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.

DPM-MVS		96.21 2	95.53 12	98.26 1	96.26 98	95.09 1	99.15 7	96.98 34	93.39 14	96.45 22	98.79 8	90.17 10	99.99 1	89.33 121	99.25 6	99.70 3

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 9				98.54 19	92.06 3	99.84 12	99.11 2	99.37 1	99.74 1

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 46					99.81 21	98.08 12	98.81 24	99.43 11

No_MVS				97.14 3	99.05 9	92.19 4		96.83 46					99.81 21	98.08 12	98.81 24	99.43 11

MVS		90.60 99	88.64 124	96.50 5	94.25 156	90.53 8	93.33 280	97.21 22	77.59 287	78.88 231	97.31 90	71.52 197	99.69 47	89.60 116	98.03 54	99.27 20

DELS-MVS		94.98 13	94.49 21	96.44 6	96.42 95	90.59 7	99.21 4	97.02 32	94.40 8	91.46 84	97.08 102	83.32 45	99.69 47	92.83 77	98.70 30	99.04 25
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
MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 21	97.10 30	95.17 3	92.11 76	98.46 24	87.33 24	99.97 2	97.21 26	99.31 4	99.63 7

MM				96.15 8		89.50 9	99.18 5	98.10 8	95.68 1	96.64 18	97.92 56	80.72 59	99.80 25	99.16 1	97.96 56	99.15 24

PS-MVSNAJ		94.17 26	93.52 37	96.10 9	95.65 113	92.35 2	98.21 42	95.79 149	92.42 21	96.24 24	98.18 36	71.04 202	99.17 93	96.77 31	97.39 75	96.79 152

xiu_mvs_v2_base		93.92 31	93.26 41	95.91 10	95.07 131	92.02 6	98.19 43	95.68 155	92.06 25	96.01 28	98.14 40	70.83 205	98.96 107	96.74 33	96.57 94	96.76 155

MVS_0304		95.36 9	95.20 14	95.85 11	94.89 138	89.22 12	98.83 23	97.88 11	94.68 4	95.14 36	97.99 50	80.80 58	99.81 21	98.60 4	97.95 57	98.50 50

MG-MVS		94.25 25	93.72 31	95.85 11	99.38 3	89.35 11	97.98 57	98.09 9	89.99 49	92.34 72	96.97 106	81.30 56	98.99 105	88.54 127	98.88 20	99.20 22

CANet		94.89 14	94.64 19	95.63 13	97.55 75	88.12 16	99.06 14	96.39 106	94.07 10	95.34 32	97.80 65	76.83 115	99.87 8	97.08 28	97.64 66	98.89 30

WTY-MVS		92.65 56	91.68 71	95.56 14	96.00 105	88.90 13	98.23 41	97.65 14	88.57 67	89.82 108	97.22 96	79.29 73	99.06 102	89.57 117	88.73 176	98.73 39

CNVR-MVS		96.30 1	96.54 1	95.55 15	99.31 5	87.69 22	99.06 14	97.12 28	94.66 5	96.79 14	98.78 9	86.42 29	99.95 3	97.59 21	99.18 7	99.00 27

canonicalmvs		92.27 63	91.22 77	95.41 16	95.80 110	88.31 14	97.09 127	94.64 212	88.49 69	92.99 67	97.31 90	72.68 183	98.57 125	93.38 69	88.58 177	99.36 16

HY-MVS	84.06 6	91.63 75	90.37 94	95.39 17	96.12 102	88.25 15	90.22 318	97.58 16	88.33 73	90.50 101	91.96 215	79.26 74	99.06 102	90.29 109	89.07 171	98.88 31

test_0728_SECOND				95.14 18	99.04 14	86.14 35	99.06 14	96.77 55					99.84 12	97.90 15	98.85 21	99.45 10

alignmvs		92.97 44	92.26 60	95.12 19	95.54 116	87.77 20	98.67 27	96.38 107	88.04 78	93.01 66	97.45 83	79.20 76	98.60 123	93.25 72	88.76 175	98.99 29

DeepC-MVS_fast	89.06 2	94.48 21	94.30 26	95.02 20	98.86 21	85.68 44	98.06 53	96.64 75	93.64 12	91.74 82	98.54 19	80.17 67	99.90 5	92.28 82	98.75 28	99.49 8
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator+	82.88 8	89.63 117	87.85 137	94.99 21	94.49 152	86.76 31	97.84 65	95.74 152	86.10 116	75.47 276	96.02 129	65.00 238	99.51 69	82.91 184	97.07 82	98.72 40

DVP-MVS++		96.05 4	96.41 3	94.96 22	99.05 9	85.34 49	98.13 47	96.77 55	88.38 71	97.70 6	98.77 10	92.06 3	99.84 12	97.47 22	99.37 1	99.70 3

SED-MVS		95.88 5	96.22 4	94.87 23	99.03 15	85.03 61	99.12 9	96.78 49	88.72 64	97.79 4	98.91 2	88.48 17	99.82 18	98.15 9	98.97 17	99.74 1

HPM-MVS++		95.32 10	95.48 13	94.85 24	98.62 34	86.04 36	97.81 68	96.93 40	92.45 20	95.69 29	98.50 22	85.38 31	99.85 10	94.75 52	99.18 7	98.65 43

VNet		92.11 66	91.22 77	94.79 25	96.91 91	86.98 27	97.91 61	97.96 10	86.38 112	93.65 57	95.74 134	70.16 210	98.95 109	93.39 67	88.87 174	98.43 55

SMA-MVS		94.70 18	94.68 18	94.76 26	98.02 59	85.94 39	97.47 93	96.77 55	85.32 130	97.92 3	98.70 15	83.09 47	99.84 12	95.79 40	99.08 10	98.49 51
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
lupinMVS		93.87 32	93.58 36	94.75 27	93.00 194	88.08 17	99.15 7	95.50 164	91.03 35	94.90 41	97.66 70	78.84 81	97.56 167	94.64 55	97.46 70	98.62 45

NCCC		95.63 6	95.94 8	94.69 28	99.21 6	85.15 59	99.16 6	96.96 37	94.11 9	95.59 30	98.64 17	85.07 33	99.91 4	95.61 43	99.10 9	99.00 27

DPE-MVS		95.32 10	95.55 11	94.64 29	98.79 23	84.87 66	97.77 70	96.74 60	86.11 115	96.54 21	98.89 6	88.39 19	99.74 37	97.67 20	99.05 12	99.31 18
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.58 8	95.91 9	94.57 30	99.05 9	85.18 54	99.06 14	96.46 96	88.75 62	96.69 15	98.76 12	87.69 22	99.76 30	97.90 15	98.85 21	98.77 34
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
SF-MVS		94.17 26	94.05 30	94.55 31	97.56 74	85.95 37	97.73 74	96.43 100	84.02 167	95.07 39	98.74 14	82.93 48	99.38 76	95.42 47	98.51 34	98.32 60

PAPR		92.74 49	92.17 63	94.45 32	98.89 20	84.87 66	97.20 111	96.20 122	87.73 86	88.40 128	98.12 41	78.71 84	99.76 30	87.99 134	96.28 97	98.74 35

3Dnovator	82.32 10	89.33 122	87.64 142	94.42 33	93.73 172	85.70 43	97.73 74	96.75 59	86.73 111	76.21 264	95.93 130	62.17 252	99.68 49	81.67 190	97.81 61	97.88 91

DP-MVS Recon		91.72 73	90.85 82	94.34 34	99.50 1	85.00 63	98.51 33	95.96 139	80.57 235	88.08 133	97.63 76	76.84 113	99.89 7	85.67 151	94.88 114	98.13 74

PAPM		92.87 47	92.40 56	94.30 35	92.25 219	87.85 19	96.40 174	96.38 107	91.07 34	88.72 124	96.90 107	82.11 53	97.37 184	90.05 112	97.70 64	97.67 109

SD-MVS		94.84 15	95.02 16	94.29 36	97.87 64	84.61 69	97.76 72	96.19 124	89.59 54	96.66 17	98.17 39	84.33 36	99.60 57	96.09 35	98.50 36	98.66 42
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
test12				94.25 37	98.34 46	85.55 46		96.35 111		92.36 71		80.84 57	99.22 85		98.31 47	97.98 86

test_yl		91.46 79	90.53 89	94.24 38	97.41 80	85.18 54	98.08 50	97.72 12	80.94 226	89.85 106	96.14 126	75.61 135	98.81 117	90.42 107	88.56 178	98.74 35

DCV-MVSNet		91.46 79	90.53 89	94.24 38	97.41 80	85.18 54	98.08 50	97.72 12	80.94 226	89.85 106	96.14 126	75.61 135	98.81 117	90.42 107	88.56 178	98.74 35

jason		92.73 50	92.23 61	94.21 40	90.50 263	87.30 26	98.65 28	95.09 185	90.61 40	92.76 69	97.13 99	75.28 150	97.30 187	93.32 70	96.75 91	98.02 79
jason: jason.
ACMMP_NAP		93.46 36	93.23 42	94.17 41	97.16 88	84.28 74	96.82 147	96.65 72	86.24 113	94.27 50	97.99 50	77.94 94	99.83 16	93.39 67	98.57 33	98.39 57

1314		88.94 129	87.20 155	94.17 41	93.21 186	85.73 42	93.33 280	96.64 75	82.89 196	75.98 267	96.36 122	66.83 226	99.39 75	83.52 178	96.02 104	97.39 130

LFMVS		89.27 124	87.64 142	94.16 43	97.16 88	85.52 47	97.18 113	94.66 209	79.17 268	89.63 112	96.57 120	55.35 307	98.22 142	89.52 119	89.54 167	98.74 35

QAPM		86.88 172	84.51 193	93.98 44	94.04 165	85.89 40	97.19 112	96.05 133	73.62 319	75.12 279	95.62 140	62.02 255	99.74 37	70.88 286	96.06 103	96.30 171

MSLP-MVS++		94.28 23	94.39 24	93.97 45	98.30 49	84.06 77	98.64 29	96.93 40	90.71 38	93.08 65	98.70 15	79.98 68	99.21 86	94.12 60	99.07 11	98.63 44

APDe-MVS		94.56 20	94.75 17	93.96 46	98.84 22	83.40 90	98.04 55	96.41 102	85.79 122	95.00 40	98.28 32	84.32 39	99.18 92	97.35 24	98.77 27	99.28 19
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TSAR-MVS + GP.		94.35 22	94.50 20	93.89 47	97.38 84	83.04 97	98.10 49	95.29 179	91.57 28	93.81 55	97.45 83	86.64 27	99.43 74	96.28 34	94.01 126	99.20 22

CANet_DTU		90.98 91	90.04 101	93.83 48	94.76 141	86.23 34	96.32 179	93.12 294	93.11 16	93.71 56	96.82 113	63.08 248	99.48 71	84.29 161	95.12 113	95.77 180

API-MVS		90.18 107	88.97 119	93.80 49	98.66 28	82.95 98	97.50 92	95.63 158	75.16 308	86.31 148	97.69 68	72.49 185	99.90 5	81.26 192	96.07 102	98.56 47

EPNet		94.06 29	94.15 28	93.76 50	97.27 87	84.35 72	98.29 39	97.64 15	94.57 6	95.36 31	96.88 109	79.96 69	99.12 98	91.30 90	96.11 101	97.82 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
train_agg		94.28 23	94.45 22	93.74 51	98.64 31	83.71 82	97.82 66	96.65 72	84.50 153	95.16 33	98.09 43	84.33 36	99.36 79	95.91 39	98.96 19	98.16 71

CDPH-MVS		93.12 40	92.91 46	93.74 51	98.65 30	83.88 78	97.67 79	96.26 116	83.00 194	93.22 63	98.24 33	81.31 55	99.21 86	89.12 122	98.74 29	98.14 73

MVSFormer		91.36 82	90.57 88	93.73 53	93.00 194	88.08 17	94.80 246	94.48 220	80.74 231	94.90 41	97.13 99	78.84 81	95.10 295	83.77 169	97.46 70	98.02 79

APD-MVS		93.61 34	93.59 35	93.69 54	98.76 24	83.26 93	97.21 109	96.09 129	82.41 208	94.65 46	98.21 34	81.96 54	98.81 117	94.65 54	98.36 45	99.01 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		94.79 17	95.17 15	93.64 55	97.66 69	84.10 76	95.85 205	96.42 101	91.26 31	97.49 10	96.80 114	86.50 28	98.49 129	95.54 45	99.03 13	98.33 59
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CHOSEN 1792x2688		91.07 90	90.21 97	93.64 55	95.18 127	83.53 87	96.26 182	96.13 126	88.92 61	84.90 161	93.10 200	72.86 181	99.62 56	88.86 124	95.67 109	97.79 101

MVS_Test		90.29 106	89.18 116	93.62 57	95.23 124	84.93 64	94.41 251	94.66 209	84.31 158	90.37 104	91.02 230	75.13 152	97.82 156	83.11 182	94.42 121	98.12 75

sss		90.87 95	89.96 104	93.60 58	94.15 159	83.84 81	97.14 120	98.13 7	85.93 120	89.68 110	96.09 128	71.67 194	99.30 81	87.69 137	89.16 170	97.66 110

PVSNet_Blended		93.13 39	92.98 45	93.57 59	97.47 76	83.86 79	99.32 1	96.73 61	91.02 36	89.53 114	96.21 125	76.42 122	99.57 62	94.29 57	95.81 108	97.29 135

xiu_mvs_v1_base_debu		90.54 100	89.54 111	93.55 60	92.31 212	87.58 23	96.99 131	94.87 195	87.23 98	93.27 60	97.56 79	57.43 290	98.32 138	92.72 78	93.46 136	94.74 205

xiu_mvs_v1_base		90.54 100	89.54 111	93.55 60	92.31 212	87.58 23	96.99 131	94.87 195	87.23 98	93.27 60	97.56 79	57.43 290	98.32 138	92.72 78	93.46 136	94.74 205

xiu_mvs_v1_base_debi		90.54 100	89.54 111	93.55 60	92.31 212	87.58 23	96.99 131	94.87 195	87.23 98	93.27 60	97.56 79	57.43 290	98.32 138	92.72 78	93.46 136	94.74 205

OpenMVS	79.58 14	86.09 185	83.62 209	93.50 63	90.95 252	86.71 32	97.44 96	95.83 147	75.35 305	72.64 300	95.72 135	57.42 293	99.64 53	71.41 280	95.85 107	94.13 215

GG-mvs-BLEND				93.49 64	94.94 135	86.26 33	81.62 365	97.00 33		88.32 130	94.30 175	91.23 5	96.21 236	88.49 129	97.43 73	98.00 84

ab-mvs		87.08 168	84.94 188	93.48 65	93.34 185	83.67 84	88.82 326	95.70 154	81.18 223	84.55 167	90.14 247	62.72 249	98.94 111	85.49 153	82.54 230	97.85 95

PHI-MVS		93.59 35	93.63 34	93.48 65	98.05 58	81.76 123	98.64 29	97.13 26	82.60 204	94.09 53	98.49 23	80.35 62	99.85 10	94.74 53	98.62 32	98.83 32

MVS_111021_HR		93.41 37	93.39 40	93.47 67	97.34 85	82.83 99	97.56 86	98.27 6	89.16 59	89.71 109	97.14 98	79.77 70	99.56 64	93.65 65	97.94 58	98.02 79

PAPM_NR		91.46 79	90.82 83	93.37 68	98.50 40	81.81 122	95.03 240	96.13 126	84.65 149	86.10 151	97.65 74	79.24 75	99.75 35	83.20 180	96.88 86	98.56 47

MP-MVS-pluss		92.58 58	92.35 57	93.29 69	97.30 86	82.53 103	96.44 170	96.04 134	84.68 148	89.12 118	98.37 27	77.48 103	99.74 37	93.31 71	98.38 43	97.59 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
IB-MVS	85.34 4	88.67 138	87.14 158	93.26 70	93.12 192	84.32 73	98.76 24	97.27 20	87.19 101	79.36 228	90.45 240	83.92 42	98.53 127	84.41 160	69.79 309	96.93 146
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
gg-mvs-nofinetune		85.48 197	82.90 220	93.24 71	94.51 151	85.82 41	79.22 369	96.97 36	61.19 367	87.33 139	53.01 385	90.58 6	96.07 239	86.07 149	97.23 79	97.81 100

ZNCC-MVS		92.75 48	92.60 53	93.23 72	98.24 51	81.82 121	97.63 80	96.50 92	85.00 141	91.05 93	97.74 67	78.38 87	99.80 25	90.48 102	98.34 46	98.07 77

SteuartSystems-ACMMP		94.13 28	94.44 23	93.20 73	95.41 119	81.35 133	99.02 18	96.59 82	89.50 55	94.18 52	98.36 28	83.68 44	99.45 73	94.77 51	98.45 39	98.81 33
Skip Steuart: Steuart Systems R&D Blog.
casdiffmvs_mvg		91.13 88	90.45 91	93.17 74	92.99 197	83.58 86	97.46 95	94.56 217	87.69 87	87.19 142	94.98 163	74.50 163	97.60 164	91.88 88	92.79 143	98.34 58
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
新几何1				93.12 75	97.44 78	81.60 130		96.71 64	74.54 313	91.22 91	97.57 78	79.13 77	99.51 69	77.40 231	98.46 38	98.26 67

CSCG		92.02 67	91.65 72	93.12 75	98.53 36	80.59 151	97.47 93	97.18 25	77.06 296	84.64 166	97.98 53	83.98 41	99.52 67	90.72 99	97.33 76	99.23 21

Effi-MVS+		90.70 97	89.90 107	93.09 77	93.61 173	83.48 88	95.20 230	92.79 299	83.22 186	91.82 80	95.70 136	71.82 193	97.48 177	91.25 91	93.67 132	98.32 60

test_prior				93.09 77	98.68 26	81.91 116		96.40 104					99.06 102			98.29 64

GST-MVS		92.43 61	92.22 62	93.04 79	98.17 54	81.64 128	97.40 102	96.38 107	84.71 147	90.90 96	97.40 88	77.55 102	99.76 30	89.75 115	97.74 63	97.72 105

thisisatest0515		90.95 93	90.26 95	93.01 80	94.03 167	84.27 75	97.91 61	96.67 69	83.18 187	86.87 145	95.51 144	88.66 16	97.85 155	80.46 197	89.01 172	96.92 148

HFP-MVS		92.89 46	92.86 48	92.98 81	98.71 25	81.12 136	97.58 84	96.70 65	85.20 135	91.75 81	97.97 55	78.47 86	99.71 43	90.95 93	98.41 41	98.12 75

ET-MVSNet_ETH3D		90.01 110	89.03 117	92.95 82	94.38 153	86.77 30	98.14 44	96.31 114	89.30 57	63.33 347	96.72 118	90.09 11	93.63 326	90.70 100	82.29 233	98.46 53

DeepC-MVS	86.58 3	91.53 78	91.06 81	92.94 83	94.52 148	81.89 117	95.95 197	95.98 137	90.76 37	83.76 177	96.76 115	73.24 179	99.71 43	91.67 89	96.96 83	97.22 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline1		88.85 133	87.49 148	92.93 84	95.21 126	86.85 29	95.47 218	94.61 214	87.29 96	83.11 184	94.99 162	80.70 60	96.89 210	82.28 186	73.72 283	95.05 197

test_fmvsmconf_n		93.99 30	94.36 25	92.86 85	92.82 201	81.12 136	99.26 3	96.37 110	93.47 13	95.16 33	98.21 34	79.00 78	99.64 53	98.21 8	96.73 92	97.83 97

MSP-MVS		95.62 7	96.54 1	92.86 85	98.31 48	80.10 167	97.42 100	96.78 49	92.20 22	97.11 12	98.29 31	93.46 1	99.10 99	96.01 36	99.30 5	99.38 14
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
MTAPA		92.45 60	92.31 58	92.86 85	97.90 61	80.85 145	92.88 291	96.33 112	87.92 81	90.20 105	98.18 36	76.71 118	99.76 30	92.57 81	98.09 51	97.96 89

region2R		92.72 52	92.70 50	92.79 88	98.68 26	80.53 156	97.53 88	96.51 90	85.22 133	91.94 79	97.98 53	77.26 105	99.67 51	90.83 97	98.37 44	98.18 69

ACMMPR		92.69 54	92.67 51	92.75 89	98.66 28	80.57 152	97.58 84	96.69 67	85.20 135	91.57 83	97.92 56	77.01 110	99.67 51	90.95 93	98.41 41	98.00 84

baseline		90.76 96	90.10 100	92.74 90	92.90 200	82.56 102	94.60 248	94.56 217	87.69 87	89.06 120	95.67 138	73.76 172	97.51 174	90.43 106	92.23 152	98.16 71

thres200		88.92 130	87.65 141	92.73 91	96.30 96	85.62 45	97.85 64	98.86 1	84.38 157	84.82 162	93.99 184	75.12 153	98.01 147	70.86 287	86.67 191	94.56 210

PVSNet	82.34 9	89.02 127	87.79 139	92.71 92	95.49 117	81.50 131	97.70 76	97.29 19	87.76 85	85.47 155	95.12 157	56.90 296	98.90 113	80.33 198	94.02 125	97.71 107

PVSNet_Blended_VisFu		91.24 85	90.77 84	92.66 93	95.09 129	82.40 107	97.77 70	95.87 146	88.26 74	86.39 147	93.94 185	76.77 116	99.27 82	88.80 126	94.00 127	96.31 170

test_fmvsmconf0.1_n		93.08 42	93.22 43	92.65 94	88.45 294	80.81 146	99.00 19	95.11 184	93.21 15	94.00 54	97.91 58	76.84 113	99.59 58	97.91 14	96.55 95	97.54 117

test2506		90.96 92	90.39 92	92.65 94	93.54 176	82.46 106	96.37 175	97.35 18	86.78 109	87.55 136	95.25 147	77.83 98	97.50 175	84.07 163	94.80 115	97.98 86

XVS		92.69 54	92.71 49	92.63 96	98.52 37	80.29 159	97.37 103	96.44 98	87.04 103	91.38 85	97.83 64	77.24 107	99.59 58	90.46 103	98.07 52	98.02 79

X-MVStestdata		86.26 183	84.14 202	92.63 96	98.52 37	80.29 159	97.37 103	96.44 98	87.04 103	91.38 85	20.73 396	77.24 107	99.59 58	90.46 103	98.07 52	98.02 79

casdiffmvs		90.95 93	90.39 92	92.63 96	92.82 201	82.53 103	96.83 145	94.47 222	87.69 87	88.47 126	95.56 143	74.04 169	97.54 171	90.90 96	92.74 144	97.83 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
cascas		86.50 178	84.48 195	92.55 99	92.64 207	85.95 37	97.04 130	95.07 187	75.32 306	80.50 213	91.02 230	54.33 314	97.98 148	86.79 147	87.62 185	93.71 223

tfpn200view9		88.48 143	87.15 156	92.47 100	96.21 99	85.30 52	97.44 96	98.85 2	83.37 184	83.99 171	93.82 187	75.36 146	97.93 149	69.04 295	86.24 198	94.17 212

test_fmvsm_n_1920		94.81 16	95.60 10	92.45 101	95.29 123	80.96 142	99.29 2	97.21 22	94.50 7	97.29 11	98.44 25	82.15 52	99.78 28	98.56 5	97.68 65	96.61 159

114514_t		88.79 136	87.57 146	92.45 101	98.21 53	81.74 124	96.99 131	95.45 168	75.16 308	82.48 188	95.69 137	68.59 215	98.50 128	80.33 198	95.18 112	97.10 142

diffmvs		91.17 87	90.74 85	92.44 103	93.11 193	82.50 105	96.25 183	93.62 272	87.79 84	90.40 103	95.93 130	73.44 177	97.42 179	93.62 66	92.55 146	97.41 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MP-MVS		92.61 57	92.67 51	92.42 104	98.13 56	79.73 177	97.33 105	96.20 122	85.63 124	90.53 100	97.66 70	78.14 92	99.70 46	92.12 84	98.30 48	97.85 95
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
AdaColmap		88.81 134	87.61 145	92.39 105	99.33 4	79.95 168	96.70 157	95.58 159	77.51 288	83.05 185	96.69 119	61.90 258	99.72 41	84.29 161	93.47 135	97.50 123

fmvsm_s_conf0.5_n		93.69 33	94.13 29	92.34 106	94.56 145	82.01 111	99.07 13	97.13 26	92.09 23	96.25 23	98.53 21	76.47 120	99.80 25	98.39 6	94.71 117	95.22 195

CP-MVS		92.54 59	92.60 53	92.34 106	98.50 40	79.90 170	98.40 36	96.40 104	84.75 144	90.48 102	98.09 43	77.40 104	99.21 86	91.15 92	98.23 50	97.92 90

patch_mono-2		95.14 12	96.08 7	92.33 108	98.44 43	77.84 233	98.43 34	97.21 22	92.58 19	97.68 8	97.65 74	86.88 26	99.83 16	98.25 7	97.60 67	99.33 17

thres100view900		88.30 149	86.95 162	92.33 108	96.10 103	84.90 65	97.14 120	98.85 2	82.69 202	83.41 179	93.66 191	75.43 143	97.93 149	69.04 295	86.24 198	94.17 212

PGM-MVS		91.93 68	91.80 69	92.32 110	98.27 50	79.74 176	95.28 224	97.27 20	83.83 175	90.89 97	97.78 66	76.12 128	99.56 64	88.82 125	97.93 60	97.66 110

test_fmvsmconf0.01_n		91.08 89	90.68 86	92.29 111	82.43 354	80.12 166	97.94 60	93.93 250	92.07 24	91.97 77	97.60 77	67.56 218	99.53 66	97.09 27	95.56 110	97.21 138

ETV-MVS		92.72 52	92.87 47	92.28 112	94.54 147	81.89 117	97.98 57	95.21 182	89.77 53	93.11 64	96.83 111	77.23 109	97.50 175	95.74 41	95.38 111	97.44 126

fmvsm_s_conf0.1_n		92.93 45	93.16 44	92.24 113	90.52 262	81.92 115	98.42 35	96.24 118	91.17 32	96.02 27	98.35 29	75.34 149	99.74 37	97.84 18	94.58 119	95.05 197

thres400		88.42 146	87.15 156	92.23 114	96.21 99	85.30 52	97.44 96	98.85 2	83.37 184	83.99 171	93.82 187	75.36 146	97.93 149	69.04 295	86.24 198	93.45 228

fmvsm_s_conf0.5_n_a		93.34 38	93.71 32	92.22 115	93.38 184	81.71 126	98.86 22	96.98 34	91.64 27	96.85 13	98.55 18	75.58 138	99.77 29	97.88 17	93.68 131	95.18 196

VDDNet		86.44 179	84.51 193	92.22 115	91.56 240	81.83 120	97.10 126	94.64 212	69.50 345	87.84 134	95.19 152	48.01 334	97.92 154	89.82 114	86.92 189	96.89 149

EPMVS		87.47 166	85.90 172	92.18 117	95.41 119	82.26 110	87.00 342	96.28 115	85.88 121	84.23 168	85.57 311	75.07 154	96.26 233	71.14 285	92.50 147	98.03 78

test_fmvsmvis_n_1920		92.12 65	92.10 65	92.17 118	90.87 255	81.04 138	98.34 38	93.90 254	92.71 18	87.24 141	97.90 59	74.83 156	99.72 41	96.96 29	96.20 98	95.76 181

FA-MVS(test-final)		87.71 162	86.23 169	92.17 118	94.19 158	80.55 153	87.16 341	96.07 132	82.12 213	85.98 152	88.35 267	72.04 192	98.49 129	80.26 200	89.87 165	97.48 125

thres600view7		88.06 154	86.70 166	92.15 120	96.10 103	85.17 58	97.14 120	98.85 2	82.70 201	83.41 179	93.66 191	75.43 143	97.82 156	67.13 304	85.88 202	93.45 228

PCF-MVS	84.09 5	86.77 176	85.00 187	92.08 121	92.06 231	83.07 96	92.14 299	94.47 222	79.63 258	76.90 250	94.78 166	71.15 200	99.20 90	72.87 271	91.05 160	93.98 218
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mPP-MVS		91.88 69	91.82 68	92.07 122	98.38 44	78.63 205	97.29 106	96.09 129	85.12 137	88.45 127	97.66 70	75.53 139	99.68 49	89.83 113	98.02 55	97.88 91

fmvsm_s_conf0.1_n_a		92.38 62	92.49 55	92.06 123	88.08 298	81.62 129	97.97 59	96.01 135	90.62 39	96.58 19	98.33 30	74.09 168	99.71 43	97.23 25	93.46 136	94.86 201

VDD-MVS		88.28 150	87.02 161	92.06 123	95.09 129	80.18 165	97.55 87	94.45 224	83.09 190	89.10 119	95.92 132	47.97 335	98.49 129	93.08 76	86.91 190	97.52 122

EI-MVSNet-Vis-set		91.84 70	91.77 70	92.04 125	97.60 71	81.17 135	96.61 159	96.87 43	88.20 75	89.19 117	97.55 82	78.69 85	99.14 95	90.29 109	90.94 161	95.80 179

dcpmvs_2		93.10 41	93.46 39	92.02 126	97.77 65	79.73 177	94.82 244	93.86 257	86.91 105	91.33 88	96.76 115	85.20 32	98.06 146	96.90 30	97.60 67	98.27 66

1112_ss		88.60 141	87.47 150	92.00 127	93.21 186	80.97 141	96.47 167	92.46 302	83.64 181	80.86 210	97.30 92	80.24 65	97.62 163	77.60 226	85.49 206	97.40 129

PatchmatchNet		86.83 174	85.12 185	91.95 128	94.12 162	82.27 109	86.55 346	95.64 157	84.59 151	82.98 186	84.99 323	77.26 105	95.96 248	68.61 298	91.34 159	97.64 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Test_1112_low_res		88.03 155	86.73 164	91.94 129	93.15 189	80.88 144	96.44 170	92.41 304	83.59 183	80.74 212	91.16 228	80.18 66	97.59 165	77.48 229	85.40 207	97.36 131

HPM-MVS		91.62 76	91.53 74	91.89 130	97.88 63	79.22 189	96.99 131	95.73 153	82.07 214	89.50 116	97.19 97	75.59 137	98.93 112	90.91 95	97.94 58	97.54 117
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mvs_anonymous		88.68 137	87.62 144	91.86 131	94.80 140	81.69 127	93.53 276	94.92 192	82.03 215	78.87 232	90.43 241	75.77 133	95.34 281	85.04 156	93.16 140	98.55 49

MAR-MVS		90.63 98	90.22 96	91.86 131	98.47 42	78.20 221	97.18 113	96.61 78	83.87 174	88.18 132	98.18 36	68.71 214	99.75 35	83.66 174	97.15 80	97.63 113
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
Anonymous202405211		84.41 214	81.93 235	91.85 133	96.78 93	78.41 211	97.44 96	91.34 320	70.29 341	84.06 169	94.26 176	41.09 359	98.96 107	79.46 208	82.65 229	98.17 70

SR-MVS		92.16 64	92.27 59	91.83 134	98.37 45	78.41 211	96.67 158	95.76 150	82.19 212	91.97 77	98.07 47	76.44 121	98.64 121	93.71 64	97.27 78	98.45 54

FE-MVS		86.06 186	84.15 201	91.78 135	94.33 155	79.81 171	84.58 357	96.61 78	76.69 298	85.00 159	87.38 280	70.71 206	98.37 137	70.39 290	91.70 157	97.17 140

EI-MVSNet-UG-set		91.35 83	91.22 77	91.73 136	97.39 82	80.68 149	96.47 167	96.83 46	87.92 81	88.30 131	97.36 89	77.84 97	99.13 97	89.43 120	89.45 168	95.37 190

CNLPA		86.96 170	85.37 179	91.72 137	97.59 72	79.34 187	97.21 109	91.05 325	74.22 314	78.90 230	96.75 117	67.21 223	98.95 109	74.68 257	90.77 162	96.88 150

ECVR-MVS		88.35 148	87.25 154	91.65 138	93.54 176	79.40 184	96.56 163	90.78 330	86.78 109	85.57 154	95.25 147	57.25 294	97.56 167	84.73 159	94.80 115	97.98 86

RPMNet		79.85 277	75.92 296	91.64 139	90.16 269	79.75 174	79.02 371	95.44 169	58.43 377	82.27 195	72.55 374	73.03 180	98.41 136	46.10 375	86.25 196	96.75 156

ACMMP		90.39 103	89.97 103	91.64 139	97.58 73	78.21 220	96.78 150	96.72 63	84.73 146	84.72 164	97.23 95	71.22 199	99.63 55	88.37 132	92.41 149	97.08 143
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
HyFIR lowres test		89.36 121	88.60 125	91.63 141	94.91 137	80.76 148	95.60 214	95.53 161	82.56 205	84.03 170	91.24 227	78.03 93	96.81 216	87.07 144	88.41 180	97.32 132

SCA		85.63 193	83.64 208	91.60 142	92.30 215	81.86 119	92.88 291	95.56 160	84.85 142	82.52 187	85.12 321	58.04 283	95.39 278	73.89 265	87.58 187	97.54 117

thisisatest0530		89.65 116	89.02 118	91.53 143	93.46 182	80.78 147	96.52 164	96.67 69	81.69 219	83.79 176	94.90 164	88.85 15	97.68 160	77.80 220	87.49 188	96.14 173

BH-RMVSNet		86.84 173	85.28 180	91.49 144	95.35 121	80.26 162	96.95 138	92.21 306	82.86 198	81.77 203	95.46 145	59.34 273	97.64 162	69.79 293	93.81 130	96.57 161

MVS_111021_LR		91.60 77	91.64 73	91.47 145	95.74 111	78.79 202	96.15 189	96.77 55	88.49 69	88.64 125	97.07 103	72.33 187	99.19 91	93.13 75	96.48 96	96.43 164

test1111		88.11 153	87.04 160	91.35 146	93.15 189	78.79 202	96.57 161	90.78 330	86.88 107	85.04 158	95.20 151	57.23 295	97.39 182	83.88 166	94.59 118	97.87 93

TESTMET0.1,1		89.83 113	89.34 114	91.31 147	92.54 209	80.19 164	97.11 123	96.57 84	86.15 114	86.85 146	91.83 219	79.32 72	96.95 206	81.30 191	92.35 150	96.77 154

tpmrst		88.36 147	87.38 152	91.31 147	94.36 154	79.92 169	87.32 339	95.26 181	85.32 130	88.34 129	86.13 305	80.60 61	96.70 220	83.78 168	85.34 209	97.30 134

CHOSEN 280x420		91.71 74	91.85 67	91.29 149	94.94 135	82.69 100	87.89 335	96.17 125	85.94 119	87.27 140	94.31 174	90.27 9	95.65 267	94.04 61	95.86 106	95.53 186

UGNet		87.73 161	86.55 167	91.27 150	95.16 128	79.11 193	96.35 177	96.23 119	88.14 76	87.83 135	90.48 239	50.65 324	99.09 100	80.13 203	94.03 124	95.60 184
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
SDMVSNet		87.02 169	85.61 174	91.24 151	94.14 160	83.30 92	93.88 268	95.98 137	84.30 160	79.63 225	92.01 211	58.23 281	97.68 160	90.28 111	82.02 234	92.75 231

Vis-MVSNet		88.67 138	87.82 138	91.24 151	92.68 203	78.82 199	96.95 138	93.85 258	87.55 90	87.07 144	95.13 156	63.43 246	97.21 192	77.58 227	96.15 100	97.70 108
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
原ACMM1				91.22 153	97.77 65	78.10 223		96.61 78	81.05 225	91.28 90	97.42 87	77.92 96	98.98 106	79.85 206	98.51 34	96.59 160

iter_conf05		90.14 108	89.79 109	91.17 154	95.85 109	86.93 28	97.68 78	88.67 351	89.93 50	81.73 204	92.80 202	90.37 8	96.03 240	90.44 105	80.65 242	90.56 246

CostFormer		89.08 126	88.39 129	91.15 155	93.13 191	79.15 192	88.61 329	96.11 128	83.14 188	89.58 113	86.93 289	83.83 43	96.87 212	88.22 133	85.92 201	97.42 127

CDS-MVSNet		89.50 119	88.96 120	91.14 156	91.94 236	80.93 143	97.09 127	95.81 148	84.26 163	84.72 164	94.20 179	80.31 63	95.64 268	83.37 179	88.96 173	96.85 151
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DP-MVS		81.47 261	78.28 278	91.04 157	98.14 55	78.48 207	95.09 239	86.97 357	61.14 368	71.12 310	92.78 205	59.59 269	99.38 76	53.11 359	86.61 192	95.27 194

HPM-MVS_fast		90.38 105	90.17 99	91.03 158	97.61 70	77.35 245	97.15 119	95.48 165	79.51 260	88.79 122	96.90 107	71.64 196	98.81 117	87.01 145	97.44 72	96.94 145

GA-MVS		85.79 191	84.04 203	91.02 159	89.47 283	80.27 161	96.90 142	94.84 198	85.57 125	80.88 209	89.08 255	56.56 300	96.47 227	77.72 223	85.35 208	96.34 167

baseline2		90.39 103	90.21 97	90.93 160	90.86 256	80.99 140	95.20 230	97.41 17	86.03 118	80.07 222	94.61 169	90.58 6	97.47 178	87.29 141	89.86 166	94.35 211

Fast-Effi-MVS+		87.93 158	86.94 163	90.92 161	94.04 165	79.16 191	98.26 40	93.72 268	81.29 222	83.94 174	92.90 201	69.83 211	96.68 221	76.70 237	91.74 156	96.93 146

CS-MVS-test		92.98 43	93.67 33	90.90 162	96.52 94	76.87 252	98.68 26	94.73 204	90.36 46	94.84 43	97.89 60	77.94 94	97.15 198	94.28 59	97.80 62	98.70 41

APD-MVS_3200maxsize		91.23 86	91.35 76	90.89 163	97.89 62	76.35 261	96.30 180	95.52 163	79.82 254	91.03 94	97.88 61	74.70 158	98.54 126	92.11 85	96.89 85	97.77 102

nrg030		86.79 175	85.43 177	90.87 164	88.76 288	85.34 49	97.06 129	94.33 231	84.31 158	80.45 215	91.98 214	72.36 186	96.36 230	88.48 130	71.13 296	90.93 243

SR-MVS-dyc-post		91.29 84	91.45 75	90.80 165	97.76 67	76.03 266	96.20 187	95.44 169	80.56 236	90.72 98	97.84 62	75.76 134	98.61 122	91.99 86	96.79 89	97.75 103

Anonymous20240529		83.15 234	80.60 255	90.80 165	95.74 111	78.27 215	96.81 148	94.92 192	60.10 372	81.89 201	92.54 206	45.82 343	98.82 116	79.25 211	78.32 265	95.31 192

EIA-MVS		91.73 71	92.05 66	90.78 167	94.52 148	76.40 260	98.06 53	95.34 177	89.19 58	88.90 121	97.28 94	77.56 101	97.73 159	90.77 98	96.86 88	98.20 68

OMC-MVS		88.80 135	88.16 133	90.72 168	95.30 122	77.92 230	94.81 245	94.51 219	86.80 108	84.97 160	96.85 110	67.53 219	98.60 123	85.08 155	87.62 185	95.63 183

FMVSNet3		84.71 207	82.71 224	90.70 169	94.55 146	87.71 21	95.92 199	94.67 208	81.73 218	75.82 271	88.08 272	66.99 224	94.47 311	71.23 282	75.38 276	89.91 262

tpm2		87.35 167	86.26 168	90.62 170	92.93 199	78.67 204	88.06 334	95.99 136	79.33 263	87.40 137	86.43 300	80.28 64	96.40 228	80.23 201	85.73 205	96.79 152

EC-MVSNet		91.73 71	92.11 64	90.58 171	93.54 176	77.77 236	98.07 52	94.40 227	87.44 92	92.99 67	97.11 101	74.59 162	96.87 212	93.75 63	97.08 81	97.11 141

TAMVS		88.48 143	87.79 139	90.56 172	91.09 250	79.18 190	96.45 169	95.88 144	83.64 181	83.12 183	93.33 195	75.94 131	95.74 263	82.40 185	88.27 181	96.75 156

BH-w/o		88.24 151	87.47 150	90.54 173	95.03 134	78.54 206	97.41 101	93.82 259	84.08 165	78.23 237	94.51 172	69.34 213	97.21 192	80.21 202	94.58 119	95.87 178

CS-MVS		92.73 50	93.48 38	90.48 174	96.27 97	75.93 271	98.55 32	94.93 191	89.32 56	94.54 48	97.67 69	78.91 80	97.02 202	93.80 62	97.32 77	98.49 51

TR-MVS		86.30 182	84.93 189	90.42 175	94.63 143	77.58 240	96.57 161	93.82 259	80.30 244	82.42 190	95.16 154	58.74 277	97.55 169	74.88 255	87.82 184	96.13 174

iter_conf_final		89.51 118	89.21 115	90.39 176	95.60 114	84.44 71	97.22 107	89.09 344	89.11 60	82.07 198	92.80 202	87.03 25	96.03 240	89.10 123	80.89 238	90.70 244

tpm cat1		83.63 226	81.38 243	90.39 176	93.53 181	78.19 222	85.56 353	95.09 185	70.78 339	78.51 234	83.28 336	74.80 157	97.03 201	66.77 305	84.05 214	95.95 175

h-mvs33		89.30 123	88.95 121	90.36 178	95.07 131	76.04 265	96.96 137	97.11 29	90.39 44	92.22 74	95.10 158	74.70 158	98.86 114	93.14 73	65.89 341	96.16 172

PVSNet_BlendedMVS		90.05 109	89.96 104	90.33 179	97.47 76	83.86 79	98.02 56	96.73 61	87.98 79	89.53 114	89.61 252	76.42 122	99.57 62	94.29 57	79.59 249	87.57 317

dp		84.30 216	82.31 229	90.28 180	94.24 157	77.97 226	86.57 345	95.53 161	79.94 253	80.75 211	85.16 319	71.49 198	96.39 229	63.73 321	83.36 219	96.48 163

UA-Net		88.92 130	88.48 128	90.24 181	94.06 164	77.18 249	93.04 288	94.66 209	87.39 94	91.09 92	93.89 186	74.92 155	98.18 145	75.83 247	91.43 158	95.35 191

MVSTER		89.25 125	88.92 122	90.24 181	95.98 106	84.66 68	96.79 149	95.36 174	87.19 101	80.33 217	90.61 238	90.02 12	95.97 245	85.38 154	78.64 258	90.09 258

IS-MVSNet		88.67 138	88.16 133	90.20 183	93.61 173	76.86 253	96.77 152	93.07 295	84.02 167	83.62 178	95.60 141	74.69 161	96.24 235	78.43 219	93.66 133	97.49 124

testdata				90.13 184	95.92 107	74.17 288		96.49 95	73.49 322	94.82 45	97.99 50	78.80 83	97.93 149	83.53 177	97.52 69	98.29 64

CR-MVSNet		83.53 227	81.36 244	90.06 185	90.16 269	79.75 174	79.02 371	91.12 322	84.24 164	82.27 195	80.35 350	75.45 141	93.67 325	63.37 324	86.25 196	96.75 156

VPNet		84.69 208	82.92 219	90.01 186	89.01 287	83.45 89	96.71 155	95.46 167	85.71 123	79.65 224	92.18 210	56.66 299	96.01 244	83.05 183	67.84 329	90.56 246

BH-untuned		86.95 171	85.94 171	89.99 187	94.52 148	77.46 242	96.78 150	93.37 284	81.80 217	76.62 254	93.81 189	66.64 227	97.02 202	76.06 244	93.88 129	95.48 188

test-LLR		88.48 143	87.98 135	89.98 188	92.26 217	77.23 247	97.11 123	95.96 139	83.76 178	86.30 149	91.38 223	72.30 188	96.78 218	80.82 194	91.92 154	95.94 176

test-mter		88.95 128	88.60 125	89.98 188	92.26 217	77.23 247	97.11 123	95.96 139	85.32 130	86.30 149	91.38 223	76.37 124	96.78 218	80.82 194	91.92 154	95.94 176

ADS-MVSNet		81.26 264	78.36 277	89.96 190	93.78 169	79.78 172	79.48 367	93.60 273	73.09 325	80.14 219	79.99 352	62.15 253	95.24 287	59.49 336	83.52 216	94.85 202

PVSNet_0	77.72 15	81.70 258	78.95 275	89.94 191	90.77 259	76.72 256	95.96 196	96.95 38	85.01 140	70.24 317	88.53 265	52.32 318	98.20 143	86.68 148	44.08 382	94.89 200

DeepPCF-MVS	89.82 1	94.61 19	96.17 5	89.91 192	97.09 90	70.21 324	98.99 20	96.69 67	95.57 2	95.08 38	99.23 1	86.40 30	99.87 8	97.84 18	98.66 31	99.65 6

EPP-MVSNet		89.76 114	89.72 110	89.87 193	93.78 169	76.02 268	97.22 107	96.51 90	79.35 262	85.11 157	95.01 161	84.82 34	97.10 200	87.46 140	88.21 182	96.50 162

tpmvs		83.04 237	80.77 250	89.84 194	95.43 118	77.96 227	85.59 352	95.32 178	75.31 307	76.27 262	83.70 333	73.89 170	97.41 180	59.53 335	81.93 236	94.14 214

GeoE		86.36 180	85.20 181	89.83 195	93.17 188	76.13 263	97.53 88	92.11 307	79.58 259	80.99 208	94.01 183	66.60 228	96.17 238	73.48 269	89.30 169	97.20 139

FMVSNet2		82.79 241	80.44 257	89.83 195	92.66 204	85.43 48	95.42 220	94.35 229	79.06 271	74.46 283	87.28 281	56.38 302	94.31 314	69.72 294	74.68 280	89.76 264

PLC	83.97 7	88.00 156	87.38 152	89.83 195	98.02 59	76.46 258	97.16 117	94.43 225	79.26 267	81.98 199	96.28 124	69.36 212	99.27 82	77.71 224	92.25 151	93.77 222
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VPA-MVSNet		85.32 198	83.83 204	89.77 198	90.25 266	82.63 101	96.36 176	97.07 31	83.03 193	81.21 207	89.02 257	61.58 259	96.31 232	85.02 157	70.95 298	90.36 249

tttt0517		88.57 142	88.19 132	89.71 199	93.00 194	75.99 269	95.67 210	96.67 69	80.78 230	81.82 202	94.40 173	88.97 14	97.58 166	76.05 245	86.31 195	95.57 185

test_cas_vis1_n_1920		89.90 112	90.02 102	89.54 200	90.14 271	74.63 283	98.71 25	94.43 225	93.04 17	92.40 70	96.35 123	53.41 317	99.08 101	95.59 44	96.16 99	94.90 199

CLD-MVS		87.97 157	87.48 149	89.44 201	92.16 224	80.54 155	98.14 44	94.92 192	91.41 29	79.43 227	95.40 146	62.34 251	97.27 190	90.60 101	82.90 225	90.50 248
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		83.84 222	82.00 234	89.35 202	87.13 309	81.38 132	95.72 208	94.26 234	80.15 248	75.92 269	90.63 237	61.96 257	96.52 225	78.98 214	73.28 288	90.14 254

CPTT-MVS		89.72 115	89.87 108	89.29 203	98.33 47	73.30 294	97.70 76	95.35 176	75.68 304	87.40 137	97.44 86	70.43 207	98.25 141	89.56 118	96.90 84	96.33 169

sd_testset		84.62 209	83.11 217	89.17 204	94.14 160	77.78 235	91.54 309	94.38 228	84.30 160	79.63 225	92.01 211	52.28 319	96.98 204	77.67 225	82.02 234	92.75 231

MSDG		80.62 273	77.77 283	89.14 205	93.43 183	77.24 246	91.89 302	90.18 334	69.86 344	68.02 324	91.94 217	52.21 320	98.84 115	59.32 338	83.12 220	91.35 238

TAPA-MVS	81.61 12	85.02 203	83.67 206	89.06 206	96.79 92	73.27 297	95.92 199	94.79 202	74.81 311	80.47 214	96.83 111	71.07 201	98.19 144	49.82 368	92.57 145	95.71 182
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LS3D		82.22 251	79.94 266	89.06 206	97.43 79	74.06 290	93.20 286	92.05 308	61.90 362	73.33 293	95.21 150	59.35 272	99.21 86	54.54 355	92.48 148	93.90 220

PatchMatch-RL		85.00 204	83.66 207	89.02 208	95.86 108	74.55 285	92.49 295	93.60 273	79.30 265	79.29 229	91.47 221	58.53 279	98.45 133	70.22 291	92.17 153	94.07 217

HQP-MVS		87.91 159	87.55 147	88.98 209	92.08 228	78.48 207	97.63 80	94.80 200	90.52 41	82.30 191	94.56 170	65.40 234	97.32 185	87.67 138	83.01 222	91.13 239

Vis-MVSNet (Re-imp)		88.88 132	88.87 123	88.91 210	93.89 168	74.43 286	96.93 140	94.19 239	84.39 156	83.22 182	95.67 138	78.24 89	94.70 305	78.88 215	94.40 122	97.61 115

NR-MVSNet		83.35 229	81.52 242	88.84 211	88.76 288	81.31 134	94.45 250	95.16 183	84.65 149	67.81 325	90.82 234	70.36 208	94.87 301	74.75 256	66.89 338	90.33 251

Patchmatch-test		78.25 290	74.72 304	88.83 212	91.20 246	74.10 289	73.91 382	88.70 350	59.89 373	66.82 331	85.12 321	78.38 87	94.54 309	48.84 371	79.58 250	97.86 94

tpm		85.55 195	84.47 196	88.80 213	90.19 268	75.39 276	88.79 327	94.69 205	84.83 143	83.96 173	85.21 317	78.22 90	94.68 306	76.32 243	78.02 267	96.34 167

HQP_MVS		87.50 165	87.09 159	88.74 214	91.86 237	77.96 227	97.18 113	94.69 205	89.89 51	81.33 205	94.15 180	64.77 240	97.30 187	87.08 142	82.82 226	90.96 241

MIMVSNet		79.18 286	75.99 295	88.72 215	87.37 308	80.66 150	79.96 366	91.82 311	77.38 290	74.33 284	81.87 342	41.78 355	90.74 355	66.36 311	83.10 221	94.76 204

FIs		86.73 177	86.10 170	88.61 216	90.05 272	80.21 163	96.14 190	96.95 38	85.56 127	78.37 236	92.30 208	76.73 117	95.28 285	79.51 207	79.27 252	90.35 250

UniMVSNet (Re)		85.31 199	84.23 199	88.55 217	89.75 276	80.55 153	96.72 153	96.89 42	85.42 128	78.40 235	88.93 258	75.38 145	95.52 275	78.58 217	68.02 326	89.57 266

PatchT		79.75 278	76.85 290	88.42 218	89.55 281	75.49 275	77.37 375	94.61 214	63.07 358	82.46 189	73.32 371	75.52 140	93.41 330	51.36 362	84.43 212	96.36 165

WR-MVS		84.32 215	82.96 218	88.41 219	89.38 285	80.32 158	96.59 160	96.25 117	83.97 169	76.63 253	90.36 242	67.53 219	94.86 302	75.82 248	70.09 307	90.06 260

GBi-Net		82.42 247	80.43 258	88.39 220	92.66 204	81.95 112	94.30 257	93.38 281	79.06 271	75.82 271	85.66 307	56.38 302	93.84 321	71.23 282	75.38 276	89.38 269

test1		82.42 247	80.43 258	88.39 220	92.66 204	81.95 112	94.30 257	93.38 281	79.06 271	75.82 271	85.66 307	56.38 302	93.84 321	71.23 282	75.38 276	89.38 269

FMVSNet1		79.50 282	76.54 292	88.39 220	88.47 293	81.95 112	94.30 257	93.38 281	73.14 324	72.04 305	85.66 307	43.86 346	93.84 321	65.48 313	72.53 289	89.38 269

DU-MVS		84.57 211	83.33 214	88.28 223	88.76 288	79.36 185	96.43 172	95.41 173	85.42 128	78.11 238	90.82 234	67.61 216	95.14 292	79.14 212	68.30 323	90.33 251

AUN-MVS		86.25 184	85.57 175	88.26 224	93.57 175	73.38 292	95.45 219	95.88 144	83.94 171	85.47 155	94.21 178	73.70 175	96.67 222	83.54 176	64.41 345	94.73 208

hse-mvs2		88.22 152	88.21 131	88.25 225	93.54 176	73.41 291	95.41 221	95.89 143	90.39 44	92.22 74	94.22 177	74.70 158	96.66 223	93.14 73	64.37 346	94.69 209

v2v482		83.46 228	81.86 236	88.25 225	86.19 319	79.65 179	96.34 178	94.02 248	81.56 220	77.32 244	88.23 269	65.62 231	96.03 240	77.77 221	69.72 311	89.09 280

UniMVSNet_NR-MVSNet		85.49 196	84.59 191	88.21 227	89.44 284	79.36 185	96.71 155	96.41 102	85.22 133	78.11 238	90.98 232	76.97 112	95.14 292	79.14 212	68.30 323	90.12 255

miper_enhance_ethall		85.95 188	85.20 181	88.19 228	94.85 139	79.76 173	96.00 194	94.06 247	82.98 195	77.74 241	88.76 260	79.42 71	95.46 277	80.58 196	72.42 290	89.36 272

OPM-MVS		85.84 189	85.10 186	88.06 229	88.34 295	77.83 234	95.72 208	94.20 238	87.89 83	80.45 215	94.05 182	58.57 278	97.26 191	83.88 166	82.76 228	89.09 280
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PMMVS		89.46 120	89.92 106	88.06 229	94.64 142	69.57 330	96.22 184	94.95 190	87.27 97	91.37 87	96.54 121	65.88 230	97.39 182	88.54 127	93.89 128	97.23 136

test_vis1_n_1920		89.95 111	90.59 87	88.03 231	92.36 211	68.98 333	99.12 9	94.34 230	93.86 11	93.64 58	97.01 105	51.54 321	99.59 58	96.76 32	96.71 93	95.53 186

cl22		85.11 202	84.17 200	87.92 232	95.06 133	78.82 199	95.51 216	94.22 237	79.74 256	76.77 251	87.92 274	75.96 130	95.68 264	79.93 205	72.42 290	89.27 274

TranMVSNet+NR-MVSNet		83.24 233	81.71 238	87.83 233	87.71 303	78.81 201	96.13 192	94.82 199	84.52 152	76.18 265	90.78 236	64.07 243	94.60 307	74.60 260	66.59 340	90.09 258

pmmvs4		82.54 245	80.79 249	87.79 234	86.11 321	80.49 157	93.55 275	93.18 291	77.29 291	73.35 292	89.40 254	65.26 237	95.05 299	75.32 252	73.61 284	87.83 311

v1144		82.90 240	81.27 245	87.78 235	86.29 317	79.07 196	96.14 190	93.93 250	80.05 250	77.38 242	86.80 291	65.50 232	95.93 250	75.21 253	70.13 304	88.33 303

dmvs_re		84.10 218	82.90 220	87.70 236	91.41 245	73.28 295	90.59 316	93.19 289	85.02 139	77.96 240	93.68 190	57.92 288	96.18 237	75.50 250	80.87 239	93.63 224

F-COLMAP		84.50 213	83.44 213	87.67 237	95.22 125	72.22 303	95.95 197	93.78 264	75.74 303	76.30 261	95.18 153	59.50 271	98.45 133	72.67 273	86.59 193	92.35 236

FC-MVSNet-test		85.96 187	85.39 178	87.66 238	89.38 285	78.02 224	95.65 212	96.87 43	85.12 137	77.34 243	91.94 217	76.28 126	94.74 304	77.09 232	78.82 256	90.21 253

tt0805		81.20 266	79.06 274	87.61 239	86.50 313	72.97 300	93.66 271	95.48 165	74.11 315	76.23 263	91.99 213	41.36 358	97.40 181	77.44 230	74.78 279	92.45 234

v1192		82.31 250	80.55 256	87.60 240	85.94 323	78.47 210	95.85 205	93.80 262	79.33 263	76.97 249	86.51 295	63.33 247	95.87 253	73.11 270	70.13 304	88.46 299

EI-MVSNet		85.80 190	85.20 181	87.59 241	91.55 241	77.41 243	95.13 234	95.36 174	80.43 241	80.33 217	94.71 167	73.72 173	95.97 245	76.96 235	78.64 258	89.39 267

XVG-OURS		85.18 200	84.38 197	87.59 241	90.42 265	71.73 314	91.06 313	94.07 246	82.00 216	83.29 181	95.08 159	56.42 301	97.55 169	83.70 173	83.42 218	93.49 227

V42		83.04 237	81.53 241	87.57 243	86.27 318	79.09 195	95.87 203	94.11 244	80.35 243	77.22 246	86.79 292	65.32 236	96.02 243	77.74 222	70.14 303	87.61 316

v144192		82.43 246	80.73 252	87.54 244	85.81 326	78.22 217	95.98 195	93.78 264	79.09 270	77.11 247	86.49 296	64.66 242	95.91 251	74.20 263	69.42 312	88.49 297

miper_ehance_all_eth		84.57 211	83.60 210	87.50 245	92.64 207	78.25 216	95.40 222	93.47 277	79.28 266	76.41 258	87.64 277	76.53 119	95.24 287	78.58 217	72.42 290	89.01 285

XVG-OURS-SEG-HR		85.74 192	85.16 184	87.49 246	90.22 267	71.45 317	91.29 310	94.09 245	81.37 221	83.90 175	95.22 149	60.30 266	97.53 173	85.58 152	84.42 213	93.50 226

v1921920		82.02 254	80.23 260	87.41 247	85.62 328	77.92 230	95.79 207	93.69 269	78.86 274	76.67 252	86.44 298	62.50 250	95.83 255	72.69 272	69.77 310	88.47 298

Anonymous20231211		79.72 279	77.19 287	87.33 248	95.59 115	77.16 250	95.18 233	94.18 240	59.31 375	72.57 301	86.20 304	47.89 337	95.66 265	74.53 261	69.24 315	89.18 276

v8		81.88 256	80.06 264	87.32 249	86.63 312	79.04 197	94.41 251	93.65 271	78.77 275	73.19 295	85.57 311	66.87 225	95.81 256	73.84 267	67.61 331	87.11 325

IterMVS-LS		83.93 220	82.80 223	87.31 250	91.46 244	77.39 244	95.66 211	93.43 279	80.44 239	75.51 275	87.26 283	73.72 173	95.16 291	76.99 233	70.72 300	89.39 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		81.70 258	79.83 268	87.30 251	85.50 329	77.70 239	95.48 217	93.44 278	78.46 279	76.53 255	86.44 298	60.85 263	95.84 254	71.59 279	70.17 302	88.35 302

c3_l		83.80 223	82.65 225	87.25 252	92.10 227	77.74 238	95.25 227	93.04 296	78.58 277	76.01 266	87.21 285	75.25 151	95.11 294	77.54 228	68.89 317	88.91 291

UniMVSNet_ETH3D		80.86 270	78.75 276	87.22 253	86.31 316	72.02 308	91.95 300	93.76 267	73.51 320	75.06 280	90.16 246	43.04 352	95.66 265	76.37 242	78.55 262	93.98 218

v10		81.43 262	79.53 270	87.11 254	86.38 314	78.87 198	94.31 256	93.43 279	77.88 283	73.24 294	85.26 315	65.44 233	95.75 260	72.14 276	67.71 330	86.72 329

ACMH	75.40 17	77.99 292	74.96 300	87.10 255	90.67 260	76.41 259	93.19 287	91.64 315	72.47 331	63.44 346	87.61 278	43.34 349	97.16 195	58.34 340	73.94 282	87.72 312
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mvsmamba		85.17 201	84.54 192	87.05 256	87.94 300	75.11 279	96.22 184	87.79 355	86.91 105	78.55 233	91.77 220	64.93 239	95.91 251	86.94 146	79.80 244	90.12 255

v148		82.41 249	80.89 248	86.99 257	86.18 320	76.81 254	96.27 181	93.82 259	80.49 238	75.28 278	86.11 306	67.32 222	95.75 260	75.48 251	67.03 337	88.42 301

EPNet_dtu		87.65 163	87.89 136	86.93 258	94.57 144	71.37 318	96.72 153	96.50 92	88.56 68	87.12 143	95.02 160	75.91 132	94.01 319	66.62 306	90.00 164	95.42 189
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
cl____		83.27 231	82.12 231	86.74 259	92.20 220	75.95 270	95.11 236	93.27 287	78.44 280	74.82 281	87.02 288	74.19 166	95.19 289	74.67 258	69.32 313	89.09 280

DIV-MVS_self_test		83.27 231	82.12 231	86.74 259	92.19 221	75.92 272	95.11 236	93.26 288	78.44 280	74.81 282	87.08 287	74.19 166	95.19 289	74.66 259	69.30 314	89.11 279

PS-MVSNAJss		84.91 205	84.30 198	86.74 259	85.89 325	74.40 287	94.95 241	94.16 241	83.93 172	76.45 257	90.11 248	71.04 202	95.77 258	83.16 181	79.02 255	90.06 260

pmmvs5		81.34 263	79.54 269	86.73 262	85.02 336	76.91 251	96.22 184	91.65 314	77.65 286	73.55 287	88.61 262	55.70 305	94.43 312	74.12 264	73.35 287	88.86 292

MS-PatchMatch		83.05 236	81.82 237	86.72 263	89.64 279	79.10 194	94.88 243	94.59 216	79.70 257	70.67 313	89.65 251	50.43 326	96.82 215	70.82 289	95.99 105	84.25 353

eth_miper_zixun_eth		83.12 235	82.01 233	86.47 264	91.85 239	74.80 281	94.33 255	93.18 291	79.11 269	75.74 274	87.25 284	72.71 182	95.32 283	76.78 236	67.13 335	89.27 274

LPG-MVS_test		84.20 217	83.49 212	86.33 265	90.88 253	73.06 298	95.28 224	94.13 242	82.20 210	76.31 259	93.20 196	54.83 312	96.95 206	83.72 171	80.83 240	88.98 286

LGP-MVS_train				86.33 265	90.88 253	73.06 298		94.13 242	82.20 210	76.31 259	93.20 196	54.83 312	96.95 206	83.72 171	80.83 240	88.98 286

ACMP	81.66 11	84.00 219	83.22 216	86.33 265	91.53 243	72.95 301	95.91 201	93.79 263	83.70 180	73.79 286	92.22 209	54.31 315	96.89 210	83.98 164	79.74 247	89.16 277
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
tfpnnormal		78.14 291	75.42 298	86.31 268	88.33 296	79.24 188	94.41 251	96.22 120	73.51 320	69.81 319	85.52 313	55.43 306	95.75 260	47.65 373	67.86 328	83.95 356

ACMM	80.70 13	83.72 225	82.85 222	86.31 268	91.19 247	72.12 306	95.88 202	94.29 233	80.44 239	77.02 248	91.96 215	55.24 308	97.14 199	79.30 210	80.38 243	89.67 265
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
bld_raw_dy_0_64		82.13 252	80.76 251	86.24 270	85.78 327	75.03 280	94.40 254	82.62 375	83.12 189	76.46 256	90.96 233	53.83 316	94.55 308	81.04 193	78.60 261	89.14 278

pm-mvs1		80.05 276	78.02 281	86.15 271	85.42 330	75.81 273	95.11 236	92.69 301	77.13 293	70.36 315	87.43 279	58.44 280	95.27 286	71.36 281	64.25 347	87.36 323

ppachtmachnet_test		77.19 301	74.22 309	86.13 272	85.39 331	78.22 217	93.98 264	91.36 319	71.74 335	67.11 328	84.87 324	56.67 298	93.37 331	52.21 360	64.59 344	86.80 328

D2MVS		82.67 243	81.55 240	86.04 273	87.77 302	76.47 257	95.21 229	96.58 83	82.66 203	70.26 316	85.46 314	60.39 265	95.80 257	76.40 241	79.18 253	85.83 343

USDC		78.65 288	76.25 293	85.85 274	87.58 304	74.60 284	89.58 321	90.58 333	84.05 166	63.13 348	88.23 269	40.69 362	96.86 214	66.57 308	75.81 274	86.09 339

KD-MVS_2432*1600		77.63 297	74.92 302	85.77 275	90.86 256	79.44 182	88.08 332	93.92 252	76.26 300	67.05 329	82.78 338	72.15 190	91.92 342	61.53 328	41.62 385	85.94 341

miper_refine_blended		77.63 297	74.92 302	85.77 275	90.86 256	79.44 182	88.08 332	93.92 252	76.26 300	67.05 329	82.78 338	72.15 190	91.92 342	61.53 328	41.62 385	85.94 341

RRT_MVS		83.88 221	83.27 215	85.71 277	87.53 307	72.12 306	95.35 223	94.33 231	83.81 176	75.86 270	91.28 226	60.55 264	95.09 297	83.93 165	76.76 270	89.90 263

ADS-MVSNet2		79.57 281	77.53 284	85.71 277	93.78 169	72.13 305	79.48 367	86.11 363	73.09 325	80.14 219	79.99 352	62.15 253	90.14 360	59.49 336	83.52 216	94.85 202

mvsany_test1		87.58 164	88.22 130	85.67 279	89.78 275	67.18 340	95.25 227	87.93 353	83.96 170	88.79 122	97.06 104	72.52 184	94.53 310	92.21 83	86.45 194	95.30 193

Patchmtry		77.36 300	74.59 305	85.67 279	89.75 276	75.75 274	77.85 374	91.12 322	60.28 370	71.23 308	80.35 350	75.45 141	93.56 327	57.94 341	67.34 334	87.68 314

test_fmvs1		87.79 160	88.52 127	85.62 281	92.98 198	64.31 349	97.88 63	92.42 303	87.95 80	92.24 73	95.82 133	47.94 336	98.44 135	95.31 48	94.09 123	94.09 216

MVP-Stereo		82.65 244	81.67 239	85.59 282	86.10 322	78.29 214	93.33 280	92.82 298	77.75 285	69.17 323	87.98 273	59.28 274	95.76 259	71.77 277	96.88 86	82.73 361
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Fast-Effi-MVS+-dtu		83.33 230	82.60 226	85.50 283	89.55 281	69.38 331	96.09 193	91.38 317	82.30 209	75.96 268	91.41 222	56.71 297	95.58 273	75.13 254	84.90 211	91.54 237

our_test_3		77.90 295	75.37 299	85.48 284	85.39 331	76.74 255	93.63 272	91.67 313	73.39 323	65.72 338	84.65 326	58.20 282	93.13 332	57.82 342	67.87 327	86.57 332

test_vis1_n		85.60 194	85.70 173	85.33 285	84.79 338	64.98 347	96.83 145	91.61 316	87.36 95	91.00 95	94.84 165	36.14 367	97.18 194	95.66 42	93.03 141	93.82 221

v7n		79.32 285	77.34 285	85.28 286	84.05 347	72.89 302	93.38 278	93.87 256	75.02 310	70.68 312	84.37 327	59.58 270	95.62 270	67.60 300	67.50 332	87.32 324

IterMVS		80.67 272	79.16 272	85.20 287	89.79 274	76.08 264	92.97 290	91.86 310	80.28 245	71.20 309	85.14 320	57.93 287	91.34 349	72.52 274	70.74 299	88.18 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_fmvs1_n		86.34 181	86.72 165	85.17 288	87.54 306	63.64 354	96.91 141	92.37 305	87.49 91	91.33 88	95.58 142	40.81 361	98.46 132	95.00 50	93.49 134	93.41 230

ACMH+	76.62 16	77.47 299	74.94 301	85.05 289	91.07 251	71.58 316	93.26 284	90.01 335	71.80 334	64.76 341	88.55 263	41.62 356	96.48 226	62.35 327	71.00 297	87.09 326

jajsoiax		82.12 253	81.15 247	85.03 290	84.19 344	70.70 320	94.22 261	93.95 249	83.07 191	73.48 288	89.75 250	49.66 330	95.37 280	82.24 187	79.76 245	89.02 284

mvs_tets		81.74 257	80.71 253	84.84 291	84.22 343	70.29 323	93.91 267	93.78 264	82.77 200	73.37 291	89.46 253	47.36 340	95.31 284	81.99 188	79.55 251	88.92 290

LTVRE_ROB	73.68 18	77.99 292	75.74 297	84.74 292	90.45 264	72.02 308	86.41 347	91.12 322	72.57 330	66.63 333	87.27 282	54.95 311	96.98 204	56.29 350	75.98 271	85.21 347
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
IterMVS-SCA-FT		80.51 274	79.10 273	84.73 293	89.63 280	74.66 282	92.98 289	91.81 312	80.05 250	71.06 311	85.18 318	58.04 283	91.40 348	72.48 275	70.70 301	88.12 307

Baseline_NR-MVSNet		81.22 265	80.07 263	84.68 294	85.32 334	75.12 278	96.48 166	88.80 347	76.24 302	77.28 245	86.40 301	67.61 216	94.39 313	75.73 249	66.73 339	84.54 350

miper_lstm_enhance		81.66 260	80.66 254	84.67 295	91.19 247	71.97 310	91.94 301	93.19 289	77.86 284	72.27 303	85.26 315	73.46 176	93.42 329	73.71 268	67.05 336	88.61 293

test_djsdf		83.00 239	82.45 228	84.64 296	84.07 346	69.78 327	94.80 246	94.48 220	80.74 231	75.41 277	87.70 276	61.32 262	95.10 295	83.77 169	79.76 245	89.04 283

TransMVSNet (Re)		76.94 303	74.38 307	84.62 297	85.92 324	75.25 277	95.28 224	89.18 343	73.88 318	67.22 326	86.46 297	59.64 268	94.10 317	59.24 339	52.57 371	84.50 351

Patchmatch-RL test		76.65 305	74.01 312	84.55 298	77.37 370	64.23 350	78.49 373	82.84 374	78.48 278	64.63 342	73.40 370	76.05 129	91.70 347	76.99 233	57.84 360	97.72 105

AllTest		75.92 308	73.06 316	84.47 299	92.18 222	67.29 338	91.07 312	84.43 368	67.63 348	63.48 344	90.18 244	38.20 364	97.16 195	57.04 346	73.37 285	88.97 288

TestCases				84.47 299	92.18 222	67.29 338		84.43 368	67.63 348	63.48 344	90.18 244	38.20 364	97.16 195	57.04 346	73.37 285	88.97 288

MVS-HIRNet		71.36 331	67.00 336	84.46 301	90.58 261	69.74 328	79.15 370	87.74 356	46.09 382	61.96 355	50.50 386	45.14 344	95.64 268	53.74 357	88.11 183	88.00 309

JIA-IIPM		79.00 287	77.20 286	84.40 302	89.74 278	64.06 352	75.30 379	95.44 169	62.15 361	81.90 200	59.08 383	78.92 79	95.59 272	66.51 309	85.78 204	93.54 225

LCM-MVSNet-Re		83.75 224	83.54 211	84.39 303	93.54 176	64.14 351	92.51 294	84.03 370	83.90 173	66.14 336	86.59 294	67.36 221	92.68 333	84.89 158	92.87 142	96.35 166

anonymousdsp		80.98 269	79.97 265	84.01 304	81.73 356	70.44 322	92.49 295	93.58 275	77.10 295	72.98 297	86.31 302	57.58 289	94.90 300	79.32 209	78.63 260	86.69 330

COLMAP_ROB	73.24 19	75.74 310	73.00 317	83.94 305	92.38 210	69.08 332	91.85 303	86.93 358	61.48 365	65.32 339	90.27 243	42.27 354	96.93 209	50.91 364	75.63 275	85.80 344
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-ACMP-BASELINE		79.38 284	77.90 282	83.81 306	84.98 337	67.14 344	89.03 325	93.18 291	80.26 247	72.87 298	88.15 271	38.55 363	96.26 233	76.05 245	78.05 266	88.02 308

CP-MVSNet		81.01 268	80.08 262	83.79 307	87.91 301	70.51 321	94.29 260	95.65 156	80.83 228	72.54 302	88.84 259	63.71 244	92.32 337	68.58 299	68.36 322	88.55 294

WR-MVS_H		81.02 267	80.09 261	83.79 307	88.08 298	71.26 319	94.46 249	96.54 87	80.08 249	72.81 299	86.82 290	70.36 208	92.65 334	64.18 318	67.50 332	87.46 322

test0.0.03 1		82.79 241	82.48 227	83.74 309	86.81 311	72.22 303	96.52 164	95.03 188	83.76 178	73.00 296	93.20 196	72.30 188	88.88 362	64.15 319	77.52 268	90.12 255

Effi-MVS+-dtu		84.61 210	84.90 190	83.72 310	91.96 234	63.14 357	94.95 241	93.34 285	85.57 125	79.79 223	87.12 286	61.99 256	95.61 271	83.55 175	85.83 203	92.41 235

EG-PatchMatch MVS		74.92 313	72.02 320	83.62 311	83.76 351	73.28 295	93.62 273	92.04 309	68.57 347	58.88 364	83.80 332	31.87 376	95.57 274	56.97 348	78.67 257	82.00 367

pmmvs6		74.65 315	71.67 321	83.60 312	79.13 364	69.94 325	93.31 283	90.88 329	61.05 369	65.83 337	84.15 330	43.43 348	94.83 303	66.62 306	60.63 356	86.02 340

PS-CasMVS		80.27 275	79.18 271	83.52 313	87.56 305	69.88 326	94.08 263	95.29 179	80.27 246	72.08 304	88.51 266	59.22 275	92.23 339	67.49 301	68.15 325	88.45 300

OpenMVS_ROB	68.52 20	73.02 323	69.57 330	83.37 314	80.54 360	71.82 312	93.60 274	88.22 352	62.37 360	61.98 354	83.15 337	35.31 371	95.47 276	45.08 376	75.88 273	82.82 359

FMVSNet5		76.46 306	74.16 310	83.35 315	90.05 272	76.17 262	89.58 321	89.85 336	71.39 337	65.29 340	80.42 349	50.61 325	87.70 369	61.05 333	69.24 315	86.18 337

PEN-MVS		79.47 283	78.26 279	83.08 316	86.36 315	68.58 334	93.85 269	94.77 203	79.76 255	71.37 306	88.55 263	59.79 267	92.46 335	64.50 317	65.40 342	88.19 305

MDA-MVSNet_test_wron		73.54 319	70.43 327	82.86 317	84.55 339	71.85 311	91.74 305	91.32 321	67.63 348	46.73 378	81.09 347	55.11 309	90.42 358	55.91 352	59.76 357	86.31 335

YYNet1		73.53 320	70.43 327	82.85 318	84.52 341	71.73 314	91.69 306	91.37 318	67.63 348	46.79 377	81.21 346	55.04 310	90.43 357	55.93 351	59.70 358	86.38 334

TinyColmap		72.41 325	68.99 334	82.68 319	88.11 297	69.59 329	88.41 330	85.20 365	65.55 354	57.91 367	84.82 325	30.80 378	95.94 249	51.38 361	68.70 318	82.49 364

CVMVSNet		84.83 206	85.57 175	82.63 320	91.55 241	60.38 365	95.13 234	95.03 188	80.60 234	82.10 197	94.71 167	66.40 229	90.19 359	74.30 262	90.32 163	97.31 133

pmmvs-eth3d		73.59 318	70.66 325	82.38 321	76.40 374	73.38 292	89.39 324	89.43 340	72.69 329	60.34 361	77.79 358	46.43 342	91.26 351	66.42 310	57.06 361	82.51 362

ITE_SJBPF				82.38 321	87.00 310	65.59 346		89.55 338	79.99 252	69.37 321	91.30 225	41.60 357	95.33 282	62.86 326	74.63 281	86.24 336

DTE-MVSNet		78.37 289	77.06 288	82.32 323	85.22 335	67.17 343	93.40 277	93.66 270	78.71 276	70.53 314	88.29 268	59.06 276	92.23 339	61.38 331	63.28 351	87.56 318

test_0402		72.68 324	69.54 331	82.09 324	88.67 291	71.81 313	92.72 293	86.77 360	61.52 364	62.21 353	83.91 331	43.22 350	93.76 324	34.60 383	72.23 293	80.72 371

MDA-MVSNet-bldmvs		71.45 330	67.94 335	81.98 325	85.33 333	68.50 335	92.35 298	88.76 348	70.40 340	42.99 381	81.96 341	46.57 341	91.31 350	48.75 372	54.39 365	86.11 338

UnsupCasMVSNet_eth		73.25 321	70.57 326	81.30 326	77.53 368	66.33 345	87.24 340	93.89 255	80.38 242	57.90 368	81.59 343	42.91 353	90.56 356	65.18 315	48.51 376	87.01 327

SixPastTwentyTwo		76.04 307	74.32 308	81.22 327	84.54 340	61.43 363	91.16 311	89.30 342	77.89 282	64.04 343	86.31 302	48.23 332	94.29 315	63.54 323	63.84 349	87.93 310

myMVS_eth3d		81.93 255	82.18 230	81.18 328	92.13 225	67.18 340	93.97 265	94.23 235	82.43 206	73.39 289	93.57 193	76.98 111	87.86 366	50.53 366	82.34 231	88.51 295

RPSCF		77.73 296	76.63 291	81.06 329	88.66 292	55.76 376	87.77 336	87.88 354	64.82 357	74.14 285	92.79 204	49.22 331	96.81 216	67.47 302	76.88 269	90.62 245

UnsupCasMVSNet_bld		68.60 338	64.50 342	80.92 330	74.63 377	67.80 336	83.97 359	92.94 297	65.12 356	54.63 373	68.23 379	35.97 368	92.17 341	60.13 334	44.83 380	82.78 360

CL-MVSNet_self_test		75.81 309	74.14 311	80.83 331	78.33 366	67.79 337	94.22 261	93.52 276	77.28 292	69.82 318	81.54 344	61.47 261	89.22 361	57.59 344	53.51 367	85.48 345

OurMVSNet-221017-0		77.18 302	76.06 294	80.55 332	83.78 350	60.00 367	90.35 317	91.05 325	77.01 297	66.62 334	87.92 274	47.73 338	94.03 318	71.63 278	68.44 321	87.62 315

Anonymous20231206		75.29 312	73.64 313	80.22 333	80.75 357	63.38 356	93.36 279	90.71 332	73.09 325	67.12 327	83.70 333	50.33 327	90.85 354	53.63 358	70.10 306	86.44 333

lessismore_v0				79.98 334	80.59 359	58.34 370		80.87 377		58.49 365	83.46 335	43.10 351	93.89 320	63.11 325	48.68 375	87.72 312

K. test v3		73.62 317	71.59 322	79.69 335	82.98 352	59.85 368	90.85 315	88.83 346	77.13 293	58.90 363	82.11 340	43.62 347	91.72 346	65.83 312	54.10 366	87.50 321

TDRefinement		69.20 336	65.78 340	79.48 336	66.04 386	62.21 359	88.21 331	86.12 362	62.92 359	61.03 359	85.61 310	33.23 373	94.16 316	55.82 353	53.02 369	82.08 366

testing3		80.74 271	81.17 246	79.44 337	91.15 249	63.48 355	97.16 117	95.76 150	80.83 228	71.36 307	93.15 199	78.22 90	87.30 371	43.19 378	79.67 248	87.55 320

testgi		74.88 314	73.40 314	79.32 338	80.13 361	61.75 360	93.21 285	86.64 361	79.49 261	66.56 335	91.06 229	35.51 370	88.67 363	56.79 349	71.25 295	87.56 318

CMPMVS	54.94 21	75.71 311	74.56 306	79.17 339	79.69 362	55.98 373	89.59 320	93.30 286	60.28 370	53.85 374	89.07 256	47.68 339	96.33 231	76.55 238	81.02 237	85.22 346
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs2		79.59 280	79.90 267	78.67 340	82.86 353	55.82 375	95.20 230	89.55 338	81.09 224	80.12 221	89.80 249	34.31 372	93.51 328	87.82 135	78.36 264	86.69 330

test_vis1_rt		73.96 316	72.40 319	78.64 341	83.91 348	61.16 364	95.63 213	68.18 391	76.32 299	60.09 362	74.77 365	29.01 380	97.54 171	87.74 136	75.94 272	77.22 375

Anonymous20240521		72.06 328	69.91 329	78.50 342	77.11 371	61.67 362	91.62 308	90.97 327	65.52 355	62.37 352	79.05 355	36.32 366	90.96 353	57.75 343	68.52 320	82.87 358

MIMVSNet1		69.44 334	66.65 338	77.84 343	76.48 373	62.84 358	87.42 338	88.97 345	66.96 353	57.75 369	79.72 354	32.77 375	85.83 375	46.32 374	63.42 350	84.85 349

Syy-MVS		77.97 294	78.05 280	77.74 344	92.13 225	56.85 371	93.97 265	94.23 235	82.43 206	73.39 289	93.57 193	57.95 286	87.86 366	32.40 384	82.34 231	88.51 295

new-patchmatchnet		68.85 337	65.93 339	77.61 345	73.57 379	63.94 353	90.11 319	88.73 349	71.62 336	55.08 372	73.60 369	40.84 360	87.22 372	51.35 363	48.49 377	81.67 370

LF4IMVS		72.36 326	70.82 324	76.95 346	79.18 363	56.33 372	86.12 349	86.11 363	69.30 346	63.06 349	86.66 293	33.03 374	92.25 338	65.33 314	68.64 319	82.28 365

EU-MVSNet		76.92 304	76.95 289	76.83 347	84.10 345	54.73 378	91.77 304	92.71 300	72.74 328	69.57 320	88.69 261	58.03 285	87.43 370	64.91 316	70.00 308	88.33 303

PM-MVS		69.32 335	66.93 337	76.49 348	73.60 378	55.84 374	85.91 350	79.32 381	74.72 312	61.09 358	78.18 357	21.76 383	91.10 352	70.86 287	56.90 362	82.51 362

pmmvs3		65.75 341	62.18 344	76.45 349	67.12 385	64.54 348	88.68 328	85.05 366	54.77 381	57.54 370	73.79 368	29.40 379	86.21 374	55.49 354	47.77 378	78.62 373

ambc				76.02 350	68.11 383	51.43 379	64.97 387	89.59 337		60.49 360	74.49 367	17.17 386	92.46 335	61.50 330	52.85 370	84.17 354

test20.03		72.36 326	71.15 323	75.98 351	77.79 367	59.16 369	92.40 297	89.35 341	74.09 316	61.50 356	84.32 328	48.09 333	85.54 376	50.63 365	62.15 354	83.24 357

KD-MVS_self_test		70.97 332	69.31 332	75.95 352	76.24 376	55.39 377	87.45 337	90.94 328	70.20 342	62.96 351	77.48 359	44.01 345	88.09 364	61.25 332	53.26 368	84.37 352

DSMNet-mixed		73.13 322	72.45 318	75.19 353	77.51 369	46.82 383	85.09 355	82.01 376	67.61 352	69.27 322	81.33 345	50.89 323	86.28 373	54.54 355	83.80 215	92.46 233

new_pmnet		66.18 340	63.18 343	75.18 354	76.27 375	61.74 361	83.79 360	84.66 367	56.64 379	51.57 375	71.85 377	31.29 377	87.93 365	49.98 367	62.55 352	75.86 376

mvsany_test3		67.19 339	65.34 341	72.72 355	63.08 387	48.57 381	83.12 362	78.09 382	72.07 332	61.21 357	77.11 361	22.94 382	87.78 368	78.59 216	51.88 372	81.80 368

test_fmvs3		69.56 333	69.19 333	70.67 356	69.01 381	47.05 382	90.87 314	86.81 359	71.31 338	66.79 332	77.15 360	16.40 387	83.17 379	81.84 189	62.51 353	81.79 369

test_f		64.01 342	62.13 345	69.65 357	63.00 388	45.30 388	83.66 361	80.68 378	61.30 366	55.70 371	72.62 373	14.23 389	84.64 377	69.84 292	58.11 359	79.00 372

dmvs_testset		72.00 329	73.36 315	67.91 358	83.83 349	31.90 398	85.30 354	77.12 383	82.80 199	63.05 350	92.46 207	61.54 260	82.55 381	42.22 380	71.89 294	89.29 273

EGC-MVSNET		52.46 351	47.56 354	67.15 359	81.98 355	60.11 366	82.54 364	72.44 387	0.11 399	0.70 400	74.59 366	25.11 381	83.26 378	29.04 386	61.51 355	58.09 384

APD_test1		56.56 346	53.58 350	65.50 360	67.93 384	46.51 385	77.24 377	72.95 386	38.09 384	42.75 382	75.17 364	13.38 390	82.78 380	40.19 381	54.53 364	67.23 381

LCM-MVSNet		52.52 350	48.24 353	65.35 361	47.63 397	41.45 390	72.55 383	83.62 372	31.75 386	37.66 384	57.92 384	9.19 396	76.76 386	49.26 369	44.60 381	77.84 374

PMMVS2		50.90 352	46.31 355	64.67 362	55.53 391	46.67 384	77.30 376	71.02 388	40.89 383	34.16 387	59.32 382	9.83 395	76.14 388	40.09 382	28.63 390	71.21 377

N_pmnet		61.30 343	60.20 346	64.60 363	84.32 342	17.00 404	91.67 307	10.98 402	61.77 363	58.45 366	78.55 356	49.89 329	91.83 345	42.27 379	63.94 348	84.97 348

DeepMVS_CX				64.06 364	78.53 365	43.26 389		68.11 393	69.94 343	38.55 383	76.14 363	18.53 385	79.34 382	43.72 377	41.62 385	69.57 379

test_method		56.77 345	54.53 349	63.49 365	76.49 372	40.70 391	75.68 378	74.24 385	19.47 393	48.73 376	71.89 376	19.31 384	65.80 393	57.46 345	47.51 379	83.97 355

test_vis3_rt		54.10 349	51.04 352	63.27 366	58.16 389	46.08 387	84.17 358	49.32 401	56.48 380	36.56 385	49.48 388	8.03 397	91.91 344	67.29 303	49.87 373	51.82 387

FPMVS		55.09 348	52.93 351	61.57 367	55.98 390	40.51 392	83.11 363	83.41 373	37.61 385	34.95 386	71.95 375	14.40 388	76.95 385	29.81 385	65.16 343	67.25 380

ANet_high		46.22 353	41.28 360	61.04 368	39.91 399	46.25 386	70.59 384	76.18 384	58.87 376	23.09 392	48.00 389	12.58 392	66.54 392	28.65 387	13.62 393	70.35 378

WB-MVS		57.26 344	56.22 347	60.39 369	69.29 380	35.91 396	86.39 348	70.06 389	59.84 374	46.46 379	72.71 372	51.18 322	78.11 383	15.19 393	34.89 388	67.14 382

SSC-MVS		56.01 347	54.96 348	59.17 370	68.42 382	34.13 397	84.98 356	69.23 390	58.08 378	45.36 380	71.67 378	50.30 328	77.46 384	14.28 394	32.33 389	65.91 383

testf1		45.70 354	42.41 356	55.58 371	53.29 394	40.02 393	68.96 385	62.67 395	27.45 388	29.85 388	61.58 380	5.98 398	73.83 390	28.49 388	43.46 383	52.90 385

APD_test2		45.70 354	42.41 356	55.58 371	53.29 394	40.02 393	68.96 385	62.67 395	27.45 388	29.85 388	61.58 380	5.98 398	73.83 390	28.49 388	43.46 383	52.90 385

Gipuma		45.11 356	42.05 358	54.30 373	80.69 358	51.30 380	35.80 391	83.81 371	28.13 387	27.94 391	34.53 391	11.41 394	76.70 387	21.45 390	54.65 363	34.90 391
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	34.80 23	39.19 358	35.53 361	50.18 374	29.72 400	30.30 399	59.60 389	66.20 394	26.06 390	17.91 394	49.53 387	3.12 400	74.09 389	18.19 392	49.40 374	46.14 388
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	35.65 22	33.85 359	29.49 364	46.92 375	41.86 398	36.28 395	50.45 390	56.52 398	18.75 394	18.28 393	37.84 390	2.41 401	58.41 394	18.71 391	20.62 391	46.06 389
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		41.54 357	41.93 359	40.38 376	20.10 401	26.84 400	61.93 388	59.09 397	14.81 395	28.51 390	80.58 348	35.53 369	48.33 397	63.70 322	13.11 394	45.96 390

E-PMN		32.70 360	32.39 362	33.65 377	53.35 393	25.70 401	74.07 381	53.33 399	21.08 391	17.17 395	33.63 393	11.85 393	54.84 395	12.98 395	14.04 392	20.42 392

EMVS		31.70 361	31.45 363	32.48 378	50.72 396	23.95 402	74.78 380	52.30 400	20.36 392	16.08 396	31.48 394	12.80 391	53.60 396	11.39 396	13.10 395	19.88 393

wuyk23d		14.10 363	13.89 366	14.72 379	55.23 392	22.91 403	33.83 392	3.56 403	4.94 396	4.11 397	2.28 399	2.06 402	19.66 398	10.23 397	8.74 396	1.59 396

test123		9.07 365	11.73 368	1.11 380	0.50 403	0.77 405	89.44 323	0.20 405	0.34 398	2.15 399	10.72 398	0.34 403	0.32 399	1.79 399	0.08 398	2.23 394

testmvs		9.92 364	12.94 367	0.84 381	0.65 402	0.29 406	93.78 270	0.39 404	0.42 397	2.85 398	15.84 397	0.17 404	0.30 400	2.18 398	0.21 397	1.91 395

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

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		21.43 362	28.57 365	0.00 382	0.00 404	0.00 407	0.00 393	95.93 142	0.00 400	0.00 401	97.66 70	63.57 245	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		5.92 367	7.89 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	71.04 202	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		8.11 366	10.81 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	97.30 92	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

WAC-MVS						67.18 340								49.00 370

FOURS1					98.51 39	78.01 225	98.13 47	96.21 121	83.04 192	94.39 49

PC_three_1452									91.12 33	98.33 2	98.42 26	92.51 2	99.81 21	98.96 3	99.37 1	99.70 3

test_one_0601					98.91 18	84.56 70		96.70 65	88.06 77	96.57 20	98.77 10	88.04 20

eth-test2					0.00 404

eth-test					0.00 404

ZD-MVS					99.09 8	83.22 94		96.60 81	82.88 197	93.61 59	98.06 48	82.93 48	99.14 95	95.51 46	98.49 37

RE-MVS-def			91.18 80		97.76 67	76.03 266	96.20 187	95.44 169	80.56 236	90.72 98	97.84 62	73.36 178		91.99 86	96.79 89	97.75 103

IU-MVS					99.03 15	85.34 49		96.86 45	92.05 26	98.74 1				98.15 9	98.97 17	99.42 13

test_241102_TWO								96.78 49	88.72 64	97.70 6	98.91 2	87.86 21	99.82 18	98.15 9	99.00 15	99.47 9

test_241102_ONE					99.03 15	85.03 61		96.78 49	88.72 64	97.79 4	98.90 5	88.48 17	99.82 18

9.14			94.26 27		98.10 57		98.14 44	96.52 89	84.74 145	94.83 44	98.80 7	82.80 50	99.37 78	95.95 38	98.42 40

save fliter					98.24 51	83.34 91	98.61 31	96.57 84	91.32 30

test_0728_THIRD									88.38 71	96.69 15	98.76 12	89.64 13	99.76 30	97.47 22	98.84 23	99.38 14

test0726					99.05 9	85.18 54	99.11 12	96.78 49	88.75 62	97.65 9	98.91 2	87.69 22

GSMVS																97.54 117

test_part2					98.90 19	85.14 60				96.07 26

sam_mvs1												77.59 100				97.54 117

sam_mvs												75.35 148

MTGPA								96.33 112

test_post1							85.88 351				30.24 395	73.77 171	95.07 298	73.89 265

test_post											33.80 392	76.17 127	95.97 245

patchmatchnet-post											77.09 362	77.78 99	95.39 278

MTMP							97.53 88	68.16 392

gm-plane-assit					92.27 216	79.64 180			84.47 155		95.15 155		97.93 149	85.81 150

test9_res														96.00 37	99.03 13	98.31 62

TEST9					98.64 31	83.71 82	97.82 66	96.65 72	84.29 162	95.16 33	98.09 43	84.39 35	99.36 79

test_8					98.63 33	83.64 85	97.81 68	96.63 77	84.50 153	95.10 37	98.11 42	84.33 36	99.23 84

agg_prior2														94.30 56	99.00 15	98.57 46

agg_prior					98.59 35	83.13 95		96.56 86		94.19 51			99.16 94

test_prior4						82.34 108	97.75 73

test_prior2							98.37 37		86.08 117	94.57 47	98.02 49	83.14 46		95.05 49	98.79 26

旧先验2							96.97 136		74.06 317	96.10 25			97.76 158	88.38 131

新几何2							96.42 173

旧先验1					97.39 82	79.58 181		96.54 87			98.08 46	84.00 40			97.42 74	97.62 114

无先验							96.87 143	96.78 49	77.39 289				99.52 67	79.95 204		98.43 55

原ACMM2							96.84 144

test222					96.15 101	78.41 211	95.87 203	96.46 96	71.97 333	89.66 111	97.45 83	76.33 125			98.24 49	98.30 63

testdata2													99.48 71	76.45 240

segment_acmp												82.69 51

testdata1							95.57 215		87.44 92

plane_prior7					91.86 237	77.55 241

plane_prior6					91.98 233	77.92 230						64.77 240

plane_prior5								94.69 205					97.30 187	87.08 142	82.82 226	90.96 241

plane_prior4											94.15 180

plane_prior3						77.75 237			90.17 48	81.33 205

plane_prior2							97.18 113		89.89 51

plane_prior1					91.95 235

plane_prior						77.96 227	97.52 91		90.36 46						82.96 224

n2								0.00 406

nn								0.00 406

door-mid								79.75 380

test11								96.50 92

door								80.13 379

HQP5-MVS						78.48 207

HQP-NCC					92.08 228		97.63 80		90.52 41	82.30 191

ACMP_Plane					92.08 228		97.63 80		90.52 41	82.30 191

BP-MVS														87.67 138

HQP4-MVS										82.30 191			97.32 185			91.13 239

HQP3-MVS								94.80 200							83.01 222

HQP2-MVS												65.40 234

NP-MVS					92.04 232	78.22 217					94.56 170

MDTV_nov1_ep13_2view						81.74 124	86.80 343		80.65 233	85.65 153		74.26 165		76.52 239		96.98 144

MDTV_nov1_ep13			83.69 205		94.09 163	81.01 139	86.78 344	96.09 129	83.81 176	84.75 163	84.32 328	74.44 164	96.54 224	63.88 320	85.07 210

ACMMP++_ref															78.45 263

ACMMP++															79.05 254

Test By Simon												71.65 195

High-resolution multi-view benchmark