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.

MSP-MVS		82.30 5	83.47 1	78.80 48	82.99 111	52.71 124	85.04 121	88.63 33	66.08 55	86.77 3	92.75 22	72.05 1	91.46 61	83.35 8	93.53 1	92.23 32
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
MCST-MVS		83.01 1	83.30 2	82.15 10	92.84 2	57.58 14	93.77 1	91.10 6	75.95 3	77.10 27	93.09 19	54.15 27	95.57 12	85.80 3	85.87 34	93.31 11

DELS-MVS		82.32 4	82.50 3	81.79 11	86.80 42	56.89 25	92.77 2	86.30 74	77.83 1	77.88 24	92.13 30	60.24 6	94.78 19	78.97 30	89.61 7	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
DVP-MVS++		82.44 2	82.38 4	82.62 4	91.77 4	57.49 15	84.98 124	88.88 24	58.00 187	83.60 6	93.39 12	67.21 2	96.39 4	81.64 17	91.98 4	93.98 5

DPM-MVS		82.39 3	82.36 5	82.49 5	80.12 175	59.50 5	92.24 8	90.72 9	69.37 23	83.22 8	94.47 2	63.81 5	93.18 29	74.02 66	93.25 2	94.80 1

CNVR-MVS		81.76 7	81.90 6	81.33 17	90.04 10	57.70 12	91.71 9	88.87 26	70.31 17	77.64 26	93.87 7	52.58 34	93.91 25	84.17 5	87.92 15	92.39 28

SED-MVS		81.92 6	81.75 7	82.44 7	89.48 17	56.89 25	92.48 3	88.94 22	57.50 201	84.61 4	94.09 3	58.81 11	96.37 6	82.28 13	87.60 17	94.06 3

patch_mono-2		80.84 10	81.59 8	78.62 55	90.34 9	53.77 93	88.08 50	88.36 40	76.17 2	79.40 22	91.09 49	55.43 19	90.09 101	85.01 4	80.40 78	91.99 41

DeepPCF-MVS	69.37 1	80.65 11	81.56 9	77.94 73	85.46 58	49.56 190	90.99 19	86.66 68	70.58 15	80.07 19	95.30 1	56.18 17	90.97 76	82.57 12	86.22 32	93.28 12

CANet		80.90 9	81.17 10	80.09 30	87.62 37	54.21 86	91.60 12	86.47 70	73.13 6	79.89 20	93.10 17	49.88 54	92.98 30	84.09 7	84.75 46	93.08 16

DVP-MVS		81.30 8	81.00 11	82.20 8	89.40 20	57.45 17	92.34 5	89.99 13	57.71 195	81.91 12	93.64 10	55.17 20	96.44 2	81.68 15	87.13 20	92.72 23
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
HPM-MVS++		80.50 12	80.71 12	79.88 32	87.34 39	55.20 60	89.93 27	87.55 55	66.04 58	79.46 21	93.00 21	53.10 31	91.76 55	80.40 23	89.56 8	92.68 24

CSCG		80.41 13	79.72 13	82.49 5	89.12 25	57.67 13	89.29 38	91.54 3	59.19 163	71.82 67	90.05 77	59.72 9	96.04 10	78.37 35	88.40 13	93.75 7

DPE-MVS		79.82 16	79.66 14	80.29 24	89.27 24	55.08 65	88.70 44	87.92 46	55.55 231	81.21 15	93.69 9	56.51 16	94.27 22	78.36 36	85.70 36	91.51 54
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PS-MVSNAJ		80.06 14	79.52 15	81.68 13	85.58 55	60.97 3	91.69 10	87.02 60	70.62 14	80.75 17	93.22 16	37.77 173	92.50 40	82.75 10	86.25 31	91.57 51

xiu_mvs_v2_base		79.86 15	79.31 16	81.53 14	85.03 67	60.73 4	91.65 11	86.86 63	70.30 18	80.77 16	93.07 20	37.63 178	92.28 45	82.73 11	85.71 35	91.57 51

NCCC		79.57 17	79.23 17	80.59 20	89.50 15	56.99 23	91.38 14	88.17 42	67.71 38	73.81 43	92.75 22	46.88 72	93.28 28	78.79 33	84.07 51	91.50 55

dcpmvs_2		79.33 18	78.94 18	80.49 21	89.75 12	56.54 31	84.83 130	83.68 139	67.85 35	69.36 84	90.24 69	60.20 7	92.10 50	84.14 6	80.40 78	92.82 20

SMA-MVS		79.10 19	78.76 19	80.12 28	84.42 75	55.87 45	87.58 62	86.76 65	61.48 123	80.26 18	93.10 17	46.53 77	92.41 42	79.97 24	88.77 10	92.08 36
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
EPNet		78.36 24	78.49 20	77.97 71	85.49 57	52.04 136	89.36 36	84.07 132	73.22 5	77.03 28	91.72 40	49.32 58	90.17 100	73.46 70	82.77 56	91.69 46
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TSAR-MVS + MP.		78.31 25	78.26 21	78.48 59	81.33 150	56.31 37	81.59 214	86.41 71	69.61 22	81.72 14	88.16 113	55.09 22	88.04 161	74.12 65	86.31 30	91.09 65
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APDe-MVS		78.44 21	78.20 22	79.19 38	88.56 26	54.55 80	89.76 31	87.77 50	55.91 226	78.56 23	92.49 26	48.20 60	92.65 38	79.49 25	83.04 55	90.39 78

9.14			78.19 23		85.67 53		88.32 48	88.84 27	59.89 146	74.58 38	92.62 25	46.80 73	92.66 37	81.40 21	85.62 37

lupinMVS		78.38 23	78.11 24	79.19 38	83.02 109	55.24 57	91.57 13	84.82 112	69.12 24	76.67 29	92.02 34	44.82 99	90.23 98	80.83 22	80.09 82	92.08 36

alignmvs		78.08 27	77.98 25	78.39 63	83.53 92	53.22 112	89.77 30	85.45 88	66.11 53	76.59 31	91.99 36	54.07 28	89.05 122	77.34 43	77.00 108	92.89 19

VNet		77.99 29	77.92 26	78.19 67	87.43 38	50.12 178	90.93 20	91.41 4	67.48 41	75.12 33	90.15 75	46.77 74	91.00 73	73.52 69	78.46 99	93.44 9

canonicalmvs		78.17 26	77.86 27	79.12 42	84.30 77	54.22 85	87.71 57	84.57 121	67.70 39	77.70 25	92.11 33	50.90 45	89.95 104	78.18 39	77.54 105	93.20 14

DeepC-MVS_fast	67.50 3	78.00 28	77.63 28	79.13 41	88.52 27	55.12 62	89.95 26	85.98 79	68.31 27	71.33 74	92.75 22	45.52 89	90.37 91	71.15 79	85.14 42	91.91 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + GP.		77.82 30	77.59 29	78.49 58	85.25 63	50.27 177	90.02 24	90.57 10	56.58 220	74.26 40	91.60 44	54.26 25	92.16 47	75.87 49	79.91 86	93.05 17

WTY-MVS		77.47 34	77.52 30	77.30 85	88.33 30	46.25 255	88.46 47	90.32 11	71.40 11	72.32 63	91.72 40	53.44 29	92.37 43	66.28 106	75.42 122	93.28 12

SF-MVS		77.64 32	77.42 31	78.32 65	83.75 89	52.47 129	86.63 83	87.80 47	58.78 175	74.63 36	92.38 27	47.75 64	91.35 63	78.18 39	86.85 24	91.15 64

casdiffmvs_mvg		77.75 31	77.28 32	79.16 40	80.42 171	54.44 82	87.76 56	85.46 87	71.67 9	71.38 73	88.35 108	51.58 38	91.22 66	79.02 29	79.89 88	91.83 45
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS-test		77.20 36	77.25 33	77.05 91	84.60 72	49.04 201	89.42 34	85.83 82	65.90 59	72.85 55	91.98 37	45.10 92	91.27 64	75.02 58	84.56 47	90.84 70

LFMVS		78.52 20	77.14 34	82.67 3	89.58 13	58.90 7	91.27 17	88.05 44	63.22 96	74.63 36	90.83 58	41.38 143	94.40 20	75.42 55	79.90 87	94.72 2

PHI-MVS		77.49 33	77.00 35	78.95 43	85.33 61	50.69 161	88.57 46	88.59 36	58.14 184	73.60 44	93.31 14	43.14 120	93.79 26	73.81 67	88.53 12	92.37 29

MG-MVS		78.42 22	76.99 36	82.73 2	93.17 1	64.46 1	89.93 27	88.51 38	64.83 71	73.52 46	88.09 114	48.07 61	92.19 46	62.24 134	84.53 48	91.53 53

casdiffmvs		77.36 35	76.85 37	78.88 46	80.40 172	54.66 78	87.06 74	85.88 80	72.11 8	71.57 70	88.63 106	50.89 47	90.35 92	76.00 48	79.11 94	91.63 48
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ETV-MVS		77.17 37	76.74 38	78.48 59	81.80 134	54.55 80	86.13 91	85.33 93	68.20 29	73.10 51	90.52 63	45.23 91	90.66 84	79.37 26	80.95 70	90.22 82

CS-MVS		76.77 44	76.70 39	76.99 96	83.55 91	48.75 209	88.60 45	85.18 101	66.38 48	72.47 61	91.62 43	45.53 88	90.99 75	74.48 61	82.51 58	91.23 62

PVSNet_Blended		76.53 47	76.54 40	76.50 106	85.91 48	51.83 142	88.89 42	84.24 129	67.82 36	69.09 86	89.33 92	46.70 75	88.13 157	75.43 53	81.48 69	89.55 97

jason		77.01 39	76.45 41	78.69 52	79.69 180	54.74 72	90.56 22	83.99 135	68.26 28	74.10 41	90.91 55	42.14 131	89.99 103	79.30 27	79.12 93	91.36 59
jason: jason.
train_agg		76.91 40	76.40 42	78.45 61	85.68 51	55.42 51	87.59 60	84.00 133	57.84 192	72.99 52	90.98 52	44.99 94	88.58 139	78.19 37	85.32 40	91.34 61

SteuartSystems-ACMMP		77.08 38	76.33 43	79.34 36	80.98 154	55.31 55	89.76 31	86.91 62	62.94 100	71.65 68	91.56 45	42.33 127	92.56 39	77.14 44	83.69 53	90.15 85
Skip Steuart: Steuart Systems R&D Blog.
DeepC-MVS	67.15 4	76.90 42	76.27 44	78.80 48	80.70 164	55.02 66	86.39 85	86.71 66	66.96 44	67.91 93	89.97 79	48.03 62	91.41 62	75.60 52	84.14 50	89.96 90
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline		76.86 43	76.24 45	78.71 51	80.47 170	54.20 88	83.90 156	84.88 111	71.38 12	71.51 71	89.15 95	50.51 48	90.55 88	75.71 50	78.65 97	91.39 57

PAPM		76.76 45	76.07 46	78.81 47	80.20 173	59.11 6	86.86 80	86.23 75	68.60 26	70.18 83	88.84 100	51.57 39	87.16 183	65.48 112	86.68 27	90.15 85

APD-MVS		76.15 52	75.68 47	77.54 79	88.52 27	53.44 103	87.26 71	85.03 107	53.79 247	74.91 34	91.68 42	43.80 107	90.31 94	74.36 62	81.82 65	88.87 111
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMMP_NAP		76.43 48	75.66 48	78.73 50	81.92 132	54.67 77	84.06 152	85.35 92	61.10 128	72.99 52	91.50 46	40.25 151	91.00 73	76.84 45	86.98 22	90.51 77

MAR-MVS		76.76 45	75.60 49	80.21 25	90.87 7	54.68 76	89.14 39	89.11 19	62.95 99	70.54 81	92.33 28	41.05 144	94.95 17	57.90 178	86.55 29	91.00 67
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
MVS		76.91 40	75.48 50	81.23 18	84.56 73	55.21 59	80.23 237	91.64 2	58.65 177	65.37 118	91.48 47	45.72 86	95.05 16	72.11 77	89.52 9	93.44 9

CLD-MVS		75.60 60	75.39 51	76.24 110	80.69 165	52.40 130	90.69 21	86.20 76	74.40 4	65.01 123	88.93 97	42.05 133	90.58 87	76.57 46	73.96 133	85.73 171
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS_111021_HR		76.39 49	75.38 52	79.42 35	85.33 61	56.47 33	88.15 49	84.97 108	65.15 69	66.06 110	89.88 80	43.79 108	92.16 47	75.03 57	80.03 85	89.64 96

DROMVSNet		75.30 62	75.20 53	75.62 125	80.98 154	49.00 202	87.43 63	84.68 118	63.49 93	70.97 78	90.15 75	42.86 124	91.14 70	74.33 63	81.90 64	86.71 156

CDPH-MVS		76.05 54	75.19 54	78.62 55	86.51 44	54.98 68	87.32 66	84.59 120	58.62 178	70.75 79	90.85 57	43.10 122	90.63 86	70.50 83	84.51 49	90.24 81

EIA-MVS		75.92 55	75.18 55	78.13 68	85.14 64	51.60 146	87.17 72	85.32 94	64.69 72	68.56 89	90.53 62	45.79 85	91.58 58	67.21 99	82.18 62	91.20 63

MP-MVS-pluss		75.54 61	75.03 56	77.04 92	81.37 149	52.65 126	84.34 143	84.46 122	61.16 126	69.14 85	91.76 39	39.98 157	88.99 127	78.19 37	84.89 45	89.48 99
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ZNCC-MVS		75.82 59	75.02 57	78.23 66	83.88 87	53.80 92	86.91 79	86.05 78	59.71 149	67.85 94	90.55 61	42.23 129	91.02 72	72.66 75	85.29 41	89.87 93

VDD-MVS		76.08 53	74.97 58	79.44 34	84.27 79	53.33 109	91.13 18	85.88 80	65.33 66	72.37 62	89.34 90	32.52 239	92.76 36	77.90 41	75.96 116	92.22 34

MVS_Test		75.85 56	74.93 59	78.62 55	84.08 81	55.20 60	83.99 154	85.17 102	68.07 32	73.38 48	82.76 182	50.44 49	89.00 125	65.90 108	80.61 74	91.64 47

SD-MVS		76.18 51	74.85 60	80.18 26	85.39 59	56.90 24	85.75 100	82.45 163	56.79 215	74.48 39	91.81 38	43.72 111	90.75 82	74.61 60	78.65 97	92.91 18
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
test_yl		75.85 56	74.83 61	78.91 44	88.08 34	51.94 138	91.30 15	89.28 16	57.91 189	71.19 76	89.20 93	42.03 134	92.77 34	69.41 86	75.07 127	92.01 39

DCV-MVSNet		75.85 56	74.83 61	78.91 44	88.08 34	51.94 138	91.30 15	89.28 16	57.91 189	71.19 76	89.20 93	42.03 134	92.77 34	69.41 86	75.07 127	92.01 39

diffmvs		75.11 67	74.65 63	76.46 107	78.52 204	53.35 107	83.28 177	79.94 200	70.51 16	71.64 69	88.72 101	46.02 82	86.08 217	77.52 42	75.75 120	89.96 90
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline2		75.15 66	74.54 64	76.98 97	81.67 137	51.74 144	83.84 157	91.94 1	69.97 19	58.98 196	86.02 142	59.73 8	91.73 56	68.37 92	70.40 163	87.48 139

MP-MVS		74.99 68	74.33 65	76.95 98	82.89 115	53.05 118	85.63 104	83.50 144	57.86 191	67.25 97	90.24 69	43.38 117	88.85 133	76.03 47	82.23 61	88.96 109
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PAPR		75.20 65	74.13 66	78.41 62	88.31 31	55.10 64	84.31 144	85.66 84	63.76 86	67.55 95	90.73 59	43.48 116	89.40 115	66.36 105	77.03 107	90.73 72

ET-MVSNet_ETH3D		75.23 64	74.08 67	78.67 53	84.52 74	55.59 47	88.92 41	89.21 18	68.06 33	53.13 267	90.22 71	49.71 55	87.62 175	72.12 76	70.82 158	92.82 20

CHOSEN 1792x2688		76.24 50	74.03 68	82.88 1	83.09 106	62.84 2	85.73 102	85.39 90	69.79 20	64.87 125	83.49 172	41.52 142	93.69 27	70.55 82	81.82 65	92.12 35

GST-MVS		74.87 69	73.90 69	77.77 74	83.30 99	53.45 102	85.75 100	85.29 96	59.22 162	66.50 105	89.85 81	40.94 145	90.76 81	70.94 81	83.35 54	89.10 107

Effi-MVS+		75.24 63	73.61 70	80.16 27	81.92 132	57.42 19	85.21 113	76.71 266	60.68 137	73.32 49	89.34 90	47.30 68	91.63 57	68.28 93	79.72 89	91.42 56

PVSNet_BlendedMVS		73.42 85	73.30 71	73.76 168	85.91 48	51.83 142	86.18 90	84.24 129	65.40 63	69.09 86	80.86 209	46.70 75	88.13 157	75.43 53	65.92 195	81.33 246

CANet_DTU		73.71 81	73.14 72	75.40 130	82.61 124	50.05 179	84.67 137	79.36 216	69.72 21	75.39 32	90.03 78	29.41 262	85.93 223	67.99 95	79.11 94	90.22 82

HY-MVS	67.03 5	73.90 77	73.14 72	76.18 115	84.70 71	47.36 238	75.56 268	86.36 73	66.27 50	70.66 80	83.91 165	51.05 43	89.31 116	67.10 100	72.61 144	91.88 43

HFP-MVS		74.37 71	73.13 74	78.10 69	84.30 77	53.68 95	85.58 105	84.36 124	56.82 213	65.78 114	90.56 60	40.70 149	90.90 77	69.18 88	80.88 71	89.71 94

h-mvs33		73.95 76	72.89 75	77.15 90	80.17 174	50.37 171	84.68 135	83.33 145	68.08 30	71.97 65	88.65 105	42.50 125	91.15 69	78.82 31	57.78 262	89.91 92

ACMMPR		73.76 79	72.61 76	77.24 89	83.92 85	52.96 121	85.58 105	84.29 125	56.82 213	65.12 119	90.45 64	37.24 188	90.18 99	69.18 88	80.84 72	88.58 119

EI-MVSNet-Vis-set		73.19 88	72.60 77	74.99 140	82.56 125	49.80 186	82.55 192	89.00 21	66.17 52	65.89 113	88.98 96	43.83 106	92.29 44	65.38 119	69.01 171	82.87 223

region2R		73.75 80	72.55 78	77.33 83	83.90 86	52.98 120	85.54 108	84.09 131	56.83 212	65.10 120	90.45 64	37.34 186	90.24 97	68.89 90	80.83 73	88.77 115

3Dnovator	64.70 6	74.46 70	72.48 79	80.41 23	82.84 117	55.40 54	83.08 181	88.61 35	67.61 40	59.85 179	88.66 102	34.57 221	93.97 23	58.42 168	88.70 11	91.85 44

PVSNet_Blended_VisFu		73.40 86	72.44 80	76.30 108	81.32 151	54.70 75	85.81 96	78.82 226	63.70 87	64.53 130	85.38 150	47.11 71	87.38 180	67.75 96	77.55 104	86.81 155

test2506		72.91 91	72.43 81	74.32 152	80.12 175	44.18 280	83.19 178	84.77 115	64.02 79	65.97 111	87.43 125	47.67 65	88.72 134	59.08 159	79.66 90	90.08 87

TESTMET0.1,1		72.86 92	72.33 82	74.46 146	81.98 131	50.77 159	85.13 116	85.47 86	66.09 54	67.30 96	83.69 170	37.27 187	83.57 252	65.06 120	78.97 96	89.05 108

MVSTER		73.25 87	72.33 82	76.01 120	85.54 56	53.76 94	83.52 162	87.16 58	67.06 43	63.88 143	81.66 201	52.77 32	90.44 89	64.66 121	64.69 200	83.84 205

CostFormer		73.89 78	72.30 84	78.66 54	82.36 128	56.58 28	75.56 268	85.30 95	66.06 56	70.50 82	76.88 252	57.02 14	89.06 121	68.27 94	68.74 173	90.33 80

MSLP-MVS++		74.21 73	72.25 85	80.11 29	81.45 147	56.47 33	86.32 87	79.65 208	58.19 183	66.36 106	92.29 29	36.11 204	90.66 84	67.39 97	82.49 59	93.18 15

iter_conf05		73.51 84	72.24 86	77.33 83	87.93 36	55.97 43	87.90 55	70.81 313	68.72 25	64.04 138	84.36 159	47.54 66	90.87 78	71.11 80	67.75 181	85.13 181

thisisatest0515		73.64 82	72.20 87	77.97 71	81.63 138	53.01 119	86.69 82	88.81 28	62.53 106	64.06 137	85.65 146	52.15 37	92.50 40	58.43 166	69.84 166	88.39 123

MVSFormer		73.53 83	72.19 88	77.57 78	83.02 109	55.24 57	81.63 211	81.44 179	50.28 271	76.67 29	90.91 55	44.82 99	86.11 212	60.83 145	80.09 82	91.36 59

VDDNet		74.37 71	72.13 89	81.09 19	79.58 181	56.52 32	90.02 24	86.70 67	52.61 256	71.23 75	87.20 128	31.75 249	93.96 24	74.30 64	75.77 119	92.79 22

baseline1		72.51 98	72.12 90	73.69 171	85.05 65	44.46 274	83.51 166	86.13 77	71.61 10	64.64 127	87.97 117	55.00 23	89.48 114	59.07 160	56.05 275	87.13 146

API-MVS		74.17 74	72.07 91	80.49 21	90.02 11	58.55 8	87.30 68	84.27 126	57.51 200	65.77 115	87.77 120	41.61 140	95.97 11	51.71 223	82.63 57	86.94 147

PMMVS		72.98 89	72.05 92	75.78 124	83.57 90	48.60 212	84.08 150	82.85 158	61.62 119	68.24 91	90.33 68	28.35 266	87.78 170	72.71 74	76.69 110	90.95 68

IB-MVS	68.87 2	74.01 75	72.03 93	79.94 31	83.04 108	55.50 49	90.24 23	88.65 31	67.14 42	61.38 168	81.74 200	53.21 30	94.28 21	60.45 153	62.41 223	90.03 89
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
EI-MVSNet-UG-set		72.37 99	71.73 94	74.29 153	81.60 140	49.29 196	81.85 206	88.64 32	65.29 68	65.05 121	88.29 111	43.18 118	91.83 54	63.74 124	67.97 178	81.75 233

XVS		72.92 90	71.62 95	76.81 100	83.41 94	52.48 127	84.88 128	83.20 151	58.03 185	63.91 141	89.63 85	35.50 211	89.78 107	65.50 110	80.50 76	88.16 124

nrg030		72.27 104	71.56 96	74.42 148	75.93 242	50.60 163	86.97 76	83.21 150	62.75 102	67.15 98	84.38 157	50.07 51	86.66 198	71.19 78	62.37 224	85.99 166

HPM-MVS		72.60 95	71.50 97	75.89 122	82.02 130	51.42 151	80.70 231	83.05 153	56.12 225	64.03 139	89.53 86	37.55 180	88.37 147	70.48 84	80.04 84	87.88 131
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		72.59 97	71.46 98	76.00 121	82.93 114	52.32 133	86.93 78	82.48 162	55.15 234	63.65 145	90.44 67	35.03 218	88.53 143	68.69 91	77.83 103	87.15 145

HQP-MVS		72.34 100	71.44 99	75.03 138	79.02 191	51.56 147	88.00 51	83.68 139	65.45 60	64.48 131	85.13 151	37.35 184	88.62 137	66.70 101	73.12 138	84.91 185

VPNet		72.07 105	71.42 100	74.04 159	78.64 202	47.17 243	89.91 29	87.97 45	72.56 7	64.66 126	85.04 153	41.83 138	88.33 150	61.17 143	60.97 230	86.62 157

MS-PatchMatch		72.34 100	71.26 101	75.61 126	82.38 127	55.55 48	88.00 51	89.95 14	65.38 64	56.51 241	80.74 211	32.28 242	92.89 31	57.95 177	88.10 14	78.39 281

MTAPA		72.73 93	71.22 102	77.27 87	81.54 144	53.57 97	67.06 318	81.31 181	59.41 156	68.39 90	90.96 54	36.07 206	89.01 124	73.80 68	82.45 60	89.23 102

PGM-MVS		72.60 95	71.20 103	76.80 103	82.95 112	52.82 123	83.07 182	82.14 165	56.51 221	63.18 150	89.81 82	35.68 210	89.76 109	67.30 98	80.19 81	87.83 132

Fast-Effi-MVS+		72.73 93	71.15 104	77.48 80	82.75 119	54.76 71	86.77 81	80.64 190	63.05 98	65.93 112	84.01 163	44.42 103	89.03 123	56.45 194	76.36 115	88.64 117

ECVR-MVS		71.81 108	71.00 105	74.26 154	80.12 175	43.49 285	84.69 134	82.16 164	64.02 79	64.64 127	87.43 125	35.04 217	89.21 118	61.24 142	79.66 90	90.08 87

mvs_anonymous		72.29 102	70.74 106	76.94 99	82.85 116	54.72 74	78.43 253	81.54 177	63.77 85	61.69 167	79.32 220	51.11 42	85.31 230	62.15 136	75.79 118	90.79 71

hse-mvs2		71.44 115	70.68 107	73.73 170	76.34 233	47.44 237	79.45 246	79.47 212	68.08 30	71.97 65	86.01 144	42.50 125	86.93 191	78.82 31	53.46 299	86.83 154

VPA-MVSNet		71.12 117	70.66 108	72.49 193	78.75 197	44.43 276	87.64 58	90.02 12	63.97 82	65.02 122	81.58 203	42.14 131	87.42 179	63.42 126	63.38 212	85.63 175

3Dnovator+	62.71 7	72.29 102	70.50 109	77.65 77	83.40 97	51.29 155	87.32 66	86.40 72	59.01 170	58.49 209	88.32 110	32.40 240	91.27 64	57.04 187	82.15 63	90.38 79

MVP-Stereo		70.97 121	70.44 110	72.59 190	76.03 241	51.36 152	85.02 123	86.99 61	60.31 141	56.53 240	78.92 226	40.11 155	90.00 102	60.00 157	90.01 6	76.41 303
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test1111		71.06 119	70.42 111	72.97 183	79.48 182	41.49 304	84.82 131	82.74 159	64.20 77	62.98 153	87.43 125	35.20 214	87.92 163	58.54 165	78.42 100	89.49 98

mPP-MVS		71.79 110	70.38 112	76.04 119	82.65 123	52.06 135	84.45 140	81.78 174	55.59 230	62.05 165	89.68 84	33.48 231	88.28 154	65.45 115	78.24 102	87.77 134

DP-MVS Recon		71.99 106	70.31 113	77.01 94	90.65 8	53.44 103	89.37 35	82.97 156	56.33 223	63.56 148	89.47 87	34.02 225	92.15 49	54.05 206	72.41 145	85.43 178

xiu_mvs_v1_base_debu		71.60 111	70.29 114	75.55 127	77.26 223	53.15 113	85.34 109	79.37 213	55.83 227	72.54 57	90.19 72	22.38 306	86.66 198	73.28 71	76.39 112	86.85 151

xiu_mvs_v1_base		71.60 111	70.29 114	75.55 127	77.26 223	53.15 113	85.34 109	79.37 213	55.83 227	72.54 57	90.19 72	22.38 306	86.66 198	73.28 71	76.39 112	86.85 151

xiu_mvs_v1_base_debi		71.60 111	70.29 114	75.55 127	77.26 223	53.15 113	85.34 109	79.37 213	55.83 227	72.54 57	90.19 72	22.38 306	86.66 198	73.28 71	76.39 112	86.85 151

FIs		70.00 138	70.24 117	69.30 249	77.93 214	38.55 318	83.99 154	87.72 52	66.86 45	57.66 222	84.17 162	52.28 35	85.31 230	52.72 220	68.80 172	84.02 196

sss		70.49 129	70.13 118	71.58 217	81.59 141	39.02 315	80.78 230	84.71 117	59.34 158	66.61 102	88.09 114	37.17 189	85.52 226	61.82 139	71.02 156	90.20 84

EPP-MVSNet		71.14 116	70.07 119	74.33 151	79.18 188	46.52 249	83.81 158	86.49 69	56.32 224	57.95 215	84.90 155	54.23 26	89.14 120	58.14 173	69.65 168	87.33 142

PAPM_NR		71.80 109	69.98 120	77.26 88	81.54 144	53.34 108	78.60 252	85.25 99	53.46 249	60.53 176	88.66 102	45.69 87	89.24 117	56.49 191	79.62 92	89.19 104

HQP_MVS		70.96 122	69.91 121	74.12 157	77.95 212	49.57 188	85.76 98	82.59 160	63.60 90	62.15 163	83.28 176	36.04 207	88.30 152	65.46 113	72.34 146	84.49 188

tpmrst		71.04 120	69.77 122	74.86 141	83.19 103	55.86 46	75.64 267	78.73 230	67.88 34	64.99 124	73.73 281	49.96 53	79.56 287	65.92 107	67.85 180	89.14 106

SR-MVS		70.92 123	69.73 123	74.50 145	83.38 98	50.48 167	84.27 145	79.35 217	48.96 281	66.57 104	90.45 64	33.65 230	87.11 184	66.42 103	74.56 130	85.91 169

iter_conf_final		71.46 114	69.68 124	76.81 100	86.03 46	53.49 98	84.73 132	74.37 286	60.27 142	66.28 107	84.36 159	35.14 216	90.87 78	65.41 117	70.51 161	86.05 165

OPM-MVS		70.75 126	69.58 125	74.26 154	75.55 247	51.34 153	86.05 93	83.29 149	61.94 115	62.95 154	85.77 145	34.15 224	88.44 145	65.44 116	71.07 155	82.99 220
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CDS-MVSNet		70.48 130	69.43 126	73.64 172	77.56 218	48.83 208	83.51 166	77.45 252	63.27 95	62.33 160	85.54 149	43.85 105	83.29 256	57.38 186	74.00 132	88.79 114
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
1314		71.11 118	69.41 127	76.22 111	79.32 185	50.49 166	80.23 237	85.14 105	59.44 155	58.93 198	88.89 99	33.83 229	89.60 113	61.49 140	77.42 106	88.57 120

1112_ss		70.05 136	69.37 128	72.10 199	80.77 163	42.78 292	85.12 119	76.75 264	59.69 150	61.19 170	92.12 31	47.48 67	83.84 247	53.04 213	68.21 175	89.66 95

Vis-MVSNet		70.61 128	69.34 129	74.42 148	80.95 159	48.49 217	86.03 94	77.51 251	58.74 176	65.55 117	87.78 119	34.37 222	85.95 222	52.53 221	80.61 74	88.80 113
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
QAPM		71.88 107	69.33 130	79.52 33	82.20 129	54.30 84	86.30 88	88.77 29	56.61 219	59.72 181	87.48 123	33.90 227	95.36 13	47.48 250	81.49 68	88.90 110

ACMMP		70.81 125	69.29 131	75.39 131	81.52 146	51.92 140	83.43 169	83.03 154	56.67 218	58.80 203	88.91 98	31.92 247	88.58 139	65.89 109	73.39 137	85.67 172
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
XXY-MVS		70.18 132	69.28 132	72.89 186	77.64 216	42.88 291	85.06 120	87.50 56	62.58 105	62.66 158	82.34 193	43.64 113	89.83 106	58.42 168	63.70 207	85.96 168

ab-mvs		70.65 127	69.11 133	75.29 134	80.87 160	46.23 256	73.48 283	85.24 100	59.99 145	66.65 100	80.94 208	43.13 121	88.69 135	63.58 125	68.07 176	90.95 68

test-LLR		69.65 147	69.01 134	71.60 215	78.67 199	48.17 224	85.13 116	79.72 205	59.18 165	63.13 151	82.58 187	36.91 193	80.24 278	60.56 149	75.17 124	86.39 162

miper_enhance_ethall		69.77 143	68.90 135	72.38 195	78.93 194	49.91 182	83.29 176	78.85 224	64.90 70	59.37 189	79.46 218	52.77 32	85.16 235	63.78 123	58.72 245	82.08 229

EI-MVSNet		69.70 146	68.70 136	72.68 188	75.00 253	48.90 206	79.54 243	87.16 58	61.05 129	63.88 143	83.74 168	45.87 83	90.44 89	57.42 185	64.68 201	78.70 274

thisisatest0530		70.47 131	68.56 137	76.20 113	79.78 179	51.52 149	83.49 168	88.58 37	57.62 198	58.60 205	82.79 181	51.03 44	91.48 60	52.84 215	62.36 225	85.59 176

BH-w/o		70.02 137	68.51 138	74.56 144	82.77 118	50.39 170	86.60 84	78.14 241	59.77 148	59.65 182	85.57 148	39.27 162	87.30 181	49.86 233	74.94 129	85.99 166

tpm2		70.82 124	68.44 139	77.98 70	80.78 162	56.11 39	74.21 279	81.28 183	60.24 143	68.04 92	75.27 270	52.26 36	88.50 144	55.82 197	68.03 177	89.33 100

PCF-MVS	61.03 10	70.10 134	68.40 140	75.22 137	77.15 227	51.99 137	79.30 248	82.12 166	56.47 222	61.88 166	86.48 140	43.98 104	87.24 182	55.37 198	72.79 143	86.43 161
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_vis1_n_1920		68.59 165	68.31 141	69.44 248	69.16 307	41.51 303	84.63 138	68.58 322	58.80 174	73.26 50	88.37 107	25.30 289	80.60 273	79.10 28	67.55 182	86.23 164

UniMVSNet_NR-MVSNet		68.82 158	68.29 142	70.40 235	75.71 245	42.59 294	84.23 146	86.78 64	66.31 49	58.51 206	82.45 190	51.57 39	84.64 243	53.11 211	55.96 276	83.96 202

APD-MVS_3200maxsize		69.62 148	68.23 143	73.80 167	81.58 142	48.22 223	81.91 204	79.50 211	48.21 284	64.24 136	89.75 83	31.91 248	87.55 177	63.08 128	73.85 135	85.64 174

TAMVS		69.51 150	68.16 144	73.56 175	76.30 236	48.71 211	82.57 190	77.17 257	62.10 111	61.32 169	84.23 161	41.90 136	83.46 254	54.80 202	73.09 140	88.50 122

BH-RMVSNet		70.08 135	68.01 145	76.27 109	84.21 80	51.22 157	87.29 69	79.33 219	58.96 172	63.63 146	86.77 134	33.29 233	90.30 96	44.63 266	73.96 133	87.30 144

FC-MVSNet-test		67.49 184	67.91 146	66.21 280	76.06 239	33.06 336	80.82 229	87.18 57	64.44 74	54.81 251	82.87 179	50.40 50	82.60 258	48.05 247	66.55 189	82.98 221

MVS_111021_LR		69.07 152	67.91 146	72.54 191	77.27 222	49.56 190	79.77 241	73.96 291	59.33 160	60.73 174	87.82 118	30.19 258	81.53 264	69.94 85	72.19 148	86.53 158

GeoE		69.96 140	67.88 148	76.22 111	81.11 153	51.71 145	84.15 148	76.74 265	59.83 147	60.91 171	84.38 157	41.56 141	88.10 159	51.67 224	70.57 160	88.84 112

Anonymous202405211		70.11 133	67.88 148	76.79 104	87.20 40	47.24 242	89.49 33	77.38 254	54.88 239	66.14 108	86.84 133	20.93 316	91.54 59	56.45 194	71.62 151	91.59 49

114514_t		69.87 142	67.88 148	75.85 123	88.38 29	52.35 132	86.94 77	83.68 139	53.70 248	55.68 247	85.60 147	30.07 259	91.20 67	55.84 196	71.02 156	83.99 198

TR-MVS		69.71 144	67.85 151	75.27 135	82.94 113	48.48 218	87.40 65	80.86 187	57.15 208	64.61 129	87.08 130	32.67 238	89.64 112	46.38 257	71.55 153	87.68 137

PVSNet	62.49 8	69.27 151	67.81 152	73.64 172	84.41 76	51.85 141	84.63 138	77.80 245	66.42 47	59.80 180	84.95 154	22.14 311	80.44 276	55.03 199	75.11 126	88.62 118

cl22		68.85 156	67.69 153	72.35 196	78.07 211	49.98 181	82.45 195	78.48 236	62.50 107	58.46 210	77.95 232	49.99 52	85.17 234	62.55 131	58.72 245	81.90 231

v2v482		69.55 149	67.64 154	75.26 136	72.32 283	53.83 91	84.93 127	81.94 169	65.37 65	60.80 173	79.25 222	41.62 139	88.98 128	63.03 129	59.51 238	82.98 221

miper_ehance_all_eth		68.70 164	67.58 155	72.08 200	76.91 229	49.48 193	82.47 194	78.45 237	62.68 103	58.28 214	77.88 234	50.90 45	85.01 238	61.91 137	58.72 245	81.75 233

HyFIR lowres test		69.94 141	67.58 155	77.04 92	77.11 228	57.29 20	81.49 219	79.11 222	58.27 182	58.86 201	80.41 212	42.33 127	86.96 189	61.91 137	68.68 174	86.87 149

IS-MVSNet		68.80 160	67.55 157	72.54 191	78.50 205	43.43 286	81.03 225	79.35 217	59.12 168	57.27 232	86.71 135	46.05 81	87.70 172	44.32 268	75.60 121	86.49 159

OpenMVS	61.00 11	69.99 139	67.55 157	77.30 85	78.37 208	54.07 90	84.36 142	85.76 83	57.22 206	56.71 237	87.67 121	30.79 255	92.83 33	43.04 273	84.06 52	85.01 183

tpm		68.36 167	67.48 159	70.97 227	79.93 178	51.34 153	76.58 264	78.75 229	67.73 37	63.54 149	74.86 272	48.33 59	72.36 330	53.93 207	63.71 206	89.21 103

FMVSNet3		68.84 157	67.40 160	73.19 179	85.05 65	48.53 215	85.71 103	85.36 91	60.90 133	57.58 224	79.15 224	42.16 130	86.77 194	47.25 252	63.40 209	84.27 192

test-mter		68.36 167	67.29 161	71.60 215	78.67 199	48.17 224	85.13 116	79.72 205	53.38 250	63.13 151	82.58 187	27.23 276	80.24 278	60.56 149	75.17 124	86.39 162

Anonymous20240529		69.71 144	67.28 162	77.00 95	83.78 88	50.36 172	88.87 43	85.10 106	47.22 289	64.03 139	83.37 174	27.93 270	92.10 50	57.78 181	67.44 183	88.53 121

thres200		68.71 162	67.27 163	73.02 181	84.73 70	46.76 246	85.03 122	87.73 51	62.34 109	59.87 178	83.45 173	43.15 119	88.32 151	31.25 322	67.91 179	83.98 200

PS-MVSNAJss		68.78 161	67.17 164	73.62 174	73.01 273	48.33 222	84.95 126	84.81 113	59.30 161	58.91 200	79.84 216	37.77 173	88.86 132	62.83 130	63.12 218	83.67 208

UGNet		68.71 162	67.11 165	73.50 176	80.55 169	47.61 234	84.08 150	78.51 235	59.45 154	65.68 116	82.73 185	23.78 298	85.08 237	52.80 216	76.40 111	87.80 133
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
SR-MVS-dyc-post		68.27 171	66.87 166	72.48 194	80.96 156	48.14 226	81.54 215	76.98 260	46.42 296	62.75 156	89.42 88	31.17 253	86.09 216	60.52 151	72.06 149	83.19 216

v1144		68.81 159	66.82 167	74.80 142	72.34 282	53.46 100	84.68 135	81.77 175	64.25 76	60.28 177	77.91 233	40.23 152	88.95 129	60.37 154	59.52 237	81.97 230

UniMVSNet (Re)		67.71 179	66.80 168	70.45 233	74.44 258	42.93 290	82.42 196	84.90 110	63.69 88	59.63 183	80.99 207	47.18 69	85.23 233	51.17 227	56.75 267	83.19 216

WR-MVS		67.58 181	66.76 169	70.04 242	75.92 243	45.06 272	86.23 89	85.28 97	64.31 75	58.50 208	81.00 206	44.80 101	82.00 263	49.21 239	55.57 281	83.06 219

EPNet_dtu		66.25 210	66.71 170	64.87 290	78.66 201	34.12 331	82.80 187	75.51 277	61.75 117	64.47 134	86.90 132	37.06 190	72.46 329	43.65 271	69.63 169	88.02 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GA-MVS		69.04 153	66.70 171	76.06 118	75.11 249	52.36 131	83.12 180	80.23 196	63.32 94	60.65 175	79.22 223	30.98 254	88.37 147	61.25 141	66.41 190	87.46 140

RE-MVS-def			66.66 172		80.96 156	48.14 226	81.54 215	76.98 260	46.42 296	62.75 156	89.42 88	29.28 264		60.52 151	72.06 149	83.19 216

c3_l		67.97 174	66.66 172	71.91 211	76.20 238	49.31 195	82.13 200	78.00 243	61.99 113	57.64 223	76.94 249	49.41 56	84.93 239	60.62 148	57.01 266	81.49 237

FA-MVS(test-final)		69.00 155	66.60 174	76.19 114	83.48 93	47.96 232	74.73 275	82.07 167	57.27 205	62.18 162	78.47 230	36.09 205	92.89 31	53.76 209	71.32 154	87.73 135

BH-untuned		68.28 170	66.40 175	73.91 162	81.62 139	50.01 180	85.56 107	77.39 253	57.63 197	57.47 229	83.69 170	36.36 202	87.08 185	44.81 264	73.08 141	84.65 187

AUN-MVS		68.20 173	66.35 176	73.76 168	76.37 232	47.45 236	79.52 245	79.52 210	60.98 131	62.34 159	86.02 142	36.59 201	86.94 190	62.32 133	53.47 298	86.89 148

v148		68.24 172	66.35 176	73.88 163	71.76 286	51.47 150	84.23 146	81.90 173	63.69 88	58.94 197	76.44 257	43.72 111	87.78 170	60.63 147	55.86 278	82.39 227

tttt0517		68.33 169	66.29 178	74.46 146	78.08 210	49.06 198	80.88 228	89.08 20	54.40 244	54.75 253	80.77 210	51.31 41	90.33 93	49.35 237	58.01 256	83.99 198

HPM-MVS_fast		67.86 176	66.28 179	72.61 189	80.67 166	48.34 221	81.18 223	75.95 275	50.81 269	59.55 186	88.05 116	27.86 271	85.98 219	58.83 162	73.58 136	83.51 209

UA-Net		67.32 190	66.23 180	70.59 231	78.85 195	41.23 307	73.60 281	75.45 279	61.54 121	66.61 102	84.53 156	38.73 166	86.57 203	42.48 279	74.24 131	83.98 200

Test_1112_low_res		67.18 193	66.23 180	70.02 243	78.75 197	41.02 308	83.43 169	73.69 293	57.29 204	58.45 211	82.39 192	45.30 90	80.88 270	50.50 229	66.26 194	88.16 124

tfpn200view9		67.57 182	66.13 182	71.89 212	84.05 82	45.07 269	83.40 171	87.71 53	60.79 134	57.79 219	82.76 182	43.53 114	87.80 167	28.80 329	66.36 191	82.78 225

thres400		67.40 189	66.13 182	71.19 223	84.05 82	45.07 269	83.40 171	87.71 53	60.79 134	57.79 219	82.76 182	43.53 114	87.80 167	28.80 329	66.36 191	80.71 255

cascas		69.01 154	66.13 182	77.66 76	79.36 183	55.41 53	86.99 75	83.75 138	56.69 217	58.92 199	81.35 205	24.31 296	92.10 50	53.23 210	70.61 159	85.46 177

NR-MVSNet		67.25 191	65.99 185	71.04 226	73.27 271	43.91 281	85.32 112	84.75 116	66.05 57	53.65 265	82.11 196	45.05 93	85.97 221	47.55 249	56.18 273	83.24 214

cl____		67.43 186	65.93 186	71.95 208	76.33 234	48.02 229	82.58 189	79.12 221	61.30 125	56.72 236	76.92 250	46.12 79	86.44 205	57.98 175	56.31 270	81.38 245

DIV-MVS_self_test		67.43 186	65.93 186	71.94 209	76.33 234	48.01 230	82.57 190	79.11 222	61.31 124	56.73 235	76.92 250	46.09 80	86.43 206	57.98 175	56.31 270	81.39 244

CPTT-MVS		67.15 194	65.84 188	71.07 225	80.96 156	50.32 174	81.94 203	74.10 288	46.18 299	57.91 216	87.64 122	29.57 261	81.31 266	64.10 122	70.18 165	81.56 236

FMVSNet2		67.57 182	65.79 189	72.90 184	82.71 120	47.97 231	85.15 115	84.93 109	58.55 179	56.71 237	78.26 231	36.72 198	86.67 197	46.15 259	62.94 220	84.07 195

v144192		67.86 176	65.76 190	74.16 156	71.68 287	53.09 116	84.14 149	80.83 188	62.85 101	59.21 194	77.28 243	39.30 161	88.00 162	58.67 164	57.88 260	81.40 243

v1192		67.96 175	65.74 191	74.63 143	71.79 285	53.43 105	84.06 152	80.99 186	63.19 97	59.56 185	77.46 240	37.50 183	88.65 136	58.20 172	58.93 244	81.79 232

DU-MVS		66.84 203	65.74 191	70.16 238	73.27 271	42.59 294	81.50 217	82.92 157	63.53 92	58.51 206	82.11 196	40.75 146	84.64 243	53.11 211	55.96 276	83.24 214

Vis-MVSNet (Re-imp)		65.52 216	65.63 193	65.17 288	77.49 219	30.54 343	75.49 271	77.73 247	59.34 158	52.26 276	86.69 136	49.38 57	80.53 275	37.07 293	75.28 123	84.42 190

TranMVSNet+NR-MVSNet		66.94 200	65.61 194	70.93 228	73.45 268	43.38 287	83.02 184	84.25 127	65.31 67	58.33 213	81.90 199	39.92 158	85.52 226	49.43 236	54.89 286	83.89 204

V42		67.66 180	65.60 195	73.86 164	70.69 298	53.63 96	81.50 217	78.61 233	63.85 84	59.49 188	77.49 239	37.98 170	87.65 173	62.33 132	58.43 249	80.29 260

AdaColmap		67.86 176	65.48 196	75.00 139	88.15 33	54.99 67	86.10 92	76.63 268	49.30 278	57.80 218	86.65 137	29.39 263	88.94 131	45.10 263	70.21 164	81.06 250

GBi-Net		67.09 195	65.47 197	71.96 205	82.71 120	46.36 251	83.52 162	83.31 146	58.55 179	57.58 224	76.23 261	36.72 198	86.20 208	47.25 252	63.40 209	83.32 211

test1		67.09 195	65.47 197	71.96 205	82.71 120	46.36 251	83.52 162	83.31 146	58.55 179	57.58 224	76.23 261	36.72 198	86.20 208	47.25 252	63.40 209	83.32 211

EPMVS		68.45 166	65.44 199	77.47 81	84.91 68	56.17 38	71.89 299	81.91 172	61.72 118	60.85 172	72.49 295	36.21 203	87.06 186	47.32 251	71.62 151	89.17 105

thres100view900		66.87 202	65.42 200	71.24 221	83.29 100	43.15 288	81.67 210	87.78 48	59.04 169	55.92 245	82.18 195	43.73 109	87.80 167	28.80 329	66.36 191	82.78 225

IterMVS-LS		66.63 204	65.36 201	70.42 234	75.10 250	48.90 206	81.45 220	76.69 267	61.05 129	55.71 246	77.10 246	45.86 84	83.65 251	57.44 184	57.88 260	78.70 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
eth_miper_zixun_eth		66.98 199	65.28 202	72.06 201	75.61 246	50.40 169	81.00 226	76.97 263	62.00 112	56.99 234	76.97 248	44.84 98	85.58 225	58.75 163	54.42 290	80.21 261

v1921920		67.45 185	65.23 203	74.10 158	71.51 290	52.90 122	83.75 160	80.44 193	62.48 108	59.12 195	77.13 244	36.98 191	87.90 164	57.53 183	58.14 254	81.49 237

thres600view7		66.46 207	65.12 204	70.47 232	83.41 94	43.80 283	82.15 199	87.78 48	59.37 157	56.02 244	82.21 194	43.73 109	86.90 192	26.51 341	64.94 197	80.71 255

OMC-MVS		65.97 214	65.06 205	68.71 258	72.97 274	42.58 296	78.61 251	75.35 280	54.72 240	59.31 191	86.25 141	33.30 232	77.88 301	57.99 174	67.05 185	85.66 173

v8		67.25 191	64.99 206	74.04 159	72.89 276	53.31 110	82.37 197	80.11 198	61.54 121	54.29 258	76.02 266	42.89 123	88.41 146	58.43 166	56.36 268	80.39 259

Effi-MVS+-dtu		66.24 211	64.96 207	70.08 240	75.17 248	49.64 187	82.01 201	74.48 285	62.15 110	57.83 217	76.08 265	30.59 256	83.79 248	65.40 118	60.93 231	76.81 296

mvsmamba		66.93 201	64.88 208	73.09 180	75.06 251	47.26 240	83.36 175	69.21 319	62.64 104	55.68 247	81.43 204	29.72 260	89.20 119	63.35 127	63.50 208	82.79 224

v1240		66.99 198	64.68 209	73.93 161	71.38 293	52.66 125	83.39 173	79.98 199	61.97 114	58.44 212	77.11 245	35.25 213	87.81 166	56.46 193	58.15 252	81.33 246

LPG-MVS_test		66.44 208	64.58 210	72.02 202	74.42 259	48.60 212	83.07 182	80.64 190	54.69 241	53.75 263	83.83 166	25.73 287	86.98 187	60.33 155	64.71 198	80.48 257

gg-mvs-nofinetune		67.43 186	64.53 211	76.13 116	85.95 47	47.79 233	64.38 322	88.28 41	39.34 325	66.62 101	41.27 357	58.69 13	89.00 125	49.64 235	86.62 28	91.59 49

ACMP	61.11 9	66.24 211	64.33 212	72.00 204	74.89 255	49.12 197	83.18 179	79.83 203	55.41 233	52.29 274	82.68 186	25.83 285	86.10 214	60.89 144	63.94 205	80.78 253
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Baseline_NR-MVSNet		65.49 217	64.27 213	69.13 250	74.37 261	41.65 301	83.39 173	78.85 224	59.56 152	59.62 184	76.88 252	40.75 146	87.44 178	49.99 231	55.05 284	78.28 283

v10		66.61 205	64.20 214	73.83 166	72.59 279	53.37 106	81.88 205	79.91 202	61.11 127	54.09 260	75.60 268	40.06 156	88.26 155	56.47 192	56.10 274	79.86 265

Fast-Effi-MVS+-dtu		66.53 206	64.10 215	73.84 165	72.41 281	52.30 134	84.73 132	75.66 276	59.51 153	56.34 242	79.11 225	28.11 268	85.85 224	57.74 182	63.29 213	83.35 210

Anonymous20231211		66.08 213	63.67 216	73.31 177	83.07 107	48.75 209	86.01 95	84.67 119	45.27 303	56.54 239	76.67 255	28.06 269	88.95 129	52.78 217	59.95 233	82.23 228

PatchmatchNet		67.07 197	63.63 217	77.40 82	83.10 104	58.03 9	72.11 297	77.77 246	58.85 173	59.37 189	70.83 308	37.84 172	84.93 239	42.96 275	69.83 167	89.26 101
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm cat1		66.28 209	62.78 218	76.77 105	81.40 148	57.14 22	70.03 306	77.19 256	53.00 253	58.76 204	70.73 311	46.17 78	86.73 196	43.27 272	64.46 202	86.44 160

pm-mvs1		64.12 222	62.56 219	68.78 256	71.68 287	38.87 316	82.89 186	81.57 176	55.54 232	53.89 262	77.82 235	37.73 176	86.74 195	48.46 245	53.49 297	80.72 254

test0.0.03 1		62.54 237	62.44 220	62.86 300	72.28 284	29.51 349	82.93 185	78.78 227	59.18 165	53.07 268	82.41 191	36.91 193	77.39 305	37.45 289	58.96 243	81.66 235

miper_lstm_enhance		63.91 223	62.30 221	68.75 257	75.06 251	46.78 245	69.02 310	81.14 184	59.68 151	52.76 270	72.39 298	40.71 148	77.99 299	56.81 190	53.09 300	81.48 239

X-MVStestdata		65.85 215	62.20 222	76.81 100	83.41 94	52.48 127	84.88 128	83.20 151	58.03 185	63.91 141	4.82 376	35.50 211	89.78 107	65.50 110	80.50 76	88.16 124

FMVSNet1		64.57 218	62.11 223	71.96 205	77.32 221	46.36 251	83.52 162	83.31 146	52.43 258	54.42 256	76.23 261	27.80 272	86.20 208	42.59 278	61.34 229	83.32 211

ACMM	58.35 12	64.35 220	62.01 224	71.38 219	74.21 262	48.51 216	82.25 198	79.66 207	47.61 287	54.54 255	80.11 213	25.26 290	86.00 218	51.26 225	63.16 216	79.64 266
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS		63.77 226	61.67 225	70.08 240	72.68 278	51.24 156	80.44 233	75.51 277	60.51 139	51.41 279	73.70 284	32.08 244	78.91 289	54.30 204	54.35 291	80.08 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dp		64.41 219	61.58 226	72.90 184	82.40 126	54.09 89	72.53 289	76.59 269	60.39 140	55.68 247	70.39 312	35.18 215	76.90 309	39.34 285	61.71 227	87.73 135

test_djsdf		63.84 224	61.56 227	70.70 230	68.78 309	44.69 273	81.63 211	81.44 179	50.28 271	52.27 275	76.26 260	26.72 279	86.11 212	60.83 145	55.84 279	81.29 249

MDTV_nov1_ep13			61.56 227		81.68 136	55.12 62	72.41 291	78.18 240	59.19 163	58.85 202	69.29 316	34.69 220	86.16 211	36.76 297	62.96 219

D2MVS		63.49 228	61.39 229	69.77 244	69.29 306	48.93 205	78.89 250	77.71 248	60.64 138	49.70 288	72.10 303	27.08 277	83.48 253	54.48 203	62.65 221	76.90 295

tt0805		63.39 229	61.31 230	69.64 245	69.36 305	38.87 316	78.00 254	85.48 85	48.82 282	55.66 250	81.66 201	24.38 295	86.37 207	49.04 240	59.36 241	83.68 207

pmmvs5		62.80 236	61.18 231	67.66 267	69.53 304	42.37 299	82.65 188	75.19 281	54.30 246	52.03 277	78.51 229	31.64 250	80.67 271	48.60 243	58.15 252	79.95 264

CL-MVSNet_self_test		62.98 233	61.14 232	68.50 262	65.86 324	42.96 289	84.37 141	82.98 155	60.98 131	53.95 261	72.70 294	40.43 150	83.71 250	41.10 280	47.93 313	78.83 273

pmmvs4		63.34 230	61.07 233	70.16 238	70.14 300	50.53 165	79.97 240	71.41 310	55.08 235	54.12 259	78.58 228	32.79 237	82.09 262	50.33 230	57.22 265	77.86 287

RRT_MVS		63.68 227	61.01 234	71.70 213	73.48 267	45.98 258	81.19 222	76.08 273	54.33 245	52.84 269	79.27 221	22.21 309	87.65 173	54.13 205	55.54 282	81.46 240

jajsoiax		63.21 231	60.84 235	70.32 236	68.33 314	44.45 275	81.23 221	81.05 185	53.37 251	50.96 284	77.81 236	17.49 330	85.49 228	59.31 158	58.05 255	81.02 251

TransMVSNet (Re)		62.82 235	60.76 236	69.02 251	73.98 264	41.61 302	86.36 86	79.30 220	56.90 210	52.53 271	76.44 257	41.85 137	87.60 176	38.83 286	40.61 337	77.86 287

mvs_tets		62.96 234	60.55 237	70.19 237	68.22 317	44.24 279	80.90 227	80.74 189	52.99 254	50.82 286	77.56 237	16.74 334	85.44 229	59.04 161	57.94 257	80.89 252

UniMVSNet_ETH3D		62.51 238	60.49 238	68.57 261	68.30 315	40.88 310	73.89 280	79.93 201	51.81 264	54.77 252	79.61 217	24.80 293	81.10 267	49.93 232	61.35 228	83.73 206

CVMVSNet		60.85 249	60.44 239	62.07 301	75.00 253	32.73 338	79.54 243	73.49 296	36.98 333	56.28 243	83.74 168	29.28 264	69.53 338	46.48 256	63.23 214	83.94 203

FE-MVS		64.15 221	60.43 240	75.30 133	80.85 161	49.86 184	68.28 314	78.37 238	50.26 274	59.31 191	73.79 280	26.19 283	91.92 53	40.19 282	66.67 187	84.12 193

MIMVSNet		63.12 232	60.29 241	71.61 214	75.92 243	46.65 247	65.15 319	81.94 169	59.14 167	54.65 254	69.47 315	25.74 286	80.63 272	41.03 281	69.56 170	87.55 138

TAPA-MVS	56.12 14	61.82 245	60.18 242	66.71 276	78.48 206	37.97 321	75.19 273	76.41 271	46.82 292	57.04 233	86.52 139	27.67 274	77.03 307	26.50 342	67.02 186	85.14 180
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SCA		63.84 224	60.01 243	75.32 132	78.58 203	57.92 10	61.61 330	77.53 250	56.71 216	57.75 221	70.77 309	31.97 245	79.91 284	48.80 241	56.36 268	88.13 127

EG-PatchMatch MVS		62.40 242	59.59 244	70.81 229	73.29 270	49.05 199	85.81 96	84.78 114	51.85 263	44.19 312	73.48 287	15.52 339	89.85 105	40.16 283	67.24 184	73.54 322

XVG-OURS-SEG-HR		62.02 243	59.54 245	69.46 247	65.30 327	45.88 259	65.06 320	73.57 295	46.45 295	57.42 230	83.35 175	26.95 278	78.09 295	53.77 208	64.03 203	84.42 190

tpmvs		62.45 241	59.42 246	71.53 218	83.93 84	54.32 83	70.03 306	77.61 249	51.91 261	53.48 266	68.29 319	37.91 171	86.66 198	33.36 312	58.27 250	73.62 321

XVG-OURS		61.88 244	59.34 247	69.49 246	65.37 326	46.27 254	64.80 321	73.49 296	47.04 291	57.41 231	82.85 180	25.15 291	78.18 293	53.00 214	64.98 196	84.01 197

v7n		62.50 239	59.27 248	72.20 198	67.25 320	49.83 185	77.87 256	80.12 197	52.50 257	48.80 292	73.07 289	32.10 243	87.90 164	46.83 255	54.92 285	78.86 272

tfpnnormal		61.47 246	59.09 249	68.62 260	76.29 237	41.69 300	81.14 224	85.16 103	54.48 243	51.32 280	73.63 285	32.32 241	86.89 193	21.78 352	55.71 280	77.29 293

CR-MVSNet		62.47 240	59.04 250	72.77 187	73.97 265	56.57 29	60.52 333	71.72 305	60.04 144	57.49 227	65.86 326	38.94 163	80.31 277	42.86 276	59.93 234	81.42 241

PLC	52.38 18	60.89 248	58.97 251	66.68 278	81.77 135	45.70 263	78.96 249	74.04 290	43.66 315	47.63 298	83.19 178	23.52 301	77.78 304	37.47 288	60.46 232	76.55 302
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
IterMVS-SCA-FT		59.12 259	58.81 252	60.08 313	70.68 299	45.07 269	80.42 234	74.25 287	43.54 316	50.02 287	73.73 281	31.97 245	56.74 351	51.06 228	53.60 296	78.42 280

CNLPA		60.59 250	58.44 253	67.05 273	79.21 187	47.26 240	79.75 242	64.34 331	42.46 321	51.90 278	83.94 164	27.79 273	75.41 314	37.12 291	59.49 239	78.47 278

WR-MVS_H		58.91 264	58.04 254	61.54 306	69.07 308	33.83 333	76.91 261	81.99 168	51.40 266	48.17 293	74.67 273	40.23 152	74.15 318	31.78 319	48.10 311	76.64 300

anonymousdsp		60.46 251	57.65 255	68.88 252	63.63 336	45.09 268	72.93 287	78.63 232	46.52 294	51.12 281	72.80 293	21.46 314	83.07 257	57.79 180	53.97 292	78.47 278

Anonymous20231206		59.08 261	57.59 256	63.55 295	68.77 310	32.14 341	80.26 236	79.78 204	50.00 275	49.39 289	72.39 298	26.64 280	78.36 292	33.12 315	57.94 257	80.14 262

CP-MVSNet		58.54 270	57.57 257	61.46 307	68.50 312	33.96 332	76.90 262	78.60 234	51.67 265	47.83 296	76.60 256	34.99 219	72.79 327	35.45 300	47.58 315	77.64 291

PVSNet_0	57.04 13	61.19 247	57.24 258	73.02 181	77.45 220	50.31 175	79.43 247	77.36 255	63.96 83	47.51 301	72.45 297	25.03 292	83.78 249	52.76 219	19.22 368	84.96 184

pmmvs6		59.64 254	57.15 259	67.09 271	66.01 322	36.86 325	80.50 232	78.64 231	45.05 305	49.05 291	73.94 279	27.28 275	86.10 214	43.96 270	49.94 308	78.31 282

PEN-MVS		58.35 271	57.15 259	61.94 303	67.55 319	34.39 330	77.01 260	78.35 239	51.87 262	47.72 297	76.73 254	33.91 226	73.75 322	34.03 310	47.17 319	77.68 289

PS-CasMVS		58.12 272	57.03 261	61.37 308	68.24 316	33.80 334	76.73 263	78.01 242	51.20 267	47.54 300	76.20 264	32.85 235	72.76 328	35.17 305	47.37 317	77.55 292

bld_raw_dy_0_64		59.75 253	57.01 262	67.96 265	66.73 321	45.30 266	77.59 258	59.97 338	50.49 270	47.15 303	77.03 247	17.45 331	79.06 288	56.92 189	59.76 236	79.51 267

LCM-MVSNet-Re		58.82 265	56.54 263	65.68 282	79.31 186	29.09 352	61.39 332	45.79 350	60.73 136	37.65 338	72.47 296	31.42 251	81.08 268	49.66 234	70.41 162	86.87 149

FMVSNet5		58.61 267	56.45 264	65.10 289	77.20 226	39.74 312	74.77 274	77.12 258	50.27 273	43.28 318	67.71 321	26.15 284	76.90 309	36.78 296	54.78 287	78.65 276

KD-MVS_2432*1600		59.04 262	56.44 265	66.86 274	79.07 189	45.87 260	72.13 295	80.42 194	55.03 236	48.15 294	71.01 306	36.73 196	78.05 297	35.21 303	30.18 356	76.67 297

miper_refine_blended		59.04 262	56.44 265	66.86 274	79.07 189	45.87 260	72.13 295	80.42 194	55.03 236	48.15 294	71.01 306	36.73 196	78.05 297	35.21 303	30.18 356	76.67 297

CHOSEN 280x420		57.53 274	56.38 267	60.97 311	74.01 263	48.10 228	46.30 351	54.31 344	48.18 285	50.88 285	77.43 241	38.37 169	59.16 349	54.83 200	63.14 217	75.66 307

DP-MVS		59.24 257	56.12 268	68.63 259	88.24 32	50.35 173	82.51 193	64.43 330	41.10 323	46.70 306	78.77 227	24.75 294	88.57 142	22.26 350	56.29 272	66.96 342

OpenMVS_ROB	53.19 17	59.20 258	56.00 269	68.83 254	71.13 295	44.30 277	83.64 161	75.02 282	46.42 296	46.48 308	73.03 290	18.69 324	88.14 156	27.74 337	61.80 226	74.05 318

ACMH	53.70 16	59.78 252	55.94 270	71.28 220	76.59 231	48.35 220	80.15 239	76.11 272	49.74 276	41.91 323	73.45 288	16.50 336	90.31 94	31.42 320	57.63 263	75.17 311
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DTE-MVSNet		57.03 275	55.73 271	60.95 312	65.94 323	32.57 339	75.71 266	77.09 259	51.16 268	46.65 307	76.34 259	32.84 236	73.22 326	30.94 323	44.87 328	77.06 294

ACMH+	54.58 15	58.55 269	55.24 272	68.50 262	74.68 257	45.80 262	80.27 235	70.21 316	47.15 290	42.77 320	75.48 269	16.73 335	85.98 219	35.10 307	54.78 287	73.72 320

MVS_0304		56.72 276	55.17 273	61.37 308	70.71 296	36.80 326	75.74 265	68.75 321	44.11 313	52.53 271	68.20 320	15.05 340	74.53 317	42.98 274	58.44 248	72.79 327

UnsupCasMVSNet_eth		57.56 273	55.15 274	64.79 291	64.57 333	33.12 335	73.17 286	83.87 137	58.98 171	41.75 324	70.03 313	22.54 305	79.92 282	46.12 260	35.31 345	81.32 248

MSDG		59.44 255	55.14 275	72.32 197	74.69 256	50.71 160	74.39 278	73.58 294	44.44 309	43.40 317	77.52 238	19.45 320	90.87 78	31.31 321	57.49 264	75.38 309

our_test_3		59.11 260	55.08 276	71.18 224	71.42 291	53.29 111	81.96 202	74.52 284	48.32 283	42.08 321	69.28 317	28.14 267	82.15 260	34.35 309	45.68 327	78.11 286

ppachtmachnet_test		58.56 268	54.34 277	71.24 221	71.42 291	54.74 72	81.84 207	72.27 302	49.02 280	45.86 311	68.99 318	26.27 281	83.30 255	30.12 324	43.23 332	75.69 306

Patchmatch-RL test		58.72 266	54.32 278	71.92 210	63.91 335	44.25 278	61.73 329	55.19 342	57.38 203	49.31 290	54.24 349	37.60 179	80.89 269	62.19 135	47.28 318	90.63 73

RPMNet		59.29 256	54.25 279	74.42 148	73.97 265	56.57 29	60.52 333	76.98 260	35.72 337	57.49 227	58.87 345	37.73 176	85.26 232	27.01 340	59.93 234	81.42 241

test20.03		55.22 287	54.07 280	58.68 317	63.14 338	25.00 357	77.69 257	74.78 283	52.64 255	43.43 316	72.39 298	26.21 282	74.76 316	29.31 327	47.05 321	76.28 304

LS3D		56.40 281	53.82 281	64.12 292	81.12 152	45.69 264	73.42 284	66.14 326	35.30 341	43.24 319	79.88 214	22.18 310	79.62 286	19.10 358	64.00 204	67.05 341

PatchMatch-RL		56.66 277	53.75 282	65.37 287	77.91 215	45.28 267	69.78 308	60.38 336	41.35 322	47.57 299	73.73 281	16.83 333	76.91 308	36.99 294	59.21 242	73.92 319

F-COLMAP		55.96 285	53.65 283	62.87 299	72.76 277	42.77 293	74.70 277	70.37 315	40.03 324	41.11 328	79.36 219	17.77 329	73.70 323	32.80 316	53.96 293	72.15 329

test_0402		56.45 280	53.03 284	66.69 277	76.78 230	50.31 175	81.76 208	69.61 318	42.79 319	43.88 313	72.13 301	22.82 304	86.46 204	16.57 361	50.94 306	63.31 350

PatchT		56.60 278	52.97 285	67.48 268	72.94 275	46.16 257	57.30 341	73.78 292	38.77 327	54.37 257	57.26 348	37.52 181	78.06 296	32.02 317	52.79 301	78.23 285

Patchmtry		56.56 279	52.95 286	67.42 269	72.53 280	50.59 164	59.05 337	71.72 305	37.86 331	46.92 304	65.86 326	38.94 163	80.06 281	36.94 295	46.72 323	71.60 333

XVG-ACMP-BASELINE		56.03 283	52.85 287	65.58 283	61.91 341	40.95 309	63.36 323	72.43 301	45.20 304	46.02 309	74.09 277	9.20 351	78.12 294	45.13 262	58.27 250	77.66 290

pmmvs-eth3d		55.97 284	52.78 288	65.54 284	61.02 343	46.44 250	75.36 272	67.72 324	49.61 277	43.65 315	67.58 322	21.63 313	77.04 306	44.11 269	44.33 329	73.15 326

CMPMVS	40.41 21	55.34 286	52.64 289	63.46 296	60.88 344	43.84 282	61.58 331	71.06 311	30.43 347	36.33 340	74.63 274	24.14 297	75.44 313	48.05 247	66.62 188	71.12 336
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testgi		54.25 291	52.57 290	59.29 315	62.76 339	21.65 364	72.21 294	70.47 314	53.25 252	41.94 322	77.33 242	14.28 341	77.95 300	29.18 328	51.72 305	78.28 283

test_fmvs1		53.60 296	52.54 291	56.78 321	58.07 346	30.26 344	68.95 311	42.19 355	32.46 343	63.59 147	82.56 189	11.55 344	60.81 344	58.25 171	55.27 283	79.28 268

ADS-MVSNet		56.17 282	51.95 292	68.84 253	80.60 167	53.07 117	55.03 344	70.02 317	44.72 306	51.00 282	61.19 338	22.83 302	78.88 290	28.54 332	53.63 294	74.57 315

ADS-MVSNet2		55.21 288	51.44 293	66.51 279	80.60 167	49.56 190	55.03 344	65.44 327	44.72 306	51.00 282	61.19 338	22.83 302	75.41 314	28.54 332	53.63 294	74.57 315

USDC		54.36 290	51.23 294	63.76 294	64.29 334	37.71 322	62.84 328	73.48 298	56.85 211	35.47 343	71.94 304	9.23 350	78.43 291	38.43 287	48.57 310	75.13 312

test_fmvs1_n		52.55 300	51.19 295	56.65 322	51.90 354	30.14 345	67.66 315	42.84 354	32.27 344	62.30 161	82.02 198	9.12 352	60.84 343	57.82 179	54.75 289	78.99 270

EU-MVSNet		52.63 299	50.72 296	58.37 318	62.69 340	28.13 354	72.60 288	75.97 274	30.94 346	40.76 330	72.11 302	20.16 318	70.80 334	35.11 306	46.11 325	76.19 305

UnsupCasMVSNet_bld		53.86 293	50.53 297	63.84 293	63.52 337	34.75 329	71.38 300	81.92 171	46.53 293	38.95 334	57.93 346	20.55 317	80.20 280	39.91 284	34.09 352	76.57 301

SixPastTwentyTwo		54.37 289	50.10 298	67.21 270	70.70 297	41.46 305	74.73 275	64.69 329	47.56 288	39.12 333	69.49 314	18.49 327	84.69 242	31.87 318	34.20 351	75.48 308

YYNet1		53.82 294	49.96 299	65.41 286	70.09 302	48.95 203	72.30 292	71.66 307	44.25 311	31.89 352	63.07 334	23.73 299	73.95 320	33.26 313	39.40 339	73.34 323

MDA-MVSNet_test_wron		53.82 294	49.95 300	65.43 285	70.13 301	49.05 199	72.30 292	71.65 308	44.23 312	31.85 353	63.13 333	23.68 300	74.01 319	33.25 314	39.35 340	73.23 325

LTVRE_ROB	45.45 19	52.73 298	49.74 301	61.69 305	69.78 303	34.99 328	44.52 352	67.60 325	43.11 318	43.79 314	74.03 278	18.54 326	81.45 265	28.39 334	57.94 257	68.62 339
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
test_vis1_n		51.19 305	49.66 302	55.76 325	51.26 355	29.85 347	67.20 317	38.86 358	32.12 345	59.50 187	79.86 215	8.78 353	58.23 350	56.95 188	52.46 302	79.19 269

K. test v3		54.04 292	49.42 303	67.92 266	68.55 311	42.57 297	75.51 270	63.07 333	52.07 259	39.21 332	64.59 330	19.34 321	82.21 259	37.11 292	25.31 361	78.97 271

OurMVSNet-221017-0		52.39 301	48.73 304	63.35 297	65.21 328	38.42 319	68.54 313	64.95 328	38.19 328	39.57 331	71.43 305	13.23 343	79.92 282	37.16 290	40.32 338	71.72 332

Anonymous20240521		51.65 303	48.42 305	61.34 310	56.43 350	39.65 314	73.57 282	73.47 299	36.64 335	36.59 339	63.98 331	10.75 347	72.25 331	35.35 301	49.01 309	72.11 330

Patchmatch-test		53.33 297	48.17 306	68.81 255	73.31 269	42.38 298	42.98 354	58.23 339	32.53 342	38.79 335	70.77 309	39.66 159	73.51 324	25.18 344	52.06 304	90.55 74

COLMAP_ROB	43.60 20	50.90 306	48.05 307	59.47 314	67.81 318	40.57 311	71.25 301	62.72 335	36.49 336	36.19 341	73.51 286	13.48 342	73.92 321	20.71 354	50.26 307	63.92 349
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet1		50.35 307	47.81 308	57.96 319	61.53 342	27.80 355	67.40 316	74.06 289	43.25 317	33.31 351	65.38 329	16.03 337	71.34 332	21.80 351	47.55 316	74.75 313

JIA-IIPM		52.33 302	47.77 309	66.03 281	71.20 294	46.92 244	40.00 359	76.48 270	37.10 332	46.73 305	37.02 359	32.96 234	77.88 301	35.97 298	52.45 303	73.29 324

MDA-MVSNet-bldmvs		51.56 304	47.75 310	63.00 298	71.60 289	47.32 239	69.70 309	72.12 303	43.81 314	27.65 359	63.38 332	21.97 312	75.96 311	27.30 339	32.19 353	65.70 347

KD-MVS_self_test		49.24 308	46.85 311	56.44 323	54.32 351	22.87 360	57.39 340	73.36 300	44.36 310	37.98 337	59.30 344	18.97 323	71.17 333	33.48 311	42.44 333	75.26 310

new-patchmatchnet		48.21 310	46.55 312	53.18 328	57.73 348	18.19 372	70.24 304	71.02 312	45.70 300	33.70 347	60.23 340	18.00 328	69.86 337	27.97 336	34.35 349	71.49 335

MVS-HIRNet		49.01 309	44.71 313	61.92 304	76.06 239	46.61 248	63.23 325	54.90 343	24.77 353	33.56 348	36.60 361	21.28 315	75.88 312	29.49 326	62.54 222	63.26 351

AllTest		47.32 312	44.66 314	55.32 326	65.08 329	37.50 323	62.96 327	54.25 345	35.45 339	33.42 349	72.82 291	9.98 348	59.33 347	24.13 347	43.84 330	69.13 337

TinyColmap		48.15 311	44.49 315	59.13 316	65.73 325	38.04 320	63.34 324	62.86 334	38.78 326	29.48 355	67.23 324	6.46 361	73.30 325	24.59 346	41.90 335	66.04 345

test_fmvs2		45.89 314	44.32 316	50.62 331	45.85 363	24.70 358	58.87 339	37.84 361	25.22 352	52.46 273	74.56 275	7.07 356	54.69 352	49.28 238	47.70 314	72.48 328

RPSCF		45.77 315	44.13 317	50.68 330	57.67 349	29.66 348	54.92 346	45.25 352	26.69 351	45.92 310	75.92 267	17.43 332	45.70 362	27.44 338	45.95 326	76.67 297

PM-MVS		46.92 313	43.76 318	56.41 324	52.18 353	32.26 340	63.21 326	38.18 359	37.99 330	40.78 329	66.20 325	5.09 364	65.42 341	48.19 246	41.99 334	71.54 334

mvsany_test1		43.38 317	42.57 319	45.82 335	50.96 356	26.10 356	55.80 342	27.74 371	27.15 350	47.41 302	74.39 276	18.67 325	44.95 363	44.66 265	36.31 343	66.40 344

pmmvs3		45.53 316	41.55 320	57.44 320	48.97 359	39.68 313	70.06 305	57.66 340	28.32 349	34.06 346	57.29 347	8.50 354	66.85 340	34.86 308	34.26 350	65.80 346

N_pmnet		41.25 318	39.77 321	45.66 336	68.50 312	0.82 383	72.51 290	0.38 383	35.61 338	35.26 344	61.51 337	20.07 319	67.74 339	23.51 349	40.63 336	68.42 340

test_vis1_rt		40.29 320	38.64 322	45.25 337	48.91 360	30.09 346	59.44 336	27.07 372	24.52 354	38.48 336	51.67 353	6.71 359	49.44 357	44.33 267	46.59 324	56.23 353

TDRefinement		40.91 319	38.37 323	48.55 333	50.45 357	33.03 337	58.98 338	50.97 348	28.50 348	29.89 354	67.39 323	6.21 363	54.51 353	17.67 360	35.25 346	58.11 352

test_fmvs3		37.95 322	35.75 324	44.55 338	35.50 369	18.92 368	48.32 348	34.00 366	18.36 360	41.31 327	61.58 336	2.29 371	48.06 361	42.72 277	37.71 342	66.66 343

DSMNet-mixed		38.35 321	35.36 325	47.33 334	48.11 361	14.91 376	37.87 360	36.60 362	19.18 358	34.37 345	59.56 343	15.53 338	53.01 355	20.14 356	46.89 322	74.07 317

FPMVS		35.40 323	33.67 326	40.57 341	46.34 362	28.74 353	41.05 356	57.05 341	20.37 357	22.27 361	53.38 351	6.87 358	44.94 364	8.62 367	47.11 320	48.01 360

LF4IMVS		33.04 327	32.55 327	34.52 345	40.96 364	22.03 362	44.45 353	35.62 363	20.42 356	28.12 358	62.35 335	5.03 365	31.88 375	21.61 353	34.42 348	49.63 359

new_pmnet		33.56 326	31.89 328	38.59 342	49.01 358	20.42 365	51.01 347	37.92 360	20.58 355	23.45 360	46.79 355	6.66 360	49.28 359	20.00 357	31.57 355	46.09 361

EGC-MVSNET		33.75 325	30.42 329	43.75 339	64.94 331	36.21 327	60.47 335	40.70 357	0.02 377	0.10 378	53.79 350	7.39 355	60.26 345	11.09 366	35.23 347	34.79 363

ANet_high		34.39 324	29.59 330	48.78 332	30.34 373	22.28 361	55.53 343	63.79 332	38.11 329	15.47 365	36.56 362	6.94 357	59.98 346	13.93 363	5.64 376	64.08 348

mvsany_test3		28.00 329	25.98 331	34.05 346	28.97 374	15.31 374	34.54 363	18.17 377	16.24 361	29.30 356	53.37 352	2.79 369	33.38 374	30.01 325	20.41 367	53.45 356

test_f		27.12 331	24.85 332	33.93 347	26.17 379	15.25 375	30.24 367	22.38 376	12.53 366	28.23 357	49.43 354	2.59 370	34.34 373	25.12 345	26.99 359	52.20 357

cdsmvs_eth3d_5k		18.33 341	24.44 333	0.00 362	0.00 384	0.00 385	0.00 373	89.40 15	0.00 378	0.00 381	92.02 34	38.55 167	0.00 379	0.00 379	0.00 377	0.00 377

APD_test1		26.46 333	24.41 334	32.62 350	37.58 366	21.74 363	40.50 358	30.39 368	11.45 367	16.33 364	43.76 356	1.63 376	41.62 365	11.24 365	26.82 360	34.51 364

Gipuma		27.47 330	24.26 335	37.12 344	60.55 345	29.17 351	11.68 371	60.00 337	14.18 363	10.52 372	15.12 373	2.20 373	63.01 342	8.39 368	35.65 344	19.18 369
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		28.07 328	23.85 336	40.71 340	27.46 378	18.93 367	30.82 366	46.19 349	12.76 365	16.40 363	34.70 364	1.90 374	48.69 360	20.25 355	24.22 362	54.51 355

PMMVS2		26.71 332	22.98 337	37.87 343	36.89 367	8.51 380	42.51 355	29.32 370	19.09 359	13.01 367	37.54 358	2.23 372	53.11 354	14.54 362	11.71 369	51.99 358

test_vis3_rt		24.79 335	22.95 338	30.31 351	28.59 375	18.92 368	37.43 361	17.27 379	12.90 364	21.28 362	29.92 368	1.02 378	36.35 368	28.28 335	29.82 358	35.65 362

PMVS	19.57 22	25.07 334	22.43 339	32.99 349	23.12 380	22.98 359	40.98 357	35.19 364	15.99 362	11.95 371	35.87 363	1.47 377	49.29 358	5.41 374	31.90 354	26.70 368
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		24.09 336	21.07 340	33.16 348	27.67 377	8.35 381	26.63 368	35.11 365	3.40 374	14.35 366	36.98 360	3.46 368	35.31 370	19.08 359	22.95 363	55.81 354

testf1		21.11 337	19.08 341	27.18 353	30.56 371	18.28 370	33.43 364	24.48 373	8.02 371	12.02 369	33.50 365	0.75 380	35.09 371	7.68 369	21.32 364	28.17 366

APD_test2		21.11 337	19.08 341	27.18 353	30.56 371	18.28 370	33.43 364	24.48 373	8.02 371	12.02 369	33.50 365	0.75 380	35.09 371	7.68 369	21.32 364	28.17 366

E-PMN		19.16 339	18.40 343	21.44 355	36.19 368	13.63 377	47.59 349	30.89 367	10.73 368	5.91 375	16.59 371	3.66 367	39.77 366	5.95 373	8.14 371	10.92 371

EMVS		18.42 340	17.66 344	20.71 356	34.13 370	12.64 378	46.94 350	29.94 369	10.46 370	5.58 376	14.93 374	4.23 366	38.83 367	5.24 375	7.51 373	10.67 372

MVE	16.60 23	17.34 342	13.39 345	29.16 352	28.43 376	19.72 366	13.73 370	23.63 375	7.23 373	7.96 373	21.41 369	0.80 379	36.08 369	6.97 371	10.39 370	31.69 365
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		9.44 343	10.68 346	5.73 359	2.49 382	4.21 382	10.48 372	18.04 378	0.34 376	12.59 368	20.49 370	11.39 345	7.03 378	13.84 364	6.46 375	5.95 373

ab-mvs-re		7.68 345	10.24 347	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	92.12 31	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

wuyk23d		9.11 344	8.77 348	10.15 358	40.18 365	16.76 373	20.28 369	1.01 382	2.58 375	2.66 377	0.98 377	0.23 382	12.49 377	4.08 376	6.90 374	1.19 374

testmvs		6.14 346	8.18 349	0.01 360	0.01 383	0.00 385	73.40 285	0.00 384	0.00 378	0.02 379	0.15 378	0.00 383	0.00 379	0.02 377	0.00 377	0.02 375

test123		6.01 347	8.01 350	0.01 360	0.00 384	0.01 384	71.93 298	0.00 384	0.00 378	0.02 379	0.11 379	0.00 383	0.00 379	0.02 377	0.00 377	0.02 375

pcd_1.5k_mvsjas		3.15 348	4.20 351	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	37.77 173	0.00 379	0.00 379	0.00 377	0.00 377

test_blank		0.00 349	0.00 352	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 384	0.00 385	0.00 373	0.00 384	0.00 378	0.00 381	0.00 380	0.00 383	0.00 379	0.00 379	0.00 377	0.00 377

FOURS1					83.24 101	49.90 183	84.98 124	78.76 228	47.71 286	73.42 47

MSC_two_6792asdad				81.53 14	91.77 4	56.03 41		91.10 6					96.22 8	81.46 19	86.80 25	92.34 30

PC_three_1452									66.58 46	87.27 2	93.70 8	66.82 4	94.95 17	89.74 2	91.98 4	93.98 5

No_MVS				81.53 14	91.77 4	56.03 41		91.10 6					96.22 8	81.46 19	86.80 25	92.34 30

test_one_0601					89.39 22	57.29 20		88.09 43	57.21 207	82.06 11	93.39 12	54.94 24

eth-test2					0.00 384

eth-test					0.00 384

ZD-MVS					89.55 14	53.46 100		84.38 123	57.02 209	73.97 42	91.03 50	44.57 102	91.17 68	75.41 56	81.78 67

IU-MVS					89.48 17	57.49 15		91.38 5	66.22 51	88.26 1				82.83 9	87.60 17	92.44 27

OPU-MVS				81.71 12	92.05 3	55.97 43	92.48 3				94.01 5	67.21 2	95.10 15	89.82 1	92.55 3	94.06 3

test_241102_TWO								88.76 30	57.50 201	83.60 6	94.09 3	56.14 18	96.37 6	82.28 13	87.43 19	92.55 25

test_241102_ONE					89.48 17	56.89 25		88.94 22	57.53 199	84.61 4	93.29 15	58.81 11	96.45 1

save fliter					85.35 60	56.34 36	89.31 37	81.46 178	61.55 120

test_0728_THIRD									58.00 187	81.91 12	93.64 10	56.54 15	96.44 2	81.64 17	86.86 23	92.23 32

test_0728_SECOND				82.20 8	89.50 15	57.73 11	92.34 5	88.88 24					96.39 4	81.68 15	87.13 20	92.47 26

test0726					89.40 20	57.45 17	92.32 7	88.63 33	57.71 195	83.14 9	93.96 6	55.17 20

GSMVS																88.13 127

test_part2					89.33 23	55.48 50				82.27 10

sam_mvs1												38.86 165				88.13 127

sam_mvs												35.99 209

ambc				62.06 302	53.98 352	29.38 350	35.08 362	79.65 208		41.37 325	59.96 341	6.27 362	82.15 260	35.34 302	38.22 341	74.65 314

MTGPA								81.31 181

test_post1							70.84 303				14.72 375	34.33 223	83.86 246	48.80 241

test_post											16.22 372	37.52 181	84.72 241

patchmatchnet-post											59.74 342	38.41 168	79.91 284

GG-mvs-BLEND				77.77 74	86.68 43	50.61 162	68.67 312	88.45 39		68.73 88	87.45 124	59.15 10	90.67 83	54.83 200	87.67 16	92.03 38

MTMP							87.27 70	15.34 380

gm-plane-assit					83.24 101	54.21 86			70.91 13		88.23 112		95.25 14	66.37 104

test9_res														78.72 34	85.44 39	91.39 57

TEST9					85.68 51	55.42 51	87.59 60	84.00 133	57.72 194	72.99 52	90.98 52	44.87 97	88.58 139

test_8					85.72 50	55.31 55	87.60 59	83.88 136	57.84 192	72.84 56	90.99 51	44.99 94	88.34 149

agg_prior2														75.65 51	85.11 43	91.01 66

agg_prior					85.64 54	54.92 69		83.61 143		72.53 60			88.10 159

TestCases				55.32 326	65.08 329	37.50 323		54.25 345	35.45 339	33.42 349	72.82 291	9.98 348	59.33 347	24.13 347	43.84 330	69.13 337

test_prior4						56.39 35	87.15 73

test_prior2							89.04 40		61.88 116	73.55 45	91.46 48	48.01 63		74.73 59	85.46 38

test_prior				78.39 63	86.35 45	54.91 70		85.45 88					89.70 110			90.55 74

旧先验2							81.73 209		45.53 302	74.66 35			70.48 336	58.31 170

新几何2							81.61 213

新几何1				73.30 178	83.10 104	53.48 99		71.43 309	45.55 301	66.14 108	87.17 129	33.88 228	80.54 274	48.50 244	80.33 80	85.88 170

旧先验1					81.57 143	47.48 235		71.83 304			88.66 102	36.94 192			78.34 101	88.67 116

无先验							85.19 114	78.00 243	49.08 279				85.13 236	52.78 217		87.45 141

原ACMM2							83.77 159

原ACMM1				76.13 116	84.89 69	54.59 79		85.26 98	51.98 260	66.70 99	87.07 131	40.15 154	89.70 110	51.23 226	85.06 44	84.10 194

test222					79.36 183	50.97 158	77.99 255	67.84 323	42.54 320	62.84 155	86.53 138	30.26 257			76.91 109	85.23 179

testdata2													77.81 303	45.64 261

segment_acmp												44.97 96

testdata				67.08 272	77.59 217	45.46 265		69.20 320	44.47 308	71.50 72	88.34 109	31.21 252	70.76 335	52.20 222	75.88 117	85.03 182

testdata1							77.55 259		64.14 78

test12				79.24 37	86.89 41	56.08 40		85.16 103		72.27 64		47.15 70	91.10 71		85.93 33	90.54 76

plane_prior7					77.95 212	48.46 219

plane_prior6					78.42 207	49.39 194						36.04 207

plane_prior5								82.59 160					88.30 152	65.46 113	72.34 146	84.49 188

plane_prior4											83.28 176

plane_prior3						48.95 203			64.01 81	62.15 163

plane_prior2							85.76 98		63.60 90

plane_prior1					78.31 209

plane_prior						49.57 188	87.43 63		64.57 73						72.84 142

n2								0.00 384

nn								0.00 384

door-mid								41.31 356

lessismore_v0				67.98 264	64.76 332	41.25 306		45.75 351		36.03 342	65.63 328	19.29 322	84.11 245	35.67 299	21.24 366	78.59 277

LGP-MVS_train				72.02 202	74.42 259	48.60 212		80.64 190	54.69 241	53.75 263	83.83 166	25.73 287	86.98 187	60.33 155	64.71 198	80.48 257

test11								84.25 127

door								43.27 353

HQP5-MVS						51.56 147

HQP-NCC					79.02 191		88.00 51		65.45 60	64.48 131

ACMP_Plane					79.02 191		88.00 51		65.45 60	64.48 131

BP-MVS														66.70 101

HQP4-MVS										64.47 134			88.61 138			84.91 185

HQP3-MVS								83.68 139							73.12 138

HQP2-MVS												37.35 184

NP-MVS					78.76 196	50.43 168					85.12 152

MDTV_nov1_ep13_2view						43.62 284	71.13 302		54.95 238	59.29 193		36.76 195		46.33 258		87.32 143

ACMMP++_ref															63.20 215

ACMMP++															59.38 240

Test By Simon												39.38 160

ITE_SJBPF				51.84 329	58.03 347	31.94 342		53.57 347	36.67 334	41.32 326	75.23 271	11.17 346	51.57 356	25.81 343	48.04 312	72.02 331

DeepMVS_CX				13.10 357	21.34 381	8.99 379		10.02 381	10.59 369	7.53 374	30.55 367	1.82 375	14.55 376	6.83 372	7.52 372	15.75 370

High-resolution multi-view benchmark