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.

AdaColmap		93.82 131	93.06 139	96.10 120	99.88 1	89.07 173	98.33 204	97.55 125	86.81 245	90.39 201	98.65 101	75.09 249	99.98 9	93.32 156	97.53 131	99.26 108

DP-MVS Recon		95.85 66	95.15 82	97.95 32	99.87 2	94.38 55	99.60 39	97.48 141	86.58 249	94.42 132	99.13 47	87.36 98	99.98 9	93.64 148	98.33 114	99.48 86

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 4	95.96 99	99.33 22	92.62 25	100.00 1	98.99 25	99.93 1	99.98 6

CNVR-MVS		98.46 1	98.38 1	98.72 10	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

MG-MVS		97.24 20	96.83 31	98.47 15	99.79 5	95.71 19	99.07 113	99.06 10	94.45 41	96.42 93	98.70 98	88.81 71	99.74 91	95.35 113	99.86 12	99.97 7

NCCC		98.12 5	98.11 3	98.13 25	99.76 6	94.46 51	99.81 12	97.88 58	96.54 13	98.84 24	99.46 10	92.55 26	99.98 9	98.25 50	99.93 1	99.94 18

region2R		96.30 50	96.17 52	96.70 85	99.70 7	90.31 140	99.46 59	97.66 97	90.55 132	97.07 73	99.07 54	86.85 109	99.97 21	95.43 111	99.74 29	99.81 35

HFP-MVS		96.42 46	96.26 46	96.90 73	99.69 8	90.96 126	99.47 55	97.81 69	90.54 133	96.88 76	99.05 57	87.57 90	99.96 28	95.65 104	99.72 32	99.78 41

ACMMPR		96.28 51	96.14 56	96.73 82	99.68 9	90.47 138	99.47 55	97.80 71	90.54 133	96.83 81	99.03 59	86.51 121	99.95 32	95.65 104	99.72 32	99.75 49

ZD-MVS					99.67 10	93.28 75		97.61 112	87.78 220	97.41 63	99.16 39	90.15 54	99.56 108	98.35 45	99.70 37

CP-MVS		96.22 52	96.15 55	96.42 102	99.67 10	89.62 164	99.70 27	97.61 112	90.07 148	96.00 98	99.16 39	87.43 93	99.92 41	96.03 99	99.72 32	99.70 55

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 32	99.72 24	97.47 143	93.95 49	99.07 15	99.46 10	93.18 21	99.97 21	99.64 8	99.82 19	99.69 58
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_SECOND				98.77 8	99.66 12	96.37 14	99.72 24	97.68 92					99.98 9	99.64 8	99.82 19	99.96 10

test0726					99.66 12	95.20 32	99.77 18	97.70 88	93.95 49	99.35 7	99.54 3	93.18 21

CPTT-MVS		94.60 109	94.43 97	95.09 161	99.66 12	86.85 234	99.44 62	97.47 143	83.22 305	94.34 136	98.96 70	82.50 187	99.55 109	94.81 127	99.50 55	98.88 143

MSLP-MVS++		97.50 17	97.45 18	97.63 41	99.65 16	93.21 77	99.70 27	98.13 42	94.61 36	97.78 58	99.46 10	89.85 57	99.81 79	97.97 54	99.91 6	99.88 26

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 18				99.19 33	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 27	99.77 18	97.72 83	94.17 44	99.30 8	99.54 3	93.32 18	99.98 9	99.70 5	99.81 23	99.99 1

IU-MVS					99.63 18	95.38 24		97.73 82	95.54 26	99.54 3				99.69 7	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 27		97.72 83	94.16 46	99.30 8	99.49 9	93.32 18	99.98 9

PAPR		96.35 47	95.82 62	97.94 33	99.63 18	94.19 60	99.42 67	97.55 125	92.43 87	93.82 147	99.12 49	87.30 100	99.91 46	94.02 140	99.06 80	99.74 50

XVS		96.47 45	96.37 44	96.77 78	99.62 22	90.66 134	99.43 65	97.58 120	92.41 90	96.86 77	98.96 70	87.37 95	99.87 58	95.65 104	99.43 61	99.78 41

X-MVStestdata		90.69 206	88.66 229	96.77 78	99.62 22	90.66 134	99.43 65	97.58 120	92.41 90	96.86 77	29.59 422	87.37 95	99.87 58	95.65 104	99.43 61	99.78 41

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 24	99.55 44	97.68 92	93.01 74	99.23 10	99.45 14	95.12 8	99.98 9	99.25 18	99.92 3	99.97 7

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 90					99.98 9	99.55 13	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 90					99.98 9	99.55 13	99.83 15	99.96 10

DeepC-MVS_fast	93.52 2	97.16 24	96.84 29	98.13 25	99.61 24	94.45 52	98.85 135	97.64 105	96.51 16	95.88 102	99.39 18	87.35 99	99.99 5	96.61 85	99.69 38	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
test_one_0601					99.59 28	94.89 37		97.64 105	93.14 73	98.93 21	99.45 14	93.45 17

CDPH-MVS		96.56 43	96.18 49	97.70 39	99.59 28	93.92 63	99.13 107	97.44 149	89.02 177	97.90 55	99.22 30	88.90 70	99.49 115	94.63 132	99.79 27	99.68 60

test_prior				97.01 64	99.58 30	91.77 104		97.57 123					99.49 115			99.79 38

APDe-MVS		97.53 15	97.47 16	97.70 39	99.58 30	93.63 67	99.56 43	97.52 133	93.59 64	98.01 52	99.12 49	90.80 42	99.55 109	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
mPP-MVS		95.90 65	95.75 67	96.38 105	99.58 30	89.41 168	99.26 85	97.41 153	90.66 125	94.82 124	98.95 73	86.15 129	99.98 9	95.24 118	99.64 42	99.74 50

TEST9					99.57 33	93.17 78	99.38 71	97.66 97	89.57 162	98.39 37	99.18 36	90.88 40	99.66 97

train_agg		97.20 23	97.08 23	97.57 45	99.57 33	93.17 78	99.38 71	97.66 97	90.18 142	98.39 37	99.18 36	90.94 37	99.66 97	98.58 36	99.85 13	99.88 26

test_8					99.55 35	93.07 81	99.37 74	97.64 105	90.18 142	98.36 39	99.19 33	90.94 37	99.64 103

test_part2					99.54 36	95.42 22				98.13 44

MSP-MVS		97.77 10	98.18 2	96.53 97	99.54 36	90.14 146	99.41 68	97.70 88	95.46 28	98.60 31	99.19 33	95.71 5	99.49 115	98.15 52	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
agg_prior					99.54 36	92.66 91		97.64 105		97.98 53			99.61 105

CSCG		94.87 98	94.71 91	95.36 149	99.54 36	86.49 239	99.34 77	98.15 40	82.71 318	90.15 204	99.25 26	89.48 62	99.86 63	94.97 125	98.82 95	99.72 53

HPM-MVS++		97.72 12	97.59 13	98.14 24	99.53 40	94.76 45	99.19 90	97.75 78	95.66 24	98.21 42	99.29 23	91.10 34	99.99 5	97.68 60	99.87 9	99.68 60

APD-MVS		96.95 29	96.72 35	97.63 41	99.51 41	93.58 68	99.16 96	97.44 149	90.08 147	98.59 32	99.07 54	89.06 65	99.42 126	97.92 55	99.66 39	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
FOURS1					99.50 42	88.94 182	99.55 44	97.47 143	91.32 113	98.12 46

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 23	99.29 80	97.72 83	94.50 38	98.64 30	99.54 3	93.32 18	99.97 21	99.58 11	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
PGM-MVS		95.85 66	95.65 72	96.45 100	99.50 42	89.77 161	98.22 213	98.90 13	89.19 172	96.74 86	98.95 73	85.91 133	99.92 41	93.94 141	99.46 57	99.66 64

GST-MVS		95.97 60	95.66 70	96.90 73	99.49 45	91.22 113	99.45 61	97.48 141	89.69 156	95.89 101	98.72 94	86.37 124	99.95 32	94.62 133	99.22 74	99.52 80

MP-MVS		96.00 57	95.82 62	96.54 96	99.47 46	90.13 148	99.36 75	97.41 153	90.64 128	95.49 114	98.95 73	85.51 138	99.98 9	96.00 100	99.59 51	99.52 80
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.09 55	95.81 64	96.95 72	99.42 47	91.19 115	99.55 44	97.53 129	89.72 155	95.86 104	98.94 76	86.59 117	99.97 21	95.13 119	99.56 52	99.68 60

SR-MVS		96.13 54	96.16 54	96.07 121	99.42 47	89.04 174	98.59 171	97.33 163	90.44 136	96.84 79	99.12 49	86.75 111	99.41 129	97.47 63	99.44 60	99.76 48

PAPM_NR		95.43 80	95.05 87	96.57 95	99.42 47	90.14 146	98.58 173	97.51 135	90.65 127	92.44 165	98.90 79	87.77 89	99.90 50	90.88 180	99.32 66	99.68 60

9.14			96.87 27		99.34 50		99.50 51	97.49 140	89.41 169	98.59 32	99.43 16	89.78 58	99.69 94	98.69 30	99.62 46

save fliter					99.34 50	93.85 65	99.65 36	97.63 109	95.69 22

PHI-MVS		96.65 40	96.46 42	97.21 58	99.34 50	91.77 104	99.70 27	98.05 46	86.48 254	98.05 49	99.20 32	89.33 63	99.96 28	98.38 43	99.62 46	99.90 22

test12				97.83 35	99.33 53	94.45 52		97.55 125		97.56 59		88.60 74	99.50 114		99.71 36	99.55 77

SMA-MVS		97.24 20	96.99 24	98.00 31	99.30 54	94.20 59	99.16 96	97.65 104	89.55 164	99.22 12	99.52 8	90.34 51	99.99 5	98.32 47	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
MTAPA		96.09 55	95.80 65	96.96 71	99.29 55	91.19 115	97.23 274	97.45 146	92.58 84	94.39 134	99.24 28	86.43 123	99.99 5	96.22 92	99.40 64	99.71 54

HPM-MVS		95.41 82	95.22 80	95.99 127	99.29 55	89.14 171	99.17 95	97.09 188	87.28 234	95.40 115	98.48 116	84.93 148	99.38 131	95.64 108	99.65 40	99.47 88
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		94.67 107	94.30 98	95.79 134	99.25 57	88.13 203	98.41 192	98.67 21	90.38 138	91.43 182	98.72 94	82.22 196	99.95 32	93.83 145	95.76 165	99.29 105
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
APD-MVS_3200maxsize		95.64 77	95.65 72	95.62 142	99.24 58	87.80 209	98.42 190	97.22 171	88.93 182	96.64 91	98.98 64	85.49 139	99.36 133	96.68 82	99.27 70	99.70 55

SR-MVS-dyc-post		95.75 72	95.86 61	95.41 148	99.22 59	87.26 229	98.40 195	97.21 172	89.63 158	96.67 89	98.97 65	86.73 113	99.36 133	96.62 83	99.31 67	99.60 73

RE-MVS-def			95.70 68		99.22 59	87.26 229	98.40 195	97.21 172	89.63 158	96.67 89	98.97 65	85.24 145		96.62 83	99.31 67	99.60 73

patch_mono-2		97.10 26	97.97 8	94.49 183	99.21 61	83.73 299	99.62 38	98.25 31	95.28 30	99.38 6	98.91 78	92.28 29	99.94 35	99.61 10	99.22 74	99.78 41

API-MVS		94.78 101	94.18 104	96.59 92	99.21 61	90.06 153	98.80 141	97.78 75	83.59 300	93.85 145	99.21 31	83.79 161	99.97 21	92.37 167	99.00 84	99.74 50

PLC	91.07 3	94.23 119	94.01 108	94.87 169	99.17 63	87.49 218	99.25 86	96.55 223	88.43 197	91.26 186	98.21 129	85.92 131	99.86 63	89.77 195	97.57 128	97.24 217
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EI-MVSNet-Vis-set		95.76 71	95.63 74	96.17 117	99.14 64	90.33 139	98.49 183	97.82 66	91.92 98	94.75 126	98.88 83	87.06 105	99.48 119	95.40 112	97.17 141	98.70 160

TSAR-MVS + MP.		97.44 18	97.46 17	97.39 52	99.12 65	93.49 72	98.52 177	97.50 138	94.46 39	98.99 17	98.64 102	91.58 31	99.08 151	98.49 40	99.83 15	99.60 73
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		97.22 22	96.92 25	98.12 27	99.11 66	94.88 38	99.44 62	97.45 146	89.60 160	98.70 27	99.42 17	90.42 48	99.72 92	98.47 41	99.65 40	99.77 46

HPM-MVS_fast		94.89 94	94.62 92	95.70 137	99.11 66	88.44 199	99.14 104	97.11 184	85.82 262	95.69 110	98.47 117	83.46 166	99.32 138	93.16 158	99.63 45	99.35 99

MAR-MVS		94.43 115	94.09 106	95.45 146	99.10 68	87.47 219	98.39 199	97.79 73	88.37 199	94.02 142	99.17 38	78.64 233	99.91 46	92.48 166	98.85 94	98.96 133
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
114514_t		94.06 121	93.05 140	97.06 62	99.08 69	92.26 99	98.97 127	97.01 196	82.58 320	92.57 163	98.22 127	80.68 214	99.30 139	89.34 201	99.02 83	99.63 70

EI-MVSNet-UG-set		95.43 80	95.29 78	95.86 132	99.07 70	89.87 158	98.43 189	97.80 71	91.78 100	94.11 139	98.77 88	86.25 127	99.48 119	94.95 126	96.45 151	98.22 189

原ACMM1				96.18 115	99.03 71	90.08 149		97.63 109	88.98 178	97.00 74	98.97 65	88.14 83	99.71 93	88.23 213	99.62 46	98.76 157

SD-MVS		97.51 16	97.40 19	97.81 36	99.01 72	93.79 66	99.33 78	97.38 156	93.73 60	98.83 25	99.02 61	90.87 41	99.88 54	98.69 30	99.74 29	99.77 46
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
MVS_0304		97.81 9	97.51 15	98.74 9	98.97 73	96.57 11	99.91 2	98.17 36	97.45 3	98.76 26	98.97 65	86.69 114	99.96 28	99.72 3	98.92 90	99.69 58

旧先验1					98.97 73	92.90 89		97.74 79			99.15 42	91.05 36			99.33 65	99.60 73

LS3D		90.19 216	88.72 227	94.59 182	98.97 73	86.33 246	96.90 286	96.60 217	74.96 374	84.06 260	98.74 91	75.78 246	99.83 73	74.93 334	97.57 128	97.62 207

CNLPA		93.64 138	92.74 147	96.36 107	98.96 76	90.01 156	99.19 90	95.89 280	86.22 257	89.40 213	98.85 84	80.66 215	99.84 69	88.57 209	96.92 145	99.24 109

reproduce-ours		96.66 37	96.80 32	96.22 111	98.95 77	89.03 176	98.62 163	97.38 156	93.42 66	96.80 84	99.36 19	88.92 68	99.80 81	98.51 38	99.26 71	99.82 32

our_new_method		96.66 37	96.80 32	96.22 111	98.95 77	89.03 176	98.62 163	97.38 156	93.42 66	96.80 84	99.36 19	88.92 68	99.80 81	98.51 38	99.26 71	99.82 32

MP-MVS-pluss		95.80 68	95.30 77	97.29 54	98.95 77	92.66 91	98.59 171	97.14 180	88.95 180	93.12 156	99.25 26	85.62 135	99.94 35	96.56 87	99.48 56	99.28 106
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
reproduce_model		96.57 42	96.75 34	96.02 124	98.93 80	88.46 198	98.56 174	97.34 162	93.18 72	96.96 75	99.35 21	88.69 73	99.80 81	98.53 37	99.21 77	99.79 38

新几何1				97.40 51	98.92 81	92.51 96		97.77 77	85.52 267	96.69 88	99.06 56	88.08 84	99.89 53	84.88 251	99.62 46	99.79 38

DP-MVS		88.75 244	86.56 263	95.34 151	98.92 81	87.45 220	97.64 258	93.52 363	70.55 387	81.49 301	97.25 166	74.43 255	99.88 54	71.14 358	94.09 181	98.67 162

TSAR-MVS + GP.		96.95 29	96.91 26	97.07 61	98.88 83	91.62 107	99.58 41	96.54 224	95.09 32	96.84 79	98.63 104	91.16 32	99.77 88	99.04 24	96.42 152	99.81 35

CANet		97.00 28	96.49 40	98.55 12	98.86 84	96.10 16	99.83 10	97.52 133	95.90 19	97.21 69	98.90 79	82.66 186	99.93 39	98.71 29	98.80 96	99.63 70

dcpmvs_2		95.67 76	96.18 49	94.12 199	98.82 85	84.22 292	97.37 267	95.45 307	90.70 124	95.77 107	98.63 104	90.47 46	98.68 171	99.20 20	99.22 74	99.45 89

ACMMP_NAP		96.59 41	96.18 49	97.81 36	98.82 85	93.55 69	98.88 134	97.59 118	90.66 125	97.98 53	99.14 45	86.59 117	100.00 1	96.47 89	99.46 57	99.89 25

PVSNet_BlendedMVS		93.36 146	93.20 137	93.84 211	98.77 87	91.61 108	99.47 55	98.04 48	91.44 109	94.21 137	92.63 286	83.50 164	99.87 58	97.41 64	83.37 283	90.05 348

PVSNet_Blended		95.94 63	95.66 70	96.75 80	98.77 87	91.61 108	99.88 4	98.04 48	93.64 63	94.21 137	97.76 140	83.50 164	99.87 58	97.41 64	97.75 126	98.79 153

DeepPCF-MVS	93.56 1	96.55 44	97.84 10	92.68 236	98.71 89	78.11 358	99.70 27	97.71 87	98.18 1	97.36 65	99.76 1	90.37 50	99.94 35	99.27 16	99.54 54	99.99 1

EPNet		96.82 33	96.68 37	97.25 57	98.65 90	93.10 80	99.48 53	98.76 14	96.54 13	97.84 56	98.22 127	87.49 92	99.66 97	95.35 113	97.78 125	99.00 129
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		93.90 128	93.62 125	94.73 176	98.63 91	87.00 232	98.04 232	96.56 222	92.19 94	92.46 164	98.73 92	79.49 224	99.14 148	92.16 169	94.34 180	98.03 196

MVS_111021_HR		96.69 36	96.69 36	96.72 84	98.58 92	91.00 125	99.14 104	99.45 1	93.86 55	95.15 120	98.73 92	88.48 75	99.76 89	97.23 70	99.56 52	99.40 93

test_yl		95.27 86	94.60 93	97.28 55	98.53 93	92.98 84	99.05 117	98.70 18	86.76 246	94.65 129	97.74 142	87.78 87	99.44 122	95.57 109	92.61 197	99.44 90

DCV-MVSNet		95.27 86	94.60 93	97.28 55	98.53 93	92.98 84	99.05 117	98.70 18	86.76 246	94.65 129	97.74 142	87.78 87	99.44 122	95.57 109	92.61 197	99.44 90

TAPA-MVS	87.50 9	90.35 211	89.05 220	94.25 194	98.48 95	85.17 278	98.42 190	96.58 221	82.44 325	87.24 231	98.53 108	82.77 181	98.84 160	59.09 396	97.88 121	98.72 158
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.32 96	91.21 114	98.08 230	97.58 120	83.74 296	95.87 103	99.02 61	86.74 112			99.64 42	99.81 35

MM		97.76 11	97.39 20	98.86 5	98.30 97	96.83 7	99.81 12	99.13 9	97.66 2	98.29 41	98.96 70	85.84 134	99.90 50	99.72 3	98.80 96	99.85 30

reproduce_monomvs		92.11 178	91.82 168	92.98 226	98.25 98	90.55 136	98.38 201	97.93 55	94.81 33	80.46 311	92.37 288	96.46 3	97.17 254	94.06 139	73.61 343	91.23 316

DPM-MVS		97.86 8	97.25 22	99.68 1	98.25 98	99.10 1	99.76 21	97.78 75	96.61 12	98.15 43	99.53 7	93.62 16	100.00 1	91.79 172	99.80 26	99.94 18

LFMVS		92.23 174	90.84 189	96.42 102	98.24 100	91.08 122	98.24 212	96.22 243	83.39 303	94.74 127	98.31 123	61.12 349	98.85 159	94.45 135	92.82 193	99.32 102

testdata				95.26 156	98.20 101	87.28 226		97.60 114	85.21 271	98.48 35	99.15 42	88.15 82	98.72 169	90.29 188	99.45 59	99.78 41

PatchMatch-RL		91.47 186	90.54 196	94.26 193	98.20 101	86.36 245	96.94 284	97.14 180	87.75 222	88.98 216	95.75 226	71.80 282	99.40 130	80.92 293	97.39 135	97.02 225

MVS_111021_LR		95.78 69	95.94 58	95.28 155	98.19 103	87.69 210	98.80 141	99.26 7	93.39 68	95.04 122	98.69 99	84.09 158	99.76 89	96.96 76	99.06 80	98.38 176

F-COLMAP		92.07 179	91.75 171	93.02 225	98.16 104	82.89 311	98.79 145	95.97 262	86.54 251	87.92 223	97.80 137	78.69 232	99.65 101	85.97 237	95.93 164	96.53 239

Anonymous202405211		88.84 238	87.03 257	94.27 192	98.14 105	84.18 293	98.44 188	95.58 300	76.79 366	89.34 214	96.88 190	53.42 378	99.54 111	87.53 221	87.12 251	99.09 124

VNet		95.08 91	94.26 99	97.55 46	98.07 106	93.88 64	98.68 154	98.73 17	90.33 139	97.16 72	97.43 158	79.19 227	99.53 112	96.91 78	91.85 213	99.24 109

SPE-MVS-test		95.98 59	96.34 45	94.90 168	98.06 107	87.66 213	99.69 34	96.10 253	93.66 61	98.35 40	99.05 57	86.28 125	97.66 230	96.96 76	98.90 92	99.37 96

DELS-MVS		97.12 25	96.60 38	98.68 11	98.03 108	96.57 11	99.84 9	97.84 62	96.36 18	95.20 119	98.24 126	88.17 80	99.83 73	96.11 97	99.60 50	99.64 68
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
PVSNet	87.13 12	93.69 134	92.83 146	96.28 110	97.99 109	90.22 144	99.38 71	98.93 12	91.42 111	93.66 149	97.68 145	71.29 287	99.64 103	87.94 217	97.20 138	98.98 131

test_fmvsm_n_1920		97.08 27	97.55 14	95.67 139	97.94 110	89.61 165	99.93 1	98.48 23	97.08 5	99.08 14	99.13 47	88.17 80	99.93 39	99.11 23	99.06 80	97.47 210

cl22		89.57 227	88.79 226	91.91 250	97.94 110	87.62 214	97.98 235	96.51 225	85.03 276	82.37 284	91.79 299	83.65 162	96.50 284	85.96 238	77.89 309	91.61 299

CS-MVS		95.75 72	96.19 47	94.40 187	97.88 112	86.22 249	99.66 35	96.12 252	92.69 83	98.07 48	98.89 81	87.09 103	97.59 236	96.71 80	98.62 104	99.39 95

CHOSEN 280x420		96.80 34	96.85 28	96.66 89	97.85 113	94.42 54	94.76 340	98.36 28	92.50 86	95.62 112	97.52 153	97.92 1	97.38 248	98.31 48	98.80 96	98.20 191

thres200		93.69 134	92.59 152	96.97 70	97.76 114	94.74 46	99.35 76	99.36 2	89.23 170	91.21 188	96.97 183	83.42 167	98.77 163	85.08 247	90.96 232	97.39 212

HY-MVS	88.56 7	95.29 85	94.23 100	98.48 14	97.72 115	96.41 13	94.03 349	98.74 15	92.42 89	95.65 111	94.76 244	86.52 120	99.49 115	95.29 116	92.97 192	99.53 79

Anonymous20231211		84.72 306	82.65 318	90.91 271	97.71 116	84.55 288	97.28 270	96.67 212	66.88 400	79.18 328	90.87 320	58.47 357	96.60 277	82.61 280	74.20 338	91.59 301

tfpn200view9		93.43 142	92.27 157	96.90 73	97.68 117	94.84 41	99.18 92	99.36 2	88.45 194	90.79 191	96.90 187	83.31 168	98.75 166	84.11 263	90.69 234	97.12 219

thres400		93.39 144	92.27 157	96.73 82	97.68 117	94.84 41	99.18 92	99.36 2	88.45 194	90.79 191	96.90 187	83.31 168	98.75 166	84.11 263	90.69 234	96.61 234

thres100view900		93.34 147	92.15 160	96.90 73	97.62 119	94.84 41	99.06 116	99.36 2	87.96 215	90.47 199	96.78 195	83.29 170	98.75 166	84.11 263	90.69 234	97.12 219

thres600view7		93.18 152	92.00 163	96.75 80	97.62 119	94.92 36	99.07 113	99.36 2	87.96 215	90.47 199	96.78 195	83.29 170	98.71 170	82.93 277	90.47 238	96.61 234

WTY-MVS		95.97 60	95.11 85	98.54 13	97.62 119	96.65 9	99.44 62	98.74 15	92.25 93	95.21 118	98.46 119	86.56 119	99.46 121	95.00 124	92.69 196	99.50 84

balanced_conf03		96.83 32	96.51 39	97.81 36	97.60 122	95.15 34	98.40 195	96.77 208	93.00 76	98.69 28	96.19 214	89.75 59	98.76 165	98.45 42	99.72 32	99.51 82

fmvsm_l_conf0.5_n_a		97.70 13	97.80 11	97.42 49	97.59 123	92.91 88	99.86 5	98.04 48	96.70 10	99.58 2	99.26 24	90.90 39	99.94 35	99.57 12	98.66 103	99.40 93

Anonymous20240529		87.66 264	85.58 277	93.92 208	97.59 123	85.01 281	98.13 221	97.13 182	66.69 401	88.47 220	96.01 221	55.09 370	99.51 113	87.00 224	84.12 274	97.23 218

HyFIR lowres test		93.68 136	93.29 135	94.87 169	97.57 125	88.04 205	98.18 217	98.47 24	87.57 228	91.24 187	95.05 240	85.49 139	97.46 243	93.22 157	92.82 193	99.10 123

sasdasda		95.02 92	93.96 113	98.20 21	97.53 126	95.92 17	98.71 149	96.19 246	91.78 100	95.86 104	98.49 113	79.53 222	99.03 152	96.12 95	91.42 227	99.66 64

canonicalmvs		95.02 92	93.96 113	98.20 21	97.53 126	95.92 17	98.71 149	96.19 246	91.78 100	95.86 104	98.49 113	79.53 222	99.03 152	96.12 95	91.42 227	99.66 64

fmvsm_l_conf0.5_n		97.65 14	97.72 12	97.41 50	97.51 128	92.78 90	99.85 8	98.05 46	96.78 8	99.60 1	99.23 29	90.42 48	99.92 41	99.55 13	98.50 108	99.55 77

MGCFI-Net		94.89 94	93.84 120	98.06 29	97.49 129	95.55 21	98.64 160	96.10 253	91.60 105	95.75 108	98.46 119	79.31 226	98.98 156	95.95 101	91.24 231	99.65 67

ETVMVS		94.50 113	93.90 118	96.31 109	97.48 130	92.98 84	99.07 113	97.86 60	88.09 210	94.40 133	96.90 187	88.35 77	97.28 252	90.72 185	92.25 207	98.66 165

CHOSEN 1792x2688		94.35 116	93.82 121	95.95 129	97.40 131	88.74 191	98.41 192	98.27 30	92.18 95	91.43 182	96.40 207	78.88 228	99.81 79	93.59 149	97.81 122	99.30 104

SteuartSystems-ACMMP		97.25 19	97.34 21	97.01 64	97.38 132	91.46 111	99.75 22	97.66 97	94.14 48	98.13 44	99.26 24	92.16 30	99.66 97	97.91 56	99.64 42	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n		96.19 53	96.49 40	95.30 154	97.37 133	89.16 170	99.86 5	98.47 24	95.68 23	98.87 22	99.15 42	82.44 193	99.92 41	99.14 21	97.43 134	96.83 230

alignmvs		95.77 70	95.00 88	98.06 29	97.35 134	95.68 20	99.71 26	97.50 138	91.50 107	96.16 97	98.61 106	86.28 125	99.00 154	96.19 93	91.74 215	99.51 82

PS-MVSNAJ		96.87 31	96.40 43	98.29 19	97.35 134	97.29 5	99.03 119	97.11 184	95.83 20	98.97 19	99.14 45	82.48 189	99.60 106	98.60 33	99.08 78	98.00 197

testing222		94.48 114	94.00 109	95.95 129	97.30 136	92.27 98	98.82 138	97.92 56	89.20 171	94.82 124	97.26 164	87.13 102	97.32 251	91.95 170	91.56 219	98.25 185

EPNet_dtu		92.28 172	92.15 160	92.70 235	97.29 137	84.84 284	98.64 160	97.82 66	92.91 80	93.02 158	97.02 181	85.48 141	95.70 331	72.25 355	94.89 175	97.55 209
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVSTER		92.71 160	92.32 155	93.86 210	97.29 137	92.95 87	99.01 122	96.59 218	90.09 146	85.51 247	94.00 254	94.61 15	96.56 280	90.77 184	83.03 285	92.08 287

MVSMamba_PlusPlus		95.73 74	95.15 82	97.44 47	97.28 139	94.35 57	98.26 210	96.75 209	83.09 308	97.84 56	95.97 222	89.59 61	98.48 180	97.86 57	99.73 31	99.49 85

EPMVS		92.59 165	91.59 173	95.59 144	97.22 140	90.03 154	91.78 370	98.04 48	90.42 137	91.66 176	90.65 328	86.49 122	97.46 243	81.78 288	96.31 155	99.28 106

testing11		95.33 84	94.98 89	96.37 106	97.20 141	92.31 97	99.29 80	97.68 92	90.59 129	94.43 131	97.20 169	90.79 43	98.60 174	95.25 117	92.38 201	98.18 192

testing99		94.88 96	94.45 95	96.17 117	97.20 141	91.91 102	99.20 89	97.66 97	89.95 150	93.68 148	97.06 178	90.28 52	98.50 177	93.52 150	91.54 221	98.12 194

testing91		94.88 96	94.44 96	96.21 113	97.19 143	91.90 103	99.23 87	97.66 97	89.91 151	93.66 149	97.05 180	90.21 53	98.50 177	93.52 150	91.53 224	98.25 185

test_fmvs1		92.35 169	92.94 144	90.57 281	97.19 143	75.43 370	99.55 44	94.97 327	95.20 31	96.82 82	97.57 152	59.59 354	99.84 69	97.30 67	98.29 117	96.46 241

tpmvs		89.16 231	87.76 244	93.35 219	97.19 143	84.75 286	90.58 385	97.36 160	81.99 331	84.56 253	89.31 357	83.98 160	98.17 194	74.85 336	90.00 241	97.12 219

DeepC-MVS	91.02 4	94.56 112	93.92 116	96.46 99	97.16 146	90.76 130	98.39 199	97.11 184	93.92 51	88.66 218	98.33 122	78.14 237	99.85 67	95.02 122	98.57 106	98.78 155
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PVSNet_Blended_VisFu		94.67 107	94.11 105	96.34 108	97.14 147	91.10 120	99.32 79	97.43 151	92.10 97	91.53 181	96.38 210	83.29 170	99.68 95	93.42 155	96.37 153	98.25 185

h-mvs33		92.47 168	91.95 165	94.05 203	97.13 148	85.01 281	98.36 202	98.08 44	93.85 56	96.27 95	96.73 198	83.19 173	99.43 125	95.81 102	68.09 372	97.70 203

miper_enhance_ethall		90.33 212	89.70 207	92.22 242	97.12 149	88.93 184	98.35 203	95.96 264	88.60 189	83.14 269	92.33 289	87.38 94	96.18 309	86.49 232	77.89 309	91.55 302

xiu_mvs_v2_base		96.66 37	96.17 52	98.11 28	97.11 150	96.96 6	99.01 122	97.04 191	95.51 27	98.86 23	99.11 53	82.19 197	99.36 133	98.59 35	98.14 118	98.00 197

mamv4		91.41 188	93.57 126	84.91 358	97.11 150	58.11 405	95.68 331	95.93 270	82.09 330	89.78 209	95.71 227	90.09 55	98.24 191	97.26 68	98.50 108	98.38 176

VDD-MVS		91.24 195	90.18 201	94.45 186	97.08 152	85.84 265	98.40 195	96.10 253	86.99 237	93.36 153	98.16 130	54.27 374	99.20 141	96.59 86	90.63 237	98.31 183

UGNet		91.91 181	90.85 188	95.10 160	97.06 153	88.69 192	98.01 233	98.24 33	92.41 90	92.39 167	93.61 266	60.52 351	99.68 95	88.14 214	97.25 137	96.92 228
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
baseline1		92.61 164	91.28 179	96.58 93	97.05 154	94.63 49	97.72 252	96.20 244	89.82 153	88.56 219	96.85 191	86.85 109	97.82 216	88.42 210	80.10 300	97.30 214

CANet_DTU		94.31 117	93.35 132	97.20 59	97.03 155	94.71 47	98.62 163	95.54 302	95.61 25	97.21 69	98.47 117	71.88 280	99.84 69	88.38 211	97.46 133	97.04 224

WBMVS		91.35 191	90.49 197	93.94 207	96.97 156	93.40 74	99.27 84	96.71 210	87.40 232	83.10 270	91.76 302	92.38 27	96.23 307	88.95 208	77.89 309	92.17 283

UBG		95.73 74	95.41 75	96.69 86	96.97 156	93.23 76	99.13 107	97.79 73	91.28 114	94.38 135	96.78 195	92.37 28	98.56 176	96.17 94	93.84 184	98.26 184

MSDG		88.29 253	86.37 265	94.04 204	96.90 158	86.15 253	96.52 299	94.36 349	77.89 361	79.22 327	96.95 184	69.72 294	99.59 107	73.20 349	92.58 199	96.37 244

BH-w/o		92.32 170	91.79 169	93.91 209	96.85 159	86.18 251	99.11 110	95.74 290	88.13 208	84.81 251	97.00 182	77.26 242	97.91 209	89.16 206	98.03 119	97.64 204

AllTest		84.97 304	83.12 310	90.52 284	96.82 160	78.84 350	95.89 321	92.17 376	77.96 359	75.94 347	95.50 230	55.48 366	99.18 142	71.15 356	87.14 249	93.55 261

TestCases				90.52 284	96.82 160	78.84 350		92.17 376	77.96 359	75.94 347	95.50 230	55.48 366	99.18 142	71.15 356	87.14 249	93.55 261

SDMVSNet		91.09 196	89.91 204	94.65 178	96.80 162	90.54 137	97.78 245	97.81 69	88.34 201	85.73 243	95.26 237	66.44 323	98.26 189	94.25 138	86.75 252	95.14 252

sd_testset		89.23 230	88.05 243	92.74 234	96.80 162	85.33 274	95.85 326	97.03 193	88.34 201	85.73 243	95.26 237	61.12 349	97.76 225	85.61 243	86.75 252	95.14 252

PMMVS		93.62 139	93.90 118	92.79 231	96.79 164	81.40 327	98.85 135	96.81 204	91.25 115	96.82 82	98.15 131	77.02 243	98.13 196	93.15 159	96.30 156	98.83 149

BH-RMVSNet		91.25 194	89.99 203	95.03 165	96.75 165	88.55 195	98.65 158	94.95 328	87.74 223	87.74 225	97.80 137	68.27 305	98.14 195	80.53 298	97.49 132	98.41 173

MVS_Test		93.67 137	92.67 149	96.69 86	96.72 166	92.66 91	97.22 275	96.03 259	87.69 226	95.12 121	94.03 252	81.55 203	98.28 188	89.17 205	96.46 150	99.14 117

COLMAP_ROB	82.69 18	84.54 310	82.82 312	89.70 307	96.72 166	78.85 349	95.89 321	92.83 369	71.55 384	77.54 342	95.89 224	59.40 355	99.14 148	67.26 373	88.26 245	91.11 320
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
mvs_anonymous		92.50 167	91.65 172	95.06 162	96.60 168	89.64 163	97.06 280	96.44 230	86.64 248	84.14 258	93.93 257	82.49 188	96.17 310	91.47 173	96.08 161	99.35 99

UWE-MVS		93.18 152	93.40 131	92.50 239	96.56 169	83.55 301	98.09 229	97.84 62	89.50 165	91.72 174	96.23 213	91.08 35	96.70 274	86.28 234	93.33 188	97.26 216

ETV-MVS		96.00 57	96.00 57	96.00 126	96.56 169	91.05 123	99.63 37	96.61 216	93.26 71	97.39 64	98.30 124	86.62 116	98.13 196	98.07 53	97.57 128	98.82 150

GG-mvs-BLEND				96.98 69	96.53 171	94.81 44	87.20 390	97.74 79		93.91 144	96.40 207	96.56 2	96.94 265	95.08 120	98.95 89	99.20 113

FMVSNet3		88.81 242	87.08 256	93.99 206	96.52 172	94.59 50	98.08 230	96.20 244	85.85 261	82.12 288	91.60 305	74.05 260	95.40 340	79.04 305	80.24 297	91.99 290

fmvsm_s_conf0.5_n_a		95.97 60	96.19 47	95.31 153	96.51 173	89.01 178	99.81 12	98.39 26	95.46 28	99.19 13	99.16 39	81.44 208	99.91 46	98.83 28	96.97 143	97.01 226

BH-untuned		91.46 187	90.84 189	93.33 220	96.51 173	84.83 285	98.84 137	95.50 304	86.44 256	83.50 262	96.70 199	75.49 248	97.77 220	86.78 230	97.81 122	97.40 211

FE-MVS		91.38 190	90.16 202	95.05 164	96.46 175	87.53 217	89.69 387	97.84 62	82.97 311	92.18 169	92.00 296	84.07 159	98.93 158	80.71 295	95.52 169	98.68 161

sss		94.85 99	93.94 115	97.58 43	96.43 176	94.09 62	98.93 129	99.16 8	89.50 165	95.27 117	97.85 134	81.50 205	99.65 101	92.79 164	94.02 182	98.99 130

mvsmamba		94.27 118	93.91 117	95.35 150	96.42 177	88.61 193	97.77 247	96.38 232	91.17 117	94.05 141	95.27 236	78.41 235	97.96 208	97.36 66	98.40 112	99.48 86

test2506		94.80 100	94.21 101	96.58 93	96.41 178	92.18 100	98.01 233	98.96 11	90.82 122	93.46 152	97.28 162	85.92 131	98.45 181	89.82 193	97.19 139	99.12 120

ECVR-MVS		92.29 171	91.33 178	95.15 159	96.41 178	87.84 208	98.10 226	94.84 331	90.82 122	91.42 184	97.28 162	65.61 328	98.49 179	90.33 187	97.19 139	99.12 120

ET-MVSNet_ETH3D		92.56 166	91.45 176	95.88 131	96.39 180	94.13 61	99.46 59	96.97 199	92.18 95	66.94 390	98.29 125	94.65 14	94.28 360	94.34 136	83.82 278	99.24 109

dp		90.16 218	88.83 225	94.14 198	96.38 181	86.42 241	91.57 374	97.06 190	84.76 282	88.81 217	90.19 346	84.29 156	97.43 246	75.05 333	91.35 230	98.56 167

EIA-MVS		95.11 89	95.27 79	94.64 180	96.34 182	86.51 238	99.59 40	96.62 215	92.51 85	94.08 140	98.64 102	86.05 130	98.24 191	95.07 121	98.50 108	99.18 114

test_vis1_n_1920		93.08 156	93.42 130	92.04 249	96.31 183	79.36 345	99.83 10	96.06 258	96.72 9	98.53 34	98.10 132	58.57 356	99.91 46	97.86 57	98.79 99	96.85 229

TR-MVS		90.77 203	89.44 212	94.76 173	96.31 183	88.02 206	97.92 237	95.96 264	85.52 267	88.22 222	97.23 167	66.80 319	98.09 199	84.58 255	92.38 201	98.17 193

UA-Net		93.30 148	92.62 151	95.34 151	96.27 185	88.53 197	95.88 323	96.97 199	90.90 120	95.37 116	97.07 177	82.38 194	99.10 150	83.91 267	94.86 176	98.38 176

tpmrst		92.78 159	92.16 159	94.65 178	96.27 185	87.45 220	91.83 369	97.10 187	89.10 176	94.68 128	90.69 325	88.22 79	97.73 228	89.78 194	91.80 214	98.77 156

hse-mvs2		91.67 184	91.51 175	92.15 246	96.22 187	82.61 317	97.74 251	97.53 129	93.85 56	96.27 95	96.15 215	83.19 173	97.44 245	95.81 102	66.86 379	96.40 243

AUN-MVS		90.17 217	89.50 210	92.19 244	96.21 188	82.67 315	97.76 250	97.53 129	88.05 211	91.67 175	96.15 215	83.10 175	97.47 242	88.11 215	66.91 378	96.43 242

ADS-MVSNet2		87.62 265	86.88 259	89.86 301	96.21 188	79.14 348	87.15 391	92.99 366	83.01 309	89.91 207	87.27 371	78.87 229	92.80 374	74.20 341	92.27 205	97.64 204

ADS-MVSNet		88.99 233	87.30 252	94.07 201	96.21 188	87.56 216	87.15 391	96.78 207	83.01 309	89.91 207	87.27 371	78.87 229	97.01 262	74.20 341	92.27 205	97.64 204

PatchmatchNet		92.05 180	91.04 184	95.06 162	96.17 191	89.04 174	91.26 378	97.26 165	89.56 163	90.64 195	90.56 334	88.35 77	97.11 257	79.53 301	96.07 162	99.03 128
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test1111		92.12 176	91.19 181	94.94 167	96.15 192	87.36 223	98.12 223	94.84 331	90.85 121	90.97 189	97.26 164	65.60 329	98.37 183	89.74 196	97.14 142	99.07 127

gg-mvs-nofinetune		90.00 221	87.71 246	96.89 77	96.15 192	94.69 48	85.15 397	97.74 79	68.32 396	92.97 159	60.16 410	96.10 4	96.84 268	93.89 142	98.87 93	99.14 117

MDTV_nov1_ep13			90.47 199		96.14 194	88.55 195	91.34 377	97.51 135	89.58 161	92.24 168	90.50 338	86.99 108	97.61 235	77.64 316	92.34 203

IS-MVSNet		93.00 157	92.51 153	94.49 183	96.14 194	87.36 223	98.31 207	95.70 292	88.58 190	90.17 203	97.50 154	83.02 177	97.22 253	87.06 222	96.07 162	98.90 142

Vis-MVSNet (Re-imp)		93.26 151	93.00 143	94.06 202	96.14 194	86.71 237	98.68 154	96.70 211	88.30 203	89.71 212	97.64 148	85.43 142	96.39 291	88.06 216	96.32 154	99.08 125

thisisatest0515		94.75 102	94.19 102	96.43 101	96.13 197	92.64 94	99.47 55	97.60 114	87.55 229	93.17 155	97.59 150	94.71 12	98.42 182	88.28 212	93.20 189	98.24 188

RRT-MVS		93.39 144	92.64 150	95.64 140	96.11 198	88.75 190	97.40 263	95.77 288	89.46 167	92.70 162	95.42 233	72.98 269	98.81 161	96.91 78	96.97 143	99.37 96

FA-MVS(test-final)		92.22 175	91.08 183	95.64 140	96.05 199	88.98 179	91.60 373	97.25 166	86.99 237	91.84 171	92.12 290	83.03 176	99.00 154	86.91 227	93.91 183	98.93 139

test_fmvsmconf_n		96.78 35	96.84 29	96.61 90	95.99 200	90.25 141	99.90 3	98.13 42	96.68 11	98.42 36	98.92 77	85.34 144	99.88 54	99.12 22	99.08 78	99.70 55

ab-mvs		91.05 199	89.17 217	96.69 86	95.96 201	91.72 106	92.62 363	97.23 170	85.61 266	89.74 210	93.89 259	68.55 302	99.42 126	91.09 176	87.84 247	98.92 141

Fast-Effi-MVS+		91.72 183	90.79 192	94.49 183	95.89 202	87.40 222	99.54 49	95.70 292	85.01 278	89.28 215	95.68 228	77.75 239	97.57 240	83.22 272	95.06 174	98.51 169

kuosan		84.40 314	83.34 308	87.60 334	95.87 203	79.21 346	92.39 365	96.87 202	76.12 370	73.79 360	93.98 255	81.51 204	90.63 389	64.13 382	75.42 323	92.95 264

EPP-MVSNet		93.75 133	93.67 124	94.01 205	95.86 204	85.70 267	98.67 156	97.66 97	84.46 285	91.36 185	97.18 172	91.16 32	97.79 218	92.93 161	93.75 185	98.53 168

mvsany_test1		94.57 111	95.09 86	92.98 226	95.84 205	82.07 321	98.76 147	95.24 320	92.87 82	96.45 92	98.71 97	84.81 151	99.15 144	97.68 60	95.49 170	97.73 202

Effi-MVS+		93.87 129	93.15 138	96.02 124	95.79 206	90.76 130	96.70 296	95.78 286	86.98 240	95.71 109	97.17 173	79.58 220	98.01 206	94.57 134	96.09 160	99.31 103

tpm cat1		88.89 236	87.27 253	93.76 213	95.79 206	85.32 275	90.76 383	97.09 188	76.14 369	85.72 245	88.59 360	82.92 178	98.04 204	76.96 320	91.43 226	97.90 200

thisisatest0530		94.00 123	93.52 127	95.43 147	95.76 208	90.02 155	98.99 124	97.60 114	86.58 249	91.74 173	97.36 161	94.78 11	98.34 184	86.37 233	92.48 200	97.94 199

3Dnovator+	87.72 8	93.43 142	91.84 167	98.17 23	95.73 209	95.08 35	98.92 131	97.04 191	91.42 111	81.48 302	97.60 149	74.60 252	99.79 85	90.84 181	98.97 86	99.64 68

MVS		93.92 126	92.28 156	98.83 7	95.69 210	96.82 8	96.22 312	98.17 36	84.89 280	84.34 257	98.61 106	79.32 225	99.83 73	93.88 143	99.43 61	99.86 29

cascas		90.93 201	89.33 215	95.76 135	95.69 210	93.03 83	98.99 124	96.59 218	80.49 346	86.79 238	94.45 247	65.23 332	98.60 174	93.52 150	92.18 208	95.66 251

QAPM		91.41 188	89.49 211	97.17 60	95.66 212	93.42 73	98.60 169	97.51 135	80.92 344	81.39 303	97.41 159	72.89 272	99.87 58	82.33 282	98.68 101	98.21 190

tttt0517		93.30 148	93.01 142	94.17 197	95.57 213	86.47 240	98.51 180	97.60 114	85.99 260	90.55 196	97.19 171	94.80 10	98.31 185	85.06 248	91.86 212	97.74 201

1112_ss		92.71 160	91.55 174	96.20 114	95.56 214	91.12 118	98.48 185	94.69 338	88.29 204	86.89 236	98.50 111	87.02 106	98.66 172	84.75 252	89.77 242	98.81 151

diffmvs		94.59 110	94.19 102	95.81 133	95.54 215	90.69 132	98.70 152	95.68 294	91.61 103	95.96 99	97.81 136	80.11 216	98.06 201	96.52 88	95.76 165	98.67 162
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LCM-MVSNet-Re		88.59 249	88.61 230	88.51 327	95.53 216	72.68 383	96.85 288	88.43 403	88.45 194	73.14 366	90.63 329	75.82 245	94.38 359	92.95 160	95.71 167	98.48 171

Test_1112_low_res		92.27 173	90.97 185	96.18 115	95.53 216	91.10 120	98.47 187	94.66 339	88.28 205	86.83 237	93.50 270	87.00 107	98.65 173	84.69 253	89.74 243	98.80 152

PCF-MVS	89.78 5	91.26 192	89.63 208	96.16 119	95.44 218	91.58 110	95.29 335	96.10 253	85.07 275	82.75 272	97.45 157	78.28 236	99.78 87	80.60 297	95.65 168	97.12 219
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EC-MVSNet		95.09 90	95.17 81	94.84 171	95.42 219	88.17 201	99.48 53	95.92 272	91.47 108	97.34 66	98.36 121	82.77 181	97.41 247	97.24 69	98.58 105	98.94 138

3Dnovator	87.35 11	93.17 154	91.77 170	97.37 53	95.41 220	93.07 81	98.82 138	97.85 61	91.53 106	82.56 278	97.58 151	71.97 279	99.82 76	91.01 178	99.23 73	99.22 112

IB-MVS	89.43 6	92.12 176	90.83 191	95.98 128	95.40 221	90.78 129	99.81 12	98.06 45	91.23 116	85.63 246	93.66 265	90.63 44	98.78 162	91.22 175	71.85 361	98.36 180
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
test_cas_vis1_n_1920		93.86 130	93.74 123	94.22 195	95.39 222	86.08 255	99.73 23	96.07 257	96.38 17	97.19 71	97.78 139	65.46 331	99.86 63	96.71 80	98.92 90	96.73 231

miper_ehance_all_eth		88.94 235	88.12 241	91.40 261	95.32 223	86.93 233	97.85 242	95.55 301	84.19 288	81.97 293	91.50 307	84.16 157	95.91 323	84.69 253	77.89 309	91.36 310

1314		93.44 141	91.98 164	97.84 34	95.24 224	94.38 55	96.22 312	97.92 56	90.18 142	82.28 285	97.71 144	77.63 240	99.80 81	91.94 171	98.67 102	99.34 101

XVG-OURS		90.83 202	90.49 197	91.86 251	95.23 225	81.25 331	95.79 328	95.92 272	88.96 179	90.02 206	98.03 133	71.60 284	99.35 136	91.06 177	87.78 248	94.98 255

casdiffmvs_mvg		94.00 123	93.33 133	96.03 123	95.22 226	90.90 128	99.09 111	95.99 260	90.58 130	91.55 180	97.37 160	79.91 218	98.06 201	95.01 123	95.22 172	99.13 119
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TESTMET0.1,1		93.82 131	93.26 136	95.49 145	95.21 227	90.25 141	99.15 101	97.54 128	89.18 173	91.79 172	94.87 242	89.13 64	97.63 233	86.21 235	96.29 157	98.60 166

xiu_mvs_v1_base_debu		94.73 103	93.98 110	96.99 66	95.19 228	95.24 27	98.62 163	96.50 226	92.99 77	97.52 60	98.83 85	72.37 275	99.15 144	97.03 72	96.74 147	96.58 236

xiu_mvs_v1_base		94.73 103	93.98 110	96.99 66	95.19 228	95.24 27	98.62 163	96.50 226	92.99 77	97.52 60	98.83 85	72.37 275	99.15 144	97.03 72	96.74 147	96.58 236

xiu_mvs_v1_base_debi		94.73 103	93.98 110	96.99 66	95.19 228	95.24 27	98.62 163	96.50 226	92.99 77	97.52 60	98.83 85	72.37 275	99.15 144	97.03 72	96.74 147	96.58 236

XVG-OURS-SEG-HR		90.95 200	90.66 195	91.83 252	95.18 231	81.14 334	95.92 320	95.92 272	88.40 198	90.33 202	97.85 134	70.66 290	99.38 131	92.83 163	88.83 244	94.98 255

Effi-MVS+-dtu		89.97 222	90.68 194	87.81 332	95.15 232	71.98 385	97.87 241	95.40 311	91.92 98	87.57 226	91.44 308	74.27 258	96.84 268	89.45 198	93.10 191	94.60 257

Syy-MVS		84.10 319	84.53 297	82.83 370	95.14 233	65.71 397	97.68 255	96.66 213	86.52 252	82.63 275	96.84 192	68.15 306	89.89 393	45.62 408	91.54 221	92.87 265

myMVS_eth3d		88.68 248	89.07 219	87.50 336	95.14 233	79.74 343	97.68 255	96.66 213	86.52 252	82.63 275	96.84 192	85.22 146	89.89 393	69.43 364	91.54 221	92.87 265

Vis-MVSNet		92.64 162	91.85 166	95.03 165	95.12 235	88.23 200	98.48 185	96.81 204	91.61 103	92.16 170	97.22 168	71.58 285	98.00 207	85.85 242	97.81 122	98.88 143
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GBi-Net		86.67 277	84.96 285	91.80 254	95.11 236	88.81 187	96.77 290	95.25 317	82.94 312	82.12 288	90.25 341	62.89 341	94.97 347	79.04 305	80.24 297	91.62 296

test1		86.67 277	84.96 285	91.80 254	95.11 236	88.81 187	96.77 290	95.25 317	82.94 312	82.12 288	90.25 341	62.89 341	94.97 347	79.04 305	80.24 297	91.62 296

FMVSNet2		86.90 272	84.79 291	93.24 221	95.11 236	92.54 95	97.67 257	95.86 284	82.94 312	80.55 309	91.17 314	62.89 341	95.29 342	77.23 317	79.71 303	91.90 291

GeoE		90.60 209	89.56 209	93.72 215	95.10 239	85.43 271	99.41 68	94.94 329	83.96 293	87.21 232	96.83 194	74.37 256	97.05 261	80.50 299	93.73 186	98.67 162

baseline		93.91 127	93.30 134	95.72 136	95.10 239	90.07 150	97.48 262	95.91 277	91.03 118	93.54 151	97.68 145	79.58 220	98.02 205	94.27 137	95.14 173	99.08 125

casdiffmvs		93.98 125	93.43 129	95.61 143	95.07 241	89.86 159	98.80 141	95.84 285	90.98 119	92.74 161	97.66 147	79.71 219	98.10 198	94.72 130	95.37 171	98.87 145
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSFormer		94.71 106	94.08 107	96.61 90	95.05 242	94.87 39	97.77 247	96.17 249	86.84 243	98.04 50	98.52 109	85.52 136	95.99 316	89.83 191	98.97 86	98.96 133

lupinMVS		96.32 49	95.94 58	97.44 47	95.05 242	94.87 39	99.86 5	96.50 226	93.82 58	98.04 50	98.77 88	85.52 136	98.09 199	96.98 75	98.97 86	99.37 96

CostFormer		92.89 158	92.48 154	94.12 199	94.99 244	85.89 262	92.89 359	97.00 197	86.98 240	95.00 123	90.78 321	90.05 56	97.51 241	92.92 162	91.73 216	98.96 133

c3_l		88.19 255	87.23 254	91.06 267	94.97 245	86.17 252	97.72 252	95.38 312	83.43 302	81.68 300	91.37 309	82.81 180	95.72 330	84.04 266	73.70 342	91.29 314

SCA		90.64 208	89.25 216	94.83 172	94.95 246	88.83 186	96.26 309	97.21 172	90.06 149	90.03 205	90.62 330	66.61 320	96.81 270	83.16 273	94.36 179	98.84 146

test-LLR		93.11 155	92.68 148	94.40 187	94.94 247	87.27 227	99.15 101	97.25 166	90.21 140	91.57 177	94.04 250	84.89 149	97.58 237	85.94 239	96.13 158	98.36 180

test-mter		93.27 150	92.89 145	94.40 187	94.94 247	87.27 227	99.15 101	97.25 166	88.95 180	91.57 177	94.04 250	88.03 85	97.58 237	85.94 239	96.13 158	98.36 180

cl____		87.82 257	86.79 261	90.89 273	94.88 249	85.43 271	97.81 243	95.24 320	82.91 316	80.71 308	91.22 312	81.97 200	95.84 325	81.34 290	75.06 326	91.40 309

DIV-MVS_self_test		87.82 257	86.81 260	90.87 274	94.87 250	85.39 273	97.81 243	95.22 325	82.92 315	80.76 307	91.31 311	81.99 198	95.81 327	81.36 289	75.04 327	91.42 308

tpm2		91.77 182	91.09 182	93.82 212	94.83 251	85.56 270	92.51 364	97.16 179	84.00 291	93.83 146	90.66 327	87.54 91	97.17 254	87.73 219	91.55 220	98.72 158

PVSNet_0	83.28 16	87.31 268	85.16 283	93.74 214	94.78 252	84.59 287	98.91 132	98.69 20	89.81 154	78.59 334	93.23 275	61.95 345	99.34 137	94.75 128	55.72 401	97.30 214

CDS-MVSNet		93.47 140	93.04 141	94.76 173	94.75 253	89.45 167	98.82 138	97.03 193	87.91 217	90.97 189	96.48 205	89.06 65	96.36 293	89.50 197	92.81 195	98.49 170
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gm-plane-assit					94.69 254	88.14 202			88.22 206		97.20 169		98.29 187	90.79 183

eth_miper_zixun_eth		87.76 259	87.00 258	90.06 295	94.67 255	82.65 316	97.02 283	95.37 313	84.19 288	81.86 298	91.58 306	81.47 206	95.90 324	83.24 271	73.61 343	91.61 299

testing3		87.75 260	88.22 239	86.36 345	94.66 256	77.41 361	99.52 50	97.95 54	86.05 259	81.12 304	96.69 200	86.18 128	89.31 397	61.65 390	90.12 240	92.35 276

RPSCF		85.33 300	85.55 278	84.67 361	94.63 257	62.28 400	93.73 351	93.76 357	74.38 377	85.23 250	97.06 178	64.09 335	98.31 185	80.98 291	86.08 260	93.41 263

miper_lstm_enhance		86.90 272	86.20 268	89.00 322	94.53 258	81.19 332	96.74 294	95.24 320	82.33 326	80.15 315	90.51 337	81.99 198	94.68 356	80.71 295	73.58 345	91.12 319

Patchmatch-test		86.25 286	84.06 303	92.82 230	94.42 259	82.88 312	82.88 406	94.23 351	71.58 383	79.39 325	90.62 330	89.00 67	96.42 290	63.03 386	91.37 229	99.16 115

VDDNet		90.08 220	88.54 234	94.69 177	94.41 260	87.68 211	98.21 215	96.40 231	76.21 368	93.33 154	97.75 141	54.93 372	98.77 163	94.71 131	90.96 232	97.61 208

fmvsm_s_conf0.1_n		95.56 78	95.68 69	95.20 157	94.35 261	89.10 172	99.50 51	97.67 96	94.76 35	98.68 29	99.03 59	81.13 211	99.86 63	98.63 32	97.36 136	96.63 233

test_fmvsmvis_n_1920		95.47 79	95.40 76	95.70 137	94.33 262	90.22 144	99.70 27	96.98 198	96.80 7	92.75 160	98.89 81	82.46 192	99.92 41	98.36 44	98.33 114	96.97 227

KD-MVS_2432*1600		82.98 325	80.52 334	90.38 288	94.32 263	88.98 179	92.87 360	95.87 282	80.46 347	73.79 360	87.49 368	82.76 183	93.29 368	70.56 360	46.53 412	88.87 365

miper_refine_blended		82.98 325	80.52 334	90.38 288	94.32 263	88.98 179	92.87 360	95.87 282	80.46 347	73.79 360	87.49 368	82.76 183	93.29 368	70.56 360	46.53 412	88.87 365

EI-MVSNet		89.87 223	89.38 214	91.36 263	94.32 263	85.87 263	97.61 259	96.59 218	85.10 273	85.51 247	97.10 175	81.30 210	96.56 280	83.85 269	83.03 285	91.64 294

CVMVSNet		90.30 213	90.91 187	88.46 328	94.32 263	73.58 378	97.61 259	97.59 118	90.16 145	88.43 221	97.10 175	76.83 244	92.86 371	82.64 279	93.54 187	98.93 139

WB-MVSnew		88.69 246	88.34 236	89.77 305	94.30 267	85.99 260	98.14 220	97.31 164	87.15 236	87.85 224	96.07 219	69.91 291	95.52 335	72.83 352	91.47 225	87.80 372

dongtai		81.36 334	80.61 332	83.62 367	94.25 268	73.32 379	95.15 337	96.81 204	73.56 380	69.79 377	92.81 283	81.00 212	86.80 404	52.08 405	70.06 368	90.75 331

test_fmvs1_n		91.07 197	91.41 177	90.06 295	94.10 269	74.31 374	99.18 92	94.84 331	94.81 33	96.37 94	97.46 156	50.86 387	99.82 76	97.14 71	97.90 120	96.04 248

IterMVS-LS		88.34 251	87.44 249	91.04 268	94.10 269	85.85 264	98.10 226	95.48 305	85.12 272	82.03 292	91.21 313	81.35 209	95.63 333	83.86 268	75.73 322	91.63 295
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAMVS		92.62 163	92.09 162	94.20 196	94.10 269	87.68 211	98.41 192	96.97 199	87.53 230	89.74 210	96.04 220	84.77 153	96.49 286	88.97 207	92.31 204	98.42 172

PAPM		96.35 47	95.94 58	97.58 43	94.10 269	95.25 26	98.93 129	98.17 36	94.26 43	93.94 143	98.72 94	89.68 60	97.88 212	96.36 90	99.29 69	99.62 72

CLD-MVS		91.06 198	90.71 193	92.10 247	94.05 273	86.10 254	99.55 44	96.29 240	94.16 46	84.70 252	97.17 173	69.62 296	97.82 216	94.74 129	86.08 260	92.39 272
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP-NCC					93.95 274		99.16 96		93.92 51	87.57 226

ACMP_Plane					93.95 274		99.16 96		93.92 51	87.57 226

HQP-MVS		91.50 185	91.23 180	92.29 241	93.95 274	86.39 243	99.16 96	96.37 233	93.92 51	87.57 226	96.67 201	73.34 264	97.77 220	93.82 146	86.29 255	92.72 267

NP-MVS					93.94 277	86.22 249					96.67 201

plane_prior6					93.92 278	86.02 259						72.92 270

ACMP	87.39 10	88.71 245	88.24 238	90.12 294	93.91 279	81.06 335	98.50 181	95.67 295	89.43 168	80.37 312	95.55 229	65.67 326	97.83 215	90.55 186	84.51 269	91.47 304
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
plane_prior1					93.90 280

HQP_MVS		91.26 192	90.95 186	92.16 245	93.84 281	86.07 257	99.02 120	96.30 237	93.38 69	86.99 233	96.52 203	72.92 270	97.75 226	93.46 153	86.17 258	92.67 269

plane_prior7					93.84 281	85.73 266

dmvs_re		88.69 246	88.06 242	90.59 280	93.83 283	78.68 352	95.75 329	96.18 248	87.99 214	84.48 256	96.32 211	67.52 313	96.94 265	84.98 250	85.49 264	96.14 246

MVS-HIRNet		79.01 346	75.13 359	90.66 279	93.82 284	81.69 324	85.16 396	93.75 358	54.54 406	74.17 358	59.15 412	57.46 360	96.58 279	63.74 383	94.38 178	93.72 260

FMVSNet5		82.29 328	80.54 333	87.52 335	93.79 285	84.01 295	93.73 351	92.47 373	76.92 364	74.27 357	86.15 379	63.69 339	89.24 398	69.07 366	74.79 330	89.29 360

ACMH+	83.78 15	84.21 315	82.56 321	89.15 319	93.73 286	79.16 347	96.43 302	94.28 350	81.09 341	74.00 359	94.03 252	54.58 373	97.67 229	76.10 327	78.81 305	90.63 336

ACMM	86.95 13	88.77 243	88.22 239	90.43 286	93.61 287	81.34 329	98.50 181	95.92 272	87.88 218	83.85 261	95.20 239	67.20 316	97.89 211	86.90 228	84.90 267	92.06 288
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS	85.28 14	90.75 204	88.84 224	96.48 98	93.58 288	93.51 71	98.80 141	97.41 153	82.59 319	78.62 332	97.49 155	68.00 309	99.82 76	84.52 257	98.55 107	96.11 247

IterMVS		85.81 293	84.67 294	89.22 317	93.51 289	83.67 300	96.32 306	94.80 334	85.09 274	78.69 330	90.17 347	66.57 322	93.17 370	79.48 303	77.42 316	90.81 326
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		88.83 240	87.38 251	93.16 223	93.47 290	86.24 247	84.97 399	94.20 352	88.92 183	90.76 193	86.88 375	84.43 154	94.82 352	70.64 359	92.17 209	98.41 173

RPMNet		85.07 303	81.88 322	94.64 180	93.47 290	86.24 247	84.97 399	97.21 172	64.85 403	90.76 193	78.80 401	80.95 213	99.27 140	53.76 402	92.17 209	98.41 173

IterMVS-SCA-FT		85.73 296	84.64 295	89.00 322	93.46 292	82.90 310	96.27 307	94.70 337	85.02 277	78.62 332	90.35 339	66.61 320	93.33 367	79.38 304	77.36 317	90.76 330

Fast-Effi-MVS+-dtu		88.84 238	88.59 232	89.58 310	93.44 293	78.18 356	98.65 158	94.62 340	88.46 193	84.12 259	95.37 235	68.91 299	96.52 283	82.06 285	91.70 217	94.06 258

Patchmtry		83.61 324	81.64 324	89.50 312	93.36 294	82.84 313	84.10 402	94.20 352	69.47 393	79.57 323	86.88 375	84.43 154	94.78 353	68.48 369	74.30 336	90.88 325

LPG-MVS_test		88.86 237	88.47 235	90.06 295	93.35 295	80.95 336	98.22 213	95.94 267	87.73 224	83.17 267	96.11 217	66.28 324	97.77 220	90.19 189	85.19 265	91.46 305

LGP-MVS_train				90.06 295	93.35 295	80.95 336		95.94 267	87.73 224	83.17 267	96.11 217	66.28 324	97.77 220	90.19 189	85.19 265	91.46 305

JIA-IIPM		85.97 289	84.85 289	89.33 316	93.23 297	73.68 377	85.05 398	97.13 182	69.62 392	91.56 179	68.03 408	88.03 85	96.96 263	77.89 315	93.12 190	97.34 213

ACMH	83.09 17	84.60 308	82.61 319	90.57 281	93.18 298	82.94 308	96.27 307	94.92 330	81.01 342	72.61 372	93.61 266	56.54 362	97.79 218	74.31 339	81.07 295	90.99 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PatchT		85.44 299	83.19 309	92.22 242	93.13 299	83.00 307	83.80 405	96.37 233	70.62 386	90.55 196	79.63 400	84.81 151	94.87 350	58.18 398	91.59 218	98.79 153

baseline2		94.04 122	93.80 122	94.74 175	93.07 300	90.25 141	98.12 223	98.16 39	89.86 152	86.53 239	96.95 184	95.56 6	98.05 203	91.44 174	94.53 177	95.93 249

jason		95.40 83	94.86 90	97.03 63	92.91 301	94.23 58	99.70 27	96.30 237	93.56 65	96.73 87	98.52 109	81.46 207	97.91 209	96.08 98	98.47 111	98.96 133
jason: jason.
LTVRE_ROB	81.71 19	84.59 309	82.72 317	90.18 292	92.89 302	83.18 306	93.15 356	94.74 335	78.99 352	75.14 354	92.69 284	65.64 327	97.63 233	69.46 363	81.82 293	89.74 353
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
mmtdpeth		83.69 321	82.59 320	86.99 341	92.82 303	76.98 363	96.16 315	91.63 385	82.89 317	92.41 166	82.90 386	54.95 371	98.19 193	96.27 91	53.27 404	85.81 386

VPA-MVSNet		89.10 232	87.66 247	93.45 217	92.56 304	91.02 124	97.97 236	98.32 29	86.92 242	86.03 241	92.01 294	68.84 301	97.10 259	90.92 179	75.34 324	92.23 279

tpm		89.67 225	88.95 222	91.82 253	92.54 305	81.43 326	92.95 358	95.92 272	87.81 219	90.50 198	89.44 354	84.99 147	95.65 332	83.67 270	82.71 288	98.38 176

GA-MVS		90.10 219	88.69 228	94.33 190	92.44 306	87.97 207	99.08 112	96.26 241	89.65 157	86.92 235	93.11 278	68.09 307	96.96 263	82.54 281	90.15 239	98.05 195

test_fmvsmconf0.1_n		95.94 63	95.79 66	96.40 104	92.42 307	89.92 157	99.79 17	96.85 203	96.53 15	97.22 68	98.67 100	82.71 185	99.84 69	98.92 27	98.98 85	99.43 92

FIs		90.70 205	89.87 205	93.18 222	92.29 308	91.12 118	98.17 219	98.25 31	89.11 175	83.44 263	94.82 243	82.26 195	96.17 310	87.76 218	82.76 287	92.25 277

ITE_SJBPF				87.93 330	92.26 309	76.44 365		93.47 364	87.67 227	79.95 318	95.49 232	56.50 363	97.38 248	75.24 332	82.33 291	89.98 350

UniMVSNet (Re)		89.50 229	88.32 237	93.03 224	92.21 310	90.96 126	98.90 133	98.39 26	89.13 174	83.22 264	92.03 292	81.69 202	96.34 299	86.79 229	72.53 354	91.81 292

UniMVSNet_NR-MVSNet		89.60 226	88.55 233	92.75 233	92.17 311	90.07 150	98.74 148	98.15 40	88.37 199	83.21 265	93.98 255	82.86 179	95.93 320	86.95 225	72.47 355	92.25 277

TinyColmap		80.42 339	77.94 344	87.85 331	92.09 312	78.58 353	93.74 350	89.94 396	74.99 373	69.77 378	91.78 300	46.09 394	97.58 237	65.17 381	77.89 309	87.38 374

fmvsm_s_conf0.1_n_a		95.16 88	95.15 82	95.18 158	92.06 313	88.94 182	99.29 80	97.53 129	94.46 39	98.98 18	98.99 63	79.99 217	99.85 67	98.24 51	96.86 146	96.73 231

tt0805		86.50 282	84.79 291	91.63 259	91.97 314	81.49 325	96.49 301	97.38 156	82.24 327	82.44 280	95.82 225	51.22 384	98.25 190	84.55 256	80.96 296	95.13 254

MS-PatchMatch		86.75 275	85.92 272	89.22 317	91.97 314	82.47 318	96.91 285	96.14 251	83.74 296	77.73 340	93.53 269	58.19 358	97.37 250	76.75 323	98.35 113	87.84 370

VPNet		88.30 252	86.57 262	93.49 216	91.95 316	91.35 112	98.18 217	97.20 176	88.61 188	84.52 255	94.89 241	62.21 344	96.76 273	89.34 201	72.26 358	92.36 273

FMVSNet1		83.94 320	81.32 329	91.80 254	91.94 317	88.81 187	96.77 290	95.25 317	77.98 357	78.25 337	90.25 341	50.37 388	94.97 347	73.27 348	77.81 314	91.62 296

WR-MVS		88.54 250	87.22 255	92.52 238	91.93 318	89.50 166	98.56 174	97.84 62	86.99 237	81.87 296	93.81 260	74.25 259	95.92 322	85.29 245	74.43 334	92.12 285

D2MVS		87.96 256	87.39 250	89.70 307	91.84 319	83.40 303	98.31 207	98.49 22	88.04 212	78.23 338	90.26 340	73.57 262	96.79 272	84.21 260	83.53 281	88.90 364

MonoMVSNet		90.69 206	89.78 206	93.45 217	91.78 320	84.97 283	96.51 300	94.44 343	90.56 131	85.96 242	90.97 317	78.61 234	96.27 306	95.35 113	83.79 279	99.11 122

FC-MVSNet-test		90.22 215	89.40 213	92.67 237	91.78 320	89.86 159	97.89 238	98.22 34	88.81 185	82.96 271	94.66 245	81.90 201	95.96 318	85.89 241	82.52 290	92.20 282

MIMVSNet		84.48 311	81.83 323	92.42 240	91.73 322	87.36 223	85.52 394	94.42 347	81.40 337	81.91 294	87.58 365	51.92 381	92.81 373	73.84 344	88.15 246	97.08 223

USDC		84.74 305	82.93 311	90.16 293	91.73 322	83.54 302	95.00 338	93.30 365	88.77 186	73.19 365	93.30 273	53.62 377	97.65 232	75.88 329	81.54 294	89.30 359

test_vis1_n		90.40 210	90.27 200	90.79 276	91.55 324	76.48 364	99.12 109	94.44 343	94.31 42	97.34 66	96.95 184	43.60 398	99.42 126	97.57 62	97.60 127	96.47 240

nrg030		90.23 214	88.87 223	94.32 191	91.53 325	93.54 70	98.79 145	95.89 280	88.12 209	84.55 254	94.61 246	78.80 231	96.88 267	92.35 168	75.21 325	92.53 271

DU-MVS		88.83 240	87.51 248	92.79 231	91.46 326	90.07 150	98.71 149	97.62 111	88.87 184	83.21 265	93.68 263	74.63 250	95.93 320	86.95 225	72.47 355	92.36 273

NR-MVSNet		87.74 263	86.00 271	92.96 228	91.46 326	90.68 133	96.65 297	97.42 152	88.02 213	73.42 363	93.68 263	77.31 241	95.83 326	84.26 259	71.82 362	92.36 273

tfpnnormal		83.65 322	81.35 328	90.56 283	91.37 328	88.06 204	97.29 269	97.87 59	78.51 356	76.20 344	90.91 318	64.78 333	96.47 287	61.71 389	73.50 346	87.13 379

test_vis1_rt		81.31 335	80.05 338	85.11 355	91.29 329	70.66 389	98.98 126	77.39 418	85.76 264	68.80 381	82.40 389	36.56 405	99.44 122	92.67 165	86.55 254	85.24 393

test_0402		78.81 348	76.33 353	86.26 346	91.18 330	78.44 355	95.88 323	91.34 390	68.55 394	70.51 376	89.91 349	52.65 380	94.99 346	47.14 407	79.78 302	85.34 392

test0.0.03 1		88.96 234	88.61 230	90.03 299	91.09 331	84.43 289	98.97 127	97.02 195	90.21 140	80.29 313	96.31 212	84.89 149	91.93 385	72.98 350	85.70 263	93.73 259

WR-MVS_H		86.53 281	85.49 279	89.66 309	91.04 332	83.31 305	97.53 261	98.20 35	84.95 279	79.64 321	90.90 319	78.01 238	95.33 341	76.29 326	72.81 351	90.35 340

CP-MVSNet		86.54 280	85.45 280	89.79 304	91.02 333	82.78 314	97.38 266	97.56 124	85.37 269	79.53 324	93.03 279	71.86 281	95.25 343	79.92 300	73.43 349	91.34 311

TranMVSNet+NR-MVSNet		87.75 260	86.31 266	92.07 248	90.81 334	88.56 194	98.33 204	97.18 177	87.76 221	81.87 296	93.90 258	72.45 274	95.43 338	83.13 275	71.30 365	92.23 279

PS-CasMVS		85.81 293	84.58 296	89.49 314	90.77 335	82.11 320	97.20 276	97.36 160	84.83 281	79.12 329	92.84 282	67.42 315	95.16 345	78.39 313	73.25 350	91.21 317

DeepMVS_CX				76.08 381	90.74 336	51.65 414		90.84 392	86.47 255	57.89 402	87.98 362	35.88 406	92.60 375	65.77 379	65.06 383	83.97 397

OPM-MVS		89.76 224	89.15 218	91.57 260	90.53 337	85.58 269	98.11 225	95.93 270	92.88 81	86.05 240	96.47 206	67.06 318	97.87 213	89.29 204	86.08 260	91.26 315
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XXY-MVS		87.75 260	86.02 270	92.95 229	90.46 338	89.70 162	97.71 254	95.90 278	84.02 290	80.95 305	94.05 249	67.51 314	97.10 259	85.16 246	78.41 306	92.04 289

UniMVSNet_ETH3D		85.65 298	83.79 306	91.21 264	90.41 339	80.75 339	95.36 333	95.78 286	78.76 355	81.83 299	94.33 248	49.86 389	96.66 275	84.30 258	83.52 282	96.22 245

v10		85.73 296	84.01 304	90.87 274	90.03 340	86.73 236	97.20 276	95.22 325	81.25 339	79.85 320	89.75 351	73.30 266	96.28 305	76.87 321	72.64 353	89.61 356

v8		86.11 287	84.45 298	91.10 266	89.99 341	86.85 234	97.24 273	95.36 314	81.99 331	79.89 319	89.86 350	74.53 254	96.39 291	78.83 309	72.32 357	90.05 348

V42		87.00 271	85.68 276	90.98 270	89.91 342	86.08 255	98.32 206	95.61 298	83.67 299	82.72 273	90.67 326	74.00 261	96.53 282	81.94 287	74.28 337	90.32 341

XVG-ACMP-BASELINE		85.86 291	84.95 287	88.57 326	89.90 343	77.12 362	94.30 344	95.60 299	87.40 232	82.12 288	92.99 281	53.42 378	97.66 230	85.02 249	83.83 276	90.92 324

PEN-MVS		85.21 301	83.93 305	89.07 321	89.89 344	81.31 330	97.09 279	97.24 169	84.45 286	78.66 331	92.68 285	68.44 304	94.87 350	75.98 328	70.92 366	91.04 321

test_fmvs2		85.10 302	85.45 280	84.02 364	89.85 345	65.63 398	98.49 183	92.59 371	90.45 135	85.43 249	93.32 271	43.94 396	96.59 278	90.81 182	84.19 273	89.85 352

v1144		86.83 274	85.31 282	91.40 261	89.75 346	87.21 231	98.31 207	95.45 307	83.22 305	82.70 274	90.78 321	73.36 263	96.36 293	79.49 302	74.69 331	90.63 336

TransMVSNet (Re)		81.97 330	79.61 340	89.08 320	89.70 347	84.01 295	97.26 271	91.85 382	78.84 353	73.07 369	91.62 304	67.17 317	95.21 344	67.50 372	59.46 395	88.02 369

v2v482		87.27 269	85.76 274	91.78 258	89.59 348	87.58 215	98.56 174	95.54 302	84.53 284	82.51 279	91.78 300	73.11 268	96.47 287	82.07 284	74.14 340	91.30 313

pm-mvs1		84.68 307	82.78 315	90.40 287	89.58 349	85.18 277	97.31 268	94.73 336	81.93 333	76.05 346	92.01 294	65.48 330	96.11 313	78.75 310	69.14 369	89.91 351

pmmvs4		87.58 266	86.17 269	91.80 254	89.58 349	88.92 185	97.25 272	95.28 316	82.54 321	80.49 310	93.17 277	75.62 247	96.05 315	82.75 278	78.90 304	90.42 339

v1192		86.32 285	84.71 293	91.17 265	89.53 351	86.40 242	98.13 221	95.44 309	82.52 322	82.42 282	90.62 330	71.58 285	96.33 300	77.23 317	74.88 328	90.79 328

v144192		86.40 283	84.89 288	90.91 271	89.48 352	85.59 268	98.21 215	95.43 310	82.45 324	82.62 277	90.58 333	72.79 273	96.36 293	78.45 312	74.04 341	90.79 328

v148		86.38 284	85.06 284	90.37 290	89.47 353	84.10 294	98.52 177	95.48 305	83.80 295	80.93 306	90.22 344	74.60 252	96.31 301	80.92 293	71.55 363	90.69 334

v1921920		86.02 288	84.44 299	90.77 277	89.32 354	85.20 276	98.10 226	95.35 315	82.19 328	82.25 286	90.71 323	70.73 288	96.30 304	76.85 322	74.49 333	90.80 327

v1240		85.77 295	84.11 302	90.73 278	89.26 355	85.15 279	97.88 240	95.23 324	81.89 334	82.16 287	90.55 335	69.60 297	96.31 301	75.59 331	74.87 329	90.72 333

our_test_3		84.47 312	82.80 313	89.50 312	89.01 356	83.90 297	97.03 281	94.56 341	81.33 338	75.36 353	90.52 336	71.69 283	94.54 358	68.81 367	76.84 318	90.07 346

ppachtmachnet_test		83.63 323	81.57 326	89.80 303	89.01 356	85.09 280	97.13 278	94.50 342	78.84 353	76.14 345	91.00 316	69.78 293	94.61 357	63.40 384	74.36 335	89.71 355

DTE-MVSNet		84.14 317	82.80 313	88.14 329	88.95 358	79.87 342	96.81 289	96.24 242	83.50 301	77.60 341	92.52 287	67.89 311	94.24 361	72.64 353	69.05 370	90.32 341

PS-MVSNAJss		89.54 228	89.05 220	91.00 269	88.77 359	84.36 290	97.39 264	95.97 262	88.47 191	81.88 295	93.80 261	82.48 189	96.50 284	89.34 201	83.34 284	92.15 284

Baseline_NR-MVSNet		85.83 292	84.82 290	88.87 325	88.73 360	83.34 304	98.63 162	91.66 384	80.41 349	82.44 280	91.35 310	74.63 250	95.42 339	84.13 262	71.39 364	87.84 370

MVP-Stereo		86.61 279	85.83 273	88.93 324	88.70 361	83.85 298	96.07 317	94.41 348	82.15 329	75.64 351	91.96 297	67.65 312	96.45 289	77.20 319	98.72 100	86.51 382
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EU-MVSNet		84.19 316	84.42 300	83.52 368	88.64 362	67.37 396	96.04 318	95.76 289	85.29 270	78.44 335	93.18 276	70.67 289	91.48 387	75.79 330	75.98 320	91.70 293

pmmvs5		85.87 290	84.40 301	90.30 291	88.53 363	84.23 291	98.60 169	93.71 359	81.53 336	80.29 313	92.02 293	64.51 334	95.52 335	82.04 286	78.34 307	91.15 318

MDA-MVSNet-bldmvs		77.82 355	74.75 361	87.03 340	88.33 364	78.52 354	96.34 305	92.85 368	75.57 371	48.87 408	87.89 363	57.32 361	92.49 379	60.79 391	64.80 384	90.08 345

N_pmnet		70.19 368	69.87 370	71.12 388	88.24 365	30.63 427	95.85 326	28.70 426	70.18 389	68.73 382	86.55 377	64.04 336	93.81 363	53.12 403	73.46 347	88.94 363

v7n		84.42 313	82.75 316	89.43 315	88.15 366	81.86 322	96.75 293	95.67 295	80.53 345	78.38 336	89.43 355	69.89 292	96.35 298	73.83 345	72.13 359	90.07 346

SixPastTwentyTwo		82.63 327	81.58 325	85.79 351	88.12 367	71.01 388	95.17 336	92.54 372	84.33 287	72.93 370	92.08 291	60.41 352	95.61 334	74.47 338	74.15 339	90.75 331

test_djsdf		88.26 254	87.73 245	89.84 302	88.05 368	82.21 319	97.77 247	96.17 249	86.84 243	82.41 283	91.95 298	72.07 278	95.99 316	89.83 191	84.50 270	91.32 312

mvs_tets		87.09 270	86.22 267	89.71 306	87.87 369	81.39 328	96.73 295	95.90 278	88.19 207	79.99 317	93.61 266	59.96 353	96.31 301	89.40 200	84.34 272	91.43 307

OurMVSNet-221017-0		84.13 318	83.59 307	85.77 352	87.81 370	70.24 390	94.89 339	93.65 361	86.08 258	76.53 343	93.28 274	61.41 347	96.14 312	80.95 292	77.69 315	90.93 323

YYNet1		79.64 345	77.04 350	87.43 338	87.80 371	79.98 341	96.23 311	94.44 343	73.83 379	51.83 405	87.53 366	67.96 310	92.07 384	66.00 378	67.75 376	90.23 343

MDA-MVSNet_test_wron		79.65 344	77.05 349	87.45 337	87.79 372	80.13 340	96.25 310	94.44 343	73.87 378	51.80 406	87.47 370	68.04 308	92.12 383	66.02 377	67.79 375	90.09 344

jajsoiax		87.35 267	86.51 264	89.87 300	87.75 373	81.74 323	97.03 281	95.98 261	88.47 191	80.15 315	93.80 261	61.47 346	96.36 293	89.44 199	84.47 271	91.50 303

K. test v3		81.04 336	79.77 339	84.83 359	87.41 374	70.23 391	95.60 332	93.93 356	83.70 298	67.51 388	89.35 356	55.76 364	93.58 366	76.67 324	68.03 373	90.67 335

dmvs_testset		77.17 357	78.99 342	71.71 386	87.25 375	38.55 423	91.44 375	81.76 414	85.77 263	69.49 379	95.94 223	69.71 295	84.37 406	52.71 404	76.82 319	92.21 281

testgi		82.29 328	81.00 331	86.17 347	87.24 376	74.84 373	97.39 264	91.62 386	88.63 187	75.85 350	95.42 233	46.07 395	91.55 386	66.87 376	79.94 301	92.12 285

LF4IMVS		81.94 331	81.17 330	84.25 363	87.23 377	68.87 395	93.35 355	91.93 381	83.35 304	75.40 352	93.00 280	49.25 392	96.65 276	78.88 308	78.11 308	87.22 378

EG-PatchMatch MVS		79.92 340	77.59 346	86.90 342	87.06 378	77.90 360	96.20 314	94.06 354	74.61 375	66.53 392	88.76 359	40.40 403	96.20 308	67.02 374	83.66 280	86.61 380

test_fmvsmconf0.01_n		94.14 120	93.51 128	96.04 122	86.79 379	89.19 169	99.28 83	95.94 267	95.70 21	95.50 113	98.49 113	73.27 267	99.79 85	98.28 49	98.32 116	99.15 116

Gipuma		54.77 380	52.22 384	62.40 397	86.50 380	59.37 404	50.20 415	90.35 395	36.52 413	41.20 414	49.49 415	18.33 416	81.29 408	32.10 414	65.34 382	46.54 415
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
anonymousdsp		86.69 276	85.75 275	89.53 311	86.46 381	82.94 308	96.39 303	95.71 291	83.97 292	79.63 322	90.70 324	68.85 300	95.94 319	86.01 236	84.02 275	89.72 354

EGC-MVSNET		60.70 375	55.37 379	76.72 380	86.35 382	71.08 386	89.96 386	84.44 411	0.38 423	1.50 424	84.09 384	37.30 404	88.10 401	40.85 412	73.44 348	70.97 408

MVStest1		76.56 358	73.43 364	85.96 350	86.30 383	80.88 338	94.26 345	91.74 383	61.98 405	58.53 401	89.96 348	69.30 298	91.47 388	59.26 395	49.56 410	85.52 389

test_method		70.10 369	68.66 372	74.41 385	86.30 383	55.84 407	94.47 341	89.82 397	35.18 414	66.15 393	84.75 383	30.54 408	77.96 415	70.40 362	60.33 393	89.44 358

lessismore_v0				85.08 356	85.59 385	69.28 393		90.56 394		67.68 387	90.21 345	54.21 375	95.46 337	73.88 343	62.64 387	90.50 338

CMPMVS	58.40 21	80.48 338	80.11 337	81.59 376	85.10 386	59.56 403	94.14 348	95.95 266	68.54 395	60.71 399	93.31 272	55.35 369	97.87 213	83.06 276	84.85 268	87.33 376
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20231206		80.76 337	79.42 341	84.79 360	84.78 387	72.98 380	96.53 298	92.97 367	79.56 350	74.33 356	88.83 358	61.27 348	92.15 382	60.59 392	75.92 321	89.24 361

DSMNet-mixed		81.60 333	81.43 327	82.10 373	84.36 388	60.79 401	93.63 353	86.74 406	79.00 351	79.32 326	87.15 373	63.87 337	89.78 395	66.89 375	91.92 211	95.73 250

pmmvs6		79.90 341	77.31 348	87.67 333	84.17 389	78.13 357	95.86 325	93.68 360	67.94 397	72.67 371	89.62 353	50.98 386	95.75 328	74.80 337	66.04 380	89.14 362

new_pmnet		76.02 359	73.71 363	82.95 369	83.88 390	72.85 382	91.26 378	92.26 375	70.44 388	62.60 397	81.37 393	47.64 393	92.32 380	61.85 388	72.10 360	83.68 398

OpenMVS_ROB	73.86 20	77.99 354	75.06 360	86.77 343	83.81 391	77.94 359	96.38 304	91.53 388	67.54 398	68.38 383	87.13 374	43.94 396	96.08 314	55.03 401	81.83 292	86.29 384

ttmdpeth		79.80 343	77.91 345	85.47 354	83.34 392	75.75 367	95.32 334	91.45 389	76.84 365	74.81 355	91.71 303	53.98 376	94.13 362	72.42 354	61.29 390	86.51 382

test20.03		78.51 351	77.48 347	81.62 375	83.07 393	71.03 387	96.11 316	92.83 369	81.66 335	69.31 380	89.68 352	57.53 359	87.29 403	58.65 397	68.47 371	86.53 381

Anonymous20240521		78.63 350	76.90 351	83.82 365	82.82 394	72.86 381	95.72 330	93.57 362	73.55 381	72.17 373	84.79 382	49.69 390	92.51 378	65.29 380	74.50 332	86.09 385

UnsupCasMVSNet_eth		78.90 347	76.67 352	85.58 353	82.81 395	74.94 372	91.98 368	96.31 236	84.64 283	65.84 394	87.71 364	51.33 383	92.23 381	72.89 351	56.50 400	89.56 357

KD-MVS_self_test		77.47 356	75.88 355	82.24 371	81.59 396	68.93 394	92.83 362	94.02 355	77.03 363	73.14 366	83.39 385	55.44 368	90.42 390	67.95 370	57.53 398	87.38 374

CL-MVSNet_self_test		79.89 342	78.34 343	84.54 362	81.56 397	75.01 371	96.88 287	95.62 297	81.10 340	75.86 349	85.81 380	68.49 303	90.26 391	63.21 385	56.51 399	88.35 367

MIMVSNet1		75.92 360	73.30 365	83.81 366	81.29 398	75.57 369	92.26 366	92.05 379	73.09 382	67.48 389	86.18 378	40.87 402	87.64 402	55.78 400	70.68 367	88.21 368

Patchmatch-RL test		81.90 332	80.13 336	87.23 339	80.71 399	70.12 392	84.07 403	88.19 404	83.16 307	70.57 374	82.18 391	87.18 101	92.59 376	82.28 283	62.78 386	98.98 131

APD_test1		68.93 370	66.98 373	74.77 384	80.62 400	53.15 411	87.97 389	85.01 409	53.76 407	59.26 400	87.52 367	25.19 410	89.95 392	56.20 399	67.33 377	81.19 402

mvs5depth		78.17 352	75.56 356	85.97 349	80.43 401	76.44 365	85.46 395	89.24 401	76.39 367	78.17 339	88.26 361	51.73 382	95.73 329	69.31 365	61.09 391	85.73 387

pmmvs-eth3d		78.71 349	76.16 354	86.38 344	80.25 402	81.19 332	94.17 347	92.13 378	77.97 358	66.90 391	82.31 390	55.76 364	92.56 377	73.63 347	62.31 389	85.38 390

UnsupCasMVSNet_bld		73.85 365	70.14 369	84.99 357	79.44 403	75.73 368	88.53 388	95.24 320	70.12 390	61.94 398	74.81 405	41.41 401	93.62 365	68.65 368	51.13 408	85.62 388

PM-MVS		74.88 363	72.85 366	80.98 377	78.98 404	64.75 399	90.81 382	85.77 407	80.95 343	68.23 385	82.81 387	29.08 409	92.84 372	76.54 325	62.46 388	85.36 391

new-patchmatchnet		74.80 364	72.40 367	81.99 374	78.36 405	72.20 384	94.44 342	92.36 374	77.06 362	63.47 396	79.98 399	51.04 385	88.85 399	60.53 393	54.35 402	84.92 395

test_fmvs3		75.09 362	75.19 358	74.81 383	77.45 406	54.08 409	95.93 319	90.64 393	82.51 323	73.29 364	81.19 394	22.29 412	86.29 405	85.50 244	67.89 374	84.06 396

WB-MVS		66.44 371	66.29 374	66.89 391	74.84 407	44.93 418	93.00 357	84.09 412	71.15 385	55.82 403	81.63 392	63.79 338	80.31 413	21.85 417	50.47 409	75.43 404

SSC-MVS		65.42 372	65.20 375	66.06 392	73.96 408	43.83 419	92.08 367	83.54 413	69.77 391	54.73 404	80.92 396	63.30 340	79.92 414	20.48 418	48.02 411	74.44 405

pmmvs3		72.86 366	69.76 371	82.17 372	73.86 409	74.19 375	94.20 346	89.01 402	64.23 404	67.72 386	80.91 397	41.48 400	88.65 400	62.40 387	54.02 403	83.68 398

mvsany_test3		75.85 361	74.52 362	79.83 378	73.53 410	60.64 402	91.73 371	87.87 405	83.91 294	70.55 375	82.52 388	31.12 407	93.66 364	86.66 231	62.83 385	85.19 394

test_f		71.94 367	70.82 368	75.30 382	72.77 411	53.28 410	91.62 372	89.66 399	75.44 372	64.47 395	78.31 402	20.48 413	89.56 396	78.63 311	66.02 381	83.05 401

ambc				79.60 379	72.76 412	56.61 406	76.20 410	92.01 380		68.25 384	80.23 398	23.34 411	94.73 354	73.78 346	60.81 392	87.48 373

TDRefinement		78.01 353	75.31 357	86.10 348	70.06 413	73.84 376	93.59 354	91.58 387	74.51 376	73.08 368	91.04 315	49.63 391	97.12 256	74.88 335	59.47 394	87.33 376

test_vis3_rt		61.29 374	58.75 377	68.92 390	67.41 414	52.84 412	91.18 380	59.23 425	66.96 399	41.96 413	58.44 413	11.37 421	94.72 355	74.25 340	57.97 397	59.20 412

testf1		56.38 378	53.73 381	64.31 395	64.84 415	45.11 416	80.50 408	75.94 420	38.87 410	42.74 410	75.07 403	11.26 422	81.19 409	41.11 410	53.27 404	66.63 409

APD_test2		56.38 378	53.73 381	64.31 395	64.84 415	45.11 416	80.50 408	75.94 420	38.87 410	42.74 410	75.07 403	11.26 422	81.19 409	41.11 410	53.27 404	66.63 409

PMMVS2		58.97 377	55.07 380	70.69 389	62.72 417	55.37 408	85.97 393	80.52 415	49.48 408	45.94 409	68.31 407	15.73 418	80.78 411	49.79 406	37.12 414	75.91 403

E-PMN		41.02 385	40.93 387	41.29 401	61.97 418	33.83 424	84.00 404	65.17 423	27.17 416	27.56 416	46.72 417	17.63 417	60.41 420	19.32 419	18.82 416	29.61 416

wuyk23d		16.71 389	16.73 393	16.65 403	60.15 419	25.22 428	41.24 416	5.17 427	6.56 420	5.48 423	3.61 423	3.64 425	22.72 422	15.20 421	9.52 420	1.99 420

FPMVS		61.57 373	60.32 376	65.34 393	60.14 420	42.44 421	91.02 381	89.72 398	44.15 409	42.63 412	80.93 395	19.02 414	80.59 412	42.50 409	72.76 352	73.00 406

EMVS		39.96 386	39.88 388	40.18 402	59.57 421	32.12 426	84.79 401	64.57 424	26.27 417	26.14 418	44.18 420	18.73 415	59.29 421	17.03 420	17.67 418	29.12 417

LCM-MVSNet		60.07 376	56.37 378	71.18 387	54.81 422	48.67 415	82.17 407	89.48 400	37.95 412	49.13 407	69.12 406	13.75 420	81.76 407	59.28 394	51.63 407	83.10 400

MVE	44.00 22	41.70 384	37.64 389	53.90 400	49.46 423	43.37 420	65.09 414	66.66 422	26.19 418	25.77 419	48.53 416	3.58 426	63.35 419	26.15 416	27.28 415	54.97 414
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		50.71 382	46.17 385	64.33 394	44.27 424	52.30 413	76.13 411	78.73 416	64.95 402	27.37 417	55.23 414	14.61 419	67.74 417	36.01 413	18.23 417	72.95 407

PMVS	41.42 23	45.67 383	42.50 386	55.17 399	34.28 425	32.37 425	66.24 413	78.71 417	30.72 415	22.04 420	59.59 411	4.59 424	77.85 416	27.49 415	58.84 396	55.29 413
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		53.66 381	52.86 383	56.05 398	32.75 426	41.97 422	73.42 412	76.12 419	21.91 419	39.68 415	96.39 209	42.59 399	65.10 418	78.00 314	14.92 419	61.08 411

testmvs		18.81 388	23.05 391	6.10 405	4.48 427	2.29 430	97.78 245	3.00 428	3.27 421	18.60 421	62.71 409	1.53 428	2.49 424	14.26 422	1.80 421	13.50 419

test123		16.58 390	19.47 392	7.91 404	3.59 428	5.37 429	94.32 343	1.39 429	2.49 422	13.98 422	44.60 419	2.91 427	2.65 423	11.35 423	0.57 422	15.70 418

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

eth-test2					0.00 429

eth-test					0.00 429

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

cdsmvs_eth3d_5k		22.52 387	30.03 390	0.00 406	0.00 429	0.00 431	0.00 417	97.17 178	0.00 424	0.00 425	98.77 88	74.35 257	0.00 425	0.00 424	0.00 423	0.00 421

pcd_1.5k_mvsjas		6.87 392	9.16 395	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	82.48 189	0.00 425	0.00 424	0.00 423	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

ab-mvs-re		8.21 391	10.94 394	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	98.50 111	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 431	0.00 417	0.00 430	0.00 424	0.00 425	0.00 424	0.00 429	0.00 425	0.00 424	0.00 423	0.00 421

WAC-MVS						79.74 343								67.75 371

PC_three_1452									94.60 37	99.41 4	99.12 49	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

test_241102_TWO								97.72 83	94.17 44	99.23 10	99.54 3	93.14 23	99.98 9	99.70 5	99.82 19	99.99 1

test_0728_THIRD									93.01 74	99.07 15	99.46 10	94.66 13	99.97 21	99.25 18	99.82 19	99.95 15

GSMVS																98.84 146

sam_mvs1												88.39 76				98.84 146

sam_mvs												87.08 104

MTGPA								97.45 146

test_post1							90.74 384				41.37 421	85.38 143	96.36 293	83.16 273

test_post											46.00 418	87.37 95	97.11 257

patchmatchnet-post											84.86 381	88.73 72	96.81 270

MTMP							99.21 88	91.09 391

test9_res														98.60 33	99.87 9	99.90 22

agg_prior2														97.84 59	99.87 9	99.91 21

test_prior4						92.00 101	99.41 68

test_prior2							99.57 42		91.43 110	98.12 46	98.97 65	90.43 47		98.33 46	99.81 23

旧先验2							98.67 156		85.75 265	98.96 20			98.97 157	93.84 144

新几何2							98.26 210

无先验							98.52 177	97.82 66	87.20 235				99.90 50	87.64 220		99.85 30

原ACMM2							98.69 153

testdata2													99.88 54	84.16 261

segment_acmp												90.56 45

testdata1							97.89 238		92.43 87

plane_prior5								96.30 237					97.75 226	93.46 153	86.17 258	92.67 269

plane_prior4											96.52 203

plane_prior3						85.91 261			93.65 62	86.99 233

plane_prior2							99.02 120		93.38 69

plane_prior						86.07 257	99.14 104		93.81 59						86.26 257

n2								0.00 430

nn								0.00 430

door-mid								84.90 410

test11								97.68 92

door								85.30 408

HQP5-MVS						86.39 243

BP-MVS														93.82 146

HQP4-MVS										87.57 226			97.77 220			92.72 267

HQP3-MVS								96.37 233							86.29 255

HQP2-MVS												73.34 264

MDTV_nov1_ep13_2view						91.17 117	91.38 376		87.45 231	93.08 157		86.67 115		87.02 223		98.95 137

ACMMP++_ref															82.64 289

ACMMP++															83.83 276

Test By Simon												83.62 163

High-resolution multi-view benchmark