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.

SED-MVS		95.88 5	96.22 4	94.87 25	99.03 15	85.03 74	99.12 13	96.78 61	88.72 79	97.79 8	98.91 2	88.48 17	99.82 19	98.15 18	98.97 17	99.74 1

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 13				98.54 22	92.06 3	99.84 13	99.11 4	99.37 1	99.74 1

DVP-MVS++		96.05 4	96.41 3	94.96 24	99.05 9	85.34 61	98.13 60	96.77 67	88.38 87	97.70 10	98.77 10	92.06 3	99.84 13	97.47 33	99.37 1	99.70 3

PC_three_1452									91.12 45	98.33 3	98.42 35	92.51 2	99.81 22	98.96 5	99.37 1	99.70 3

DPM-MVS		96.21 2	95.53 13	98.26 1	96.26 106	95.09 1	99.15 9	96.98 42	93.39 19	96.45 31	98.79 8	90.17 9	99.99 1	89.33 154	99.25 6	99.70 3

DeepPCF-MVS	89.82 1	94.61 22	96.17 5	89.91 230	97.09 95	70.21 368	98.99 26	96.69 80	95.57 2	95.08 50	99.23 1	86.40 31	99.87 8	97.84 29	98.66 32	99.65 6

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 28	97.10 33	95.17 4	92.11 97	98.46 31	87.33 25	99.97 2	97.21 38	99.31 4	99.63 7

DeepC-MVS_fast	89.06 2	94.48 27	94.30 34	95.02 22	98.86 21	85.68 51	98.06 66	96.64 89	93.64 17	91.74 104	98.54 22	80.17 81	99.90 5	92.28 105	98.75 29	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
test_241102_TWO								96.78 61	88.72 79	97.70 10	98.91 2	87.86 22	99.82 19	98.15 18	99.00 15	99.47 9

test_0728_SECOND				95.14 20	99.04 14	86.14 39	99.06 20	96.77 67					99.84 13	97.90 26	98.85 21	99.45 10

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 58					99.81 22	98.08 22	98.81 24	99.43 11

No_MVS				97.14 3	99.05 9	92.19 4		96.83 58					99.81 22	98.08 22	98.81 24	99.43 11

IU-MVS					99.03 15	85.34 61		96.86 56	92.05 36	98.74 1				98.15 18	98.97 17	99.42 13

test_0728_THIRD									88.38 87	96.69 24	98.76 12	89.64 12	99.76 36	97.47 33	98.84 23	99.38 14

MSP-MVS		95.62 8	96.54 1	92.86 103	98.31 48	80.10 198	97.42 117	96.78 61	92.20 31	97.11 19	98.29 44	93.46 1	99.10 113	96.01 48	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
sasdasda		92.27 86	91.22 103	95.41 17	95.80 124	88.31 15	97.09 147	94.64 249	88.49 84	92.99 82	97.31 105	72.68 212	98.57 139	93.38 87	88.58 210	99.36 16

canonicalmvs		92.27 86	91.22 103	95.41 17	95.80 124	88.31 15	97.09 147	94.64 249	88.49 84	92.99 82	97.31 105	72.68 212	98.57 139	93.38 87	88.58 210	99.36 16

patch_mono-2		95.14 13	96.08 7	92.33 131	98.44 43	77.84 268	98.43 47	97.21 24	92.58 25	97.68 12	97.65 89	86.88 27	99.83 17	98.25 14	97.60 69	99.33 18

MGCFI-Net		91.95 93	91.03 109	94.72 31	95.68 128	86.38 36	96.93 163	94.48 258	88.25 92	92.78 85	97.24 111	72.34 217	98.46 148	93.13 95	88.43 214	99.32 19

DPE-MVS		95.32 11	95.55 12	94.64 33	98.79 23	84.87 79	97.77 85	96.74 72	86.11 143	96.54 30	98.89 6	88.39 19	99.74 44	97.67 31	99.05 12	99.31 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		94.56 25	94.75 22	93.96 51	98.84 22	83.40 105	98.04 68	96.41 119	85.79 152	95.00 52	98.28 45	84.32 46	99.18 106	97.35 35	98.77 28	99.28 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVS		90.60 130	88.64 157	96.50 5	94.25 181	90.53 8	93.33 320	97.21 24	77.59 325	78.88 271	97.31 105	71.52 229	99.69 56	89.60 149	98.03 56	99.27 22

balanced_conf03		94.60 24	94.30 34	95.48 16	96.45 101	88.82 14	96.33 206	95.58 189	91.12 45	95.84 39	93.87 218	83.47 55	98.37 155	97.26 36	98.81 24	99.24 23

CSCG		92.02 92	91.65 95	93.12 90	98.53 36	80.59 179	97.47 110	97.18 27	77.06 334	84.64 204	97.98 68	83.98 50	99.52 77	90.72 129	97.33 79	99.23 24

TSAR-MVS + GP.		94.35 28	94.50 27	93.89 52	97.38 89	83.04 113	98.10 62	95.29 212	91.57 39	93.81 69	97.45 98	86.64 28	99.43 84	96.28 46	94.01 144	99.20 25

MG-MVS		94.25 31	93.72 42	95.85 12	99.38 3	89.35 11	97.98 70	98.09 9	89.99 63	92.34 92	96.97 125	81.30 70	98.99 119	88.54 161	98.88 20	99.20 25

MM		95.85 6	95.74 10	96.15 8	96.34 103	89.50 9	99.18 7	98.10 8	95.68 1	96.64 27	97.92 71	80.72 72	99.80 26	99.16 2	97.96 58	99.15 27

MVSMamba_PlusPlus		92.37 85	91.55 97	94.83 27	95.37 138	87.69 24	95.60 247	95.42 205	74.65 354	93.95 68	92.81 236	83.11 58	97.70 189	94.49 72	98.53 35	99.11 28

DELS-MVS		94.98 14	94.49 28	96.44 6	96.42 102	90.59 7	99.21 6	97.02 39	94.40 11	91.46 106	97.08 120	83.32 56	99.69 56	92.83 98	98.70 31	99.04 29
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
APD-MVS		93.61 42	93.59 46	93.69 65	98.76 24	83.26 108	97.21 129	96.09 150	82.41 245	94.65 59	98.21 47	81.96 67	98.81 131	94.65 70	98.36 47	99.01 30
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		96.30 1	96.54 1	95.55 15	99.31 5	87.69 24	99.06 20	97.12 31	94.66 7	96.79 23	98.78 9	86.42 30	99.95 3	97.59 32	99.18 7	99.00 31

NCCC		95.63 7	95.94 8	94.69 32	99.21 6	85.15 71	99.16 8	96.96 46	94.11 12	95.59 42	98.64 18	85.07 36	99.91 4	95.61 55	99.10 9	99.00 31

alignmvs		92.97 56	92.26 81	95.12 21	95.54 133	87.77 22	98.67 38	96.38 124	88.04 98	93.01 81	97.45 98	79.20 94	98.60 137	93.25 91	88.76 207	98.99 33

mvsmamba		90.53 134	90.08 132	91.88 156	94.81 159	80.93 169	93.94 305	94.45 263	88.24 93	87.02 175	92.35 243	68.04 250	95.80 293	94.86 66	97.03 91	98.92 34

MVS_0304		95.58 9	95.44 15	96.01 10	97.63 71	89.26 12	99.27 4	96.59 96	94.71 6	97.08 20	97.99 65	78.69 103	99.86 10	99.15 3	97.85 62	98.91 35

CANet		94.89 16	94.64 25	95.63 13	97.55 77	88.12 18	99.06 20	96.39 123	94.07 14	95.34 44	97.80 80	76.83 140	99.87 8	97.08 40	97.64 68	98.89 36

HY-MVS	84.06 6	91.63 103	90.37 124	95.39 19	96.12 111	88.25 17	90.22 361	97.58 15	88.33 90	90.50 123	91.96 254	79.26 92	99.06 116	90.29 140	89.07 202	98.88 37

PHI-MVS		93.59 43	93.63 45	93.48 79	98.05 58	81.76 145	98.64 40	97.13 29	82.60 241	94.09 66	98.49 27	80.35 76	99.85 11	94.74 69	98.62 33	98.83 38

SteuartSystems-ACMMP		94.13 35	94.44 30	93.20 87	95.41 136	81.35 156	99.02 24	96.59 96	89.50 71	94.18 65	98.36 41	83.68 54	99.45 83	94.77 67	98.45 41	98.81 39
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS		95.58 9	95.91 9	94.57 34	99.05 9	85.18 66	99.06 20	96.46 113	88.75 77	96.69 24	98.76 12	87.69 23	99.76 36	97.90 26	98.85 21	98.77 40
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
RRT-MVS		89.67 148	88.67 156	92.67 112	94.44 175	81.08 163	94.34 292	94.45 263	86.05 146	85.79 188	92.39 242	63.39 285	98.16 165	93.22 92	93.95 148	98.76 41

test_yl		91.46 107	90.53 118	94.24 42	97.41 84	85.18 66	98.08 63	97.72 11	80.94 264	89.85 128	96.14 146	75.61 163	98.81 131	90.42 138	88.56 212	98.74 42

DCV-MVSNet		91.46 107	90.53 118	94.24 42	97.41 84	85.18 66	98.08 63	97.72 11	80.94 264	89.85 128	96.14 146	75.61 163	98.81 131	90.42 138	88.56 212	98.74 42

LFMVS		89.27 156	87.64 177	94.16 48	97.16 93	85.52 58	97.18 133	94.66 246	79.17 306	89.63 134	96.57 139	55.35 349	98.22 161	89.52 152	89.54 197	98.74 42

PAPR		92.74 64	92.17 85	94.45 36	98.89 20	84.87 79	97.20 131	96.20 142	87.73 107	88.40 156	98.12 55	78.71 102	99.76 36	87.99 168	96.28 109	98.74 42

WTY-MVS		92.65 75	91.68 94	95.56 14	96.00 114	88.90 13	98.23 54	97.65 13	88.57 82	89.82 130	97.22 113	79.29 91	99.06 116	89.57 150	88.73 208	98.73 46

3Dnovator+	82.88 8	89.63 150	87.85 172	94.99 23	94.49 174	86.76 34	97.84 79	95.74 181	86.10 144	75.47 317	96.02 149	65.00 277	99.51 79	82.91 219	97.07 90	98.72 47

SPE-MVS-test		92.98 55	93.67 44	90.90 198	96.52 100	76.87 291	98.68 37	94.73 239	90.36 60	94.84 55	97.89 75	77.94 115	97.15 232	94.28 76	97.80 64	98.70 48

SD-MVS		94.84 18	95.02 20	94.29 40	97.87 64	84.61 82	97.76 87	96.19 144	89.59 69	96.66 26	98.17 52	84.33 43	99.60 67	96.09 47	98.50 38	98.66 49
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
HPM-MVS++		95.32 11	95.48 14	94.85 26	98.62 34	86.04 40	97.81 82	96.93 49	92.45 26	95.69 40	98.50 26	85.38 34	99.85 11	94.75 68	99.18 7	98.65 50

MSLP-MVS++		94.28 29	94.39 31	93.97 50	98.30 49	84.06 91	98.64 40	96.93 49	90.71 52	93.08 80	98.70 16	79.98 85	99.21 99	94.12 77	99.07 11	98.63 51

lupinMVS		93.87 40	93.58 47	94.75 30	93.00 225	88.08 19	99.15 9	95.50 196	91.03 48	94.90 53	97.66 85	78.84 99	97.56 197	94.64 71	97.46 72	98.62 52

agg_prior2														94.30 73	99.00 15	98.57 53

PAPM_NR		91.46 107	90.82 112	93.37 82	98.50 40	81.81 144	95.03 276	96.13 147	84.65 181	86.10 186	97.65 89	79.24 93	99.75 41	83.20 215	96.88 96	98.56 54

API-MVS		90.18 139	88.97 150	93.80 55	98.66 28	82.95 114	97.50 109	95.63 188	75.16 349	86.31 182	97.69 83	72.49 215	99.90 5	81.26 230	96.07 115	98.56 54

mvs_anonymous		88.68 171	87.62 179	91.86 157	94.80 160	81.69 149	93.53 316	94.92 227	82.03 252	78.87 272	90.43 278	75.77 161	95.34 319	85.04 192	93.16 162	98.55 56

CS-MVS		92.73 65	93.48 51	90.48 211	96.27 105	75.93 312	98.55 43	94.93 226	89.32 72	94.54 61	97.67 84	78.91 98	97.02 236	93.80 80	97.32 80	98.49 57

SMA-MVS		94.70 21	94.68 24	94.76 29	98.02 59	85.94 44	97.47 110	96.77 67	85.32 161	97.92 4	98.70 16	83.09 59	99.84 13	95.79 52	99.08 10	98.49 57
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
ET-MVSNet_ETH3D		90.01 141	89.03 148	92.95 99	94.38 178	86.77 33	98.14 57	96.31 133	89.30 73	63.33 393	96.72 137	90.09 10	93.63 370	90.70 131	82.29 275	98.46 59

SR-MVS		92.16 89	92.27 80	91.83 160	98.37 45	78.41 245	96.67 184	95.76 179	82.19 249	91.97 99	98.07 62	76.44 147	98.64 135	93.71 82	97.27 81	98.45 60

fmvsm_l_conf0.5_n_3		94.61 22	94.92 21	93.68 66	94.52 168	82.80 116	99.33 1	96.37 127	95.08 5	97.59 15	98.48 29	77.40 126	99.79 30	98.28 12	97.21 83	98.44 61

无先验							96.87 167	96.78 61	77.39 327				99.52 77	79.95 241		98.43 62

VNet		92.11 91	91.22 103	94.79 28	96.91 96	86.98 31	97.91 75	97.96 10	86.38 140	93.65 71	95.74 154	70.16 243	98.95 123	93.39 85	88.87 206	98.43 62

ACMMP_NAP		93.46 47	93.23 56	94.17 46	97.16 93	84.28 88	96.82 171	96.65 86	86.24 141	94.27 63	97.99 65	77.94 115	99.83 17	93.39 85	98.57 34	98.39 64

casdiffmvs_mvg		91.13 117	90.45 121	93.17 89	92.99 228	83.58 101	97.46 112	94.56 255	87.69 108	87.19 172	94.98 190	74.50 192	97.60 194	91.88 115	92.79 165	98.34 65
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TSAR-MVS + MP.		94.79 20	95.17 18	93.64 68	97.66 70	84.10 90	95.85 235	96.42 118	91.26 43	97.49 16	96.80 133	86.50 29	98.49 145	95.54 57	99.03 13	98.33 66
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		94.17 32	94.05 39	94.55 35	97.56 76	85.95 42	97.73 89	96.43 117	84.02 201	95.07 51	98.74 14	82.93 60	99.38 86	95.42 59	98.51 36	98.32 67

Effi-MVS+		90.70 128	89.90 139	93.09 92	93.61 201	83.48 103	95.20 264	92.79 346	83.22 224	91.82 102	95.70 156	71.82 225	97.48 207	91.25 119	93.67 154	98.32 67

test9_res														96.00 49	99.03 13	98.31 69

test222					96.15 110	78.41 245	95.87 233	96.46 113	71.97 375	89.66 133	97.45 98	76.33 151			98.24 51	98.30 70

test_prior				93.09 92	98.68 26	81.91 138		96.40 121					99.06 116			98.29 71

testdata				90.13 220	95.92 120	74.17 327		96.49 111	73.49 364	94.82 57	97.99 65	78.80 101	97.93 175	83.53 212	97.52 71	98.29 71

dcpmvs_2		93.10 53	93.46 52	92.02 150	97.77 66	79.73 209	94.82 281	93.86 301	86.91 129	91.33 110	96.76 134	85.20 35	98.06 168	96.90 42	97.60 69	98.27 73

新几何1				93.12 90	97.44 82	81.60 153		96.71 77	74.54 355	91.22 113	97.57 93	79.13 95	99.51 79	77.40 271	98.46 40	98.26 74

reproduce-ours		92.70 70	93.02 59	91.75 162	97.45 80	77.77 272	96.16 216	95.94 166	84.12 197	92.45 87	98.43 33	80.06 83	99.24 95	95.35 60	97.18 84	98.24 75

our_new_method		92.70 70	93.02 59	91.75 162	97.45 80	77.77 272	96.16 216	95.94 166	84.12 197	92.45 87	98.43 33	80.06 83	99.24 95	95.35 60	97.18 84	98.24 75

EIA-MVS		91.73 99	92.05 88	90.78 203	94.52 168	76.40 301	98.06 66	95.34 210	89.19 74	88.90 147	97.28 110	77.56 123	97.73 188	90.77 128	96.86 98	98.20 77

region2R		92.72 67	92.70 67	92.79 107	98.68 26	80.53 185	97.53 105	96.51 106	85.22 164	91.94 101	97.98 68	77.26 128	99.67 60	90.83 127	98.37 46	98.18 78

Anonymous202405211		84.41 257	81.93 278	91.85 159	96.78 98	78.41 245	97.44 113	91.34 368	70.29 383	84.06 209	94.26 206	41.09 405	98.96 121	79.46 245	82.65 271	98.17 79

train_agg		94.28 29	94.45 29	93.74 59	98.64 31	83.71 97	97.82 80	96.65 86	84.50 185	95.16 46	98.09 58	84.33 43	99.36 89	95.91 51	98.96 19	98.16 80

baseline		90.76 127	90.10 131	92.74 109	92.90 231	82.56 120	94.60 285	94.56 255	87.69 108	89.06 145	95.67 158	73.76 201	97.51 204	90.43 137	92.23 176	98.16 80

reproduce_model		92.53 79	92.87 63	91.50 176	97.41 84	77.14 289	96.02 223	95.91 169	83.65 218	92.45 87	98.39 37	79.75 88	99.21 99	95.27 63	96.98 92	98.14 82

CDPH-MVS		93.12 52	92.91 62	93.74 59	98.65 30	83.88 92	97.67 93	96.26 136	83.00 231	93.22 77	98.24 46	81.31 69	99.21 99	89.12 155	98.74 30	98.14 82

DP-MVS Recon		91.72 101	90.85 111	94.34 38	99.50 1	85.00 76	98.51 45	95.96 162	80.57 273	88.08 162	97.63 91	76.84 138	99.89 7	85.67 187	94.88 131	98.13 84

HFP-MVS		92.89 59	92.86 65	92.98 97	98.71 25	81.12 161	97.58 100	96.70 78	85.20 166	91.75 103	97.97 70	78.47 106	99.71 52	90.95 122	98.41 43	98.12 85

MVS_Test		90.29 138	89.18 147	93.62 70	95.23 142	84.93 77	94.41 288	94.66 246	84.31 190	90.37 126	91.02 268	75.13 180	97.82 184	83.11 217	94.42 139	98.12 85

ZNCC-MVS		92.75 63	92.60 70	93.23 86	98.24 51	81.82 143	97.63 94	96.50 108	85.00 172	91.05 115	97.74 82	78.38 107	99.80 26	90.48 133	98.34 48	98.07 87

EPMVS		87.47 204	85.90 212	92.18 141	95.41 136	82.26 129	87.00 390	96.28 134	85.88 151	84.23 206	85.57 354	75.07 182	96.26 271	71.14 326	92.50 169	98.03 88

XVS		92.69 72	92.71 66	92.63 117	98.52 37	80.29 188	97.37 121	96.44 115	87.04 127	91.38 107	97.83 79	77.24 130	99.59 68	90.46 135	98.07 54	98.02 89

X-MVStestdata		86.26 221	84.14 243	92.63 117	98.52 37	80.29 188	97.37 121	96.44 115	87.04 127	91.38 107	20.73 447	77.24 130	99.59 68	90.46 135	98.07 54	98.02 89

MVSFormer		91.36 111	90.57 117	93.73 61	93.00 225	88.08 19	94.80 283	94.48 258	80.74 269	94.90 53	97.13 116	78.84 99	95.10 334	83.77 204	97.46 72	98.02 89

jason		92.73 65	92.23 82	94.21 44	90.50 304	87.30 30	98.65 39	95.09 219	90.61 54	92.76 86	97.13 116	75.28 178	97.30 218	93.32 89	96.75 102	98.02 89
jason: jason.
MVS_111021_HR		93.41 48	93.39 53	93.47 81	97.34 90	82.83 115	97.56 102	98.27 6	89.16 75	89.71 131	97.14 115	79.77 87	99.56 74	93.65 83	97.94 59	98.02 89

GG-mvs-BLEND				93.49 78	94.94 155	86.26 37	81.62 415	97.00 40		88.32 158	94.30 205	91.23 5	96.21 275	88.49 163	97.43 75	98.00 94

ACMMPR		92.69 72	92.67 68	92.75 108	98.66 28	80.57 180	97.58 100	96.69 80	85.20 166	91.57 105	97.92 71	77.01 135	99.67 60	90.95 122	98.41 43	98.00 94

test2506		90.96 123	90.39 122	92.65 114	93.54 204	82.46 124	96.37 202	97.35 19	86.78 134	87.55 166	95.25 170	77.83 119	97.50 205	84.07 199	94.80 132	97.98 96

ECVR-MVS		88.35 183	87.25 190	91.65 167	93.54 204	79.40 216	96.56 189	90.78 378	86.78 134	85.57 190	95.25 170	57.25 336	97.56 197	84.73 195	94.80 132	97.98 96

test12				94.25 41	98.34 46	85.55 57		96.35 129		92.36 91		80.84 71	99.22 98		98.31 49	97.98 96

MTAPA		92.45 81	92.31 79	92.86 103	97.90 61	80.85 172	92.88 332	96.33 130	87.92 101	90.20 127	98.18 49	76.71 143	99.76 36	92.57 102	98.09 53	97.96 99

fmvsm_s_conf0.5_n_8		94.52 26	95.04 19	92.96 98	95.15 148	81.14 160	99.09 17	96.66 85	95.53 3	97.84 7	98.71 15	76.33 151	99.81 22	99.24 1	96.85 99	97.92 100

CP-MVS		92.54 78	92.60 70	92.34 129	98.50 40	79.90 202	98.40 49	96.40 121	84.75 176	90.48 124	98.09 58	77.40 126	99.21 99	91.15 120	98.23 52	97.92 100

mPP-MVS		91.88 97	91.82 91	92.07 146	98.38 44	78.63 239	97.29 126	96.09 150	85.12 168	88.45 155	97.66 85	75.53 167	99.68 58	89.83 144	98.02 57	97.88 102

3Dnovator	82.32 10	89.33 154	87.64 177	94.42 37	93.73 200	85.70 49	97.73 89	96.75 71	86.73 137	76.21 306	95.93 150	62.17 291	99.68 58	81.67 227	97.81 63	97.88 102

SymmetryMVS		92.45 81	92.33 78	92.82 106	95.19 145	82.02 132	97.94 73	97.43 17	92.34 28	92.15 96	96.53 141	77.03 134	98.57 139	91.13 121	91.19 184	97.87 104

test1111		88.11 188	87.04 196	91.35 182	93.15 220	78.79 235	96.57 187	90.78 378	86.88 130	85.04 195	95.20 176	57.23 337	97.39 213	83.88 201	94.59 135	97.87 104

Patchmatch-test		78.25 333	74.72 348	88.83 250	91.20 285	74.10 328	73.91 433	88.70 397	59.89 420	66.82 376	85.12 364	78.38 107	94.54 351	48.84 419	79.58 289	97.86 106

MP-MVS		92.61 76	92.67 68	92.42 127	98.13 56	79.73 209	97.33 124	96.20 142	85.63 154	90.53 122	97.66 85	78.14 113	99.70 55	92.12 108	98.30 50	97.85 107
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ab-mvs		87.08 206	84.94 228	93.48 79	93.34 214	83.67 99	88.82 372	95.70 183	81.18 261	84.55 205	90.14 284	62.72 288	98.94 125	85.49 189	82.54 272	97.85 107

test_fmvsmconf_n		93.99 37	94.36 32	92.86 103	92.82 233	81.12 161	99.26 5	96.37 127	93.47 18	95.16 46	98.21 47	79.00 96	99.64 62	98.21 16	96.73 103	97.83 109

casdiffmvs		90.95 124	90.39 122	92.63 117	92.82 233	82.53 121	96.83 169	94.47 261	87.69 108	88.47 154	95.56 163	74.04 198	97.54 201	90.90 125	92.74 166	97.83 109
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPNet		94.06 36	94.15 37	93.76 57	97.27 92	84.35 85	98.29 52	97.64 14	94.57 8	95.36 43	96.88 128	79.96 86	99.12 112	91.30 118	96.11 114	97.82 111
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		85.48 239	82.90 263	93.24 85	94.51 172	85.82 46	79.22 420	96.97 45	61.19 414	87.33 169	53.01 436	90.58 6	96.07 278	86.07 184	97.23 82	97.81 112

CHOSEN 1792x2688		91.07 120	90.21 128	93.64 68	95.18 146	83.53 102	96.26 210	96.13 147	88.92 76	84.90 198	93.10 234	72.86 210	99.62 66	88.86 157	95.67 124	97.79 113

APD-MVS_3200maxsize		91.23 115	91.35 100	90.89 199	97.89 62	76.35 302	96.30 208	95.52 194	79.82 292	91.03 116	97.88 76	74.70 187	98.54 142	92.11 109	96.89 95	97.77 114

lecture		93.17 50	93.57 48	91.96 152	97.80 65	78.79 235	98.50 46	96.98 42	86.61 138	94.75 58	98.16 53	78.36 109	99.35 91	93.89 79	97.12 88	97.75 115

SR-MVS-dyc-post		91.29 113	91.45 99	90.80 201	97.76 68	76.03 307	96.20 214	95.44 201	80.56 274	90.72 120	97.84 77	75.76 162	98.61 136	91.99 111	96.79 100	97.75 115

RE-MVS-def			91.18 107		97.76 68	76.03 307	96.20 214	95.44 201	80.56 274	90.72 120	97.84 77	73.36 207		91.99 111	96.79 100	97.75 115

GST-MVS		92.43 83	92.22 84	93.04 94	98.17 54	81.64 151	97.40 119	96.38 124	84.71 179	90.90 118	97.40 103	77.55 124	99.76 36	89.75 147	97.74 65	97.72 118

Patchmatch-RL test		76.65 349	74.01 356	84.55 339	77.37 420	64.23 398	78.49 424	82.84 425	78.48 316	64.63 388	73.40 421	76.05 156	91.70 393	76.99 273	57.84 402	97.72 118

PVSNet	82.34 9	89.02 160	87.79 174	92.71 111	95.49 134	81.50 154	97.70 91	97.29 20	87.76 106	85.47 192	95.12 182	56.90 338	98.90 127	80.33 235	94.02 143	97.71 120

BP-MVS1		93.55 46	93.50 50	93.71 63	92.64 241	85.39 60	97.78 84	96.84 57	89.52 70	92.00 98	97.06 122	88.21 20	98.03 170	91.45 117	96.00 119	97.70 121

Vis-MVSNet		88.67 172	87.82 173	91.24 187	92.68 237	78.82 232	96.95 161	93.85 302	87.55 111	87.07 174	95.13 181	63.43 284	97.21 225	77.58 267	96.15 113	97.70 121
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPM		92.87 61	92.40 75	94.30 39	92.25 256	87.85 21	96.40 201	96.38 124	91.07 47	88.72 152	96.90 126	82.11 65	97.37 215	90.05 143	97.70 66	97.67 123

PGM-MVS		91.93 94	91.80 92	92.32 133	98.27 50	79.74 208	95.28 258	97.27 22	83.83 210	90.89 119	97.78 81	76.12 155	99.56 74	88.82 158	97.93 61	97.66 124

sss		90.87 126	89.96 136	93.60 71	94.15 185	83.84 95	97.14 140	98.13 7	85.93 150	89.68 132	96.09 148	71.67 226	99.30 92	87.69 172	89.16 201	97.66 124

PatchmatchNet		86.83 212	85.12 225	91.95 153	94.12 188	82.27 128	86.55 394	95.64 187	84.59 183	82.98 226	84.99 366	77.26 128	95.96 285	68.61 339	91.34 183	97.64 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MAR-MVS		90.63 129	90.22 127	91.86 157	98.47 42	78.20 256	97.18 133	96.61 92	83.87 208	88.18 160	98.18 49	68.71 248	99.75 41	83.66 209	97.15 86	97.63 127
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
旧先验1					97.39 87	79.58 213		96.54 102			98.08 61	84.00 49			97.42 76	97.62 128

Vis-MVSNet (Re-imp)		88.88 166	88.87 155	88.91 248	93.89 195	74.43 325	96.93 163	94.19 283	84.39 188	83.22 222	95.67 158	78.24 110	94.70 347	78.88 253	94.40 140	97.61 129

MP-MVS-pluss		92.58 77	92.35 76	93.29 83	97.30 91	82.53 121	96.44 197	96.04 156	84.68 180	89.12 143	98.37 40	77.48 125	99.74 44	93.31 90	98.38 45	97.59 130
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ETVMVS		90.99 121	90.26 125	93.19 88	95.81 123	85.64 55	96.97 158	97.18 27	85.43 158	88.77 151	94.86 192	82.00 66	96.37 267	82.70 220	88.60 209	97.57 131

test_fmvsmconf0.1_n		93.08 54	93.22 57	92.65 114	88.45 341	80.81 173	99.00 25	95.11 218	93.21 20	94.00 67	97.91 73	76.84 138	99.59 68	97.91 25	96.55 107	97.54 132

GSMVS																97.54 132

sam_mvs1												77.59 122				97.54 132

SCA		85.63 232	83.64 251	91.60 171	92.30 251	81.86 141	92.88 332	95.56 191	84.85 174	82.52 227	85.12 364	58.04 325	95.39 316	73.89 305	87.58 226	97.54 132

HPM-MVS		91.62 104	91.53 98	91.89 155	97.88 63	79.22 222	96.99 153	95.73 182	82.07 251	89.50 138	97.19 114	75.59 165	98.93 126	90.91 124	97.94 59	97.54 132
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
VDD-MVS		88.28 185	87.02 197	92.06 147	95.09 149	80.18 195	97.55 104	94.45 263	83.09 227	89.10 144	95.92 152	47.97 380	98.49 145	93.08 97	86.91 231	97.52 137

AdaColmap		88.81 168	87.61 180	92.39 128	99.33 4	79.95 200	96.70 183	95.58 189	77.51 326	83.05 225	96.69 138	61.90 299	99.72 49	84.29 197	93.47 157	97.50 138

IS-MVSNet		88.67 172	88.16 167	90.20 219	93.61 201	76.86 292	96.77 177	93.07 341	84.02 201	83.62 218	95.60 161	74.69 190	96.24 274	78.43 257	93.66 155	97.49 139

FA-MVS(test-final)		87.71 200	86.23 209	92.17 142	94.19 183	80.55 181	87.16 389	96.07 153	82.12 250	85.98 187	88.35 306	72.04 223	98.49 145	80.26 237	89.87 194	97.48 140

GDP-MVS		92.85 62	92.55 72	93.75 58	92.82 233	85.76 47	97.63 94	95.05 222	88.34 89	93.15 78	97.10 119	86.92 26	98.01 172	87.95 169	94.00 145	97.47 141

MonoMVSNet		85.68 231	84.22 240	90.03 223	88.43 342	77.83 269	92.95 331	91.46 364	87.28 119	78.11 279	85.96 349	66.31 268	94.81 343	90.71 130	76.81 308	97.46 142

ETV-MVS		92.72 67	92.87 63	92.28 135	94.54 167	81.89 139	97.98 70	95.21 216	89.77 67	93.11 79	96.83 130	77.23 132	97.50 205	95.74 53	95.38 128	97.44 143

CostFormer		89.08 159	88.39 162	91.15 190	93.13 222	79.15 225	88.61 375	96.11 149	83.14 226	89.58 135	86.93 330	83.83 53	96.87 248	88.22 167	85.92 242	97.42 144

testing91		91.90 96	91.31 102	93.66 67	95.99 115	85.68 51	97.39 120	96.89 52	86.75 136	88.85 148	95.23 173	83.93 51	97.90 181	88.91 156	87.89 221	97.41 145

diffmvs		91.17 116	90.74 114	92.44 125	93.11 224	82.50 123	96.25 211	93.62 316	87.79 105	90.40 125	95.93 150	73.44 206	97.42 209	93.62 84	92.55 168	97.41 145
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
1112_ss		88.60 175	87.47 186	92.00 151	93.21 217	80.97 167	96.47 194	92.46 349	83.64 219	80.86 249	97.30 108	80.24 79	97.62 193	77.60 266	85.49 247	97.40 147

1314		88.94 163	87.20 191	94.17 46	93.21 217	85.73 48	93.33 320	96.64 89	82.89 233	75.98 309	96.36 142	66.83 263	99.39 85	83.52 213	96.02 118	97.39 148

UBG		92.68 74	92.35 76	93.70 64	95.61 130	85.65 54	97.25 127	97.06 36	87.92 101	89.28 140	95.03 186	86.06 33	98.07 167	92.24 106	90.69 190	97.37 149

Test_1112_low_res		88.03 190	86.73 203	91.94 154	93.15 220	80.88 171	96.44 197	92.41 351	83.59 221	80.74 251	91.16 266	80.18 80	97.59 195	77.48 269	85.40 248	97.36 150

testing11		92.48 80	92.04 89	93.78 56	95.94 118	86.00 41	97.56 102	97.08 34	87.52 112	89.32 139	95.40 167	84.60 39	98.02 171	91.93 114	89.04 203	97.32 151

HyFIR lowres test		89.36 153	88.60 158	91.63 170	94.91 157	80.76 175	95.60 247	95.53 192	82.56 242	84.03 210	91.24 265	78.03 114	96.81 252	87.07 179	88.41 215	97.32 151

CVMVSNet		84.83 249	85.57 215	82.63 363	91.55 279	60.38 414	95.13 270	95.03 223	80.60 272	82.10 237	94.71 196	66.40 267	90.19 405	74.30 302	90.32 191	97.31 153

tpmrst		88.36 182	87.38 188	91.31 183	94.36 179	79.92 201	87.32 387	95.26 214	85.32 161	88.34 157	86.13 347	80.60 75	96.70 256	83.78 203	85.34 250	97.30 154

PVSNet_Blended		93.13 51	92.98 61	93.57 73	97.47 78	83.86 93	99.32 2	96.73 74	91.02 49	89.53 136	96.21 145	76.42 148	99.57 72	94.29 74	95.81 123	97.29 155

PMMVS		89.46 152	89.92 138	88.06 269	94.64 162	69.57 374	96.22 212	94.95 225	87.27 120	91.37 109	96.54 140	65.88 269	97.39 213	88.54 161	93.89 149	97.23 156

fmvsm_l_conf0.5_n		94.89 16	95.24 17	93.86 53	94.42 176	84.61 82	99.13 12	96.15 146	92.06 34	97.92 4	98.52 25	84.52 41	99.74 44	98.76 7	95.67 124	97.22 157

DeepC-MVS	86.58 3	91.53 106	91.06 108	92.94 100	94.52 168	81.89 139	95.95 227	95.98 160	90.76 51	83.76 217	96.76 134	73.24 208	99.71 52	91.67 116	96.96 93	97.22 157
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testing99		91.91 95	91.35 100	93.60 71	95.98 116	85.70 49	97.31 125	96.92 51	86.82 132	88.91 146	95.25 170	84.26 47	97.89 182	88.80 159	87.94 220	97.21 159

test_fmvsmconf0.01_n		91.08 119	90.68 115	92.29 134	82.43 403	80.12 197	97.94 73	93.93 294	92.07 33	91.97 99	97.60 92	67.56 253	99.53 76	97.09 39	95.56 127	97.21 159

GeoE		86.36 218	85.20 221	89.83 233	93.17 219	76.13 304	97.53 105	92.11 354	79.58 297	80.99 247	94.01 214	66.60 265	96.17 277	73.48 309	89.30 199	97.20 161

KinetiMVS		89.13 158	87.95 170	92.65 114	92.16 261	82.39 126	97.04 151	96.05 154	86.59 139	88.08 162	94.85 193	61.54 301	98.38 154	81.28 229	93.99 147	97.19 162

FE-MVS		86.06 224	84.15 242	91.78 161	94.33 180	79.81 203	84.58 407	96.61 92	76.69 339	85.00 196	87.38 321	70.71 239	98.37 155	70.39 331	91.70 181	97.17 163

myMVS_eth3d28		92.72 67	92.23 82	94.21 44	96.16 109	87.46 29	97.37 121	96.99 41	88.13 96	88.18 160	95.47 165	84.12 48	98.04 169	92.46 104	91.17 185	97.14 164

EC-MVSNet		91.73 99	92.11 86	90.58 207	93.54 204	77.77 272	98.07 65	94.40 269	87.44 114	92.99 82	97.11 118	74.59 191	96.87 248	93.75 81	97.08 89	97.11 165

114514_t		88.79 170	87.57 182	92.45 123	98.21 53	81.74 146	96.99 153	95.45 200	75.16 349	82.48 228	95.69 157	68.59 249	98.50 144	80.33 235	95.18 129	97.10 166

fmvsm_l_conf0.5_n_a		94.91 15	95.30 16	93.72 62	94.50 173	84.30 87	99.14 11	96.00 158	91.94 37	97.91 6	98.60 19	84.78 38	99.77 34	98.84 6	96.03 117	97.08 167

ACMMP		90.39 135	89.97 135	91.64 168	97.58 75	78.21 255	96.78 175	96.72 76	84.73 178	84.72 202	97.23 112	71.22 231	99.63 64	88.37 166	92.41 173	97.08 167
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
AstraMVS		88.99 161	88.35 163	90.92 196	90.81 299	78.29 248	96.73 178	94.24 278	89.96 64	86.13 185	95.04 185	62.12 294	97.41 210	92.54 103	87.57 227	97.06 169

MDTV_nov1_ep13_2view						81.74 146	86.80 391		80.65 271	85.65 189		74.26 194		76.52 279		96.98 170

testing222		91.09 118	90.49 120	92.87 102	95.82 122	85.04 73	96.51 192	97.28 21	86.05 146	89.13 142	95.34 169	80.16 82	96.62 260	85.82 185	88.31 216	96.96 171

HPM-MVS_fast		90.38 137	90.17 130	91.03 193	97.61 72	77.35 283	97.15 139	95.48 197	79.51 298	88.79 149	96.90 126	71.64 228	98.81 131	87.01 180	97.44 74	96.94 172

Fast-Effi-MVS+		87.93 194	86.94 199	90.92 196	94.04 192	79.16 224	98.26 53	93.72 312	81.29 260	83.94 214	92.90 235	69.83 244	96.68 257	76.70 277	91.74 180	96.93 173

IB-MVS	85.34 4	88.67 172	87.14 194	93.26 84	93.12 223	84.32 86	98.76 34	97.27 22	87.19 124	79.36 267	90.45 277	83.92 52	98.53 143	84.41 196	69.79 350	96.93 173
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
thisisatest0515		90.95 124	90.26 125	93.01 95	94.03 194	84.27 89	97.91 75	96.67 82	83.18 225	86.87 176	95.51 164	88.66 15	97.85 183	80.46 234	89.01 204	96.92 175

guyue		89.85 144	89.33 146	91.40 181	92.53 245	80.15 196	96.82 171	95.68 184	89.66 68	86.43 180	94.23 207	67.00 259	97.16 228	91.96 113	89.65 196	96.89 176

VDDNet		86.44 217	84.51 232	92.22 138	91.56 278	81.83 142	97.10 146	94.64 249	69.50 388	87.84 164	95.19 177	48.01 379	97.92 180	89.82 145	86.92 230	96.89 176

CNLPA		86.96 208	85.37 219	91.72 166	97.59 74	79.34 219	97.21 129	91.05 373	74.22 356	78.90 270	96.75 136	67.21 258	98.95 123	74.68 297	90.77 188	96.88 178

CDS-MVSNet		89.50 151	88.96 151	91.14 191	91.94 274	80.93 169	97.09 147	95.81 177	84.26 195	84.72 202	94.20 210	80.31 77	95.64 306	83.37 214	88.96 205	96.85 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
fmvsm_s_conf0.5_n_6		94.17 32	94.70 23	92.58 120	93.50 210	81.20 158	99.08 18	96.48 112	92.24 30	98.62 2	98.39 37	78.58 105	99.72 49	98.08 22	97.36 78	96.81 180

PS-MVSNAJ		94.17 32	93.52 49	96.10 9	95.65 129	92.35 2	98.21 55	95.79 178	92.42 27	96.24 33	98.18 49	71.04 234	99.17 107	96.77 43	97.39 77	96.79 181

tpm2		87.35 205	86.26 208	90.62 206	92.93 230	78.67 238	88.06 382	95.99 159	79.33 301	87.40 167	86.43 341	80.28 78	96.40 265	80.23 238	85.73 246	96.79 181

fmvsm_s_conf0.5_n_3		93.95 38	94.53 26	92.20 140	94.41 177	80.04 199	98.90 30	95.96 162	94.53 9	97.63 14	98.58 20	75.95 158	99.79 30	98.25 14	96.60 105	96.77 183

TESTMET0.1,1		89.83 145	89.34 145	91.31 183	92.54 244	80.19 194	97.11 143	96.57 99	86.15 142	86.85 177	91.83 259	79.32 90	96.95 241	81.30 228	92.35 174	96.77 183

xiu_mvs_v2_base		93.92 39	93.26 55	95.91 11	95.07 151	92.02 6	98.19 56	95.68 184	92.06 34	96.01 38	98.14 54	70.83 238	98.96 121	96.74 45	96.57 106	96.76 185

CR-MVSNet		83.53 270	81.36 287	90.06 222	90.16 310	79.75 206	79.02 422	91.12 370	84.24 196	82.27 235	80.35 397	75.45 169	93.67 369	63.37 368	86.25 237	96.75 186

RPMNet		79.85 320	75.92 340	91.64 168	90.16 310	79.75 206	79.02 422	95.44 201	58.43 424	82.27 235	72.55 425	73.03 209	98.41 153	46.10 423	86.25 237	96.75 186

TAMVS		88.48 178	87.79 174	90.56 208	91.09 290	79.18 223	96.45 196	95.88 173	83.64 219	83.12 223	93.33 229	75.94 159	95.74 301	82.40 222	88.27 217	96.75 186

fmvsm_s_conf0.5_n_5		93.57 45	93.75 41	93.01 95	92.87 232	82.73 117	98.93 29	95.90 170	90.96 50	95.61 41	98.39 37	76.57 144	99.63 64	98.32 11	96.24 110	96.68 189

test_fmvsm_n_1920		94.81 19	95.60 11	92.45 123	95.29 141	80.96 168	99.29 3	97.21 24	94.50 10	97.29 18	98.44 32	82.15 64	99.78 32	98.56 8	97.68 67	96.61 190

原ACMM1				91.22 189	97.77 66	78.10 258		96.61 92	81.05 263	91.28 112	97.42 102	77.92 117	98.98 120	79.85 243	98.51 36	96.59 191

BH-RMVSNet		86.84 211	85.28 220	91.49 177	95.35 139	80.26 191	96.95 161	92.21 353	82.86 235	81.77 243	95.46 166	59.34 314	97.64 192	69.79 334	93.81 151	96.57 192

EPP-MVSNet		89.76 146	89.72 141	89.87 231	93.78 197	76.02 309	97.22 128	96.51 106	79.35 300	85.11 194	95.01 188	84.82 37	97.10 234	87.46 175	88.21 218	96.50 193

dp		84.30 259	82.31 272	90.28 216	94.24 182	77.97 261	86.57 393	95.53 192	79.94 291	80.75 250	85.16 362	71.49 230	96.39 266	63.73 365	83.36 261	96.48 194

MVS_111021_LR		91.60 105	91.64 96	91.47 178	95.74 126	78.79 235	96.15 218	96.77 67	88.49 84	88.64 153	97.07 121	72.33 218	99.19 105	93.13 95	96.48 108	96.43 195

PatchT		79.75 321	76.85 333	88.42 257	89.55 325	75.49 316	77.37 426	94.61 252	63.07 404	82.46 229	73.32 422	75.52 168	93.41 374	51.36 410	84.43 254	96.36 196

LCM-MVSNet-Re		83.75 267	83.54 254	84.39 344	93.54 204	64.14 399	92.51 335	84.03 420	83.90 207	66.14 381	86.59 335	67.36 256	92.68 377	84.89 194	92.87 164	96.35 197

GA-MVS		85.79 229	84.04 244	91.02 194	89.47 327	80.27 190	96.90 166	94.84 233	85.57 155	80.88 248	89.08 292	56.56 342	96.47 264	77.72 263	85.35 249	96.34 198

tpm		85.55 236	84.47 235	88.80 251	90.19 309	75.39 317	88.79 373	94.69 242	84.83 175	83.96 213	85.21 360	78.22 111	94.68 349	76.32 283	78.02 305	96.34 198

CPTT-MVS		89.72 147	89.87 140	89.29 241	98.33 47	73.30 333	97.70 91	95.35 209	75.68 345	87.40 167	97.44 101	70.43 240	98.25 160	89.56 151	96.90 94	96.33 200

PVSNet_Blended_VisFu		91.24 114	90.77 113	92.66 113	95.09 149	82.40 125	97.77 85	95.87 175	88.26 91	86.39 181	93.94 216	76.77 141	99.27 93	88.80 159	94.00 145	96.31 201

QAPM		86.88 210	84.51 232	93.98 49	94.04 192	85.89 45	97.19 132	96.05 154	73.62 361	75.12 320	95.62 160	62.02 296	99.74 44	70.88 327	96.06 116	96.30 202

h-mvs33		89.30 155	88.95 152	90.36 214	95.07 151	76.04 306	96.96 160	97.11 32	90.39 58	92.22 94	95.10 183	74.70 187	98.86 128	93.14 93	65.89 383	96.16 203

thisisatest0530		89.65 149	89.02 149	91.53 173	93.46 211	80.78 174	96.52 190	96.67 82	81.69 257	83.79 216	94.90 191	88.85 14	97.68 190	77.80 260	87.49 228	96.14 204

TR-MVS		86.30 220	84.93 229	90.42 212	94.63 163	77.58 278	96.57 187	93.82 303	80.30 282	82.42 230	95.16 179	58.74 318	97.55 199	74.88 295	87.82 222	96.13 205

mamv4		85.50 237	86.76 202	81.72 371	93.23 216	54.93 428	89.95 363	92.94 343	69.96 385	79.00 269	92.20 246	80.69 74	94.22 358	92.06 110	90.77 188	96.01 206

tpm cat1		83.63 269	81.38 286	90.39 213	93.53 209	78.19 257	85.56 401	95.09 219	70.78 381	78.51 274	83.28 381	74.80 186	97.03 235	66.77 347	84.05 256	95.95 207

test-LLR		88.48 178	87.98 169	89.98 226	92.26 254	77.23 285	97.11 143	95.96 162	83.76 213	86.30 183	91.38 262	72.30 219	96.78 254	80.82 231	91.92 178	95.94 208

test-mter		88.95 162	88.60 158	89.98 226	92.26 254	77.23 285	97.11 143	95.96 162	85.32 161	86.30 183	91.38 262	76.37 150	96.78 254	80.82 231	91.92 178	95.94 208

BH-w/o		88.24 186	87.47 186	90.54 210	95.03 154	78.54 240	97.41 118	93.82 303	84.08 199	78.23 278	94.51 202	69.34 246	97.21 225	80.21 239	94.58 136	95.87 210

testing3-2		91.37 110	91.01 110	92.44 125	95.93 119	83.77 96	98.83 33	97.45 16	86.88 130	86.63 178	94.69 198	84.57 40	97.75 187	89.65 148	84.44 253	95.80 211

EI-MVSNet-Vis-set		91.84 98	91.77 93	92.04 149	97.60 73	81.17 159	96.61 185	96.87 54	88.20 94	89.19 141	97.55 97	78.69 103	99.14 109	90.29 140	90.94 187	95.80 211

CANet_DTU		90.98 122	90.04 133	93.83 54	94.76 161	86.23 38	96.32 207	93.12 340	93.11 21	93.71 70	96.82 132	63.08 287	99.48 81	84.29 197	95.12 130	95.77 213

test_fmvsmvis_n_1920		92.12 90	92.10 87	92.17 142	90.87 295	81.04 164	98.34 51	93.90 298	92.71 24	87.24 171	97.90 74	74.83 185	99.72 49	96.96 41	96.20 111	95.76 214

TAPA-MVS	81.61 12	85.02 246	83.67 247	89.06 244	96.79 97	73.27 336	95.92 229	94.79 237	74.81 352	80.47 253	96.83 130	71.07 233	98.19 163	49.82 416	92.57 167	95.71 215
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_s_conf0.5_n_7		92.88 60	93.82 40	90.08 221	92.79 236	76.45 299	98.54 44	96.74 72	92.28 29	95.22 45	98.49 27	74.91 184	98.15 166	98.28 12	97.13 87	95.63 216

OMC-MVS		88.80 169	88.16 167	90.72 204	95.30 140	77.92 265	94.81 282	94.51 257	86.80 133	84.97 197	96.85 129	67.53 254	98.60 137	85.08 191	87.62 224	95.63 216

UGNet		87.73 198	86.55 206	91.27 186	95.16 147	79.11 226	96.35 204	96.23 139	88.14 95	87.83 165	90.48 276	50.65 368	99.09 114	80.13 240	94.03 142	95.60 218
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
UWE-MVS		88.56 177	88.91 154	87.50 285	94.17 184	72.19 345	95.82 237	97.05 37	84.96 173	84.78 200	93.51 228	81.33 68	94.75 345	79.43 246	89.17 200	95.57 219

tttt0517		88.57 176	88.19 166	89.71 237	93.00 225	75.99 310	95.67 242	96.67 82	80.78 268	81.82 241	94.40 203	88.97 13	97.58 196	76.05 285	86.31 236	95.57 219

test_vis1_n_1920		89.95 142	90.59 116	88.03 271	92.36 247	68.98 377	99.12 13	94.34 272	93.86 15	93.64 72	97.01 124	51.54 363	99.59 68	96.76 44	96.71 104	95.53 221

CHOSEN 280x420		91.71 102	91.85 90	91.29 185	94.94 155	82.69 118	87.89 383	96.17 145	85.94 149	87.27 170	94.31 204	90.27 8	95.65 305	94.04 78	95.86 121	95.53 221

BH-untuned		86.95 209	85.94 211	89.99 225	94.52 168	77.46 280	96.78 175	93.37 329	81.80 254	76.62 296	93.81 222	66.64 264	97.02 236	76.06 284	93.88 150	95.48 223

EPNet_dtu		87.65 201	87.89 171	86.93 298	94.57 164	71.37 360	96.72 179	96.50 108	88.56 83	87.12 173	95.02 187	75.91 160	94.01 362	66.62 349	90.00 193	95.42 224
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EI-MVSNet-UG-set		91.35 112	91.22 103	91.73 164	97.39 87	80.68 176	96.47 194	96.83 58	87.92 101	88.30 159	97.36 104	77.84 118	99.13 111	89.43 153	89.45 198	95.37 225

UA-Net		88.92 164	88.48 161	90.24 217	94.06 191	77.18 287	93.04 328	94.66 246	87.39 116	91.09 114	93.89 217	74.92 183	98.18 164	75.83 287	91.43 182	95.35 226

Anonymous20240529		83.15 277	80.60 297	90.80 201	95.74 126	78.27 250	96.81 173	94.92 227	60.10 419	81.89 240	92.54 240	45.82 389	98.82 130	79.25 249	78.32 303	95.31 227

mvsany_test1		87.58 202	88.22 164	85.67 319	89.78 316	67.18 384	95.25 261	87.93 399	83.96 204	88.79 149	97.06 122	72.52 214	94.53 352	92.21 107	86.45 235	95.30 228

DP-MVS		81.47 303	78.28 321	91.04 192	98.14 55	78.48 241	95.09 275	86.97 403	61.14 415	71.12 354	92.78 239	59.59 310	99.38 86	53.11 407	86.61 233	95.27 229

fmvsm_s_conf0.5_n		93.69 41	94.13 38	92.34 129	94.56 165	82.01 133	99.07 19	97.13 29	92.09 32	96.25 32	98.53 24	76.47 146	99.80 26	98.39 10	94.71 134	95.22 230

fmvsm_s_conf0.5_n_4		93.59 43	94.32 33	91.41 180	93.89 195	79.24 220	98.89 31	96.53 104	92.82 23	97.37 17	98.47 30	77.21 133	99.78 32	98.11 21	95.59 126	95.21 231

fmvsm_s_conf0.5_n_a		93.34 49	93.71 43	92.22 138	93.38 213	81.71 148	98.86 32	96.98 42	91.64 38	96.85 22	98.55 21	75.58 166	99.77 34	97.88 28	93.68 153	95.18 232

Elysia		85.62 233	83.66 248	91.51 174	88.76 332	82.21 130	95.15 268	94.70 240	76.96 336	84.13 207	92.20 246	50.81 366	97.26 222	77.81 258	92.42 171	95.06 233

StellarMVS		85.62 233	83.66 248	91.51 174	88.76 332	82.21 130	95.15 268	94.70 240	76.96 336	84.13 207	92.20 246	50.81 366	97.26 222	77.81 258	92.42 171	95.06 233

fmvsm_s_conf0.1_n		92.93 58	93.16 58	92.24 136	90.52 303	81.92 137	98.42 48	96.24 138	91.17 44	96.02 37	98.35 42	75.34 177	99.74 44	97.84 29	94.58 136	95.05 235

baseline1		88.85 167	87.49 184	92.93 101	95.21 144	86.85 32	95.47 252	94.61 252	87.29 118	83.11 224	94.99 189	80.70 73	96.89 245	82.28 223	73.72 321	95.05 235

test_cas_vis1_n_1920		89.90 143	90.02 134	89.54 238	90.14 312	74.63 322	98.71 36	94.43 266	93.04 22	92.40 90	96.35 143	53.41 359	99.08 115	95.59 56	96.16 112	94.90 237

PVSNet_0	77.72 15	81.70 300	78.95 318	89.94 229	90.77 300	76.72 295	95.96 226	96.95 47	85.01 171	70.24 361	88.53 302	52.32 360	98.20 162	86.68 183	44.08 432	94.89 238

fmvsm_s_conf0.1_n_a		92.38 84	92.49 73	92.06 147	88.08 346	81.62 152	97.97 72	96.01 157	90.62 53	96.58 28	98.33 43	74.09 197	99.71 52	97.23 37	93.46 158	94.86 239

ADS-MVSNet2		79.57 324	77.53 327	85.71 318	93.78 197	72.13 346	79.48 418	86.11 410	73.09 367	80.14 258	79.99 400	62.15 292	90.14 406	59.49 382	83.52 258	94.85 240

ADS-MVSNet		81.26 306	78.36 320	89.96 228	93.78 197	79.78 204	79.48 418	93.60 317	73.09 367	80.14 258	79.99 400	62.15 292	95.24 325	59.49 382	83.52 258	94.85 240

MIMVSNet		79.18 329	75.99 339	88.72 253	87.37 354	80.66 177	79.96 416	91.82 358	77.38 328	74.33 326	81.87 388	41.78 401	90.74 401	66.36 354	83.10 263	94.76 242

fmvsm_s_conf0.5_n_2		92.97 56	93.38 54	91.73 164	94.10 189	80.64 178	98.96 27	95.89 171	94.09 13	97.05 21	98.40 36	68.92 247	99.80 26	98.53 9	94.50 138	94.74 243

xiu_mvs_v1_base_debu		90.54 131	89.54 142	93.55 74	92.31 248	87.58 26	96.99 153	94.87 230	87.23 121	93.27 74	97.56 94	57.43 332	98.32 157	92.72 99	93.46 158	94.74 243

xiu_mvs_v1_base		90.54 131	89.54 142	93.55 74	92.31 248	87.58 26	96.99 153	94.87 230	87.23 121	93.27 74	97.56 94	57.43 332	98.32 157	92.72 99	93.46 158	94.74 243

xiu_mvs_v1_base_debi		90.54 131	89.54 142	93.55 74	92.31 248	87.58 26	96.99 153	94.87 230	87.23 121	93.27 74	97.56 94	57.43 332	98.32 157	92.72 99	93.46 158	94.74 243

AUN-MVS		86.25 222	85.57 215	88.26 264	93.57 203	73.38 331	95.45 253	95.88 173	83.94 205	85.47 192	94.21 209	73.70 204	96.67 258	83.54 211	64.41 387	94.73 247

hse-mvs2		88.22 187	88.21 165	88.25 265	93.54 204	73.41 330	95.41 255	95.89 171	90.39 58	92.22 94	94.22 208	74.70 187	96.66 259	93.14 93	64.37 388	94.69 248

thres200		88.92 164	87.65 176	92.73 110	96.30 104	85.62 56	97.85 78	98.86 1	84.38 189	84.82 199	93.99 215	75.12 181	98.01 172	70.86 328	86.67 232	94.56 249

fmvsm_s_conf0.1_n_2		92.26 88	92.48 74	91.60 171	92.29 252	80.55 181	98.73 35	94.33 274	93.80 16	96.18 34	98.11 56	66.93 261	99.75 41	98.19 17	93.74 152	94.50 250

baseline2		90.39 135	90.21 128	90.93 195	90.86 296	80.99 166	95.20 264	97.41 18	86.03 148	80.07 261	94.61 199	90.58 6	97.47 208	87.29 176	89.86 195	94.35 251

LuminaMVS		88.02 191	86.89 200	91.43 179	88.65 339	83.16 110	94.84 280	94.41 268	83.67 217	86.56 179	91.95 256	62.04 295	96.88 247	89.78 146	90.06 192	94.24 252

thres100view900		88.30 184	86.95 198	92.33 131	96.10 112	84.90 78	97.14 140	98.85 2	82.69 239	83.41 219	93.66 224	75.43 171	97.93 175	69.04 336	86.24 239	94.17 253

tfpn200view9		88.48 178	87.15 192	92.47 122	96.21 107	85.30 64	97.44 113	98.85 2	83.37 222	83.99 211	93.82 220	75.36 174	97.93 175	69.04 336	86.24 239	94.17 253

tpmvs		83.04 280	80.77 293	89.84 232	95.43 135	77.96 262	85.59 400	95.32 211	75.31 348	76.27 304	83.70 377	73.89 199	97.41 210	59.53 381	81.93 278	94.14 255

OpenMVS	79.58 14	86.09 223	83.62 252	93.50 77	90.95 292	86.71 35	97.44 113	95.83 176	75.35 346	72.64 343	95.72 155	57.42 335	99.64 62	71.41 321	95.85 122	94.13 256

test_fmvs1		87.79 197	88.52 160	85.62 321	92.98 229	64.31 397	97.88 77	92.42 350	87.95 100	92.24 93	95.82 153	47.94 381	98.44 152	95.31 62	94.09 141	94.09 257

PatchMatch-RL		85.00 247	83.66 248	89.02 246	95.86 121	74.55 324	92.49 336	93.60 317	79.30 303	79.29 268	91.47 260	58.53 320	98.45 150	70.22 332	92.17 177	94.07 258

UniMVSNet_ETH3D		80.86 313	78.75 319	87.22 294	86.31 363	72.02 348	91.95 342	93.76 311	73.51 362	75.06 322	90.16 283	43.04 398	95.66 303	76.37 282	78.55 300	93.98 259

PCF-MVS	84.09 5	86.77 214	85.00 227	92.08 145	92.06 269	83.07 112	92.14 341	94.47 261	79.63 296	76.90 292	94.78 195	71.15 232	99.20 104	72.87 312	91.05 186	93.98 259
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LS3D		82.22 294	79.94 308	89.06 244	97.43 83	74.06 329	93.20 326	92.05 355	61.90 409	73.33 336	95.21 175	59.35 313	99.21 99	54.54 403	92.48 170	93.90 261

test_vis1_n		85.60 235	85.70 213	85.33 326	84.79 384	64.98 395	96.83 169	91.61 363	87.36 117	91.00 117	94.84 194	36.14 415	97.18 227	95.66 54	93.03 163	93.82 262

PLC	83.97 7	88.00 192	87.38 188	89.83 233	98.02 59	76.46 298	97.16 137	94.43 266	79.26 305	81.98 238	96.28 144	69.36 245	99.27 93	77.71 264	92.25 175	93.77 263
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
cascas		86.50 216	84.48 234	92.55 121	92.64 241	85.95 42	97.04 151	95.07 221	75.32 347	80.50 252	91.02 268	54.33 356	97.98 174	86.79 182	87.62 224	93.71 264

dmvs_re		84.10 261	82.90 263	87.70 276	91.41 283	73.28 334	90.59 359	93.19 334	85.02 170	77.96 282	93.68 223	57.92 330	96.18 276	75.50 290	80.87 280	93.63 265

JIA-IIPM		79.00 330	77.20 329	84.40 343	89.74 320	64.06 400	75.30 430	95.44 201	62.15 408	81.90 239	59.08 434	78.92 97	95.59 310	66.51 352	85.78 245	93.54 266

XVG-OURS-SEG-HR		85.74 230	85.16 224	87.49 287	90.22 308	71.45 358	91.29 352	94.09 289	81.37 259	83.90 215	95.22 174	60.30 307	97.53 203	85.58 188	84.42 255	93.50 267

XVG-OURS		85.18 244	84.38 237	87.59 281	90.42 306	71.73 355	91.06 356	94.07 290	82.00 253	83.29 221	95.08 184	56.42 343	97.55 199	83.70 208	83.42 260	93.49 268

thres600view7		88.06 189	86.70 205	92.15 144	96.10 112	85.17 70	97.14 140	98.85 2	82.70 238	83.41 219	93.66 224	75.43 171	97.82 184	67.13 345	85.88 243	93.45 269

thres400		88.42 181	87.15 192	92.23 137	96.21 107	85.30 64	97.44 113	98.85 2	83.37 222	83.99 211	93.82 220	75.36 174	97.93 175	69.04 336	86.24 239	93.45 269

test_fmvs1_n		86.34 219	86.72 204	85.17 329	87.54 353	63.64 402	96.91 165	92.37 352	87.49 113	91.33 110	95.58 162	40.81 408	98.46 148	95.00 65	93.49 156	93.41 271

SDMVSNet		87.02 207	85.61 214	91.24 187	94.14 186	83.30 107	93.88 307	95.98 160	84.30 192	79.63 264	92.01 250	58.23 322	97.68 190	90.28 142	82.02 276	92.75 272

sd_testset		84.62 252	83.11 260	89.17 242	94.14 186	77.78 271	91.54 351	94.38 270	84.30 192	79.63 264	92.01 250	52.28 361	96.98 239	77.67 265	82.02 276	92.75 272

DSMNet-mixed		73.13 367	72.45 362	75.19 403	77.51 419	46.82 434	85.09 405	82.01 427	67.61 397	69.27 366	81.33 392	50.89 365	86.28 421	54.54 403	83.80 257	92.46 274

tt0805		81.20 308	79.06 317	87.61 279	86.50 360	72.97 340	93.66 311	95.48 197	74.11 357	76.23 305	91.99 252	41.36 404	97.40 212	77.44 270	74.78 317	92.45 275

UWE-MVS-28		85.41 241	86.36 207	82.59 364	91.12 289	66.81 389	93.88 307	97.03 38	83.86 209	78.55 273	93.84 219	77.76 121	88.55 410	73.47 310	87.69 223	92.41 276

Effi-MVS+-dtu		84.61 253	84.90 230	83.72 351	91.96 272	63.14 405	94.95 277	93.34 330	85.57 155	79.79 262	87.12 327	61.99 297	95.61 309	83.55 210	85.83 244	92.41 276

F-COLMAP		84.50 256	83.44 257	87.67 277	95.22 143	72.22 343	95.95 227	93.78 308	75.74 344	76.30 303	95.18 178	59.50 312	98.45 150	72.67 314	86.59 234	92.35 278

Fast-Effi-MVS+-dtu		83.33 273	82.60 269	85.50 323	89.55 325	69.38 375	96.09 222	91.38 365	82.30 246	75.96 310	91.41 261	56.71 339	95.58 311	75.13 294	84.90 252	91.54 279

MSDG		80.62 316	77.77 326	89.14 243	93.43 212	77.24 284	91.89 344	90.18 382	69.86 387	68.02 369	91.94 257	52.21 362	98.84 129	59.32 384	83.12 262	91.35 280

HQP4-MVS										82.30 231			97.32 216			91.13 281

HQP-MVS		87.91 195	87.55 183	88.98 247	92.08 266	78.48 241	97.63 94	94.80 235	90.52 55	82.30 231	94.56 200	65.40 273	97.32 216	87.67 173	83.01 264	91.13 281

HQP_MVS		87.50 203	87.09 195	88.74 252	91.86 275	77.96 262	97.18 133	94.69 242	89.89 65	81.33 244	94.15 211	64.77 278	97.30 218	87.08 177	82.82 268	90.96 283

plane_prior5								94.69 242					97.30 218	87.08 177	82.82 268	90.96 283

nrg030		86.79 213	85.43 217	90.87 200	88.76 332	85.34 61	97.06 150	94.33 274	84.31 190	80.45 254	91.98 253	72.36 216	96.36 268	88.48 164	71.13 337	90.93 285

sc_t1		72.37 371	68.03 382	85.39 325	83.78 397	70.51 364	91.27 353	83.70 422	52.46 429	68.29 368	82.02 386	30.58 428	94.81 343	64.50 360	55.69 405	90.85 286

RPSCF		77.73 340	76.63 335	81.06 375	88.66 338	55.76 426	87.77 384	87.88 400	64.82 402	74.14 327	92.79 238	49.22 376	96.81 252	67.47 343	76.88 307	90.62 287

VPNet		84.69 251	82.92 262	90.01 224	89.01 331	83.45 104	96.71 181	95.46 199	85.71 153	79.65 263	92.18 249	56.66 341	96.01 281	83.05 218	67.84 370	90.56 288

CLD-MVS		87.97 193	87.48 185	89.44 239	92.16 261	80.54 184	98.14 57	94.92 227	91.41 41	79.43 266	95.40 167	62.34 290	97.27 221	90.60 132	82.90 267	90.50 289
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
VPA-MVSNet		85.32 242	83.83 245	89.77 236	90.25 307	82.63 119	96.36 203	97.07 35	83.03 230	81.21 246	89.02 294	61.58 300	96.31 270	85.02 193	70.95 339	90.36 290

FIs		86.73 215	86.10 210	88.61 255	90.05 313	80.21 193	96.14 219	96.95 47	85.56 157	78.37 276	92.30 244	76.73 142	95.28 323	79.51 244	79.27 291	90.35 291

DU-MVS		84.57 254	83.33 258	88.28 263	88.76 332	79.36 217	96.43 199	95.41 206	85.42 159	78.11 279	90.82 271	67.61 251	95.14 331	79.14 250	68.30 364	90.33 292

NR-MVSNet		83.35 272	81.52 285	88.84 249	88.76 332	81.31 157	94.45 287	95.16 217	84.65 181	67.81 370	90.82 271	70.36 241	94.87 340	74.75 296	66.89 380	90.33 292

WBMVS		87.73 198	86.79 201	90.56 208	95.61 130	85.68 51	97.63 94	95.52 194	83.77 212	78.30 277	88.44 304	86.14 32	95.78 295	82.54 221	73.15 328	90.21 294

FC-MVSNet-test		85.96 225	85.39 218	87.66 278	89.38 329	78.02 259	95.65 244	96.87 54	85.12 168	77.34 285	91.94 257	76.28 153	94.74 346	77.09 272	78.82 295	90.21 294

XXY-MVS		83.84 265	82.00 277	89.35 240	87.13 355	81.38 155	95.72 240	94.26 277	80.15 286	75.92 311	90.63 274	61.96 298	96.52 262	78.98 252	73.28 326	90.14 296

test0.0.03 1		82.79 284	82.48 270	83.74 350	86.81 358	72.22 343	96.52 190	95.03 223	83.76 213	73.00 339	93.20 230	72.30 219	88.88 408	64.15 363	77.52 306	90.12 297

UniMVSNet_NR-MVSNet		85.49 238	84.59 231	88.21 267	89.44 328	79.36 217	96.71 181	96.41 119	85.22 164	78.11 279	90.98 270	76.97 137	95.14 331	79.14 250	68.30 364	90.12 297

TranMVSNet+NR-MVSNet		83.24 276	81.71 281	87.83 273	87.71 350	78.81 234	96.13 221	94.82 234	84.52 184	76.18 307	90.78 273	64.07 281	94.60 350	74.60 300	66.59 382	90.09 299

MVSTER		89.25 157	88.92 153	90.24 217	95.98 116	84.66 81	96.79 174	95.36 207	87.19 124	80.33 256	90.61 275	90.02 11	95.97 282	85.38 190	78.64 297	90.09 299

PS-MVSNAJss		84.91 248	84.30 238	86.74 299	85.89 372	74.40 326	94.95 277	94.16 285	83.93 206	76.45 299	90.11 285	71.04 234	95.77 296	83.16 216	79.02 294	90.06 301

WR-MVS		84.32 258	82.96 261	88.41 258	89.38 329	80.32 187	96.59 186	96.25 137	83.97 203	76.63 295	90.36 279	67.53 254	94.86 341	75.82 288	70.09 348	90.06 301

FMVSNet3		84.71 250	82.71 267	90.70 205	94.55 166	87.71 23	95.92 229	94.67 245	81.73 256	75.82 312	88.08 311	66.99 260	94.47 353	71.23 323	75.38 314	89.91 303

FMVSNet2		82.79 284	80.44 299	89.83 233	92.66 238	85.43 59	95.42 254	94.35 271	79.06 309	74.46 325	87.28 322	56.38 344	94.31 356	69.72 335	74.68 318	89.76 304

ACMM	80.70 13	83.72 268	82.85 265	86.31 308	91.19 286	72.12 347	95.88 232	94.29 276	80.44 277	77.02 290	91.96 254	55.24 350	97.14 233	79.30 248	80.38 283	89.67 305
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet (Re)		85.31 243	84.23 239	88.55 256	89.75 318	80.55 181	96.72 179	96.89 52	85.42 159	78.40 275	88.93 295	75.38 173	95.52 313	78.58 255	68.02 367	89.57 306

EI-MVSNet		85.80 228	85.20 221	87.59 281	91.55 279	77.41 281	95.13 270	95.36 207	80.43 279	80.33 256	94.71 196	73.72 202	95.97 282	76.96 275	78.64 297	89.39 307

IterMVS-LS		83.93 264	82.80 266	87.31 291	91.46 282	77.39 282	95.66 243	93.43 324	80.44 277	75.51 316	87.26 324	73.72 202	95.16 330	76.99 273	70.72 341	89.39 307
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS3.2		81.06 309	79.49 313	85.75 317	89.78 316	73.00 339	94.40 291	95.23 215	83.76 213	76.61 297	87.82 315	49.48 375	94.88 339	66.80 346	71.56 335	89.38 309

GBi-Net		82.42 290	80.43 300	88.39 260	92.66 238	81.95 134	94.30 295	93.38 326	79.06 309	75.82 312	85.66 350	56.38 344	93.84 365	71.23 323	75.38 314	89.38 309

test1		82.42 290	80.43 300	88.39 260	92.66 238	81.95 134	94.30 295	93.38 326	79.06 309	75.82 312	85.66 350	56.38 344	93.84 365	71.23 323	75.38 314	89.38 309

FMVSNet1		79.50 325	76.54 336	88.39 260	88.47 340	81.95 134	94.30 295	93.38 326	73.14 366	72.04 348	85.66 350	43.86 392	93.84 365	65.48 356	72.53 329	89.38 309

miper_enhance_ethall		85.95 226	85.20 221	88.19 268	94.85 158	79.76 205	96.00 224	94.06 291	82.98 232	77.74 283	88.76 297	79.42 89	95.46 315	80.58 233	72.42 330	89.36 313

dmvs_testset		72.00 375	73.36 359	67.91 409	83.83 396	31.90 449	85.30 403	77.12 434	82.80 236	63.05 396	92.46 241	61.54 301	82.55 431	42.22 430	71.89 334	89.29 314

cl22		85.11 245	84.17 241	87.92 272	95.06 153	78.82 232	95.51 250	94.22 281	79.74 294	76.77 293	87.92 313	75.96 157	95.68 302	79.93 242	72.42 330	89.27 315

eth_miper_zixun_eth		83.12 278	82.01 276	86.47 304	91.85 277	74.80 320	94.33 293	93.18 336	79.11 307	75.74 315	87.25 325	72.71 211	95.32 321	76.78 276	67.13 377	89.27 315

Anonymous20231211		79.72 322	77.19 330	87.33 289	95.59 132	77.16 288	95.18 267	94.18 284	59.31 422	72.57 344	86.20 346	47.89 382	95.66 303	74.53 301	69.24 356	89.18 317

ACMP	81.66 11	84.00 263	83.22 259	86.33 305	91.53 281	72.95 341	95.91 231	93.79 307	83.70 216	73.79 328	92.22 245	54.31 357	96.89 245	83.98 200	79.74 286	89.16 318
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DIV-MVS_self_test		83.27 274	82.12 274	86.74 299	92.19 258	75.92 313	95.11 272	93.26 333	78.44 318	74.81 324	87.08 328	74.19 195	95.19 327	74.66 299	69.30 355	89.11 319

cl____		83.27 274	82.12 274	86.74 299	92.20 257	75.95 311	95.11 272	93.27 332	78.44 318	74.82 323	87.02 329	74.19 195	95.19 327	74.67 298	69.32 354	89.09 320

OPM-MVS		85.84 227	85.10 226	88.06 269	88.34 343	77.83 269	95.72 240	94.20 282	87.89 104	80.45 254	94.05 213	58.57 319	97.26 222	83.88 201	82.76 270	89.09 320
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v2v482		83.46 271	81.86 279	88.25 265	86.19 366	79.65 211	96.34 205	94.02 292	81.56 258	77.32 286	88.23 308	65.62 270	96.03 279	77.77 261	69.72 352	89.09 320

test_djsdf		83.00 282	82.45 271	84.64 337	84.07 393	69.78 371	94.80 283	94.48 258	80.74 269	75.41 318	87.70 316	61.32 304	95.10 334	83.77 204	79.76 284	89.04 323

VortexMVS		85.45 240	84.40 236	88.63 254	93.25 215	81.66 150	95.39 257	94.34 272	87.15 126	75.10 321	87.65 317	66.58 266	95.19 327	86.89 181	73.21 327	89.03 324

jajsoiax		82.12 295	81.15 290	85.03 331	84.19 391	70.70 363	94.22 299	93.95 293	83.07 228	73.48 331	89.75 287	49.66 374	95.37 318	82.24 224	79.76 284	89.02 325

miper_ehance_all_eth		84.57 254	83.60 253	87.50 285	92.64 241	78.25 251	95.40 256	93.47 321	79.28 304	76.41 300	87.64 318	76.53 145	95.24 325	78.58 255	72.42 330	89.01 326

LPG-MVS_test		84.20 260	83.49 256	86.33 305	90.88 293	73.06 337	95.28 258	94.13 286	82.20 247	76.31 301	93.20 230	54.83 354	96.95 241	83.72 206	80.83 281	88.98 327

LGP-MVS_train				86.33 305	90.88 293	73.06 337		94.13 286	82.20 247	76.31 301	93.20 230	54.83 354	96.95 241	83.72 206	80.83 281	88.98 327

AllTest		75.92 352	73.06 360	84.47 340	92.18 259	67.29 382	91.07 355	84.43 416	67.63 393	63.48 390	90.18 281	38.20 411	97.16 228	57.04 393	73.37 323	88.97 329

TestCases				84.47 340	92.18 259	67.29 382		84.43 416	67.63 393	63.48 390	90.18 281	38.20 411	97.16 228	57.04 393	73.37 323	88.97 329

mvs_tets		81.74 299	80.71 295	84.84 332	84.22 390	70.29 367	93.91 306	93.78 308	82.77 237	73.37 334	89.46 290	47.36 385	95.31 322	81.99 225	79.55 290	88.92 331

c3_l		83.80 266	82.65 268	87.25 293	92.10 265	77.74 276	95.25 261	93.04 342	78.58 315	76.01 308	87.21 326	75.25 179	95.11 333	77.54 268	68.89 358	88.91 332

pmmvs5		81.34 305	79.54 311	86.73 302	85.02 382	76.91 290	96.22 212	91.65 361	77.65 324	73.55 330	88.61 299	55.70 347	94.43 354	74.12 304	73.35 325	88.86 333

reproduce_monomvs		87.80 196	87.60 181	88.40 259	96.56 99	80.26 191	95.80 238	96.32 132	91.56 40	73.60 329	88.36 305	88.53 16	96.25 273	90.47 134	67.23 376	88.67 334

miper_lstm_enhance		81.66 302	80.66 296	84.67 336	91.19 286	71.97 350	91.94 343	93.19 334	77.86 322	72.27 346	85.26 358	73.46 205	93.42 373	73.71 308	67.05 378	88.61 335

CP-MVSNet		81.01 311	80.08 304	83.79 348	87.91 348	70.51 364	94.29 298	95.65 186	80.83 266	72.54 345	88.84 296	63.71 282	92.32 383	68.58 340	68.36 363	88.55 336

Syy-MVS		77.97 338	78.05 323	77.74 392	92.13 263	56.85 421	93.97 303	94.23 279	82.43 243	73.39 332	93.57 226	57.95 328	87.86 414	32.40 435	82.34 273	88.51 337

myMVS_eth3d		81.93 297	82.18 273	81.18 374	92.13 263	67.18 384	93.97 303	94.23 279	82.43 243	73.39 332	93.57 226	76.98 136	87.86 414	50.53 414	82.34 273	88.51 337

v144192		82.43 289	80.73 294	87.54 284	85.81 373	78.22 252	95.98 225	93.78 308	79.09 308	77.11 289	86.49 337	64.66 280	95.91 288	74.20 303	69.42 353	88.49 339

v1921920		82.02 296	80.23 302	87.41 288	85.62 374	77.92 265	95.79 239	93.69 313	78.86 312	76.67 294	86.44 339	62.50 289	95.83 291	72.69 313	69.77 351	88.47 340

v1192		82.31 293	80.55 298	87.60 280	85.94 370	78.47 244	95.85 235	93.80 306	79.33 301	76.97 291	86.51 336	63.33 286	95.87 289	73.11 311	70.13 345	88.46 341

PS-CasMVS		80.27 318	79.18 314	83.52 354	87.56 352	69.88 370	94.08 301	95.29 212	80.27 284	72.08 347	88.51 303	59.22 316	92.23 385	67.49 342	68.15 366	88.45 342

v148		82.41 292	80.89 291	86.99 297	86.18 367	76.81 293	96.27 209	93.82 303	80.49 276	75.28 319	86.11 348	67.32 257	95.75 298	75.48 291	67.03 379	88.42 343

v1240		81.70 300	79.83 310	87.30 292	85.50 375	77.70 277	95.48 251	93.44 322	78.46 317	76.53 298	86.44 339	60.85 305	95.84 290	71.59 320	70.17 343	88.35 344

v1144		82.90 283	81.27 288	87.78 275	86.29 364	79.07 229	96.14 219	93.93 294	80.05 288	77.38 284	86.80 332	65.50 271	95.93 287	75.21 293	70.13 345	88.33 345

EU-MVSNet		76.92 348	76.95 332	76.83 397	84.10 392	54.73 429	91.77 346	92.71 347	72.74 370	69.57 364	88.69 298	58.03 327	87.43 418	64.91 359	70.00 349	88.33 345

PEN-MVS		79.47 326	78.26 322	83.08 357	86.36 362	68.58 378	93.85 309	94.77 238	79.76 293	71.37 350	88.55 300	59.79 308	92.46 379	64.50 360	65.40 384	88.19 347

IterMVS		80.67 315	79.16 315	85.20 328	89.79 315	76.08 305	92.97 330	91.86 357	80.28 283	71.20 353	85.14 363	57.93 329	91.34 395	72.52 315	70.74 340	88.18 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		80.51 317	79.10 316	84.73 334	89.63 323	74.66 321	92.98 329	91.81 359	80.05 288	71.06 355	85.18 361	58.04 325	91.40 394	72.48 316	70.70 342	88.12 349

XVG-ACMP-BASELINE		79.38 327	77.90 325	83.81 347	84.98 383	67.14 388	89.03 371	93.18 336	80.26 285	72.87 341	88.15 310	38.55 410	96.26 271	76.05 285	78.05 304	88.02 350

MVS-HIRNet		71.36 378	67.00 384	84.46 342	90.58 302	69.74 372	79.15 421	87.74 401	46.09 433	61.96 402	50.50 437	45.14 390	95.64 306	53.74 405	88.11 219	88.00 351

SixPastTwentyTwo		76.04 351	74.32 352	81.22 373	84.54 386	61.43 412	91.16 354	89.30 390	77.89 320	64.04 389	86.31 343	48.23 377	94.29 357	63.54 367	63.84 391	87.93 352

pmmvs4		82.54 288	80.79 292	87.79 274	86.11 368	80.49 186	93.55 315	93.18 336	77.29 329	73.35 335	89.40 291	65.26 276	95.05 337	75.32 292	73.61 322	87.83 353

lessismore_v0				79.98 381	80.59 408	58.34 420		80.87 428		58.49 414	83.46 379	43.10 397	93.89 364	63.11 369	48.68 422	87.72 354

ACMH	75.40 17	77.99 336	74.96 344	87.10 296	90.67 301	76.41 300	93.19 327	91.64 362	72.47 373	63.44 392	87.61 319	43.34 395	97.16 228	58.34 387	73.94 320	87.72 354
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Patchmtry		77.36 344	74.59 349	85.67 319	89.75 318	75.75 315	77.85 425	91.12 370	60.28 417	71.23 352	80.35 397	75.45 169	93.56 371	57.94 388	67.34 375	87.68 356

OurMVSNet-221017-0		77.18 346	76.06 338	80.55 378	83.78 397	60.00 416	90.35 360	91.05 373	77.01 335	66.62 379	87.92 313	47.73 383	94.03 361	71.63 319	68.44 362	87.62 357

V42		83.04 280	81.53 284	87.57 283	86.27 365	79.09 228	95.87 233	94.11 288	80.35 281	77.22 288	86.79 333	65.32 275	96.02 280	77.74 262	70.14 344	87.61 358

PVSNet_BlendedMVS		90.05 140	89.96 136	90.33 215	97.47 78	83.86 93	98.02 69	96.73 74	87.98 99	89.53 136	89.61 289	76.42 148	99.57 72	94.29 74	79.59 288	87.57 359

testgi		74.88 358	73.40 358	79.32 385	80.13 410	61.75 409	93.21 325	86.64 408	79.49 299	66.56 380	91.06 267	35.51 418	88.67 409	56.79 396	71.25 336	87.56 360

DTE-MVSNet		78.37 332	77.06 331	82.32 367	85.22 381	67.17 387	93.40 317	93.66 314	78.71 314	70.53 358	88.29 307	59.06 317	92.23 385	61.38 375	63.28 393	87.56 360

testing3		80.74 314	81.17 289	79.44 384	91.15 288	63.48 403	97.16 137	95.76 179	80.83 266	71.36 351	93.15 233	78.22 111	87.30 419	43.19 427	79.67 287	87.55 362

K. test v3		73.62 361	71.59 367	79.69 382	82.98 401	59.85 417	90.85 358	88.83 393	77.13 331	58.90 412	82.11 385	43.62 393	91.72 392	65.83 355	54.10 411	87.50 363

WR-MVS_H		81.02 310	80.09 303	83.79 348	88.08 346	71.26 361	94.46 286	96.54 102	80.08 287	72.81 342	86.82 331	70.36 241	92.65 378	64.18 362	67.50 373	87.46 364

pm-mvs1		80.05 319	78.02 324	86.15 310	85.42 376	75.81 314	95.11 272	92.69 348	77.13 331	70.36 359	87.43 320	58.44 321	95.27 324	71.36 322	64.25 389	87.36 365

v7n		79.32 328	77.34 328	85.28 327	84.05 394	72.89 342	93.38 318	93.87 300	75.02 351	70.68 356	84.37 370	59.58 311	95.62 308	67.60 341	67.50 373	87.32 366

v8		81.88 298	80.06 306	87.32 290	86.63 359	79.04 230	94.41 288	93.65 315	78.77 313	73.19 338	85.57 354	66.87 262	95.81 292	73.84 307	67.61 372	87.11 367

ACMH+	76.62 16	77.47 343	74.94 345	85.05 330	91.07 291	71.58 357	93.26 324	90.01 383	71.80 376	64.76 387	88.55 300	41.62 402	96.48 263	62.35 371	71.00 338	87.09 368

UnsupCasMVSNet_eth		73.25 366	70.57 371	81.30 372	77.53 418	66.33 391	87.24 388	93.89 299	80.38 280	57.90 417	81.59 389	42.91 399	90.56 402	65.18 358	48.51 423	87.01 369

ppachtmachnet_test		77.19 345	74.22 353	86.13 311	85.39 377	78.22 252	93.98 302	91.36 367	71.74 377	67.11 373	84.87 367	56.67 340	93.37 375	52.21 408	64.59 386	86.80 370

v10		81.43 304	79.53 312	87.11 295	86.38 361	78.87 231	94.31 294	93.43 324	77.88 321	73.24 337	85.26 358	65.44 272	95.75 298	72.14 317	67.71 371	86.72 371

test_fmvs2		79.59 323	79.90 309	78.67 388	82.86 402	55.82 425	95.20 264	89.55 386	81.09 262	80.12 260	89.80 286	34.31 420	93.51 372	87.82 170	78.36 302	86.69 372

anonymousdsp		80.98 312	79.97 307	84.01 345	81.73 405	70.44 366	92.49 336	93.58 319	77.10 333	72.98 340	86.31 343	57.58 331	94.90 338	79.32 247	78.63 299	86.69 372

our_test_3		77.90 339	75.37 343	85.48 324	85.39 377	76.74 294	93.63 312	91.67 360	73.39 365	65.72 383	84.65 369	58.20 324	93.13 376	57.82 389	67.87 368	86.57 374

Anonymous20231206		75.29 356	73.64 357	80.22 380	80.75 406	63.38 404	93.36 319	90.71 380	73.09 367	67.12 372	83.70 377	50.33 371	90.85 400	53.63 406	70.10 347	86.44 375

YYNet1		73.53 365	70.43 372	82.85 360	84.52 387	71.73 355	91.69 348	91.37 366	67.63 393	46.79 428	81.21 393	55.04 352	90.43 403	55.93 398	59.70 400	86.38 376

MDA-MVSNet_test_wron		73.54 364	70.43 372	82.86 359	84.55 385	71.85 352	91.74 347	91.32 369	67.63 393	46.73 429	81.09 394	55.11 351	90.42 404	55.91 399	59.76 399	86.31 377

ITE_SJBPF				82.38 365	87.00 356	65.59 393		89.55 386	79.99 290	69.37 365	91.30 264	41.60 403	95.33 320	62.86 370	74.63 319	86.24 378

FMVSNet5		76.46 350	74.16 354	83.35 356	90.05 313	76.17 303	89.58 366	89.85 384	71.39 379	65.29 386	80.42 396	50.61 369	87.70 417	61.05 377	69.24 356	86.18 379

MDA-MVSNet-bldmvs		71.45 376	67.94 383	81.98 369	85.33 379	68.50 379	92.35 339	88.76 395	70.40 382	42.99 432	81.96 387	46.57 387	91.31 396	48.75 420	54.39 410	86.11 380

USDC		78.65 331	76.25 337	85.85 313	87.58 351	74.60 323	89.58 366	90.58 381	84.05 200	63.13 394	88.23 308	40.69 409	96.86 250	66.57 351	75.81 312	86.09 381

pmmvs6		74.65 359	71.67 366	83.60 353	79.13 413	69.94 369	93.31 323	90.88 377	61.05 416	65.83 382	84.15 373	43.43 394	94.83 342	66.62 349	60.63 398	86.02 382

WB-MVSnew		84.08 262	83.51 255	85.80 314	91.34 284	76.69 296	95.62 246	96.27 135	81.77 255	81.81 242	92.81 236	58.23 322	94.70 347	66.66 348	87.06 229	85.99 383

KD-MVS_2432*1600		77.63 341	74.92 346	85.77 315	90.86 296	79.44 214	88.08 380	93.92 296	76.26 341	67.05 374	82.78 383	72.15 221	91.92 388	61.53 372	41.62 435	85.94 384

miper_refine_blended		77.63 341	74.92 346	85.77 315	90.86 296	79.44 214	88.08 380	93.92 296	76.26 341	67.05 374	82.78 383	72.15 221	91.92 388	61.53 372	41.62 435	85.94 384

D2MVS		82.67 286	81.55 283	86.04 312	87.77 349	76.47 297	95.21 263	96.58 98	82.66 240	70.26 360	85.46 357	60.39 306	95.80 293	76.40 281	79.18 292	85.83 386

COLMAP_ROB	73.24 19	75.74 354	73.00 361	83.94 346	92.38 246	69.08 376	91.85 345	86.93 404	61.48 412	65.32 385	90.27 280	42.27 400	96.93 244	50.91 412	75.63 313	85.80 387
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CL-MVSNet_self_test		75.81 353	74.14 355	80.83 377	78.33 416	67.79 381	94.22 299	93.52 320	77.28 330	69.82 362	81.54 391	61.47 303	89.22 407	57.59 391	53.51 412	85.48 388

CMPMVS	54.94 21	75.71 355	74.56 350	79.17 386	79.69 411	55.98 423	89.59 365	93.30 331	60.28 417	53.85 424	89.07 293	47.68 384	96.33 269	76.55 278	81.02 279	85.22 389
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LTVRE_ROB	73.68 18	77.99 336	75.74 341	84.74 333	90.45 305	72.02 348	86.41 395	91.12 370	72.57 372	66.63 378	87.27 323	54.95 353	96.98 239	56.29 397	75.98 309	85.21 390
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
N_pmnet		61.30 395	60.20 398	64.60 414	84.32 389	17.00 455	91.67 349	10.98 453	61.77 410	58.45 415	78.55 404	49.89 373	91.83 391	42.27 429	63.94 390	84.97 391

MIMVSNet1		69.44 385	66.65 387	77.84 391	76.48 423	62.84 406	87.42 386	88.97 392	66.96 398	57.75 418	79.72 402	32.77 424	85.83 423	46.32 422	63.42 392	84.85 392

tt0320-xc		69.70 381	65.27 392	82.99 358	84.33 388	71.92 351	89.56 368	82.08 426	50.11 430	61.87 403	77.50 407	30.48 429	92.34 382	60.30 379	51.20 418	84.71 393

tt0320		70.21 380	66.07 388	82.64 362	83.42 400	70.82 362	89.63 364	84.10 419	49.75 432	62.71 398	77.28 409	33.35 421	92.45 381	58.78 386	55.62 406	84.64 394

Baseline_NR-MVSNet		81.22 307	80.07 305	84.68 335	85.32 380	75.12 319	96.48 193	88.80 394	76.24 343	77.28 287	86.40 342	67.61 251	94.39 355	75.73 289	66.73 381	84.54 395

TransMVSNet (Re)		76.94 347	74.38 351	84.62 338	85.92 371	75.25 318	95.28 258	89.18 391	73.88 360	67.22 371	86.46 338	59.64 309	94.10 360	59.24 385	52.57 416	84.50 396

KD-MVS_self_test		70.97 379	69.31 377	75.95 402	76.24 426	55.39 427	87.45 385	90.94 376	70.20 384	62.96 397	77.48 408	44.01 391	88.09 412	61.25 376	53.26 413	84.37 397

MS-PatchMatch		83.05 279	81.82 280	86.72 303	89.64 322	79.10 227	94.88 279	94.59 254	79.70 295	70.67 357	89.65 288	50.43 370	96.82 251	70.82 330	95.99 120	84.25 398

ambc				76.02 400	68.11 435	51.43 430	64.97 438	89.59 385		60.49 408	74.49 418	17.17 437	92.46 379	61.50 374	52.85 415	84.17 399

test_method		56.77 397	54.53 401	63.49 416	76.49 422	40.70 442	75.68 429	74.24 436	19.47 444	48.73 426	71.89 427	19.31 435	65.80 444	57.46 392	47.51 427	83.97 400

tfpnnormal		78.14 334	75.42 342	86.31 308	88.33 344	79.24 220	94.41 288	96.22 140	73.51 362	69.81 363	85.52 356	55.43 348	95.75 298	47.65 421	67.86 369	83.95 401

test20.03		72.36 372	71.15 368	75.98 401	77.79 417	59.16 418	92.40 338	89.35 389	74.09 358	61.50 404	84.32 371	48.09 378	85.54 424	50.63 413	62.15 396	83.24 402

Anonymous20240521		72.06 374	69.91 374	78.50 390	77.11 421	61.67 411	91.62 350	90.97 375	65.52 400	62.37 399	79.05 403	36.32 414	90.96 399	57.75 390	68.52 361	82.87 403

OpenMVS_ROB	68.52 20	73.02 368	69.57 375	83.37 355	80.54 409	71.82 353	93.60 314	88.22 398	62.37 407	61.98 401	83.15 382	35.31 419	95.47 314	45.08 425	75.88 311	82.82 404

UnsupCasMVSNet_bld		68.60 389	64.50 393	80.92 376	74.63 429	67.80 380	83.97 409	92.94 343	65.12 401	54.63 423	68.23 430	35.97 416	92.17 387	60.13 380	44.83 430	82.78 405

MVP-Stereo		82.65 287	81.67 282	85.59 322	86.10 369	78.29 248	93.33 320	92.82 345	77.75 323	69.17 367	87.98 312	59.28 315	95.76 297	71.77 318	96.88 96	82.73 406
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pmmvs-eth3d		73.59 362	70.66 370	82.38 365	76.40 424	73.38 331	89.39 370	89.43 388	72.69 371	60.34 409	77.79 406	46.43 388	91.26 397	66.42 353	57.06 403	82.51 407

PM-MVS		69.32 386	66.93 385	76.49 398	73.60 430	55.84 424	85.91 398	79.32 432	74.72 353	61.09 406	78.18 405	21.76 434	91.10 398	70.86 328	56.90 404	82.51 407

TinyColmap		72.41 370	68.99 379	82.68 361	88.11 345	69.59 373	88.41 376	85.20 412	65.55 399	57.91 416	84.82 368	30.80 427	95.94 286	51.38 409	68.70 359	82.49 409

mmtdpeth		78.04 335	76.76 334	81.86 370	89.60 324	66.12 392	92.34 340	87.18 402	76.83 338	85.55 191	76.49 413	46.77 386	97.02 236	90.85 126	45.24 429	82.43 410

LF4IMVS		72.36 372	70.82 369	76.95 396	79.18 412	56.33 422	86.12 397	86.11 410	69.30 389	63.06 395	86.66 334	33.03 423	92.25 384	65.33 357	68.64 360	82.28 411

mvs5depth		71.40 377	68.36 381	80.54 379	75.31 428	65.56 394	79.94 417	85.14 413	69.11 390	71.75 349	81.59 389	41.02 406	93.94 363	60.90 378	50.46 419	82.10 412

TDRefinement		69.20 387	65.78 390	79.48 383	66.04 438	62.21 408	88.21 377	86.12 409	62.92 405	61.03 407	85.61 353	33.23 422	94.16 359	55.82 400	53.02 414	82.08 413

EG-PatchMatch MVS		74.92 357	72.02 365	83.62 352	83.76 399	73.28 334	93.62 313	92.04 356	68.57 391	58.88 413	83.80 376	31.87 425	95.57 312	56.97 395	78.67 296	82.00 414

mvsany_test3		67.19 390	65.34 391	72.72 405	63.08 439	48.57 432	83.12 412	78.09 433	72.07 374	61.21 405	77.11 411	22.94 433	87.78 416	78.59 254	51.88 417	81.80 415

test_fmvs3		69.56 383	69.19 378	70.67 407	69.01 433	47.05 433	90.87 357	86.81 405	71.31 380	66.79 377	77.15 410	16.40 438	83.17 429	81.84 226	62.51 395	81.79 416

ttmdpeth		69.58 382	66.92 386	77.54 394	75.95 427	62.40 407	88.09 379	84.32 418	62.87 406	65.70 384	86.25 345	36.53 413	88.53 411	55.65 401	46.96 428	81.70 417

new-patchmatchnet		68.85 388	65.93 389	77.61 393	73.57 431	63.94 401	90.11 362	88.73 396	71.62 378	55.08 422	73.60 420	40.84 407	87.22 420	51.35 411	48.49 424	81.67 418

MVStest1		66.93 391	63.01 395	78.69 387	78.56 414	71.43 359	85.51 402	86.81 405	49.79 431	48.57 427	84.15 373	53.46 358	83.31 427	43.14 428	37.15 438	81.34 419

test_0402		72.68 369	69.54 376	82.09 368	88.67 337	71.81 354	92.72 334	86.77 407	61.52 411	62.21 400	83.91 375	43.22 396	93.76 368	34.60 433	72.23 333	80.72 420

kuosan		73.55 363	72.39 364	77.01 395	89.68 321	66.72 390	85.24 404	93.44 322	67.76 392	60.04 411	83.40 380	71.90 224	84.25 426	45.34 424	54.75 407	80.06 421

test_f		64.01 394	62.13 397	69.65 408	63.00 440	45.30 439	83.66 411	80.68 429	61.30 413	55.70 421	72.62 424	14.23 440	84.64 425	69.84 333	58.11 401	79.00 422

pmmvs3		65.75 393	62.18 396	76.45 399	67.12 437	64.54 396	88.68 374	85.05 414	54.77 428	57.54 419	73.79 419	29.40 430	86.21 422	55.49 402	47.77 426	78.62 423

LCM-MVSNet		52.52 402	48.24 405	65.35 412	47.63 449	41.45 441	72.55 434	83.62 423	31.75 437	37.66 435	57.92 435	9.19 447	76.76 437	49.26 417	44.60 431	77.84 424

test_vis1_rt		73.96 360	72.40 363	78.64 389	83.91 395	61.16 413	95.63 245	68.18 442	76.32 340	60.09 410	74.77 416	29.01 431	97.54 201	87.74 171	75.94 310	77.22 425

new_pmnet		66.18 392	63.18 394	75.18 404	76.27 425	61.74 410	83.79 410	84.66 415	56.64 426	51.57 425	71.85 428	31.29 426	87.93 413	49.98 415	62.55 394	75.86 426

dongtai		69.47 384	68.98 380	70.93 406	86.87 357	58.45 419	88.19 378	93.18 336	63.98 403	56.04 420	80.17 399	70.97 237	79.24 433	33.46 434	47.94 425	75.09 427

PMMVS2		50.90 404	46.31 407	64.67 413	55.53 443	46.67 435	77.30 427	71.02 439	40.89 434	34.16 438	59.32 433	9.83 446	76.14 439	40.09 432	28.63 441	71.21 428

ANet_high		46.22 405	41.28 412	61.04 419	39.91 451	46.25 437	70.59 435	76.18 435	58.87 423	23.09 443	48.00 440	12.58 443	66.54 443	28.65 438	13.62 444	70.35 429

DeepMVS_CX				64.06 415	78.53 415	43.26 440		68.11 444	69.94 386	38.55 434	76.14 414	18.53 436	79.34 432	43.72 426	41.62 435	69.57 430

FPMVS		55.09 400	52.93 403	61.57 418	55.98 442	40.51 443	83.11 413	83.41 424	37.61 436	34.95 437	71.95 426	14.40 439	76.95 436	29.81 436	65.16 385	67.25 431

APD_test1		56.56 398	53.58 402	65.50 411	67.93 436	46.51 436	77.24 428	72.95 437	38.09 435	42.75 433	75.17 415	13.38 441	82.78 430	40.19 431	54.53 409	67.23 432

WB-MVS		57.26 396	56.22 399	60.39 420	69.29 432	35.91 447	86.39 396	70.06 440	59.84 421	46.46 430	72.71 423	51.18 364	78.11 434	15.19 444	34.89 439	67.14 433

SSC-MVS		56.01 399	54.96 400	59.17 421	68.42 434	34.13 448	84.98 406	69.23 441	58.08 425	45.36 431	71.67 429	50.30 372	77.46 435	14.28 445	32.33 440	65.91 434

EGC-MVSNET		52.46 403	47.56 406	67.15 410	81.98 404	60.11 415	82.54 414	72.44 438	0.11 450	0.70 451	74.59 417	25.11 432	83.26 428	29.04 437	61.51 397	58.09 435

testf1		45.70 406	42.41 408	55.58 422	53.29 446	40.02 444	68.96 436	62.67 446	27.45 439	29.85 439	61.58 431	5.98 449	73.83 441	28.49 439	43.46 433	52.90 436

APD_test2		45.70 406	42.41 408	55.58 422	53.29 446	40.02 444	68.96 436	62.67 446	27.45 439	29.85 439	61.58 431	5.98 449	73.83 441	28.49 439	43.46 433	52.90 436

test_vis3_rt		54.10 401	51.04 404	63.27 417	58.16 441	46.08 438	84.17 408	49.32 452	56.48 427	36.56 436	49.48 439	8.03 448	91.91 390	67.29 344	49.87 420	51.82 438

PMVS	34.80 23	39.19 410	35.53 413	50.18 425	29.72 452	30.30 450	59.60 440	66.20 445	26.06 441	17.91 445	49.53 438	3.12 451	74.09 440	18.19 443	49.40 421	46.14 439
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	35.65 22	33.85 411	29.49 416	46.92 426	41.86 450	36.28 446	50.45 441	56.52 449	18.75 445	18.28 444	37.84 441	2.41 452	58.41 445	18.71 442	20.62 442	46.06 440
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		41.54 409	41.93 411	40.38 427	20.10 453	26.84 451	61.93 439	59.09 448	14.81 446	28.51 441	80.58 395	35.53 417	48.33 448	63.70 366	13.11 445	45.96 441

Gipuma		45.11 408	42.05 410	54.30 424	80.69 407	51.30 431	35.80 442	83.81 421	28.13 438	27.94 442	34.53 442	11.41 445	76.70 438	21.45 441	54.65 408	34.90 442
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		32.70 412	32.39 414	33.65 428	53.35 445	25.70 452	74.07 432	53.33 450	21.08 442	17.17 446	33.63 444	11.85 444	54.84 446	12.98 446	14.04 443	20.42 443

EMVS		31.70 413	31.45 415	32.48 429	50.72 448	23.95 453	74.78 431	52.30 451	20.36 443	16.08 447	31.48 445	12.80 442	53.60 447	11.39 447	13.10 446	19.88 444

test123		9.07 417	11.73 420	1.11 431	0.50 455	0.77 456	89.44 369	0.20 456	0.34 449	2.15 450	10.72 449	0.34 454	0.32 450	1.79 450	0.08 449	2.23 445

testmvs		9.92 416	12.94 419	0.84 432	0.65 454	0.29 457	93.78 310	0.39 455	0.42 448	2.85 449	15.84 448	0.17 455	0.30 451	2.18 449	0.21 448	1.91 446

wuyk23d		14.10 415	13.89 418	14.72 430	55.23 444	22.91 454	33.83 443	3.56 454	4.94 447	4.11 448	2.28 450	2.06 453	19.66 449	10.23 448	8.74 447	1.59 447

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		21.43 414	28.57 417	0.00 433	0.00 456	0.00 458	0.00 444	95.93 168	0.00 451	0.00 452	97.66 85	63.57 283	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		5.92 419	7.89 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	71.04 234	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		8.11 418	10.81 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	97.30 108	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						67.18 384								49.00 418

FOURS1					98.51 39	78.01 260	98.13 60	96.21 141	83.04 229	94.39 62

test_one_0601					98.91 18	84.56 84		96.70 78	88.06 97	96.57 29	98.77 10	88.04 21

eth-test2					0.00 456

eth-test					0.00 456

ZD-MVS					99.09 8	83.22 109		96.60 95	82.88 234	93.61 73	98.06 63	82.93 60	99.14 109	95.51 58	98.49 39

test_241102_ONE					99.03 15	85.03 74		96.78 61	88.72 79	97.79 8	98.90 5	88.48 17	99.82 19

9.14			94.26 36		98.10 57		98.14 57	96.52 105	84.74 177	94.83 56	98.80 7	82.80 62	99.37 88	95.95 50	98.42 42

save fliter					98.24 51	83.34 106	98.61 42	96.57 99	91.32 42

test0726					99.05 9	85.18 66	99.11 16	96.78 61	88.75 77	97.65 13	98.91 2	87.69 23

test_part2					98.90 19	85.14 72				96.07 36

sam_mvs												75.35 176

MTGPA								96.33 130

test_post1							85.88 399				30.24 446	73.77 200	95.07 336	73.89 305

test_post											33.80 443	76.17 154	95.97 282

patchmatchnet-post											77.09 412	77.78 120	95.39 316

MTMP							97.53 105	68.16 443

gm-plane-assit					92.27 253	79.64 212			84.47 187		95.15 180		97.93 175	85.81 186

TEST9					98.64 31	83.71 97	97.82 80	96.65 86	84.29 194	95.16 46	98.09 58	84.39 42	99.36 89

test_8					98.63 33	83.64 100	97.81 82	96.63 91	84.50 185	95.10 49	98.11 56	84.33 43	99.23 97

agg_prior					98.59 35	83.13 111		96.56 101		94.19 64			99.16 108

test_prior4						82.34 127	97.75 88

test_prior2							98.37 50		86.08 145	94.57 60	98.02 64	83.14 57		95.05 64	98.79 27

旧先验2							96.97 158		74.06 359	96.10 35			97.76 186	88.38 165

新几何2							96.42 200

原ACMM2							96.84 168

testdata2													99.48 81	76.45 280

segment_acmp												82.69 63

testdata1							95.57 249		87.44 114

plane_prior7					91.86 275	77.55 279

plane_prior6					91.98 271	77.92 265						64.77 278

plane_prior4											94.15 211

plane_prior3						77.75 275			90.17 62	81.33 244

plane_prior2							97.18 133		89.89 65

plane_prior1					91.95 273

plane_prior						77.96 262	97.52 108		90.36 60						82.96 266

n2								0.00 457

nn								0.00 457

door-mid								79.75 431

test11								96.50 108

door								80.13 430

HQP5-MVS						78.48 241

HQP-NCC					92.08 266		97.63 94		90.52 55	82.30 231

ACMP_Plane					92.08 266		97.63 94		90.52 55	82.30 231

BP-MVS														87.67 173

HQP3-MVS								94.80 235							83.01 264

HQP2-MVS												65.40 273

NP-MVS					92.04 270	78.22 252					94.56 200

MDTV_nov1_ep13			83.69 246		94.09 190	81.01 165	86.78 392	96.09 150	83.81 211	84.75 201	84.32 371	74.44 193	96.54 261	63.88 364	85.07 251

ACMMP++_ref															78.45 301

ACMMP++															79.05 293

Test By Simon												71.65 227

High-resolution multi-view benchmark