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.

CHOSEN 1792x2688		76.24 59	74.03 84	82.88 1	83.09 117	62.84 2	85.73 111	85.39 106	69.79 28	64.87 152	83.49 199	41.52 168	93.69 29	70.55 103	81.82 69	92.12 40

MG-MVS		78.42 28	76.99 45	82.73 2	93.17 1	64.46 1	89.93 29	88.51 49	64.83 92	73.52 59	88.09 135	48.07 76	92.19 54	62.24 162	84.53 52	91.53 62

LFMVS		78.52 25	77.14 43	82.67 3	89.58 13	58.90 8	91.27 19	88.05 55	63.22 122	74.63 48	90.83 75	41.38 169	94.40 20	75.42 72	79.90 91	94.72 2

DVP-MVS++		82.44 3	82.38 6	82.62 4	91.77 4	57.49 17	84.98 137	88.88 33	58.00 219	83.60 6	93.39 18	67.21 2	96.39 4	81.64 31	91.98 4	93.98 5

DPM-MVS		82.39 4	82.36 7	82.49 5	80.12 198	59.50 5	92.24 8	90.72 15	69.37 33	83.22 8	94.47 2	63.81 5	93.18 32	74.02 84	93.25 2	94.80 1

CSCG		80.41 15	79.72 16	82.49 5	89.12 25	57.67 15	89.29 41	91.54 5	59.19 195	71.82 82	90.05 95	59.72 10	96.04 10	78.37 50	88.40 14	93.75 7

SED-MVS		81.92 8	81.75 9	82.44 7	89.48 17	56.89 29	92.48 3	88.94 31	57.50 233	84.61 4	94.09 3	58.81 12	96.37 6	82.28 26	87.60 18	94.06 3

DVP-MVS		81.30 10	81.00 13	82.20 8	89.40 20	57.45 19	92.34 5	89.99 19	57.71 227	81.91 14	93.64 12	55.17 29	96.44 2	81.68 29	87.13 21	92.72 28
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				82.20 8	89.50 15	57.73 13	92.34 5	88.88 33					96.39 4	81.68 29	87.13 21	92.47 31

MCST-MVS		83.01 1	83.30 2	82.15 10	92.84 2	57.58 16	93.77 1	91.10 11	75.95 3	77.10 37	93.09 27	54.15 37	95.57 12	85.80 10	85.87 38	93.31 11

balanced_conf03		80.28 16	79.73 15	81.90 11	86.47 51	59.34 6	80.45 258	89.51 23	69.76 29	71.05 94	86.66 162	58.68 15	93.24 31	84.64 14	90.40 6	93.14 18

DELS-MVS		82.32 5	82.50 5	81.79 12	86.80 47	56.89 29	92.77 2	86.30 89	77.83 1	77.88 33	92.13 41	60.24 7	94.78 19	78.97 44	89.61 8	93.69 8
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
OPU-MVS				81.71 13	92.05 3	55.97 48	92.48 3				94.01 5	67.21 2	95.10 15	89.82 3	92.55 3	94.06 3

PS-MVSNAJ		80.06 17	79.52 18	81.68 14	85.58 63	60.97 3	91.69 12	87.02 73	70.62 22	80.75 21	93.22 24	37.77 204	92.50 46	82.75 23	86.25 35	91.57 60

MSC_two_6792asdad				81.53 15	91.77 4	56.03 46		91.10 11					96.22 8	81.46 33	86.80 28	92.34 35

No_MVS				81.53 15	91.77 4	56.03 46		91.10 11					96.22 8	81.46 33	86.80 28	92.34 35

xiu_mvs_v2_base		79.86 18	79.31 19	81.53 15	85.03 75	60.73 4	91.65 13	86.86 76	70.30 26	80.77 20	93.07 29	37.63 209	92.28 52	82.73 24	85.71 39	91.57 60

CNVR-MVS		81.76 9	81.90 8	81.33 18	90.04 10	57.70 14	91.71 11	88.87 35	70.31 25	77.64 36	93.87 7	52.58 44	93.91 26	84.17 15	87.92 16	92.39 33

MVS		76.91 49	75.48 62	81.23 19	84.56 82	55.21 65	80.23 264	91.64 4	58.65 209	65.37 144	91.48 62	45.72 104	95.05 16	72.11 98	89.52 10	93.44 9

VDDNet		74.37 87	72.13 110	81.09 20	79.58 204	56.52 37	90.02 26	86.70 80	52.61 290	71.23 90	87.20 153	31.75 289	93.96 25	74.30 82	75.77 134	92.79 27

MVSMamba_PlusPlus		75.28 76	73.39 87	80.96 21	80.85 183	58.25 10	74.47 307	87.61 66	50.53 304	65.24 145	83.41 201	57.38 18	92.83 36	73.92 86	87.13 21	91.80 54

MM		82.69 2	83.29 3	80.89 22	84.38 86	55.40 59	92.16 10	89.85 21	75.28 4	82.41 11	93.86 8	54.30 34	93.98 23	90.29 1	87.13 21	93.30 12

testing91		78.30 32	77.54 37	80.61 23	88.16 35	57.12 25	87.94 60	91.07 14	71.43 17	70.75 97	88.04 139	55.82 26	92.65 42	69.61 108	75.00 147	92.05 44

NCCC		79.57 20	79.23 20	80.59 24	89.50 15	56.99 26	91.38 16	88.17 53	67.71 48	73.81 56	92.75 32	46.88 89	93.28 30	78.79 47	84.07 55	91.50 64

dcpmvs_2		79.33 21	78.94 21	80.49 25	89.75 12	56.54 36	84.83 144	83.68 156	67.85 45	69.36 105	90.24 87	60.20 8	92.10 58	84.14 16	80.40 82	92.82 25

API-MVS		74.17 90	72.07 112	80.49 25	90.02 11	58.55 9	87.30 75	84.27 143	57.51 232	65.77 141	87.77 144	41.61 166	95.97 11	51.71 254	82.63 61	86.94 176

MVS_0304		82.10 7	82.64 4	80.47 27	86.63 49	54.69 84	92.20 9	86.66 81	74.48 5	82.63 10	93.80 9	50.83 59	93.70 28	90.11 2	86.44 33	93.01 21

testing99		78.45 26	77.78 34	80.45 28	88.28 33	56.81 32	87.95 59	91.49 6	71.72 14	70.84 96	88.09 135	57.29 19	92.63 44	69.24 111	75.13 143	91.91 49

3Dnovator	64.70 6	74.46 85	72.48 100	80.41 29	82.84 130	55.40 59	83.08 197	88.61 46	67.61 51	59.85 211	88.66 121	34.57 260	93.97 24	58.42 197	88.70 12	91.85 52

DPE-MVS		79.82 19	79.66 17	80.29 30	89.27 24	55.08 72	88.70 47	87.92 57	55.55 263	81.21 19	93.69 11	56.51 22	94.27 22	78.36 51	85.70 40	91.51 63
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MAR-MVS		76.76 54	75.60 60	80.21 31	90.87 7	54.68 85	89.14 42	89.11 28	62.95 126	70.54 102	92.33 39	41.05 170	94.95 17	57.90 208	86.55 32	91.00 79
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
SD-MVS		76.18 60	74.85 73	80.18 32	85.39 67	56.90 28	85.75 109	82.45 180	56.79 247	74.48 51	91.81 52	43.72 135	90.75 89	74.61 78	78.65 101	92.91 22
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
testing11		79.18 22	78.85 23	80.16 33	88.33 30	56.99 26	88.31 52	92.06 1	72.82 10	70.62 101	88.37 127	57.69 17	92.30 50	75.25 74	76.24 128	91.20 73

Effi-MVS+		75.24 77	73.61 86	80.16 33	81.92 148	57.42 21	85.21 126	76.71 294	60.68 170	73.32 62	89.34 108	47.30 84	91.63 65	68.28 118	79.72 93	91.42 65

SMA-MVS		79.10 23	78.76 24	80.12 35	84.42 84	55.87 49	87.58 69	86.76 78	61.48 152	80.26 23	93.10 25	46.53 94	92.41 48	79.97 38	88.77 11	92.08 41
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
MSLP-MVS++		74.21 89	72.25 106	80.11 36	81.45 169	56.47 38	86.32 96	79.65 234	58.19 215	66.36 132	92.29 40	36.11 242	90.66 91	67.39 122	82.49 63	93.18 17

CANet		80.90 11	81.17 12	80.09 37	87.62 41	54.21 96	91.60 14	86.47 85	73.13 8	79.89 25	93.10 25	49.88 68	92.98 33	84.09 17	84.75 50	93.08 19

IB-MVS	68.87 2	74.01 92	72.03 115	79.94 38	83.04 119	55.50 53	90.24 25	88.65 42	67.14 55	61.38 198	81.74 235	53.21 40	94.28 21	60.45 182	62.41 255	90.03 105
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
HPM-MVS++		80.50 14	80.71 14	79.88 39	87.34 43	55.20 67	89.93 29	87.55 67	66.04 76	79.46 26	93.00 30	53.10 41	91.76 63	80.40 37	89.56 9	92.68 29

QAPM		71.88 132	69.33 158	79.52 40	82.20 143	54.30 93	86.30 97	88.77 39	56.61 251	59.72 213	87.48 148	33.90 267	95.36 13	47.48 282	81.49 72	88.90 130

VDD-MVS		76.08 62	74.97 71	79.44 41	84.27 90	53.33 119	91.13 20	85.88 96	65.33 87	72.37 76	89.34 108	32.52 279	92.76 40	77.90 57	75.96 131	92.22 39

MVS_111021_HR		76.39 58	75.38 65	79.42 42	85.33 69	56.47 38	88.15 53	84.97 124	65.15 90	66.06 135	89.88 98	43.79 132	92.16 55	75.03 75	80.03 89	89.64 113

SteuartSystems-ACMMP		77.08 47	76.33 52	79.34 43	80.98 176	55.31 61	89.76 33	86.91 75	62.94 127	71.65 83	91.56 60	42.33 153	92.56 45	77.14 61	83.69 57	90.15 101
Skip Steuart: Steuart Systems R&D Blog.
test12				79.24 44	86.89 46	56.08 45		85.16 119		72.27 78		47.15 86	91.10 80		85.93 37	90.54 89

APDe-MVS		78.44 27	78.20 27	79.19 45	88.56 26	54.55 89	89.76 33	87.77 61	55.91 258	78.56 30	92.49 37	48.20 75	92.65 42	79.49 39	83.04 59	90.39 91
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lupinMVS		78.38 29	78.11 29	79.19 45	83.02 120	55.24 63	91.57 15	84.82 128	69.12 34	76.67 39	92.02 46	44.82 121	90.23 105	80.83 36	80.09 86	92.08 41

casdiffmvs_mvg		77.75 39	77.28 40	79.16 47	80.42 194	54.44 91	87.76 61	85.46 103	71.67 15	71.38 88	88.35 129	51.58 48	91.22 75	79.02 43	79.89 92	91.83 53
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
testing222		77.70 40	77.22 42	79.14 48	86.95 45	54.89 78	87.18 79	91.96 2	72.29 12	71.17 93	88.70 120	55.19 28	91.24 74	65.18 146	76.32 127	91.29 71

DeepC-MVS_fast	67.50 3	78.00 36	77.63 35	79.13 49	88.52 27	55.12 69	89.95 28	85.98 95	68.31 36	71.33 89	92.75 32	45.52 107	90.37 98	71.15 101	85.14 46	91.91 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
sasdasda		78.17 33	77.86 32	79.12 50	84.30 87	54.22 94	87.71 62	84.57 137	67.70 49	77.70 34	92.11 44	50.90 55	89.95 111	78.18 54	77.54 111	93.20 15

canonicalmvs		78.17 33	77.86 32	79.12 50	84.30 87	54.22 94	87.71 62	84.57 137	67.70 49	77.70 34	92.11 44	50.90 55	89.95 111	78.18 54	77.54 111	93.20 15

RRT-MVS		73.29 107	71.37 123	79.07 52	84.63 80	54.16 99	78.16 283	86.64 83	61.67 147	60.17 208	82.35 226	40.63 178	92.26 53	70.19 106	77.87 108	90.81 83

PHI-MVS		77.49 42	77.00 44	78.95 53	85.33 69	50.69 173	88.57 49	88.59 47	58.14 216	73.60 57	93.31 21	43.14 145	93.79 27	73.81 87	88.53 13	92.37 34

test_yl		75.85 67	74.83 74	78.91 54	88.08 37	51.94 149	91.30 17	89.28 25	57.91 221	71.19 91	89.20 111	42.03 160	92.77 38	69.41 109	75.07 145	92.01 46

DCV-MVSNet		75.85 67	74.83 74	78.91 54	88.08 37	51.94 149	91.30 17	89.28 25	57.91 221	71.19 91	89.20 111	42.03 160	92.77 38	69.41 109	75.07 145	92.01 46

casdiffmvs		77.36 44	76.85 46	78.88 56	80.40 195	54.66 87	87.06 82	85.88 96	72.11 13	71.57 85	88.63 125	50.89 58	90.35 99	76.00 65	79.11 98	91.63 57
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UBG		78.86 24	78.86 22	78.86 57	87.80 40	55.43 55	87.67 64	91.21 10	72.83 9	72.10 79	88.40 126	58.53 16	89.08 135	73.21 94	77.98 107	92.08 41

PAPM		76.76 54	76.07 56	78.81 58	80.20 196	59.11 7	86.86 88	86.23 90	68.60 35	70.18 104	88.84 118	51.57 49	87.16 210	65.48 139	86.68 30	90.15 101

MSP-MVS		82.30 6	83.47 1	78.80 59	82.99 122	52.71 134	85.04 134	88.63 44	66.08 73	86.77 3	92.75 32	72.05 1	91.46 69	83.35 20	93.53 1	92.23 37
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
DeepC-MVS	67.15 4	76.90 51	76.27 53	78.80 59	80.70 187	55.02 73	86.39 94	86.71 79	66.96 58	67.91 118	89.97 97	48.03 77	91.41 70	75.60 69	84.14 54	89.96 107
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP_NAP		76.43 57	75.66 59	78.73 61	81.92 148	54.67 86	84.06 166	85.35 108	61.10 159	72.99 65	91.50 61	40.25 180	91.00 82	76.84 62	86.98 25	90.51 90

baseline		76.86 52	76.24 54	78.71 62	80.47 193	54.20 98	83.90 171	84.88 127	71.38 19	71.51 86	89.15 113	50.51 60	90.55 95	75.71 67	78.65 101	91.39 66

jason		77.01 48	76.45 50	78.69 63	79.69 203	54.74 80	90.56 24	83.99 152	68.26 37	74.10 54	90.91 72	42.14 157	89.99 110	79.30 41	79.12 97	91.36 68
jason: jason.
ET-MVSNet_ETH3D		75.23 78	74.08 82	78.67 64	84.52 83	55.59 51	88.92 44	89.21 27	68.06 42	53.13 303	90.22 89	49.71 69	87.62 199	72.12 97	70.82 182	92.82 25

CostFormer		73.89 96	72.30 105	78.66 65	82.36 141	56.58 33	75.56 297	85.30 111	66.06 74	70.50 103	76.88 287	57.02 20	89.06 136	68.27 119	68.74 198	90.33 93

patch_mono-2		80.84 12	81.59 10	78.62 66	90.34 9	53.77 104	88.08 54	88.36 51	76.17 2	79.40 27	91.09 64	55.43 27	90.09 108	85.01 12	80.40 82	91.99 48

MVS_Test		75.85 67	74.93 72	78.62 66	84.08 92	55.20 67	83.99 168	85.17 118	68.07 41	73.38 61	82.76 210	50.44 61	89.00 140	65.90 135	80.61 78	91.64 56

CDPH-MVS		76.05 63	75.19 67	78.62 66	86.51 50	54.98 75	87.32 73	84.59 136	58.62 210	70.75 97	90.85 74	43.10 147	90.63 93	70.50 104	84.51 53	90.24 96

TSAR-MVS + GP.		77.82 38	77.59 36	78.49 69	85.25 71	50.27 190	90.02 26	90.57 16	56.58 252	74.26 53	91.60 59	54.26 35	92.16 55	75.87 66	79.91 90	93.05 20

ETV-MVS		77.17 46	76.74 47	78.48 70	81.80 151	54.55 89	86.13 100	85.33 109	68.20 38	73.10 64	90.52 81	45.23 111	90.66 91	79.37 40	80.95 74	90.22 97

TSAR-MVS + MP.		78.31 31	78.26 26	78.48 70	81.33 172	56.31 42	81.59 238	86.41 86	69.61 31	81.72 16	88.16 134	55.09 31	88.04 181	74.12 83	86.31 34	91.09 76
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
train_agg		76.91 49	76.40 51	78.45 72	85.68 59	55.42 56	87.59 67	84.00 150	57.84 224	72.99 65	90.98 67	44.99 115	88.58 158	78.19 52	85.32 44	91.34 70

PAPR		75.20 79	74.13 80	78.41 73	88.31 32	55.10 71	84.31 158	85.66 100	63.76 109	67.55 120	90.73 77	43.48 140	89.40 125	66.36 130	77.03 115	90.73 85

alignmvs		78.08 35	77.98 30	78.39 74	83.53 103	53.22 122	89.77 32	85.45 104	66.11 71	76.59 41	91.99 48	54.07 38	89.05 137	77.34 60	77.00 116	92.89 23

test_prior				78.39 74	86.35 53	54.91 77		85.45 104					89.70 119			90.55 87

SF-MVS		77.64 41	77.42 39	78.32 76	83.75 100	52.47 139	86.63 92	87.80 58	58.78 207	74.63 48	92.38 38	47.75 81	91.35 71	78.18 54	86.85 27	91.15 75

ZNCC-MVS		75.82 70	75.02 70	78.23 77	83.88 98	53.80 103	86.91 87	86.05 94	59.71 181	67.85 119	90.55 79	42.23 155	91.02 81	72.66 96	85.29 45	89.87 110

VNet		77.99 37	77.92 31	78.19 78	87.43 42	50.12 191	90.93 22	91.41 8	67.48 52	75.12 43	90.15 93	46.77 91	91.00 82	73.52 89	78.46 103	93.44 9

EIA-MVS		75.92 65	75.18 68	78.13 79	85.14 72	51.60 158	87.17 80	85.32 110	64.69 93	68.56 113	90.53 80	45.79 103	91.58 66	67.21 124	82.18 66	91.20 73

HFP-MVS		74.37 87	73.13 95	78.10 80	84.30 87	53.68 106	85.58 115	84.36 141	56.82 245	65.78 140	90.56 78	40.70 177	90.90 86	69.18 112	80.88 75	89.71 111

tpm2		70.82 152	68.44 168	77.98 81	80.78 185	56.11 44	74.21 309	81.28 201	60.24 175	68.04 117	75.27 305	52.26 46	88.50 163	55.82 228	68.03 202	89.33 119

thisisatest0515		73.64 103	72.20 107	77.97 82	81.63 159	53.01 129	86.69 91	88.81 38	62.53 133	64.06 165	85.65 172	52.15 47	92.50 46	58.43 195	69.84 190	88.39 147

EPNet		78.36 30	78.49 25	77.97 82	85.49 65	52.04 147	89.36 39	84.07 149	73.22 7	77.03 38	91.72 54	49.32 72	90.17 107	73.46 90	82.77 60	91.69 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	69.37 1	80.65 13	81.56 11	77.94 84	85.46 66	49.56 203	90.99 21	86.66 81	70.58 23	80.07 24	95.30 1	56.18 24	90.97 85	82.57 25	86.22 36	93.28 13

GST-MVS		74.87 83	73.90 85	77.77 85	83.30 110	53.45 112	85.75 109	85.29 112	59.22 194	66.50 131	89.85 99	40.94 172	90.76 88	70.94 102	83.35 58	89.10 127

GG-mvs-BLEND				77.77 85	86.68 48	50.61 174	68.67 345	88.45 50		68.73 112	87.45 149	59.15 11	90.67 90	54.83 231	87.67 17	92.03 45

cascas		69.01 185	66.13 214	77.66 87	79.36 206	55.41 58	86.99 83	83.75 155	56.69 249	58.92 231	81.35 239	24.31 338	92.10 58	53.23 241	70.61 184	85.46 209

3Dnovator+	62.71 7	72.29 124	70.50 134	77.65 88	83.40 108	51.29 167	87.32 73	86.40 87	59.01 202	58.49 241	88.32 131	32.40 280	91.27 72	57.04 217	82.15 67	90.38 92

MVSFormer		73.53 104	72.19 108	77.57 89	83.02 120	55.24 63	81.63 235	81.44 197	50.28 305	76.67 39	90.91 72	44.82 121	86.11 241	60.83 174	80.09 86	91.36 68

APD-MVS		76.15 61	75.68 58	77.54 90	88.52 27	53.44 113	87.26 78	85.03 123	53.79 280	74.91 46	91.68 56	43.80 131	90.31 101	74.36 80	81.82 69	88.87 132
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Fast-Effi-MVS+		72.73 115	71.15 127	77.48 91	82.75 132	54.76 79	86.77 90	80.64 212	63.05 125	65.93 137	84.01 189	44.42 126	89.03 138	56.45 224	76.36 126	88.64 138

EPMVS		68.45 197	65.44 233	77.47 92	84.91 76	56.17 43	71.89 331	81.91 189	61.72 146	60.85 202	72.49 331	36.21 241	87.06 213	47.32 283	71.62 174	89.17 125

PatchmatchNet		67.07 231	63.63 251	77.40 93	83.10 115	58.03 11	72.11 329	77.77 273	58.85 205	59.37 221	70.83 344	37.84 203	84.93 268	42.96 308	69.83 191	89.26 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
region2R		73.75 99	72.55 99	77.33 94	83.90 97	52.98 130	85.54 119	84.09 148	56.83 244	65.10 147	90.45 82	37.34 218	90.24 104	68.89 114	80.83 77	88.77 136

WTY-MVS		77.47 43	77.52 38	77.30 95	88.33 30	46.25 285	88.46 50	90.32 17	71.40 18	72.32 77	91.72 54	53.44 39	92.37 49	66.28 131	75.42 137	93.28 13

OpenMVS	61.00 11	69.99 167	67.55 187	77.30 95	78.37 232	54.07 101	84.36 156	85.76 99	57.22 238	56.71 270	87.67 146	30.79 295	92.83 36	43.04 307	84.06 56	85.01 214

MTAPA		72.73 115	71.22 125	77.27 97	81.54 165	53.57 108	67.06 352	81.31 199	59.41 188	68.39 114	90.96 69	36.07 244	89.01 139	73.80 88	82.45 64	89.23 122

PAPM_NR		71.80 134	69.98 148	77.26 98	81.54 165	53.34 118	78.60 281	85.25 115	53.46 283	60.53 206	88.66 121	45.69 105	89.24 130	56.49 221	79.62 96	89.19 124

ACMMPR		73.76 98	72.61 97	77.24 99	83.92 96	52.96 131	85.58 115	84.29 142	56.82 245	65.12 146	90.45 82	37.24 221	90.18 106	69.18 112	80.84 76	88.58 140

h-mvs33		73.95 93	72.89 96	77.15 100	80.17 197	50.37 184	84.68 148	83.33 162	68.08 39	71.97 80	88.65 124	42.50 151	91.15 78	78.82 45	57.78 295	89.91 109

SPE-MVS-test		77.20 45	77.25 41	77.05 101	84.60 81	49.04 218	89.42 36	85.83 98	65.90 77	72.85 68	91.98 50	45.10 112	91.27 72	75.02 76	84.56 51	90.84 82

MP-MVS-pluss		75.54 74	75.03 69	77.04 102	81.37 171	52.65 136	84.34 157	84.46 139	61.16 156	69.14 108	91.76 53	39.98 187	88.99 142	78.19 52	84.89 49	89.48 118
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HyFIR lowres test		69.94 169	67.58 185	77.04 102	77.11 253	57.29 22	81.49 243	79.11 248	58.27 214	58.86 233	80.41 246	42.33 153	86.96 216	61.91 165	68.68 199	86.87 178

DP-MVS Recon		71.99 129	70.31 141	77.01 104	90.65 8	53.44 113	89.37 37	82.97 173	56.33 255	63.56 176	89.47 105	34.02 265	92.15 57	54.05 237	72.41 167	85.43 210

Anonymous20240529		69.71 172	67.28 193	77.00 105	83.78 99	50.36 185	88.87 46	85.10 122	47.22 327	64.03 166	83.37 202	27.93 310	92.10 58	57.78 211	67.44 207	88.53 143

CS-MVS		76.77 53	76.70 48	76.99 106	83.55 102	48.75 228	88.60 48	85.18 117	66.38 66	72.47 75	91.62 58	45.53 106	90.99 84	74.48 79	82.51 62	91.23 72

baseline2		75.15 80	74.54 78	76.98 107	81.67 158	51.74 155	83.84 173	91.94 3	69.97 27	58.98 228	86.02 168	59.73 9	91.73 64	68.37 117	70.40 187	87.48 167

MP-MVS		74.99 82	74.33 79	76.95 108	82.89 127	53.05 128	85.63 114	83.50 161	57.86 223	67.25 122	90.24 87	43.38 142	88.85 151	76.03 64	82.23 65	88.96 129
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mvs_anonymous		72.29 124	70.74 130	76.94 109	82.85 129	54.72 82	78.43 282	81.54 195	63.77 108	61.69 195	79.32 256	51.11 52	85.31 259	62.15 164	75.79 133	90.79 84

ETVMVS		75.80 71	75.44 63	76.89 110	86.23 54	50.38 183	85.55 118	91.42 7	71.30 20	68.80 111	87.94 141	56.42 23	89.24 130	56.54 220	74.75 150	91.07 77

XVS		72.92 111	71.62 117	76.81 111	83.41 105	52.48 137	84.88 142	83.20 168	58.03 217	63.91 168	89.63 103	35.50 249	89.78 115	65.50 137	80.50 80	88.16 150

X-MVStestdata		65.85 249	62.20 257	76.81 111	83.41 105	52.48 137	84.88 142	83.20 168	58.03 217	63.91 168	4.82 420	35.50 249	89.78 115	65.50 137	80.50 80	88.16 150

PGM-MVS		72.60 117	71.20 126	76.80 113	82.95 123	52.82 133	83.07 198	82.14 182	56.51 253	63.18 178	89.81 100	35.68 248	89.76 117	67.30 123	80.19 85	87.83 159

Anonymous202405211		70.11 161	67.88 178	76.79 114	87.20 44	47.24 271	89.49 35	77.38 281	54.88 272	66.14 133	86.84 158	20.93 358	91.54 67	56.45 224	71.62 174	91.59 58

tpm cat1		66.28 243	62.78 253	76.77 115	81.40 170	57.14 24	70.03 338	77.19 283	53.00 287	58.76 236	70.73 347	46.17 96	86.73 223	43.27 306	64.46 231	86.44 189

PVSNet_Blended		76.53 56	76.54 49	76.50 116	85.91 56	51.83 153	88.89 45	84.24 146	67.82 46	69.09 109	89.33 110	46.70 92	88.13 177	75.43 70	81.48 73	89.55 115

diffmvs		75.11 81	74.65 76	76.46 117	78.52 228	53.35 117	83.28 192	79.94 226	70.51 24	71.64 84	88.72 119	46.02 100	86.08 246	77.52 58	75.75 135	89.96 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		73.40 106	72.44 101	76.30 118	81.32 173	54.70 83	85.81 105	78.82 252	63.70 110	64.53 158	85.38 176	47.11 87	87.38 206	67.75 121	77.55 110	86.81 184

BH-RMVSNet		70.08 163	68.01 175	76.27 119	84.21 91	51.22 169	87.29 76	79.33 245	58.96 204	63.63 174	86.77 159	33.29 273	90.30 103	44.63 300	73.96 154	87.30 173

CLD-MVS		75.60 72	75.39 64	76.24 120	80.69 188	52.40 140	90.69 23	86.20 91	74.40 6	65.01 150	88.93 115	42.05 159	90.58 94	76.57 63	73.96 154	85.73 203
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		69.96 168	67.88 178	76.22 121	81.11 175	51.71 156	84.15 162	76.74 293	59.83 179	60.91 201	84.38 185	41.56 167	88.10 179	51.67 255	70.57 185	88.84 133

1314		71.11 145	69.41 155	76.22 121	79.32 208	50.49 178	80.23 264	85.14 121	59.44 187	58.93 230	88.89 117	33.83 269	89.60 122	61.49 169	77.42 113	88.57 141

thisisatest0530		70.47 159	68.56 165	76.20 123	79.78 202	51.52 161	83.49 184	88.58 48	57.62 230	58.60 237	82.79 209	51.03 54	91.48 68	52.84 246	62.36 257	85.59 208

FA-MVS(test-final)		69.00 186	66.60 205	76.19 124	83.48 104	47.96 259	74.73 304	82.07 184	57.27 237	62.18 190	78.47 265	36.09 243	92.89 34	53.76 240	71.32 178	87.73 162

HY-MVS	67.03 5	73.90 95	73.14 93	76.18 125	84.70 79	47.36 268	75.56 297	86.36 88	66.27 68	70.66 100	83.91 191	51.05 53	89.31 128	67.10 125	72.61 166	91.88 51

gg-mvs-nofinetune		67.43 219	64.53 244	76.13 126	85.95 55	47.79 263	64.38 359	88.28 52	39.34 364	66.62 127	41.27 401	58.69 14	89.00 140	49.64 267	86.62 31	91.59 58

原ACMM1				76.13 126	84.89 77	54.59 88		85.26 114	51.98 294	66.70 125	87.07 156	40.15 183	89.70 119	51.23 258	85.06 48	84.10 227

GA-MVS		69.04 184	66.70 202	76.06 128	75.11 279	52.36 141	83.12 196	80.23 220	63.32 120	60.65 205	79.22 258	30.98 294	88.37 166	61.25 170	66.41 216	87.46 168

mPP-MVS		71.79 135	70.38 139	76.04 129	82.65 136	52.06 146	84.45 154	81.78 192	55.59 262	62.05 193	89.68 102	33.48 271	88.28 174	65.45 142	78.24 106	87.77 161

MVSTER		73.25 108	72.33 103	76.01 130	85.54 64	53.76 105	83.52 178	87.16 71	67.06 56	63.88 170	81.66 236	52.77 42	90.44 96	64.66 150	64.69 229	83.84 238

CP-MVS		72.59 119	71.46 120	76.00 131	82.93 125	52.32 143	86.93 86	82.48 179	55.15 267	63.65 173	90.44 85	35.03 256	88.53 162	68.69 115	77.83 109	87.15 174

HPM-MVS		72.60 117	71.50 119	75.89 132	82.02 144	51.42 163	80.70 256	83.05 170	56.12 257	64.03 166	89.53 104	37.55 212	88.37 166	70.48 105	80.04 88	87.88 158
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
114514_t		69.87 170	67.88 178	75.85 133	88.38 29	52.35 142	86.94 85	83.68 156	53.70 281	55.68 280	85.60 173	30.07 300	91.20 76	55.84 227	71.02 180	83.99 231

reproduce-ours		71.77 136	70.43 136	75.78 134	81.96 146	49.54 206	82.54 211	81.01 206	48.77 317	69.21 106	90.96 69	37.13 224	89.40 125	66.28 131	76.01 129	88.39 147

our_new_method		71.77 136	70.43 136	75.78 134	81.96 146	49.54 206	82.54 211	81.01 206	48.77 317	69.21 106	90.96 69	37.13 224	89.40 125	66.28 131	76.01 129	88.39 147

PMMVS		72.98 110	72.05 113	75.78 134	83.57 101	48.60 231	84.08 164	82.85 175	61.62 148	68.24 116	90.33 86	28.35 306	87.78 191	72.71 95	76.69 121	90.95 80

SDMVSNet		71.89 131	70.62 133	75.70 137	81.70 155	51.61 157	73.89 310	88.72 41	66.58 61	61.64 196	82.38 223	37.63 209	89.48 123	77.44 59	65.60 223	86.01 195

EC-MVSNet		75.30 75	75.20 66	75.62 138	80.98 176	49.00 219	87.43 70	84.68 134	63.49 117	70.97 95	90.15 93	42.86 150	91.14 79	74.33 81	81.90 68	86.71 185

test_fmvsm_n_1920		75.56 73	75.54 61	75.61 139	74.60 288	49.51 208	81.82 229	74.08 316	66.52 64	80.40 22	93.46 17	46.95 88	89.72 118	86.69 7	75.30 138	87.61 165

MS-PatchMatch		72.34 122	71.26 124	75.61 139	82.38 140	55.55 52	88.00 55	89.95 20	65.38 85	56.51 274	80.74 245	32.28 282	92.89 34	57.95 206	88.10 15	78.39 314

fmvsm_s_conf0.5_n		74.48 84	74.12 81	75.56 141	76.96 254	47.85 261	85.32 123	69.80 352	64.16 100	78.74 28	93.48 16	45.51 108	89.29 129	86.48 8	66.62 213	89.55 115

WBMVS		73.93 94	73.39 87	75.55 142	87.82 39	55.21 65	89.37 37	87.29 69	67.27 53	63.70 172	80.30 247	60.32 6	86.47 231	61.58 168	62.85 252	84.97 215

xiu_mvs_v1_base_debu		71.60 138	70.29 142	75.55 142	77.26 248	53.15 123	85.34 120	79.37 239	55.83 259	72.54 71	90.19 90	22.38 349	86.66 225	73.28 91	76.39 123	86.85 180

xiu_mvs_v1_base		71.60 138	70.29 142	75.55 142	77.26 248	53.15 123	85.34 120	79.37 239	55.83 259	72.54 71	90.19 90	22.38 349	86.66 225	73.28 91	76.39 123	86.85 180

xiu_mvs_v1_base_debi		71.60 138	70.29 142	75.55 142	77.26 248	53.15 123	85.34 120	79.37 239	55.83 259	72.54 71	90.19 90	22.38 349	86.66 225	73.28 91	76.39 123	86.85 180

test_fmvsmconf_n		74.41 86	74.05 83	75.49 146	74.16 294	48.38 240	82.66 205	72.57 329	67.05 57	75.11 44	92.88 31	46.35 95	87.81 186	83.93 18	71.71 173	90.28 95

fmvsm_s_conf0.1_n		73.80 97	73.26 90	75.43 147	73.28 302	47.80 262	84.57 153	69.43 354	63.34 119	78.40 31	93.29 22	44.73 124	89.22 132	85.99 9	66.28 220	89.26 120

CANet_DTU		73.71 100	73.14 93	75.40 148	82.61 137	50.05 192	84.67 150	79.36 242	69.72 30	75.39 42	90.03 96	29.41 302	85.93 252	67.99 120	79.11 98	90.22 97

ACMMP		70.81 153	69.29 159	75.39 149	81.52 167	51.92 151	83.43 185	83.03 171	56.67 250	58.80 235	88.91 116	31.92 287	88.58 158	65.89 136	73.39 158	85.67 204
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
test_fmvsmconf0.1_n		73.69 101	73.15 91	75.34 150	70.71 332	48.26 245	82.15 219	71.83 334	66.75 60	74.47 52	92.59 36	44.89 118	87.78 191	83.59 19	71.35 177	89.97 106

SCA		63.84 258	60.01 279	75.32 151	78.58 227	57.92 12	61.61 371	77.53 277	56.71 248	57.75 253	70.77 345	31.97 285	79.91 319	48.80 273	56.36 301	88.13 153

fmvsm_l_conf0.5_n_a		75.88 66	76.07 56	75.31 152	76.08 266	48.34 242	85.24 125	70.62 345	63.13 124	81.45 18	93.62 14	49.98 66	87.40 205	87.76 6	76.77 120	90.20 99

fmvsm_l_conf0.5_n		75.95 64	76.16 55	75.31 152	76.01 270	48.44 239	84.98 137	71.08 342	63.50 116	81.70 17	93.52 15	50.00 64	87.18 209	87.80 5	76.87 119	90.32 94

FE-MVS		64.15 255	60.43 275	75.30 154	80.85 183	49.86 197	68.28 347	78.37 264	50.26 308	59.31 223	73.79 316	26.19 323	91.92 61	40.19 315	66.67 212	84.12 226

fmvsm_s_conf0.5_n_a		73.68 102	73.15 91	75.29 155	75.45 277	48.05 254	83.88 172	68.84 357	63.43 118	78.60 29	93.37 20	45.32 109	88.92 147	85.39 11	64.04 233	88.89 131

ab-mvs		70.65 155	69.11 161	75.29 155	80.87 182	46.23 286	73.48 314	85.24 116	59.99 177	66.65 126	80.94 242	43.13 146	88.69 153	63.58 154	68.07 201	90.95 80

reproduce_model		71.07 146	69.67 152	75.28 157	81.51 168	48.82 226	81.73 232	80.57 215	47.81 323	68.26 115	90.78 76	36.49 239	88.60 157	65.12 147	74.76 149	88.42 146

TR-MVS		69.71 172	67.85 181	75.27 158	82.94 124	48.48 237	87.40 72	80.86 209	57.15 240	64.61 156	87.08 155	32.67 278	89.64 121	46.38 291	71.55 176	87.68 164

v2v482		69.55 178	67.64 184	75.26 159	72.32 316	53.83 102	84.93 141	81.94 186	65.37 86	60.80 203	79.25 257	41.62 165	88.98 143	63.03 157	59.51 270	82.98 254

PCF-MVS	61.03 10	70.10 162	68.40 169	75.22 160	77.15 252	51.99 148	79.30 276	82.12 183	56.47 254	61.88 194	86.48 166	43.98 128	87.24 208	55.37 229	72.79 165	86.43 190
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.1_n_a		72.82 114	72.05 113	75.12 161	70.95 331	47.97 257	82.72 204	68.43 359	62.52 134	78.17 32	93.08 28	44.21 127	88.86 148	84.82 13	63.54 239	88.54 142

test_fmvsmconf0.01_n		71.97 130	70.95 129	75.04 162	66.21 357	47.87 260	80.35 261	70.08 349	65.85 78	72.69 70	91.68 56	39.99 186	87.67 195	82.03 28	69.66 192	89.58 114

HQP-MVS		72.34 122	71.44 121	75.03 163	79.02 215	51.56 159	88.00 55	83.68 156	65.45 81	64.48 159	85.13 177	37.35 216	88.62 155	66.70 126	73.12 160	84.91 217

AdaColmap		67.86 207	65.48 230	75.00 164	88.15 36	54.99 74	86.10 101	76.63 296	49.30 312	57.80 250	86.65 163	29.39 303	88.94 146	45.10 297	70.21 188	81.06 284

EI-MVSNet-Vis-set		73.19 109	72.60 98	74.99 165	82.56 138	49.80 199	82.55 210	89.00 30	66.17 70	65.89 138	88.98 114	43.83 130	92.29 51	65.38 145	69.01 196	82.87 256

mvsmamba		69.38 180	67.52 189	74.95 166	82.86 128	52.22 145	67.36 350	76.75 291	61.14 157	49.43 324	82.04 232	37.26 220	84.14 275	73.93 85	76.91 117	88.50 144

tpmrst		71.04 148	69.77 150	74.86 167	83.19 114	55.86 50	75.64 296	78.73 256	67.88 44	64.99 151	73.73 317	49.96 67	79.56 323	65.92 134	67.85 205	89.14 126

v1144		68.81 190	66.82 198	74.80 168	72.34 315	53.46 110	84.68 148	81.77 193	64.25 98	60.28 207	77.91 268	40.23 181	88.95 144	60.37 183	59.52 269	81.97 263

v1192		67.96 206	65.74 225	74.63 169	71.79 319	53.43 115	84.06 166	80.99 208	63.19 123	59.56 217	77.46 275	37.50 215	88.65 154	58.20 201	58.93 276	81.79 266

BH-w/o		70.02 165	68.51 167	74.56 170	82.77 131	50.39 182	86.60 93	78.14 268	59.77 180	59.65 214	85.57 174	39.27 192	87.30 207	49.86 265	74.94 148	85.99 197

SR-MVS		70.92 151	69.73 151	74.50 171	83.38 109	50.48 179	84.27 159	79.35 243	48.96 315	66.57 130	90.45 82	33.65 270	87.11 211	66.42 128	74.56 151	85.91 200

tttt0517		68.33 200	66.29 210	74.46 172	78.08 234	49.06 215	80.88 253	89.08 29	54.40 278	54.75 288	80.77 244	51.31 51	90.33 100	49.35 269	58.01 289	83.99 231

TESTMET0.1,1		72.86 113	72.33 103	74.46 172	81.98 145	50.77 171	85.13 129	85.47 102	66.09 72	67.30 121	83.69 196	37.27 219	83.57 283	65.06 148	78.97 100	89.05 128

nrg030		72.27 126	71.56 118	74.42 174	75.93 271	50.60 175	86.97 84	83.21 167	62.75 129	67.15 123	84.38 185	50.07 63	86.66 225	71.19 100	62.37 256	85.99 197

RPMNet		59.29 291	54.25 315	74.42 174	73.97 297	56.57 34	60.52 374	76.98 287	35.72 376	57.49 259	58.87 386	37.73 207	85.26 261	27.01 374	59.93 266	81.42 274

Vis-MVSNet		70.61 156	69.34 157	74.42 174	80.95 181	48.49 236	86.03 103	77.51 278	58.74 208	65.55 143	87.78 143	34.37 262	85.95 251	52.53 252	80.61 78	88.80 134
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPP-MVSNet		71.14 143	70.07 147	74.33 177	79.18 212	46.52 278	83.81 174	86.49 84	56.32 256	57.95 247	84.90 183	54.23 36	89.14 134	58.14 202	69.65 193	87.33 171

test2506		72.91 112	72.43 102	74.32 178	80.12 198	44.18 309	83.19 194	84.77 131	64.02 102	65.97 136	87.43 150	47.67 82	88.72 152	59.08 188	79.66 94	90.08 103

EI-MVSNet-UG-set		72.37 121	71.73 116	74.29 179	81.60 161	49.29 213	81.85 227	88.64 43	65.29 89	65.05 148	88.29 132	43.18 143	91.83 62	63.74 153	67.97 203	81.75 267

ECVR-MVS		71.81 133	71.00 128	74.26 180	80.12 198	43.49 314	84.69 147	82.16 181	64.02 102	64.64 154	87.43 150	35.04 255	89.21 133	61.24 171	79.66 94	90.08 103

OPM-MVS		70.75 154	69.58 153	74.26 180	75.55 276	51.34 165	86.05 102	83.29 166	61.94 143	62.95 182	85.77 171	34.15 264	88.44 164	65.44 143	71.07 179	82.99 253
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		67.86 207	65.76 224	74.16 182	71.68 321	53.09 126	84.14 163	80.83 210	62.85 128	59.21 226	77.28 279	39.30 191	88.00 182	58.67 193	57.88 293	81.40 276

HQP_MVS		70.96 150	69.91 149	74.12 183	77.95 236	49.57 201	85.76 107	82.59 177	63.60 113	62.15 191	83.28 204	36.04 245	88.30 172	65.46 140	72.34 168	84.49 221

v1921920		67.45 218	65.23 237	74.10 184	71.51 324	52.90 132	83.75 176	80.44 216	62.48 136	59.12 227	77.13 280	36.98 228	87.90 184	57.53 213	58.14 287	81.49 271

v8		67.25 224	64.99 240	74.04 185	72.89 309	53.31 120	82.37 217	80.11 222	61.54 150	54.29 294	76.02 301	42.89 149	88.41 165	58.43 195	56.36 301	80.39 293

VPNet		72.07 128	71.42 122	74.04 185	78.64 226	47.17 272	89.91 31	87.97 56	72.56 11	64.66 153	85.04 180	41.83 164	88.33 170	61.17 172	60.97 262	86.62 186

test_fmvsmvis_n_1920		71.29 142	70.38 139	74.00 187	71.04 330	48.79 227	79.19 277	64.62 368	62.75 129	66.73 124	91.99 48	40.94 172	88.35 168	83.00 21	73.18 159	84.85 219

MonoMVSNet		66.80 237	64.41 245	73.96 188	76.21 264	48.07 253	76.56 294	78.26 266	64.34 96	54.32 293	74.02 314	37.21 222	86.36 236	64.85 149	53.96 325	87.45 169

v1240		66.99 232	64.68 242	73.93 189	71.38 327	52.66 135	83.39 189	79.98 224	61.97 142	58.44 244	77.11 281	35.25 251	87.81 186	56.46 223	58.15 285	81.33 279

BH-untuned		68.28 201	66.40 207	73.91 190	81.62 160	50.01 193	85.56 117	77.39 280	57.63 229	57.47 261	83.69 196	36.36 240	87.08 212	44.81 298	73.08 163	84.65 220

v148		68.24 203	66.35 208	73.88 191	71.76 320	51.47 162	84.23 160	81.90 190	63.69 111	58.94 229	76.44 292	43.72 135	87.78 191	60.63 176	55.86 311	82.39 260

V42		67.66 212	65.60 229	73.86 192	70.69 334	53.63 107	81.50 241	78.61 259	63.85 107	59.49 220	77.49 274	37.98 201	87.65 196	62.33 160	58.43 280	80.29 294

Fast-Effi-MVS+-dtu		66.53 240	64.10 249	73.84 193	72.41 314	52.30 144	84.73 146	75.66 303	59.51 185	56.34 275	79.11 260	28.11 308	85.85 253	57.74 212	63.29 244	83.35 243

v10		66.61 239	64.20 248	73.83 194	72.59 312	53.37 116	81.88 226	79.91 228	61.11 158	54.09 296	75.60 303	40.06 185	88.26 175	56.47 222	56.10 307	79.86 299

APD-MVS_3200maxsize		69.62 177	68.23 173	73.80 195	81.58 163	48.22 246	81.91 225	79.50 237	48.21 321	64.24 164	89.75 101	31.91 288	87.55 201	63.08 156	73.85 156	85.64 206

AUN-MVS		68.20 204	66.35 208	73.76 196	76.37 258	47.45 266	79.52 273	79.52 236	60.98 162	62.34 187	86.02 168	36.59 238	86.94 217	62.32 161	53.47 331	86.89 177

PVSNet_BlendedMVS		73.42 105	73.30 89	73.76 196	85.91 56	51.83 153	86.18 99	84.24 146	65.40 84	69.09 109	80.86 243	46.70 92	88.13 177	75.43 70	65.92 222	81.33 279

hse-mvs2		71.44 141	70.68 131	73.73 198	76.34 259	47.44 267	79.45 274	79.47 238	68.08 39	71.97 80	86.01 170	42.50 151	86.93 218	78.82 45	53.46 332	86.83 183

baseline1		72.51 120	72.12 111	73.69 199	85.05 73	44.46 302	83.51 182	86.13 93	71.61 16	64.64 154	87.97 140	55.00 32	89.48 123	59.07 189	56.05 308	87.13 175

CDS-MVSNet		70.48 158	69.43 154	73.64 200	77.56 243	48.83 225	83.51 182	77.45 279	63.27 121	62.33 188	85.54 175	43.85 129	83.29 288	57.38 216	74.00 153	88.79 135
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PVSNet	62.49 8	69.27 182	67.81 182	73.64 200	84.41 85	51.85 152	84.63 151	77.80 272	66.42 65	59.80 212	84.95 182	22.14 353	80.44 311	55.03 230	75.11 144	88.62 139

PS-MVSNAJss		68.78 192	67.17 195	73.62 202	73.01 306	48.33 244	84.95 140	84.81 129	59.30 193	58.91 232	79.84 252	37.77 204	88.86 148	62.83 158	63.12 249	83.67 241

TAMVS		69.51 179	68.16 174	73.56 203	76.30 262	48.71 230	82.57 208	77.17 284	62.10 139	61.32 199	84.23 187	41.90 162	83.46 285	54.80 233	73.09 162	88.50 144

UGNet		68.71 193	67.11 196	73.50 204	80.55 192	47.61 264	84.08 164	78.51 261	59.45 186	65.68 142	82.73 213	23.78 340	85.08 266	52.80 247	76.40 122	87.80 160
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
sd_testset		67.79 210	65.95 219	73.32 205	81.70 155	46.33 283	68.99 343	80.30 219	66.58 61	61.64 196	82.38 223	30.45 297	87.63 197	55.86 226	65.60 223	86.01 195

Anonymous20231211		66.08 247	63.67 250	73.31 206	83.07 118	48.75 228	86.01 104	84.67 135	45.27 341	56.54 272	76.67 290	28.06 309	88.95 144	52.78 248	59.95 265	82.23 261

新几何1				73.30 207	83.10 115	53.48 109		71.43 340	45.55 339	66.14 133	87.17 154	33.88 268	80.54 309	48.50 276	80.33 84	85.88 202

reproduce_monomvs		69.71 172	68.52 166	73.29 208	86.43 52	48.21 247	83.91 170	86.17 92	68.02 43	54.91 285	77.46 275	42.96 148	88.86 148	68.44 116	48.38 345	82.80 257

FMVSNet3		68.84 188	67.40 191	73.19 209	85.05 73	48.53 234	85.71 113	85.36 107	60.90 166	57.58 256	79.15 259	42.16 156	86.77 221	47.25 284	63.40 240	84.27 225

thres200		68.71 193	67.27 194	73.02 210	84.73 78	46.76 275	85.03 135	87.73 62	62.34 137	59.87 210	83.45 200	43.15 144	88.32 171	31.25 356	67.91 204	83.98 233

PVSNet_0	57.04 13	61.19 282	57.24 295	73.02 210	77.45 245	50.31 188	79.43 275	77.36 282	63.96 106	47.51 339	72.45 333	25.03 332	83.78 280	52.76 250	19.22 408	84.96 216

test1111		71.06 147	70.42 138	72.97 212	79.48 205	41.49 337	84.82 145	82.74 176	64.20 99	62.98 181	87.43 150	35.20 252	87.92 183	58.54 194	78.42 104	89.49 117

dp		64.41 253	61.58 261	72.90 213	82.40 139	54.09 100	72.53 321	76.59 297	60.39 173	55.68 280	70.39 348	35.18 253	76.90 345	39.34 318	61.71 259	87.73 162

FMVSNet2		67.57 215	65.79 223	72.90 213	82.71 133	47.97 257	85.15 128	84.93 125	58.55 211	56.71 270	78.26 266	36.72 235	86.67 224	46.15 293	62.94 251	84.07 228

XXY-MVS		70.18 160	69.28 160	72.89 215	77.64 240	42.88 324	85.06 133	87.50 68	62.58 132	62.66 186	82.34 227	43.64 137	89.83 114	58.42 197	63.70 238	85.96 199

CR-MVSNet		62.47 274	59.04 286	72.77 216	73.97 297	56.57 34	60.52 374	71.72 336	60.04 176	57.49 259	65.86 363	38.94 194	80.31 312	42.86 309	59.93 266	81.42 274

WB-MVSnew		69.36 181	68.24 172	72.72 217	79.26 210	49.40 210	85.72 112	88.85 36	61.33 153	64.59 157	82.38 223	34.57 260	87.53 202	46.82 288	70.63 183	81.22 283

EI-MVSNet		69.70 175	68.70 164	72.68 218	75.00 282	48.90 223	79.54 271	87.16 71	61.05 160	63.88 170	83.74 194	45.87 101	90.44 96	57.42 215	64.68 230	78.70 307

HPM-MVS_fast		67.86 207	66.28 211	72.61 219	80.67 189	48.34 242	81.18 246	75.95 302	50.81 303	59.55 218	88.05 138	27.86 311	85.98 248	58.83 191	73.58 157	83.51 242

MVP-Stereo		70.97 149	70.44 135	72.59 220	76.03 269	51.36 164	85.02 136	86.99 74	60.31 174	56.53 273	78.92 261	40.11 184	90.00 109	60.00 186	90.01 7	76.41 336
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVS_111021_LR		69.07 183	67.91 176	72.54 221	77.27 247	49.56 203	79.77 269	73.96 319	59.33 192	60.73 204	87.82 142	30.19 299	81.53 296	69.94 107	72.19 170	86.53 187

IS-MVSNet		68.80 191	67.55 187	72.54 221	78.50 229	43.43 316	81.03 248	79.35 243	59.12 200	57.27 264	86.71 160	46.05 99	87.70 194	44.32 302	75.60 136	86.49 188

VPA-MVSNet		71.12 144	70.66 132	72.49 223	78.75 221	44.43 304	87.64 65	90.02 18	63.97 105	65.02 149	81.58 238	42.14 157	87.42 204	63.42 155	63.38 243	85.63 207

SR-MVS-dyc-post		68.27 202	66.87 197	72.48 224	80.96 178	48.14 250	81.54 239	76.98 287	46.42 334	62.75 184	89.42 106	31.17 293	86.09 245	60.52 180	72.06 171	83.19 249

dmvs_re		67.61 213	66.00 217	72.42 225	81.86 150	43.45 315	64.67 358	80.00 223	69.56 32	60.07 209	85.00 181	34.71 258	87.63 197	51.48 256	66.68 211	86.17 194

miper_enhance_ethall		69.77 171	68.90 163	72.38 226	78.93 218	49.91 195	83.29 191	78.85 250	64.90 91	59.37 221	79.46 254	52.77 42	85.16 264	63.78 152	58.72 277	82.08 262

cl22		68.85 187	67.69 183	72.35 227	78.07 235	49.98 194	82.45 215	78.48 262	62.50 135	58.46 242	77.95 267	49.99 65	85.17 263	62.55 159	58.72 277	81.90 265

MGCFI-Net		74.07 91	74.64 77	72.34 228	82.90 126	43.33 319	80.04 267	79.96 225	65.61 79	74.93 45	91.85 51	48.01 78	80.86 303	71.41 99	77.10 114	92.84 24

MSDG		59.44 290	55.14 310	72.32 229	74.69 285	50.71 172	74.39 308	73.58 322	44.44 348	43.40 354	77.52 273	19.45 362	90.87 87	31.31 355	57.49 297	75.38 342

UWE-MVS		72.17 127	72.15 109	72.21 230	82.26 142	44.29 306	86.83 89	89.58 22	65.58 80	65.82 139	85.06 179	45.02 114	84.35 274	54.07 236	75.18 140	87.99 157

v7n		62.50 273	59.27 284	72.20 231	67.25 356	49.83 198	77.87 286	80.12 221	52.50 291	48.80 329	73.07 325	32.10 283	87.90 184	46.83 287	54.92 317	78.86 305

1112_ss		70.05 164	69.37 156	72.10 232	80.77 186	42.78 325	85.12 132	76.75 291	59.69 182	61.19 200	92.12 42	47.48 83	83.84 278	53.04 244	68.21 200	89.66 112

miper_ehance_all_eth		68.70 195	67.58 185	72.08 233	76.91 255	49.48 209	82.47 214	78.45 263	62.68 131	58.28 246	77.88 269	50.90 55	85.01 267	61.91 165	58.72 277	81.75 267

eth_miper_zixun_eth		66.98 233	65.28 236	72.06 234	75.61 275	50.40 181	81.00 249	76.97 290	62.00 140	56.99 266	76.97 283	44.84 120	85.58 254	58.75 192	54.42 322	80.21 295

LPG-MVS_test		66.44 242	64.58 243	72.02 235	74.42 290	48.60 231	83.07 198	80.64 212	54.69 274	53.75 299	83.83 192	25.73 327	86.98 214	60.33 184	64.71 227	80.48 291

LGP-MVS_train				72.02 235	74.42 290	48.60 231		80.64 212	54.69 274	53.75 299	83.83 192	25.73 327	86.98 214	60.33 184	64.71 227	80.48 291

ACMP	61.11 9	66.24 245	64.33 246	72.00 237	74.89 284	49.12 214	83.18 195	79.83 229	55.41 265	52.29 308	82.68 214	25.83 325	86.10 243	60.89 173	63.94 236	80.78 287
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GBi-Net		67.09 229	65.47 231	71.96 238	82.71 133	46.36 280	83.52 178	83.31 163	58.55 211	57.58 256	76.23 296	36.72 235	86.20 237	47.25 284	63.40 240	83.32 244

test1		67.09 229	65.47 231	71.96 238	82.71 133	46.36 280	83.52 178	83.31 163	58.55 211	57.58 256	76.23 296	36.72 235	86.20 237	47.25 284	63.40 240	83.32 244

FMVSNet1		64.57 252	62.11 258	71.96 238	77.32 246	46.36 280	83.52 178	83.31 163	52.43 292	54.42 291	76.23 296	27.80 312	86.20 237	42.59 311	61.34 261	83.32 244

cl____		67.43 219	65.93 220	71.95 241	76.33 260	48.02 255	82.58 207	79.12 247	61.30 155	56.72 269	76.92 285	46.12 97	86.44 233	57.98 204	56.31 303	81.38 278

DIV-MVS_self_test		67.43 219	65.93 220	71.94 242	76.33 260	48.01 256	82.57 208	79.11 248	61.31 154	56.73 268	76.92 285	46.09 98	86.43 234	57.98 204	56.31 303	81.39 277

Patchmatch-RL test		58.72 301	54.32 314	71.92 243	63.91 372	44.25 307	61.73 370	55.19 382	57.38 235	49.31 326	54.24 392	37.60 211	80.89 301	62.19 163	47.28 353	90.63 86

c3_l		67.97 205	66.66 203	71.91 244	76.20 265	49.31 212	82.13 221	78.00 270	61.99 141	57.64 255	76.94 284	49.41 70	84.93 268	60.62 177	57.01 299	81.49 271

tfpn200view9		67.57 215	66.13 214	71.89 245	84.05 93	45.07 297	83.40 187	87.71 64	60.79 167	57.79 251	82.76 210	43.53 138	87.80 188	28.80 363	66.36 217	82.78 258

MIMVSNet		63.12 266	60.29 276	71.61 246	75.92 272	46.65 276	65.15 355	81.94 186	59.14 199	54.65 289	69.47 351	25.74 326	80.63 307	41.03 314	69.56 195	87.55 166

test-LLR		69.65 176	69.01 162	71.60 247	78.67 223	48.17 248	85.13 129	79.72 231	59.18 197	63.13 179	82.58 217	36.91 230	80.24 313	60.56 178	75.17 141	86.39 191

test-mter		68.36 198	67.29 192	71.60 247	78.67 223	48.17 248	85.13 129	79.72 231	53.38 284	63.13 179	82.58 217	27.23 316	80.24 313	60.56 178	75.17 141	86.39 191

sss		70.49 157	70.13 146	71.58 249	81.59 162	39.02 348	80.78 255	84.71 133	59.34 190	66.61 128	88.09 135	37.17 223	85.52 255	61.82 167	71.02 180	90.20 99

tpmvs		62.45 275	59.42 282	71.53 250	83.93 95	54.32 92	70.03 338	77.61 276	51.91 295	53.48 302	68.29 357	37.91 202	86.66 225	33.36 346	58.27 283	73.62 358

ACMM	58.35 12	64.35 254	62.01 259	71.38 251	74.21 293	48.51 235	82.25 218	79.66 233	47.61 325	54.54 290	80.11 248	25.26 330	86.00 247	51.26 257	63.16 247	79.64 300
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH	53.70 16	59.78 288	55.94 306	71.28 252	76.59 257	48.35 241	80.15 266	76.11 300	49.74 310	41.91 360	73.45 324	16.50 378	90.31 101	31.42 354	57.63 296	75.17 345
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ppachtmachnet_test		58.56 303	54.34 313	71.24 253	71.42 325	54.74 80	81.84 228	72.27 331	49.02 314	45.86 348	68.99 355	26.27 321	83.30 287	30.12 358	43.23 367	75.69 339

thres100view900		66.87 235	65.42 234	71.24 253	83.29 111	43.15 321	81.67 234	87.78 59	59.04 201	55.92 278	82.18 229	43.73 133	87.80 188	28.80 363	66.36 217	82.78 258

thres400		67.40 222	66.13 214	71.19 255	84.05 93	45.07 297	83.40 187	87.71 64	60.79 167	57.79 251	82.76 210	43.53 138	87.80 188	28.80 363	66.36 217	80.71 289

our_test_3		59.11 295	55.08 311	71.18 256	71.42 325	53.29 121	81.96 223	74.52 312	48.32 319	42.08 358	69.28 354	28.14 307	82.15 292	34.35 343	45.68 362	78.11 319

CPTT-MVS		67.15 227	65.84 222	71.07 257	80.96 178	50.32 187	81.94 224	74.10 315	46.18 337	57.91 248	87.64 147	29.57 301	81.31 298	64.10 151	70.18 189	81.56 270

NR-MVSNet		67.25 224	65.99 218	71.04 258	73.27 303	43.91 310	85.32 123	84.75 132	66.05 75	53.65 301	82.11 230	45.05 113	85.97 250	47.55 281	56.18 306	83.24 247

tpm		68.36 198	67.48 190	70.97 259	79.93 201	51.34 165	76.58 293	78.75 255	67.73 47	63.54 177	74.86 307	48.33 74	72.36 367	53.93 238	63.71 237	89.21 123

TranMVSNet+NR-MVSNet		66.94 234	65.61 228	70.93 260	73.45 299	43.38 317	83.02 200	84.25 144	65.31 88	58.33 245	81.90 234	39.92 188	85.52 255	49.43 268	54.89 318	83.89 237

EG-PatchMatch MVS		62.40 276	59.59 280	70.81 261	73.29 301	49.05 216	85.81 105	84.78 130	51.85 297	44.19 349	73.48 323	15.52 381	89.85 113	40.16 316	67.24 208	73.54 359

test_djsdf		63.84 258	61.56 262	70.70 262	68.78 345	44.69 301	81.63 235	81.44 197	50.28 305	52.27 309	76.26 295	26.72 319	86.11 241	60.83 174	55.84 312	81.29 282

UA-Net		67.32 223	66.23 212	70.59 263	78.85 219	41.23 340	73.60 312	75.45 306	61.54 150	66.61 128	84.53 184	38.73 197	86.57 230	42.48 312	74.24 152	83.98 233

thres600view7		66.46 241	65.12 238	70.47 264	83.41 105	43.80 312	82.15 219	87.78 59	59.37 189	56.02 277	82.21 228	43.73 133	86.90 219	26.51 375	64.94 226	80.71 289

UniMVSNet (Re)		67.71 211	66.80 199	70.45 265	74.44 289	42.93 323	82.42 216	84.90 126	63.69 111	59.63 215	80.99 241	47.18 85	85.23 262	51.17 259	56.75 300	83.19 249

IterMVS-LS		66.63 238	65.36 235	70.42 266	75.10 280	48.90 223	81.45 244	76.69 295	61.05 160	55.71 279	77.10 282	45.86 102	83.65 282	57.44 214	57.88 293	78.70 307
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet_NR-MVSNet		68.82 189	68.29 171	70.40 267	75.71 274	42.59 327	84.23 160	86.78 77	66.31 67	58.51 238	82.45 220	51.57 49	84.64 272	53.11 242	55.96 309	83.96 235

jajsoiax		63.21 265	60.84 270	70.32 268	68.33 350	44.45 303	81.23 245	81.05 203	53.37 285	50.96 318	77.81 271	17.49 372	85.49 257	59.31 187	58.05 288	81.02 285

mvs_tets		62.96 268	60.55 272	70.19 269	68.22 353	44.24 308	80.90 252	80.74 211	52.99 288	50.82 320	77.56 272	16.74 376	85.44 258	59.04 190	57.94 290	80.89 286

pmmvs4		63.34 264	61.07 269	70.16 270	70.14 336	50.53 177	79.97 268	71.41 341	55.08 268	54.12 295	78.58 263	32.79 277	82.09 294	50.33 262	57.22 298	77.86 320

DU-MVS		66.84 236	65.74 225	70.16 270	73.27 303	42.59 327	81.50 241	82.92 174	63.53 115	58.51 238	82.11 230	40.75 174	84.64 272	53.11 242	55.96 309	83.24 247

Effi-MVS+-dtu		66.24 245	64.96 241	70.08 272	75.17 278	49.64 200	82.01 222	74.48 313	62.15 138	57.83 249	76.08 300	30.59 296	83.79 279	65.40 144	60.93 263	76.81 329

IterMVS		63.77 260	61.67 260	70.08 272	72.68 311	51.24 168	80.44 259	75.51 304	60.51 172	51.41 313	73.70 320	32.08 284	78.91 324	54.30 235	54.35 323	80.08 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WR-MVS		67.58 214	66.76 200	70.04 274	75.92 272	45.06 300	86.23 98	85.28 113	64.31 97	58.50 240	81.00 240	44.80 123	82.00 295	49.21 271	55.57 314	83.06 252

Test_1112_low_res		67.18 226	66.23 212	70.02 275	78.75 221	41.02 341	83.43 185	73.69 321	57.29 236	58.45 243	82.39 222	45.30 110	80.88 302	50.50 261	66.26 221	88.16 150

D2MVS		63.49 262	61.39 264	69.77 276	69.29 342	48.93 222	78.89 279	77.71 275	60.64 171	49.70 323	72.10 339	27.08 317	83.48 284	54.48 234	62.65 253	76.90 328

tt0805		63.39 263	61.31 266	69.64 277	69.36 341	38.87 349	78.00 284	85.48 101	48.82 316	55.66 282	81.66 236	24.38 337	86.37 235	49.04 272	59.36 273	83.68 240

XVG-OURS		61.88 278	59.34 283	69.49 278	65.37 362	46.27 284	64.80 357	73.49 324	47.04 329	57.41 263	82.85 208	25.15 331	78.18 328	53.00 245	64.98 225	84.01 230

XVG-OURS-SEG-HR		62.02 277	59.54 281	69.46 279	65.30 363	45.88 288	65.06 356	73.57 323	46.45 333	57.42 262	83.35 203	26.95 318	78.09 330	53.77 239	64.03 234	84.42 223

test_vis1_n_1920		68.59 196	68.31 170	69.44 280	69.16 343	41.51 336	84.63 151	68.58 358	58.80 206	73.26 63	88.37 127	25.30 329	80.60 308	79.10 42	67.55 206	86.23 193

FIs		70.00 166	70.24 145	69.30 281	77.93 238	38.55 351	83.99 168	87.72 63	66.86 59	57.66 254	84.17 188	52.28 45	85.31 259	52.72 251	68.80 197	84.02 229

Baseline_NR-MVSNet		65.49 251	64.27 247	69.13 282	74.37 292	41.65 334	83.39 189	78.85 250	59.56 184	59.62 216	76.88 287	40.75 174	87.44 203	49.99 263	55.05 316	78.28 316

TransMVSNet (Re)		62.82 269	60.76 271	69.02 283	73.98 296	41.61 335	86.36 95	79.30 246	56.90 242	52.53 306	76.44 292	41.85 163	87.60 200	38.83 319	40.61 372	77.86 320

anonymousdsp		60.46 286	57.65 292	68.88 284	63.63 374	45.09 296	72.93 318	78.63 258	46.52 332	51.12 315	72.80 329	21.46 356	83.07 289	57.79 210	53.97 324	78.47 311

ADS-MVSNet		56.17 318	51.95 328	68.84 285	80.60 190	53.07 127	55.03 386	70.02 350	44.72 345	51.00 316	61.19 378	22.83 345	78.88 325	28.54 366	53.63 327	74.57 352

OpenMVS_ROB	53.19 17	59.20 293	56.00 305	68.83 286	71.13 329	44.30 305	83.64 177	75.02 309	46.42 334	46.48 345	73.03 326	18.69 366	88.14 176	27.74 371	61.80 258	74.05 355

Patchmatch-test		53.33 333	48.17 343	68.81 287	73.31 300	42.38 331	42.98 398	58.23 378	32.53 382	38.79 375	70.77 345	39.66 189	73.51 361	25.18 378	52.06 337	90.55 87

pm-mvs1		64.12 256	62.56 254	68.78 288	71.68 321	38.87 349	82.89 202	81.57 194	55.54 264	53.89 298	77.82 270	37.73 207	86.74 222	48.46 277	53.49 330	80.72 288

miper_lstm_enhance		63.91 257	62.30 256	68.75 289	75.06 281	46.78 274	69.02 342	81.14 202	59.68 183	52.76 305	72.39 334	40.71 176	77.99 334	56.81 219	53.09 333	81.48 273

OMC-MVS		65.97 248	65.06 239	68.71 290	72.97 307	42.58 329	78.61 280	75.35 307	54.72 273	59.31 223	86.25 167	33.30 272	77.88 336	57.99 203	67.05 209	85.66 205

DP-MVS		59.24 292	56.12 304	68.63 291	88.24 34	50.35 186	82.51 213	64.43 369	41.10 361	46.70 343	78.77 262	24.75 335	88.57 161	22.26 387	56.29 305	66.96 379

tfpnnormal		61.47 281	59.09 285	68.62 292	76.29 263	41.69 333	81.14 247	85.16 119	54.48 276	51.32 314	73.63 321	32.32 281	86.89 220	21.78 389	55.71 313	77.29 326

test_cas_vis1_n_1920		67.10 228	66.60 205	68.59 293	65.17 365	43.23 320	83.23 193	69.84 351	55.34 266	70.67 99	87.71 145	24.70 336	76.66 347	78.57 49	64.20 232	85.89 201

UniMVSNet_ETH3D		62.51 272	60.49 273	68.57 294	68.30 351	40.88 343	73.89 310	79.93 227	51.81 298	54.77 287	79.61 253	24.80 334	81.10 299	49.93 264	61.35 260	83.73 239

CL-MVSNet_self_test		62.98 267	61.14 268	68.50 295	65.86 360	42.96 322	84.37 155	82.98 172	60.98 162	53.95 297	72.70 330	40.43 179	83.71 281	41.10 313	47.93 348	78.83 306

ACMH+	54.58 15	58.55 304	55.24 308	68.50 295	74.68 286	45.80 291	80.27 262	70.21 348	47.15 328	42.77 357	75.48 304	16.73 377	85.98 248	35.10 341	54.78 319	73.72 357

lessismore_v0				67.98 297	64.76 369	41.25 339		45.75 392		36.03 382	65.63 366	19.29 364	84.11 276	35.67 333	21.24 405	78.59 310

K. test v3		54.04 328	49.42 340	67.92 298	68.55 347	42.57 330	75.51 299	63.07 373	52.07 293	39.21 372	64.59 369	19.34 363	82.21 291	37.11 325	25.31 399	78.97 304

pmmvs5		62.80 270	61.18 267	67.66 299	69.53 340	42.37 332	82.65 206	75.19 308	54.30 279	52.03 311	78.51 264	31.64 290	80.67 306	48.60 275	58.15 285	79.95 298

PatchT		56.60 314	52.97 321	67.48 300	72.94 308	46.16 287	57.30 382	73.78 320	38.77 366	54.37 292	57.26 389	37.52 213	78.06 331	32.02 351	52.79 334	78.23 318

Patchmtry		56.56 315	52.95 322	67.42 301	72.53 313	50.59 176	59.05 378	71.72 336	37.86 370	46.92 341	65.86 363	38.94 194	80.06 316	36.94 328	46.72 358	71.60 369

mmtdpeth		57.93 308	54.78 312	67.39 302	72.32 316	43.38 317	72.72 319	68.93 356	54.45 277	56.85 267	62.43 374	17.02 374	83.46 285	57.95 206	30.31 393	75.31 343

SixPastTwentyTwo		54.37 325	50.10 334	67.21 303	70.70 333	41.46 338	74.73 304	64.69 367	47.56 326	39.12 373	69.49 350	18.49 369	84.69 271	31.87 352	34.20 387	75.48 341

pmmvs6		59.64 289	57.15 296	67.09 304	66.01 358	36.86 359	80.50 257	78.64 257	45.05 343	49.05 327	73.94 315	27.28 315	86.10 243	43.96 304	49.94 342	78.31 315

testdata				67.08 305	77.59 242	45.46 294		69.20 355	44.47 347	71.50 87	88.34 130	31.21 292	70.76 372	52.20 253	75.88 132	85.03 213

CNLPA		60.59 285	58.44 289	67.05 306	79.21 211	47.26 270	79.75 270	64.34 370	42.46 359	51.90 312	83.94 190	27.79 313	75.41 352	37.12 324	59.49 271	78.47 311

KD-MVS_2432*1600		59.04 297	56.44 301	66.86 307	79.07 213	45.87 289	72.13 327	80.42 217	55.03 269	48.15 331	71.01 342	36.73 233	78.05 332	35.21 337	30.18 394	76.67 330

miper_refine_blended		59.04 297	56.44 301	66.86 307	79.07 213	45.87 289	72.13 327	80.42 217	55.03 269	48.15 331	71.01 342	36.73 233	78.05 332	35.21 337	30.18 394	76.67 330

TAPA-MVS	56.12 14	61.82 279	60.18 278	66.71 309	78.48 230	37.97 355	75.19 302	76.41 299	46.82 330	57.04 265	86.52 165	27.67 314	77.03 342	26.50 376	67.02 210	85.14 212
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_0402		56.45 316	53.03 320	66.69 310	76.78 256	50.31 188	81.76 230	69.61 353	42.79 357	43.88 350	72.13 337	22.82 347	86.46 232	16.57 401	50.94 339	63.31 388

PLC	52.38 18	60.89 283	58.97 287	66.68 311	81.77 152	45.70 292	78.96 278	74.04 318	43.66 353	47.63 336	83.19 206	23.52 343	77.78 339	37.47 321	60.46 264	76.55 335
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ADS-MVSNet2		55.21 324	51.44 329	66.51 312	80.60 190	49.56 203	55.03 386	65.44 365	44.72 345	51.00 316	61.19 378	22.83 345	75.41 352	28.54 366	53.63 327	74.57 352

FC-MVSNet-test		67.49 217	67.91 176	66.21 313	76.06 267	33.06 372	80.82 254	87.18 70	64.44 95	54.81 286	82.87 207	50.40 62	82.60 290	48.05 279	66.55 215	82.98 254

JIA-IIPM		52.33 338	47.77 346	66.03 314	71.20 328	46.92 273	40.00 403	76.48 298	37.10 371	46.73 342	37.02 403	32.96 274	77.88 336	35.97 332	52.45 336	73.29 361

LCM-MVSNet-Re		58.82 300	56.54 299	65.68 315	79.31 209	29.09 391	61.39 373	45.79 391	60.73 169	37.65 378	72.47 332	31.42 291	81.08 300	49.66 266	70.41 186	86.87 178

XVG-ACMP-BASELINE		56.03 319	52.85 323	65.58 316	61.91 379	40.95 342	63.36 362	72.43 330	45.20 342	46.02 346	74.09 312	9.20 394	78.12 329	45.13 296	58.27 283	77.66 323

pmmvs-eth3d		55.97 320	52.78 324	65.54 317	61.02 381	46.44 279	75.36 301	67.72 361	49.61 311	43.65 352	67.58 359	21.63 355	77.04 341	44.11 303	44.33 364	73.15 363

MDA-MVSNet_test_wron		53.82 330	49.95 337	65.43 318	70.13 337	49.05 216	72.30 324	71.65 339	44.23 351	31.85 394	63.13 372	23.68 342	74.01 356	33.25 348	39.35 375	73.23 362

YYNet1		53.82 330	49.96 336	65.41 319	70.09 338	48.95 220	72.30 324	71.66 338	44.25 350	31.89 393	63.07 373	23.73 341	73.95 357	33.26 347	39.40 374	73.34 360

PatchMatch-RL		56.66 313	53.75 318	65.37 320	77.91 239	45.28 295	69.78 340	60.38 376	41.35 360	47.57 337	73.73 317	16.83 375	76.91 343	36.99 327	59.21 274	73.92 356

Vis-MVSNet (Re-imp)		65.52 250	65.63 227	65.17 321	77.49 244	30.54 379	75.49 300	77.73 274	59.34 190	52.26 310	86.69 161	49.38 71	80.53 310	37.07 326	75.28 139	84.42 223

FMVSNet5		58.61 302	56.45 300	65.10 322	77.20 251	39.74 345	74.77 303	77.12 285	50.27 307	43.28 355	67.71 358	26.15 324	76.90 345	36.78 329	54.78 319	78.65 309

EPNet_dtu		66.25 244	66.71 201	64.87 323	78.66 225	34.12 367	82.80 203	75.51 304	61.75 145	64.47 162	86.90 157	37.06 226	72.46 366	43.65 305	69.63 194	88.02 156
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UnsupCasMVSNet_eth		57.56 310	55.15 309	64.79 324	64.57 370	33.12 371	73.17 317	83.87 154	58.98 203	41.75 361	70.03 349	22.54 348	79.92 317	46.12 294	35.31 381	81.32 281

LS3D		56.40 317	53.82 317	64.12 325	81.12 174	45.69 293	73.42 315	66.14 364	35.30 380	43.24 356	79.88 250	22.18 352	79.62 322	19.10 396	64.00 235	67.05 378

UnsupCasMVSNet_bld		53.86 329	50.53 333	63.84 326	63.52 375	34.75 362	71.38 332	81.92 188	46.53 331	38.95 374	57.93 387	20.55 359	80.20 315	39.91 317	34.09 388	76.57 334

USDC		54.36 326	51.23 330	63.76 327	64.29 371	37.71 356	62.84 367	73.48 326	56.85 243	35.47 383	71.94 340	9.23 393	78.43 326	38.43 320	48.57 344	75.13 346

Anonymous20231206		59.08 296	57.59 293	63.55 328	68.77 346	32.14 377	80.26 263	79.78 230	50.00 309	49.39 325	72.39 334	26.64 320	78.36 327	33.12 349	57.94 290	80.14 296

CMPMVS	40.41 21	55.34 322	52.64 325	63.46 329	60.88 382	43.84 311	61.58 372	71.06 343	30.43 388	36.33 380	74.63 309	24.14 339	75.44 351	48.05 279	66.62 213	71.12 372
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
myMVS_eth3d		63.52 261	63.56 252	63.40 330	81.73 153	34.28 364	80.97 250	81.02 204	60.93 164	55.06 283	82.64 215	48.00 80	80.81 304	23.42 385	58.32 281	75.10 347

OurMVSNet-221017-0		52.39 337	48.73 341	63.35 331	65.21 364	38.42 352	68.54 346	64.95 366	38.19 367	39.57 371	71.43 341	13.23 384	79.92 317	37.16 323	40.32 373	71.72 368

MDA-MVSNet-bldmvs		51.56 340	47.75 347	63.00 332	71.60 323	47.32 269	69.70 341	72.12 332	43.81 352	27.65 401	63.38 371	21.97 354	75.96 349	27.30 373	32.19 389	65.70 384

mvs5depth		50.97 342	46.98 348	62.95 333	56.63 389	34.23 366	62.73 368	67.35 363	45.03 344	48.00 333	65.41 367	10.40 390	79.88 321	36.00 331	31.27 392	74.73 350

F-COLMAP		55.96 321	53.65 319	62.87 334	72.76 310	42.77 326	74.70 306	70.37 347	40.03 362	41.11 366	79.36 255	17.77 371	73.70 360	32.80 350	53.96 325	72.15 365

test0.0.03 1		62.54 271	62.44 255	62.86 335	72.28 318	29.51 388	82.93 201	78.78 253	59.18 197	53.07 304	82.41 221	36.91 230	77.39 340	37.45 322	58.96 275	81.66 269

CVMVSNet		60.85 284	60.44 274	62.07 336	75.00 282	32.73 374	79.54 271	73.49 324	36.98 372	56.28 276	83.74 194	29.28 304	69.53 375	46.48 290	63.23 245	83.94 236

ambc				62.06 337	53.98 393	29.38 389	35.08 406	79.65 234		41.37 362	59.96 382	6.27 405	82.15 292	35.34 336	38.22 376	74.65 351

Syy-MVS		61.51 280	61.35 265	62.00 338	81.73 153	30.09 383	80.97 250	81.02 204	60.93 164	55.06 283	82.64 215	35.09 254	80.81 304	16.40 402	58.32 281	75.10 347

PEN-MVS		58.35 306	57.15 296	61.94 339	67.55 355	34.39 363	77.01 289	78.35 265	51.87 296	47.72 335	76.73 289	33.91 266	73.75 359	34.03 344	47.17 354	77.68 322

MVS-HIRNet		49.01 347	44.71 351	61.92 340	76.06 267	46.61 277	63.23 364	54.90 383	24.77 396	33.56 388	36.60 405	21.28 357	75.88 350	29.49 360	62.54 254	63.26 389

LTVRE_ROB	45.45 19	52.73 334	49.74 338	61.69 341	69.78 339	34.99 361	44.52 395	67.60 362	43.11 356	43.79 351	74.03 313	18.54 368	81.45 297	28.39 368	57.94 290	68.62 376
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
WR-MVS_H		58.91 299	58.04 291	61.54 342	69.07 344	33.83 369	76.91 290	81.99 185	51.40 300	48.17 330	74.67 308	40.23 181	74.15 355	31.78 353	48.10 346	76.64 333

CP-MVSNet		58.54 305	57.57 294	61.46 343	68.50 348	33.96 368	76.90 291	78.60 260	51.67 299	47.83 334	76.60 291	34.99 257	72.79 364	35.45 334	47.58 350	77.64 324

PS-CasMVS		58.12 307	57.03 298	61.37 344	68.24 352	33.80 370	76.73 292	78.01 269	51.20 301	47.54 338	76.20 299	32.85 275	72.76 365	35.17 339	47.37 352	77.55 325

Anonymous20240521		51.65 339	48.42 342	61.34 345	56.43 390	39.65 347	73.57 313	73.47 327	36.64 374	36.59 379	63.98 370	10.75 389	72.25 368	35.35 335	49.01 343	72.11 366

CHOSEN 280x420		57.53 311	56.38 303	60.97 346	74.01 295	48.10 252	46.30 394	54.31 384	48.18 322	50.88 319	77.43 277	38.37 200	59.16 390	54.83 231	63.14 248	75.66 340

DTE-MVSNet		57.03 312	55.73 307	60.95 347	65.94 359	32.57 375	75.71 295	77.09 286	51.16 302	46.65 344	76.34 294	32.84 276	73.22 363	30.94 357	44.87 363	77.06 327

IterMVS-SCA-FT		59.12 294	58.81 288	60.08 348	70.68 335	45.07 297	80.42 260	74.25 314	43.54 354	50.02 322	73.73 317	31.97 285	56.74 394	51.06 260	53.60 329	78.42 313

COLMAP_ROB	43.60 20	50.90 343	48.05 344	59.47 349	67.81 354	40.57 344	71.25 333	62.72 375	36.49 375	36.19 381	73.51 322	13.48 383	73.92 358	20.71 391	50.26 341	63.92 387
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testing3		59.97 287	60.19 277	59.32 350	77.60 241	30.01 385	81.75 231	81.79 191	53.54 282	50.34 321	79.94 249	48.99 73	76.91 343	17.19 400	50.59 340	71.03 373

testgi		54.25 327	52.57 326	59.29 351	62.76 377	21.65 406	72.21 326	70.47 346	53.25 286	41.94 359	77.33 278	14.28 382	77.95 335	29.18 362	51.72 338	78.28 316

TinyColmap		48.15 349	44.49 353	59.13 352	65.73 361	38.04 353	63.34 363	62.86 374	38.78 365	29.48 396	67.23 361	6.46 404	73.30 362	24.59 380	41.90 370	66.04 382

test20.03		55.22 323	54.07 316	58.68 353	63.14 376	25.00 397	77.69 287	74.78 311	52.64 289	43.43 353	72.39 334	26.21 322	74.76 354	29.31 361	47.05 356	76.28 337

EU-MVSNet		52.63 335	50.72 332	58.37 354	62.69 378	28.13 394	72.60 320	75.97 301	30.94 387	40.76 368	72.11 338	20.16 360	70.80 371	35.11 340	46.11 360	76.19 338

MIMVSNet1		50.35 344	47.81 345	57.96 355	61.53 380	27.80 395	67.40 349	74.06 317	43.25 355	33.31 392	65.38 368	16.03 379	71.34 369	21.80 388	47.55 351	74.75 349

pmmvs3		45.53 354	41.55 360	57.44 356	48.97 403	39.68 346	70.06 337	57.66 379	28.32 391	34.06 386	57.29 388	8.50 397	66.85 378	34.86 342	34.26 386	65.80 383

test_fmvs1		53.60 332	52.54 327	56.78 357	58.07 385	30.26 381	68.95 344	42.19 397	32.46 383	63.59 175	82.56 219	11.55 386	60.81 384	58.25 200	55.27 315	79.28 301

test_fmvs1_n		52.55 336	51.19 331	56.65 358	51.90 396	30.14 382	67.66 348	42.84 396	32.27 384	62.30 189	82.02 233	9.12 395	60.84 383	57.82 209	54.75 321	78.99 303

KD-MVS_self_test		49.24 346	46.85 349	56.44 359	54.32 391	22.87 400	57.39 381	73.36 328	44.36 349	37.98 377	59.30 385	18.97 365	71.17 370	33.48 345	42.44 368	75.26 344

PM-MVS		46.92 351	43.76 358	56.41 360	52.18 395	32.26 376	63.21 365	38.18 403	37.99 369	40.78 367	66.20 362	5.09 408	65.42 379	48.19 278	41.99 369	71.54 370

dmvs_testset		57.65 309	58.21 290	55.97 361	74.62 287	9.82 422	63.75 361	63.34 372	67.23 54	48.89 328	83.68 198	39.12 193	76.14 348	23.43 384	59.80 268	81.96 264

test_vis1_n		51.19 341	49.66 339	55.76 362	51.26 398	29.85 386	67.20 351	38.86 402	32.12 385	59.50 219	79.86 251	8.78 396	58.23 391	56.95 218	52.46 335	79.19 302

AllTest		47.32 350	44.66 352	55.32 363	65.08 366	37.50 357	62.96 366	54.25 385	35.45 378	33.42 389	72.82 327	9.98 391	59.33 387	24.13 381	43.84 365	69.13 374

TestCases				55.32 363	65.08 366	37.50 357		54.25 385	35.45 378	33.42 389	72.82 327	9.98 391	59.33 387	24.13 381	43.84 365	69.13 374

new-patchmatchnet		48.21 348	46.55 350	53.18 365	57.73 387	18.19 414	70.24 336	71.02 344	45.70 338	33.70 387	60.23 381	18.00 370	69.86 374	27.97 370	34.35 385	71.49 371

ITE_SJBPF				51.84 366	58.03 386	31.94 378		53.57 387	36.67 373	41.32 364	75.23 306	11.17 388	51.57 399	25.81 377	48.04 347	72.02 367

RPSCF		45.77 353	44.13 355	50.68 367	57.67 388	29.66 387	54.92 388	45.25 393	26.69 393	45.92 347	75.92 302	17.43 373	45.70 405	27.44 372	45.95 361	76.67 330

test_fmvs2		45.89 352	44.32 354	50.62 368	45.85 407	24.70 398	58.87 380	37.84 405	25.22 394	52.46 307	74.56 310	7.07 399	54.69 395	49.28 270	47.70 349	72.48 364

kuosan		50.20 345	50.09 335	50.52 369	73.09 305	29.09 391	65.25 354	74.89 310	48.27 320	41.34 363	60.85 380	43.45 141	67.48 377	18.59 398	25.07 400	55.01 394

ttmdpeth		40.58 360	37.50 364	49.85 370	49.40 401	22.71 401	56.65 383	46.78 389	28.35 390	40.29 370	69.42 352	5.35 407	61.86 382	20.16 393	21.06 406	64.96 385

MVStest1		38.35 362	34.53 368	49.82 371	51.43 397	30.41 380	50.39 390	55.25 381	17.56 404	26.45 402	65.85 365	11.72 385	57.00 393	14.79 403	17.31 410	62.05 390

ANet_high		34.39 368	29.59 374	48.78 372	30.34 417	22.28 402	55.53 385	63.79 371	38.11 368	15.47 409	36.56 406	6.94 400	59.98 386	13.93 405	5.64 420	64.08 386

TDRefinement		40.91 359	38.37 363	48.55 373	50.45 400	33.03 373	58.98 379	50.97 388	28.50 389	29.89 395	67.39 360	6.21 406	54.51 396	17.67 399	35.25 382	58.11 391

DSMNet-mixed		38.35 362	35.36 367	47.33 374	48.11 405	14.91 418	37.87 404	36.60 406	19.18 401	34.37 385	59.56 384	15.53 380	53.01 398	20.14 394	46.89 357	74.07 354

mvsany_test1		43.38 356	42.57 359	45.82 375	50.96 399	26.10 396	55.80 384	27.74 415	27.15 392	47.41 340	74.39 311	18.67 367	44.95 406	44.66 299	36.31 379	66.40 381

N_pmnet		41.25 358	39.77 361	45.66 376	68.50 348	0.82 428	72.51 322	0.38 427	35.61 377	35.26 384	61.51 377	20.07 361	67.74 376	23.51 383	40.63 371	68.42 377

test_vis1_rt		40.29 361	38.64 362	45.25 377	48.91 404	30.09 383	59.44 377	27.07 416	24.52 397	38.48 376	51.67 397	6.71 402	49.44 400	44.33 301	46.59 359	56.23 392

test_fmvs3		37.95 364	35.75 366	44.55 378	35.50 413	18.92 410	48.32 391	34.00 410	18.36 403	41.31 365	61.58 376	2.29 415	48.06 404	42.72 310	37.71 377	66.66 380

EGC-MVSNET		33.75 369	30.42 373	43.75 379	64.94 368	36.21 360	60.47 376	40.70 400	0.02 421	0.10 422	53.79 393	7.39 398	60.26 385	11.09 408	35.23 383	34.79 407

dongtai		43.51 355	44.07 356	41.82 380	63.75 373	21.90 404	63.80 360	72.05 333	39.59 363	33.35 391	54.54 391	41.04 171	57.30 392	10.75 409	17.77 409	46.26 403

LCM-MVSNet		28.07 372	23.85 380	40.71 381	27.46 422	18.93 409	30.82 410	46.19 390	12.76 409	16.40 407	34.70 408	1.90 418	48.69 403	20.25 392	24.22 401	54.51 395

FPMVS		35.40 366	33.67 370	40.57 382	46.34 406	28.74 393	41.05 400	57.05 380	20.37 400	22.27 405	53.38 394	6.87 401	44.94 407	8.62 410	47.11 355	48.01 401

WB-MVS		37.41 365	36.37 365	40.54 383	54.23 392	10.43 421	65.29 353	43.75 394	34.86 381	27.81 400	54.63 390	24.94 333	63.21 380	6.81 416	15.00 411	47.98 402

new_pmnet		33.56 370	31.89 372	38.59 384	49.01 402	20.42 407	51.01 389	37.92 404	20.58 398	23.45 404	46.79 399	6.66 403	49.28 402	20.00 395	31.57 391	46.09 404

mamv4		42.60 357	44.05 357	38.26 385	59.21 384	38.00 354	44.14 397	39.03 401	25.03 395	40.61 369	68.39 356	37.01 227	24.28 419	46.62 289	36.43 378	52.50 397

SSC-MVS		35.20 367	34.30 369	37.90 386	52.58 394	8.65 424	61.86 369	41.64 398	31.81 386	25.54 403	52.94 396	23.39 344	59.28 389	6.10 417	12.86 412	45.78 405

PMMVS2		26.71 376	22.98 381	37.87 387	36.89 411	8.51 425	42.51 399	29.32 414	19.09 402	13.01 411	37.54 402	2.23 416	53.11 397	14.54 404	11.71 413	51.99 399

Gipuma		27.47 374	24.26 379	37.12 388	60.55 383	29.17 390	11.68 415	60.00 377	14.18 407	10.52 416	15.12 417	2.20 417	63.01 381	8.39 411	35.65 380	19.18 413
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LF4IMVS		33.04 371	32.55 371	34.52 389	40.96 408	22.03 403	44.45 396	35.62 407	20.42 399	28.12 399	62.35 375	5.03 409	31.88 418	21.61 390	34.42 384	49.63 400

mvsany_test3		28.00 373	25.98 375	34.05 390	28.97 418	15.31 416	34.54 407	18.17 421	16.24 405	29.30 397	53.37 395	2.79 413	33.38 417	30.01 359	20.41 407	53.45 396

test_f		27.12 375	24.85 376	33.93 391	26.17 423	15.25 417	30.24 411	22.38 420	12.53 410	28.23 398	49.43 398	2.59 414	34.34 416	25.12 379	26.99 397	52.20 398

test_method		24.09 380	21.07 384	33.16 392	27.67 421	8.35 426	26.63 412	35.11 409	3.40 418	14.35 410	36.98 404	3.46 412	35.31 413	19.08 397	22.95 402	55.81 393

PMVS	19.57 22	25.07 378	22.43 383	32.99 393	23.12 424	22.98 399	40.98 401	35.19 408	15.99 406	11.95 415	35.87 407	1.47 421	49.29 401	5.41 419	31.90 390	26.70 412
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
APD_test1		26.46 377	24.41 378	32.62 394	37.58 410	21.74 405	40.50 402	30.39 412	11.45 411	16.33 408	43.76 400	1.63 420	41.62 408	11.24 407	26.82 398	34.51 408

test_vis3_rt		24.79 379	22.95 382	30.31 395	28.59 419	18.92 410	37.43 405	17.27 423	12.90 408	21.28 406	29.92 412	1.02 422	36.35 411	28.28 369	29.82 396	35.65 406

MVE	16.60 23	17.34 386	13.39 389	29.16 396	28.43 420	19.72 408	13.73 414	23.63 419	7.23 417	7.96 417	21.41 413	0.80 423	36.08 412	6.97 414	10.39 414	31.69 409
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		21.11 381	19.08 385	27.18 397	30.56 415	18.28 412	33.43 408	24.48 417	8.02 415	12.02 413	33.50 409	0.75 424	35.09 414	7.68 412	21.32 403	28.17 410

APD_test2		21.11 381	19.08 385	27.18 397	30.56 415	18.28 412	33.43 408	24.48 417	8.02 415	12.02 413	33.50 409	0.75 424	35.09 414	7.68 412	21.32 403	28.17 410

E-PMN		19.16 383	18.40 387	21.44 399	36.19 412	13.63 419	47.59 392	30.89 411	10.73 412	5.91 419	16.59 415	3.66 411	39.77 409	5.95 418	8.14 415	10.92 415

EMVS		18.42 384	17.66 388	20.71 400	34.13 414	12.64 420	46.94 393	29.94 413	10.46 414	5.58 420	14.93 418	4.23 410	38.83 410	5.24 420	7.51 417	10.67 416

DeepMVS_CX				13.10 401	21.34 425	8.99 423		10.02 425	10.59 413	7.53 418	30.55 411	1.82 419	14.55 420	6.83 415	7.52 416	15.75 414

wuyk23d		9.11 388	8.77 392	10.15 402	40.18 409	16.76 415	20.28 413	1.01 426	2.58 419	2.66 421	0.98 421	0.23 426	12.49 421	4.08 421	6.90 418	1.19 418

tmp_tt		9.44 387	10.68 390	5.73 403	2.49 426	4.21 427	10.48 416	18.04 422	0.34 420	12.59 412	20.49 414	11.39 387	7.03 422	13.84 406	6.46 419	5.95 417

testmvs		6.14 390	8.18 393	0.01 404	0.01 427	0.00 430	73.40 316	0.00 428	0.00 422	0.02 423	0.15 422	0.00 427	0.00 423	0.02 422	0.00 421	0.02 419

test123		6.01 391	8.01 394	0.01 404	0.00 428	0.01 429	71.93 330	0.00 428	0.00 422	0.02 423	0.11 423	0.00 427	0.00 423	0.02 422	0.00 421	0.02 419

mmdepth		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

uanet_test		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

cdsmvs_eth3d_5k		18.33 385	24.44 377	0.00 406	0.00 428	0.00 430	0.00 417	89.40 24	0.00 422	0.00 425	92.02 46	38.55 198	0.00 423	0.00 424	0.00 421	0.00 421

pcd_1.5k_mvsjas		3.15 392	4.20 395	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	37.77 204	0.00 423	0.00 424	0.00 421	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

ab-mvs-re		7.68 389	10.24 391	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	92.12 42	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 428	0.00 430	0.00 417	0.00 428	0.00 422	0.00 425	0.00 424	0.00 427	0.00 423	0.00 424	0.00 421	0.00 421

WAC-MVS						34.28 364								22.56 386

FOURS1					83.24 112	49.90 196	84.98 137	78.76 254	47.71 324	73.42 60

PC_three_1452									66.58 61	87.27 2	93.70 10	66.82 4	94.95 17	89.74 4	91.98 4	93.98 5

test_one_0601					89.39 22	57.29 22		88.09 54	57.21 239	82.06 13	93.39 18	54.94 33

eth-test2					0.00 428

eth-test					0.00 428

ZD-MVS					89.55 14	53.46 110		84.38 140	57.02 241	73.97 55	91.03 65	44.57 125	91.17 77	75.41 73	81.78 71

RE-MVS-def			66.66 203		80.96 178	48.14 250	81.54 239	76.98 287	46.42 334	62.75 184	89.42 106	29.28 304		60.52 180	72.06 171	83.19 249

IU-MVS					89.48 17	57.49 17		91.38 9	66.22 69	88.26 1				82.83 22	87.60 18	92.44 32

test_241102_TWO								88.76 40	57.50 233	83.60 6	94.09 3	56.14 25	96.37 6	82.28 26	87.43 20	92.55 30

test_241102_ONE					89.48 17	56.89 29		88.94 31	57.53 231	84.61 4	93.29 22	58.81 12	96.45 1

9.14			78.19 28		85.67 61		88.32 51	88.84 37	59.89 178	74.58 50	92.62 35	46.80 90	92.66 41	81.40 35	85.62 41

save fliter					85.35 68	56.34 41	89.31 40	81.46 196	61.55 149

test_0728_THIRD									58.00 219	81.91 14	93.64 12	56.54 21	96.44 2	81.64 31	86.86 26	92.23 37

test0726					89.40 20	57.45 19	92.32 7	88.63 44	57.71 227	83.14 9	93.96 6	55.17 29

GSMVS																88.13 153

test_part2					89.33 23	55.48 54				82.27 12

sam_mvs1												38.86 196				88.13 153

sam_mvs												35.99 247

MTGPA								81.31 199

test_post1							70.84 335				14.72 419	34.33 263	83.86 277	48.80 273

test_post											16.22 416	37.52 213	84.72 270

patchmatchnet-post											59.74 383	38.41 199	79.91 319

MTMP							87.27 77	15.34 424

gm-plane-assit					83.24 112	54.21 96			70.91 21		88.23 133		95.25 14	66.37 129

test9_res														78.72 48	85.44 43	91.39 66

TEST9					85.68 59	55.42 56	87.59 67	84.00 150	57.72 226	72.99 65	90.98 67	44.87 119	88.58 158

test_8					85.72 58	55.31 61	87.60 66	83.88 153	57.84 224	72.84 69	90.99 66	44.99 115	88.34 169

agg_prior2														75.65 68	85.11 47	91.01 78

agg_prior					85.64 62	54.92 76		83.61 160		72.53 74			88.10 179

test_prior4						56.39 40	87.15 81

test_prior2							89.04 43		61.88 144	73.55 58	91.46 63	48.01 78		74.73 77	85.46 42

旧先验2							81.73 232		45.53 340	74.66 47			70.48 373	58.31 199

新几何2							81.61 237

旧先验1					81.57 164	47.48 265		71.83 334			88.66 121	36.94 229			78.34 105	88.67 137

无先验							85.19 127	78.00 270	49.08 313				85.13 265	52.78 248		87.45 169

原ACMM2							83.77 175

test222					79.36 206	50.97 170	77.99 285	67.84 360	42.54 358	62.84 183	86.53 164	30.26 298			76.91 117	85.23 211

testdata2													77.81 338	45.64 295

segment_acmp												44.97 117

testdata1							77.55 288		64.14 101

plane_prior7					77.95 236	48.46 238

plane_prior6					78.42 231	49.39 211						36.04 245

plane_prior5								82.59 177					88.30 172	65.46 140	72.34 168	84.49 221

plane_prior4											83.28 204

plane_prior3						48.95 220			64.01 104	62.15 191

plane_prior2							85.76 107		63.60 113

plane_prior1					78.31 233

plane_prior						49.57 201	87.43 70		64.57 94						72.84 164

n2								0.00 428

nn								0.00 428

door-mid								41.31 399

test11								84.25 144

door								43.27 395

HQP5-MVS						51.56 159

HQP-NCC					79.02 215		88.00 55		65.45 81	64.48 159

ACMP_Plane					79.02 215		88.00 55		65.45 81	64.48 159

BP-MVS														66.70 126

HQP4-MVS										64.47 162			88.61 156			84.91 217

HQP3-MVS								83.68 156							73.12 160

HQP2-MVS												37.35 216

NP-MVS					78.76 220	50.43 180					85.12 178

MDTV_nov1_ep13_2view						43.62 313	71.13 334		54.95 271	59.29 225		36.76 232		46.33 292		87.32 172

MDTV_nov1_ep13			61.56 262		81.68 157	55.12 69	72.41 323	78.18 267	59.19 195	58.85 234	69.29 353	34.69 259	86.16 240	36.76 330	62.96 250

ACMMP++_ref															63.20 246

ACMMP++															59.38 272

Test By Simon												39.38 190

High-resolution multi-view benchmark