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		90.70 3	90.52 9	91.24 1	89.68 160	76.68 2	97.29 1	95.35 16	82.87 24	91.58 13	97.22 3	79.93 5	99.10 9	83.12 104	97.64 2	97.94 1

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 55	96.89 6	94.44 47	71.65 221	92.11 7	97.21 4	76.79 9	99.11 6	92.34 24	95.36 14	97.62 2

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 9	83.82 2	99.15 2	95.72 5	97.63 3	97.62 2

DVP-MVS++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 42	93.96 72	94.37 53	72.48 191	92.07 9	96.85 16	83.82 2	99.15 2	91.53 32	97.42 4	97.55 4

PC_three_1452									80.91 50	94.07 2	96.83 18	83.57 4	99.12 5	95.70 7	97.42 4	97.55 4

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 135	93.00 75	58.16 315	96.72 9	94.41 49	86.50 8	90.25 22	97.83 1	75.46 14	98.67 25	92.78 21	95.49 13	97.32 6

balanced_conf03		89.08 15	88.84 17	89.81 6	93.66 54	75.15 5	90.61 228	93.43 88	84.06 14	86.20 51	90.17 185	72.42 33	96.98 103	93.09 18	95.92 10	97.29 7

LFMVS		84.34 87	82.73 114	89.18 13	94.76 33	73.25 11	94.99 42	91.89 155	71.90 209	82.16 93	93.49 117	47.98 281	97.05 94	82.55 110	84.82 147	97.25 8

sasdasda		86.85 37	86.25 48	88.66 20	91.80 113	71.92 16	93.54 97	91.71 165	80.26 58	87.55 39	95.25 63	63.59 104	96.93 111	88.18 52	84.34 152	97.11 9

canonicalmvs		86.85 37	86.25 48	88.66 20	91.80 113	71.92 16	93.54 97	91.71 165	80.26 58	87.55 39	95.25 63	63.59 104	96.93 111	88.18 52	84.34 152	97.11 9

MCST-MVS		91.08 1	91.46 3	89.94 4	97.66 2	73.37 10	97.13 2	95.58 11	89.33 1	85.77 56	96.26 32	72.84 29	99.38 1	92.64 22	95.93 9	97.08 11

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 70	73.88 9	97.01 4	94.40 51	88.32 3	85.71 57	94.91 75	74.11 21	98.91 18	87.26 64	95.94 8	97.03 12
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
MGCFI-Net		85.59 65	85.73 60	85.17 119	91.41 127	62.44 238	92.87 124	91.31 182	79.65 70	86.99 46	95.14 69	62.90 117	96.12 143	87.13 66	84.13 159	96.96 13

CSCG		86.87 36	86.26 47	88.72 17	95.05 31	70.79 29	93.83 84	95.33 17	68.48 274	77.63 147	94.35 93	73.04 27	98.45 30	84.92 86	93.71 47	96.92 14

MM		90.87 2	91.52 2	88.92 15	92.12 100	71.10 27	97.02 3	96.04 6	88.70 2	91.57 14	96.19 34	70.12 45	98.91 18	96.83 1	95.06 17	96.76 15

MVS		84.66 81	82.86 112	90.06 2	90.93 136	74.56 7	87.91 284	95.54 14	68.55 272	72.35 208	94.71 80	59.78 148	98.90 20	81.29 121	94.69 32	96.74 16

alignmvs		87.28 32	86.97 37	88.24 27	91.30 129	71.14 26	95.61 25	93.56 80	79.30 77	87.07 44	95.25 63	68.43 50	96.93 111	87.87 55	84.33 154	96.65 17

DeepC-MVS_fast	79.48 2	87.95 22	88.00 25	87.79 31	95.86 27	68.32 80	95.74 21	94.11 61	83.82 16	83.49 79	96.19 34	64.53 90	98.44 31	83.42 103	94.88 25	96.61 18
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								94.41 49	71.65 221	92.07 9	97.21 4	74.58 18	99.11 6	92.34 24	95.36 14	96.59 19

TSAR-MVS + GP.		87.96 21	88.37 21	86.70 65	93.51 61	65.32 160	95.15 36	93.84 66	78.17 98	85.93 55	94.80 78	75.80 13	98.21 34	89.38 43	88.78 107	96.59 19

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 50	96.53 13	93.78 67	86.89 6	89.68 28	95.78 42	65.94 72	99.10 9	92.99 19	93.91 42	96.58 21

WTY-MVS		86.32 48	85.81 57	87.85 29	92.82 81	69.37 57	95.20 34	95.25 18	82.71 25	81.91 94	94.73 79	67.93 56	97.63 58	79.55 134	82.25 173	96.54 22

VNet		86.20 50	85.65 61	87.84 30	93.92 47	69.99 38	95.73 23	95.94 7	78.43 95	86.00 54	93.07 123	58.22 168	97.00 99	85.22 80	84.33 154	96.52 23

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 27					99.07 13	92.01 27	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 27					99.07 13	92.01 27	94.77 26	96.51 24

test_0728_SECOND				88.70 18	96.45 12	70.43 33	96.64 10	94.37 53					99.15 2	91.91 30	94.90 22	96.51 24

ET-MVSNet_ETH3D		84.01 96	83.15 106	86.58 70	90.78 141	70.89 28	94.74 47	94.62 41	81.44 42	58.19 341	93.64 113	73.64 25	92.35 290	82.66 108	78.66 208	96.50 27

MVSMamba_PlusPlus		84.97 77	83.65 88	88.93 14	90.17 151	74.04 8	87.84 286	92.69 118	62.18 326	81.47 99	87.64 223	71.47 40	96.28 136	84.69 88	94.74 31	96.47 28

IU-MVS					96.46 11	69.91 42		95.18 21	80.75 51	95.28 1				92.34 24	95.36 14	96.47 28

MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 36	97.00 5	93.73 74	87.30 4	92.15 6	96.15 36	66.38 67	98.94 17	96.71 2	94.67 33	96.47 28

test_0728_THIRD									72.48 191	90.55 20	96.93 11	76.24 11	99.08 11	91.53 32	94.99 18	96.43 31

MSP-MVS		90.38 5	91.87 1	85.88 91	92.83 79	64.03 195	93.06 114	94.33 55	82.19 31	93.65 3	96.15 36	85.89 1	97.19 86	91.02 36	97.75 1	96.43 31
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
HY-MVS	76.49 5	84.28 88	83.36 100	87.02 55	92.22 95	67.74 98	84.65 312	94.50 44	79.15 81	82.23 92	87.93 218	66.88 62	96.94 109	80.53 126	82.20 175	96.39 33

DPE-MVS		88.77 17	89.21 16	87.45 43	96.26 20	67.56 103	94.17 59	94.15 60	68.77 270	90.74 18	97.27 2	76.09 12	98.49 29	90.58 40	94.91 21	96.30 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 38	96.64 10	94.52 43	71.92 207	90.55 20	96.93 11	73.77 23	99.08 11	91.91 30	94.90 22	96.29 35
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
MSLP-MVS++		86.27 49	85.91 56	87.35 45	92.01 105	68.97 66	95.04 40	92.70 116	79.04 87	81.50 97	96.50 26	58.98 161	96.78 117	83.49 102	93.93 41	96.29 35

patch_mono-2		89.71 11	90.99 6	85.85 94	96.04 24	63.70 205	95.04 40	95.19 20	86.74 7	91.53 15	95.15 68	73.86 22	97.58 61	93.38 16	92.00 69	96.28 37

test_yl		84.28 88	83.16 104	87.64 34	94.52 37	69.24 59	95.78 18	95.09 24	69.19 264	81.09 103	92.88 129	57.00 181	97.44 68	81.11 123	81.76 180	96.23 38

DCV-MVSNet		84.28 88	83.16 104	87.64 34	94.52 37	69.24 59	95.78 18	95.09 24	69.19 264	81.09 103	92.88 129	57.00 181	97.44 68	81.11 123	81.76 180	96.23 38

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 31	84.83 11	89.07 31	96.80 19	70.86 41	99.06 15	92.64 22	95.71 11	96.12 40

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 86	95.24 33	94.49 45	82.43 28	88.90 32	96.35 29	71.89 38	98.63 26	88.76 50	96.40 6	96.06 41

SD-MVS		87.49 28	87.49 31	87.50 42	93.60 56	68.82 69	93.90 76	92.63 123	76.86 119	87.90 37	95.76 43	66.17 69	97.63 58	89.06 48	91.48 78	96.05 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
PHI-MVS		86.83 39	86.85 41	86.78 63	93.47 62	65.55 156	95.39 30	95.10 23	71.77 217	85.69 58	96.52 24	62.07 124	98.77 23	86.06 76	95.60 12	96.03 43

APDe-MVS		87.54 27	87.84 26	86.65 66	96.07 23	66.30 138	94.84 45	93.78 67	69.35 261	88.39 34	96.34 30	67.74 57	97.66 56	90.62 39	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lupinMVS		87.74 25	87.77 27	87.63 38	89.24 175	71.18 24	96.57 12	92.90 111	82.70 26	87.13 42	95.27 61	64.99 81	95.80 156	89.34 44	91.80 72	95.93 45

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 63	96.38 15	94.64 40	84.42 12	86.74 47	96.20 33	66.56 66	98.76 24	89.03 49	94.56 34	95.92 46

SMA-MVS		88.14 18	88.29 22	87.67 33	93.21 67	68.72 72	93.85 79	94.03 63	74.18 154	91.74 12	96.67 22	65.61 76	98.42 33	89.24 46	96.08 7	95.88 47
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
dcpmvs_2		87.37 31	87.55 30	86.85 58	95.04 32	68.20 87	90.36 234	90.66 208	79.37 76	81.20 101	93.67 112	74.73 16	96.55 125	90.88 37	92.00 69	95.82 48

Anonymous202405211		77.96 210	75.33 228	85.87 92	93.73 53	64.52 175	94.85 44	85.36 340	62.52 324	76.11 162	90.18 184	29.43 376	97.29 78	68.51 227	77.24 223	95.81 49

RRT-MVS		82.61 125	81.16 132	86.96 57	91.10 133	68.75 70	87.70 289	92.20 138	76.97 117	72.68 197	87.10 234	51.30 250	96.41 132	83.56 101	87.84 117	95.74 50

mvs_anonymous		81.36 145	79.99 156	85.46 106	90.39 147	68.40 78	86.88 301	90.61 210	74.41 149	70.31 233	84.67 260	63.79 98	92.32 292	73.13 179	85.70 141	95.67 51

MG-MVS		87.11 34	86.27 46	89.62 8	97.79 1	76.27 4	94.96 43	94.49 45	78.74 92	83.87 77	92.94 126	64.34 91	96.94 109	75.19 165	94.09 38	95.66 52

PAPR		85.15 72	84.47 79	87.18 49	96.02 25	68.29 81	91.85 172	93.00 108	76.59 126	79.03 131	95.00 70	61.59 129	97.61 60	78.16 148	89.00 105	95.63 53

VDD-MVS		83.06 116	81.81 127	86.81 61	90.86 139	67.70 99	95.40 29	91.50 176	75.46 137	81.78 95	92.34 142	40.09 322	97.13 92	86.85 70	82.04 177	95.60 54

casdiffmvs_mvg		85.66 63	85.18 69	87.09 52	88.22 202	69.35 58	93.74 88	91.89 155	81.47 39	80.10 117	91.45 161	64.80 86	96.35 134	87.23 65	87.69 119	95.58 55
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Effi-MVS+		83.82 100	82.76 113	86.99 56	89.56 163	69.40 53	91.35 195	86.12 332	72.59 188	83.22 83	92.81 132	59.60 150	96.01 153	81.76 114	87.80 118	95.56 56

TSAR-MVS + MP.		88.11 20	88.64 18	86.54 72	91.73 115	68.04 90	90.36 234	93.55 81	82.89 23	91.29 16	92.89 128	72.27 35	96.03 151	87.99 54	94.77 26	95.54 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
UBG		86.83 39	86.70 42	87.20 48	93.07 73	69.81 46	93.43 105	95.56 13	81.52 38	81.50 97	92.12 147	73.58 26	96.28 136	84.37 92	85.20 144	95.51 58

SteuartSystems-ACMMP		86.82 41	86.90 39	86.58 70	90.42 145	66.38 135	96.09 17	93.87 65	77.73 106	84.01 76	95.66 45	63.39 107	97.94 40	87.40 62	93.55 50	95.42 59
Skip Steuart: Steuart Systems R&D Blog.
SPE-MVS-test		86.14 52	87.01 36	83.52 177	92.63 87	59.36 304	95.49 27	91.92 152	80.09 62	85.46 61	95.53 51	61.82 128	95.77 159	86.77 71	93.37 52	95.41 60

casdiffmvs		85.37 68	84.87 75	86.84 59	88.25 200	69.07 62	93.04 116	91.76 162	81.27 46	80.84 108	92.07 149	64.23 92	96.06 149	84.98 85	87.43 123	95.39 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EIA-MVS		84.84 78	84.88 74	84.69 137	91.30 129	62.36 241	93.85 79	92.04 145	79.45 73	79.33 128	94.28 98	62.42 120	96.35 134	80.05 130	91.25 83	95.38 62

testing91		85.93 56	85.31 67	87.78 32	93.59 57	71.47 19	93.50 100	95.08 26	80.26 58	80.53 112	91.93 152	70.43 43	96.51 127	80.32 129	82.13 176	95.37 63

CS-MVS		85.80 59	86.65 44	83.27 186	92.00 106	58.92 308	95.31 31	91.86 157	79.97 63	84.82 67	95.40 54	62.26 122	95.51 177	86.11 75	92.08 68	95.37 63

GG-mvs-BLEND				86.53 73	91.91 110	69.67 52	75.02 378	94.75 34		78.67 139	90.85 171	77.91 7	94.56 210	72.25 191	93.74 45	95.36 65

agg_prior2														86.41 72	94.75 30	95.33 66

3Dnovator+	73.60 7	82.10 134	80.60 148	86.60 68	90.89 138	66.80 126	95.20 34	93.44 87	74.05 156	67.42 273	92.49 137	49.46 266	97.65 57	70.80 204	91.68 74	95.33 66

baseline		85.01 75	84.44 80	86.71 64	88.33 197	68.73 71	90.24 239	91.82 161	81.05 49	81.18 102	92.50 135	63.69 100	96.08 148	84.45 91	86.71 133	95.32 68

ab-mvs		80.18 167	78.31 182	85.80 96	88.44 192	65.49 159	83.00 331	92.67 119	71.82 215	77.36 151	85.01 256	54.50 212	96.59 121	76.35 158	75.63 232	95.32 68

test9_res														89.41 42	94.96 19	95.29 70

EPNet		87.84 24	88.38 20	86.23 82	93.30 64	66.05 142	95.26 32	94.84 30	87.09 5	88.06 35	94.53 84	66.79 63	97.34 75	83.89 97	91.68 74	95.29 70
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SF-MVS		87.03 35	87.09 35	86.84 59	92.70 85	67.45 108	93.64 92	93.76 70	70.78 245	86.25 49	96.44 27	66.98 61	97.79 47	88.68 51	94.56 34	95.28 72

VDDNet		80.50 160	78.26 183	87.21 47	86.19 248	69.79 47	94.48 50	91.31 182	60.42 340	79.34 127	90.91 170	38.48 330	96.56 124	82.16 111	81.05 186	95.27 73

MVSFormer		83.75 103	82.88 111	86.37 78	89.24 175	71.18 24	89.07 266	90.69 205	65.80 293	87.13 42	94.34 94	64.99 81	92.67 277	72.83 182	91.80 72	95.27 73

jason		86.40 46	86.17 50	87.11 51	86.16 250	70.54 32	95.71 24	92.19 140	82.00 33	84.58 69	94.34 94	61.86 126	95.53 176	87.76 56	90.89 86	95.27 73
jason: jason.
train_agg		87.21 33	87.42 32	86.60 68	94.18 41	67.28 110	94.16 60	93.51 82	71.87 212	85.52 59	95.33 56	68.19 52	97.27 82	89.09 47	94.90 22	95.25 76

MVS_Test		84.16 94	83.20 103	87.05 54	91.56 120	69.82 45	89.99 248	92.05 144	77.77 105	82.84 86	86.57 240	63.93 96	96.09 145	74.91 170	89.18 102	95.25 76

3Dnovator	73.91 6	82.69 124	80.82 141	88.31 26	89.57 162	71.26 22	92.60 138	94.39 52	78.84 89	67.89 266	92.48 138	48.42 276	98.52 28	68.80 225	94.40 36	95.15 78

testing99		86.01 54	85.47 63	87.63 38	93.62 55	71.25 23	93.47 103	95.23 19	80.42 56	80.60 111	91.95 151	71.73 39	96.50 128	80.02 131	82.22 174	95.13 79

Patchmatch-test		65.86 331	60.94 346	80.62 254	83.75 291	58.83 309	58.91 409	75.26 383	44.50 397	50.95 374	77.09 349	58.81 162	87.90 346	35.13 388	64.03 318	95.12 80

mvsmamba		81.55 142	80.72 143	84.03 163	91.42 124	66.93 122	83.08 328	89.13 270	78.55 94	67.50 271	87.02 235	51.79 243	90.07 331	87.48 60	90.49 92	95.10 81

APD-MVS		85.93 56	85.99 54	85.76 98	95.98 26	65.21 163	93.59 95	92.58 125	66.54 288	86.17 52	95.88 41	63.83 97	97.00 99	86.39 73	92.94 57	95.06 82
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
gg-mvs-nofinetune		77.18 221	74.31 242	85.80 96	91.42 124	68.36 79	71.78 383	94.72 35	49.61 383	77.12 154	45.92 409	77.41 8	93.98 238	67.62 235	93.16 55	95.05 83

test_prior				86.42 76	94.71 35	67.35 109		93.10 103					96.84 115			95.05 83

Patchmatch-RL test		68.17 317	64.49 328	79.19 286	71.22 385	53.93 347	70.07 388	71.54 394	69.22 263	56.79 351	62.89 396	56.58 190	88.61 338	69.53 215	52.61 373	95.03 85

CHOSEN 1792x2688		84.98 76	83.45 94	89.57 11	89.94 155	75.14 6	92.07 159	92.32 131	81.87 34	75.68 166	88.27 209	60.18 142	98.60 27	80.46 127	90.27 94	94.96 86

test_fmvsmconf_n		86.58 44	87.17 34	84.82 128	85.28 265	62.55 237	94.26 58	89.78 241	83.81 17	87.78 38	96.33 31	65.33 78	96.98 103	94.40 11	87.55 121	94.95 87

ACMMP_NAP		86.05 53	85.80 58	86.80 62	91.58 119	67.53 105	91.79 174	93.49 85	74.93 145	84.61 68	95.30 58	59.42 152	97.92 41	86.13 74	94.92 20	94.94 88

test2506		83.29 111	82.92 110	84.37 151	88.39 195	63.18 223	92.01 162	91.35 181	77.66 108	78.49 140	91.42 162	64.58 89	95.09 188	73.19 178	89.23 100	94.85 89

ECVR-MVS		81.29 146	80.38 152	84.01 164	88.39 195	61.96 250	92.56 143	86.79 324	77.66 108	76.63 158	91.42 162	46.34 294	95.24 185	74.36 174	89.23 100	94.85 89

PAPM_NR		82.97 118	81.84 126	86.37 78	94.10 44	66.76 127	87.66 290	92.84 112	69.96 254	74.07 185	93.57 115	63.10 114	97.50 66	70.66 207	90.58 90	94.85 89

ETVMVS		84.22 92	83.71 86	85.76 98	92.58 89	68.25 85	92.45 145	95.53 15	79.54 72	79.46 125	91.64 159	70.29 44	94.18 225	69.16 220	82.76 170	94.84 92

CDPH-MVS		85.71 61	85.46 64	86.46 74	94.75 34	67.19 112	93.89 77	92.83 113	70.90 241	83.09 84	95.28 59	63.62 102	97.36 73	80.63 125	94.18 37	94.84 92

test12				87.09 52	94.60 36	68.86 67		92.91 110		82.67 91		65.44 77	97.55 64		93.69 48	94.84 92

testing11		86.71 43	86.44 45	87.55 40	93.54 59	71.35 21	93.65 91	95.58 11	81.36 45	80.69 109	92.21 146	72.30 34	96.46 130	85.18 82	83.43 162	94.82 95

testing222		85.18 71	84.69 78	86.63 67	92.91 77	69.91 42	92.61 137	95.80 9	80.31 57	80.38 114	92.27 143	68.73 49	95.19 186	75.94 159	83.27 164	94.81 96

BP-MVS1		86.54 45	86.68 43	86.13 85	87.80 215	67.18 114	92.97 119	95.62 10	79.92 64	82.84 86	94.14 102	74.95 15	96.46 130	82.91 106	88.96 106	94.74 97

PatchmatchNet		77.46 217	74.63 235	85.96 89	89.55 164	70.35 34	79.97 357	89.55 251	72.23 200	70.94 223	76.91 351	57.03 179	92.79 272	54.27 318	81.17 185	94.74 97
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		78.49 202	75.98 219	86.02 87	91.21 131	69.68 51	80.23 352	91.20 187	75.25 141	72.48 204	78.11 339	54.65 211	93.69 248	57.66 307	83.04 165	94.69 99

GSMVS																94.68 100

sam_mvs1												57.85 171				94.68 100

SCA		75.82 246	72.76 262	85.01 123	86.63 240	70.08 37	81.06 345	89.19 265	71.60 226	70.01 236	77.09 349	45.53 300	90.25 323	60.43 293	73.27 247	94.68 100

fmvsm_l_conf0.5_n		87.49 28	88.19 23	85.39 109	86.95 234	64.37 185	94.30 56	88.45 297	80.51 53	92.70 4	96.86 15	69.98 46	97.15 91	95.83 4	88.08 115	94.65 103

Vis-MVSNet		80.92 154	79.98 157	83.74 168	88.48 190	61.80 252	93.44 104	88.26 305	73.96 160	77.73 145	91.76 155	49.94 261	94.76 197	65.84 255	90.37 93	94.65 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvsmconf0.1_n		85.71 61	86.08 53	84.62 142	80.83 320	62.33 242	93.84 82	88.81 285	83.50 19	87.00 45	96.01 39	63.36 108	96.93 111	94.04 13	87.29 124	94.61 105

fmvsm_l_conf0.5_n_a		87.44 30	88.15 24	85.30 113	87.10 231	64.19 192	94.41 52	88.14 306	80.24 61	92.54 5	96.97 10	69.52 48	97.17 87	95.89 3	88.51 110	94.56 106

旧先验1					91.94 107	60.74 276		91.50 176			94.36 89	65.23 79			91.84 71	94.55 107

sss		82.71 123	82.38 120	83.73 170	89.25 172	59.58 299	92.24 150	94.89 29	77.96 100	79.86 120	92.38 140	56.70 187	97.05 94	77.26 153	80.86 188	94.55 107

xiu_mvs_v2_base		87.92 23	87.38 33	89.55 12	91.41 127	76.43 3	95.74 21	93.12 102	83.53 18	89.55 29	95.95 40	53.45 230	97.68 51	91.07 35	92.62 60	94.54 109

PS-MVSNAJ		88.14 18	87.61 29	89.71 7	92.06 101	76.72 1	95.75 20	93.26 94	83.86 15	89.55 29	96.06 38	53.55 226	97.89 43	91.10 34	93.31 53	94.54 109

test1111		80.84 155	80.02 154	83.33 184	87.87 211	60.76 274	92.62 136	86.86 323	77.86 103	75.73 165	91.39 164	46.35 293	94.70 203	72.79 184	88.68 109	94.52 111

ZNCC-MVS		85.33 69	85.08 71	86.06 86	93.09 72	65.65 152	93.89 77	93.41 90	73.75 165	79.94 119	94.68 81	60.61 139	98.03 38	82.63 109	93.72 46	94.52 111

MAR-MVS		84.18 93	83.43 95	86.44 75	96.25 21	65.93 147	94.28 57	94.27 57	74.41 149	79.16 130	95.61 47	53.99 221	98.88 22	69.62 214	93.26 54	94.50 113
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
HFP-MVS		84.73 80	84.40 81	85.72 100	93.75 52	65.01 169	93.50 100	93.19 98	72.19 201	79.22 129	94.93 73	59.04 159	97.67 53	81.55 115	92.21 64	94.49 114

ETV-MVS		86.01 54	86.11 51	85.70 101	90.21 150	67.02 120	93.43 105	91.92 152	81.21 47	84.13 75	94.07 105	60.93 136	95.63 167	89.28 45	89.81 96	94.46 115

reproduce-ours		83.51 107	83.33 101	84.06 159	92.18 98	60.49 283	90.74 220	92.04 145	64.35 303	83.24 80	95.59 49	59.05 157	97.27 82	83.61 99	89.17 103	94.41 116

our_new_method		83.51 107	83.33 101	84.06 159	92.18 98	60.49 283	90.74 220	92.04 145	64.35 303	83.24 80	95.59 49	59.05 157	97.27 82	83.61 99	89.17 103	94.41 116

diffmvs		84.28 88	83.83 85	85.61 103	87.40 224	68.02 91	90.88 214	89.24 262	80.54 52	81.64 96	92.52 134	59.83 147	94.52 213	87.32 63	85.11 145	94.29 118
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
reproduce_model		83.15 114	82.96 107	83.73 170	92.02 102	59.74 296	90.37 233	92.08 143	63.70 310	82.86 85	95.48 52	58.62 163	97.17 87	83.06 105	88.42 111	94.26 119

test_fmvsm_n_1920		87.69 26	88.50 19	85.27 115	87.05 233	63.55 212	93.69 89	91.08 196	84.18 13	90.17 24	97.04 8	67.58 58	97.99 39	95.72 5	90.03 95	94.26 119

region2R		84.36 86	84.03 84	85.36 111	93.54 59	64.31 188	93.43 105	92.95 109	72.16 204	78.86 136	94.84 77	56.97 183	97.53 65	81.38 119	92.11 67	94.24 121

test_fmvsmconf0.01_n		83.70 105	83.52 89	84.25 156	75.26 373	61.72 256	92.17 152	87.24 320	82.36 29	84.91 66	95.41 53	55.60 201	96.83 116	92.85 20	85.87 140	94.21 122

GDP-MVS		85.54 66	85.32 66	86.18 83	87.64 218	67.95 94	92.91 123	92.36 130	77.81 104	83.69 78	94.31 96	72.84 29	96.41 132	80.39 128	85.95 139	94.19 123

MTAPA		83.91 98	83.38 99	85.50 105	91.89 111	65.16 165	81.75 337	92.23 134	75.32 140	80.53 112	95.21 66	56.06 197	97.16 90	84.86 87	92.55 62	94.18 124

PMMVS		81.98 136	82.04 123	81.78 225	89.76 159	56.17 334	91.13 207	90.69 205	77.96 100	80.09 118	93.57 115	46.33 295	94.99 191	81.41 118	87.46 122	94.17 125

CostFormer		82.33 128	81.15 133	85.86 93	89.01 180	68.46 77	82.39 334	93.01 106	75.59 135	80.25 116	81.57 298	72.03 37	94.96 192	79.06 140	77.48 219	94.16 126

MVS_111021_HR		86.19 51	85.80 58	87.37 44	93.17 69	69.79 47	93.99 71	93.76 70	79.08 84	78.88 135	93.99 106	62.25 123	98.15 36	85.93 77	91.15 84	94.15 127

PVSNet_Blended		86.73 42	86.86 40	86.31 81	93.76 50	67.53 105	96.33 16	93.61 78	82.34 30	81.00 106	93.08 122	63.19 111	97.29 78	87.08 67	91.38 80	94.13 128

1112_ss		80.56 159	79.83 159	82.77 195	88.65 187	60.78 272	92.29 148	88.36 299	72.58 189	72.46 205	94.95 71	65.09 80	93.42 254	66.38 249	77.71 213	94.10 129

IB-MVS	77.80 4	82.18 130	80.46 151	87.35 45	89.14 177	70.28 35	95.59 26	95.17 22	78.85 88	70.19 234	85.82 249	70.66 42	97.67 53	72.19 194	66.52 295	94.09 130
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
PAPM		85.89 58	85.46 64	87.18 49	88.20 203	72.42 15	92.41 146	92.77 114	82.11 32	80.34 115	93.07 123	68.27 51	95.02 189	78.39 147	93.59 49	94.09 130

MP-MVS-pluss		85.24 70	85.13 70	85.56 104	91.42 124	65.59 154	91.54 184	92.51 127	74.56 148	80.62 110	95.64 46	59.15 156	97.00 99	86.94 69	93.80 43	94.07 132
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		85.02 74	84.97 73	85.17 119	92.60 88	64.27 190	93.24 109	92.27 133	73.13 176	79.63 123	94.43 87	61.90 125	97.17 87	85.00 84	92.56 61	94.06 133
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS	77.85 3	85.52 67	85.24 68	86.37 78	88.80 185	66.64 129	92.15 153	93.68 76	81.07 48	76.91 157	93.64 113	62.59 119	98.44 31	85.50 78	92.84 59	94.03 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMPR		84.37 85	84.06 83	85.28 114	93.56 58	64.37 185	93.50 100	93.15 100	72.19 201	78.85 137	94.86 76	56.69 188	97.45 67	81.55 115	92.20 65	94.02 135

无先验							92.71 130	92.61 124	62.03 329				97.01 98	66.63 244		93.97 136

XVS		83.87 99	83.47 93	85.05 121	93.22 65	63.78 199	92.92 121	92.66 120	73.99 157	78.18 141	94.31 96	55.25 203	97.41 70	79.16 138	91.58 76	93.95 137

X-MVStestdata		76.86 227	74.13 246	85.05 121	93.22 65	63.78 199	92.92 121	92.66 120	73.99 157	78.18 141	10.19 424	55.25 203	97.41 70	79.16 138	91.58 76	93.95 137

h-mvs33		83.01 117	82.56 117	84.35 152	89.34 167	62.02 248	92.72 129	93.76 70	81.45 40	82.73 89	92.25 145	60.11 143	97.13 92	87.69 57	62.96 323	93.91 139

CP-MVS		83.71 104	83.40 98	84.65 139	93.14 70	63.84 197	94.59 49	92.28 132	71.03 239	77.41 150	94.92 74	55.21 206	96.19 140	81.32 120	90.70 88	93.91 139

PVSNet	73.49 8	80.05 170	78.63 178	84.31 153	90.92 137	64.97 170	92.47 144	91.05 199	79.18 80	72.43 206	90.51 176	37.05 347	94.06 231	68.06 229	86.00 138	93.90 141

GST-MVS		84.63 82	84.29 82	85.66 102	92.82 81	65.27 161	93.04 116	93.13 101	73.20 174	78.89 132	94.18 101	59.41 153	97.85 45	81.45 117	92.48 63	93.86 142

Test_1112_low_res		79.56 178	78.60 179	82.43 204	88.24 201	60.39 287	92.09 157	87.99 310	72.10 205	71.84 213	87.42 227	64.62 88	93.04 258	65.80 256	77.30 221	93.85 143

GeoE		78.90 191	77.43 196	83.29 185	88.95 181	62.02 248	92.31 147	86.23 330	70.24 251	71.34 222	89.27 197	54.43 216	94.04 234	63.31 275	80.81 190	93.81 144

thisisatest0515		83.41 109	82.49 118	86.16 84	89.46 166	68.26 83	93.54 97	94.70 37	74.31 152	75.75 164	90.92 169	72.62 31	96.52 126	69.64 212	81.50 183	93.71 145

HyFIR lowres test		81.03 152	79.56 163	85.43 107	87.81 214	68.11 89	90.18 240	90.01 236	70.65 247	72.95 194	86.06 247	63.61 103	94.50 214	75.01 168	79.75 197	93.67 146

CANet_DTU		84.09 95	83.52 89	85.81 95	90.30 148	66.82 124	91.87 170	89.01 277	85.27 9	86.09 53	93.74 110	47.71 285	96.98 103	77.90 150	89.78 98	93.65 147

mPP-MVS		82.96 119	82.44 119	84.52 145	92.83 79	62.92 230	92.76 127	91.85 159	71.52 229	75.61 169	94.24 99	53.48 229	96.99 102	78.97 141	90.73 87	93.64 148

tpmrst		80.57 158	79.14 173	84.84 127	90.10 152	68.28 82	81.70 338	89.72 248	77.63 110	75.96 163	79.54 330	64.94 83	92.71 274	75.43 163	77.28 222	93.55 149

tpm2		79.80 175	77.95 189	85.34 112	88.28 198	68.26 83	81.56 340	91.42 179	70.11 252	77.59 149	80.50 316	67.40 59	94.26 223	67.34 237	77.35 220	93.51 150

SR-MVS		82.81 120	82.58 116	83.50 180	93.35 63	61.16 266	92.23 151	91.28 186	64.48 302	81.27 100	95.28 59	53.71 225	95.86 155	82.87 107	88.77 108	93.49 151

FA-MVS(test-final)		79.12 186	77.23 202	84.81 131	90.54 143	63.98 196	81.35 343	91.71 165	71.09 238	74.85 177	82.94 278	52.85 233	97.05 94	67.97 230	81.73 182	93.41 152

PGM-MVS		83.25 112	82.70 115	84.92 124	92.81 83	64.07 194	90.44 229	92.20 138	71.28 233	77.23 153	94.43 87	55.17 207	97.31 77	79.33 137	91.38 80	93.37 153

新几何1				84.73 134	92.32 92	64.28 189		91.46 178	59.56 347	79.77 121	92.90 127	56.95 184	96.57 123	63.40 273	92.91 58	93.34 154

HPM-MVS		83.25 112	82.95 109	84.17 157	92.25 94	62.88 232	90.91 211	91.86 157	70.30 250	77.12 154	93.96 107	56.75 186	96.28 136	82.04 112	91.34 82	93.34 154
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TESTMET0.1,1		82.41 127	81.98 125	83.72 172	88.08 204	63.74 201	92.70 131	93.77 69	79.30 77	77.61 148	87.57 225	58.19 169	94.08 229	73.91 176	86.68 134	93.33 156

IS-MVSNet		80.14 168	79.41 167	82.33 208	87.91 209	60.08 292	91.97 166	88.27 303	72.90 184	71.44 221	91.73 157	61.44 130	93.66 249	62.47 283	86.53 135	93.24 157

MonoMVSNet		76.99 225	75.08 231	82.73 196	83.32 297	63.24 219	86.47 304	86.37 326	79.08 84	66.31 285	79.30 332	49.80 264	91.72 304	79.37 135	65.70 299	93.23 158

1314		80.70 157	78.95 175	85.94 90	87.77 217	67.56 103	87.91 284	92.55 126	72.17 203	67.44 272	93.09 121	50.27 258	97.04 97	71.68 199	87.64 120	93.23 158

CDS-MVSNet		81.43 144	80.74 142	83.52 177	86.26 247	64.45 179	92.09 157	90.65 209	75.83 133	73.95 187	89.81 192	63.97 95	92.91 267	71.27 200	82.82 167	93.20 160
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		81.14 148	80.01 155	84.51 146	90.24 149	65.86 148	94.12 64	89.15 268	73.81 164	75.37 172	88.26 210	57.26 176	94.53 212	66.97 243	84.92 146	93.15 161

API-MVS		82.28 129	80.53 149	87.54 41	96.13 22	70.59 31	93.63 93	91.04 200	65.72 295	75.45 171	92.83 131	56.11 196	98.89 21	64.10 269	89.75 99	93.15 161

test222					89.77 158	61.60 258	89.55 254	89.42 256	56.83 362	77.28 152	92.43 139	52.76 234			91.14 85	93.09 163

TAMVS		80.37 163	79.45 166	83.13 190	85.14 269	63.37 216	91.23 201	90.76 204	74.81 147	72.65 199	88.49 204	60.63 138	92.95 262	69.41 216	81.95 179	93.08 164

fmvsm_s_conf0.5_n		86.39 47	86.91 38	84.82 128	87.36 226	63.54 213	94.74 47	90.02 235	82.52 27	90.14 25	96.92 13	62.93 116	97.84 46	95.28 8	82.26 172	93.07 165

testdata				81.34 235	89.02 179	57.72 319		89.84 240	58.65 351	85.32 63	94.09 103	57.03 179	93.28 255	69.34 217	90.56 91	93.03 166

tpm		78.58 200	77.03 204	83.22 188	85.94 255	64.56 174	83.21 327	91.14 192	78.31 96	73.67 188	79.68 328	64.01 94	92.09 297	66.07 253	71.26 264	93.03 166

test_fmvsmvis_n_1920		83.80 101	83.48 92	84.77 132	82.51 306	63.72 203	91.37 193	83.99 355	81.42 43	77.68 146	95.74 44	58.37 166	97.58 61	93.38 16	86.87 127	93.00 168

GA-MVS		78.33 205	76.23 215	84.65 139	83.65 293	66.30 138	91.44 185	90.14 229	76.01 131	70.32 232	84.02 268	42.50 314	94.72 200	70.98 202	77.00 224	92.94 169

BH-RMVSNet		79.46 182	77.65 192	84.89 125	91.68 117	65.66 151	93.55 96	88.09 308	72.93 181	73.37 190	91.12 168	46.20 297	96.12 143	56.28 311	85.61 143	92.91 170

fmvsm_s_conf0.5_n_a		85.75 60	86.09 52	84.72 135	85.73 259	63.58 210	93.79 85	89.32 259	81.42 43	90.21 23	96.91 14	62.41 121	97.67 53	94.48 10	80.56 191	92.90 171

APD-MVS_3200maxsize		81.64 141	81.32 131	82.59 202	92.36 91	58.74 310	91.39 190	91.01 201	63.35 314	79.72 122	94.62 83	51.82 241	96.14 142	79.71 132	87.93 116	92.89 172

fmvsm_s_conf0.1_n		85.61 64	85.93 55	84.68 138	82.95 303	63.48 215	94.03 70	89.46 253	81.69 36	89.86 26	96.74 20	61.85 127	97.75 49	94.74 9	82.01 178	92.81 173

DP-MVS Recon		82.73 121	81.65 128	85.98 88	97.31 4	67.06 117	95.15 36	91.99 149	69.08 267	76.50 161	93.89 108	54.48 215	98.20 35	70.76 205	85.66 142	92.69 174

UGNet		79.87 174	78.68 177	83.45 182	89.96 154	61.51 259	92.13 154	90.79 203	76.83 121	78.85 137	86.33 244	38.16 333	96.17 141	67.93 232	87.17 125	92.67 175
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
EPP-MVSNet		81.79 138	81.52 129	82.61 201	88.77 186	60.21 290	93.02 118	93.66 77	68.52 273	72.90 195	90.39 179	72.19 36	94.96 192	74.93 169	79.29 202	92.67 175

PVSNet_Blended_VisFu		83.97 97	83.50 91	85.39 109	90.02 153	66.59 132	93.77 86	91.73 163	77.43 114	77.08 156	89.81 192	63.77 99	96.97 106	79.67 133	88.21 113	92.60 177

MDTV_nov1_ep13_2view						59.90 294	80.13 354		67.65 279	72.79 196		54.33 218		59.83 297		92.58 178

QAPM		79.95 173	77.39 200	87.64 34	89.63 161	71.41 20	93.30 108	93.70 75	65.34 298	67.39 275	91.75 156	47.83 283	98.96 16	57.71 306	89.81 96	92.54 179

fmvsm_s_conf0.1_n_a		84.76 79	84.84 76	84.53 144	80.23 330	63.50 214	92.79 126	88.73 288	80.46 54	89.84 27	96.65 23	60.96 135	97.57 63	93.80 14	80.14 193	92.53 180

dp		75.01 257	72.09 272	83.76 167	89.28 171	66.22 141	79.96 358	89.75 243	71.16 235	67.80 268	77.19 348	51.81 242	92.54 282	50.39 329	71.44 263	92.51 181

EPNet_dtu		78.80 194	79.26 171	77.43 306	88.06 205	49.71 368	91.96 167	91.95 151	77.67 107	76.56 160	91.28 166	58.51 164	90.20 328	56.37 310	80.95 187	92.39 182
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20240529		76.84 229	74.15 245	84.88 126	91.02 134	64.95 171	93.84 82	91.09 194	53.57 371	73.00 192	87.42 227	35.91 351	97.32 76	69.14 221	72.41 256	92.36 183

Vis-MVSNet (Re-imp)		79.24 184	79.57 162	78.24 298	88.46 191	52.29 353	90.41 231	89.12 271	74.24 153	69.13 244	91.91 153	65.77 74	90.09 330	59.00 302	88.09 114	92.33 184

原ACMM1				84.42 148	93.21 67	64.27 190		93.40 91	65.39 296	79.51 124	92.50 135	58.11 170	96.69 119	65.27 263	93.96 40	92.32 185

TR-MVS		78.77 196	77.37 201	82.95 192	90.49 144	60.88 270	93.67 90	90.07 231	70.08 253	74.51 179	91.37 165	45.69 299	95.70 166	60.12 296	80.32 192	92.29 186

SR-MVS-dyc-post		81.06 151	80.70 144	82.15 216	92.02 102	58.56 312	90.90 212	90.45 212	62.76 321	78.89 132	94.46 85	51.26 251	95.61 169	78.77 144	86.77 131	92.28 187

RE-MVS-def			80.48 150		92.02 102	58.56 312	90.90 212	90.45 212	62.76 321	78.89 132	94.46 85	49.30 268		78.77 144	86.77 131	92.28 187

LCM-MVSNet-Re		72.93 276	71.84 275	76.18 320	88.49 189	48.02 376	80.07 355	70.17 396	73.96 160	52.25 366	80.09 324	49.98 260	88.24 344	67.35 236	84.23 157	92.28 187

EC-MVSNet		84.53 83	85.04 72	83.01 191	89.34 167	61.37 263	94.42 51	91.09 194	77.91 102	83.24 80	94.20 100	58.37 166	95.40 178	85.35 79	91.41 79	92.27 190

MVS_111021_LR		82.02 135	81.52 129	83.51 179	88.42 193	62.88 232	89.77 251	88.93 281	76.78 122	75.55 170	93.10 120	50.31 257	95.38 180	83.82 98	87.02 126	92.26 191

FE-MVS		75.97 243	73.02 259	84.82 128	89.78 157	65.56 155	77.44 368	91.07 197	64.55 301	72.66 198	79.85 326	46.05 298	96.69 119	54.97 315	80.82 189	92.21 192

BH-w/o		80.49 161	79.30 170	84.05 162	90.83 140	64.36 187	93.60 94	89.42 256	74.35 151	69.09 245	90.15 187	55.23 205	95.61 169	64.61 266	86.43 137	92.17 193

test_vis1_n_1920		81.66 140	82.01 124	80.64 252	82.24 308	55.09 342	94.76 46	86.87 322	81.67 37	84.40 71	94.63 82	38.17 332	94.67 204	91.98 29	83.34 163	92.16 194

UWE-MVS		80.81 156	81.01 139	80.20 262	89.33 169	57.05 328	91.91 168	94.71 36	75.67 134	75.01 175	89.37 196	63.13 113	91.44 315	67.19 240	82.80 169	92.12 195

fmvsm_s_conf0.5_n_2		85.06 73	85.60 62	83.44 183	86.92 239	60.53 282	94.41 52	87.31 318	83.30 20	88.72 33	96.72 21	54.28 219	97.75 49	94.07 12	84.68 151	92.04 196

CVMVSNet		74.04 265	74.27 243	73.33 340	85.33 263	43.94 394	89.53 256	88.39 298	54.33 370	70.37 231	90.13 188	49.17 271	84.05 371	61.83 287	79.36 200	91.99 197

tpm cat1		75.30 253	72.21 271	84.58 143	88.52 188	67.77 97	78.16 366	88.02 309	61.88 332	68.45 259	76.37 355	60.65 137	94.03 236	53.77 321	74.11 241	91.93 198

ACMMP		81.49 143	80.67 145	83.93 165	91.71 116	62.90 231	92.13 154	92.22 137	71.79 216	71.68 217	93.49 117	50.32 256	96.96 107	78.47 146	84.22 158	91.93 198
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
fmvsm_s_conf0.1_n_2		84.40 84	84.78 77	83.27 186	85.25 266	60.41 285	94.13 63	85.69 338	83.05 22	87.99 36	96.37 28	52.75 235	97.68 51	93.75 15	84.05 160	91.71 200

test-LLR		80.10 169	79.56 163	81.72 227	86.93 237	61.17 264	92.70 131	91.54 173	71.51 230	75.62 167	86.94 236	53.83 222	92.38 287	72.21 192	84.76 149	91.60 201

test-mter		79.96 172	79.38 169	81.72 227	86.93 237	61.17 264	92.70 131	91.54 173	73.85 162	75.62 167	86.94 236	49.84 263	92.38 287	72.21 192	84.76 149	91.60 201

thisisatest0530		81.15 147	80.07 153	84.39 150	88.26 199	65.63 153	91.40 188	94.62 41	71.27 234	70.93 224	89.18 198	72.47 32	96.04 150	65.62 258	76.89 225	91.49 203

AUN-MVS		78.37 203	77.43 196	81.17 238	86.60 241	57.45 324	89.46 258	91.16 189	74.11 155	74.40 180	90.49 177	55.52 202	94.57 207	74.73 173	60.43 349	91.48 204

MIMVSNet		71.64 288	68.44 301	81.23 237	81.97 312	64.44 180	73.05 380	88.80 286	69.67 258	64.59 296	74.79 364	32.79 361	87.82 348	53.99 319	76.35 228	91.42 205

hse-mvs2		81.12 150	81.11 137	81.16 239	86.52 242	57.48 323	89.40 259	91.16 189	81.45 40	82.73 89	90.49 177	60.11 143	94.58 205	87.69 57	60.41 350	91.41 206

xiu_mvs_v1_base_debu		82.16 131	81.12 134	85.26 116	86.42 243	68.72 72	92.59 140	90.44 215	73.12 177	84.20 72	94.36 89	38.04 335	95.73 161	84.12 94	86.81 128	91.33 207

xiu_mvs_v1_base		82.16 131	81.12 134	85.26 116	86.42 243	68.72 72	92.59 140	90.44 215	73.12 177	84.20 72	94.36 89	38.04 335	95.73 161	84.12 94	86.81 128	91.33 207

xiu_mvs_v1_base_debi		82.16 131	81.12 134	85.26 116	86.42 243	68.72 72	92.59 140	90.44 215	73.12 177	84.20 72	94.36 89	38.04 335	95.73 161	84.12 94	86.81 128	91.33 207

BH-untuned		78.68 197	77.08 203	83.48 181	89.84 156	63.74 201	92.70 131	88.59 294	71.57 227	66.83 282	88.65 203	51.75 244	95.39 179	59.03 301	84.77 148	91.32 210

HPM-MVS_fast		80.25 166	79.55 165	82.33 208	91.55 121	59.95 293	91.32 197	89.16 267	65.23 299	74.71 178	93.07 123	47.81 284	95.74 160	74.87 172	88.23 112	91.31 211

baseline1		81.84 137	81.03 138	84.28 155	91.60 118	66.62 130	91.08 208	91.66 170	81.87 34	74.86 176	91.67 158	69.98 46	94.92 195	71.76 197	64.75 310	91.29 212

test_cas_vis1_n_1920		80.45 162	80.61 147	79.97 271	78.25 356	57.01 330	94.04 69	88.33 300	79.06 86	82.81 88	93.70 111	38.65 327	91.63 307	90.82 38	79.81 195	91.27 213

baseline2		83.68 106	83.42 97	84.48 147	87.37 225	66.00 144	90.06 243	95.93 8	79.71 69	69.08 246	90.39 179	77.92 6	96.28 136	78.91 142	81.38 184	91.16 214

TAPA-MVS	70.22 12	74.94 258	73.53 254	79.17 287	90.40 146	52.07 354	89.19 264	89.61 250	62.69 323	70.07 235	92.67 133	48.89 275	94.32 217	38.26 382	79.97 194	91.12 215
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
AdaColmap		78.94 190	77.00 206	84.76 133	96.34 17	65.86 148	92.66 135	87.97 312	62.18 326	70.56 227	92.37 141	43.53 310	97.35 74	64.50 267	82.86 166	91.05 216

OMC-MVS		78.67 199	77.91 190	80.95 248	85.76 258	57.40 325	88.49 275	88.67 291	73.85 162	72.43 206	92.10 148	49.29 269	94.55 211	72.73 186	77.89 212	90.91 217

EI-MVSNet-Vis-set		83.77 102	83.67 87	84.06 159	92.79 84	63.56 211	91.76 177	94.81 32	79.65 70	77.87 144	94.09 103	63.35 109	97.90 42	79.35 136	79.36 200	90.74 218

cascas		78.18 206	75.77 222	85.41 108	87.14 230	69.11 61	92.96 120	91.15 191	66.71 287	70.47 228	86.07 246	37.49 341	96.48 129	70.15 210	79.80 196	90.65 219

CR-MVSNet		73.79 269	70.82 284	82.70 198	83.15 299	67.96 92	70.25 386	84.00 353	73.67 169	69.97 238	72.41 371	57.82 172	89.48 335	52.99 324	73.13 248	90.64 220

RPMNet		70.42 296	65.68 317	84.63 141	83.15 299	67.96 92	70.25 386	90.45 212	46.83 392	69.97 238	65.10 392	56.48 193	95.30 184	35.79 387	73.13 248	90.64 220

test_fmvs1		74.07 264	73.69 252	75.22 324	78.91 348	47.34 381	89.06 268	74.69 384	63.68 311	79.41 126	91.59 160	24.36 386	87.77 350	85.22 80	76.26 229	90.55 222

PCF-MVS	73.15 9	79.29 183	77.63 193	84.29 154	86.06 251	65.96 146	87.03 297	91.10 193	69.86 256	69.79 241	90.64 172	57.54 175	96.59 121	64.37 268	82.29 171	90.32 223
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_0	68.08 15	71.81 287	68.32 303	82.27 210	84.68 275	62.31 244	88.68 272	90.31 221	75.84 132	57.93 346	80.65 315	37.85 338	94.19 224	69.94 211	29.05 412	90.31 224

tttt0517		79.50 179	78.53 180	82.41 207	87.22 228	61.43 262	89.75 252	94.76 33	69.29 262	67.91 264	88.06 217	72.92 28	95.63 167	62.91 279	73.90 245	90.16 225

CPTT-MVS		79.59 177	79.16 172	80.89 250	91.54 122	59.80 295	92.10 156	88.54 296	60.42 340	72.96 193	93.28 119	48.27 277	92.80 271	78.89 143	86.50 136	90.06 226

EI-MVSNet-UG-set		83.14 115	82.96 107	83.67 175	92.28 93	63.19 222	91.38 192	94.68 38	79.22 79	76.60 159	93.75 109	62.64 118	97.76 48	78.07 149	78.01 211	90.05 227

test_fmvs1_n		72.69 283	71.92 274	74.99 327	71.15 386	47.08 383	87.34 295	75.67 379	63.48 313	78.08 143	91.17 167	20.16 398	87.87 347	84.65 89	75.57 233	90.01 228

test_vis1_n		71.63 289	70.73 285	74.31 334	69.63 392	47.29 382	86.91 299	72.11 390	63.21 317	75.18 173	90.17 185	20.40 396	85.76 362	84.59 90	74.42 239	89.87 229

dmvs_re		76.93 226	75.36 227	81.61 229	87.78 216	60.71 277	80.00 356	87.99 310	79.42 74	69.02 248	89.47 195	46.77 288	94.32 217	63.38 274	74.45 238	89.81 230

XVG-OURS-SEG-HR		74.70 260	73.08 258	79.57 281	78.25 356	57.33 326	80.49 348	87.32 316	63.22 316	68.76 254	90.12 190	44.89 306	91.59 308	70.55 208	74.09 242	89.79 231

114514_t		79.17 185	77.67 191	83.68 174	95.32 29	65.53 157	92.85 125	91.60 172	63.49 312	67.92 263	90.63 174	46.65 290	95.72 165	67.01 242	83.54 161	89.79 231

UA-Net		80.02 171	79.65 161	81.11 241	89.33 169	57.72 319	86.33 305	89.00 280	77.44 113	81.01 105	89.15 199	59.33 154	95.90 154	61.01 290	84.28 156	89.73 233

XVG-OURS		74.25 263	72.46 269	79.63 279	78.45 354	57.59 322	80.33 350	87.39 315	63.86 308	68.76 254	89.62 194	40.50 321	91.72 304	69.00 222	74.25 240	89.58 234

UniMVSNet_ETH3D		72.74 280	70.53 287	79.36 284	78.62 353	56.64 332	85.01 310	89.20 264	63.77 309	64.84 295	84.44 264	34.05 358	91.86 301	63.94 270	70.89 266	89.57 235

thres200		79.66 176	78.33 181	83.66 176	92.54 90	65.82 150	93.06 114	96.31 3	74.90 146	73.30 191	88.66 202	59.67 149	95.61 169	47.84 345	78.67 207	89.56 236

SDMVSNet		80.26 165	78.88 176	84.40 149	89.25 172	67.63 102	85.35 308	93.02 105	76.77 123	70.84 225	87.12 232	47.95 282	96.09 145	85.04 83	74.55 235	89.48 237

sd_testset		77.08 224	75.37 226	82.20 214	89.25 172	62.11 247	82.06 335	89.09 273	76.77 123	70.84 225	87.12 232	41.43 318	95.01 190	67.23 239	74.55 235	89.48 237

OpenMVS	70.45 11	78.54 201	75.92 220	86.41 77	85.93 256	71.68 18	92.74 128	92.51 127	66.49 289	64.56 297	91.96 150	43.88 309	98.10 37	54.61 316	90.65 89	89.44 239

CHOSEN 280x420		77.35 219	76.95 207	78.55 293	87.07 232	62.68 236	69.71 389	82.95 362	68.80 269	71.48 220	87.27 231	66.03 71	84.00 373	76.47 157	82.81 168	88.95 240

thres100view900		78.37 203	77.01 205	82.46 203	91.89 111	63.21 221	91.19 205	96.33 1	72.28 199	70.45 230	87.89 219	60.31 140	95.32 181	45.16 356	77.58 216	88.83 241

tfpn200view9		78.79 195	77.43 196	82.88 193	92.21 96	64.49 176	92.05 160	96.28 4	73.48 171	71.75 215	88.26 210	60.07 145	95.32 181	45.16 356	77.58 216	88.83 241

nrg030		80.93 153	79.86 158	84.13 158	83.69 292	68.83 68	93.23 110	91.20 187	75.55 136	75.06 174	88.22 213	63.04 115	94.74 199	81.88 113	66.88 292	88.82 243

PatchT		69.11 307	65.37 321	80.32 257	82.07 311	63.68 207	67.96 396	87.62 314	50.86 380	69.37 242	65.18 391	57.09 178	88.53 341	41.59 371	66.60 294	88.74 244

HQP4-MVS										74.18 181			95.61 169			88.63 245

HQP-MVS		81.14 148	80.64 146	82.64 200	87.54 220	63.66 208	94.06 65	91.70 168	79.80 66	74.18 181	90.30 181	51.63 246	95.61 169	77.63 151	78.90 204	88.63 245

tt0805		73.07 273	70.73 285	80.07 265	78.37 355	57.05 328	87.78 287	92.18 141	61.23 336	67.04 278	86.49 241	31.35 369	94.58 205	65.06 264	67.12 290	88.57 247

VPNet		78.82 193	77.53 195	82.70 198	84.52 279	66.44 134	93.93 74	92.23 134	80.46 54	72.60 200	88.38 207	49.18 270	93.13 257	72.47 190	63.97 320	88.55 248

Effi-MVS+-dtu		76.14 236	75.28 229	78.72 292	83.22 298	55.17 341	89.87 249	87.78 313	75.42 138	67.98 262	81.43 300	45.08 305	92.52 283	75.08 167	71.63 259	88.48 249

CNLPA		74.31 262	72.30 270	80.32 257	91.49 123	61.66 257	90.85 215	80.72 368	56.67 363	63.85 306	90.64 172	46.75 289	90.84 318	53.79 320	75.99 231	88.47 250

HQP_MVS		80.34 164	79.75 160	82.12 218	86.94 235	62.42 239	93.13 112	91.31 182	78.81 90	72.53 202	89.14 200	50.66 254	95.55 174	76.74 154	78.53 209	88.39 251

plane_prior5								91.31 182					95.55 174	76.74 154	78.53 209	88.39 251

VPA-MVSNet		79.03 187	78.00 187	82.11 221	85.95 253	64.48 178	93.22 111	94.66 39	75.05 144	74.04 186	84.95 257	52.17 240	93.52 251	74.90 171	67.04 291	88.32 253

CLD-MVS		82.73 121	82.35 121	83.86 166	87.90 210	67.65 101	95.45 28	92.18 141	85.06 10	72.58 201	92.27 143	52.46 238	95.78 157	84.18 93	79.06 203	88.16 254
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		77.94 211	76.44 212	82.43 204	82.60 305	64.44 180	92.01 162	91.83 160	73.59 170	70.00 237	85.82 249	54.43 216	94.76 197	69.63 213	68.02 285	88.10 255

WBMVS		81.67 139	80.98 140	83.72 172	93.07 73	69.40 53	94.33 55	93.05 104	76.84 120	72.05 211	84.14 266	74.49 19	93.88 243	72.76 185	68.09 283	87.88 256

FIs		79.47 181	79.41 167	79.67 278	85.95 253	59.40 301	91.68 181	93.94 64	78.06 99	68.96 250	88.28 208	66.61 65	91.77 303	66.20 252	74.99 234	87.82 257

Fast-Effi-MVS+-dtu		75.04 256	73.37 256	80.07 265	80.86 319	59.52 300	91.20 204	85.38 339	71.90 209	65.20 291	84.84 258	41.46 317	92.97 261	66.50 248	72.96 250	87.73 258

UniMVSNet_NR-MVSNet		78.15 207	77.55 194	79.98 269	84.46 281	60.26 288	92.25 149	93.20 97	77.50 112	68.88 251	86.61 239	66.10 70	92.13 295	66.38 249	62.55 327	87.54 259

MVSTER		82.47 126	82.05 122	83.74 168	92.68 86	69.01 64	91.90 169	93.21 95	79.83 65	72.14 209	85.71 251	74.72 17	94.72 200	75.72 161	72.49 254	87.50 260

thres600view7		78.00 208	76.66 210	82.03 223	91.93 108	63.69 206	91.30 198	96.33 1	72.43 194	70.46 229	87.89 219	60.31 140	94.92 195	42.64 368	76.64 226	87.48 261

thres400		78.68 197	77.43 196	82.43 204	92.21 96	64.49 176	92.05 160	96.28 4	73.48 171	71.75 215	88.26 210	60.07 145	95.32 181	45.16 356	77.58 216	87.48 261

TranMVSNet+NR-MVSNet		75.86 245	74.52 239	79.89 273	82.44 307	60.64 280	91.37 193	91.37 180	76.63 125	67.65 269	86.21 245	52.37 239	91.55 309	61.84 286	60.81 345	87.48 261

FC-MVSNet-test		77.99 209	78.08 186	77.70 301	84.89 274	55.51 339	90.27 237	93.75 73	76.87 118	66.80 283	87.59 224	65.71 75	90.23 327	62.89 280	73.94 243	87.37 264

DU-MVS		76.86 227	75.84 221	79.91 272	82.96 301	60.26 288	91.26 199	91.54 173	76.46 128	68.88 251	86.35 242	56.16 194	92.13 295	66.38 249	62.55 327	87.35 265

NR-MVSNet		76.05 240	74.59 236	80.44 255	82.96 301	62.18 246	90.83 216	91.73 163	77.12 116	60.96 325	86.35 242	59.28 155	91.80 302	60.74 291	61.34 342	87.35 265

FMVSNet3		77.73 214	76.04 218	82.80 194	91.20 132	68.99 65	91.87 170	91.99 149	73.35 173	67.04 278	83.19 277	56.62 189	92.14 294	59.80 298	69.34 271	87.28 267

PS-MVSNAJss		77.26 220	76.31 214	80.13 264	80.64 324	59.16 306	90.63 227	91.06 198	72.80 185	68.58 257	84.57 262	53.55 226	93.96 239	72.97 180	71.96 258	87.27 268

mvsany_test1		68.77 310	68.56 299	69.39 362	73.57 379	45.88 390	80.93 346	60.88 410	59.65 346	71.56 218	90.26 183	43.22 312	75.05 397	74.26 175	62.70 326	87.25 269

FMVSNet2		76.07 237	74.01 248	82.26 212	88.85 182	67.66 100	91.33 196	91.61 171	70.84 242	65.98 286	82.25 287	48.03 278	92.00 299	58.46 303	68.73 279	87.10 270

ADS-MVSNet2		66.90 326	63.44 334	77.26 310	88.06 205	60.70 278	68.01 394	75.56 381	57.57 354	64.48 298	69.87 381	38.68 325	84.10 370	40.87 373	67.89 286	86.97 271

ADS-MVSNet		68.54 313	64.38 330	81.03 246	88.06 205	66.90 123	68.01 394	84.02 352	57.57 354	64.48 298	69.87 381	38.68 325	89.21 337	40.87 373	67.89 286	86.97 271

WR-MVS		76.76 231	75.74 223	79.82 275	84.60 277	62.27 245	92.60 138	92.51 127	76.06 130	67.87 267	85.34 253	56.76 185	90.24 326	62.20 284	63.69 322	86.94 273

DSMNet-mixed		56.78 362	54.44 366	63.79 376	63.21 403	29.44 419	64.43 401	64.10 406	42.12 403	51.32 371	71.60 376	31.76 366	75.04 398	36.23 384	65.20 305	86.87 274

UniMVSNet (Re)		77.58 216	76.78 208	79.98 269	84.11 287	60.80 271	91.76 177	93.17 99	76.56 127	69.93 240	84.78 259	63.32 110	92.36 289	64.89 265	62.51 329	86.78 275

GBi-Net		75.65 248	73.83 250	81.10 242	88.85 182	65.11 166	90.01 245	90.32 218	70.84 242	67.04 278	80.25 321	48.03 278	91.54 310	59.80 298	69.34 271	86.64 276

test1		75.65 248	73.83 250	81.10 242	88.85 182	65.11 166	90.01 245	90.32 218	70.84 242	67.04 278	80.25 321	48.03 278	91.54 310	59.80 298	69.34 271	86.64 276

FMVSNet1		72.71 281	69.91 292	81.10 242	83.60 294	65.11 166	90.01 245	90.32 218	63.92 307	63.56 308	80.25 321	36.35 350	91.54 310	54.46 317	66.75 293	86.64 276

v2v482		77.42 218	75.65 224	82.73 196	80.38 326	67.13 116	91.85 172	90.23 226	75.09 143	69.37 242	83.39 275	53.79 224	94.44 215	71.77 196	65.00 307	86.63 279

miper_enhance_ethall		78.86 192	77.97 188	81.54 231	88.00 208	65.17 164	91.41 186	89.15 268	75.19 142	68.79 253	83.98 269	67.17 60	92.82 269	72.73 186	65.30 301	86.62 280

cl22		77.94 211	76.78 208	81.42 233	87.57 219	64.93 172	90.67 223	88.86 284	72.45 193	67.63 270	82.68 282	64.07 93	92.91 267	71.79 195	65.30 301	86.44 281

PLC	68.80 14	75.23 254	73.68 253	79.86 274	92.93 76	58.68 311	90.64 225	88.30 301	60.90 337	64.43 301	90.53 175	42.38 315	94.57 207	56.52 309	76.54 227	86.33 282
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EI-MVSNet		78.97 189	78.22 184	81.25 236	85.33 263	62.73 235	89.53 256	93.21 95	72.39 196	72.14 209	90.13 188	60.99 133	94.72 200	67.73 234	72.49 254	86.29 283

IterMVS-LS		76.49 233	75.18 230	80.43 256	84.49 280	62.74 234	90.64 225	88.80 286	72.40 195	65.16 292	81.72 294	60.98 134	92.27 293	67.74 233	64.65 312	86.29 283
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		77.60 215	76.44 212	81.09 245	85.70 260	64.41 183	90.65 224	88.64 293	72.31 197	67.37 276	82.52 283	64.77 87	92.64 280	70.67 206	65.30 301	86.24 285

OPM-MVS		79.00 188	78.09 185	81.73 226	83.52 295	63.83 198	91.64 183	90.30 222	76.36 129	71.97 212	89.93 191	46.30 296	95.17 187	75.10 166	77.70 214	86.19 286
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DIV-MVS_self_test		76.07 237	74.67 233	80.28 259	85.14 269	61.75 255	90.12 241	88.73 288	71.16 235	65.42 290	81.60 297	61.15 131	92.94 266	66.54 246	62.16 333	86.14 287

eth_miper_zixun_eth		75.96 244	74.40 241	80.66 251	84.66 276	63.02 225	89.28 261	88.27 303	71.88 211	65.73 287	81.65 295	59.45 151	92.81 270	68.13 228	60.53 347	86.14 287

cl____		76.07 237	74.67 233	80.28 259	85.15 268	61.76 254	90.12 241	88.73 288	71.16 235	65.43 289	81.57 298	61.15 131	92.95 262	66.54 246	62.17 331	86.13 289

PatchMatch-RL		72.06 286	69.98 289	78.28 296	89.51 165	55.70 338	83.49 320	83.39 360	61.24 335	63.72 307	82.76 280	34.77 355	93.03 259	53.37 323	77.59 215	86.12 290

c3_l		76.83 230	75.47 225	80.93 249	85.02 272	64.18 193	90.39 232	88.11 307	71.66 220	66.65 284	81.64 296	63.58 106	92.56 281	69.31 218	62.86 324	86.04 291

RPSCF		64.24 341	61.98 343	71.01 358	76.10 370	45.00 391	75.83 375	75.94 378	46.94 391	58.96 338	84.59 261	31.40 368	82.00 387	47.76 346	60.33 351	86.04 291

Anonymous20231211		73.08 272	70.39 288	81.13 240	90.62 142	63.33 217	91.40 188	90.06 233	51.84 376	64.46 300	80.67 314	36.49 349	94.07 230	63.83 271	64.17 316	85.98 293

v1192		75.98 242	73.92 249	82.15 216	79.73 334	66.24 140	91.22 202	89.75 243	72.67 187	68.49 258	81.42 301	49.86 262	94.27 221	67.08 241	65.02 306	85.95 294

JIA-IIPM		66.06 330	62.45 340	76.88 315	81.42 317	54.45 346	57.49 410	88.67 291	49.36 384	63.86 305	46.86 408	56.06 197	90.25 323	49.53 334	68.83 277	85.95 294

v1921920		75.63 250	73.49 255	82.06 222	79.38 339	66.35 136	91.07 210	89.48 252	71.98 206	67.99 261	81.22 306	49.16 272	93.90 242	66.56 245	64.56 313	85.92 296

reproduce_monomvs		79.49 180	79.11 174	80.64 252	92.91 77	61.47 261	91.17 206	93.28 93	83.09 21	64.04 303	82.38 285	66.19 68	94.57 207	81.19 122	57.71 358	85.88 297

v1144		76.73 232	74.88 232	82.27 210	80.23 330	66.60 131	91.68 181	90.21 228	73.69 167	69.06 247	81.89 291	52.73 236	94.40 216	69.21 219	65.23 304	85.80 298

v144192		76.05 240	74.03 247	82.12 218	79.50 338	66.55 133	91.39 190	89.71 249	72.30 198	68.17 260	81.33 303	51.75 244	94.03 236	67.94 231	64.19 315	85.77 299

v1240		75.21 255	72.98 260	81.88 224	79.20 341	66.00 144	90.75 219	89.11 272	71.63 225	67.41 274	81.22 306	47.36 286	93.87 244	65.46 261	64.72 311	85.77 299

v148		76.19 235	74.47 240	81.36 234	80.05 332	64.44 180	91.75 179	90.23 226	73.68 168	67.13 277	80.84 311	55.92 199	93.86 246	68.95 223	61.73 338	85.76 301

test0.0.03 1		72.76 279	72.71 265	72.88 344	80.25 329	47.99 377	91.22 202	89.45 254	71.51 230	62.51 320	87.66 222	53.83 222	85.06 367	50.16 331	67.84 288	85.58 302

test_djsdf		73.76 270	72.56 267	77.39 307	77.00 366	53.93 347	89.07 266	90.69 205	65.80 293	63.92 304	82.03 290	43.14 313	92.67 277	72.83 182	68.53 280	85.57 303

dmvs_testset		65.55 334	66.45 310	62.86 378	79.87 333	22.35 424	76.55 370	71.74 392	77.42 115	55.85 353	87.77 221	51.39 248	80.69 391	31.51 403	65.92 298	85.55 304

ACMM	69.62 13	74.34 261	72.73 264	79.17 287	84.25 286	57.87 317	90.36 234	89.93 237	63.17 318	65.64 288	86.04 248	37.79 339	94.10 227	65.89 254	71.52 261	85.55 304
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs5		73.35 271	71.52 278	78.86 291	78.64 352	60.61 281	91.08 208	86.90 321	67.69 277	63.32 310	83.64 271	44.33 308	90.53 320	62.04 285	66.02 297	85.46 306

jajsoiax		73.05 274	71.51 279	77.67 302	77.46 363	54.83 343	88.81 270	90.04 234	69.13 266	62.85 317	83.51 273	31.16 370	92.75 273	70.83 203	69.80 267	85.43 307

ACMP	71.68 10	75.58 251	74.23 244	79.62 280	84.97 273	59.64 297	90.80 217	89.07 275	70.39 249	62.95 315	87.30 229	38.28 331	93.87 244	72.89 181	71.45 262	85.36 308
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
mvs_tets		72.71 281	71.11 280	77.52 303	77.41 364	54.52 345	88.45 276	89.76 242	68.76 271	62.70 318	83.26 276	29.49 375	92.71 274	70.51 209	69.62 269	85.34 309

tpmvs		72.88 278	69.76 294	82.22 213	90.98 135	67.05 118	78.22 365	88.30 301	63.10 319	64.35 302	74.98 362	55.09 208	94.27 221	43.25 362	69.57 270	85.34 309

miper_lstm_enhance		73.05 274	71.73 277	77.03 311	83.80 290	58.32 314	81.76 336	88.88 282	69.80 257	61.01 324	78.23 338	57.19 177	87.51 354	65.34 262	59.53 352	85.27 311

LPG-MVS_test		75.82 246	74.58 237	79.56 282	84.31 284	59.37 302	90.44 229	89.73 246	69.49 259	64.86 293	88.42 205	38.65 327	94.30 219	72.56 188	72.76 251	85.01 312

LGP-MVS_train				79.56 282	84.31 284	59.37 302		89.73 246	69.49 259	64.86 293	88.42 205	38.65 327	94.30 219	72.56 188	72.76 251	85.01 312

PVSNet_BlendedMVS		83.38 110	83.43 95	83.22 188	93.76 50	67.53 105	94.06 65	93.61 78	79.13 82	81.00 106	85.14 255	63.19 111	97.29 78	87.08 67	73.91 244	84.83 314

V42		76.46 234	74.55 238	82.19 215	79.14 344	67.82 96	90.26 238	89.42 256	73.75 165	68.63 256	81.89 291	51.31 249	94.09 228	71.69 198	64.84 308	84.66 315

IterMVS		72.65 284	70.83 282	78.09 299	82.17 309	62.96 227	87.64 291	86.28 328	71.56 228	60.44 328	78.85 334	45.42 302	86.66 358	63.30 276	61.83 335	84.65 316
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		71.55 290	69.97 290	76.32 318	81.48 315	60.67 279	87.64 291	85.99 333	66.17 291	59.50 333	78.88 333	45.53 300	83.65 375	62.58 282	61.93 334	84.63 317

pm-mvs1		72.89 277	71.09 281	78.26 297	79.10 345	57.62 321	90.80 217	89.30 260	67.66 278	62.91 316	81.78 293	49.11 273	92.95 262	60.29 295	58.89 355	84.22 318

pmmvs4		73.92 267	71.81 276	80.25 261	79.17 342	65.24 162	87.43 293	87.26 319	67.64 280	63.46 309	83.91 270	48.96 274	91.53 313	62.94 278	65.49 300	83.96 319

v8		75.35 252	73.26 257	81.61 229	80.67 323	66.82 124	89.54 255	89.27 261	71.65 221	63.30 311	80.30 320	54.99 209	94.06 231	67.33 238	62.33 330	83.94 320

UnsupCasMVSNet_eth		65.79 332	63.10 335	73.88 336	70.71 388	50.29 366	81.09 344	89.88 239	72.58 189	49.25 380	74.77 365	32.57 363	87.43 355	55.96 312	41.04 393	83.90 321

WB-MVSnew		77.14 222	76.18 217	80.01 268	86.18 249	63.24 219	91.26 199	94.11 61	71.72 219	73.52 189	87.29 230	45.14 304	93.00 260	56.98 308	79.42 198	83.80 322

v10		74.77 259	72.54 268	81.46 232	80.33 328	66.71 128	89.15 265	89.08 274	70.94 240	63.08 314	79.86 325	52.52 237	94.04 234	65.70 257	62.17 331	83.64 323

F-COLMAP		70.66 293	68.44 301	77.32 308	86.37 246	55.91 336	88.00 282	86.32 327	56.94 361	57.28 350	88.07 216	33.58 359	92.49 284	51.02 327	68.37 281	83.55 324

lessismore_v0				73.72 338	72.93 382	47.83 378		61.72 409		45.86 389	73.76 366	28.63 379	89.81 332	47.75 347	31.37 408	83.53 325

v7n		71.31 291	68.65 298	79.28 285	76.40 368	60.77 273	86.71 302	89.45 254	64.17 306	58.77 340	78.24 337	44.59 307	93.54 250	57.76 305	61.75 337	83.52 326

Anonymous20231206		67.53 323	65.78 315	72.79 345	74.95 374	47.59 379	88.23 278	87.32 316	61.75 334	58.07 343	77.29 346	37.79 339	87.29 356	42.91 364	63.71 321	83.48 327

CP-MVSNet		70.50 295	69.91 292	72.26 349	80.71 322	51.00 362	87.23 296	90.30 222	67.84 276	59.64 332	82.69 281	50.23 259	82.30 385	51.28 326	59.28 353	83.46 328

K. test v3		63.09 346	59.61 351	73.53 339	76.26 369	49.38 372	83.27 324	77.15 376	64.35 303	47.77 385	72.32 373	28.73 377	87.79 349	49.93 333	36.69 400	83.41 329

PS-CasMVS		69.86 302	69.13 297	72.07 353	80.35 327	50.57 364	87.02 298	89.75 243	67.27 282	59.19 336	82.28 286	46.58 291	82.24 386	50.69 328	59.02 354	83.39 330

PEN-MVS		69.46 305	68.56 299	72.17 351	79.27 340	49.71 368	86.90 300	89.24 262	67.24 285	59.08 337	82.51 284	47.23 287	83.54 376	48.42 340	57.12 359	83.25 331

anonymousdsp		71.14 292	69.37 296	76.45 317	72.95 381	54.71 344	84.19 315	88.88 282	61.92 331	62.15 321	79.77 327	38.14 334	91.44 315	68.90 224	67.45 289	83.21 332

XVG-ACMP-BASELINE		68.04 318	65.53 319	75.56 322	74.06 378	52.37 352	78.43 362	85.88 334	62.03 329	58.91 339	81.21 308	20.38 397	91.15 317	60.69 292	68.18 282	83.16 333

MSDG		69.54 304	65.73 316	80.96 247	85.11 271	63.71 204	84.19 315	83.28 361	56.95 360	54.50 357	84.03 267	31.50 367	96.03 151	42.87 366	69.13 276	83.14 334

test_fmvs2		65.78 333	64.84 322	68.60 366	66.54 398	41.71 398	83.27 324	69.81 397	54.38 369	67.91 264	84.54 263	15.35 403	81.22 390	75.65 162	66.16 296	82.88 335

SixPastTwentyTwo		64.92 337	61.78 344	74.34 333	78.74 350	49.76 367	83.42 323	79.51 373	62.86 320	50.27 375	77.35 344	30.92 372	90.49 321	45.89 354	47.06 383	82.78 336

testgi		64.48 340	62.87 338	69.31 363	71.24 384	40.62 401	85.49 307	79.92 371	65.36 297	54.18 359	83.49 274	23.74 389	84.55 368	41.60 370	60.79 346	82.77 337

DTE-MVSNet		68.46 314	67.33 308	71.87 355	77.94 360	49.00 374	86.16 306	88.58 295	66.36 290	58.19 341	82.21 288	46.36 292	83.87 374	44.97 359	55.17 366	82.73 338

WR-MVS_H		70.59 294	69.94 291	72.53 346	81.03 318	51.43 358	87.35 294	92.03 148	67.38 281	60.23 330	80.70 312	55.84 200	83.45 377	46.33 352	58.58 357	82.72 339

ppachtmachnet_test		67.72 320	63.70 332	79.77 277	78.92 346	66.04 143	88.68 272	82.90 363	60.11 344	55.45 354	75.96 358	39.19 324	90.55 319	39.53 377	52.55 374	82.71 340

CL-MVSNet_self_test		69.92 300	68.09 304	75.41 323	73.25 380	55.90 337	90.05 244	89.90 238	69.96 254	61.96 323	76.54 352	51.05 252	87.64 351	49.51 335	50.59 378	82.70 341

LS3D		69.17 306	66.40 311	77.50 304	91.92 109	56.12 335	85.12 309	80.37 370	46.96 390	56.50 352	87.51 226	37.25 342	93.71 247	32.52 399	79.40 199	82.68 342

our_test_3		68.29 316	64.69 325	79.11 290	78.92 346	64.85 173	88.40 277	85.06 342	60.32 342	52.68 364	76.12 357	40.81 320	89.80 334	44.25 361	55.65 364	82.67 343

FMVSNet5		68.04 318	65.66 318	75.18 326	84.43 282	57.89 316	83.54 319	86.26 329	61.83 333	53.64 362	73.30 367	37.15 345	85.08 366	48.99 337	61.77 336	82.56 344

KD-MVS_2432*1600		69.03 308	66.37 312	77.01 312	85.56 261	61.06 267	81.44 341	90.25 224	67.27 282	58.00 344	76.53 353	54.49 213	87.63 352	48.04 342	35.77 403	82.34 345

miper_refine_blended		69.03 308	66.37 312	77.01 312	85.56 261	61.06 267	81.44 341	90.25 224	67.27 282	58.00 344	76.53 353	54.49 213	87.63 352	48.04 342	35.77 403	82.34 345

pmmvs6		67.57 322	64.76 324	76.00 321	72.82 383	53.37 349	88.71 271	86.78 325	53.19 372	57.58 349	78.03 340	35.33 354	92.41 286	55.56 313	54.88 368	82.21 347

EU-MVSNet		64.01 342	63.01 336	67.02 372	74.40 377	38.86 407	83.27 324	86.19 331	45.11 395	54.27 358	81.15 309	36.91 348	80.01 393	48.79 339	57.02 360	82.19 348

ACMH	63.93 17	68.62 311	64.81 323	80.03 267	85.22 267	63.25 218	87.72 288	84.66 346	60.83 338	51.57 370	79.43 331	27.29 382	94.96 192	41.76 369	64.84 308	81.88 349
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
D2MVS		73.80 268	72.02 273	79.15 289	79.15 343	62.97 226	88.58 274	90.07 231	72.94 180	59.22 335	78.30 336	42.31 316	92.70 276	65.59 259	72.00 257	81.79 350

DP-MVS		69.90 301	66.48 309	80.14 263	95.36 28	62.93 228	89.56 253	76.11 377	50.27 382	57.69 348	85.23 254	39.68 323	95.73 161	33.35 392	71.05 265	81.78 351

Patchmtry		67.53 323	63.93 331	78.34 294	82.12 310	64.38 184	68.72 391	84.00 353	48.23 389	59.24 334	72.41 371	57.82 172	89.27 336	46.10 353	56.68 363	81.36 352

Syy-MVS		69.65 303	69.52 295	70.03 360	87.87 211	43.21 396	88.07 280	89.01 277	72.91 182	63.11 312	88.10 214	45.28 303	85.54 363	22.07 410	69.23 274	81.32 353

myMVS_eth3d		72.58 285	72.74 263	72.10 352	87.87 211	49.45 370	88.07 280	89.01 277	72.91 182	63.11 312	88.10 214	63.63 101	85.54 363	32.73 397	69.23 274	81.32 353

Baseline_NR-MVSNet		73.99 266	72.83 261	77.48 305	80.78 321	59.29 305	91.79 174	84.55 348	68.85 268	68.99 249	80.70 312	56.16 194	92.04 298	62.67 281	60.98 344	81.11 355

CMPMVS	48.56 21	66.77 327	64.41 329	73.84 337	70.65 389	50.31 365	77.79 367	85.73 337	45.54 394	44.76 393	82.14 289	35.40 353	90.14 329	63.18 277	74.54 237	81.07 356
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TransMVSNet (Re)		70.07 299	67.66 305	77.31 309	80.62 325	59.13 307	91.78 176	84.94 344	65.97 292	60.08 331	80.44 317	50.78 253	91.87 300	48.84 338	45.46 386	80.94 357

ACMH+	65.35 16	67.65 321	64.55 326	76.96 314	84.59 278	57.10 327	88.08 279	80.79 367	58.59 352	53.00 363	81.09 310	26.63 384	92.95 262	46.51 350	61.69 340	80.82 358

USDC		67.43 325	64.51 327	76.19 319	77.94 360	55.29 340	78.38 363	85.00 343	73.17 175	48.36 383	80.37 318	21.23 394	92.48 285	52.15 325	64.02 319	80.81 359

OurMVSNet-221017-0		64.68 338	62.17 342	72.21 350	76.08 371	47.35 380	80.67 347	81.02 366	56.19 364	51.60 369	79.66 329	27.05 383	88.56 340	53.60 322	53.63 371	80.71 360

MS-PatchMatch		77.90 213	76.50 211	82.12 218	85.99 252	69.95 41	91.75 179	92.70 116	73.97 159	62.58 319	84.44 264	41.11 319	95.78 157	63.76 272	92.17 66	80.62 361

tfpnnormal		70.10 298	67.36 307	78.32 295	83.45 296	60.97 269	88.85 269	92.77 114	64.85 300	60.83 326	78.53 335	43.52 311	93.48 252	31.73 400	61.70 339	80.52 362

MIMVSNet1		60.16 357	57.33 358	68.67 365	69.71 391	44.13 393	78.92 360	84.21 349	55.05 368	44.63 394	71.85 375	23.91 388	81.54 389	32.63 398	55.03 367	80.35 363

YYNet1		63.76 345	60.14 349	74.62 330	78.06 359	60.19 291	83.46 322	83.99 355	56.18 365	39.25 402	71.56 378	37.18 344	83.34 378	42.90 365	48.70 381	80.32 364

MDA-MVSNet_test_wron		63.78 344	60.16 348	74.64 329	78.15 358	60.41 285	83.49 320	84.03 351	56.17 366	39.17 403	71.59 377	37.22 343	83.24 380	42.87 366	48.73 380	80.26 365

KD-MVS_self_test		60.87 353	58.60 353	67.68 369	66.13 399	39.93 404	75.63 377	84.70 345	57.32 358	49.57 378	68.45 386	29.55 374	82.87 381	48.09 341	47.94 382	80.25 366

ITE_SJBPF				70.43 359	74.44 376	47.06 384		77.32 375	60.16 343	54.04 360	83.53 272	23.30 390	84.01 372	43.07 363	61.58 341	80.21 367

test20.03		63.83 343	62.65 339	67.38 371	70.58 390	39.94 403	86.57 303	84.17 350	63.29 315	51.86 368	77.30 345	37.09 346	82.47 383	38.87 381	54.13 370	79.73 368

UnsupCasMVSNet_bld		61.60 350	57.71 355	73.29 341	68.73 394	51.64 356	78.61 361	89.05 276	57.20 359	46.11 386	61.96 399	28.70 378	88.60 339	50.08 332	38.90 398	79.63 369

AllTest		61.66 349	58.06 354	72.46 347	79.57 335	51.42 359	80.17 353	68.61 399	51.25 378	45.88 387	81.23 304	19.86 399	86.58 359	38.98 379	57.01 361	79.39 370

TestCases				72.46 347	79.57 335	51.42 359		68.61 399	51.25 378	45.88 387	81.23 304	19.86 399	86.58 359	38.98 379	57.01 361	79.39 370

ambc				69.61 361	61.38 408	41.35 399	49.07 415	85.86 336		50.18 377	66.40 389	10.16 412	88.14 345	45.73 355	44.20 387	79.32 372

Anonymous20240521		62.09 348	59.08 352	71.10 357	67.19 396	48.72 375	83.91 317	85.23 341	50.38 381	47.84 384	71.22 380	20.74 395	85.51 365	46.47 351	58.75 356	79.06 373

testing3		70.38 297	70.83 282	69.03 364	85.82 257	43.93 395	90.72 222	90.56 211	68.06 275	60.24 329	86.82 238	64.83 85	84.12 369	26.33 405	64.10 317	79.04 374

MVP-Stereo		77.12 223	76.23 215	79.79 276	81.72 313	66.34 137	89.29 260	90.88 202	70.56 248	62.01 322	82.88 279	49.34 267	94.13 226	65.55 260	93.80 43	78.88 375
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pmmvs-eth3d		65.53 335	62.32 341	75.19 325	69.39 393	59.59 298	82.80 332	83.43 358	62.52 324	51.30 372	72.49 369	32.86 360	87.16 357	55.32 314	50.73 377	78.83 376

OpenMVS_ROB	61.12 18	66.39 328	62.92 337	76.80 316	76.51 367	57.77 318	89.22 262	83.41 359	55.48 367	53.86 361	77.84 341	26.28 385	93.95 240	34.90 389	68.76 278	78.68 377

LTVRE_ROB	59.60 19	66.27 329	63.54 333	74.45 331	84.00 289	51.55 357	67.08 398	83.53 357	58.78 350	54.94 356	80.31 319	34.54 356	93.23 256	40.64 375	68.03 284	78.58 378
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
mmtdpeth		68.33 315	66.37 312	74.21 335	82.81 304	51.73 355	84.34 314	80.42 369	67.01 286	71.56 218	68.58 385	30.52 373	92.35 290	75.89 160	36.21 401	78.56 379

PM-MVS		59.40 358	56.59 360	67.84 367	63.63 402	41.86 397	76.76 369	63.22 407	59.01 349	51.07 373	72.27 374	11.72 410	83.25 379	61.34 288	50.28 379	78.39 380

test_fmvs3		56.82 361	54.86 365	62.69 380	53.59 413	35.47 410	75.87 374	65.64 404	43.91 398	55.10 355	71.43 379	6.91 418	74.40 400	68.64 226	52.63 372	78.20 381

mvs5depth		61.03 352	57.65 357	71.18 356	67.16 397	47.04 385	72.74 381	77.49 374	57.47 357	60.52 327	72.53 368	22.84 391	88.38 342	49.15 336	38.94 397	78.11 382

N_pmnet		50.55 369	49.11 371	54.88 388	77.17 365	4.02 432	84.36 313	2.00 430	48.59 385	45.86 389	68.82 384	32.22 364	82.80 382	31.58 401	51.38 376	77.81 383

new-patchmatchnet		59.30 359	56.48 361	67.79 368	65.86 400	44.19 392	82.47 333	81.77 364	59.94 345	43.65 397	66.20 390	27.67 381	81.68 388	39.34 378	41.40 392	77.50 384

EG-PatchMatch MVS		68.55 312	65.41 320	77.96 300	78.69 351	62.93 228	89.86 250	89.17 266	60.55 339	50.27 375	77.73 343	22.60 392	94.06 231	47.18 348	72.65 253	76.88 385

MVS-HIRNet		60.25 356	55.55 363	74.35 332	84.37 283	56.57 333	71.64 384	74.11 385	34.44 406	45.54 391	42.24 414	31.11 371	89.81 332	40.36 376	76.10 230	76.67 386

MDA-MVSNet-bldmvs		61.54 351	57.70 356	73.05 342	79.53 337	57.00 331	83.08 328	81.23 365	57.57 354	34.91 407	72.45 370	32.79 361	86.26 361	35.81 386	41.95 391	75.89 387

COLMAP_ROB	57.96 20	62.98 347	59.65 350	72.98 343	81.44 316	53.00 351	83.75 318	75.53 382	48.34 387	48.81 382	81.40 302	24.14 387	90.30 322	32.95 394	60.52 348	75.65 388
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TinyColmap		60.32 355	56.42 362	72.00 354	78.78 349	53.18 350	78.36 364	75.64 380	52.30 373	41.59 401	75.82 360	14.76 406	88.35 343	35.84 385	54.71 369	74.46 389

mamv4		65.18 336	67.43 306	58.44 382	77.88 362	49.36 373	69.40 390	70.99 395	48.31 388	57.78 347	85.53 252	59.01 160	51.88 420	73.67 177	64.32 314	74.07 390

ttmdpeth		53.34 367	49.96 370	63.45 377	62.07 407	40.04 402	72.06 382	65.64 404	42.54 402	51.88 367	77.79 342	13.94 409	76.48 396	32.93 395	30.82 411	73.84 391

MVStest1		51.35 368	46.89 372	64.74 374	65.06 401	51.10 361	67.33 397	72.58 388	30.20 410	35.30 405	74.82 363	27.70 380	69.89 405	24.44 407	24.57 414	73.22 392

mvsany_test3		48.86 371	46.35 374	56.41 384	46.00 419	31.67 415	62.26 403	47.25 420	43.71 399	45.54 391	68.15 387	10.84 411	64.44 416	57.95 304	35.44 405	73.13 393

pmmvs3		55.51 363	51.50 369	67.53 370	57.90 411	50.93 363	80.37 349	73.66 386	40.63 404	44.15 396	64.75 393	16.30 401	78.97 394	44.77 360	40.98 395	72.69 394

test_method		38.59 381	35.16 384	48.89 395	54.33 412	21.35 425	45.32 416	53.71 414	7.41 422	28.74 410	51.62 406	8.70 415	52.87 419	33.73 390	32.89 407	72.47 395

test_0402		64.54 339	61.09 345	74.92 328	84.10 288	60.75 275	87.95 283	79.71 372	52.03 374	52.41 365	77.20 347	32.21 365	91.64 306	23.14 408	61.03 343	72.36 396

LF4IMVS		54.01 366	52.12 367	59.69 381	62.41 405	39.91 405	68.59 392	68.28 401	42.96 401	44.55 395	75.18 361	14.09 408	68.39 407	41.36 372	51.68 375	70.78 397

TDRefinement		55.28 364	51.58 368	66.39 373	59.53 410	46.15 388	76.23 372	72.80 387	44.60 396	42.49 399	76.28 356	15.29 404	82.39 384	33.20 393	43.75 388	70.62 398

test_f		46.58 372	43.45 376	55.96 385	45.18 420	32.05 414	61.18 404	49.49 418	33.39 407	42.05 400	62.48 398	7.00 417	65.56 412	47.08 349	43.21 390	70.27 399

LCM-MVSNet		40.54 377	35.79 382	54.76 389	36.92 426	30.81 416	51.41 413	69.02 398	22.07 413	24.63 413	45.37 410	4.56 422	65.81 411	33.67 391	34.50 406	67.67 400

ANet_high		40.27 380	35.20 383	55.47 386	34.74 427	34.47 412	63.84 402	71.56 393	48.42 386	18.80 416	41.08 415	9.52 414	64.45 415	20.18 411	8.66 423	67.49 401

test_vis1_rt		59.09 360	57.31 359	64.43 375	68.44 395	46.02 389	83.05 330	48.63 419	51.96 375	49.57 378	63.86 395	16.30 401	80.20 392	71.21 201	62.79 325	67.07 402

kuosan		60.86 354	60.24 347	62.71 379	81.57 314	46.43 387	75.70 376	85.88 334	57.98 353	48.95 381	69.53 383	58.42 165	76.53 395	28.25 404	35.87 402	65.15 403

PMMVS2		37.93 382	33.61 385	50.92 392	46.31 418	24.76 422	60.55 407	50.05 416	28.94 412	20.93 414	47.59 407	4.41 424	65.13 413	25.14 406	18.55 418	62.87 404

new_pmnet		49.31 370	46.44 373	57.93 383	62.84 404	40.74 400	68.47 393	62.96 408	36.48 405	35.09 406	57.81 403	14.97 405	72.18 402	32.86 396	46.44 384	60.88 405

dongtai		55.18 365	55.46 364	54.34 390	76.03 372	36.88 408	76.07 373	84.61 347	51.28 377	43.41 398	64.61 394	56.56 191	67.81 408	18.09 413	28.50 413	58.32 406

FPMVS		45.64 374	43.10 378	53.23 391	51.42 416	36.46 409	64.97 400	71.91 391	29.13 411	27.53 411	61.55 400	9.83 413	65.01 414	16.00 417	55.58 365	58.22 407

WB-MVS		46.23 373	44.94 375	50.11 393	62.13 406	21.23 426	76.48 371	55.49 412	45.89 393	35.78 404	61.44 401	35.54 352	72.83 401	9.96 420	21.75 415	56.27 408

SSC-MVS		44.51 375	43.35 377	47.99 397	61.01 409	18.90 428	74.12 379	54.36 413	43.42 400	34.10 408	60.02 402	34.42 357	70.39 404	9.14 422	19.57 416	54.68 409

APD_test1		40.50 378	37.31 381	50.09 394	51.88 414	35.27 411	59.45 408	52.59 415	21.64 414	26.12 412	57.80 404	4.56 422	66.56 410	22.64 409	39.09 396	48.43 410

EGC-MVSNET		42.35 376	38.09 379	55.11 387	74.57 375	46.62 386	71.63 385	55.77 411	0.04 425	0.24 426	62.70 397	14.24 407	74.91 399	17.59 414	46.06 385	43.80 411

test_vis3_rt		40.46 379	37.79 380	48.47 396	44.49 421	33.35 413	66.56 399	32.84 427	32.39 408	29.65 409	39.13 417	3.91 425	68.65 406	50.17 330	40.99 394	43.40 412

testf1		32.77 384	29.47 387	42.67 400	41.89 423	30.81 416	52.07 411	43.45 421	15.45 417	18.52 417	44.82 411	2.12 426	58.38 417	16.05 415	30.87 409	38.83 413

APD_test2		32.77 384	29.47 387	42.67 400	41.89 423	30.81 416	52.07 411	43.45 421	15.45 417	18.52 417	44.82 411	2.12 426	58.38 417	16.05 415	30.87 409	38.83 413

MVE	24.84 23	24.35 388	19.77 394	38.09 402	34.56 428	26.92 421	26.57 418	38.87 425	11.73 421	11.37 422	27.44 418	1.37 429	50.42 421	11.41 419	14.60 419	36.93 415
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				34.71 403	51.45 415	24.73 423		28.48 429	31.46 409	17.49 419	52.75 405	5.80 420	42.60 424	18.18 412	19.42 417	36.81 416

PMVS	26.43 22	31.84 386	28.16 389	42.89 399	25.87 429	27.58 420	50.92 414	49.78 417	21.37 415	14.17 421	40.81 416	2.01 428	66.62 409	9.61 421	38.88 399	34.49 417
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		34.91 383	31.44 386	45.30 398	70.99 387	39.64 406	19.85 420	72.56 389	20.10 416	16.16 420	21.47 421	5.08 421	71.16 403	13.07 418	43.70 389	25.08 418
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		22.26 390	23.75 392	17.80 406	5.23 430	12.06 431	35.26 417	39.48 424	2.82 424	18.94 415	44.20 413	22.23 393	24.64 425	36.30 383	9.31 422	16.69 419

E-PMN		24.61 387	24.00 391	26.45 404	43.74 422	18.44 429	60.86 405	39.66 423	15.11 419	9.53 423	22.10 420	6.52 419	46.94 422	8.31 423	10.14 420	13.98 420

EMVS		23.76 389	23.20 393	25.46 405	41.52 425	16.90 430	60.56 406	38.79 426	14.62 420	8.99 424	20.24 423	7.35 416	45.82 423	7.25 424	9.46 421	13.64 421

wuyk23d		11.30 392	10.95 395	12.33 407	48.05 417	19.89 427	25.89 419	1.92 431	3.58 423	3.12 425	1.37 425	0.64 430	15.77 426	6.23 425	7.77 424	1.35 422

test123		6.92 395	9.21 398	0.08 408	0.03 432	0.05 433	81.65 339	0.01 433	0.02 427	0.14 428	0.85 427	0.03 431	0.02 427	0.12 427	0.00 426	0.16 423

testmvs		7.23 394	9.62 397	0.06 409	0.04 431	0.02 434	84.98 311	0.02 432	0.03 426	0.18 427	1.21 426	0.01 432	0.02 427	0.14 426	0.01 425	0.13 424

mmdepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

monomultidepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

test_blank		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

uanet_test		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

DCPMVS		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

cdsmvs_eth3d_5k		19.86 391	26.47 390	0.00 410	0.00 433	0.00 435	0.00 421	93.45 86	0.00 428	0.00 429	95.27 61	49.56 265	0.00 429	0.00 428	0.00 426	0.00 425

pcd_1.5k_mvsjas		4.46 396	5.95 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	53.55 226	0.00 429	0.00 428	0.00 426	0.00 425

sosnet-low-res		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

sosnet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

uncertanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

Regformer		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

ab-mvs-re		7.91 393	10.55 396	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	94.95 71	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

uanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 426	0.00 425

WAC-MVS						49.45 370								31.56 402

FOURS1					93.95 46	61.77 253	93.96 72	91.92 152	62.14 328	86.57 48

test_one_0601					96.32 18	69.74 49		94.18 58	71.42 232	90.67 19	96.85 16	74.45 20

eth-test2					0.00 433

eth-test					0.00 433

ZD-MVS					96.63 9	65.50 158		93.50 84	70.74 246	85.26 64	95.19 67	64.92 84	97.29 78	87.51 59	93.01 56

test_241102_ONE					96.45 12	69.38 55		94.44 47	71.65 221	92.11 7	97.05 7	76.79 9	99.11 6

9.14			87.63 28		93.86 48		94.41 52	94.18 58	72.76 186	86.21 50	96.51 25	66.64 64	97.88 44	90.08 41	94.04 39

save fliter					93.84 49	67.89 95	95.05 39	92.66 120	78.19 97

test0726					96.40 15	69.99 38	96.76 8	94.33 55	71.92 207	91.89 11	97.11 6	73.77 23

test_part2					96.29 19	68.16 88				90.78 17

sam_mvs												54.91 210

MTGPA								92.23 134

test_post1							78.95 359				20.70 422	53.05 231	91.50 314	60.43 293

test_post											23.01 419	56.49 192	92.67 277

patchmatchnet-post											67.62 388	57.62 174	90.25 323

MTMP							93.77 86	32.52 428

gm-plane-assit					88.42 193	67.04 119			78.62 93		91.83 154		97.37 72	76.57 156

TEST9					94.18 41	67.28 110	94.16 60	93.51 82	71.75 218	85.52 59	95.33 56	68.01 54	97.27 82

test_8					94.19 40	67.19 112	94.15 62	93.42 89	71.87 212	85.38 62	95.35 55	68.19 52	96.95 108

agg_prior					94.16 43	66.97 121		93.31 92		84.49 70			96.75 118

test_prior4						67.18 114	93.92 75

test_prior2							95.10 38		75.40 139	85.25 65	95.61 47	67.94 55		87.47 61	94.77 26

旧先验2							92.00 165		59.37 348	87.54 41			93.47 253	75.39 164

新几何2							91.41 186

原ACMM2							92.01 162

testdata2													96.09 145	61.26 289

segment_acmp												65.94 72

testdata1							89.21 263		77.55 111

plane_prior7					86.94 235	61.51 259

plane_prior6					87.23 227	62.32 243						50.66 254

plane_prior4											89.14 200

plane_prior3						61.95 251			79.09 83	72.53 202

plane_prior2							93.13 112		78.81 90

plane_prior1					87.15 229

plane_prior						62.42 239	93.85 79		79.38 75						78.80 206

n2								0.00 434

nn								0.00 434

door-mid								66.01 403

test11								93.01 106

door								66.57 402

HQP5-MVS						63.66 208

HQP-NCC					87.54 220		94.06 65		79.80 66	74.18 181

ACMP_Plane					87.54 220		94.06 65		79.80 66	74.18 181

BP-MVS														77.63 151

HQP3-MVS								91.70 168							78.90 204

HQP2-MVS												51.63 246

NP-MVS					87.41 223	63.04 224					90.30 181

MDTV_nov1_ep13			72.61 266		89.06 178	68.48 76	80.33 350	90.11 230	71.84 214	71.81 214	75.92 359	53.01 232	93.92 241	48.04 342	73.38 246

ACMMP++_ref															71.63 259

ACMMP++															69.72 268

Test By Simon												54.21 220

High-resolution multi-view benchmark