 255	91.46 296

LGP-MVS_train				90.06 286	93.35 283	80.95 328		95.94 255	87.73 218	83.17 258	96.11 212	66.28 310	97.77 210	90.19 180	85.19 255	91.46 296

WB-MVSnew		88.69 237	88.34 227	89.77 297	94.30 256	85.99 252	98.14 214	97.31 159	87.15 229	87.85 213	96.07 214	69.91 278	95.52 324	72.83 342	91.47 217	87.80 361

TAMVS		92.62 155	92.09 153	94.20 189	94.10 257	87.68 202	98.41 188	96.97 194	87.53 224	89.74 199	96.04 215	84.77 145	96.49 277	88.97 198	92.31 196	98.42 164

Anonymous20240529		87.66 255	85.58 268	93.92 200	97.59 117	85.01 273	98.13 215	97.13 177	66.69 387	88.47 209	96.01 216	55.09 358	99.51 110	87.00 214	84.12 266	97.23 208

dmvs_testset		77.17 343	78.99 330	71.71 371	87.25 363	38.55 408	91.44 361	81.76 399	85.77 256	69.49 365	95.94 217	69.71 282	84.37 391	52.71 390	76.82 311	92.21 271

COLMAP_ROB	82.69 18	84.54 301	82.82 302	89.70 299	96.72 158	78.85 339	95.89 312	92.83 356	71.55 370	77.54 331	95.89 218	59.40 341	99.14 145	67.26 361	88.26 235	91.11 310
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tt0805		86.50 273	84.79 282	91.63 250	91.97 301	81.49 317	96.49 293	97.38 154	82.24 318	82.44 270	95.82 219	51.22 369	98.25 183	84.55 246	80.96 289	95.13 244

PatchMatch-RL		91.47 177	90.54 186	94.26 186	98.20 96	86.36 236	96.94 277	97.14 175	87.75 216	88.98 205	95.75 220	71.80 269	99.40 127	80.92 283	97.39 129	97.02 215

Fast-Effi-MVS+		91.72 174	90.79 182	94.49 175	95.89 192	87.40 213	99.54 50	95.70 278	85.01 271	89.28 204	95.68 221	77.75 225	97.57 230	83.22 262	95.06 167	98.51 161

ACMP	87.39 10	88.71 236	88.24 229	90.12 285	93.91 267	81.06 327	98.50 177	95.67 281	89.43 161	80.37 302	95.55 222	65.67 312	97.83 205	90.55 176	84.51 260	91.47 295
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
AllTest		84.97 295	83.12 300	90.52 275	96.82 152	78.84 340	95.89 312	92.17 364	77.96 349	75.94 336	95.50 223	55.48 354	99.18 139	71.15 345	87.14 239	93.55 251

TestCases				90.52 275	96.82 152	78.84 340		92.17 364	77.96 349	75.94 336	95.50 223	55.48 354	99.18 139	71.15 345	87.14 239	93.55 251

ITE_SJBPF				87.93 322	92.26 296	76.44 354		93.47 350	87.67 221	79.95 308	95.49 225	56.50 351	97.38 238	75.24 322	82.33 283	89.98 339

iter_conf05		93.48 132	93.18 129	94.39 182	97.15 141	94.17 57	99.30 81	92.97 353	92.38 90	86.70 229	95.42 226	95.67 5	96.59 267	94.67 121	84.32 264	92.39 261

testgi		82.29 317	81.00 320	86.17 337	87.24 364	74.84 360	97.39 257	91.62 372	88.63 181	75.85 339	95.42 226	46.07 380	91.55 374	66.87 364	79.94 294	92.12 276

Fast-Effi-MVS+-dtu		88.84 229	88.59 222	89.58 302	93.44 281	78.18 346	98.65 158	94.62 326	88.46 187	84.12 250	95.37 228	68.91 285	96.52 273	82.06 275	91.70 209	94.06 248

SDMVSNet		91.09 186	89.91 193	94.65 170	96.80 154	90.54 133	97.78 240	97.81 68	88.34 195	85.73 233	95.26 229	66.44 309	98.26 182	94.25 128	86.75 242	95.14 242

sd_testset		89.23 220	88.05 234	92.74 224	96.80 154	85.33 266	95.85 317	97.03 188	88.34 195	85.73 233	95.26 229	61.12 335	97.76 215	85.61 233	86.75 242	95.14 242

ACMM	86.95 13	88.77 234	88.22 230	90.43 277	93.61 275	81.34 321	98.50 177	95.92 259	87.88 212	83.85 252	95.20 231	67.20 302	97.89 201	86.90 218	84.90 257	92.06 279
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HyFIR lowres test		93.68 128	93.29 126	94.87 161	97.57 119	88.04 196	98.18 211	98.47 25	87.57 222	91.24 177	95.05 232	85.49 131	97.46 233	93.22 146	92.82 185	99.10 115

mvsmamba		89.99 211	89.42 202	91.69 249	90.64 323	86.34 237	98.40 191	92.27 362	91.01 113	84.80 242	94.93 233	76.12 231	96.51 274	92.81 153	83.84 268	92.21 271

VPNet		88.30 243	86.57 253	93.49 208	91.95 303	91.35 107	98.18 211	97.20 171	88.61 182	84.52 246	94.89 234	62.21 330	96.76 262	89.34 192	72.26 348	92.36 263

TESTMET0.1,1		93.82 123	93.26 127	95.49 138	95.21 216	90.25 137	99.15 103	97.54 126	89.18 167	91.79 162	94.87 235	89.13 59	97.63 223	86.21 225	96.29 150	98.60 158

RRT_MVS		88.91 226	88.56 223	89.93 291	90.31 327	81.61 316	98.08 224	96.38 222	89.30 163	82.41 273	94.84 236	73.15 255	96.04 305	90.38 177	82.23 284	92.15 274

FIs		90.70 195	89.87 194	93.18 213	92.29 295	91.12 114	98.17 213	98.25 32	89.11 169	83.44 254	94.82 237	82.26 187	96.17 299	87.76 208	82.76 279	92.25 267

HY-MVS	88.56 7	95.29 79	94.23 94	98.48 14	97.72 110	96.41 13	94.03 336	98.74 16	92.42 86	95.65 105	94.76 238	86.52 112	99.49 112	95.29 105	92.97 184	99.53 74

FC-MVSNet-test		90.22 204	89.40 203	92.67 227	91.78 307	89.86 155	97.89 233	98.22 35	88.81 179	82.96 261	94.66 239	81.90 193	95.96 308	85.89 231	82.52 282	92.20 273

nrg030		90.23 203	88.87 213	94.32 184	91.53 311	93.54 67	98.79 146	95.89 267	88.12 203	84.55 245	94.61 240	78.80 219	96.88 256	92.35 158	75.21 316	92.53 260

cascas		90.93 191	89.33 205	95.76 129	95.69 199	93.03 78	98.99 125	96.59 208	80.49 336	86.79 228	94.45 241	65.23 318	98.60 168	93.52 139	92.18 200	95.66 241

UniMVSNet_ETH3D		85.65 289	83.79 297	91.21 255	90.41 326	80.75 330	95.36 323	95.78 273	78.76 345	81.83 290	94.33 242	49.86 374	96.66 264	84.30 248	83.52 274	96.22 235

XXY-MVS		87.75 251	86.02 261	92.95 219	90.46 325	89.70 158	97.71 248	95.90 265	84.02 283	80.95 296	94.05 243	67.51 300	97.10 248	85.16 236	78.41 299	92.04 280

test-LLR		93.11 147	92.68 140	94.40 179	94.94 236	87.27 218	99.15 103	97.25 161	90.21 134	91.57 167	94.04 244	84.89 141	97.58 227	85.94 229	96.13 151	98.36 171

test-mter		93.27 142	92.89 137	94.40 179	94.94 236	87.27 218	99.15 103	97.25 161	88.95 174	91.57 167	94.04 244	88.03 77	97.58 227	85.94 229	96.13 151	98.36 171

MVS_Test		93.67 129	92.67 141	96.69 82	96.72 158	92.66 86	97.22 268	96.03 247	87.69 220	95.12 115	94.03 246	81.55 195	98.28 181	89.17 196	96.46 143	99.14 110

ACMH+	83.78 15	84.21 305	82.56 310	89.15 311	93.73 274	79.16 337	96.43 294	94.28 336	81.09 331	74.00 347	94.03 246	54.58 360	97.67 219	76.10 317	78.81 298	90.63 325

MVSTER		92.71 152	92.32 146	93.86 202	97.29 132	92.95 82	99.01 123	96.59 208	90.09 140	85.51 237	94.00 248	94.61 15	96.56 270	90.77 174	83.03 277	92.08 278

UniMVSNet_NR-MVSNet		89.60 216	88.55 224	92.75 223	92.17 298	90.07 146	98.74 149	98.15 40	88.37 193	83.21 256	93.98 249	82.86 171	95.93 310	86.95 215	72.47 345	92.25 267

mvs_anonymous		92.50 159	91.65 162	95.06 154	96.60 160	89.64 159	97.06 273	96.44 220	86.64 241	84.14 249	93.93 250	82.49 180	96.17 299	91.47 163	96.08 154	99.35 92

TranMVSNet+NR-MVSNet		87.75 251	86.31 257	92.07 238	90.81 320	88.56 186	98.33 199	97.18 172	87.76 215	81.87 287	93.90 251	72.45 261	95.43 327	83.13 265	71.30 355	92.23 269

ab-mvs		91.05 189	89.17 207	96.69 82	95.96 191	91.72 101	92.62 350	97.23 165	85.61 259	89.74 199	93.89 252	68.55 288	99.42 123	91.09 166	87.84 237	98.92 133

WR-MVS		88.54 241	87.22 246	92.52 228	91.93 305	89.50 162	98.56 171	97.84 61	86.99 230	81.87 287	93.81 253	74.25 246	95.92 312	85.29 235	74.43 325	92.12 276

PS-MVSNAJss		89.54 218	89.05 210	91.00 260	88.77 347	84.36 281	97.39 257	95.97 250	88.47 185	81.88 286	93.80 254	82.48 181	96.50 275	89.34 192	83.34 276	92.15 274

jajsoiax		87.35 258	86.51 255	89.87 292	87.75 361	81.74 314	97.03 274	95.98 249	88.47 185	80.15 305	93.80 254	61.47 332	96.36 284	89.44 190	84.47 262	91.50 294

DU-MVS		88.83 231	87.51 239	92.79 221	91.46 312	90.07 146	98.71 150	97.62 109	88.87 178	83.21 256	93.68 256	74.63 237	95.93 310	86.95 215	72.47 345	92.36 263

NR-MVSNet		87.74 254	86.00 262	92.96 218	91.46 312	90.68 129	96.65 290	97.42 150	88.02 207	73.42 350	93.68 256	77.31 227	95.83 316	84.26 249	71.82 352	92.36 263

IB-MVS	89.43 6	92.12 168	90.83 181	95.98 122	95.40 210	90.78 125	99.81 12	98.06 45	91.23 111	85.63 236	93.66 258	90.63 42	98.78 156	91.22 165	71.85 351	98.36 171
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
mvs_tets		87.09 261	86.22 258	89.71 298	87.87 357	81.39 320	96.73 288	95.90 265	88.19 201	79.99 307	93.61 259	59.96 339	96.31 292	89.40 191	84.34 263	91.43 298

UGNet		91.91 172	90.85 178	95.10 152	97.06 147	88.69 185	98.01 228	98.24 34	92.41 87	92.39 157	93.61 259	60.52 337	99.68 92	88.14 204	97.25 131	96.92 218
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
ACMH	83.09 17	84.60 299	82.61 309	90.57 272	93.18 286	82.94 299	96.27 299	94.92 316	81.01 332	72.61 359	93.61 259	56.54 350	97.79 208	74.31 329	81.07 288	90.99 312
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		86.75 266	85.92 263	89.22 309	91.97 301	82.47 309	96.91 278	96.14 240	83.74 289	77.73 329	93.53 262	58.19 344	97.37 240	76.75 313	98.35 107	87.84 359

Test_1112_low_res		92.27 165	90.97 175	96.18 110	95.53 205	91.10 116	98.47 183	94.66 325	88.28 199	86.83 227	93.50 263	87.00 99	98.65 167	84.69 243	89.74 233	98.80 144

test_fmvs2		85.10 293	85.45 271	84.02 350	89.85 333	65.63 384	98.49 179	92.59 358	90.45 129	85.43 239	93.32 264	43.94 381	96.59 267	90.81 172	84.19 265	89.85 341

CMPMVS	58.40 21	80.48 326	80.11 325	81.59 361	85.10 373	59.56 389	94.14 335	95.95 254	68.54 381	60.71 385	93.31 265	55.35 357	97.87 203	83.06 266	84.85 259	87.33 365
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		84.74 296	82.93 301	90.16 284	91.73 308	83.54 293	95.00 326	93.30 351	88.77 180	73.19 352	93.30 266	53.62 363	97.65 222	75.88 319	81.54 287	89.30 348

OurMVSNet-221017-0		84.13 308	83.59 298	85.77 340	87.81 358	70.24 376	94.89 327	93.65 347	86.08 251	76.53 332	93.28 267	61.41 333	96.14 301	80.95 282	77.69 307	90.93 313

PVSNet_0	83.28 16	87.31 259	85.16 274	93.74 206	94.78 241	84.59 278	98.91 133	98.69 21	89.81 148	78.59 324	93.23 268	61.95 331	99.34 134	94.75 117	55.72 388	97.30 204

EU-MVSNet		84.19 306	84.42 291	83.52 353	88.64 350	67.37 382	96.04 309	95.76 275	85.29 263	78.44 325	93.18 269	70.67 276	91.48 375	75.79 320	75.98 312	91.70 284

pmmvs4		87.58 257	86.17 260	91.80 244	89.58 337	88.92 179	97.25 265	95.28 302	82.54 312	80.49 301	93.17 270	75.62 234	96.05 304	82.75 268	78.90 297	90.42 328

GA-MVS		90.10 208	88.69 218	94.33 183	92.44 293	87.97 198	99.08 113	96.26 231	89.65 151	86.92 225	93.11 271	68.09 293	96.96 252	82.54 271	90.15 229	98.05 185

CP-MVSNet		86.54 271	85.45 271	89.79 296	91.02 319	82.78 305	97.38 259	97.56 122	85.37 262	79.53 314	93.03 272	71.86 268	95.25 332	79.92 290	73.43 339	91.34 302

LF4IMVS		81.94 320	81.17 319	84.25 349	87.23 365	68.87 381	93.35 342	91.93 369	83.35 297	75.40 341	93.00 273	49.25 377	96.65 265	78.88 298	78.11 301	87.22 367

XVG-ACMP-BASELINE		85.86 282	84.95 278	88.57 318	89.90 331	77.12 352	94.30 332	95.60 285	87.40 226	82.12 279	92.99 274	53.42 364	97.66 220	85.02 239	83.83 269	90.92 314

PS-CasMVS		85.81 284	84.58 287	89.49 306	90.77 321	82.11 311	97.20 269	97.36 156	84.83 274	79.12 319	92.84 275	67.42 301	95.16 334	78.39 303	73.25 340	91.21 307

LTVRE_ROB	81.71 19	84.59 300	82.72 307	90.18 283	92.89 290	83.18 297	93.15 343	94.74 321	78.99 342	75.14 343	92.69 276	65.64 313	97.63 223	69.46 352	81.82 286	89.74 342
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
PEN-MVS		85.21 292	83.93 296	89.07 313	89.89 332	81.31 322	97.09 272	97.24 164	84.45 279	78.66 321	92.68 277	68.44 290	94.87 339	75.98 318	70.92 356	91.04 311

PVSNet_BlendedMVS		93.36 138	93.20 128	93.84 203	98.77 83	91.61 103	99.47 56	98.04 48	91.44 105	94.21 130	92.63 278	83.50 156	99.87 58	97.41 61	83.37 275	90.05 337

DTE-MVSNet		84.14 307	82.80 303	88.14 321	88.95 346	79.87 333	96.81 282	96.24 232	83.50 294	77.60 330	92.52 279	67.89 297	94.24 350	72.64 343	69.05 359	90.32 330

miper_enhance_ethall		90.33 201	89.70 196	92.22 232	97.12 144	88.93 178	98.35 198	95.96 252	88.60 183	83.14 260	92.33 280	87.38 86	96.18 298	86.49 222	77.89 302	91.55 293

FA-MVS(test-final)		92.22 167	91.08 173	95.64 134	96.05 189	88.98 173	91.60 359	97.25 161	86.99 230	91.84 161	92.12 281	83.03 168	99.00 150	86.91 217	93.91 176	98.93 131

SixPastTwentyTwo		82.63 316	81.58 314	85.79 339	88.12 355	71.01 374	95.17 325	92.54 359	84.33 280	72.93 357	92.08 282	60.41 338	95.61 323	74.47 328	74.15 330	90.75 321

UniMVSNet (Re)		89.50 219	88.32 228	93.03 215	92.21 297	90.96 122	98.90 134	98.39 27	89.13 168	83.22 255	92.03 283	81.69 194	96.34 290	86.79 219	72.53 344	91.81 283

pmmvs5		85.87 281	84.40 292	90.30 282	88.53 351	84.23 282	98.60 166	93.71 345	81.53 326	80.29 303	92.02 284	64.51 320	95.52 324	82.04 276	78.34 300	91.15 308

pm-mvs1		84.68 298	82.78 305	90.40 278	89.58 337	85.18 269	97.31 261	94.73 322	81.93 323	76.05 335	92.01 285	65.48 316	96.11 302	78.75 300	69.14 358	89.91 340

VPA-MVSNet		89.10 222	87.66 238	93.45 209	92.56 291	91.02 120	97.97 231	98.32 30	86.92 235	86.03 232	92.01 285	68.84 287	97.10 248	90.92 169	75.34 315	92.23 269

FE-MVS		91.38 180	90.16 191	95.05 156	96.46 167	87.53 208	89.69 373	97.84 61	82.97 303	92.18 159	92.00 287	84.07 151	98.93 153	80.71 285	95.52 162	98.68 153

MVP-Stereo		86.61 270	85.83 264	88.93 316	88.70 349	83.85 289	96.07 308	94.41 333	82.15 320	75.64 340	91.96 288	67.65 298	96.45 280	77.20 309	98.72 96	86.51 371
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_djsdf		88.26 245	87.73 236	89.84 294	88.05 356	82.21 310	97.77 242	96.17 238	86.84 236	82.41 273	91.95 289	72.07 265	95.99 306	89.83 182	84.50 261	91.32 303

cl22		89.57 217	88.79 216	91.91 240	97.94 105	87.62 205	97.98 230	96.51 215	85.03 269	82.37 275	91.79 290	83.65 154	96.50 275	85.96 228	77.89 302	91.61 290

v2v482		87.27 260	85.76 265	91.78 248	89.59 336	87.58 206	98.56 171	95.54 288	84.53 277	82.51 269	91.78 291	73.11 256	96.47 278	82.07 274	74.14 331	91.30 304

TinyColmap		80.42 327	77.94 332	87.85 323	92.09 299	78.58 343	93.74 337	89.94 381	74.99 360	69.77 364	91.78 291	46.09 379	97.58 227	65.17 369	77.89 302	87.38 363

TransMVSNet (Re)		81.97 319	79.61 328	89.08 312	89.70 335	84.01 286	97.26 264	91.85 370	78.84 343	73.07 356	91.62 293	67.17 303	95.21 333	67.50 360	59.46 382	88.02 358

FMVSNet3		88.81 233	87.08 247	93.99 199	96.52 164	94.59 47	98.08 224	96.20 234	85.85 254	82.12 279	91.60 294	74.05 247	95.40 329	79.04 295	80.24 290	91.99 281

eth_miper_zixun_eth		87.76 250	87.00 249	90.06 286	94.67 244	82.65 307	97.02 276	95.37 299	84.19 281	81.86 289	91.58 295	81.47 197	95.90 314	83.24 261	73.61 334	91.61 290

miper_ehance_all_eth		88.94 225	88.12 232	91.40 252	95.32 212	86.93 224	97.85 237	95.55 287	84.19 281	81.97 284	91.50 296	84.16 149	95.91 313	84.69 243	77.89 302	91.36 301

Effi-MVS+-dtu		89.97 212	90.68 184	87.81 324	95.15 221	71.98 371	97.87 236	95.40 297	91.92 96	87.57 215	91.44 297	74.27 245	96.84 257	89.45 189	93.10 183	94.60 247

c3_l		88.19 246	87.23 245	91.06 258	94.97 234	86.17 244	97.72 246	95.38 298	83.43 295	81.68 291	91.37 298	82.81 172	95.72 319	84.04 256	73.70 333	91.29 305

Baseline_NR-MVSNet		85.83 283	84.82 281	88.87 317	88.73 348	83.34 295	98.63 161	91.66 371	80.41 339	82.44 270	91.35 299	74.63 237	95.42 328	84.13 252	71.39 354	87.84 359

DIV-MVS_self_test		87.82 248	86.81 251	90.87 265	94.87 239	85.39 265	97.81 238	95.22 311	82.92 307	80.76 298	91.31 300	81.99 190	95.81 317	81.36 279	75.04 318	91.42 299

cl____		87.82 248	86.79 252	90.89 264	94.88 238	85.43 263	97.81 238	95.24 306	82.91 308	80.71 299	91.22 301	81.97 192	95.84 315	81.34 280	75.06 317	91.40 300

IterMVS-LS		88.34 242	87.44 240	91.04 259	94.10 257	85.85 256	98.10 220	95.48 291	85.12 265	82.03 283	91.21 302	81.35 200	95.63 322	83.86 258	75.73 314	91.63 286
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet2		86.90 263	84.79 282	93.24 212	95.11 225	92.54 90	97.67 251	95.86 271	82.94 304	80.55 300	91.17 303	62.89 327	95.29 331	77.23 307	79.71 296	91.90 282

TDRefinement		78.01 339	75.31 343	86.10 338	70.06 398	73.84 363	93.59 341	91.58 373	74.51 363	73.08 355	91.04 304	49.63 376	97.12 245	74.88 325	59.47 381	87.33 365

ppachtmachnet_test		83.63 312	81.57 315	89.80 295	89.01 344	85.09 272	97.13 271	94.50 328	78.84 343	76.14 334	91.00 305	69.78 280	94.61 346	63.40 371	74.36 326	89.71 344

tfpnnormal		83.65 311	81.35 317	90.56 274	91.37 314	88.06 195	97.29 262	97.87 58	78.51 346	76.20 333	90.91 306	64.78 319	96.47 278	61.71 376	73.50 336	87.13 368

WR-MVS_H		86.53 272	85.49 270	89.66 301	91.04 318	83.31 296	97.53 255	98.20 36	84.95 272	79.64 311	90.90 307	78.01 224	95.33 330	76.29 316	72.81 341	90.35 329

Anonymous20231211		84.72 297	82.65 308	90.91 262	97.71 111	84.55 279	97.28 263	96.67 202	66.88 386	79.18 318	90.87 308	58.47 343	96.60 266	82.61 270	74.20 329	91.59 292

v1144		86.83 265	85.31 273	91.40 252	89.75 334	87.21 222	98.31 202	95.45 293	83.22 298	82.70 264	90.78 309	73.36 250	96.36 284	79.49 292	74.69 322	90.63 325

CostFormer		92.89 150	92.48 145	94.12 192	94.99 233	85.89 254	92.89 346	97.00 192	86.98 233	95.00 117	90.78 309	90.05 53	97.51 231	92.92 151	91.73 208	98.96 125

v1921920		86.02 279	84.44 290	90.77 268	89.32 342	85.20 268	98.10 220	95.35 301	82.19 319	82.25 277	90.71 311	70.73 275	96.30 295	76.85 312	74.49 324	90.80 317

anonymousdsp		86.69 267	85.75 266	89.53 303	86.46 369	82.94 299	96.39 295	95.71 277	83.97 285	79.63 312	90.70 312	68.85 286	95.94 309	86.01 226	84.02 267	89.72 343

tpmrst		92.78 151	92.16 150	94.65 170	96.27 176	87.45 211	91.83 355	97.10 182	89.10 170	94.68 122	90.69 313	88.22 71	97.73 218	89.78 185	91.80 206	98.77 148

V42		87.00 262	85.68 267	90.98 261	89.91 330	86.08 247	98.32 201	95.61 284	83.67 292	82.72 263	90.67 314	74.00 248	96.53 272	81.94 277	74.28 328	90.32 330

tpm2		91.77 173	91.09 172	93.82 204	94.83 240	85.56 262	92.51 351	97.16 174	84.00 284	93.83 138	90.66 315	87.54 83	97.17 244	87.73 209	91.55 212	98.72 150

EPMVS		92.59 157	91.59 163	95.59 137	97.22 134	90.03 150	91.78 356	98.04 48	90.42 131	91.66 166	90.65 316	86.49 114	97.46 233	81.78 278	96.31 148	99.28 99

LCM-MVSNet-Re		88.59 240	88.61 220	88.51 319	95.53 205	72.68 369	96.85 281	88.43 388	88.45 188	73.14 353	90.63 317	75.82 232	94.38 348	92.95 149	95.71 160	98.48 163

SCA		90.64 197	89.25 206	94.83 164	94.95 235	88.83 180	96.26 301	97.21 167	90.06 143	90.03 195	90.62 318	66.61 306	96.81 259	83.16 263	94.36 172	98.84 138

Patchmatch-test		86.25 277	84.06 294	92.82 220	94.42 248	82.88 303	82.88 391	94.23 337	71.58 369	79.39 315	90.62 318	89.00 62	96.42 281	63.03 373	91.37 220	99.16 108

v1192		86.32 276	84.71 284	91.17 256	89.53 339	86.40 233	98.13 215	95.44 295	82.52 313	82.42 272	90.62 318	71.58 272	96.33 291	77.23 307	74.88 319	90.79 318

v144192		86.40 274	84.89 279	90.91 262	89.48 340	85.59 260	98.21 209	95.43 296	82.45 315	82.62 267	90.58 321	72.79 260	96.36 284	78.45 302	74.04 332	90.79 318

PatchmatchNet		92.05 171	91.04 174	95.06 154	96.17 182	89.04 170	91.26 364	97.26 160	89.56 157	90.64 185	90.56 322	88.35 69	97.11 246	79.53 291	96.07 155	99.03 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v1240		85.77 286	84.11 293	90.73 269	89.26 343	85.15 271	97.88 235	95.23 310	81.89 324	82.16 278	90.55 323	69.60 284	96.31 292	75.59 321	74.87 320	90.72 322

our_test_3		84.47 303	82.80 303	89.50 304	89.01 344	83.90 288	97.03 274	94.56 327	81.33 328	75.36 342	90.52 324	71.69 270	94.54 347	68.81 355	76.84 310	90.07 335

miper_lstm_enhance		86.90 263	86.20 259	89.00 314	94.53 247	81.19 324	96.74 287	95.24 306	82.33 317	80.15 305	90.51 325	81.99 190	94.68 345	80.71 285	73.58 335	91.12 309

MDTV_nov1_ep13			90.47 188		96.14 185	88.55 187	91.34 363	97.51 133	89.58 155	92.24 158	90.50 326	86.99 100	97.61 225	77.64 306	92.34 195

IterMVS-SCA-FT		85.73 287	84.64 286	89.00 314	93.46 280	82.90 301	96.27 299	94.70 323	85.02 270	78.62 322	90.35 327	66.61 306	93.33 355	79.38 294	77.36 309	90.76 320

D2MVS		87.96 247	87.39 241	89.70 299	91.84 306	83.40 294	98.31 202	98.49 23	88.04 206	78.23 328	90.26 328	73.57 249	96.79 261	84.21 250	83.53 273	88.90 353

GBi-Net		86.67 268	84.96 276	91.80 244	95.11 225	88.81 181	96.77 283	95.25 303	82.94 304	82.12 279	90.25 329	62.89 327	94.97 336	79.04 295	80.24 290	91.62 287

test1		86.67 268	84.96 276	91.80 244	95.11 225	88.81 181	96.77 283	95.25 303	82.94 304	82.12 279	90.25 329	62.89 327	94.97 336	79.04 295	80.24 290	91.62 287

FMVSNet1		83.94 310	81.32 318	91.80 244	91.94 304	88.81 181	96.77 283	95.25 303	77.98 347	78.25 327	90.25 329	50.37 373	94.97 336	73.27 338	77.81 306	91.62 287

v148		86.38 275	85.06 275	90.37 281	89.47 341	84.10 285	98.52 173	95.48 291	83.80 288	80.93 297	90.22 332	74.60 239	96.31 292	80.92 283	71.55 353	90.69 323

lessismore_v0				85.08 343	85.59 372	69.28 379		90.56 379		67.68 373	90.21 333	54.21 362	95.46 326	73.88 333	62.64 376	90.50 327

dp		90.16 207	88.83 215	94.14 191	96.38 172	86.42 232	91.57 360	97.06 185	84.76 275	88.81 206	90.19 334	84.29 148	97.43 236	75.05 323	91.35 221	98.56 159

IterMVS		85.81 284	84.67 285	89.22 309	93.51 277	83.67 291	96.32 298	94.80 320	85.09 267	78.69 320	90.17 335	66.57 308	93.17 358	79.48 293	77.42 308	90.81 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_0402		78.81 335	76.33 340	86.26 336	91.18 316	78.44 345	95.88 314	91.34 375	68.55 380	70.51 363	89.91 336	52.65 366	94.99 335	47.14 392	79.78 295	85.34 377

v8		86.11 278	84.45 289	91.10 257	89.99 329	86.85 225	97.24 266	95.36 300	81.99 321	79.89 309	89.86 337	74.53 241	96.39 282	78.83 299	72.32 347	90.05 337

v10		85.73 287	84.01 295	90.87 265	90.03 328	86.73 227	97.20 269	95.22 311	81.25 329	79.85 310	89.75 338	73.30 253	96.28 296	76.87 311	72.64 343	89.61 345

test20.03		78.51 338	77.48 334	81.62 360	83.07 379	71.03 373	96.11 307	92.83 356	81.66 325	69.31 366	89.68 339	57.53 346	87.29 389	58.65 383	68.47 360	86.53 370

pmmvs6		79.90 329	77.31 335	87.67 325	84.17 376	78.13 347	95.86 316	93.68 346	67.94 383	72.67 358	89.62 340	50.98 371	95.75 318	74.80 327	66.04 369	89.14 351

tpm		89.67 215	88.95 212	91.82 243	92.54 292	81.43 318	92.95 345	95.92 259	87.81 213	90.50 188	89.44 341	84.99 139	95.65 321	83.67 260	82.71 280	98.38 168

v7n		84.42 304	82.75 306	89.43 307	88.15 354	81.86 313	96.75 286	95.67 281	80.53 335	78.38 326	89.43 342	69.89 279	96.35 289	73.83 335	72.13 349	90.07 335

K. test v3		81.04 324	79.77 327	84.83 345	87.41 362	70.23 377	95.60 322	93.93 342	83.70 291	67.51 374	89.35 343	55.76 352	93.58 354	76.67 314	68.03 362	90.67 324

tpmvs		89.16 221	87.76 235	93.35 210	97.19 137	84.75 277	90.58 371	97.36 156	81.99 321	84.56 244	89.31 344	83.98 152	98.17 185	74.85 326	90.00 231	97.12 209

Anonymous20231206		80.76 325	79.42 329	84.79 346	84.78 374	72.98 366	96.53 291	92.97 353	79.56 340	74.33 344	88.83 345	61.27 334	92.15 370	60.59 379	75.92 313	89.24 350

EG-PatchMatch MVS		79.92 328	77.59 333	86.90 332	87.06 366	77.90 350	96.20 306	94.06 340	74.61 362	66.53 378	88.76 346	40.40 388	96.20 297	67.02 362	83.66 272	86.61 369

tpm cat1		88.89 227	87.27 244	93.76 205	95.79 195	85.32 267	90.76 369	97.09 183	76.14 357	85.72 235	88.59 347	82.92 170	98.04 195	76.96 310	91.43 218	97.90 190

DeepMVS_CX				76.08 366	90.74 322	51.65 399		90.84 377	86.47 248	57.89 387	87.98 348	35.88 391	92.60 363	65.77 367	65.06 372	83.97 382

MDA-MVSNet-bldmvs		77.82 341	74.75 347	87.03 331	88.33 352	78.52 344	96.34 297	92.85 355	75.57 358	48.87 393	87.89 349	57.32 348	92.49 367	60.79 378	64.80 373	90.08 334

UnsupCasMVSNet_eth		78.90 334	76.67 339	85.58 341	82.81 381	74.94 359	91.98 354	96.31 226	84.64 276	65.84 380	87.71 350	51.33 368	92.23 369	72.89 341	56.50 387	89.56 346

MIMVSNet		84.48 302	81.83 312	92.42 230	91.73 308	87.36 214	85.52 380	94.42 332	81.40 327	81.91 285	87.58 351	51.92 367	92.81 361	73.84 334	88.15 236	97.08 213

YYNet1		79.64 332	77.04 337	87.43 329	87.80 359	79.98 332	96.23 303	94.44 329	73.83 366	51.83 390	87.53 352	67.96 296	92.07 372	66.00 366	67.75 365	90.23 332

APD_test1		68.93 355	66.98 358	74.77 369	80.62 386	53.15 396	87.97 375	85.01 394	53.76 392	59.26 386	87.52 353	25.19 395	89.95 378	56.20 385	67.33 366	81.19 387

KD-MVS_2432*1600		82.98 314	80.52 322	90.38 279	94.32 252	88.98 173	92.87 347	95.87 269	80.46 337	73.79 348	87.49 354	82.76 175	93.29 356	70.56 349	46.53 397	88.87 354

miper_refine_blended		82.98 314	80.52 322	90.38 279	94.32 252	88.98 173	92.87 347	95.87 269	80.46 337	73.79 348	87.49 354	82.76 175	93.29 356	70.56 349	46.53 397	88.87 354

MDA-MVSNet_test_wron		79.65 331	77.05 336	87.45 328	87.79 360	80.13 331	96.25 302	94.44 329	73.87 365	51.80 391	87.47 356	68.04 294	92.12 371	66.02 365	67.79 364	90.09 333

ADS-MVSNet2		87.62 256	86.88 250	89.86 293	96.21 179	79.14 338	87.15 377	92.99 352	83.01 301	89.91 197	87.27 357	78.87 217	92.80 362	74.20 331	92.27 197	97.64 194

ADS-MVSNet		88.99 223	87.30 243	94.07 194	96.21 179	87.56 207	87.15 377	96.78 200	83.01 301	89.91 197	87.27 357	78.87 217	97.01 251	74.20 331	92.27 197	97.64 194

DSMNet-mixed		81.60 322	81.43 316	82.10 358	84.36 375	60.79 387	93.63 340	86.74 391	79.00 341	79.32 316	87.15 359	63.87 323	89.78 381	66.89 363	91.92 203	95.73 240

OpenMVS_ROB	73.86 20	77.99 340	75.06 346	86.77 333	83.81 378	77.94 349	96.38 296	91.53 374	67.54 384	68.38 369	87.13 360	43.94 381	96.08 303	55.03 387	81.83 285	86.29 372

CR-MVSNet		88.83 231	87.38 242	93.16 214	93.47 278	86.24 239	84.97 384	94.20 338	88.92 177	90.76 183	86.88 361	84.43 146	94.82 341	70.64 348	92.17 201	98.41 165

Patchmtry		83.61 313	81.64 313	89.50 304	93.36 282	82.84 304	84.10 387	94.20 338	69.47 379	79.57 313	86.88 361	84.43 146	94.78 342	68.48 357	74.30 327	90.88 315

N_pmnet		70.19 353	69.87 355	71.12 373	88.24 353	30.63 412	95.85 317	28.70 411	70.18 375	68.73 368	86.55 363	64.04 322	93.81 351	53.12 389	73.46 337	88.94 352

MIMVSNet1		75.92 345	73.30 350	83.81 352	81.29 384	75.57 356	92.26 352	92.05 367	73.09 368	67.48 375	86.18 364	40.87 387	87.64 388	55.78 386	70.68 357	88.21 357

FMVSNet5		82.29 317	80.54 321	87.52 326	93.79 273	84.01 286	93.73 338	92.47 360	76.92 354	74.27 345	86.15 365	63.69 325	89.24 384	69.07 354	74.79 321	89.29 349

CL-MVSNet_self_test		79.89 330	78.34 331	84.54 348	81.56 383	75.01 358	96.88 280	95.62 283	81.10 330	75.86 338	85.81 366	68.49 289	90.26 377	63.21 372	56.51 386	88.35 356

patchmatchnet-post											84.86 367	88.73 65	96.81 259

Anonymous20240521		78.63 337	76.90 338	83.82 351	82.82 380	72.86 367	95.72 321	93.57 348	73.55 367	72.17 360	84.79 368	49.69 375	92.51 366	65.29 368	74.50 323	86.09 373

test_method		70.10 354	68.66 357	74.41 370	86.30 371	55.84 392	94.47 329	89.82 382	35.18 399	66.15 379	84.75 369	30.54 393	77.96 400	70.40 351	60.33 380	89.44 347

EGC-MVSNET		60.70 360	55.37 364	76.72 365	86.35 370	71.08 372	89.96 372	84.44 396	0.38 408	1.50 409	84.09 370	37.30 389	88.10 387	40.85 397	73.44 338	70.97 393

KD-MVS_self_test		77.47 342	75.88 342	82.24 356	81.59 382	68.93 380	92.83 349	94.02 341	77.03 353	73.14 353	83.39 371	55.44 356	90.42 376	67.95 358	57.53 385	87.38 363

PM-MVS		74.88 348	72.85 351	80.98 362	78.98 389	64.75 385	90.81 368	85.77 392	80.95 333	68.23 371	82.81 372	29.08 394	92.84 360	76.54 315	62.46 377	85.36 376

mvsany_test3		75.85 346	74.52 348	79.83 363	73.53 395	60.64 388	91.73 357	87.87 390	83.91 287	70.55 362	82.52 373	31.12 392	93.66 352	86.66 221	62.83 374	85.19 379

test_vis1_rt		81.31 323	80.05 326	85.11 342	91.29 315	70.66 375	98.98 127	77.39 403	85.76 257	68.80 367	82.40 374	36.56 390	99.44 119	92.67 155	86.55 244	85.24 378

pmmvs-eth3d		78.71 336	76.16 341	86.38 334	80.25 387	81.19 324	94.17 334	92.13 366	77.97 348	66.90 377	82.31 375	55.76 352	92.56 365	73.63 337	62.31 378	85.38 375

Patchmatch-RL test		81.90 321	80.13 324	87.23 330	80.71 385	70.12 378	84.07 388	88.19 389	83.16 300	70.57 361	82.18 376	87.18 93	92.59 364	82.28 273	62.78 375	98.98 123

WB-MVS		66.44 356	66.29 359	66.89 376	74.84 392	44.93 403	93.00 344	84.09 397	71.15 371	55.82 388	81.63 377	63.79 324	80.31 398	21.85 402	50.47 395	75.43 389

new_pmnet		76.02 344	73.71 349	82.95 354	83.88 377	72.85 368	91.26 364	92.26 363	70.44 374	62.60 383	81.37 378	47.64 378	92.32 368	61.85 375	72.10 350	83.68 383

test_fmvs3		75.09 347	75.19 344	74.81 368	77.45 391	54.08 394	95.93 310	90.64 378	82.51 314	73.29 351	81.19 379	22.29 397	86.29 390	85.50 234	67.89 363	84.06 381

FPMVS		61.57 358	60.32 361	65.34 378	60.14 405	42.44 406	91.02 367	89.72 383	44.15 394	42.63 397	80.93 380	19.02 399	80.59 397	42.50 394	72.76 342	73.00 391

SSC-MVS		65.42 357	65.20 360	66.06 377	73.96 393	43.83 404	92.08 353	83.54 398	69.77 377	54.73 389	80.92 381	63.30 326	79.92 399	20.48 403	48.02 396	74.44 390

pmmvs3		72.86 351	69.76 356	82.17 357	73.86 394	74.19 362	94.20 333	89.01 386	64.23 390	67.72 372	80.91 382	41.48 385	88.65 386	62.40 374	54.02 390	83.68 383

ambc				79.60 364	72.76 397	56.61 391	76.20 395	92.01 368		68.25 370	80.23 383	23.34 396	94.73 343	73.78 336	60.81 379	87.48 362

new-patchmatchnet		74.80 349	72.40 352	81.99 359	78.36 390	72.20 370	94.44 330	92.36 361	77.06 352	63.47 382	79.98 384	51.04 370	88.85 385	60.53 380	54.35 389	84.92 380

PatchT		85.44 290	83.19 299	92.22 232	93.13 287	83.00 298	83.80 390	96.37 223	70.62 372	90.55 186	79.63 385	84.81 143	94.87 339	58.18 384	91.59 210	98.79 145

RPMNet		85.07 294	81.88 311	94.64 172	93.47 278	86.24 239	84.97 384	97.21 167	64.85 389	90.76 183	78.80 386	80.95 203	99.27 137	53.76 388	92.17 201	98.41 165

test_f		71.94 352	70.82 353	75.30 367	72.77 396	53.28 395	91.62 358	89.66 384	75.44 359	64.47 381	78.31 387	20.48 398	89.56 382	78.63 301	66.02 370	83.05 386

testf1		56.38 363	53.73 366	64.31 380	64.84 400	45.11 401	80.50 393	75.94 405	38.87 395	42.74 395	75.07 388	11.26 407	81.19 394	41.11 395	53.27 391	66.63 394

APD_test2		56.38 363	53.73 366	64.31 380	64.84 400	45.11 401	80.50 393	75.94 405	38.87 395	42.74 395	75.07 388	11.26 407	81.19 394	41.11 395	53.27 391	66.63 394

UnsupCasMVSNet_bld		73.85 350	70.14 354	84.99 344	79.44 388	75.73 355	88.53 374	95.24 306	70.12 376	61.94 384	74.81 390	41.41 386	93.62 353	68.65 356	51.13 394	85.62 374

LCM-MVSNet		60.07 361	56.37 363	71.18 372	54.81 407	48.67 400	82.17 392	89.48 385	37.95 397	49.13 392	69.12 391	13.75 405	81.76 392	59.28 381	51.63 393	83.10 385

PMMVS2		58.97 362	55.07 365	70.69 374	62.72 402	55.37 393	85.97 379	80.52 400	49.48 393	45.94 394	68.31 392	15.73 403	80.78 396	49.79 391	37.12 399	75.91 388

JIA-IIPM		85.97 280	84.85 280	89.33 308	93.23 285	73.68 364	85.05 383	97.13 177	69.62 378	91.56 169	68.03 393	88.03 77	96.96 252	77.89 305	93.12 182	97.34 203

testmvs		18.81 373	23.05 376	6.10 390	4.48 412	2.29 415	97.78 240	3.00 413	3.27 406	18.60 406	62.71 394	1.53 413	2.49 409	14.26 407	1.80 406	13.50 404

gg-mvs-nofinetune		90.00 210	87.71 237	96.89 73	96.15 183	94.69 45	85.15 382	97.74 77	68.32 382	92.97 151	60.16 395	96.10 3	96.84 257	93.89 131	98.87 89	99.14 110

PMVS	41.42 23	45.67 368	42.50 371	55.17 384	34.28 410	32.37 410	66.24 398	78.71 402	30.72 400	22.04 405	59.59 396	4.59 409	77.85 401	27.49 400	58.84 383	55.29 398
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVS-HIRNet		79.01 333	75.13 345	90.66 270	93.82 272	81.69 315	85.16 381	93.75 344	54.54 391	74.17 346	59.15 397	57.46 347	96.58 269	63.74 370	94.38 171	93.72 250

test_vis3_rt		61.29 359	58.75 362	68.92 375	67.41 399	52.84 397	91.18 366	59.23 410	66.96 385	41.96 398	58.44 398	11.37 406	94.72 344	74.25 330	57.97 384	59.20 397

ANet_high		50.71 367	46.17 370	64.33 379	44.27 409	52.30 398	76.13 396	78.73 401	64.95 388	27.37 402	55.23 399	14.61 404	67.74 402	36.01 398	18.23 402	72.95 392

Gipuma		54.77 365	52.22 369	62.40 382	86.50 368	59.37 390	50.20 400	90.35 380	36.52 398	41.20 399	49.49 400	18.33 401	81.29 393	32.10 399	65.34 371	46.54 400
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	44.00 22	41.70 369	37.64 374	53.90 385	49.46 408	43.37 405	65.09 399	66.66 407	26.19 403	25.77 404	48.53 401	3.58 411	63.35 404	26.15 401	27.28 400	54.97 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		41.02 370	40.93 372	41.29 386	61.97 403	33.83 409	84.00 389	65.17 408	27.17 401	27.56 401	46.72 402	17.63 402	60.41 405	19.32 404	18.82 401	29.61 401

test_post											46.00 403	87.37 87	97.11 246

test123		16.58 375	19.47 377	7.91 389	3.59 413	5.37 414	94.32 331	1.39 414	2.49 407	13.98 407	44.60 404	2.91 412	2.65 408	11.35 408	0.57 407	15.70 403

EMVS		39.96 371	39.88 373	40.18 387	59.57 406	32.12 411	84.79 386	64.57 409	26.27 402	26.14 403	44.18 405	18.73 400	59.29 406	17.03 405	17.67 403	29.12 402

test_post1							90.74 370				41.37 406	85.38 135	96.36 284	83.16 263

X-MVStestdata		90.69 196	88.66 219	96.77 74	99.62 22	90.66 130	99.43 66	97.58 118	92.41 87	96.86 75	29.59 407	87.37 87	99.87 58	95.65 94	99.43 60	99.78 38

wuyk23d		16.71 374	16.73 378	16.65 388	60.15 404	25.22 413	41.24 401	5.17 412	6.56 405	5.48 408	3.61 408	3.64 410	22.72 407	15.20 406	9.52 405	1.99 405

test_blank		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

pcd_1.5k_mvsjas		6.87 377	9.16 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	82.48 181	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		0.00 378	0.00 381	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	0.00 409	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

WAC-MVS						79.74 334								67.75 359

FOURS1					99.50 42	88.94 176	99.55 45	97.47 141	91.32 109	98.12 45

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 88					99.98 9	99.55 12	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 88					99.98 9	99.55 12	99.83 15	99.96 10

eth-test2					0.00 414

eth-test					0.00 414

IU-MVS					99.63 18	95.38 22		97.73 80	95.54 28	99.54 3				99.69 6	99.81 23	99.99 1

save fliter					99.34 50	93.85 62	99.65 36	97.63 107	95.69 22

test_0728_SECOND				98.77 8	99.66 12	96.37 14	99.72 24	97.68 90					99.98 9	99.64 7	99.82 19	99.96 10

GSMVS																98.84 138

test_part2					99.54 36	95.42 20				98.13 43

sam_mvs1												88.39 68				98.84 138

sam_mvs												87.08 96

MTGPA								97.45 144

MTMP							99.21 89	91.09 376

test9_res														98.60 33	99.87 9	99.90 22

agg_prior2														97.84 56	99.87 9	99.91 21

agg_prior					99.54 36	92.66 86		97.64 103		97.98 52			99.61 102

test_prior4						92.00 96	99.41 69

test_prior				97.01 60	99.58 30	91.77 99		97.57 121					99.49 112			99.79 36

旧先验2							98.67 156		85.75 258	98.96 21			98.97 152	93.84 133

新几何2							98.26 205

无先验							98.52 173	97.82 65	87.20 228				99.90 50	87.64 210		99.85 30

原ACMM2							98.69 153

testdata2													99.88 54	84.16 251

segment_acmp												90.56 43

testdata1							97.89 233		92.43 84

test12				97.83 33	99.33 53	94.45 49		97.55 123		97.56 57		88.60 66	99.50 111		99.71 34	99.55 72

plane_prior7					93.84 269	85.73 258

plane_prior6					93.92 266	86.02 251						72.92 257

plane_prior5								96.30 227					97.75 216	93.46 142	86.17 248	92.67 258

plane_prior3						85.91 253			93.65 63	86.99 223

plane_prior2							99.02 121		93.38 68

plane_prior1					93.90 268

plane_prior						86.07 249	99.14 106		93.81 60						86.26 247

n2								0.00 415

nn								0.00 415

door-mid								84.90 395

test11								97.68 90

door								85.30 393

HQP5-MVS						86.39 234

HQP-NCC					93.95 262		99.16 97		93.92 52	87.57 215

ACMP_Plane					93.95 262		99.16 97		93.92 52	87.57 215

BP-MVS														93.82 135

HQP4-MVS										87.57 215			97.77 210			92.72 256

HQP3-MVS								96.37 223							86.29 245

HQP2-MVS												73.34 251

MDTV_nov1_ep13_2view						91.17 113	91.38 362		87.45 225	93.08 149		86.67 107		87.02 213		98.95 129

ACMMP++_ref															82.64 281

ACMMP++															83.83 269

Test By Simon												83.62 155

High-resolution multi-view benchmark