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		93.82 114	93.06 121	96.10 107	99.88 1	89.07 161	98.33 191	97.55 115	86.81 229	90.39 182	98.65 96	75.09 229	99.98 9	93.32 139	97.53 122	99.26 97

DP-MVS Recon		95.85 59	95.15 74	97.95 30	99.87 2	94.38 52	99.60 36	97.48 131	86.58 233	94.42 121	99.13 42	87.36 84	99.98 9	93.64 133	98.33 105	99.48 78

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 24	97.98 51	97.18 3	95.96 92	99.33 19	92.62 26	100.00 1	98.99 23	99.93 1	99.98 6

CNVR-MVS		98.46 1	98.38 1	98.72 9	99.80 4	96.19 15	99.80 13	97.99 50	97.05 6	99.41 2	99.59 2	92.89 25	100.00 1	98.99 23	99.90 7	99.96 10

MG-MVS		97.24 17	96.83 28	98.47 15	99.79 5	95.71 18	99.07 107	99.06 10	94.45 38	96.42 86	98.70 93	88.81 59	99.74 86	95.35 99	99.86 12	99.97 7

NCCC		98.12 5	98.11 3	98.13 24	99.76 6	94.46 48	99.81 9	97.88 54	96.54 11	98.84 22	99.46 10	92.55 27	99.98 9	98.25 44	99.93 1	99.94 18

region2R		96.30 43	96.17 45	96.70 79	99.70 7	90.31 128	99.46 57	97.66 89	90.55 122	97.07 69	99.07 49	86.85 95	99.97 21	95.43 97	99.74 29	99.81 33

HFP-MVS		96.42 39	96.26 39	96.90 67	99.69 8	90.96 115	99.47 53	97.81 63	90.54 123	96.88 71	99.05 52	87.57 76	99.96 28	95.65 90	99.72 31	99.78 38

ACMMPR		96.28 44	96.14 49	96.73 76	99.68 9	90.47 126	99.47 53	97.80 65	90.54 123	96.83 76	99.03 54	86.51 106	99.95 31	95.65 90	99.72 31	99.75 46

ZD-MVS					99.67 10	93.28 71		97.61 102	87.78 206	97.41 58	99.16 34	90.15 47	99.56 103	98.35 39	99.70 35

CP-MVS		96.22 45	96.15 48	96.42 95	99.67 10	89.62 152	99.70 24	97.61 102	90.07 138	96.00 91	99.16 34	87.43 79	99.92 39	96.03 86	99.72 31	99.70 52

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 30	99.72 21	97.47 133	93.95 46	99.07 13	99.46 10	93.18 22	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_SECOND				98.77 8	99.66 12	96.37 14	99.72 21	97.68 85					99.98 9	99.64 7	99.82 19	99.96 10

test0726					99.66 12	95.20 30	99.77 15	97.70 81	93.95 46	99.35 5	99.54 3	93.18 22

CPTT-MVS		94.60 95	94.43 85	95.09 144	99.66 12	86.85 217	99.44 60	97.47 133	83.22 289	94.34 123	98.96 64	82.50 172	99.55 104	94.81 111	99.50 53	98.88 131

MSLP-MVS++		97.50 14	97.45 15	97.63 38	99.65 16	93.21 72	99.70 24	98.13 42	94.61 33	97.78 53	99.46 10	89.85 49	99.81 77	97.97 48	99.91 6	99.88 26

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 15				99.19 28	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 25	99.77 15	97.72 76	94.17 41	99.30 6	99.54 3	93.32 19	99.98 9	99.70 4	99.81 23	99.99 1

IU-MVS					99.63 18	95.38 22		97.73 75	95.54 24	99.54 1				99.69 6	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 25		97.72 76	94.16 43	99.30 6	99.49 9	93.32 19	99.98 9

PAPR		96.35 40	95.82 55	97.94 31	99.63 18	94.19 56	99.42 65	97.55 115	92.43 80	93.82 133	99.12 44	87.30 86	99.91 43	94.02 124	99.06 75	99.74 47

XVS		96.47 38	96.37 37	96.77 72	99.62 22	90.66 123	99.43 63	97.58 110	92.41 83	96.86 72	98.96 64	87.37 81	99.87 56	95.65 90	99.43 59	99.78 38

X-MVStestdata		90.69 186	88.66 209	96.77 72	99.62 22	90.66 123	99.43 63	97.58 110	92.41 83	96.86 72	29.59 398	87.37 81	99.87 56	95.65 90	99.43 59	99.78 38

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 22	99.55 42	97.68 85	93.01 68	99.23 8	99.45 14	95.12 8	99.98 9	99.25 16	99.92 3	99.97 7

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 83					99.98 9	99.55 11	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 83					99.98 9	99.55 11	99.83 15	99.96 10

DeepC-MVS_fast	93.52 2	97.16 21	96.84 26	98.13 24	99.61 24	94.45 49	98.85 129	97.64 95	96.51 14	95.88 95	99.39 18	87.35 85	99.99 5	96.61 75	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
test_one_0601					99.59 28	94.89 34		97.64 95	93.14 67	98.93 19	99.45 14	93.45 18

CDPH-MVS		96.56 36	96.18 42	97.70 36	99.59 28	93.92 60	99.13 102	97.44 139	89.02 164	97.90 51	99.22 25	88.90 58	99.49 110	94.63 117	99.79 27	99.68 56

test_prior				97.01 58	99.58 30	91.77 93		97.57 113					99.49 110			99.79 36

APDe-MVS		97.53 11	97.47 13	97.70 36	99.58 30	93.63 64	99.56 41	97.52 123	93.59 61	98.01 48	99.12 44	90.80 39	99.55 104	99.26 15	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 58	95.75 60	96.38 98	99.58 30	89.41 156	99.26 82	97.41 143	90.66 117	94.82 115	98.95 67	86.15 114	99.98 9	95.24 102	99.64 40	99.74 47

TEST9					99.57 33	93.17 73	99.38 69	97.66 89	89.57 150	98.39 33	99.18 31	90.88 37	99.66 92

train_agg		97.20 20	97.08 20	97.57 42	99.57 33	93.17 73	99.38 69	97.66 89	90.18 132	98.39 33	99.18 31	90.94 35	99.66 92	98.58 34	99.85 13	99.88 26

test_8					99.55 35	93.07 76	99.37 72	97.64 95	90.18 132	98.36 35	99.19 28	90.94 35	99.64 98

test_part2					99.54 36	95.42 20				98.13 40

MSP-MVS		97.77 9	98.18 2	96.53 90	99.54 36	90.14 134	99.41 66	97.70 81	95.46 26	98.60 27	99.19 28	95.71 4	99.49 110	98.15 46	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 83		97.64 95		97.98 49			99.61 100

CSCG		94.87 84	94.71 81	95.36 133	99.54 36	86.49 222	99.34 75	98.15 40	82.71 300	90.15 185	99.25 22	89.48 52	99.86 61	94.97 109	98.82 90	99.72 50

HPM-MVS++		97.72 10	97.59 11	98.14 23	99.53 40	94.76 42	99.19 85	97.75 71	95.66 22	98.21 38	99.29 20	91.10 33	99.99 5	97.68 53	99.87 9	99.68 56

APD-MVS		96.95 26	96.72 29	97.63 38	99.51 41	93.58 65	99.16 91	97.44 139	90.08 137	98.59 28	99.07 49	89.06 55	99.42 121	97.92 49	99.66 37	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
FOURS1					99.50 42	88.94 168	99.55 42	97.47 133	91.32 106	98.12 42

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 21	99.29 79	97.72 76	94.50 35	98.64 26	99.54 3	93.32 19	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
PGM-MVS		95.85 59	95.65 65	96.45 93	99.50 42	89.77 149	98.22 199	98.90 13	89.19 159	96.74 79	98.95 67	85.91 118	99.92 39	93.94 126	99.46 55	99.66 60

GST-MVS		95.97 53	95.66 63	96.90 67	99.49 45	91.22 102	99.45 59	97.48 131	89.69 144	95.89 94	98.72 89	86.37 109	99.95 31	94.62 118	99.22 70	99.52 74

MP-MVS		96.00 50	95.82 55	96.54 89	99.47 46	90.13 136	99.36 73	97.41 143	90.64 120	95.49 105	98.95 67	85.51 123	99.98 9	96.00 87	99.59 49	99.52 74
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.09 48	95.81 57	96.95 66	99.42 47	91.19 104	99.55 42	97.53 119	89.72 143	95.86 97	98.94 70	86.59 102	99.97 21	95.13 103	99.56 50	99.68 56

SR-MVS		96.13 47	96.16 47	96.07 108	99.42 47	89.04 162	98.59 160	97.33 150	90.44 126	96.84 74	99.12 44	86.75 97	99.41 124	97.47 56	99.44 58	99.76 45

PAPM_NR		95.43 71	95.05 78	96.57 88	99.42 47	90.14 134	98.58 162	97.51 125	90.65 119	92.44 148	98.90 74	87.77 75	99.90 48	90.88 163	99.32 64	99.68 56

9.14			96.87 24		99.34 50		99.50 49	97.49 130	89.41 155	98.59 28	99.43 16	89.78 50	99.69 89	98.69 28	99.62 44

save fliter					99.34 50	93.85 62	99.65 33	97.63 99	95.69 20

PHI-MVS		96.65 34	96.46 35	97.21 52	99.34 50	91.77 93	99.70 24	98.05 46	86.48 238	98.05 45	99.20 27	89.33 53	99.96 28	98.38 37	99.62 44	99.90 22

test12				97.83 33	99.33 53	94.45 49		97.55 115		97.56 54		88.60 61	99.50 109		99.71 34	99.55 72

SMA-MVS		97.24 17	96.99 21	98.00 29	99.30 54	94.20 55	99.16 91	97.65 94	89.55 152	99.22 10	99.52 8	90.34 46	99.99 5	98.32 41	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 48	95.80 58	96.96 65	99.29 55	91.19 104	97.23 258	97.45 136	92.58 77	94.39 122	99.24 24	86.43 108	99.99 5	96.22 81	99.40 62	99.71 51

HPM-MVS		95.41 73	95.22 72	95.99 113	99.29 55	89.14 159	99.17 90	97.09 174	87.28 219	95.40 106	98.48 110	84.93 133	99.38 126	95.64 94	99.65 38	99.47 79
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		94.67 93	94.30 86	95.79 119	99.25 57	88.13 186	98.41 180	98.67 22	90.38 128	91.43 163	98.72 89	82.22 181	99.95 31	93.83 130	95.76 155	99.29 94
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 68	95.65 65	95.62 126	99.24 58	87.80 192	98.42 178	97.22 157	88.93 169	96.64 84	98.98 59	85.49 124	99.36 128	96.68 72	99.27 68	99.70 52

SR-MVS-dyc-post		95.75 65	95.86 54	95.41 132	99.22 59	87.26 212	98.40 183	97.21 158	89.63 146	96.67 82	98.97 60	86.73 99	99.36 128	96.62 73	99.31 65	99.60 67

RE-MVS-def			95.70 61		99.22 59	87.26 212	98.40 183	97.21 158	89.63 146	96.67 82	98.97 60	85.24 130		96.62 73	99.31 65	99.60 67

patch_mono-2		97.10 23	97.97 8	94.49 166	99.21 61	83.73 282	99.62 35	98.25 32	95.28 28	99.38 4	98.91 73	92.28 28	99.94 34	99.61 9	99.22 70	99.78 38

API-MVS		94.78 87	94.18 92	96.59 85	99.21 61	90.06 141	98.80 134	97.78 68	83.59 284	93.85 131	99.21 26	83.79 146	99.97 21	92.37 151	99.00 79	99.74 47

PLC	91.07 3	94.23 102	94.01 96	94.87 152	99.17 63	87.49 201	99.25 83	96.55 204	88.43 184	91.26 167	98.21 122	85.92 116	99.86 61	89.77 178	97.57 119	97.24 197
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EI-MVSNet-Vis-set		95.76 64	95.63 67	96.17 105	99.14 64	90.33 127	98.49 171	97.82 60	91.92 93	94.75 116	98.88 78	87.06 90	99.48 114	95.40 98	97.17 132	98.70 148

TSAR-MVS + MP.		97.44 15	97.46 14	97.39 46	99.12 65	93.49 69	98.52 165	97.50 128	94.46 36	98.99 15	98.64 97	91.58 30	99.08 146	98.49 35	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
SF-MVS		97.22 19	96.92 22	98.12 26	99.11 66	94.88 35	99.44 60	97.45 136	89.60 148	98.70 24	99.42 17	90.42 44	99.72 87	98.47 36	99.65 38	99.77 43

HPM-MVS_fast		94.89 83	94.62 82	95.70 122	99.11 66	88.44 182	99.14 99	97.11 170	85.82 246	95.69 101	98.47 111	83.46 151	99.32 133	93.16 141	99.63 43	99.35 88

MAR-MVS		94.43 99	94.09 94	95.45 130	99.10 68	87.47 202	98.39 187	97.79 67	88.37 186	94.02 128	99.17 33	78.64 214	99.91 43	92.48 150	98.85 89	98.96 121
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		94.06 104	93.05 122	97.06 56	99.08 69	92.26 89	98.97 121	97.01 182	82.58 302	92.57 146	98.22 120	80.68 197	99.30 134	89.34 184	99.02 78	99.63 64

EI-MVSNet-UG-set		95.43 71	95.29 70	95.86 117	99.07 70	89.87 146	98.43 177	97.80 65	91.78 95	94.11 126	98.77 83	86.25 112	99.48 114	94.95 110	96.45 141	98.22 172

原ACMM1				96.18 103	99.03 71	90.08 137		97.63 99	88.98 165	97.00 70	98.97 60	88.14 69	99.71 88	88.23 195	99.62 44	98.76 145

SD-MVS		97.51 13	97.40 16	97.81 34	99.01 72	93.79 63	99.33 76	97.38 146	93.73 57	98.83 23	99.02 56	90.87 38	99.88 52	98.69 28	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
旧先验1					98.97 73	92.90 82		97.74 72			99.15 37	91.05 34			99.33 63	99.60 67

LS3D		90.19 195	88.72 207	94.59 165	98.97 73	86.33 230	96.90 270	96.60 198	74.96 352	84.06 241	98.74 86	75.78 226	99.83 71	74.93 316	97.57 119	97.62 188

CNLPA		93.64 121	92.74 130	96.36 99	98.96 75	90.01 144	99.19 85	95.89 258	86.22 241	89.40 193	98.85 79	80.66 198	99.84 67	88.57 191	96.92 135	99.24 98

MP-MVS-pluss		95.80 61	95.30 69	97.29 48	98.95 76	92.66 83	98.59 160	97.14 166	88.95 167	93.12 140	99.25 22	85.62 120	99.94 34	96.56 77	99.48 54	99.28 95
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
新几何1				97.40 45	98.92 77	92.51 88		97.77 70	85.52 251	96.69 81	99.06 51	88.08 70	99.89 51	84.88 233	99.62 44	99.79 36

DP-MVS		88.75 225	86.56 244	95.34 134	98.92 77	87.45 203	97.64 242	93.52 339	70.55 364	81.49 283	97.25 158	74.43 235	99.88 52	71.14 338	94.09 171	98.67 150

TSAR-MVS + GP.		96.95 26	96.91 23	97.07 55	98.88 79	91.62 96	99.58 39	96.54 205	95.09 30	96.84 74	98.63 99	91.16 31	99.77 83	99.04 22	96.42 142	99.81 33

CANet		97.00 25	96.49 33	98.55 12	98.86 80	96.10 16	99.83 7	97.52 123	95.90 17	97.21 64	98.90 74	82.66 171	99.93 37	98.71 27	98.80 91	99.63 64

dcpmvs_2		95.67 67	96.18 42	94.12 183	98.82 81	84.22 275	97.37 250	95.45 284	90.70 116	95.77 99	98.63 99	90.47 42	98.68 162	99.20 18	99.22 70	99.45 80

ACMMP_NAP		96.59 35	96.18 42	97.81 34	98.82 81	93.55 66	98.88 128	97.59 108	90.66 117	97.98 49	99.14 40	86.59 102	100.00 1	96.47 79	99.46 55	99.89 25

PVSNet_BlendedMVS		93.36 129	93.20 118	93.84 194	98.77 83	91.61 97	99.47 53	98.04 47	91.44 102	94.21 124	92.63 269	83.50 149	99.87 56	97.41 57	83.37 265	90.05 329

PVSNet_Blended		95.94 56	95.66 63	96.75 74	98.77 83	91.61 97	99.88 3	98.04 47	93.64 60	94.21 124	97.76 133	83.50 149	99.87 56	97.41 57	97.75 117	98.79 141

DeepPCF-MVS	93.56 1	96.55 37	97.84 10	92.68 218	98.71 85	78.11 339	99.70 24	97.71 80	98.18 1	97.36 60	99.76 1	90.37 45	99.94 34	99.27 14	99.54 52	99.99 1

EPNet		96.82 29	96.68 31	97.25 51	98.65 86	93.10 75	99.48 51	98.76 15	96.54 11	97.84 52	98.22 120	87.49 78	99.66 92	95.35 99	97.78 116	99.00 117
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		93.90 111	93.62 108	94.73 159	98.63 87	87.00 215	98.04 217	96.56 203	92.19 88	92.46 147	98.73 87	79.49 206	99.14 143	92.16 153	94.34 170	98.03 177

MVS_111021_HR		96.69 32	96.69 30	96.72 78	98.58 88	91.00 114	99.14 99	99.45 1	93.86 52	95.15 111	98.73 87	88.48 62	99.76 84	97.23 61	99.56 50	99.40 84

test_yl		95.27 76	94.60 83	97.28 49	98.53 89	92.98 79	99.05 110	98.70 19	86.76 230	94.65 119	97.74 135	87.78 73	99.44 117	95.57 95	92.61 185	99.44 81

DCV-MVSNet		95.27 76	94.60 83	97.28 49	98.53 89	92.98 79	99.05 110	98.70 19	86.76 230	94.65 119	97.74 135	87.78 73	99.44 117	95.57 95	92.61 185	99.44 81

TAPA-MVS	87.50 9	90.35 190	89.05 200	94.25 178	98.48 91	85.17 262	98.42 178	96.58 202	82.44 307	87.24 210	98.53 103	82.77 166	98.84 153	59.09 373	97.88 112	98.72 146
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.32 92	91.21 103	98.08 214	97.58 110	83.74 280	95.87 96	99.02 56	86.74 98			99.64 40	99.81 33

DPM-MVS		97.86 8	97.25 18	99.68 1	98.25 93	99.10 1	99.76 18	97.78 68	96.61 10	98.15 39	99.53 7	93.62 17	100.00 1	91.79 155	99.80 26	99.94 18

LFMVS		92.23 157	90.84 170	96.42 95	98.24 94	91.08 111	98.24 198	96.22 224	83.39 287	94.74 117	98.31 116	61.12 328	98.85 152	94.45 120	92.82 181	99.32 91

testdata				95.26 139	98.20 95	87.28 209		97.60 104	85.21 255	98.48 31	99.15 37	88.15 68	98.72 160	90.29 171	99.45 57	99.78 38

PatchMatch-RL		91.47 168	90.54 177	94.26 177	98.20 95	86.36 228	96.94 268	97.14 166	87.75 208	88.98 196	95.75 209	71.80 262	99.40 125	80.92 275	97.39 126	97.02 205

MVS_111021_LR		95.78 62	95.94 51	95.28 138	98.19 97	87.69 193	98.80 134	99.26 7	93.39 63	95.04 113	98.69 94	84.09 143	99.76 84	96.96 67	99.06 75	98.38 163

F-COLMAP		92.07 161	91.75 152	93.02 208	98.16 98	82.89 293	98.79 138	95.97 241	86.54 235	87.92 203	97.80 130	78.69 213	99.65 96	85.97 219	95.93 154	96.53 219

Anonymous202405211		88.84 219	87.03 237	94.27 176	98.14 99	84.18 276	98.44 176	95.58 277	76.79 346	89.34 194	96.88 178	53.42 355	99.54 106	87.53 204	87.12 231	99.09 112

VNet		95.08 81	94.26 87	97.55 43	98.07 100	93.88 61	98.68 146	98.73 18	90.33 129	97.16 68	97.43 151	79.19 208	99.53 107	96.91 69	91.85 199	99.24 98

CS-MVS-test		95.98 52	96.34 38	94.90 151	98.06 101	87.66 196	99.69 31	96.10 233	93.66 58	98.35 36	99.05 52	86.28 110	97.66 213	96.96 67	98.90 87	99.37 86

DELS-MVS		97.12 22	96.60 32	98.68 10	98.03 102	96.57 11	99.84 6	97.84 57	96.36 16	95.20 110	98.24 119	88.17 66	99.83 71	96.11 84	99.60 48	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
PVSNet	87.13 12	93.69 117	92.83 129	96.28 101	97.99 103	90.22 132	99.38 69	98.93 12	91.42 104	93.66 134	97.68 138	71.29 267	99.64 98	87.94 200	97.20 129	98.98 119

test_fmvsm_n_1920		97.08 24	97.55 12	95.67 124	97.94 104	89.61 153	99.93 1	98.48 24	97.08 5	99.08 12	99.13 42	88.17 66	99.93 37	99.11 21	99.06 75	97.47 191

cl22		89.57 207	88.79 206	91.91 231	97.94 104	87.62 197	97.98 220	96.51 206	85.03 260	82.37 266	91.79 281	83.65 147	96.50 266	85.96 220	77.89 293	91.61 282

CS-MVS		95.75 65	96.19 40	94.40 170	97.88 106	86.22 233	99.66 32	96.12 232	92.69 76	98.07 44	98.89 76	87.09 88	97.59 219	96.71 70	98.62 98	99.39 85

CHOSEN 280x420		96.80 30	96.85 25	96.66 82	97.85 107	94.42 51	94.76 319	98.36 29	92.50 79	95.62 103	97.52 146	97.92 1	97.38 231	98.31 42	98.80 91	98.20 174

thres200		93.69 117	92.59 134	96.97 64	97.76 108	94.74 43	99.35 74	99.36 2	89.23 158	91.21 169	96.97 172	83.42 152	98.77 155	85.08 229	90.96 212	97.39 193

HY-MVS	88.56 7	95.29 75	94.23 88	98.48 14	97.72 109	96.41 13	94.03 327	98.74 16	92.42 82	95.65 102	94.76 228	86.52 105	99.49 110	95.29 101	92.97 180	99.53 73

Anonymous20231211		84.72 287	82.65 298	90.91 254	97.71 110	84.55 271	97.28 254	96.67 193	66.88 377	79.18 309	90.87 299	58.47 336	96.60 256	82.61 262	74.20 320	91.59 284

tfpn200view9		93.43 126	92.27 139	96.90 67	97.68 111	94.84 38	99.18 87	99.36 2	88.45 181	90.79 172	96.90 176	83.31 153	98.75 157	84.11 245	90.69 214	97.12 199

thres400		93.39 128	92.27 139	96.73 76	97.68 111	94.84 38	99.18 87	99.36 2	88.45 181	90.79 172	96.90 176	83.31 153	98.75 157	84.11 245	90.69 214	96.61 214

thres100view900		93.34 130	92.15 142	96.90 67	97.62 113	94.84 38	99.06 109	99.36 2	87.96 201	90.47 180	96.78 183	83.29 155	98.75 157	84.11 245	90.69 214	97.12 199

thres600view7		93.18 136	92.00 145	96.75 74	97.62 113	94.92 33	99.07 107	99.36 2	87.96 201	90.47 180	96.78 183	83.29 155	98.71 161	82.93 259	90.47 218	96.61 214

WTY-MVS		95.97 53	95.11 76	98.54 13	97.62 113	96.65 9	99.44 60	98.74 16	92.25 87	95.21 109	98.46 113	86.56 104	99.46 116	95.00 108	92.69 184	99.50 77

Anonymous20240529		87.66 245	85.58 258	93.92 191	97.59 116	85.01 265	98.13 206	97.13 168	66.69 378	88.47 200	96.01 205	55.09 349	99.51 108	87.00 207	84.12 256	97.23 198

HyFIR lowres test		93.68 119	93.29 116	94.87 152	97.57 117	88.04 188	98.18 203	98.47 25	87.57 214	91.24 168	95.05 222	85.49 124	97.46 226	93.22 140	92.82 181	99.10 111

canonicalmvs		95.02 82	93.96 100	98.20 21	97.53 118	95.92 17	98.71 142	96.19 227	91.78 95	95.86 97	98.49 108	79.53 205	99.03 147	96.12 83	91.42 209	99.66 60

CHOSEN 1792x2688		94.35 100	93.82 104	95.95 115	97.40 119	88.74 176	98.41 180	98.27 31	92.18 89	91.43 163	96.40 194	78.88 209	99.81 77	93.59 134	97.81 113	99.30 93

SteuartSystems-ACMMP		97.25 16	97.34 17	97.01 58	97.38 120	91.46 100	99.75 19	97.66 89	94.14 45	98.13 40	99.26 21	92.16 29	99.66 92	97.91 50	99.64 40	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n		96.19 46	96.49 33	95.30 137	97.37 121	89.16 158	99.86 4	98.47 25	95.68 21	98.87 20	99.15 37	82.44 178	99.92 39	99.14 19	97.43 125	96.83 210

alignmvs		95.77 63	95.00 79	98.06 28	97.35 122	95.68 19	99.71 23	97.50 128	91.50 100	96.16 90	98.61 101	86.28 110	99.00 148	96.19 82	91.74 201	99.51 76

PS-MVSNAJ		96.87 28	96.40 36	98.29 19	97.35 122	97.29 5	99.03 113	97.11 170	95.83 18	98.97 17	99.14 40	82.48 174	99.60 101	98.60 31	99.08 73	98.00 178

MVS_0304		97.53 11	97.15 19	98.67 11	97.30 124	96.52 12	99.60 36	98.88 14	97.14 4	97.21 64	98.94 70	86.89 94	99.91 43	99.43 13	98.91 86	99.59 71

EPNet_dtu		92.28 155	92.15 142	92.70 217	97.29 125	84.84 267	98.64 152	97.82 60	92.91 73	93.02 142	97.02 170	85.48 126	95.70 312	72.25 335	94.89 165	97.55 190
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVSTER		92.71 143	92.32 137	93.86 193	97.29 125	92.95 81	99.01 116	96.59 199	90.09 136	85.51 227	94.00 239	94.61 16	96.56 261	90.77 167	83.03 268	92.08 269

EPMVS		92.59 148	91.59 154	95.59 128	97.22 127	90.03 142	91.78 347	98.04 47	90.42 127	91.66 157	90.65 307	86.49 107	97.46 226	81.78 270	96.31 145	99.28 95

test_fmvs1		92.35 152	92.94 127	90.57 264	97.19 128	75.43 348	99.55 42	94.97 304	95.20 29	96.82 77	97.57 145	59.59 333	99.84 67	97.30 59	98.29 108	96.46 221

tpmvs		89.16 211	87.76 224	93.35 202	97.19 128	84.75 269	90.58 362	97.36 148	81.99 312	84.56 234	89.31 335	83.98 145	98.17 178	74.85 318	90.00 221	97.12 199

DeepC-MVS	91.02 4	94.56 98	93.92 102	96.46 92	97.16 130	90.76 119	98.39 187	97.11 170	93.92 48	88.66 198	98.33 115	78.14 216	99.85 65	95.02 106	98.57 100	98.78 143
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
iter_conf05		93.48 123	93.18 119	94.39 173	97.15 131	94.17 57	99.30 78	92.97 344	92.38 86	86.70 219	95.42 215	95.67 5	96.59 257	94.67 116	84.32 254	92.39 252

PVSNet_Blended_VisFu		94.67 93	94.11 93	96.34 100	97.14 132	91.10 109	99.32 77	97.43 141	92.10 92	91.53 162	96.38 197	83.29 155	99.68 90	93.42 138	96.37 143	98.25 170

h-mvs33		92.47 151	91.95 147	94.05 187	97.13 133	85.01 265	98.36 189	98.08 44	93.85 53	96.27 88	96.73 185	83.19 158	99.43 120	95.81 88	68.09 352	97.70 184

miper_enhance_ethall		90.33 191	89.70 186	92.22 223	97.12 134	88.93 170	98.35 190	95.96 243	88.60 176	83.14 251	92.33 271	87.38 80	96.18 289	86.49 215	77.89 293	91.55 285

xiu_mvs_v2_base		96.66 33	96.17 45	98.11 27	97.11 135	96.96 6	99.01 116	97.04 177	95.51 25	98.86 21	99.11 48	82.19 182	99.36 128	98.59 33	98.14 109	98.00 178

VDD-MVS		91.24 175	90.18 181	94.45 169	97.08 136	85.84 248	98.40 183	96.10 233	86.99 221	93.36 137	98.16 123	54.27 352	99.20 136	96.59 76	90.63 217	98.31 169

UGNet		91.91 163	90.85 169	95.10 143	97.06 137	88.69 177	98.01 218	98.24 34	92.41 83	92.39 149	93.61 250	60.52 330	99.68 90	88.14 196	97.25 128	96.92 208
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		92.61 147	91.28 160	96.58 86	97.05 138	94.63 46	97.72 236	96.20 225	89.82 141	88.56 199	96.85 179	86.85 95	97.82 199	88.42 192	80.10 284	97.30 195

iter_conf_final		93.22 135	93.04 123	93.76 196	97.03 139	92.22 90	99.05 110	93.31 341	92.11 91	86.93 214	95.42 215	95.01 10	96.59 257	93.98 125	84.48 251	92.46 251

CANet_DTU		94.31 101	93.35 113	97.20 53	97.03 139	94.71 44	98.62 154	95.54 279	95.61 23	97.21 64	98.47 111	71.88 260	99.84 67	88.38 193	97.46 124	97.04 204

MSDG		88.29 233	86.37 246	94.04 188	96.90 141	86.15 237	96.52 283	94.36 325	77.89 342	79.22 308	96.95 173	69.72 273	99.59 102	73.20 331	92.58 187	96.37 224

BH-w/o		92.32 153	91.79 150	93.91 192	96.85 142	86.18 235	99.11 104	95.74 267	88.13 195	84.81 231	97.00 171	77.26 221	97.91 192	89.16 189	98.03 110	97.64 185

AllTest		84.97 285	83.12 290	90.52 267	96.82 143	78.84 331	95.89 303	92.17 355	77.96 340	75.94 327	95.50 212	55.48 345	99.18 137	71.15 336	87.14 229	93.55 241

TestCases				90.52 267	96.82 143	78.84 331		92.17 355	77.96 340	75.94 327	95.50 212	55.48 345	99.18 137	71.15 336	87.14 229	93.55 241

SDMVSNet		91.09 176	89.91 184	94.65 161	96.80 145	90.54 125	97.78 230	97.81 63	88.34 188	85.73 223	95.26 219	66.44 301	98.26 175	94.25 123	86.75 232	95.14 232

sd_testset		89.23 210	88.05 223	92.74 216	96.80 145	85.33 258	95.85 308	97.03 179	88.34 188	85.73 223	95.26 219	61.12 328	97.76 208	85.61 225	86.75 232	95.14 232

PMMVS		93.62 122	93.90 103	92.79 213	96.79 147	81.40 310	98.85 129	96.81 189	91.25 107	96.82 77	98.15 124	77.02 222	98.13 180	93.15 142	96.30 146	98.83 137

BH-RMVSNet		91.25 174	89.99 183	95.03 148	96.75 148	88.55 179	98.65 150	94.95 305	87.74 209	87.74 204	97.80 130	68.27 283	98.14 179	80.53 280	97.49 123	98.41 160

MVS_Test		93.67 120	92.67 132	96.69 80	96.72 149	92.66 83	97.22 259	96.03 238	87.69 212	95.12 112	94.03 237	81.55 188	98.28 174	89.17 188	96.46 140	99.14 106

COLMAP_ROB	82.69 18	84.54 291	82.82 292	89.70 290	96.72 149	78.85 330	95.89 303	92.83 347	71.55 361	77.54 322	95.89 207	59.40 334	99.14 143	67.26 352	88.26 225	91.11 302
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
mvs_anonymous		92.50 150	91.65 153	95.06 145	96.60 151	89.64 151	97.06 264	96.44 211	86.64 232	84.14 239	93.93 241	82.49 173	96.17 291	91.47 156	96.08 151	99.35 88

ETV-MVS		96.00 50	96.00 50	96.00 112	96.56 152	91.05 112	99.63 34	96.61 197	93.26 66	97.39 59	98.30 117	86.62 101	98.13 180	98.07 47	97.57 119	98.82 138

GG-mvs-BLEND				96.98 63	96.53 153	94.81 41	87.20 367	97.74 72		93.91 130	96.40 194	96.56 2	96.94 245	95.08 104	98.95 84	99.20 102

FMVSNet3		88.81 223	87.08 236	93.99 190	96.52 154	94.59 47	98.08 214	96.20 225	85.85 245	82.12 270	91.60 285	74.05 240	95.40 320	79.04 287	80.24 281	91.99 272

fmvsm_s_conf0.5_n_a		95.97 53	96.19 40	95.31 136	96.51 155	89.01 164	99.81 9	98.39 27	95.46 26	99.19 11	99.16 34	81.44 192	99.91 43	98.83 26	96.97 134	97.01 206

BH-untuned		91.46 169	90.84 170	93.33 203	96.51 155	84.83 268	98.84 131	95.50 281	86.44 240	83.50 243	96.70 186	75.49 228	97.77 203	86.78 213	97.81 113	97.40 192

FE-MVS		91.38 171	90.16 182	95.05 147	96.46 157	87.53 200	89.69 364	97.84 57	82.97 294	92.18 151	92.00 278	84.07 144	98.93 151	80.71 277	95.52 159	98.68 149

sss		94.85 85	93.94 101	97.58 40	96.43 158	94.09 59	98.93 123	99.16 8	89.50 153	95.27 108	97.85 127	81.50 189	99.65 96	92.79 148	94.02 172	98.99 118

test2506		94.80 86	94.21 89	96.58 86	96.41 159	92.18 91	98.01 218	98.96 11	90.82 114	93.46 136	97.28 155	85.92 116	98.45 167	89.82 176	97.19 130	99.12 109

ECVR-MVS		92.29 154	91.33 159	95.15 142	96.41 159	87.84 191	98.10 211	94.84 308	90.82 114	91.42 165	97.28 155	65.61 307	98.49 166	90.33 170	97.19 130	99.12 109

ET-MVSNet_ETH3D		92.56 149	91.45 157	95.88 116	96.39 161	94.13 58	99.46 57	96.97 185	92.18 89	66.94 367	98.29 118	94.65 15	94.28 340	94.34 121	83.82 261	99.24 98

dp		90.16 197	88.83 205	94.14 182	96.38 162	86.42 224	91.57 351	97.06 176	84.76 266	88.81 197	90.19 325	84.29 141	97.43 229	75.05 315	91.35 211	98.56 154

EIA-MVS		95.11 79	95.27 71	94.64 163	96.34 163	86.51 221	99.59 38	96.62 196	92.51 78	94.08 127	98.64 97	86.05 115	98.24 177	95.07 105	98.50 102	99.18 103

test_vis1_n_1920		93.08 139	93.42 112	92.04 230	96.31 164	79.36 327	99.83 7	96.06 237	96.72 8	98.53 30	98.10 125	58.57 335	99.91 43	97.86 51	98.79 94	96.85 209

TR-MVS		90.77 183	89.44 191	94.76 156	96.31 164	88.02 189	97.92 222	95.96 243	85.52 251	88.22 202	97.23 159	66.80 297	98.09 183	84.58 237	92.38 189	98.17 175

UA-Net		93.30 131	92.62 133	95.34 134	96.27 166	88.53 181	95.88 305	96.97 185	90.90 112	95.37 107	97.07 168	82.38 179	99.10 145	83.91 249	94.86 166	98.38 163

tpmrst		92.78 142	92.16 141	94.65 161	96.27 166	87.45 203	91.83 346	97.10 173	89.10 163	94.68 118	90.69 304	88.22 65	97.73 211	89.78 177	91.80 200	98.77 144

hse-mvs2		91.67 166	91.51 156	92.15 227	96.22 168	82.61 299	97.74 235	97.53 119	93.85 53	96.27 88	96.15 200	83.19 158	97.44 228	95.81 88	66.86 359	96.40 223

AUN-MVS		90.17 196	89.50 189	92.19 225	96.21 169	82.67 297	97.76 234	97.53 119	88.05 197	91.67 156	96.15 200	83.10 160	97.47 225	88.11 197	66.91 358	96.43 222

ADS-MVSNet2		87.62 246	86.88 239	89.86 285	96.21 169	79.14 329	87.15 368	92.99 343	83.01 292	89.91 188	87.27 348	78.87 210	92.80 353	74.20 323	92.27 192	97.64 185

ADS-MVSNet		88.99 213	87.30 232	94.07 185	96.21 169	87.56 199	87.15 368	96.78 191	83.01 292	89.91 188	87.27 348	78.87 210	97.01 242	74.20 323	92.27 192	97.64 185

PatchmatchNet		92.05 162	91.04 165	95.06 145	96.17 172	89.04 162	91.26 355	97.26 151	89.56 151	90.64 176	90.56 313	88.35 64	97.11 237	79.53 283	96.07 152	99.03 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test1111		92.12 159	91.19 162	94.94 150	96.15 173	87.36 206	98.12 208	94.84 308	90.85 113	90.97 170	97.26 157	65.60 308	98.37 169	89.74 179	97.14 133	99.07 115

gg-mvs-nofinetune		90.00 200	87.71 226	96.89 71	96.15 173	94.69 45	85.15 373	97.74 72	68.32 373	92.97 143	60.16 386	96.10 3	96.84 248	93.89 127	98.87 88	99.14 106

MDTV_nov1_ep13			90.47 179		96.14 175	88.55 179	91.34 354	97.51 125	89.58 149	92.24 150	90.50 317	86.99 93	97.61 218	77.64 298	92.34 190

IS-MVSNet		93.00 140	92.51 135	94.49 166	96.14 175	87.36 206	98.31 194	95.70 269	88.58 177	90.17 184	97.50 147	83.02 162	97.22 234	87.06 205	96.07 152	98.90 130

Vis-MVSNet (Re-imp)		93.26 134	93.00 126	94.06 186	96.14 175	86.71 220	98.68 146	96.70 192	88.30 190	89.71 192	97.64 141	85.43 127	96.39 273	88.06 198	96.32 144	99.08 113

thisisatest0515		94.75 88	94.19 90	96.43 94	96.13 178	92.64 86	99.47 53	97.60 104	87.55 215	93.17 139	97.59 143	94.71 13	98.42 168	88.28 194	93.20 177	98.24 171

FA-MVS(test-final)		92.22 158	91.08 164	95.64 125	96.05 179	88.98 165	91.60 350	97.25 152	86.99 221	91.84 153	92.12 272	83.03 161	99.00 148	86.91 210	93.91 173	98.93 127

test_fmvsmconf_n		96.78 31	96.84 26	96.61 83	95.99 180	90.25 129	99.90 2	98.13 42	96.68 9	98.42 32	98.92 72	85.34 129	99.88 52	99.12 20	99.08 73	99.70 52

ab-mvs		91.05 179	89.17 197	96.69 80	95.96 181	91.72 95	92.62 341	97.23 156	85.61 250	89.74 190	93.89 243	68.55 280	99.42 121	91.09 159	87.84 227	98.92 129

Fast-Effi-MVS+		91.72 165	90.79 173	94.49 166	95.89 182	87.40 205	99.54 47	95.70 269	85.01 262	89.28 195	95.68 210	77.75 218	97.57 223	83.22 254	95.06 164	98.51 156

EPP-MVSNet		93.75 116	93.67 107	94.01 189	95.86 183	85.70 250	98.67 148	97.66 89	84.46 269	91.36 166	97.18 163	91.16 31	97.79 201	92.93 144	93.75 174	98.53 155

mvsany_test1		94.57 97	95.09 77	92.98 209	95.84 184	82.07 303	98.76 140	95.24 297	92.87 75	96.45 85	98.71 92	84.81 136	99.15 139	97.68 53	95.49 160	97.73 183

Effi-MVS+		93.87 112	93.15 120	96.02 111	95.79 185	90.76 119	96.70 280	95.78 264	86.98 224	95.71 100	97.17 164	79.58 203	98.01 190	94.57 119	96.09 150	99.31 92

tpm cat1		88.89 217	87.27 233	93.76 196	95.79 185	85.32 259	90.76 360	97.09 174	76.14 348	85.72 225	88.59 338	82.92 163	98.04 188	76.96 302	91.43 208	97.90 181

thisisatest0530		94.00 106	93.52 109	95.43 131	95.76 187	90.02 143	98.99 118	97.60 104	86.58 233	91.74 155	97.36 154	94.78 12	98.34 170	86.37 216	92.48 188	97.94 180

3Dnovator+	87.72 8	93.43 126	91.84 149	98.17 22	95.73 188	95.08 32	98.92 125	97.04 177	91.42 104	81.48 284	97.60 142	74.60 232	99.79 80	90.84 164	98.97 81	99.64 62

MVS		93.92 109	92.28 138	98.83 7	95.69 189	96.82 8	96.22 295	98.17 37	84.89 264	84.34 238	98.61 101	79.32 207	99.83 71	93.88 128	99.43 59	99.86 29

cascas		90.93 181	89.33 195	95.76 120	95.69 189	93.03 78	98.99 118	96.59 199	80.49 327	86.79 218	94.45 232	65.23 311	98.60 165	93.52 135	92.18 194	95.66 231

QAPM		91.41 170	89.49 190	97.17 54	95.66 191	93.42 70	98.60 158	97.51 125	80.92 325	81.39 285	97.41 152	72.89 252	99.87 56	82.33 264	98.68 96	98.21 173

tttt0517		93.30 131	93.01 125	94.17 181	95.57 192	86.47 223	98.51 168	97.60 104	85.99 244	90.55 177	97.19 162	94.80 11	98.31 171	85.06 230	91.86 198	97.74 182

1112_ss		92.71 143	91.55 155	96.20 102	95.56 193	91.12 107	98.48 173	94.69 315	88.29 191	86.89 216	98.50 106	87.02 91	98.66 163	84.75 234	89.77 222	98.81 139

diffmvs		94.59 96	94.19 90	95.81 118	95.54 194	90.69 121	98.70 144	95.68 271	91.61 97	95.96 92	97.81 129	80.11 199	98.06 185	96.52 78	95.76 155	98.67 150
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		88.59 229	88.61 210	88.51 310	95.53 195	72.68 360	96.85 272	88.43 379	88.45 181	73.14 344	90.63 308	75.82 225	94.38 339	92.95 143	95.71 157	98.48 158

Test_1112_low_res		92.27 156	90.97 166	96.18 103	95.53 195	91.10 109	98.47 175	94.66 316	88.28 192	86.83 217	93.50 254	87.00 92	98.65 164	84.69 235	89.74 223	98.80 140

PCF-MVS	89.78 5	91.26 172	89.63 187	96.16 106	95.44 197	91.58 99	95.29 315	96.10 233	85.07 259	82.75 253	97.45 150	78.28 215	99.78 82	80.60 279	95.65 158	97.12 199
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EC-MVSNet		95.09 80	95.17 73	94.84 154	95.42 198	88.17 184	99.48 51	95.92 250	91.47 101	97.34 61	98.36 114	82.77 166	97.41 230	97.24 60	98.58 99	98.94 126

3Dnovator	87.35 11	93.17 137	91.77 151	97.37 47	95.41 199	93.07 76	98.82 132	97.85 56	91.53 99	82.56 259	97.58 144	71.97 259	99.82 74	91.01 161	99.23 69	99.22 101

IB-MVS	89.43 6	92.12 159	90.83 172	95.98 114	95.40 200	90.78 118	99.81 9	98.06 45	91.23 108	85.63 226	93.66 249	90.63 40	98.78 154	91.22 158	71.85 342	98.36 166
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		93.86 113	93.74 106	94.22 179	95.39 201	86.08 239	99.73 20	96.07 236	96.38 15	97.19 67	97.78 132	65.46 310	99.86 61	96.71 70	98.92 85	96.73 211

miper_ehance_all_eth		88.94 215	88.12 221	91.40 243	95.32 202	86.93 216	97.85 227	95.55 278	84.19 272	81.97 275	91.50 287	84.16 142	95.91 305	84.69 235	77.89 293	91.36 293

1314		93.44 125	91.98 146	97.84 32	95.24 203	94.38 52	96.22 295	97.92 53	90.18 132	82.28 267	97.71 137	77.63 219	99.80 79	91.94 154	98.67 97	99.34 90

XVG-OURS		90.83 182	90.49 178	91.86 232	95.23 204	81.25 314	95.79 310	95.92 250	88.96 166	90.02 187	98.03 126	71.60 264	99.35 131	91.06 160	87.78 228	94.98 235

casdiffmvs_mvg		94.00 106	93.33 114	96.03 110	95.22 205	90.90 117	99.09 105	95.99 239	90.58 121	91.55 161	97.37 153	79.91 201	98.06 185	95.01 107	95.22 162	99.13 108
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		93.82 114	93.26 117	95.49 129	95.21 206	90.25 129	99.15 96	97.54 118	89.18 160	91.79 154	94.87 225	89.13 54	97.63 216	86.21 217	96.29 147	98.60 153

xiu_mvs_v1_base_debu		94.73 89	93.98 97	96.99 60	95.19 207	95.24 25	98.62 154	96.50 207	92.99 70	97.52 55	98.83 80	72.37 255	99.15 139	97.03 63	96.74 137	96.58 216

xiu_mvs_v1_base		94.73 89	93.98 97	96.99 60	95.19 207	95.24 25	98.62 154	96.50 207	92.99 70	97.52 55	98.83 80	72.37 255	99.15 139	97.03 63	96.74 137	96.58 216

xiu_mvs_v1_base_debi		94.73 89	93.98 97	96.99 60	95.19 207	95.24 25	98.62 154	96.50 207	92.99 70	97.52 55	98.83 80	72.37 255	99.15 139	97.03 63	96.74 137	96.58 216

XVG-OURS-SEG-HR		90.95 180	90.66 176	91.83 233	95.18 210	81.14 317	95.92 302	95.92 250	88.40 185	90.33 183	97.85 127	70.66 270	99.38 126	92.83 146	88.83 224	94.98 235

Effi-MVS+-dtu		89.97 202	90.68 175	87.81 315	95.15 211	71.98 362	97.87 226	95.40 288	91.92 93	87.57 205	91.44 288	74.27 238	96.84 248	89.45 181	93.10 179	94.60 237

Syy-MVS		84.10 299	84.53 278	82.83 346	95.14 212	65.71 374	97.68 239	96.66 194	86.52 236	82.63 256	96.84 180	68.15 284	89.89 370	45.62 384	91.54 206	92.87 244

myMVS_eth3d		88.68 228	89.07 199	87.50 318	95.14 212	79.74 325	97.68 239	96.66 194	86.52 236	82.63 256	96.84 180	85.22 131	89.89 370	69.43 344	91.54 206	92.87 244

Vis-MVSNet		92.64 145	91.85 148	95.03 148	95.12 214	88.23 183	98.48 173	96.81 189	91.61 97	92.16 152	97.22 160	71.58 265	98.00 191	85.85 224	97.81 113	98.88 131
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GBi-Net		86.67 258	84.96 266	91.80 235	95.11 215	88.81 173	96.77 274	95.25 294	82.94 295	82.12 270	90.25 320	62.89 320	94.97 327	79.04 287	80.24 281	91.62 279

test1		86.67 258	84.96 266	91.80 235	95.11 215	88.81 173	96.77 274	95.25 294	82.94 295	82.12 270	90.25 320	62.89 320	94.97 327	79.04 287	80.24 281	91.62 279

FMVSNet2		86.90 253	84.79 272	93.24 204	95.11 215	92.54 87	97.67 241	95.86 262	82.94 295	80.55 291	91.17 294	62.89 320	95.29 322	77.23 299	79.71 287	91.90 273

GeoE		90.60 188	89.56 188	93.72 199	95.10 218	85.43 255	99.41 66	94.94 306	83.96 277	87.21 211	96.83 182	74.37 236	97.05 241	80.50 281	93.73 175	98.67 150

baseline		93.91 110	93.30 115	95.72 121	95.10 218	90.07 138	97.48 246	95.91 255	91.03 109	93.54 135	97.68 138	79.58 203	98.02 189	94.27 122	95.14 163	99.08 113

casdiffmvs		93.98 108	93.43 111	95.61 127	95.07 220	89.86 147	98.80 134	95.84 263	90.98 111	92.74 145	97.66 140	79.71 202	98.10 182	94.72 114	95.37 161	98.87 133
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 92	94.08 95	96.61 83	95.05 221	94.87 36	97.77 232	96.17 229	86.84 227	98.04 46	98.52 104	85.52 121	95.99 298	89.83 174	98.97 81	98.96 121

lupinMVS		96.32 42	95.94 51	97.44 44	95.05 221	94.87 36	99.86 4	96.50 207	93.82 55	98.04 46	98.77 83	85.52 121	98.09 183	96.98 66	98.97 81	99.37 86

CostFormer		92.89 141	92.48 136	94.12 183	94.99 223	85.89 245	92.89 337	97.00 183	86.98 224	95.00 114	90.78 300	90.05 48	97.51 224	92.92 145	91.73 202	98.96 121

c3_l		88.19 235	87.23 234	91.06 250	94.97 224	86.17 236	97.72 236	95.38 289	83.43 286	81.68 282	91.37 289	82.81 165	95.72 311	84.04 248	73.70 324	91.29 297

SCA		90.64 187	89.25 196	94.83 155	94.95 225	88.83 172	96.26 292	97.21 158	90.06 139	90.03 186	90.62 309	66.61 298	96.81 250	83.16 255	94.36 169	98.84 134

test-LLR		93.11 138	92.68 131	94.40 170	94.94 226	87.27 210	99.15 96	97.25 152	90.21 130	91.57 158	94.04 235	84.89 134	97.58 220	85.94 221	96.13 148	98.36 166

test-mter		93.27 133	92.89 128	94.40 170	94.94 226	87.27 210	99.15 96	97.25 152	88.95 167	91.57 158	94.04 235	88.03 71	97.58 220	85.94 221	96.13 148	98.36 166

cl____		87.82 237	86.79 241	90.89 256	94.88 228	85.43 255	97.81 228	95.24 297	82.91 299	80.71 290	91.22 292	81.97 185	95.84 307	81.34 272	75.06 308	91.40 292

DIV-MVS_self_test		87.82 237	86.81 240	90.87 257	94.87 229	85.39 257	97.81 228	95.22 302	82.92 298	80.76 289	91.31 291	81.99 183	95.81 309	81.36 271	75.04 309	91.42 291

tpm2		91.77 164	91.09 163	93.82 195	94.83 230	85.56 254	92.51 342	97.16 165	84.00 275	93.83 132	90.66 306	87.54 77	97.17 235	87.73 202	91.55 205	98.72 146

PVSNet_0	83.28 16	87.31 249	85.16 264	93.74 198	94.78 231	84.59 270	98.91 126	98.69 21	89.81 142	78.59 315	93.23 259	61.95 324	99.34 132	94.75 112	55.72 379	97.30 195

CDS-MVSNet		93.47 124	93.04 123	94.76 156	94.75 232	89.45 155	98.82 132	97.03 179	87.91 203	90.97 170	96.48 192	89.06 55	96.36 275	89.50 180	92.81 183	98.49 157
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gm-plane-assit					94.69 233	88.14 185			88.22 193		97.20 161		98.29 173	90.79 166

eth_miper_zixun_eth		87.76 240	87.00 238	90.06 278	94.67 234	82.65 298	97.02 267	95.37 290	84.19 272	81.86 280	91.58 286	81.47 190	95.90 306	83.24 253	73.61 325	91.61 282

testing3		87.75 241	88.22 219	86.36 326	94.66 235	77.41 342	99.52 48	97.95 52	86.05 243	81.12 286	96.69 187	86.18 113	89.31 374	61.65 368	90.12 220	92.35 257

RPSCF		85.33 281	85.55 259	84.67 338	94.63 236	62.28 377	93.73 329	93.76 333	74.38 355	85.23 230	97.06 169	64.09 314	98.31 171	80.98 273	86.08 240	93.41 243

miper_lstm_enhance		86.90 253	86.20 249	89.00 305	94.53 237	81.19 315	96.74 278	95.24 297	82.33 308	80.15 296	90.51 316	81.99 183	94.68 336	80.71 277	73.58 326	91.12 301

Patchmatch-test		86.25 267	84.06 284	92.82 212	94.42 238	82.88 294	82.88 382	94.23 327	71.58 360	79.39 306	90.62 309	89.00 57	96.42 272	63.03 364	91.37 210	99.16 104

VDDNet		90.08 199	88.54 215	94.69 160	94.41 239	87.68 194	98.21 201	96.40 212	76.21 347	93.33 138	97.75 134	54.93 350	98.77 155	94.71 115	90.96 212	97.61 189

fmvsm_s_conf0.1_n		95.56 69	95.68 62	95.20 140	94.35 240	89.10 160	99.50 49	97.67 88	94.76 32	98.68 25	99.03 54	81.13 195	99.86 61	98.63 30	97.36 127	96.63 213

test_fmvsmvis_n_1920		95.47 70	95.40 68	95.70 122	94.33 241	90.22 132	99.70 24	96.98 184	96.80 7	92.75 144	98.89 76	82.46 177	99.92 39	98.36 38	98.33 105	96.97 207

KD-MVS_2432*1600		82.98 304	80.52 312	90.38 271	94.32 242	88.98 165	92.87 338	95.87 260	80.46 328	73.79 339	87.49 345	82.76 168	93.29 347	70.56 340	46.53 388	88.87 346

miper_refine_blended		82.98 304	80.52 312	90.38 271	94.32 242	88.98 165	92.87 338	95.87 260	80.46 328	73.79 339	87.49 345	82.76 168	93.29 347	70.56 340	46.53 388	88.87 346

EI-MVSNet		89.87 203	89.38 194	91.36 245	94.32 242	85.87 246	97.61 243	96.59 199	85.10 257	85.51 227	97.10 166	81.30 194	96.56 261	83.85 251	83.03 268	91.64 277

CVMVSNet		90.30 192	90.91 168	88.46 311	94.32 242	73.58 356	97.61 243	97.59 108	90.16 135	88.43 201	97.10 166	76.83 223	92.86 350	82.64 261	93.54 176	98.93 127

test_fmvs1_n		91.07 177	91.41 158	90.06 278	94.10 246	74.31 352	99.18 87	94.84 308	94.81 31	96.37 87	97.46 149	50.86 363	99.82 74	97.14 62	97.90 111	96.04 228

IterMVS-LS		88.34 231	87.44 229	91.04 251	94.10 246	85.85 247	98.10 211	95.48 282	85.12 256	82.03 274	91.21 293	81.35 193	95.63 314	83.86 250	75.73 305	91.63 278
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAMVS		92.62 146	92.09 144	94.20 180	94.10 246	87.68 194	98.41 180	96.97 185	87.53 216	89.74 190	96.04 204	84.77 138	96.49 268	88.97 190	92.31 191	98.42 159

PAPM		96.35 40	95.94 51	97.58 40	94.10 246	95.25 24	98.93 123	98.17 37	94.26 40	93.94 129	98.72 89	89.68 51	97.88 195	96.36 80	99.29 67	99.62 66

CLD-MVS		91.06 178	90.71 174	92.10 228	94.05 250	86.10 238	99.55 42	96.29 221	94.16 43	84.70 233	97.17 164	69.62 275	97.82 199	94.74 113	86.08 240	92.39 252
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP-NCC					93.95 251		99.16 91		93.92 48	87.57 205

ACMP_Plane					93.95 251		99.16 91		93.92 48	87.57 205

HQP-MVS		91.50 167	91.23 161	92.29 222	93.95 251	86.39 226	99.16 91	96.37 214	93.92 48	87.57 205	96.67 188	73.34 244	97.77 203	93.82 131	86.29 235	92.72 246

NP-MVS					93.94 254	86.22 233					96.67 188

plane_prior6					93.92 255	86.02 243						72.92 250

ACMP	87.39 10	88.71 226	88.24 218	90.12 277	93.91 256	81.06 318	98.50 169	95.67 272	89.43 154	80.37 293	95.55 211	65.67 305	97.83 198	90.55 168	84.51 249	91.47 287
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
plane_prior1					93.90 257

HQP_MVS		91.26 172	90.95 167	92.16 226	93.84 258	86.07 241	99.02 114	96.30 218	93.38 64	86.99 212	96.52 190	72.92 250	97.75 209	93.46 136	86.17 238	92.67 248

plane_prior7					93.84 258	85.73 249

dmvs_re		88.69 227	88.06 222	90.59 263	93.83 260	78.68 333	95.75 311	96.18 228	87.99 200	84.48 237	96.32 198	67.52 291	96.94 245	84.98 232	85.49 244	96.14 226

MVS-HIRNet		79.01 323	75.13 335	90.66 262	93.82 261	81.69 306	85.16 372	93.75 334	54.54 382	74.17 337	59.15 388	57.46 339	96.58 260	63.74 361	94.38 168	93.72 240

FMVSNet5		82.29 307	80.54 311	87.52 317	93.79 262	84.01 278	93.73 329	92.47 351	76.92 345	74.27 336	86.15 356	63.69 318	89.24 375	69.07 345	74.79 312	89.29 341

ACMH+	83.78 15	84.21 295	82.56 300	89.15 302	93.73 263	79.16 328	96.43 285	94.28 326	81.09 322	74.00 338	94.03 237	54.58 351	97.67 212	76.10 309	78.81 289	90.63 317

ACMM	86.95 13	88.77 224	88.22 219	90.43 269	93.61 264	81.34 312	98.50 169	95.92 250	87.88 204	83.85 242	95.20 221	67.20 294	97.89 194	86.90 211	84.90 247	92.06 270
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS	85.28 14	90.75 184	88.84 204	96.48 91	93.58 265	93.51 68	98.80 134	97.41 143	82.59 301	78.62 313	97.49 148	68.00 287	99.82 74	84.52 239	98.55 101	96.11 227

IterMVS		85.81 274	84.67 275	89.22 300	93.51 266	83.67 283	96.32 289	94.80 311	85.09 258	78.69 311	90.17 326	66.57 300	93.17 349	79.48 285	77.42 299	90.81 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		88.83 221	87.38 231	93.16 206	93.47 267	86.24 231	84.97 375	94.20 328	88.92 170	90.76 174	86.88 352	84.43 139	94.82 332	70.64 339	92.17 195	98.41 160

RPMNet		85.07 284	81.88 301	94.64 163	93.47 267	86.24 231	84.97 375	97.21 158	64.85 380	90.76 174	78.80 377	80.95 196	99.27 135	53.76 379	92.17 195	98.41 160

IterMVS-SCA-FT		85.73 277	84.64 276	89.00 305	93.46 269	82.90 292	96.27 290	94.70 314	85.02 261	78.62 313	90.35 318	66.61 298	93.33 346	79.38 286	77.36 300	90.76 312

Fast-Effi-MVS+-dtu		88.84 219	88.59 212	89.58 293	93.44 270	78.18 337	98.65 150	94.62 317	88.46 180	84.12 240	95.37 218	68.91 277	96.52 264	82.06 267	91.70 203	94.06 238

Patchmtry		83.61 303	81.64 303	89.50 295	93.36 271	82.84 295	84.10 378	94.20 328	69.47 370	79.57 304	86.88 352	84.43 139	94.78 333	68.48 348	74.30 318	90.88 307

LPG-MVS_test		88.86 218	88.47 216	90.06 278	93.35 272	80.95 319	98.22 199	95.94 246	87.73 210	83.17 249	96.11 202	66.28 302	97.77 203	90.19 172	85.19 245	91.46 288

LGP-MVS_train				90.06 278	93.35 272	80.95 319		95.94 246	87.73 210	83.17 249	96.11 202	66.28 302	97.77 203	90.19 172	85.19 245	91.46 288

JIA-IIPM		85.97 270	84.85 270	89.33 299	93.23 274	73.68 355	85.05 374	97.13 168	69.62 369	91.56 160	68.03 384	88.03 71	96.96 243	77.89 297	93.12 178	97.34 194

ACMH	83.09 17	84.60 289	82.61 299	90.57 264	93.18 275	82.94 290	96.27 290	94.92 307	81.01 323	72.61 350	93.61 250	56.54 341	97.79 201	74.31 321	81.07 279	90.99 304
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PatchT		85.44 280	83.19 289	92.22 223	93.13 276	83.00 289	83.80 381	96.37 214	70.62 363	90.55 177	79.63 376	84.81 136	94.87 330	58.18 375	91.59 204	98.79 141

baseline2		94.04 105	93.80 105	94.74 158	93.07 277	90.25 129	98.12 208	98.16 39	89.86 140	86.53 220	96.95 173	95.56 6	98.05 187	91.44 157	94.53 167	95.93 229

jason		95.40 74	94.86 80	97.03 57	92.91 278	94.23 54	99.70 24	96.30 218	93.56 62	96.73 80	98.52 104	81.46 191	97.91 192	96.08 85	98.47 103	98.96 121
jason: jason.
LTVRE_ROB	81.71 19	84.59 290	82.72 297	90.18 275	92.89 279	83.18 288	93.15 334	94.74 312	78.99 333	75.14 334	92.69 267	65.64 306	97.63 216	69.46 343	81.82 277	89.74 334
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
VPA-MVSNet		89.10 212	87.66 227	93.45 201	92.56 280	91.02 113	97.97 221	98.32 30	86.92 226	86.03 222	92.01 276	68.84 279	97.10 239	90.92 162	75.34 306	92.23 260

tpm		89.67 205	88.95 202	91.82 234	92.54 281	81.43 309	92.95 336	95.92 250	87.81 205	90.50 179	89.44 332	84.99 132	95.65 313	83.67 252	82.71 271	98.38 163

GA-MVS		90.10 198	88.69 208	94.33 174	92.44 282	87.97 190	99.08 106	96.26 222	89.65 145	86.92 215	93.11 262	68.09 285	96.96 243	82.54 263	90.15 219	98.05 176

test_fmvsmconf0.1_n		95.94 56	95.79 59	96.40 97	92.42 283	89.92 145	99.79 14	96.85 188	96.53 13	97.22 63	98.67 95	82.71 170	99.84 67	98.92 25	98.98 80	99.43 83

FIs		90.70 185	89.87 185	93.18 205	92.29 284	91.12 107	98.17 205	98.25 32	89.11 162	83.44 244	94.82 227	82.26 180	96.17 291	87.76 201	82.76 270	92.25 258

ITE_SJBPF				87.93 313	92.26 285	76.44 345		93.47 340	87.67 213	79.95 299	95.49 214	56.50 342	97.38 231	75.24 314	82.33 274	89.98 331

UniMVSNet (Re)		89.50 209	88.32 217	93.03 207	92.21 286	90.96 115	98.90 127	98.39 27	89.13 161	83.22 246	92.03 274	81.69 187	96.34 281	86.79 212	72.53 335	91.81 274

UniMVSNet_NR-MVSNet		89.60 206	88.55 214	92.75 215	92.17 287	90.07 138	98.74 141	98.15 40	88.37 186	83.21 247	93.98 240	82.86 164	95.93 302	86.95 208	72.47 336	92.25 258

TinyColmap		80.42 317	77.94 322	87.85 314	92.09 288	78.58 334	93.74 328	89.94 372	74.99 351	69.77 355	91.78 282	46.09 370	97.58 220	65.17 360	77.89 293	87.38 354

fmvsm_s_conf0.1_n_a		95.16 78	95.15 74	95.18 141	92.06 289	88.94 168	99.29 79	97.53 119	94.46 36	98.98 16	98.99 58	79.99 200	99.85 65	98.24 45	96.86 136	96.73 211

tt0805		86.50 263	84.79 272	91.63 241	91.97 290	81.49 308	96.49 284	97.38 146	82.24 309	82.44 261	95.82 208	51.22 360	98.25 176	84.55 238	80.96 280	95.13 234

MS-PatchMatch		86.75 256	85.92 253	89.22 300	91.97 290	82.47 300	96.91 269	96.14 231	83.74 280	77.73 320	93.53 253	58.19 337	97.37 233	76.75 305	98.35 104	87.84 351

VPNet		88.30 232	86.57 243	93.49 200	91.95 292	91.35 101	98.18 203	97.20 162	88.61 175	84.52 236	94.89 224	62.21 323	96.76 253	89.34 184	72.26 339	92.36 254

FMVSNet1		83.94 300	81.32 308	91.80 235	91.94 293	88.81 173	96.77 274	95.25 294	77.98 338	78.25 318	90.25 320	50.37 364	94.97 327	73.27 330	77.81 297	91.62 279

WR-MVS		88.54 230	87.22 235	92.52 220	91.93 294	89.50 154	98.56 163	97.84 57	86.99 221	81.87 278	93.81 244	74.25 239	95.92 304	85.29 227	74.43 316	92.12 267

D2MVS		87.96 236	87.39 230	89.70 290	91.84 295	83.40 285	98.31 194	98.49 23	88.04 198	78.23 319	90.26 319	73.57 242	96.79 252	84.21 242	83.53 263	88.90 345

FC-MVSNet-test		90.22 194	89.40 193	92.67 219	91.78 296	89.86 147	97.89 223	98.22 35	88.81 172	82.96 252	94.66 229	81.90 186	95.96 300	85.89 223	82.52 273	92.20 264

MIMVSNet		84.48 292	81.83 302	92.42 221	91.73 297	87.36 206	85.52 371	94.42 323	81.40 318	81.91 276	87.58 342	51.92 358	92.81 352	73.84 326	88.15 226	97.08 203

USDC		84.74 286	82.93 291	90.16 276	91.73 297	83.54 284	95.00 317	93.30 342	88.77 173	73.19 343	93.30 257	53.62 354	97.65 215	75.88 311	81.54 278	89.30 340

test_vis1_n		90.40 189	90.27 180	90.79 259	91.55 299	76.48 344	99.12 103	94.44 320	94.31 39	97.34 61	96.95 173	43.60 374	99.42 121	97.57 55	97.60 118	96.47 220

nrg030		90.23 193	88.87 203	94.32 175	91.53 300	93.54 67	98.79 138	95.89 258	88.12 196	84.55 235	94.61 230	78.80 212	96.88 247	92.35 152	75.21 307	92.53 250

DU-MVS		88.83 221	87.51 228	92.79 213	91.46 301	90.07 138	98.71 142	97.62 101	88.87 171	83.21 247	93.68 247	74.63 230	95.93 302	86.95 208	72.47 336	92.36 254

NR-MVSNet		87.74 244	86.00 252	92.96 210	91.46 301	90.68 122	96.65 281	97.42 142	88.02 199	73.42 341	93.68 247	77.31 220	95.83 308	84.26 241	71.82 343	92.36 254

tfpnnormal		83.65 301	81.35 307	90.56 266	91.37 303	88.06 187	97.29 253	97.87 55	78.51 337	76.20 324	90.91 297	64.78 312	96.47 269	61.71 367	73.50 327	87.13 359

test_vis1_rt		81.31 313	80.05 316	85.11 333	91.29 304	70.66 366	98.98 120	77.39 394	85.76 248	68.80 358	82.40 365	36.56 381	99.44 117	92.67 149	86.55 234	85.24 369

test_0402		78.81 325	76.33 330	86.26 327	91.18 305	78.44 336	95.88 305	91.34 366	68.55 371	70.51 354	89.91 327	52.65 357	94.99 326	47.14 383	79.78 286	85.34 368

test0.0.03 1		88.96 214	88.61 210	90.03 282	91.09 306	84.43 272	98.97 121	97.02 181	90.21 130	80.29 294	96.31 199	84.89 134	91.93 364	72.98 332	85.70 243	93.73 239

WR-MVS_H		86.53 262	85.49 260	89.66 292	91.04 307	83.31 287	97.53 245	98.20 36	84.95 263	79.64 302	90.90 298	78.01 217	95.33 321	76.29 308	72.81 332	90.35 321

CP-MVSNet		86.54 261	85.45 261	89.79 288	91.02 308	82.78 296	97.38 249	97.56 114	85.37 253	79.53 305	93.03 263	71.86 261	95.25 323	79.92 282	73.43 330	91.34 294

TranMVSNet+NR-MVSNet		87.75 241	86.31 247	92.07 229	90.81 309	88.56 178	98.33 191	97.18 163	87.76 207	81.87 278	93.90 242	72.45 254	95.43 318	83.13 257	71.30 346	92.23 260

PS-CasMVS		85.81 274	84.58 277	89.49 297	90.77 310	82.11 302	97.20 260	97.36 148	84.83 265	79.12 310	92.84 266	67.42 293	95.16 325	78.39 295	73.25 331	91.21 299

DeepMVS_CX				76.08 357	90.74 311	51.65 390		90.84 368	86.47 239	57.89 378	87.98 339	35.88 382	92.60 354	65.77 358	65.06 363	83.97 373

mvsmamba		89.99 201	89.42 192	91.69 240	90.64 312	86.34 229	98.40 183	92.27 353	91.01 110	84.80 232	94.93 223	76.12 224	96.51 265	92.81 147	83.84 258	92.21 262

OPM-MVS		89.76 204	89.15 198	91.57 242	90.53 313	85.58 253	98.11 210	95.93 249	92.88 74	86.05 221	96.47 193	67.06 296	97.87 196	89.29 187	86.08 240	91.26 298
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XXY-MVS		87.75 241	86.02 251	92.95 211	90.46 314	89.70 150	97.71 238	95.90 256	84.02 274	80.95 287	94.05 234	67.51 292	97.10 239	85.16 228	78.41 290	92.04 271

UniMVSNet_ETH3D		85.65 279	83.79 287	91.21 246	90.41 315	80.75 321	95.36 314	95.78 264	78.76 336	81.83 281	94.33 233	49.86 365	96.66 254	84.30 240	83.52 264	96.22 225

RRT_MVS		88.91 216	88.56 213	89.93 283	90.31 316	81.61 307	98.08 214	96.38 213	89.30 156	82.41 264	94.84 226	73.15 248	96.04 297	90.38 169	82.23 275	92.15 265

v10		85.73 277	84.01 285	90.87 257	90.03 317	86.73 219	97.20 260	95.22 302	81.25 320	79.85 301	89.75 329	73.30 246	96.28 287	76.87 303	72.64 334	89.61 337

v8		86.11 268	84.45 279	91.10 249	89.99 318	86.85 217	97.24 257	95.36 291	81.99 312	79.89 300	89.86 328	74.53 234	96.39 273	78.83 291	72.32 338	90.05 329

V42		87.00 252	85.68 257	90.98 253	89.91 319	86.08 239	98.32 193	95.61 275	83.67 283	82.72 254	90.67 305	74.00 241	96.53 263	81.94 269	74.28 319	90.32 322

XVG-ACMP-BASELINE		85.86 272	84.95 268	88.57 309	89.90 320	77.12 343	94.30 323	95.60 276	87.40 218	82.12 270	92.99 265	53.42 355	97.66 213	85.02 231	83.83 259	90.92 306

PEN-MVS		85.21 282	83.93 286	89.07 304	89.89 321	81.31 313	97.09 263	97.24 155	84.45 270	78.66 312	92.68 268	68.44 282	94.87 330	75.98 310	70.92 347	91.04 303

test_fmvs2		85.10 283	85.45 261	84.02 341	89.85 322	65.63 375	98.49 171	92.59 349	90.45 125	85.43 229	93.32 255	43.94 372	96.59 257	90.81 165	84.19 255	89.85 333

v1144		86.83 255	85.31 263	91.40 243	89.75 323	87.21 214	98.31 194	95.45 284	83.22 289	82.70 255	90.78 300	73.36 243	96.36 275	79.49 284	74.69 313	90.63 317

TransMVSNet (Re)		81.97 309	79.61 318	89.08 303	89.70 324	84.01 278	97.26 255	91.85 361	78.84 334	73.07 347	91.62 284	67.17 295	95.21 324	67.50 351	59.46 373	88.02 350

v2v482		87.27 250	85.76 255	91.78 239	89.59 325	87.58 198	98.56 163	95.54 279	84.53 268	82.51 260	91.78 282	73.11 249	96.47 269	82.07 266	74.14 322	91.30 296

pm-mvs1		84.68 288	82.78 295	90.40 270	89.58 326	85.18 261	97.31 252	94.73 313	81.93 314	76.05 326	92.01 276	65.48 309	96.11 294	78.75 292	69.14 349	89.91 332

pmmvs4		87.58 247	86.17 250	91.80 235	89.58 326	88.92 171	97.25 256	95.28 293	82.54 303	80.49 292	93.17 261	75.62 227	96.05 296	82.75 260	78.90 288	90.42 320

bld_raw_dy_0_64		87.82 237	86.71 242	91.15 248	89.54 328	85.61 251	97.37 250	89.16 377	89.26 157	83.42 245	94.50 231	65.79 304	96.18 289	88.00 199	83.37 265	91.67 276

v1192		86.32 266	84.71 274	91.17 247	89.53 329	86.40 225	98.13 206	95.44 286	82.52 304	82.42 263	90.62 309	71.58 265	96.33 282	77.23 299	74.88 310	90.79 310

v144192		86.40 264	84.89 269	90.91 254	89.48 330	85.59 252	98.21 201	95.43 287	82.45 306	82.62 258	90.58 312	72.79 253	96.36 275	78.45 294	74.04 323	90.79 310

v148		86.38 265	85.06 265	90.37 273	89.47 331	84.10 277	98.52 165	95.48 282	83.80 279	80.93 288	90.22 323	74.60 232	96.31 283	80.92 275	71.55 344	90.69 315

v1921920		86.02 269	84.44 280	90.77 260	89.32 332	85.20 260	98.10 211	95.35 292	82.19 310	82.25 268	90.71 302	70.73 268	96.30 286	76.85 304	74.49 315	90.80 309

v1240		85.77 276	84.11 283	90.73 261	89.26 333	85.15 263	97.88 225	95.23 301	81.89 315	82.16 269	90.55 314	69.60 276	96.31 283	75.59 313	74.87 311	90.72 314

our_test_3		84.47 293	82.80 293	89.50 295	89.01 334	83.90 280	97.03 265	94.56 318	81.33 319	75.36 333	90.52 315	71.69 263	94.54 338	68.81 346	76.84 301	90.07 327

ppachtmachnet_test		83.63 302	81.57 305	89.80 287	89.01 334	85.09 264	97.13 262	94.50 319	78.84 334	76.14 325	91.00 296	69.78 272	94.61 337	63.40 362	74.36 317	89.71 336

DTE-MVSNet		84.14 297	82.80 293	88.14 312	88.95 336	79.87 324	96.81 273	96.24 223	83.50 285	77.60 321	92.52 270	67.89 289	94.24 341	72.64 334	69.05 350	90.32 322

PS-MVSNAJss		89.54 208	89.05 200	91.00 252	88.77 337	84.36 273	97.39 247	95.97 241	88.47 178	81.88 277	93.80 245	82.48 174	96.50 266	89.34 184	83.34 267	92.15 265

Baseline_NR-MVSNet		85.83 273	84.82 271	88.87 308	88.73 338	83.34 286	98.63 153	91.66 362	80.41 330	82.44 261	91.35 290	74.63 230	95.42 319	84.13 244	71.39 345	87.84 351

MVP-Stereo		86.61 260	85.83 254	88.93 307	88.70 339	83.85 281	96.07 299	94.41 324	82.15 311	75.64 331	91.96 279	67.65 290	96.45 271	77.20 301	98.72 95	86.51 362
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EU-MVSNet		84.19 296	84.42 281	83.52 344	88.64 340	67.37 373	96.04 300	95.76 266	85.29 254	78.44 316	93.18 260	70.67 269	91.48 366	75.79 312	75.98 303	91.70 275

pmmvs5		85.87 271	84.40 282	90.30 274	88.53 341	84.23 274	98.60 158	93.71 335	81.53 317	80.29 294	92.02 275	64.51 313	95.52 316	82.04 268	78.34 291	91.15 300

MDA-MVSNet-bldmvs		77.82 331	74.75 337	87.03 322	88.33 342	78.52 335	96.34 288	92.85 346	75.57 349	48.87 384	87.89 340	57.32 340	92.49 358	60.79 369	64.80 364	90.08 326

N_pmnet		70.19 343	69.87 345	71.12 364	88.24 343	30.63 403	95.85 308	28.70 402	70.18 366	68.73 359	86.55 354	64.04 315	93.81 342	53.12 380	73.46 328	88.94 344

v7n		84.42 294	82.75 296	89.43 298	88.15 344	81.86 304	96.75 277	95.67 272	80.53 326	78.38 317	89.43 333	69.89 271	96.35 280	73.83 327	72.13 340	90.07 327

SixPastTwentyTwo		82.63 306	81.58 304	85.79 330	88.12 345	71.01 365	95.17 316	92.54 350	84.33 271	72.93 348	92.08 273	60.41 331	95.61 315	74.47 320	74.15 321	90.75 313

test_djsdf		88.26 234	87.73 225	89.84 286	88.05 346	82.21 301	97.77 232	96.17 229	86.84 227	82.41 264	91.95 280	72.07 258	95.99 298	89.83 174	84.50 250	91.32 295

mvs_tets		87.09 251	86.22 248	89.71 289	87.87 347	81.39 311	96.73 279	95.90 256	88.19 194	79.99 298	93.61 250	59.96 332	96.31 283	89.40 183	84.34 253	91.43 290

OurMVSNet-221017-0		84.13 298	83.59 288	85.77 331	87.81 348	70.24 367	94.89 318	93.65 337	86.08 242	76.53 323	93.28 258	61.41 326	96.14 293	80.95 274	77.69 298	90.93 305

YYNet1		79.64 322	77.04 327	87.43 320	87.80 349	79.98 323	96.23 294	94.44 320	73.83 357	51.83 381	87.53 343	67.96 288	92.07 363	66.00 357	67.75 356	90.23 324

MDA-MVSNet_test_wron		79.65 321	77.05 326	87.45 319	87.79 350	80.13 322	96.25 293	94.44 320	73.87 356	51.80 382	87.47 347	68.04 286	92.12 362	66.02 356	67.79 355	90.09 325

jajsoiax		87.35 248	86.51 245	89.87 284	87.75 351	81.74 305	97.03 265	95.98 240	88.47 178	80.15 296	93.80 245	61.47 325	96.36 275	89.44 182	84.47 252	91.50 286

K. test v3		81.04 314	79.77 317	84.83 336	87.41 352	70.23 368	95.60 313	93.93 332	83.70 282	67.51 365	89.35 334	55.76 343	93.58 345	76.67 306	68.03 353	90.67 316

dmvs_testset		77.17 333	78.99 320	71.71 362	87.25 353	38.55 399	91.44 352	81.76 390	85.77 247	69.49 356	95.94 206	69.71 274	84.37 382	52.71 381	76.82 302	92.21 262

testgi		82.29 307	81.00 310	86.17 328	87.24 354	74.84 351	97.39 247	91.62 363	88.63 174	75.85 330	95.42 215	46.07 371	91.55 365	66.87 355	79.94 285	92.12 267

LF4IMVS		81.94 310	81.17 309	84.25 340	87.23 355	68.87 372	93.35 333	91.93 360	83.35 288	75.40 332	93.00 264	49.25 368	96.65 255	78.88 290	78.11 292	87.22 358

EG-PatchMatch MVS		79.92 318	77.59 323	86.90 323	87.06 356	77.90 341	96.20 297	94.06 330	74.61 353	66.53 369	88.76 337	40.40 379	96.20 288	67.02 353	83.66 262	86.61 360

test_fmvsmconf0.01_n		94.14 103	93.51 110	96.04 109	86.79 357	89.19 157	99.28 81	95.94 246	95.70 19	95.50 104	98.49 108	73.27 247	99.79 80	98.28 43	98.32 107	99.15 105

Gipuma		54.77 355	52.22 359	62.40 373	86.50 358	59.37 381	50.20 391	90.35 371	36.52 389	41.20 390	49.49 391	18.33 392	81.29 384	32.10 390	65.34 362	46.54 391
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
anonymousdsp		86.69 257	85.75 256	89.53 294	86.46 359	82.94 290	96.39 286	95.71 268	83.97 276	79.63 303	90.70 303	68.85 278	95.94 301	86.01 218	84.02 257	89.72 335

EGC-MVSNET		60.70 350	55.37 354	76.72 356	86.35 360	71.08 363	89.96 363	84.44 387	0.38 399	1.50 400	84.09 361	37.30 380	88.10 378	40.85 388	73.44 329	70.97 384

test_method		70.10 344	68.66 347	74.41 361	86.30 361	55.84 383	94.47 320	89.82 373	35.18 390	66.15 370	84.75 360	30.54 384	77.96 391	70.40 342	60.33 371	89.44 339

lessismore_v0				85.08 334	85.59 362	69.28 370		90.56 370		67.68 364	90.21 324	54.21 353	95.46 317	73.88 325	62.64 367	90.50 319

CMPMVS	58.40 21	80.48 316	80.11 315	81.59 352	85.10 363	59.56 380	94.14 326	95.95 245	68.54 372	60.71 376	93.31 256	55.35 348	97.87 196	83.06 258	84.85 248	87.33 356
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20231206		80.76 315	79.42 319	84.79 337	84.78 364	72.98 357	96.53 282	92.97 344	79.56 331	74.33 335	88.83 336	61.27 327	92.15 361	60.59 370	75.92 304	89.24 342

DSMNet-mixed		81.60 312	81.43 306	82.10 349	84.36 365	60.79 378	93.63 331	86.74 382	79.00 332	79.32 307	87.15 350	63.87 316	89.78 372	66.89 354	91.92 197	95.73 230

pmmvs6		79.90 319	77.31 325	87.67 316	84.17 366	78.13 338	95.86 307	93.68 336	67.94 374	72.67 349	89.62 331	50.98 362	95.75 310	74.80 319	66.04 360	89.14 343

new_pmnet		76.02 334	73.71 339	82.95 345	83.88 367	72.85 359	91.26 355	92.26 354	70.44 365	62.60 374	81.37 369	47.64 369	92.32 359	61.85 366	72.10 341	83.68 374

OpenMVS_ROB	73.86 20	77.99 330	75.06 336	86.77 324	83.81 368	77.94 340	96.38 287	91.53 365	67.54 375	68.38 360	87.13 351	43.94 372	96.08 295	55.03 378	81.83 276	86.29 363

test20.03		78.51 328	77.48 324	81.62 351	83.07 369	71.03 364	96.11 298	92.83 347	81.66 316	69.31 357	89.68 330	57.53 338	87.29 380	58.65 374	68.47 351	86.53 361

Anonymous20240521		78.63 327	76.90 328	83.82 342	82.82 370	72.86 358	95.72 312	93.57 338	73.55 358	72.17 351	84.79 359	49.69 366	92.51 357	65.29 359	74.50 314	86.09 364

UnsupCasMVSNet_eth		78.90 324	76.67 329	85.58 332	82.81 371	74.94 350	91.98 345	96.31 217	84.64 267	65.84 371	87.71 341	51.33 359	92.23 360	72.89 333	56.50 378	89.56 338

KD-MVS_self_test		77.47 332	75.88 332	82.24 347	81.59 372	68.93 371	92.83 340	94.02 331	77.03 344	73.14 344	83.39 362	55.44 347	90.42 367	67.95 349	57.53 376	87.38 354

CL-MVSNet_self_test		79.89 320	78.34 321	84.54 339	81.56 373	75.01 349	96.88 271	95.62 274	81.10 321	75.86 329	85.81 357	68.49 281	90.26 368	63.21 363	56.51 377	88.35 348

MIMVSNet1		75.92 335	73.30 340	83.81 343	81.29 374	75.57 347	92.26 343	92.05 358	73.09 359	67.48 366	86.18 355	40.87 378	87.64 379	55.78 377	70.68 348	88.21 349

Patchmatch-RL test		81.90 311	80.13 314	87.23 321	80.71 375	70.12 369	84.07 379	88.19 380	83.16 291	70.57 352	82.18 367	87.18 87	92.59 355	82.28 265	62.78 366	98.98 119

APD_test1		68.93 345	66.98 348	74.77 360	80.62 376	53.15 387	87.97 366	85.01 385	53.76 383	59.26 377	87.52 344	25.19 386	89.95 369	56.20 376	67.33 357	81.19 378

pmmvs-eth3d		78.71 326	76.16 331	86.38 325	80.25 377	81.19 315	94.17 325	92.13 357	77.97 339	66.90 368	82.31 366	55.76 343	92.56 356	73.63 329	62.31 369	85.38 366

UnsupCasMVSNet_bld		73.85 340	70.14 344	84.99 335	79.44 378	75.73 346	88.53 365	95.24 297	70.12 367	61.94 375	74.81 381	41.41 377	93.62 344	68.65 347	51.13 385	85.62 365

PM-MVS		74.88 338	72.85 341	80.98 353	78.98 379	64.75 376	90.81 359	85.77 383	80.95 324	68.23 362	82.81 363	29.08 385	92.84 351	76.54 307	62.46 368	85.36 367

new-patchmatchnet		74.80 339	72.40 342	81.99 350	78.36 380	72.20 361	94.44 321	92.36 352	77.06 343	63.47 373	79.98 375	51.04 361	88.85 376	60.53 371	54.35 380	84.92 371

test_fmvs3		75.09 337	75.19 334	74.81 359	77.45 381	54.08 385	95.93 301	90.64 369	82.51 305	73.29 342	81.19 370	22.29 388	86.29 381	85.50 226	67.89 354	84.06 372

WB-MVS		66.44 346	66.29 349	66.89 367	74.84 382	44.93 394	93.00 335	84.09 388	71.15 362	55.82 379	81.63 368	63.79 317	80.31 389	21.85 393	50.47 386	75.43 380

SSC-MVS		65.42 347	65.20 350	66.06 368	73.96 383	43.83 395	92.08 344	83.54 389	69.77 368	54.73 380	80.92 372	63.30 319	79.92 390	20.48 394	48.02 387	74.44 381

pmmvs3		72.86 341	69.76 346	82.17 348	73.86 384	74.19 353	94.20 324	89.01 378	64.23 381	67.72 363	80.91 373	41.48 376	88.65 377	62.40 365	54.02 381	83.68 374

mvsany_test3		75.85 336	74.52 338	79.83 354	73.53 385	60.64 379	91.73 348	87.87 381	83.91 278	70.55 353	82.52 364	31.12 383	93.66 343	86.66 214	62.83 365	85.19 370

test_f		71.94 342	70.82 343	75.30 358	72.77 386	53.28 386	91.62 349	89.66 375	75.44 350	64.47 372	78.31 378	20.48 389	89.56 373	78.63 293	66.02 361	83.05 377

ambc				79.60 355	72.76 387	56.61 382	76.20 386	92.01 359		68.25 361	80.23 374	23.34 387	94.73 334	73.78 328	60.81 370	87.48 353

TDRefinement		78.01 329	75.31 333	86.10 329	70.06 388	73.84 354	93.59 332	91.58 364	74.51 354	73.08 346	91.04 295	49.63 367	97.12 236	74.88 317	59.47 372	87.33 356

test_vis3_rt		61.29 349	58.75 352	68.92 366	67.41 389	52.84 388	91.18 357	59.23 401	66.96 376	41.96 389	58.44 389	11.37 397	94.72 335	74.25 322	57.97 375	59.20 388

testf1		56.38 353	53.73 356	64.31 371	64.84 390	45.11 392	80.50 384	75.94 396	38.87 386	42.74 386	75.07 379	11.26 398	81.19 385	41.11 386	53.27 382	66.63 385

APD_test2		56.38 353	53.73 356	64.31 371	64.84 390	45.11 392	80.50 384	75.94 396	38.87 386	42.74 386	75.07 379	11.26 398	81.19 385	41.11 386	53.27 382	66.63 385

PMMVS2		58.97 352	55.07 355	70.69 365	62.72 392	55.37 384	85.97 370	80.52 391	49.48 384	45.94 385	68.31 383	15.73 394	80.78 387	49.79 382	37.12 390	75.91 379

E-PMN		41.02 360	40.93 362	41.29 377	61.97 393	33.83 400	84.00 380	65.17 399	27.17 392	27.56 392	46.72 393	17.63 393	60.41 396	19.32 395	18.82 392	29.61 392

wuyk23d		16.71 364	16.73 368	16.65 379	60.15 394	25.22 404	41.24 392	5.17 403	6.56 396	5.48 399	3.61 399	3.64 401	22.72 398	15.20 397	9.52 396	1.99 396

FPMVS		61.57 348	60.32 351	65.34 369	60.14 395	42.44 397	91.02 358	89.72 374	44.15 385	42.63 388	80.93 371	19.02 390	80.59 388	42.50 385	72.76 333	73.00 382

EMVS		39.96 361	39.88 363	40.18 378	59.57 396	32.12 402	84.79 377	64.57 400	26.27 393	26.14 394	44.18 396	18.73 391	59.29 397	17.03 396	17.67 394	29.12 393

LCM-MVSNet		60.07 351	56.37 353	71.18 363	54.81 397	48.67 391	82.17 383	89.48 376	37.95 388	49.13 383	69.12 382	13.75 396	81.76 383	59.28 372	51.63 384	83.10 376

MVE	44.00 22	41.70 359	37.64 364	53.90 376	49.46 398	43.37 396	65.09 390	66.66 398	26.19 394	25.77 395	48.53 392	3.58 402	63.35 395	26.15 392	27.28 391	54.97 390
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		50.71 357	46.17 360	64.33 370	44.27 399	52.30 389	76.13 387	78.73 392	64.95 379	27.37 393	55.23 390	14.61 395	67.74 393	36.01 389	18.23 393	72.95 383

PMVS	41.42 23	45.67 358	42.50 361	55.17 375	34.28 400	32.37 401	66.24 389	78.71 393	30.72 391	22.04 396	59.59 387	4.59 400	77.85 392	27.49 391	58.84 374	55.29 389
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		53.66 356	52.86 358	56.05 374	32.75 401	41.97 398	73.42 388	76.12 395	21.91 395	39.68 391	96.39 196	42.59 375	65.10 394	78.00 296	14.92 395	61.08 387

testmvs		18.81 363	23.05 366	6.10 381	4.48 402	2.29 406	97.78 230	3.00 404	3.27 397	18.60 397	62.71 385	1.53 404	2.49 400	14.26 398	1.80 397	13.50 395

test123		16.58 365	19.47 367	7.91 380	3.59 403	5.37 405	94.32 322	1.39 405	2.49 398	13.98 398	44.60 395	2.91 403	2.65 399	11.35 399	0.57 398	15.70 394

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

eth-test2					0.00 404

eth-test					0.00 404

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

cdsmvs_eth3d_5k		22.52 362	30.03 365	0.00 382	0.00 404	0.00 407	0.00 393	97.17 164	0.00 400	0.00 401	98.77 83	74.35 237	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		6.87 367	9.16 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	82.48 174	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

ab-mvs-re		8.21 366	10.94 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	98.50 106	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

MM				98.86 5		96.83 7	99.81 9	99.13 9	97.66 2	98.29 37	98.96 64	85.84 119	99.90 48	99.72 3	98.80 91	99.85 30

WAC-MVS						79.74 325								67.75 350

PC_three_1452									94.60 34	99.41 2	99.12 44	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

test_241102_TWO								97.72 76	94.17 41	99.23 8	99.54 3	93.14 24	99.98 9	99.70 4	99.82 19	99.99 1

test_0728_THIRD									93.01 68	99.07 13	99.46 10	94.66 14	99.97 21	99.25 16	99.82 19	99.95 15

GSMVS																98.84 134

sam_mvs1												88.39 63				98.84 134

sam_mvs												87.08 89

MTGPA								97.45 136

test_post1							90.74 361				41.37 397	85.38 128	96.36 275	83.16 255

test_post											46.00 394	87.37 81	97.11 237

patchmatchnet-post											84.86 358	88.73 60	96.81 250

MTMP							99.21 84	91.09 367

test9_res														98.60 31	99.87 9	99.90 22

agg_prior2														97.84 52	99.87 9	99.91 21

test_prior4						92.00 92	99.41 66

test_prior2							99.57 40		91.43 103	98.12 42	98.97 60	90.43 43		98.33 40	99.81 23

旧先验2							98.67 148		85.75 249	98.96 18			98.97 150	93.84 129

新几何2							98.26 197

无先验							98.52 165	97.82 60	87.20 220				99.90 48	87.64 203		99.85 30

原ACMM2							98.69 145

testdata2													99.88 52	84.16 243

segment_acmp												90.56 41

testdata1							97.89 223		92.43 80

plane_prior5								96.30 218					97.75 209	93.46 136	86.17 238	92.67 248

plane_prior4											96.52 190

plane_prior3						85.91 244			93.65 59	86.99 212

plane_prior2							99.02 114		93.38 64

plane_prior						86.07 241	99.14 99		93.81 56						86.26 237

n2								0.00 406

nn								0.00 406

door-mid								84.90 386

test11								97.68 85

door								85.30 384

HQP5-MVS						86.39 226

BP-MVS														93.82 131

HQP4-MVS										87.57 205			97.77 203			92.72 246

HQP3-MVS								96.37 214							86.29 235

HQP2-MVS												73.34 244

MDTV_nov1_ep13_2view						91.17 106	91.38 353		87.45 217	93.08 141		86.67 100		87.02 206		98.95 125

ACMMP++_ref															82.64 272

ACMMP++															83.83 259

Test By Simon												83.62 148

High-resolution multi-view benchmark