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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

SED-MVS		88.94 1	90.98 1	86.56 1	92.53 6	95.09 1	88.55 4	76.83 6	94.16 1	86.57 1	90.85 5	87.07 1	86.18 1	86.36 7	85.08 12	88.67 19	98.21 3

DVP-MVS		88.07 2	90.73 2	84.97 4	91.98 9	95.01 2	87.86 9	76.88 5	93.90 2	85.15 2	90.11 7	86.90 2	79.46 11	86.26 10	84.67 18	88.50 26	98.25 2
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
DVP-MVS++		87.98 3	89.76 5	85.89 2	92.57 5	94.57 3	88.34 5	76.61 7	92.40 6	83.40 3	89.26 10	85.57 5	86.04 2	86.24 11	84.89 15	88.39 29	95.42 20

SF-MVS		87.30 6	88.71 6	85.64 3	94.57 1	94.55 4	91.01 1	79.94 1	89.15 12	79.85 7	92.37 3	83.29 10	79.75 8	83.52 26	82.72 32	88.75 18	95.37 23

DPE-MVS		87.60 5	90.44 4	84.29 7	92.09 8	93.44 5	88.69 3	75.11 9	93.06 5	80.80 6	94.23 2	86.70 3	81.44 6	84.84 18	83.52 27	87.64 47	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CSCG		82.90 20	84.52 23	81.02 18	91.85 10	93.43 6	87.14 11	74.01 14	81.96 31	76.14 14	70.84 36	82.49 13	69.71 62	82.32 41	85.18 11	87.26 59	95.40 22

MCST-MVS		85.75 9	86.99 13	84.31 6	94.07 2	92.80 7	88.15 8	79.10 2	85.66 21	70.72 28	76.50 32	80.45 21	82.17 4	88.35 2	87.49 3	91.63 2	97.65 4

DELS-MVS		79.49 30	79.84 40	79.08 27	88.26 36	92.49 8	84.12 25	70.63 27	65.27 81	69.60 34	61.29 62	66.50 59	72.75 42	88.07 3	88.03 2	89.13 12	97.22 6
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
CHOSEN 1792x2688		72.55 71	71.98 80	73.22 59	86.57 44	92.41 9	75.63 70	66.77 49	62.08 88	52.32 89	30.27 192	50.74 132	66.14 84	86.22 12	85.41 7	91.90 1	96.75 12

CNVR-MVS		85.96 8	87.58 11	84.06 8	92.58 4	92.40 10	87.62 10	77.77 4	88.44 14	75.93 16	79.49 25	81.97 17	81.65 5	87.04 6	86.58 4	88.79 16	97.18 7

CANet		80.90 27	82.93 28	78.53 29	86.83 43	92.26 11	81.19 41	66.95 47	81.60 34	69.90 31	66.93 44	74.80 31	76.79 20	84.68 19	84.77 17	89.50 9	95.50 18

QAPM		77.50 44	77.43 51	77.59 34	91.52 13	92.00 12	81.41 39	70.63 27	66.22 74	58.05 71	54.70 80	71.79 43	74.49 31	82.46 37	82.04 36	89.46 10	92.79 53

DPM-MVS		85.41 11	86.72 16	83.89 10	91.66 12	91.92 13	90.49 2	78.09 3	86.90 17	73.95 19	74.52 34	82.01 16	79.29 12	90.24 1	90.65 1	89.86 6	90.78 72

APDe-MVS		86.37 7	88.41 8	84.00 9	91.43 14	91.83 14	88.34 5	74.67 10	91.19 7	81.76 5	91.13 4	81.94 18	80.07 7	83.38 27	82.58 34	87.69 45	96.78 10

MVS_0304		79.43 32	82.20 30	76.20 40	84.22 51	91.79 15	81.82 36	63.81 69	76.83 49	61.71 56	66.37 47	75.52 30	76.38 22	85.54 14	85.03 13	89.28 11	94.32 32

MSP-MVS		87.87 4	90.57 3	84.73 5	89.38 26	91.60 16	88.24 7	74.15 12	93.55 3	82.28 4	94.99 1	83.21 11	85.96 3	87.67 4	84.67 18	88.32 30	98.29 1
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
PHI-MVS		79.43 32	84.06 25	74.04 55	86.15 46	91.57 17	80.85 45	68.90 38	82.22 30	51.81 92	78.10 27	74.28 32	70.39 59	84.01 24	84.00 22	86.14 85	94.24 33

DeepPCF-MVS	76.94 1	83.08 19	87.77 10	77.60 33	90.11 19	90.96 18	78.48 54	72.63 22	93.10 4	65.84 40	80.67 23	81.55 19	74.80 28	85.94 13	85.39 8	83.75 143	96.77 11

SMA-MVS		85.24 12	88.27 9	81.72 15	91.74 11	90.71 19	86.71 12	73.16 19	90.56 10	74.33 18	83.07 18	85.88 4	77.16 19	86.28 9	85.58 6	87.23 60	95.77 13
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
MVS_111021_HR		77.42 45	78.40 47	76.28 39	86.95 41	90.68 20	77.41 63	70.56 30	66.21 75	62.48 53	66.17 49	63.98 68	72.08 47	82.87 33	83.15 28	88.24 33	95.71 15

MAR-MVS		77.19 47	78.37 48	75.81 44	89.87 21	90.58 21	79.33 53	65.56 58	77.62 47	58.33 70	59.24 70	67.98 54	74.83 27	82.37 40	83.12 29	86.95 67	87.67 107
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
NCCC		84.16 16	85.46 21	82.64 11	92.34 7	90.57 22	86.57 13	76.51 8	86.85 18	72.91 22	77.20 31	78.69 25	79.09 14	84.64 20	84.88 16	88.44 27	95.41 21

OpenMVS	67.62 8	74.92 61	73.91 71	76.09 42	90.10 20	90.38 23	78.01 58	66.35 52	66.09 76	62.80 49	46.33 123	64.55 66	71.77 49	79.92 65	80.88 59	87.52 51	89.20 91

3Dnovator	70.49 5	78.42 38	76.77 57	80.35 20	91.43 14	90.27 24	81.84 35	70.79 26	72.10 58	71.95 23	50.02 99	67.86 56	77.47 18	82.89 32	84.24 20	88.61 22	89.99 82

HPM-MVS++		85.64 10	88.43 7	82.39 12	92.65 3	90.24 25	85.83 16	74.21 11	90.68 9	75.63 17	86.77 13	84.15 8	78.68 15	86.33 8	85.26 9	87.32 56	95.60 17

EPNet		79.28 36	82.25 29	75.83 43	88.31 35	90.14 26	79.43 52	68.07 41	81.76 33	61.26 59	77.26 30	70.08 49	70.06 60	82.43 39	82.00 38	87.82 41	92.09 57
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		83.54 17	86.37 18	80.25 21	89.57 25	90.10 27	85.27 20	71.66 23	87.38 15	73.08 21	84.23 17	80.16 22	75.31 24	84.85 17	83.64 24	86.57 74	94.21 35

GG-mvs-BLEND		54.54 182	77.58 50	27.67 210	0.03 224	90.09 28	77.20 65	0.02 221	66.83 73	0.05 225	59.90 67	73.33 35	0.04 220	78.40 79	79.30 73	88.65 20	95.20 25

PVSNet_BlendedMVS		76.84 49	78.47 45	74.95 50	82.37 56	89.90 29	75.45 74	65.45 59	74.99 54	70.66 29	63.07 55	58.27 98	67.60 78	84.24 22	81.70 43	88.18 34	97.10 8

PVSNet_Blended		76.84 49	78.47 45	74.95 50	82.37 56	89.90 29	75.45 74	65.45 59	74.99 54	70.66 29	63.07 55	58.27 98	67.60 78	84.24 22	81.70 43	88.18 34	97.10 8

canonicalmvs		77.65 42	79.59 41	75.39 45	81.52 62	89.83 31	81.32 40	60.74 105	80.05 39	66.72 38	68.43 40	65.09 62	74.72 30	78.87 74	82.73 31	87.32 56	92.16 56

SteuartSystems-ACMMP		82.51 21	85.35 22	79.20 25	90.25 17	89.39 32	84.79 21	70.95 25	82.86 27	68.32 36	86.44 14	77.19 26	73.07 38	83.63 25	83.64 24	87.82 41	94.34 31
Skip Steuart: Steuart Systems R&D Blog.
casdiffmvs_mvg		75.57 56	76.04 62	75.02 49	80.48 71	89.31 33	80.79 46	64.04 67	66.95 72	63.87 45	57.52 72	61.33 81	72.90 40	82.01 47	81.99 39	88.03 38	93.16 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
APD-MVS		84.83 13	87.00 12	82.30 13	89.61 24	89.21 34	86.51 14	73.64 16	90.98 8	77.99 12	89.89 8	80.04 23	79.18 13	82.00 48	81.37 49	86.88 69	95.49 19
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
casdiffmvs		75.20 59	75.69 65	74.63 54	79.26 78	89.07 35	78.47 55	63.59 72	67.05 71	63.79 46	55.72 77	60.32 86	73.58 34	82.16 43	81.78 41	89.08 13	93.72 42
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IB-MVS	64.48 11	69.02 91	68.97 102	69.09 86	81.75 61	89.01 36	64.50 150	64.91 62	56.65 109	62.59 52	47.89 107	45.23 145	51.99 154	69.18 170	81.88 40	88.77 17	92.93 50
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
MVS_Test		75.22 58	76.69 58	73.51 56	79.30 76	88.82 37	80.06 49	58.74 114	69.77 65	57.50 75	59.78 69	61.35 79	75.31 24	82.07 45	83.60 26	90.13 5	91.41 64

SD-MVS		84.31 15	86.96 14	81.22 16	88.98 30	88.68 38	85.65 17	73.85 15	89.09 13	79.63 8	87.34 12	84.84 6	73.71 33	82.66 35	81.60 46	85.48 106	94.51 29
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
gg-mvs-nofinetune		62.34 139	66.19 123	57.86 163	76.15 107	88.61 39	71.18 110	41.24 208	25.74 211	13.16 213	22.91 205	63.97 69	54.52 149	85.06 16	85.25 10	90.92 3	91.78 61

DeepC-MVS	74.46 3	80.30 29	81.05 35	79.42 23	87.42 39	88.50 40	83.23 27	73.27 18	82.78 28	71.01 27	62.86 57	69.93 50	74.80 28	84.30 21	84.20 21	86.79 72	94.77 26
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
train_agg		83.35 18	86.93 15	79.17 26	89.70 23	88.41 41	85.60 19	72.89 21	86.31 19	66.58 39	90.48 6	82.24 15	73.06 39	83.10 31	82.64 33	87.21 64	95.30 24

CDPH-MVS		79.39 35	82.13 31	76.19 41	89.22 29	88.34 42	84.20 24	71.00 24	79.67 41	56.97 76	77.77 28	72.24 41	68.50 74	81.33 52	82.74 30	87.23 60	92.84 51

3Dnovator+	70.16 6	77.87 41	77.29 53	78.55 28	89.25 28	88.32 43	80.09 48	67.95 42	74.89 56	71.83 24	52.05 92	70.68 47	76.27 23	82.27 42	82.04 36	85.92 89	90.77 73

TSAR-MVS + GP.		82.27 23	85.98 19	77.94 31	80.72 69	88.25 44	81.12 42	67.71 43	87.10 16	73.31 20	85.23 15	83.68 9	76.64 21	80.43 61	81.47 48	88.15 36	95.66 16

MP-MVS		80.94 26	83.49 26	77.96 30	88.48 31	88.16 45	82.82 31	69.34 34	80.79 37	69.67 32	82.35 20	77.13 27	71.60 51	80.97 58	80.96 57	85.87 92	94.06 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HyFIR lowres test		68.39 96	68.28 108	68.52 90	80.85 66	88.11 46	71.08 112	58.09 119	54.87 125	47.80 110	27.55 198	55.80 110	64.97 88	79.11 72	79.14 74	88.31 31	93.35 44

CLD-MVS		77.36 46	77.29 53	77.45 35	82.21 58	88.11 46	81.92 34	68.96 37	77.97 45	69.62 33	62.08 58	59.44 91	73.57 35	81.75 50	81.27 51	88.41 28	90.39 78
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ET-MVSNet_ETH3D		71.38 78	74.70 69	67.51 98	51.61 207	88.06 48	77.29 64	60.95 104	63.61 83	48.36 107	66.60 46	60.67 84	79.55 9	73.56 127	80.58 62	87.30 58	89.80 84

PCF-MVS	70.85 4	75.73 55	76.55 60	74.78 53	83.67 52	88.04 49	81.47 37	70.62 29	69.24 69	57.52 74	60.59 66	69.18 52	70.65 57	77.11 90	77.65 88	84.75 126	94.01 37
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		76.25 51	80.22 38	71.63 71	78.23 86	87.95 50	72.75 92	60.27 110	77.50 48	57.73 72	71.53 35	66.60 58	73.16 37	80.99 57	81.23 52	87.63 48	95.73 14

DeepC-MVS_fast	75.41 2	81.69 24	82.10 32	81.20 17	91.04 16	87.81 51	83.42 26	74.04 13	83.77 25	71.09 26	66.88 45	72.44 37	79.48 10	85.08 15	84.97 14	88.12 37	93.78 40
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		82.48 22	84.12 24	80.56 19	90.15 18	87.55 52	84.28 23	69.67 32	85.22 22	77.95 13	84.69 16	75.94 29	75.04 26	81.85 49	81.17 53	86.30 81	92.40 55

baseline		72.89 68	74.46 70	71.07 72	75.99 108	87.50 53	74.57 80	60.49 107	70.72 62	57.60 73	60.63 65	60.97 82	70.79 56	75.27 107	76.33 100	86.94 68	89.79 85

diffmvs		74.32 62	75.42 66	73.04 60	75.60 112	87.27 54	78.20 56	62.96 78	68.66 70	61.89 54	59.79 68	59.84 89	71.80 48	78.30 81	79.87 66	87.80 43	94.23 34
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EIA-MVS		73.48 66	76.05 61	70.47 77	78.12 87	87.21 55	71.78 100	60.63 106	69.66 66	55.56 81	64.86 51	60.69 83	69.53 65	77.35 89	78.59 77	87.22 62	94.01 37

PVSNet_Blended_VisFu		71.76 75	73.54 74	69.69 80	79.01 80	87.16 56	72.05 97	61.80 93	56.46 111	59.66 67	53.88 88	62.48 71	59.08 126	81.17 54	78.90 75	86.53 76	94.74 27

ACMMPR		80.62 28	82.98 27	77.87 32	88.41 32	87.05 57	83.02 28	69.18 35	83.91 24	68.35 35	82.89 19	73.64 34	72.16 46	80.78 59	81.13 54	86.10 86	91.43 62

CS-MVS-test		75.09 60	77.84 49	71.87 70	79.27 77	86.92 58	70.53 118	60.36 108	75.13 53	63.13 48	67.92 41	65.08 63	71.43 52	78.15 82	78.51 80	86.53 76	93.16 48

DI_MVS_plusplus_trai		73.94 65	74.85 68	72.88 61	76.57 104	86.80 59	80.41 47	61.47 96	62.35 87	59.44 68	47.91 106	68.12 53	72.24 45	82.84 34	81.50 47	87.15 66	94.42 30

CS-MVS		75.84 54	78.61 44	72.61 65	79.03 79	86.74 60	74.43 88	60.27 110	74.15 57	62.78 50	66.26 48	64.25 67	72.81 41	83.36 28	81.69 45	86.32 79	93.85 39

PGM-MVS		79.42 34	81.84 33	76.60 38	88.38 34	86.69 61	82.97 30	65.75 56	80.39 38	64.94 42	81.95 22	72.11 42	71.41 53	80.45 60	80.55 63	86.18 83	90.76 74

test1111		66.72 110	67.80 111	65.45 108	77.42 97	86.63 62	69.69 122	62.98 77	55.29 119	39.47 147	40.12 151	47.11 140	55.70 144	79.96 64	80.00 65	87.47 52	85.49 127

DROMVSNet		76.05 53	78.87 43	72.77 62	78.87 82	86.63 62	77.50 62	57.04 135	75.34 52	61.68 57	64.20 52	69.56 51	73.96 32	82.12 44	80.65 61	87.57 49	93.57 43

CANet_DTU		72.84 69	76.63 59	68.43 92	76.81 101	86.62 64	75.54 73	54.71 160	72.06 59	43.54 127	67.11 43	58.46 95	72.40 44	81.13 56	80.82 60	87.57 49	90.21 80

TSAR-MVS + ACMM		81.59 25	85.84 20	76.63 37	89.82 22	86.53 65	86.32 15	66.72 50	85.96 20	65.43 41	88.98 11	82.29 14	67.57 80	82.06 46	81.33 50	83.93 141	93.75 41

TSAR-MVS + MP.		84.39 14	86.58 17	81.83 14	88.09 37	86.47 66	85.63 18	73.62 17	90.13 11	79.24 9	89.67 9	82.99 12	77.72 17	81.22 53	80.92 58	86.68 73	94.66 28
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test2506		69.26 87	70.79 91	67.48 99	78.64 83	86.40 67	72.22 95	62.75 85	58.05 103	45.24 117	50.76 95	54.93 116	58.05 132	79.82 66	79.70 67	87.96 39	85.90 122

ECVR-MVS		67.93 101	68.49 105	67.28 102	78.64 83	86.40 67	72.22 95	62.75 85	58.05 103	44.06 125	40.92 146	48.20 137	58.05 132	79.82 66	79.70 67	87.96 39	86.32 117

baseline2		71.22 80	73.01 77	69.13 84	75.76 110	86.34 69	71.23 108	62.78 84	62.62 85	52.85 88	57.32 73	54.31 119	63.27 99	79.74 68	79.31 72	88.89 15	91.43 62

XVS					82.43 54	86.27 70	75.70 68			61.07 61		72.27 38				85.67 100

X-MVStestdata					82.43 54	86.27 70	75.70 68			61.07 61		72.27 38				85.67 100

X-MVS		78.16 40	80.55 37	75.38 46	87.99 38	86.27 70	81.05 43	68.98 36	78.33 43	61.07 61	75.25 33	72.27 38	67.52 81	80.03 63	80.52 64	85.66 103	91.20 66

CostFormer		72.18 72	73.90 72	70.18 79	79.47 74	86.19 73	76.94 66	48.62 180	66.07 77	60.40 66	54.14 86	65.82 60	67.98 75	75.84 102	76.41 99	87.67 46	92.83 52

FA-MVS(training)		70.24 86	71.77 83	68.45 91	77.52 95	86.03 74	73.33 91	49.12 179	63.55 84	55.77 78	48.91 103	56.26 106	67.78 77	77.60 84	79.62 69	87.19 65	90.40 77

CP-MVS		79.44 31	81.51 34	77.02 36	86.95 41	85.96 75	82.00 33	68.44 40	81.82 32	67.39 37	77.43 29	73.68 33	71.62 50	79.56 70	79.58 70	85.73 96	92.51 54

ACMMP		77.61 43	79.59 41	75.30 47	85.87 47	85.58 76	81.42 38	67.38 46	79.38 42	62.61 51	78.53 26	65.79 61	68.80 73	78.56 77	78.50 81	85.75 93	90.80 71
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
MS-PatchMatch		70.34 85	69.00 101	71.91 69	85.20 50	85.35 77	77.84 60	61.77 94	58.01 105	55.40 82	41.26 142	58.34 97	61.69 107	81.70 51	78.29 82	89.56 8	80.02 160

Effi-MVS+		70.42 81	71.23 87	69.47 81	78.04 88	85.24 78	75.57 72	58.88 113	59.56 97	48.47 106	52.73 91	54.94 115	69.69 63	78.34 80	77.06 92	86.18 83	90.73 75

MVS_111021_LR		74.26 63	75.95 63	72.27 66	79.43 75	85.04 79	72.71 93	65.27 61	70.92 61	63.58 47	69.32 38	60.31 87	69.43 67	77.01 91	77.15 91	83.22 150	91.93 60

AdaColmap		76.23 52	73.55 73	79.35 24	89.38 26	85.00 80	79.99 50	73.04 20	76.60 50	71.17 25	55.18 79	57.99 100	77.87 16	76.82 93	76.82 94	84.67 128	86.45 114

MSLP-MVS++		78.57 37	77.33 52	80.02 22	88.39 33	84.79 81	84.62 22	66.17 54	75.96 51	78.40 10	61.59 60	71.47 44	73.54 36	78.43 78	78.88 76	88.97 14	90.18 81

Vis-MVSNet		65.53 117	69.83 97	60.52 146	70.80 138	84.59 82	66.37 147	55.47 151	48.40 145	40.62 145	57.67 71	58.43 96	45.37 178	77.49 85	76.24 102	84.47 132	85.99 121
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
baseline1		71.47 76	72.02 79	70.82 74	80.56 70	84.51 83	76.61 67	66.93 48	56.22 113	48.66 105	55.40 78	60.43 85	62.55 103	83.35 29	80.99 55	89.60 7	83.28 143

thisisatest0530		68.38 97	70.98 89	65.35 109	72.61 125	84.42 84	68.21 131	57.98 120	59.77 96	50.80 97	54.63 81	58.48 94	57.92 134	76.99 92	77.47 89	84.60 129	85.07 128

Anonymous202405211			66.35 122		78.00 89	84.41 85	74.85 78	63.18 75	51.00 134		31.37 189	53.73 123	69.67 64	76.28 96	76.84 93	83.21 152	90.85 70

OPM-MVS		72.74 70	70.93 90	74.85 52	85.30 49	84.34 86	82.82 31	69.79 31	49.96 138	55.39 83	54.09 87	60.14 88	70.04 61	80.38 62	79.43 71	85.74 95	88.20 103
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP-MVS		78.26 39	80.91 36	75.17 48	85.67 48	84.33 87	83.01 29	69.38 33	79.88 40	55.83 77	79.85 24	64.90 65	70.81 55	82.46 37	81.78 41	86.30 81	93.18 47

IS_MVSNet		67.29 107	71.98 80	61.82 140	76.92 100	84.32 88	65.90 148	58.22 117	55.75 117	39.22 150	54.51 83	62.47 72	45.99 175	78.83 75	78.52 79	84.70 127	89.47 88

EPMVS		66.21 111	67.49 114	64.73 114	75.81 109	84.20 89	68.94 127	44.37 195	61.55 89	48.07 109	49.21 102	54.87 117	62.88 100	71.82 146	71.40 159	88.28 32	79.37 163

tttt0517		67.99 100	70.61 92	64.94 112	71.94 130	83.96 90	67.62 135	57.98 120	59.30 98	49.90 102	54.50 84	57.98 101	57.92 134	76.48 95	77.47 89	84.24 136	84.58 131

thres100view900		67.14 109	66.09 124	68.38 93	77.70 90	83.84 91	74.52 84	66.33 53	49.16 142	43.40 129	43.24 127	41.34 152	62.59 102	79.31 71	75.92 105	85.73 96	89.81 83

Anonymous20231211		68.44 95	66.37 121	70.86 73	77.58 93	83.49 92	75.15 77	61.89 91	52.54 131	58.50 69	28.89 194	56.78 104	69.29 70	74.96 111	76.61 95	82.73 156	91.36 65

EPP-MVSNet		67.58 103	71.10 88	63.48 126	75.71 111	83.35 93	66.85 141	57.83 125	53.02 130	41.15 141	55.82 75	67.89 55	56.01 143	74.40 116	72.92 145	83.33 148	90.30 79

GeoE		68.96 92	69.32 98	68.54 89	76.61 103	83.12 94	71.78 100	56.87 137	60.21 95	54.86 85	45.95 124	54.79 118	64.27 92	74.59 113	75.54 111	86.84 71	91.01 69

MVSTER		76.92 48	79.92 39	73.42 58	74.98 115	82.97 95	78.15 57	63.41 73	78.02 44	64.41 44	67.54 42	72.80 36	71.05 54	83.29 30	83.73 23	88.53 25	91.12 67

PatchmatchNet		65.43 118	67.71 112	62.78 132	73.49 122	82.83 96	66.42 146	45.40 190	60.40 94	45.27 116	49.22 101	57.60 102	60.01 118	70.61 156	71.38 160	86.08 87	81.91 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thres400		65.18 120	64.44 132	66.04 105	76.40 105	82.63 97	71.52 105	64.27 65	44.93 160	40.69 144	41.86 139	40.79 158	58.12 130	77.67 83	74.64 118	85.26 109	88.56 99

UGNet		67.57 104	71.69 84	62.76 133	69.88 140	82.58 98	66.43 145	58.64 115	54.71 126	51.87 91	61.74 59	62.01 76	45.46 177	74.78 112	74.99 114	84.24 136	91.02 68
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
CPTT-MVS		75.43 57	77.13 55	73.44 57	81.43 63	82.55 99	80.96 44	64.35 64	77.95 46	61.39 58	69.20 39	70.94 46	69.38 69	73.89 123	73.32 137	83.14 153	92.06 58

TSAR-MVS + COLMAP		73.09 67	76.86 56	68.71 87	74.97 116	82.49 100	74.51 85	61.83 92	83.16 26	49.31 104	82.22 21	51.62 129	68.94 72	78.76 76	75.52 112	82.67 158	84.23 135

PMMVS		70.37 84	75.06 67	64.90 113	71.46 131	81.88 101	64.10 152	55.64 147	71.31 60	46.69 111	70.69 37	58.56 92	69.53 65	79.03 73	75.63 108	81.96 167	88.32 102

MDTV_nov1_ep13		65.21 119	67.28 115	62.79 131	70.91 136	81.72 102	69.28 126	49.50 178	58.08 102	43.94 126	50.50 98	56.02 108	58.86 127	70.72 155	73.37 135	84.24 136	80.52 159

thres600view7		63.77 130	63.14 138	64.51 116	75.49 113	81.61 103	69.59 123	62.95 79	43.96 163	38.90 152	41.09 143	40.24 163	55.25 147	76.24 97	71.54 154	84.89 119	87.30 108

thres200		65.58 115	64.74 130	66.56 104	77.52 95	81.61 103	73.44 90	62.95 79	46.23 154	42.45 136	42.76 129	41.18 154	58.12 130	76.24 97	75.59 109	84.89 119	89.58 86

tfpn200view9		65.90 114	64.96 128	67.00 103	77.70 90	81.58 105	71.71 103	62.94 81	49.16 142	43.40 129	43.24 127	41.34 152	61.42 109	76.24 97	74.63 119	84.84 121	88.52 100

GA-MVS		64.55 124	65.76 127	63.12 128	69.68 141	81.56 106	69.59 123	58.16 118	45.23 159	35.58 170	47.01 118	41.82 151	59.41 122	79.62 69	78.54 78	86.32 79	86.56 113

tpm cat1		67.47 105	67.05 116	67.98 94	76.63 102	81.51 107	74.49 86	47.65 185	61.18 90	61.12 60	42.51 134	53.02 127	64.74 91	70.11 164	71.50 155	83.22 150	89.49 87

UA-Net		64.62 122	68.23 109	60.42 147	77.53 94	81.38 108	60.08 174	57.47 130	47.01 149	44.75 121	60.68 64	71.32 45	41.84 185	73.27 129	72.25 151	80.83 177	71.68 187

CNLPA		71.37 79	70.27 95	72.66 64	80.79 68	81.33 109	71.07 113	65.75 56	82.36 29	64.80 43	42.46 135	56.49 105	72.70 43	73.00 134	70.52 168	80.84 176	85.76 124

test-LLR		68.23 98	71.61 85	64.28 120	71.37 132	81.32 110	63.98 155	61.03 99	58.62 100	42.96 132	52.74 89	61.65 77	57.74 137	75.64 104	78.09 86	88.61 22	93.21 45

TESTMET0.1,1		67.38 106	71.61 85	62.45 136	66.05 165	81.32 110	63.98 155	55.36 152	58.62 100	42.96 132	52.74 89	61.65 77	57.74 137	75.64 104	78.09 86	88.61 22	93.21 45

Fast-Effi-MVS+		67.59 102	67.56 113	67.62 97	73.67 120	81.14 112	71.12 111	54.79 159	58.88 99	50.61 99	46.70 121	47.05 141	69.12 71	76.06 100	76.44 98	86.43 78	86.65 112

tpmrst		67.15 108	68.12 110	66.03 106	76.21 106	80.98 113	71.27 107	45.05 191	60.69 93	50.63 98	46.95 119	54.15 121	65.30 86	71.80 147	71.77 153	87.72 44	90.48 76

OMC-MVS		74.03 64	75.82 64	71.95 68	79.56 73	80.98 113	75.35 76	63.21 74	84.48 23	61.83 55	61.54 61	66.89 57	69.41 68	76.60 94	74.07 127	82.34 163	86.15 118

ACMP	68.86 7	72.15 73	72.25 78	72.03 67	80.96 65	80.87 115	77.93 59	64.13 66	69.29 67	60.79 64	64.04 53	53.54 124	63.91 94	73.74 126	75.27 113	84.45 133	88.98 93
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TAPA-MVS	67.10 9	71.45 77	73.47 75	69.10 85	77.04 99	80.78 116	73.81 89	62.10 88	80.80 36	51.28 93	60.91 63	63.80 70	67.98 75	74.59 113	72.42 149	82.37 162	80.97 157
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDS-MVSNet		64.22 126	65.89 126	62.28 138	70.05 139	80.59 117	69.91 121	57.98 120	43.53 164	46.58 112	48.22 105	50.76 131	46.45 172	75.68 103	76.08 103	82.70 157	86.34 116
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EG-PatchMatch MVS		58.73 167	58.03 174	59.55 152	72.32 126	80.49 118	63.44 161	55.55 149	32.49 200	38.31 155	28.87 195	37.22 173	42.84 183	74.30 120	75.70 107	84.84 121	77.14 169

v2v482		63.68 131	62.85 143	64.65 115	68.01 151	80.46 119	71.90 98	57.60 127	44.26 161	42.82 134	39.80 153	38.62 168	61.56 108	73.06 132	74.86 116	86.03 88	88.90 96

v1144		63.00 136	62.39 147	63.70 125	67.72 154	80.27 120	71.23 108	56.40 138	42.51 166	40.81 143	38.12 161	37.73 169	60.42 116	74.46 115	74.55 121	85.64 104	89.12 92

LGP-MVS_train		72.02 74	73.18 76	70.67 76	82.13 59	80.26 121	79.58 51	63.04 76	70.09 63	51.98 90	65.06 50	55.62 112	62.49 104	75.97 101	76.32 101	84.80 125	88.93 94

FC-MVSNet-train		68.83 93	68.29 107	69.47 81	78.35 85	79.94 122	64.72 149	66.38 51	54.96 122	54.51 86	56.75 74	47.91 139	66.91 82	75.57 106	75.75 106	85.92 89	87.12 109

v144192		62.05 146	61.46 154	62.73 135	66.59 163	79.87 123	69.30 125	55.88 143	41.50 173	39.41 149	37.23 164	36.45 177	59.62 120	72.69 139	73.51 132	85.61 105	88.93 94

v1192		62.25 142	61.64 152	62.96 129	66.88 159	79.72 124	69.96 120	55.77 145	41.58 171	39.42 148	37.05 166	35.96 182	60.50 115	74.30 120	74.09 126	85.24 110	88.76 97

dps		64.08 127	63.22 137	65.08 111	75.27 114	79.65 125	66.68 143	46.63 189	56.94 107	55.67 80	43.96 126	43.63 149	64.00 93	69.50 169	69.82 170	82.25 164	79.02 164

v1921920		61.66 149	61.10 157	62.31 137	66.32 164	79.57 126	68.41 130	55.49 150	41.03 174	38.69 153	36.64 172	35.27 185	59.60 121	73.23 130	73.41 134	85.37 107	88.51 101

v148		62.00 147	61.19 156	62.96 129	67.46 157	79.49 127	67.87 132	57.66 126	42.30 167	45.02 120	38.20 160	38.89 167	54.77 148	69.83 166	72.60 148	84.96 115	87.01 110

FMVSNet3		70.41 83	71.89 82	68.68 88	70.89 137	79.42 128	75.63 70	60.97 101	65.32 78	51.06 94	47.37 111	62.05 73	64.90 89	82.49 36	82.27 35	88.64 21	84.34 134

v1240		61.09 152	60.55 161	61.72 141	65.92 168	79.28 129	67.16 140	54.91 156	39.79 180	38.10 156	36.08 174	34.64 187	59.15 125	72.86 135	73.36 136	85.10 112	87.84 105

CMPMVS	43.63 17	57.67 173	55.43 181	60.28 148	72.01 128	79.00 130	62.77 165	53.23 168	41.77 170	45.42 115	30.74 191	39.03 165	53.01 152	64.81 184	64.65 190	75.26 198	68.03 196
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
V42		62.86 138	62.97 140	62.74 134	60.84 188	78.99 131	71.46 106	57.13 134	46.85 150	44.28 124	38.87 155	40.73 160	57.63 139	72.60 140	74.14 125	85.09 114	88.63 98

Vis-MVSNet (Re-imp)		62.25 142	68.74 103	54.68 178	73.70 119	78.74 132	56.51 183	57.49 129	55.22 120	26.86 191	54.56 82	61.35 79	31.06 193	73.10 131	74.90 115	82.49 160	83.31 141

GBi-Net		69.21 88	70.40 93	67.81 95	69.49 142	78.65 133	74.54 81	60.97 101	65.32 78	51.06 94	47.37 111	62.05 73	63.43 96	77.49 85	78.22 83	87.37 53	83.73 137

test1		69.21 88	70.40 93	67.81 95	69.49 142	78.65 133	74.54 81	60.97 101	65.32 78	51.06 94	47.37 111	62.05 73	63.43 96	77.49 85	78.22 83	87.37 53	83.73 137

FMVSNet2		68.06 99	68.57 104	67.45 100	69.49 142	78.65 133	74.54 81	60.23 112	56.29 112	49.64 103	42.13 138	57.08 103	63.43 96	81.15 55	80.99 55	87.37 53	83.73 137

tpm		64.85 121	66.02 125	63.48 126	74.52 117	78.38 136	70.98 114	44.99 193	51.61 133	43.28 131	47.66 109	53.18 125	60.57 113	70.58 158	71.30 162	86.54 75	89.45 89

ACMH	59.42 14	61.59 150	59.22 169	64.36 119	78.92 81	78.26 137	67.65 134	67.48 45	39.81 179	30.98 185	38.25 159	34.59 188	61.37 111	70.55 159	73.47 133	79.74 183	79.59 161
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v8		63.44 133	62.58 145	64.43 117	68.28 150	78.07 138	71.82 99	54.85 157	46.70 152	45.20 118	39.40 154	40.91 157	60.54 114	72.85 136	74.39 124	85.92 89	85.76 124

Patchmtry						78.06 139	67.53 136	43.18 198		41.40 138

UniMVSNet (Re)		60.62 155	62.93 142	57.92 162	67.64 155	77.90 140	61.75 168	61.24 98	49.83 139	29.80 187	42.57 132	40.62 161	43.36 181	70.49 160	73.27 139	83.76 142	85.81 123

UniMVSNet_NR-MVSNet		62.30 141	63.51 136	60.89 144	69.48 145	77.83 141	64.07 153	63.94 68	50.03 137	31.17 183	44.82 125	41.12 155	51.37 157	71.02 152	74.81 117	85.30 108	84.95 129

v10		63.00 136	62.22 148	63.90 124	67.88 153	77.78 142	71.59 104	54.34 161	45.37 158	42.76 135	38.53 156	38.93 166	61.05 112	74.39 117	74.52 122	85.75 93	86.04 119

ACMM	66.70 10	70.42 81	68.49 105	72.67 63	82.85 53	77.76 143	77.70 61	64.76 63	64.61 82	60.74 65	49.29 100	53.97 122	65.86 85	74.97 109	75.57 110	84.13 140	83.29 142
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		58.86 165	60.91 158	56.47 173	62.38 184	77.57 144	58.97 178	52.98 169	38.76 183	36.17 166	42.26 137	47.94 138	46.45 172	70.23 163	70.79 165	81.86 168	78.82 165

DCV-MVSNet		69.13 90	69.07 100	69.21 83	77.65 92	77.52 145	74.68 79	57.85 124	54.92 123	55.34 84	55.74 76	55.56 113	66.35 83	75.05 108	76.56 97	83.35 147	88.13 104

test-mter		64.06 128	69.24 99	58.01 161	59.07 194	77.40 146	59.13 177	48.11 183	55.64 118	39.18 151	51.56 94	58.54 93	55.38 146	73.52 128	76.00 104	87.22 62	92.05 59

EPNet_dtu		66.17 112	70.13 96	61.54 142	81.04 64	77.39 147	68.87 128	62.50 87	69.78 64	33.51 178	63.77 54	56.22 107	37.65 191	72.20 142	72.18 152	85.69 99	79.38 162
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs5		59.72 159	60.24 163	59.11 157	62.77 182	77.33 148	63.17 163	54.00 163	40.21 178	37.23 160	40.41 148	35.99 181	51.75 155	72.55 141	72.74 147	85.72 98	82.45 150

MIMVSNet		57.78 172	59.71 167	55.53 175	54.79 202	77.10 149	63.89 157	45.02 192	46.59 153	36.79 163	28.36 196	40.77 159	45.84 176	74.97 109	76.58 96	86.87 70	73.60 180

pm-mvs1		59.21 163	59.58 168	58.77 159	67.97 152	77.07 150	64.12 151	57.20 132	34.73 196	36.86 161	35.34 177	40.54 162	43.34 182	74.32 119	73.30 138	83.13 154	81.77 155

Fast-Effi-MVS+-dtu		63.05 135	64.72 131	61.11 143	71.21 135	76.81 151	70.72 116	43.13 200	52.51 132	35.34 171	46.55 122	46.36 142	61.40 110	71.57 150	71.44 157	84.84 121	87.79 106

MSDG		65.57 116	61.57 153	70.24 78	82.02 60	76.47 152	74.46 87	68.73 39	56.52 110	50.33 100	38.47 157	41.10 156	62.42 105	72.12 143	72.94 144	83.47 146	73.37 182

pmmvs4		63.14 134	62.46 146	63.94 123	66.03 166	76.40 153	66.82 142	57.60 127	56.74 108	50.26 101	40.81 147	37.51 171	59.26 124	71.75 148	71.48 156	83.68 145	82.53 148

FMVSNet1		63.48 132	63.07 139	63.97 122	65.31 170	76.37 154	71.77 102	57.90 123	43.32 165	45.66 114	35.06 180	49.43 134	58.57 128	77.49 85	78.22 83	84.59 130	81.60 156

tfpnnormal		58.97 164	56.48 179	61.89 139	71.27 134	76.21 155	66.65 144	61.76 95	32.90 199	36.41 165	27.83 197	29.14 205	50.64 161	73.06 132	73.05 143	84.58 131	83.15 146

DU-MVS		60.87 154	61.82 151	59.76 151	66.69 160	75.87 156	64.07 153	61.96 89	49.31 140	31.17 183	42.76 129	36.95 174	51.37 157	69.67 167	73.20 142	83.30 149	84.95 129

NR-MVSNet		61.08 153	62.09 150	59.90 149	71.96 129	75.87 156	63.60 159	61.96 89	49.31 140	27.95 188	42.76 129	33.85 192	48.82 164	74.35 118	74.05 128	85.13 111	84.45 132

LS3D		64.54 125	62.14 149	67.34 101	80.85 66	75.79 158	69.99 119	65.87 55	60.77 92	44.35 123	42.43 136	45.95 144	65.01 87	69.88 165	68.69 175	77.97 191	71.43 189

PatchMatch-RL		62.22 145	60.69 159	64.01 121	68.74 147	75.75 159	59.27 176	60.35 109	56.09 114	53.80 87	47.06 117	36.45 177	64.80 90	68.22 172	67.22 179	77.10 193	74.02 177

PatchT		60.46 156	63.85 134	56.51 172	65.95 167	75.68 160	47.34 197	41.39 205	53.89 129	41.40 138	37.84 162	50.30 133	57.29 140	72.76 137	73.27 139	85.67 100	83.23 144

thisisatest0515		59.37 162	60.68 160	57.84 164	64.39 174	75.65 161	58.56 179	53.86 164	41.55 172	42.12 137	40.40 149	39.59 164	47.09 170	71.69 149	73.79 129	81.02 175	82.08 153

TranMVSNet+NR-MVSNet		60.38 157	61.30 155	59.30 155	68.34 149	75.57 162	63.38 162	63.78 70	46.74 151	27.73 189	42.56 133	36.84 175	47.66 167	70.36 161	74.59 120	84.91 118	82.46 149

Effi-MVS+-dtu		64.58 123	64.08 133	65.16 110	73.04 124	75.17 163	70.68 117	56.23 141	54.12 128	44.71 122	47.42 110	51.10 130	63.82 95	68.08 173	66.32 184	82.47 161	86.38 115

IterMVS-LS		66.08 113	66.56 120	65.51 107	73.67 120	74.88 164	70.89 115	53.55 166	50.42 136	48.32 108	50.59 97	55.66 111	61.83 106	73.93 122	74.42 123	84.82 124	86.01 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PLC	64.00 12	68.54 94	66.66 118	70.74 75	80.28 72	74.88 164	72.64 94	63.70 71	69.26 68	55.71 79	47.24 114	55.31 114	70.42 58	72.05 145	70.67 166	81.66 170	77.19 168
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		57.04 175	56.64 178	57.52 166	62.85 181	74.75 166	61.76 167	51.80 174	35.58 195	36.02 168	32.33 186	33.61 193	50.16 162	67.73 174	70.34 169	82.51 159	82.12 152

TransMVSNet (Re)		57.83 170	56.90 177	58.91 158	72.26 127	74.69 167	63.57 160	61.42 97	32.30 201	32.65 179	33.97 182	35.96 182	39.17 189	73.84 125	72.84 146	84.37 134	74.69 175

ADS-MVSNet		58.40 169	59.16 170	57.52 166	65.80 169	74.57 168	60.26 172	40.17 209	50.51 135	38.01 157	40.11 152	44.72 146	59.36 123	64.91 182	66.55 182	81.53 171	72.72 185

ACMH+	60.36 13	61.16 151	58.38 171	64.42 118	77.37 98	74.35 169	68.45 129	62.81 83	45.86 156	38.48 154	35.71 175	37.35 172	59.81 119	67.24 175	69.80 172	79.58 184	78.32 166

Baseline_NR-MVSNet		59.47 161	60.28 162	58.54 160	66.69 160	73.90 170	61.63 169	62.90 82	49.15 144	26.87 190	35.18 179	37.62 170	48.20 165	69.67 167	73.61 131	84.92 116	82.82 147

MDTV_nov1_ep13_2view		54.47 183	54.61 182	54.30 182	60.50 189	73.82 171	57.92 180	43.38 197	39.43 182	32.51 180	33.23 183	34.05 190	47.26 169	62.36 190	66.21 185	84.24 136	73.19 183

test0.0.03 1		57.35 174	59.89 166	54.38 181	71.37 132	73.45 172	52.71 189	61.03 99	46.11 155	26.33 192	41.73 140	44.08 147	29.72 195	71.43 151	70.90 163	85.10 112	71.56 188

UniMVSNet_ETH3D		57.83 170	56.46 180	59.43 154	63.24 179	73.22 173	67.70 133	55.58 148	36.17 191	36.84 162	32.64 184	35.14 186	51.50 156	65.81 178	69.81 171	81.73 169	82.44 151

pmmvs6		54.20 184	53.54 186	54.97 176	63.22 180	72.98 174	60.17 173	52.32 173	26.77 210	34.30 175	23.29 204	36.23 179	40.33 188	68.77 171	68.76 174	79.47 186	78.00 167

MVS-HIRNet		53.86 186	53.02 188	54.85 177	60.30 190	72.36 175	44.63 205	42.20 203	39.45 181	43.47 128	21.66 208	34.00 191	55.47 145	65.42 180	67.16 180	83.02 155	71.08 191

IterMVS		61.87 148	63.55 135	59.90 149	67.29 158	72.20 176	67.34 139	48.56 181	47.48 148	37.86 159	47.07 116	48.27 135	54.08 150	72.12 143	73.71 130	84.30 135	83.99 136
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		60.21 158	62.97 140	57.00 170	66.64 162	71.84 177	67.53 136	46.93 188	47.56 147	36.77 164	46.85 120	48.21 136	52.51 153	70.36 161	72.40 150	71.63 206	83.53 140

USDC		59.69 160	60.03 165	59.28 156	64.04 175	71.84 177	63.15 164	55.36 152	54.90 124	35.02 172	48.34 104	29.79 204	58.16 129	70.60 157	71.33 161	79.99 181	73.42 181

SCA		63.90 129	66.67 117	60.66 145	73.75 118	71.78 179	59.87 175	43.66 196	61.13 91	45.03 119	51.64 93	59.45 90	57.92 134	70.96 153	70.80 164	83.71 144	80.92 158

anonymousdsp		54.99 179	57.24 176	52.36 184	53.82 204	71.75 180	51.49 190	48.14 182	33.74 197	33.66 177	38.34 158	36.13 180	47.54 168	64.53 186	70.60 167	79.53 185	85.59 126

pmnet_mix02		53.92 185	53.30 187	54.65 180	61.89 185	71.33 181	54.54 187	54.17 162	40.38 176	34.65 173	34.76 181	30.68 203	40.44 187	60.97 192	63.71 192	82.19 165	71.24 190

CR-MVSNet		62.31 140	64.75 129	59.47 153	68.63 148	71.29 182	67.53 136	43.18 198	55.83 115	41.40 138	41.04 144	55.85 109	57.29 140	72.76 137	73.27 139	78.77 188	83.23 144

RPMNet		58.63 168	62.80 144	53.76 183	67.59 156	71.29 182	54.60 186	38.13 210	55.83 115	35.70 169	41.58 141	53.04 126	47.89 166	66.10 177	67.38 177	78.65 190	84.40 133

our_test_3					63.32 177	71.07 184	55.90 184

LTVRE_ROB	47.26 16	49.41 197	49.91 200	48.82 191	64.76 172	69.79 185	49.05 193	47.12 187	20.36 217	16.52 205	36.65 171	26.96 208	50.76 160	60.47 193	63.16 195	64.73 209	72.00 186
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
Anonymous20231206		52.23 189	52.80 191	51.56 186	64.70 173	69.41 186	51.01 191	58.60 116	36.63 188	22.44 198	21.80 207	31.42 199	30.52 194	66.79 176	67.83 176	82.10 166	75.73 171

WR-MVS		51.02 191	54.56 183	46.90 197	63.84 176	69.23 187	44.78 204	56.38 139	38.19 184	14.19 209	37.38 163	36.82 176	22.39 205	60.14 194	66.20 186	79.81 182	73.95 179

CHOSEN 280x420		62.23 144	66.57 119	57.17 169	59.88 191	68.92 188	61.20 171	42.28 202	54.17 127	39.57 146	47.78 108	64.97 64	62.68 101	73.85 124	69.52 173	77.43 192	86.75 111

CVMVSNet		54.92 181	58.16 172	51.13 188	62.61 183	68.44 189	55.45 185	52.38 172	42.28 168	21.45 199	47.10 115	46.10 143	37.96 190	64.42 187	63.81 191	76.92 194	75.01 174

pmmvs-eth3d		55.20 176	53.95 185	56.65 171	57.34 200	67.77 190	57.54 181	53.74 165	40.93 175	41.09 142	31.19 190	29.10 206	49.07 163	65.54 179	67.28 178	81.14 173	75.81 170

WR-MVS_H		49.62 196	52.63 192	46.11 200	58.80 195	67.58 191	46.14 202	54.94 154	36.51 189	13.63 212	36.75 170	35.67 184	22.10 206	56.43 202	62.76 196	81.06 174	72.73 184

COLMAP_ROB	51.17 15	55.13 177	52.90 190	57.73 165	73.47 123	67.21 192	62.13 166	55.82 144	47.83 146	34.39 174	31.60 188	34.24 189	44.90 179	63.88 189	62.52 197	75.67 196	63.02 205
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testgi		48.51 199	50.53 197	46.16 199	64.78 171	67.15 193	41.54 207	54.81 158	29.12 206	17.03 203	32.07 187	31.98 195	20.15 209	65.26 181	67.00 181	78.67 189	61.10 209

FMVSNet5		58.86 165	60.24 163	57.25 168	52.66 206	66.25 194	63.77 158	52.86 171	57.85 106	37.92 158	36.12 173	52.22 128	51.37 157	70.88 154	71.43 158	84.92 116	66.91 198

PEN-MVS		51.04 190	52.94 189	48.82 191	61.45 187	66.00 195	48.68 194	57.20 132	36.87 186	15.36 207	36.98 167	32.72 194	28.77 199	57.63 198	66.37 183	81.44 172	74.00 178

CP-MVSNet		50.57 192	52.60 193	48.21 194	58.77 196	65.82 196	48.17 195	56.29 140	37.41 185	16.59 204	37.14 165	31.95 196	29.21 196	56.60 201	63.71 192	80.22 179	75.56 172

PS-CasMVS		50.17 193	52.02 194	48.02 195	58.60 197	65.54 197	48.04 196	56.19 142	36.42 190	16.42 206	35.68 176	31.33 200	28.85 198	56.42 203	63.54 194	80.01 180	75.18 173

TDRefinement		52.70 187	51.02 196	54.66 179	57.41 199	65.06 198	61.47 170	54.94 154	44.03 162	33.93 176	30.13 193	27.57 207	46.17 174	61.86 191	62.48 198	74.01 202	66.06 199

test20.03		47.23 202	48.69 202	45.53 201	63.28 178	64.39 199	41.01 208	56.93 136	29.16 205	15.21 208	23.90 201	30.76 202	17.51 212	64.63 185	65.26 187	79.21 187	62.71 206

DTE-MVSNet		49.82 195	51.92 195	47.37 196	61.75 186	64.38 200	45.89 203	57.33 131	36.11 192	12.79 214	36.87 168	31.93 197	25.73 202	58.01 196	65.22 188	80.75 178	70.93 192

SixPastTwentyTwo		49.11 198	49.22 201	48.99 190	58.54 198	64.14 201	47.18 198	47.75 184	31.15 203	24.42 194	41.01 145	26.55 209	44.04 180	54.76 206	58.70 203	71.99 205	68.21 194

TinyColmap		52.66 188	50.09 199	55.65 174	59.72 192	64.02 202	57.15 182	52.96 170	40.28 177	32.51 180	32.42 185	20.97 215	56.65 142	63.95 188	65.15 189	74.91 199	63.87 203

N_pmnet		47.67 200	47.00 204	48.45 193	54.72 203	62.78 203	46.95 199	51.25 175	36.01 193	26.09 193	26.59 200	25.93 212	35.50 192	55.67 205	59.01 201	76.22 195	63.04 204

MDA-MVSNet-bldmvs		44.15 204	42.27 209	46.34 198	38.34 214	62.31 204	46.28 200	55.74 146	29.83 204	20.98 200	27.11 199	16.45 220	41.98 184	41.11 213	57.47 204	74.72 200	61.65 208

PM-MVS		50.11 194	50.38 198	49.80 189	47.23 212	62.08 205	50.91 192	44.84 194	41.90 169	36.10 167	35.22 178	26.05 211	46.83 171	57.64 197	55.42 208	72.90 203	74.32 176

new-patchmatchnet		42.21 205	42.97 206	41.33 204	53.05 205	59.89 206	39.38 209	49.61 177	28.26 208	12.10 215	22.17 206	21.54 214	19.22 210	50.96 208	56.04 206	74.61 201	61.92 207

RPSCF		55.07 178	58.06 173	51.57 185	48.87 210	58.95 207	53.68 188	41.26 207	62.42 86	45.88 113	54.38 85	54.26 120	53.75 151	57.15 199	53.53 209	66.01 208	65.75 200

MIMVSNet1		40.84 207	43.46 205	37.79 207	32.14 215	58.92 208	39.24 210	50.83 176	27.00 209	11.29 216	16.76 214	26.53 210	17.75 211	57.14 200	61.12 200	75.46 197	56.78 210

FC-MVSNet-test		47.24 201	54.37 184	38.93 206	59.49 193	58.25 209	34.48 213	53.36 167	45.66 157	6.66 219	50.62 96	42.02 150	16.62 213	58.39 195	61.21 199	62.99 210	64.40 202

EU-MVSNet		44.84 203	47.85 203	41.32 205	49.26 209	56.59 210	43.07 206	47.64 186	33.03 198	13.82 210	36.78 169	30.99 201	24.37 203	53.80 207	55.57 207	69.78 207	68.21 194

gm-plane-assit		54.99 179	57.99 175	51.49 187	69.27 146	54.42 211	32.32 214	42.59 201	21.18 215	13.71 211	23.61 202	43.84 148	60.21 117	87.09 5	86.55 5	90.81 4	89.28 90

pmmvs3		41.86 206	42.29 208	41.36 203	39.80 213	52.66 212	38.93 211	35.85 214	23.40 214	20.22 201	19.30 209	20.84 216	40.56 186	55.98 204	58.79 202	72.80 204	65.03 201

ambc			42.30 207		50.36 208	49.51 213	35.47 212		32.04 202	23.53 195	17.36 211	8.95 222	29.06 197	64.88 183	56.26 205	61.29 211	67.12 197

FPMVS		39.11 208	36.39 210	42.28 202	55.97 201	45.94 214	46.23 201	41.57 204	35.73 194	22.61 196	23.46 203	19.82 217	28.32 200	43.57 210	40.67 212	58.96 212	45.54 212

new_pmnet		33.19 209	35.52 211	30.47 209	27.55 219	45.31 215	29.29 215	30.92 215	29.00 207	9.88 218	18.77 210	17.64 219	26.77 201	44.07 209	45.98 211	58.41 213	47.87 211

PMMVS2		20.45 213	22.31 215	18.27 215	20.52 220	26.73 216	14.85 220	28.43 217	13.69 218	0.79 224	10.35 216	9.10 221	3.83 219	27.64 216	32.87 214	41.17 215	35.81 214

PMVS	27.44 18	32.08 210	29.07 213	35.60 208	48.33 211	24.79 217	26.97 216	41.34 206	20.45 216	22.50 197	17.11 213	18.64 218	20.44 208	41.99 212	38.06 213	54.02 214	42.44 213
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		24.91 212	24.61 214	25.26 211	31.47 216	21.59 218	18.06 218	37.53 211	25.43 212	10.03 217	4.18 220	4.25 224	14.85 214	43.20 211	47.03 210	39.62 216	26.55 217
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		28.15 211	34.48 212	20.76 212	6.76 223	21.18 219	21.03 217	18.41 218	36.77 187	17.52 202	15.67 215	31.63 198	24.05 204	41.03 214	26.69 216	36.82 217	68.38 193

MVE	15.98 19	14.37 216	16.36 216	12.04 217	7.72 222	20.24 220	5.90 224	29.05 216	8.28 221	3.92 221	4.72 219	2.42 225	9.57 217	18.89 218	31.46 215	16.07 222	28.53 216
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						19.81 221	17.01 219	10.02 219	23.61 213	5.85 220	17.21 212	8.03 223	21.13 207	22.60 217		21.42 221	30.01 215

E-PMN		15.08 214	11.65 217	19.08 213	28.73 217	12.31 222	6.95 223	36.87 213	10.71 220	3.63 222	5.13 217	2.22 227	13.81 216	11.34 219	18.50 218	24.49 219	21.32 218

EMVS		14.40 215	10.71 218	18.70 214	28.15 218	12.09 223	7.06 222	36.89 212	11.00 219	3.56 223	4.95 218	2.27 226	13.91 215	10.13 220	16.06 219	22.63 220	18.51 219

tmp_tt				16.09 216	13.07 221	8.12 224	13.61 221	2.08 220	55.09 121	30.10 186	40.26 150	22.83 213	5.35 218	29.91 215	25.25 217	32.33 218

testmvs		0.05 217	0.08 219	0.01 218	0.00 225	0.01 225	0.03 226	0.01 222	0.05 222	0.00 226	0.14 222	0.01 228	0.03 222	0.05 221	0.05 220	0.01 223	0.24 221

test123		0.05 217	0.08 219	0.01 218	0.00 225	0.01 225	0.01 227	0.00 223	0.05 222	0.00 226	0.16 221	0.00 229	0.04 220	0.02 222	0.05 220	0.00 224	0.26 220

uanet_test		0.00 219	0.00 221	0.00 220	0.00 225	0.00 227	0.00 228	0.00 223	0.00 224	0.00 226	0.00 223	0.00 229	0.00 223	0.00 223	0.00 222	0.00 224	0.00 222

sosnet-low-res		0.00 219	0.00 221	0.00 220	0.00 225	0.00 227	0.00 228	0.00 223	0.00 224	0.00 226	0.00 223	0.00 229	0.00 223	0.00 223	0.00 222	0.00 224	0.00 222

sosnet		0.00 219	0.00 221	0.00 220	0.00 225	0.00 227	0.00 228	0.00 223	0.00 224	0.00 226	0.00 223	0.00 229	0.00 223	0.00 223	0.00 222	0.00 224	0.00 222

RE-MVS-def										31.47 182

9.14												84.47 7

SR-MVS					86.33 45			67.54 44				80.78 20

MTAPA										78.32 11		79.42 24

MTMP										76.04 15		76.65 28

Patchmatch-RL test							2.17 225

mPP-MVS					86.96 40							70.61 48

NP-MVS									81.60 34

High-resolution multi-view benchmark