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 7	95.09 1	88.55 5	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 21	98.21 3

DVP-MVS++		87.98 3	89.76 5	85.89 2	92.57 6	94.57 3	88.34 6	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 31	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 11	79.75 9	83.52 26	82.72 32	88.75 20	95.37 23

DVP-MVS		88.07 2	90.73 2	84.97 4	91.98 10	95.01 2	87.86 10	76.88 5	93.90 2	85.15 2	90.11 7	86.90 2	79.46 12	86.26 10	84.67 18	88.50 28	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
MSP-MVS		87.87 4	90.57 3	84.73 5	89.38 27	91.60 17	88.24 8	74.15 12	93.55 3	82.28 4	94.99 1	83.21 12	85.96 3	87.67 4	84.67 18	88.32 32	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
MCST-MVS		85.75 9	86.99 13	84.31 6	94.07 3	92.80 8	88.15 9	79.10 2	85.66 21	70.72 29	76.50 33	80.45 22	82.17 5	88.35 2	87.49 3	91.63 2	97.65 4

DPE-MVS		87.60 5	90.44 4	84.29 7	92.09 9	93.44 6	88.69 4	75.11 9	93.06 5	80.80 6	94.23 2	86.70 3	81.44 7	84.84 18	83.52 27	87.64 49	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CNVR-MVS		85.96 8	87.58 11	84.06 8	92.58 5	92.40 11	87.62 11	77.77 4	88.44 14	75.93 16	79.49 26	81.97 18	81.65 6	87.04 6	86.58 4	88.79 18	97.18 7

APDe-MVS		86.37 7	88.41 8	84.00 9	91.43 15	91.83 15	88.34 6	74.67 10	91.19 7	81.76 5	91.13 4	81.94 19	80.07 8	83.38 27	82.58 34	87.69 47	96.78 10
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPM-MVS		85.41 11	86.72 16	83.89 10	91.66 13	91.92 14	90.49 2	78.09 3	86.90 17	73.95 20	74.52 35	82.01 17	79.29 13	90.24 1	90.65 1	89.86 6	90.78 72

NCCC		84.16 16	85.46 21	82.64 11	92.34 8	90.57 23	86.57 14	76.51 8	86.85 18	72.91 23	77.20 32	78.69 26	79.09 15	84.64 20	84.88 16	88.44 29	95.41 21

HPM-MVS++		85.64 10	88.43 7	82.39 12	92.65 4	90.24 26	85.83 17	74.21 11	90.68 9	75.63 17	86.77 13	84.15 8	78.68 16	86.33 8	85.26 9	87.32 58	95.60 17

APD-MVS		84.83 13	87.00 12	82.30 13	89.61 25	89.21 35	86.51 15	73.64 16	90.98 8	77.99 12	89.89 8	80.04 24	79.18 14	82.00 48	81.37 49	86.88 71	95.49 19
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		84.39 14	86.58 17	81.83 14	88.09 38	86.47 67	85.63 19	73.62 17	90.13 11	79.24 9	89.67 9	82.99 13	77.72 18	81.22 53	80.92 58	86.68 75	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
SMA-MVS		85.24 12	88.27 9	81.72 15	91.74 12	90.71 20	86.71 13	73.16 19	90.56 10	74.33 19	83.07 18	85.88 4	77.16 20	86.28 9	85.58 6	87.23 62	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
SD-MVS		84.31 15	86.96 14	81.22 16	88.98 31	88.68 39	85.65 18	73.85 15	89.09 13	79.63 8	87.34 12	84.84 6	73.71 34	82.66 35	81.60 46	85.48 108	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
DeepC-MVS_fast	75.41 2	81.69 24	82.10 32	81.20 17	91.04 17	87.81 52	83.42 27	74.04 13	83.77 25	71.09 27	66.88 46	72.44 38	79.48 11	85.08 15	84.97 14	88.12 39	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
CSCG		82.90 20	84.52 23	81.02 18	91.85 11	93.43 7	87.14 12	74.01 14	81.96 31	76.14 14	70.84 37	82.49 14	69.71 63	82.32 41	85.18 11	87.26 61	95.40 22

HFP-MVS		82.48 22	84.12 24	80.56 19	90.15 19	87.55 53	84.28 24	69.67 32	85.22 22	77.95 13	84.69 16	75.94 30	75.04 27	81.85 49	81.17 53	86.30 83	92.40 55

3Dnovator	70.49 5	78.42 38	76.77 57	80.35 20	91.43 15	90.27 25	81.84 36	70.79 26	72.10 58	71.95 24	50.02 100	67.86 57	77.47 19	82.89 32	84.24 20	88.61 24	89.99 83

ACMMP_NAP		83.54 17	86.37 18	80.25 21	89.57 26	90.10 28	85.27 21	71.66 23	87.38 15	73.08 22	84.23 17	80.16 23	75.31 25	84.85 17	83.64 24	86.57 76	94.21 35

MSLP-MVS++		78.57 37	77.33 52	80.02 22	88.39 34	84.79 82	84.62 23	66.17 55	75.96 51	78.40 10	61.59 61	71.47 45	73.54 37	78.43 78	78.88 76	88.97 16	90.18 82

DeepC-MVS	74.46 3	80.30 29	81.05 35	79.42 23	87.42 40	88.50 41	83.23 28	73.27 18	82.78 28	71.01 28	62.86 58	69.93 51	74.80 29	84.30 21	84.20 21	86.79 74	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
AdaColmap		76.23 52	73.55 73	79.35 24	89.38 27	85.00 81	79.99 51	73.04 20	76.60 50	71.17 26	55.18 80	57.99 101	77.87 17	76.82 93	76.82 95	84.67 130	86.45 115

SteuartSystems-ACMMP		82.51 21	85.35 22	79.20 25	90.25 18	89.39 33	84.79 22	70.95 25	82.86 27	68.32 37	86.44 14	77.19 27	73.07 39	83.63 25	83.64 24	87.82 43	94.34 31
Skip Steuart: Steuart Systems R&D Blog.
train_agg		83.35 18	86.93 15	79.17 26	89.70 24	88.41 42	85.60 20	72.89 21	86.31 19	66.58 40	90.48 6	82.24 16	73.06 40	83.10 31	82.64 33	87.21 66	95.30 24

DELS-MVS		79.49 30	79.84 40	79.08 27	88.26 37	92.49 9	84.12 26	70.63 27	65.27 81	69.60 35	61.29 63	66.50 60	72.75 43	88.07 3	88.03 2	89.13 14	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
3Dnovator+	70.16 6	77.87 41	77.29 53	78.55 28	89.25 29	88.32 44	80.09 49	67.95 43	74.89 56	71.83 25	52.05 93	70.68 48	76.27 24	82.27 42	82.04 36	85.92 91	90.77 74

CANet		80.90 27	82.93 28	78.53 29	86.83 44	92.26 12	81.19 42	66.95 48	81.60 34	69.90 32	66.93 45	74.80 32	76.79 21	84.68 19	84.77 17	89.50 11	95.50 18

MP-MVS		80.94 26	83.49 26	77.96 30	88.48 32	88.16 46	82.82 32	69.34 34	80.79 37	69.67 33	82.35 21	77.13 28	71.60 52	80.97 58	80.96 57	85.87 94	94.06 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + GP.		82.27 23	85.98 19	77.94 31	80.72 70	88.25 45	81.12 43	67.71 44	87.10 16	73.31 21	85.23 15	83.68 9	76.64 22	80.43 61	81.47 48	88.15 38	95.66 16

ACMMPR		80.62 28	82.98 27	77.87 32	88.41 33	87.05 58	83.02 29	69.18 35	83.91 24	68.35 36	82.89 19	73.64 35	72.16 47	80.78 59	81.13 54	86.10 88	91.43 62

DeepPCF-MVS	76.94 1	83.08 19	87.77 10	77.60 33	90.11 20	90.96 19	78.48 55	72.63 22	93.10 4	65.84 41	80.67 24	81.55 20	74.80 29	85.94 13	85.39 8	83.75 145	96.77 11

QAPM		77.50 44	77.43 51	77.59 34	91.52 14	92.00 13	81.41 40	70.63 27	66.22 74	58.05 72	54.70 81	71.79 44	74.49 32	82.46 37	82.04 36	89.46 12	92.79 53

CLD-MVS		77.36 46	77.29 53	77.45 35	82.21 59	88.11 47	81.92 35	68.96 37	77.97 45	69.62 34	62.08 59	59.44 92	73.57 36	81.75 50	81.27 51	88.41 30	90.39 79
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CP-MVS		79.44 31	81.51 34	77.02 36	86.95 42	85.96 76	82.00 34	68.44 41	81.82 32	67.39 38	77.43 30	73.68 34	71.62 51	79.56 70	79.58 70	85.73 98	92.51 54

TSAR-MVS + ACMM		81.59 25	85.84 20	76.63 37	89.82 23	86.53 66	86.32 16	66.72 51	85.96 20	65.43 42	88.98 11	82.29 15	67.57 81	82.06 46	81.33 50	83.93 143	93.75 41

PGM-MVS		79.42 34	81.84 33	76.60 38	88.38 35	86.69 62	82.97 31	65.75 57	80.39 38	64.94 43	81.95 23	72.11 43	71.41 54	80.45 60	80.55 63	86.18 85	90.76 75

MVS_111021_HR		77.42 45	78.40 47	76.28 39	86.95 42	90.68 21	77.41 64	70.56 30	66.21 75	62.48 54	66.17 50	63.98 69	72.08 48	82.87 33	83.15 28	88.24 35	95.71 15

MVS_0304		79.43 32	82.20 30	76.20 40	84.22 52	91.79 16	81.82 37	63.81 70	76.83 49	61.71 57	66.37 48	75.52 31	76.38 23	85.54 14	85.03 13	89.28 13	94.32 32

CDPH-MVS		79.39 35	82.13 31	76.19 41	89.22 30	88.34 43	84.20 25	71.00 24	79.67 41	56.97 77	77.77 29	72.24 42	68.50 75	81.33 52	82.74 30	87.23 62	92.84 51

OpenMVS	67.62 8	74.92 61	73.91 71	76.09 42	90.10 21	90.38 24	78.01 59	66.35 53	66.09 76	62.80 50	46.33 125	64.55 67	71.77 50	79.92 65	80.88 59	87.52 53	89.20 92

EPNet		79.28 36	82.25 29	75.83 43	88.31 36	90.14 27	79.43 53	68.07 42	81.76 33	61.26 60	77.26 31	70.08 50	70.06 61	82.43 39	82.00 38	87.82 43	92.09 57
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MAR-MVS		77.19 47	78.37 48	75.81 44	89.87 22	90.58 22	79.33 54	65.56 59	77.62 47	58.33 71	59.24 71	67.98 55	74.83 28	82.37 40	83.12 29	86.95 69	87.67 108
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
canonicalmvs		77.65 42	79.59 41	75.39 45	81.52 63	89.83 32	81.32 41	60.74 106	80.05 39	66.72 39	68.43 41	65.09 63	74.72 31	78.87 74	82.73 31	87.32 58	92.16 56

X-MVS		78.16 40	80.55 37	75.38 46	87.99 39	86.27 71	81.05 44	68.98 36	78.33 43	61.07 62	75.25 34	72.27 39	67.52 82	80.03 63	80.52 64	85.66 105	91.20 66

ACMMP		77.61 43	79.59 41	75.30 47	85.87 48	85.58 77	81.42 39	67.38 47	79.38 42	62.61 52	78.53 27	65.79 62	68.80 74	78.56 77	78.50 81	85.75 95	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
HQP-MVS		78.26 39	80.91 36	75.17 48	85.67 49	84.33 88	83.01 30	69.38 33	79.88 40	55.83 78	79.85 25	64.90 66	70.81 56	82.46 37	81.78 41	86.30 83	93.18 47

casdiffmvs_mvg		75.57 56	76.04 62	75.02 49	80.48 72	89.31 34	80.79 47	64.04 68	66.95 72	63.87 46	57.52 73	61.33 82	72.90 41	82.01 47	81.99 39	88.03 40	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
PVSNet_BlendedMVS		76.84 49	78.47 45	74.95 50	82.37 57	89.90 30	75.45 75	65.45 60	74.99 54	70.66 30	63.07 56	58.27 99	67.60 79	84.24 22	81.70 43	88.18 36	97.10 8

PVSNet_Blended		76.84 49	78.47 45	74.95 50	82.37 57	89.90 30	75.45 75	65.45 60	74.99 54	70.66 30	63.07 56	58.27 99	67.60 79	84.24 22	81.70 43	88.18 36	97.10 8

OPM-MVS		72.74 70	70.93 90	74.85 52	85.30 50	84.34 87	82.82 32	69.79 31	49.96 139	55.39 84	54.09 88	60.14 89	70.04 62	80.38 62	79.43 71	85.74 97	88.20 104
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PCF-MVS	70.85 4	75.73 55	76.55 60	74.78 53	83.67 53	88.04 50	81.47 38	70.62 29	69.24 69	57.52 75	60.59 67	69.18 53	70.65 58	77.11 90	77.65 89	84.75 128	94.01 37
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		75.20 59	75.69 65	74.63 54	79.26 79	89.07 36	78.47 56	63.59 73	67.05 71	63.79 47	55.72 78	60.32 87	73.58 35	82.16 43	81.78 41	89.08 15	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
PHI-MVS		79.43 32	84.06 25	74.04 55	86.15 47	91.57 18	80.85 46	68.90 38	82.22 30	51.81 93	78.10 28	74.28 33	70.39 60	84.01 24	84.00 22	86.14 87	94.24 33

MVS_Test		75.22 58	76.69 58	73.51 56	79.30 77	88.82 38	80.06 50	58.74 115	69.77 65	57.50 76	59.78 70	61.35 80	75.31 25	82.07 45	83.60 26	90.13 5	91.41 64

CPTT-MVS		75.43 57	77.13 55	73.44 57	81.43 64	82.55 100	80.96 45	64.35 65	77.95 46	61.39 59	69.20 40	70.94 47	69.38 70	73.89 124	73.32 138	83.14 155	92.06 58

MVSTER		76.92 48	79.92 39	73.42 58	74.98 116	82.97 96	78.15 58	63.41 74	78.02 44	64.41 45	67.54 43	72.80 37	71.05 55	83.29 30	83.73 23	88.53 27	91.12 67

CHOSEN 1792x2688		72.55 71	71.98 80	73.22 59	86.57 45	92.41 10	75.63 71	66.77 50	62.08 88	52.32 90	30.27 194	50.74 133	66.14 85	86.22 12	85.41 7	91.90 1	96.75 12

diffmvs		74.32 62	75.42 66	73.04 60	75.60 113	87.27 55	78.20 57	62.96 79	68.66 70	61.89 55	59.79 69	59.84 90	71.80 49	78.30 81	79.87 66	87.80 45	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
DI_MVS_plusplus_trai		73.94 65	74.85 68	72.88 61	76.57 105	86.80 60	80.41 48	61.47 97	62.35 87	59.44 69	47.91 108	68.12 54	72.24 46	82.84 34	81.50 47	87.15 68	94.42 30

EC-MVSNet		76.05 53	78.87 43	72.77 62	78.87 83	86.63 63	77.50 63	57.04 136	75.34 52	61.68 58	64.20 53	69.56 52	73.96 33	82.12 44	80.65 61	87.57 51	93.57 43

ACMM	66.70 10	70.42 81	68.49 105	72.67 63	82.85 54	77.76 145	77.70 62	64.76 64	64.61 82	60.74 66	49.29 102	53.97 123	65.86 86	74.97 110	75.57 111	84.13 142	83.29 144
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		71.37 79	70.27 95	72.66 64	80.79 69	81.33 110	71.07 115	65.75 57	82.36 29	64.80 44	42.46 137	56.49 106	72.70 44	73.00 135	70.52 169	80.84 178	85.76 125

CS-MVS		75.84 54	78.61 44	72.61 65	79.03 80	86.74 61	74.43 89	60.27 111	74.15 57	62.78 51	66.26 49	64.25 68	72.81 42	83.36 28	81.69 45	86.32 81	93.85 39

MVS_111021_LR		74.26 63	75.95 63	72.27 66	79.43 76	85.04 80	72.71 95	65.27 62	70.92 61	63.58 48	69.32 39	60.31 88	69.43 68	77.01 91	77.15 92	83.22 152	91.93 60

ACMP	68.86 7	72.15 73	72.25 78	72.03 67	80.96 66	80.87 116	77.93 60	64.13 67	69.29 67	60.79 65	64.04 54	53.54 125	63.91 95	73.74 127	75.27 114	84.45 135	88.98 94
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		74.03 64	75.82 64	71.95 68	79.56 74	80.98 114	75.35 77	63.21 75	84.48 23	61.83 56	61.54 62	66.89 58	69.41 69	76.60 95	74.07 128	82.34 165	86.15 119

MS-PatchMatch		70.34 85	69.00 101	71.91 69	85.20 51	85.35 78	77.84 61	61.77 95	58.01 106	55.40 83	41.26 144	58.34 98	61.69 108	81.70 51	78.29 82	89.56 9	80.02 162

CS-MVS-test		75.09 60	77.84 49	71.87 70	79.27 78	86.92 59	70.53 120	60.36 109	75.13 53	63.13 49	67.92 42	65.08 64	71.43 53	78.15 82	78.51 80	86.53 78	93.16 48

ETV-MVS		76.25 51	80.22 38	71.63 71	78.23 87	87.95 51	72.75 94	60.27 111	77.50 48	57.73 73	71.53 36	66.60 59	73.16 38	80.99 57	81.23 52	87.63 50	95.73 14

baseline		72.89 68	74.46 70	71.07 72	75.99 109	87.50 54	74.57 81	60.49 108	70.72 62	57.60 74	60.63 66	60.97 83	70.79 57	75.27 108	76.33 101	86.94 70	89.79 86

Anonymous20231211		68.44 95	66.37 122	70.86 73	77.58 94	83.49 93	75.15 78	61.89 92	52.54 132	58.50 70	28.89 196	56.78 105	69.29 71	74.96 112	76.61 96	82.73 158	91.36 65

baseline1		71.47 76	72.02 79	70.82 74	80.56 71	84.51 84	76.61 68	66.93 49	56.22 114	48.66 106	55.40 79	60.43 86	62.55 104	83.35 29	80.99 55	89.60 8	83.28 145

PLC	64.00 12	68.54 94	66.66 119	70.74 75	80.28 73	74.88 166	72.64 96	63.70 72	69.26 68	55.71 80	47.24 116	55.31 115	70.42 59	72.05 146	70.67 167	81.66 172	77.19 170
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LGP-MVS_train		72.02 74	73.18 76	70.67 76	82.13 60	80.26 122	79.58 52	63.04 77	70.09 63	51.98 91	65.06 51	55.62 113	62.49 105	75.97 102	76.32 102	84.80 127	88.93 95

EIA-MVS		73.48 66	76.05 61	70.47 77	78.12 88	87.21 56	71.78 102	60.63 107	69.66 66	55.56 82	64.86 52	60.69 84	69.53 66	77.35 89	78.59 77	87.22 64	94.01 37

MSDG		65.57 117	61.57 154	70.24 78	82.02 61	76.47 154	74.46 88	68.73 40	56.52 111	50.33 101	38.47 159	41.10 158	62.42 106	72.12 144	72.94 145	83.47 148	73.37 184

CostFormer		72.18 72	73.90 72	70.18 79	79.47 75	86.19 74	76.94 67	48.62 182	66.07 77	60.40 67	54.14 87	65.82 61	67.98 76	75.84 103	76.41 100	87.67 48	92.83 52

PVSNet_Blended_VisFu		71.76 75	73.54 74	69.69 80	79.01 81	87.16 57	72.05 99	61.80 94	56.46 112	59.66 68	53.88 89	62.48 72	59.08 128	81.17 54	78.90 75	86.53 78	94.74 27

Effi-MVS+		70.42 81	71.23 87	69.47 81	78.04 89	85.24 79	75.57 73	58.88 114	59.56 97	48.47 107	52.73 92	54.94 116	69.69 64	78.34 80	77.06 93	86.18 85	90.73 76

FC-MVSNet-train		68.83 93	68.29 107	69.47 81	78.35 86	79.94 123	64.72 151	66.38 52	54.96 123	54.51 87	56.75 75	47.91 140	66.91 83	75.57 107	75.75 107	85.92 91	87.12 110

DCV-MVSNet		69.13 90	69.07 100	69.21 83	77.65 93	77.52 147	74.68 80	57.85 125	54.92 124	55.34 85	55.74 77	55.56 114	66.35 84	75.05 109	76.56 98	83.35 149	88.13 105

baseline2		71.22 80	73.01 77	69.13 84	75.76 111	86.34 70	71.23 110	62.78 85	62.62 85	52.85 89	57.32 74	54.31 120	63.27 100	79.74 68	79.31 72	88.89 17	91.43 62

TAPA-MVS	67.10 9	71.45 77	73.47 75	69.10 85	77.04 100	80.78 117	73.81 90	62.10 89	80.80 36	51.28 94	60.91 64	63.80 71	67.98 76	74.59 114	72.42 150	82.37 164	80.97 159
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
IB-MVS	64.48 11	69.02 91	68.97 102	69.09 86	81.75 62	89.01 37	64.50 152	64.91 63	56.65 110	62.59 53	47.89 109	45.23 146	51.99 156	69.18 171	81.88 40	88.77 19	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
TSAR-MVS + COLMAP		73.09 67	76.86 56	68.71 87	74.97 117	82.49 101	74.51 86	61.83 93	83.16 26	49.31 105	82.22 22	51.62 130	68.94 73	78.76 76	75.52 113	82.67 160	84.23 137

FMVSNet3		70.41 83	71.89 82	68.68 88	70.89 139	79.42 129	75.63 71	60.97 102	65.32 78	51.06 95	47.37 113	62.05 74	64.90 90	82.49 36	82.27 35	88.64 23	84.34 136

GeoE		68.96 92	69.32 98	68.54 89	76.61 104	83.12 95	71.78 102	56.87 138	60.21 95	54.86 86	45.95 126	54.79 119	64.27 93	74.59 114	75.54 112	86.84 73	91.01 69

HyFIR lowres test		68.39 96	68.28 108	68.52 90	80.85 67	88.11 47	71.08 114	58.09 120	54.87 126	47.80 111	27.55 200	55.80 111	64.97 89	79.11 72	79.14 74	88.31 33	93.35 44

FA-MVS(training)		70.24 86	71.77 83	68.45 91	77.52 96	86.03 75	73.33 92	49.12 181	63.55 84	55.77 79	48.91 105	56.26 107	67.78 78	77.60 84	79.62 69	87.19 67	90.40 78

CANet_DTU		72.84 69	76.63 59	68.43 92	76.81 102	86.62 65	75.54 74	54.71 162	72.06 59	43.54 128	67.11 44	58.46 96	72.40 45	81.13 56	80.82 60	87.57 51	90.21 81

thres100view900		67.14 110	66.09 125	68.38 93	77.70 91	83.84 92	74.52 85	66.33 54	49.16 143	43.40 130	43.24 129	41.34 154	62.59 103	79.31 71	75.92 106	85.73 98	89.81 84

dmvs_re		67.60 102	67.21 116	68.06 94	74.07 119	79.01 131	73.31 93	68.74 39	58.27 102	42.07 139	49.72 101	43.96 149	60.66 114	76.79 94	78.04 88	89.51 10	84.69 132

tpm cat1		67.47 106	67.05 117	67.98 95	76.63 103	81.51 108	74.49 87	47.65 187	61.18 90	61.12 61	42.51 136	53.02 128	64.74 92	70.11 165	71.50 156	83.22 152	89.49 88

GBi-Net		69.21 88	70.40 93	67.81 96	69.49 144	78.65 135	74.54 82	60.97 102	65.32 78	51.06 95	47.37 113	62.05 74	63.43 97	77.49 85	78.22 83	87.37 55	83.73 139

test1		69.21 88	70.40 93	67.81 96	69.49 144	78.65 135	74.54 82	60.97 102	65.32 78	51.06 95	47.37 113	62.05 74	63.43 97	77.49 85	78.22 83	87.37 55	83.73 139

Fast-Effi-MVS+		67.59 103	67.56 113	67.62 98	73.67 122	81.14 113	71.12 113	54.79 161	58.88 99	50.61 100	46.70 123	47.05 142	69.12 72	76.06 101	76.44 99	86.43 80	86.65 113

ET-MVSNet_ETH3D		71.38 78	74.70 69	67.51 99	51.61 209	88.06 49	77.29 65	60.95 105	63.61 83	48.36 108	66.60 47	60.67 85	79.55 10	73.56 128	80.58 62	87.30 60	89.80 85

test2506		69.26 87	70.79 91	67.48 100	78.64 84	86.40 68	72.22 97	62.75 86	58.05 104	45.24 118	50.76 96	54.93 117	58.05 134	79.82 66	79.70 67	87.96 41	85.90 123

FMVSNet2		68.06 99	68.57 104	67.45 101	69.49 144	78.65 135	74.54 82	60.23 113	56.29 113	49.64 104	42.13 140	57.08 104	63.43 97	81.15 55	80.99 55	87.37 55	83.73 139

LS3D		64.54 126	62.14 150	67.34 102	80.85 67	75.79 160	69.99 121	65.87 56	60.77 92	44.35 124	42.43 138	45.95 145	65.01 88	69.88 166	68.69 176	77.97 193	71.43 191

ECVR-MVS		67.93 101	68.49 105	67.28 103	78.64 84	86.40 68	72.22 97	62.75 86	58.05 104	44.06 126	40.92 148	48.20 138	58.05 134	79.82 66	79.70 67	87.96 41	86.32 118

tfpn200view9		65.90 115	64.96 129	67.00 104	77.70 91	81.58 106	71.71 105	62.94 82	49.16 143	43.40 130	43.24 129	41.34 154	61.42 110	76.24 98	74.63 120	84.84 123	88.52 101

thres200		65.58 116	64.74 131	66.56 105	77.52 96	81.61 104	73.44 91	62.95 80	46.23 155	42.45 137	42.76 131	41.18 156	58.12 132	76.24 98	75.59 110	84.89 121	89.58 87

thres400		65.18 121	64.44 133	66.04 106	76.40 106	82.63 98	71.52 107	64.27 66	44.93 161	40.69 146	41.86 141	40.79 160	58.12 132	77.67 83	74.64 119	85.26 111	88.56 100

tpmrst		67.15 109	68.12 110	66.03 107	76.21 107	80.98 114	71.27 109	45.05 193	60.69 93	50.63 99	46.95 121	54.15 122	65.30 87	71.80 148	71.77 154	87.72 46	90.48 77

IterMVS-LS		66.08 114	66.56 121	65.51 108	73.67 122	74.88 166	70.89 117	53.55 168	50.42 137	48.32 109	50.59 98	55.66 112	61.83 107	73.93 123	74.42 124	84.82 126	86.01 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test1111		66.72 111	67.80 111	65.45 109	77.42 98	86.63 63	69.69 124	62.98 78	55.29 120	39.47 149	40.12 153	47.11 141	55.70 146	79.96 64	80.00 65	87.47 54	85.49 128

thisisatest0530		68.38 97	70.98 89	65.35 110	72.61 127	84.42 85	68.21 133	57.98 121	59.77 96	50.80 98	54.63 82	58.48 95	57.92 136	76.99 92	77.47 90	84.60 131	85.07 129

Effi-MVS+-dtu		64.58 124	64.08 134	65.16 111	73.04 126	75.17 165	70.68 119	56.23 142	54.12 129	44.71 123	47.42 112	51.10 131	63.82 96	68.08 174	66.32 185	82.47 163	86.38 116

dps		64.08 128	63.22 138	65.08 112	75.27 115	79.65 126	66.68 145	46.63 191	56.94 108	55.67 81	43.96 128	43.63 151	64.00 94	69.50 170	69.82 171	82.25 166	79.02 166

tttt0517		67.99 100	70.61 92	64.94 113	71.94 132	83.96 91	67.62 137	57.98 121	59.30 98	49.90 103	54.50 85	57.98 102	57.92 136	76.48 96	77.47 90	84.24 138	84.58 133

PMMVS		70.37 84	75.06 67	64.90 114	71.46 133	81.88 102	64.10 154	55.64 148	71.31 60	46.69 112	70.69 38	58.56 93	69.53 66	79.03 73	75.63 109	81.96 169	88.32 103

EPMVS		66.21 112	67.49 114	64.73 115	75.81 110	84.20 90	68.94 129	44.37 197	61.55 89	48.07 110	49.21 104	54.87 118	62.88 101	71.82 147	71.40 160	88.28 34	79.37 165

v2v482		63.68 132	62.85 144	64.65 116	68.01 153	80.46 120	71.90 100	57.60 128	44.26 162	42.82 135	39.80 155	38.62 170	61.56 109	73.06 133	74.86 117	86.03 90	88.90 97

thres600view7		63.77 131	63.14 139	64.51 117	75.49 114	81.61 104	69.59 125	62.95 80	43.96 164	38.90 154	41.09 145	40.24 165	55.25 149	76.24 98	71.54 155	84.89 121	87.30 109

v8		63.44 134	62.58 146	64.43 118	68.28 152	78.07 140	71.82 101	54.85 159	46.70 153	45.20 119	39.40 156	40.91 159	60.54 116	72.85 137	74.39 125	85.92 91	85.76 125

ACMH+	60.36 13	61.16 152	58.38 172	64.42 119	77.37 99	74.35 171	68.45 131	62.81 84	45.86 157	38.48 156	35.71 177	37.35 174	59.81 121	67.24 176	69.80 173	79.58 186	78.32 168

ACMH	59.42 14	61.59 151	59.22 170	64.36 120	78.92 82	78.26 139	67.65 136	67.48 46	39.81 180	30.98 187	38.25 161	34.59 190	61.37 112	70.55 160	73.47 134	79.74 185	79.59 163
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test-LLR		68.23 98	71.61 85	64.28 121	71.37 134	81.32 111	63.98 157	61.03 100	58.62 100	42.96 133	52.74 90	61.65 78	57.74 139	75.64 105	78.09 86	88.61 24	93.21 45

PatchMatch-RL		62.22 146	60.69 160	64.01 122	68.74 149	75.75 161	59.27 178	60.35 110	56.09 115	53.80 88	47.06 119	36.45 179	64.80 91	68.22 173	67.22 180	77.10 195	74.02 179

FMVSNet1		63.48 133	63.07 140	63.97 123	65.31 172	76.37 156	71.77 104	57.90 124	43.32 166	45.66 115	35.06 182	49.43 135	58.57 130	77.49 85	78.22 83	84.59 132	81.60 158

pmmvs4		63.14 135	62.46 147	63.94 124	66.03 168	76.40 155	66.82 144	57.60 128	56.74 109	50.26 102	40.81 149	37.51 173	59.26 126	71.75 149	71.48 157	83.68 147	82.53 150

v10		63.00 137	62.22 149	63.90 125	67.88 155	77.78 144	71.59 106	54.34 163	45.37 159	42.76 136	38.53 158	38.93 168	61.05 113	74.39 118	74.52 123	85.75 95	86.04 120

v1144		63.00 137	62.39 148	63.70 126	67.72 156	80.27 121	71.23 110	56.40 139	42.51 167	40.81 145	38.12 163	37.73 171	60.42 118	74.46 116	74.55 122	85.64 106	89.12 93

tpm		64.85 122	66.02 126	63.48 127	74.52 118	78.38 138	70.98 116	44.99 195	51.61 134	43.28 132	47.66 111	53.18 126	60.57 115	70.58 159	71.30 163	86.54 77	89.45 90

EPP-MVSNet		67.58 104	71.10 88	63.48 127	75.71 112	83.35 94	66.85 143	57.83 126	53.02 131	41.15 143	55.82 76	67.89 56	56.01 145	74.40 117	72.92 146	83.33 150	90.30 80

GA-MVS		64.55 125	65.76 128	63.12 129	69.68 143	81.56 107	69.59 125	58.16 119	45.23 160	35.58 172	47.01 120	41.82 153	59.41 124	79.62 69	78.54 78	86.32 81	86.56 114

v1192		62.25 143	61.64 153	62.96 130	66.88 161	79.72 125	69.96 122	55.77 146	41.58 172	39.42 150	37.05 168	35.96 184	60.50 117	74.30 121	74.09 127	85.24 112	88.76 98

v148		62.00 148	61.19 157	62.96 130	67.46 159	79.49 128	67.87 134	57.66 127	42.30 168	45.02 121	38.20 162	38.89 169	54.77 150	69.83 167	72.60 149	84.96 117	87.01 111

MDTV_nov1_ep13		65.21 120	67.28 115	62.79 132	70.91 138	81.72 103	69.28 128	49.50 180	58.08 103	43.94 127	50.50 99	56.02 109	58.86 129	70.72 156	73.37 136	84.24 138	80.52 161

PatchmatchNet		65.43 119	67.71 112	62.78 133	73.49 124	82.83 97	66.42 148	45.40 192	60.40 94	45.27 117	49.22 103	57.60 103	60.01 120	70.61 157	71.38 161	86.08 89	81.91 156
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
UGNet		67.57 105	71.69 84	62.76 134	69.88 142	82.58 99	66.43 147	58.64 116	54.71 127	51.87 92	61.74 60	62.01 77	45.46 179	74.78 113	74.99 115	84.24 138	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
V42		62.86 139	62.97 141	62.74 135	60.84 190	78.99 133	71.46 108	57.13 135	46.85 151	44.28 125	38.87 157	40.73 162	57.63 141	72.60 141	74.14 126	85.09 116	88.63 99

v144192		62.05 147	61.46 155	62.73 136	66.59 165	79.87 124	69.30 127	55.88 144	41.50 174	39.41 151	37.23 166	36.45 179	59.62 122	72.69 140	73.51 133	85.61 107	88.93 95

TESTMET0.1,1		67.38 107	71.61 85	62.45 137	66.05 167	81.32 111	63.98 157	55.36 153	58.62 100	42.96 133	52.74 90	61.65 78	57.74 139	75.64 105	78.09 86	88.61 24	93.21 45

v1921920		61.66 150	61.10 158	62.31 138	66.32 166	79.57 127	68.41 132	55.49 151	41.03 175	38.69 155	36.64 174	35.27 187	59.60 123	73.23 131	73.41 135	85.37 109	88.51 102

CDS-MVSNet		64.22 127	65.89 127	62.28 139	70.05 141	80.59 118	69.91 123	57.98 121	43.53 165	46.58 113	48.22 107	50.76 132	46.45 174	75.68 104	76.08 104	82.70 159	86.34 117
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpnnormal		58.97 165	56.48 180	61.89 140	71.27 136	76.21 157	66.65 146	61.76 96	32.90 200	36.41 167	27.83 199	29.14 207	50.64 163	73.06 133	73.05 144	84.58 133	83.15 148

IS_MVSNet		67.29 108	71.98 80	61.82 141	76.92 101	84.32 89	65.90 150	58.22 118	55.75 118	39.22 152	54.51 84	62.47 73	45.99 177	78.83 75	78.52 79	84.70 129	89.47 89

v1240		61.09 153	60.55 162	61.72 142	65.92 170	79.28 130	67.16 142	54.91 158	39.79 181	38.10 158	36.08 176	34.64 189	59.15 127	72.86 136	73.36 137	85.10 114	87.84 106

EPNet_dtu		66.17 113	70.13 96	61.54 143	81.04 65	77.39 149	68.87 130	62.50 88	69.78 64	33.51 180	63.77 55	56.22 108	37.65 193	72.20 143	72.18 153	85.69 101	79.38 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Fast-Effi-MVS+-dtu		63.05 136	64.72 132	61.11 144	71.21 137	76.81 153	70.72 118	43.13 202	52.51 133	35.34 173	46.55 124	46.36 143	61.40 111	71.57 151	71.44 158	84.84 123	87.79 107

UniMVSNet_NR-MVSNet		62.30 142	63.51 137	60.89 145	69.48 147	77.83 143	64.07 155	63.94 69	50.03 138	31.17 185	44.82 127	41.12 157	51.37 159	71.02 153	74.81 118	85.30 110	84.95 130

SCA		63.90 130	66.67 118	60.66 146	73.75 120	71.78 181	59.87 177	43.66 198	61.13 91	45.03 120	51.64 94	59.45 91	57.92 136	70.96 154	70.80 165	83.71 146	80.92 160

Vis-MVSNet		65.53 118	69.83 97	60.52 147	70.80 140	84.59 83	66.37 149	55.47 152	48.40 146	40.62 147	57.67 72	58.43 97	45.37 180	77.49 85	76.24 103	84.47 134	85.99 122
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UA-Net		64.62 123	68.23 109	60.42 148	77.53 95	81.38 109	60.08 176	57.47 131	47.01 150	44.75 122	60.68 65	71.32 46	41.84 187	73.27 130	72.25 152	80.83 179	71.68 189

CMPMVS	43.63 17	57.67 174	55.43 182	60.28 149	72.01 130	79.00 132	62.77 167	53.23 170	41.77 171	45.42 116	30.74 193	39.03 167	53.01 154	64.81 185	64.65 191	75.26 200	68.03 198
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
NR-MVSNet		61.08 154	62.09 151	59.90 150	71.96 131	75.87 158	63.60 161	61.96 90	49.31 141	27.95 190	42.76 131	33.85 194	48.82 166	74.35 119	74.05 129	85.13 113	84.45 134

IterMVS		61.87 149	63.55 136	59.90 150	67.29 160	72.20 178	67.34 141	48.56 183	47.48 149	37.86 161	47.07 118	48.27 136	54.08 152	72.12 144	73.71 131	84.30 137	83.99 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DU-MVS		60.87 155	61.82 152	59.76 152	66.69 162	75.87 158	64.07 155	61.96 90	49.31 141	31.17 185	42.76 131	36.95 176	51.37 159	69.67 168	73.20 143	83.30 151	84.95 130

EG-PatchMatch MVS		58.73 168	58.03 175	59.55 153	72.32 128	80.49 119	63.44 163	55.55 150	32.49 201	38.31 157	28.87 197	37.22 175	42.84 185	74.30 121	75.70 108	84.84 123	77.14 171

CR-MVSNet		62.31 141	64.75 130	59.47 154	68.63 150	71.29 184	67.53 138	43.18 200	55.83 116	41.40 140	41.04 146	55.85 110	57.29 142	72.76 138	73.27 140	78.77 190	83.23 146

UniMVSNet_ETH3D		57.83 171	56.46 181	59.43 155	63.24 181	73.22 175	67.70 135	55.58 149	36.17 192	36.84 164	32.64 186	35.14 188	51.50 158	65.81 179	69.81 172	81.73 171	82.44 153

TranMVSNet+NR-MVSNet		60.38 158	61.30 156	59.30 156	68.34 151	75.57 164	63.38 164	63.78 71	46.74 152	27.73 191	42.56 135	36.84 177	47.66 169	70.36 162	74.59 121	84.91 120	82.46 151

USDC		59.69 161	60.03 166	59.28 157	64.04 177	71.84 179	63.15 166	55.36 153	54.90 125	35.02 174	48.34 106	29.79 206	58.16 131	70.60 158	71.33 162	79.99 183	73.42 183

pmmvs5		59.72 160	60.24 164	59.11 158	62.77 184	77.33 150	63.17 165	54.00 165	40.21 179	37.23 162	40.41 150	35.99 183	51.75 157	72.55 142	72.74 148	85.72 100	82.45 152

TransMVSNet (Re)		57.83 171	56.90 178	58.91 159	72.26 129	74.69 169	63.57 162	61.42 98	32.30 202	32.65 181	33.97 184	35.96 184	39.17 191	73.84 126	72.84 147	84.37 136	74.69 177

pm-mvs1		59.21 164	59.58 169	58.77 160	67.97 154	77.07 152	64.12 153	57.20 133	34.73 197	36.86 163	35.34 179	40.54 164	43.34 184	74.32 120	73.30 139	83.13 156	81.77 157

Baseline_NR-MVSNet		59.47 162	60.28 163	58.54 161	66.69 162	73.90 172	61.63 171	62.90 83	49.15 145	26.87 192	35.18 181	37.62 172	48.20 167	69.67 168	73.61 132	84.92 118	82.82 149

test-mter		64.06 129	69.24 99	58.01 162	59.07 196	77.40 148	59.13 179	48.11 185	55.64 119	39.18 153	51.56 95	58.54 94	55.38 148	73.52 129	76.00 105	87.22 64	92.05 59

UniMVSNet (Re)		60.62 156	62.93 143	57.92 163	67.64 157	77.90 142	61.75 170	61.24 99	49.83 140	29.80 189	42.57 134	40.62 163	43.36 183	70.49 161	73.27 140	83.76 144	85.81 124

gg-mvs-nofinetune		62.34 140	66.19 124	57.86 164	76.15 108	88.61 40	71.18 112	41.24 210	25.74 212	13.16 215	22.91 208	63.97 70	54.52 151	85.06 16	85.25 10	90.92 3	91.78 61

thisisatest0515		59.37 163	60.68 161	57.84 165	64.39 176	75.65 163	58.56 181	53.86 166	41.55 173	42.12 138	40.40 151	39.59 166	47.09 172	71.69 150	73.79 130	81.02 177	82.08 155

COLMAP_ROB	51.17 15	55.13 178	52.90 191	57.73 166	73.47 125	67.21 194	62.13 168	55.82 145	47.83 147	34.39 176	31.60 190	34.24 191	44.90 181	63.88 190	62.52 198	75.67 198	63.02 207
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v7n		57.04 176	56.64 179	57.52 167	62.85 183	74.75 168	61.76 169	51.80 176	35.58 196	36.02 170	32.33 188	33.61 195	50.16 164	67.73 175	70.34 170	82.51 161	82.12 154

ADS-MVSNet		58.40 170	59.16 171	57.52 167	65.80 171	74.57 170	60.26 174	40.17 211	50.51 136	38.01 159	40.11 154	44.72 147	59.36 125	64.91 183	66.55 183	81.53 173	72.72 187

FMVSNet5		58.86 166	60.24 164	57.25 169	52.66 208	66.25 196	63.77 160	52.86 173	57.85 107	37.92 160	36.12 175	52.22 129	51.37 159	70.88 155	71.43 159	84.92 118	66.91 200

CHOSEN 280x420		62.23 145	66.57 120	57.17 170	59.88 193	68.92 190	61.20 173	42.28 204	54.17 128	39.57 148	47.78 110	64.97 65	62.68 102	73.85 125	69.52 174	77.43 194	86.75 112

IterMVS-SCA-FT		60.21 159	62.97 141	57.00 171	66.64 164	71.84 179	67.53 138	46.93 190	47.56 148	36.77 166	46.85 122	48.21 137	52.51 155	70.36 162	72.40 151	71.63 208	83.53 142

pmmvs-eth3d		55.20 177	53.95 186	56.65 172	57.34 202	67.77 192	57.54 183	53.74 167	40.93 176	41.09 144	31.19 192	29.10 208	49.07 165	65.54 180	67.28 179	81.14 175	75.81 172

PatchT		60.46 157	63.85 135	56.51 173	65.95 169	75.68 162	47.34 199	41.39 207	53.89 130	41.40 140	37.84 164	50.30 134	57.29 142	72.76 138	73.27 140	85.67 102	83.23 146

TAMVS		58.86 166	60.91 159	56.47 174	62.38 186	77.57 146	58.97 180	52.98 171	38.76 184	36.17 168	42.26 139	47.94 139	46.45 174	70.23 164	70.79 166	81.86 170	78.82 167

TinyColmap		52.66 189	50.09 200	55.65 175	59.72 194	64.02 204	57.15 184	52.96 172	40.28 178	32.51 182	32.42 187	20.97 217	56.65 144	63.95 189	65.15 190	74.91 201	63.87 205

MIMVSNet		57.78 173	59.71 168	55.53 176	54.79 204	77.10 151	63.89 159	45.02 194	46.59 154	36.79 165	28.36 198	40.77 161	45.84 178	74.97 110	76.58 97	86.87 72	73.60 182

pmmvs6		54.20 185	53.54 187	54.97 177	63.22 182	72.98 176	60.17 175	52.32 175	26.77 211	34.30 177	23.29 207	36.23 181	40.33 190	68.77 172	68.76 175	79.47 188	78.00 169

MVS-HIRNet		53.86 187	53.02 189	54.85 178	60.30 192	72.36 177	44.63 207	42.20 205	39.45 182	43.47 129	21.66 211	34.00 193	55.47 147	65.42 181	67.16 181	83.02 157	71.08 193

Vis-MVSNet (Re-imp)		62.25 143	68.74 103	54.68 179	73.70 121	78.74 134	56.51 185	57.49 130	55.22 121	26.86 193	54.56 83	61.35 80	31.06 195	73.10 132	74.90 116	82.49 162	83.31 143

TDRefinement		52.70 188	51.02 197	54.66 180	57.41 201	65.06 200	61.47 172	54.94 156	44.03 163	33.93 178	30.13 195	27.57 209	46.17 176	61.86 192	62.48 199	74.01 204	66.06 201

pmnet_mix02		53.92 186	53.30 188	54.65 181	61.89 187	71.33 183	54.54 189	54.17 164	40.38 177	34.65 175	34.76 183	30.68 205	40.44 189	60.97 193	63.71 193	82.19 167	71.24 192

test0.0.03 1		57.35 175	59.89 167	54.38 182	71.37 134	73.45 174	52.71 191	61.03 100	46.11 156	26.33 194	41.73 142	44.08 148	29.72 197	71.43 152	70.90 164	85.10 114	71.56 190

MDTV_nov1_ep13_2view		54.47 184	54.61 183	54.30 183	60.50 191	73.82 173	57.92 182	43.38 199	39.43 183	32.51 182	33.23 185	34.05 192	47.26 171	62.36 191	66.21 186	84.24 138	73.19 185

RPMNet		58.63 169	62.80 145	53.76 184	67.59 158	71.29 184	54.60 188	38.13 212	55.83 116	35.70 171	41.58 143	53.04 127	47.89 168	66.10 178	67.38 178	78.65 192	84.40 135

anonymousdsp		54.99 180	57.24 177	52.36 185	53.82 206	71.75 182	51.49 192	48.14 184	33.74 198	33.66 179	38.34 160	36.13 182	47.54 170	64.53 187	70.60 168	79.53 187	85.59 127

RPSCF		55.07 179	58.06 174	51.57 186	48.87 213	58.95 209	53.68 190	41.26 209	62.42 86	45.88 114	54.38 86	54.26 121	53.75 153	57.15 200	53.53 210	66.01 210	65.75 202

Anonymous20231206		52.23 190	52.80 192	51.56 187	64.70 175	69.41 188	51.01 193	58.60 117	36.63 189	22.44 200	21.80 210	31.42 201	30.52 196	66.79 177	67.83 177	82.10 168	75.73 173

gm-plane-assit		54.99 180	57.99 176	51.49 188	69.27 148	54.42 213	32.32 216	42.59 203	21.18 216	13.71 213	23.61 205	43.84 150	60.21 119	87.09 5	86.55 5	90.81 4	89.28 91

CVMVSNet		54.92 182	58.16 173	51.13 189	62.61 185	68.44 191	55.45 187	52.38 174	42.28 169	21.45 201	47.10 117	46.10 144	37.96 192	64.42 188	63.81 192	76.92 196	75.01 176

PM-MVS		50.11 195	50.38 199	49.80 190	47.23 215	62.08 207	50.91 194	44.84 196	41.90 170	36.10 169	35.22 180	26.05 213	46.83 173	57.64 198	55.42 209	72.90 205	74.32 178

SixPastTwentyTwo		49.11 199	49.22 202	48.99 191	58.54 200	64.14 203	47.18 200	47.75 186	31.15 204	24.42 196	41.01 147	26.55 211	44.04 182	54.76 207	58.70 204	71.99 207	68.21 196

PEN-MVS		51.04 191	52.94 190	48.82 192	61.45 189	66.00 197	48.68 196	57.20 133	36.87 187	15.36 209	36.98 169	32.72 196	28.77 201	57.63 199	66.37 184	81.44 174	74.00 180

LTVRE_ROB	47.26 16	49.41 198	49.91 201	48.82 192	64.76 174	69.79 187	49.05 195	47.12 189	20.36 218	16.52 207	36.65 173	26.96 210	50.76 162	60.47 194	63.16 196	64.73 211	72.00 188
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
N_pmnet		47.67 201	47.00 205	48.45 194	54.72 205	62.78 205	46.95 201	51.25 177	36.01 194	26.09 195	26.59 202	25.93 214	35.50 194	55.67 206	59.01 202	76.22 197	63.04 206

CP-MVSNet		50.57 193	52.60 194	48.21 195	58.77 198	65.82 198	48.17 197	56.29 141	37.41 186	16.59 206	37.14 167	31.95 198	29.21 198	56.60 202	63.71 193	80.22 181	75.56 174

PS-CasMVS		50.17 194	52.02 195	48.02 196	58.60 199	65.54 199	48.04 198	56.19 143	36.42 191	16.42 208	35.68 178	31.33 202	28.85 200	56.42 204	63.54 195	80.01 182	75.18 175

DTE-MVSNet		49.82 196	51.92 196	47.37 197	61.75 188	64.38 202	45.89 205	57.33 132	36.11 193	12.79 216	36.87 170	31.93 199	25.73 204	58.01 197	65.22 189	80.75 180	70.93 194

WR-MVS		51.02 192	54.56 184	46.90 198	63.84 178	69.23 189	44.78 206	56.38 140	38.19 185	14.19 211	37.38 165	36.82 178	22.39 207	60.14 195	66.20 187	79.81 184	73.95 181

MDA-MVSNet-bldmvs		44.15 205	42.27 210	46.34 199	38.34 217	62.31 206	46.28 202	55.74 147	29.83 205	20.98 202	27.11 201	16.45 223	41.98 186	41.11 215	57.47 205	74.72 202	61.65 210

testgi		48.51 200	50.53 198	46.16 200	64.78 173	67.15 195	41.54 209	54.81 160	29.12 207	17.03 205	32.07 189	31.98 197	20.15 211	65.26 182	67.00 182	78.67 191	61.10 211

WR-MVS_H		49.62 197	52.63 193	46.11 201	58.80 197	67.58 193	46.14 204	54.94 156	36.51 190	13.63 214	36.75 172	35.67 186	22.10 208	56.43 203	62.76 197	81.06 176	72.73 186

test20.03		47.23 203	48.69 203	45.53 202	63.28 180	64.39 201	41.01 210	56.93 137	29.16 206	15.21 210	23.90 204	30.76 204	17.51 214	64.63 186	65.26 188	79.21 189	62.71 208

FPMVS		39.11 209	36.39 211	42.28 203	55.97 203	45.94 216	46.23 203	41.57 206	35.73 195	22.61 198	23.46 206	19.82 219	28.32 202	43.57 212	40.67 214	58.96 214	45.54 214

pmmvs3		41.86 207	42.29 209	41.36 204	39.80 216	52.66 214	38.93 213	35.85 216	23.40 215	20.22 203	19.30 212	20.84 218	40.56 188	55.98 205	58.79 203	72.80 206	65.03 203

new-patchmatchnet		42.21 206	42.97 207	41.33 205	53.05 207	59.89 208	39.38 211	49.61 179	28.26 209	12.10 217	22.17 209	21.54 216	19.22 212	50.96 209	56.04 207	74.61 203	61.92 209

EU-MVSNet		44.84 204	47.85 204	41.32 206	49.26 212	56.59 212	43.07 208	47.64 188	33.03 199	13.82 212	36.78 171	30.99 203	24.37 205	53.80 208	55.57 208	69.78 209	68.21 196

FC-MVSNet-test		47.24 202	54.37 185	38.93 207	59.49 195	58.25 211	34.48 215	53.36 169	45.66 158	6.66 221	50.62 97	42.02 152	16.62 215	58.39 196	61.21 200	62.99 212	64.40 204

MIMVSNet1		40.84 208	43.46 206	37.79 208	32.14 218	58.92 210	39.24 212	50.83 178	27.00 210	11.29 218	16.76 217	26.53 212	17.75 213	57.14 201	61.12 201	75.46 199	56.78 212

PMVS	27.44 18	32.08 211	29.07 215	35.60 209	48.33 214	24.79 220	26.97 218	41.34 208	20.45 217	22.50 199	17.11 216	18.64 220	20.44 210	41.99 214	38.06 215	54.02 216	42.44 215
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		33.19 210	35.52 212	30.47 210	27.55 222	45.31 217	29.29 217	30.92 217	29.00 208	9.88 220	18.77 213	17.64 221	26.77 203	44.07 211	45.98 212	58.41 215	47.87 213

WB-MVS		30.42 212	32.63 214	27.84 211	51.51 210	41.64 218	17.75 221	55.06 155	20.11 219	2.46 226	26.13 203	16.63 222	3.90 221	44.91 210	44.54 213	36.34 220	34.48 217

GG-mvs-BLEND		54.54 183	77.58 50	27.67 212	0.03 227	90.09 29	77.20 66	0.02 223	66.83 73	0.05 228	59.90 68	73.33 36	0.04 223	78.40 79	79.30 73	88.65 22	95.20 25

Gipuma		24.91 214	24.61 216	25.26 213	31.47 219	21.59 221	18.06 220	37.53 213	25.43 213	10.03 219	4.18 223	4.25 227	14.85 216	43.20 213	47.03 211	39.62 218	26.55 220
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		28.15 213	34.48 213	20.76 214	6.76 226	21.18 222	21.03 219	18.41 220	36.77 188	17.52 204	15.67 218	31.63 200	24.05 206	41.03 216	26.69 218	36.82 219	68.38 195

E-PMN		15.08 216	11.65 219	19.08 215	28.73 220	12.31 225	6.95 226	36.87 215	10.71 222	3.63 224	5.13 220	2.22 230	13.81 218	11.34 221	18.50 220	24.49 222	21.32 221

EMVS		14.40 217	10.71 220	18.70 216	28.15 221	12.09 226	7.06 225	36.89 214	11.00 221	3.56 225	4.95 221	2.27 229	13.91 217	10.13 222	16.06 221	22.63 223	18.51 222

PMMVS2		20.45 215	22.31 217	18.27 217	20.52 223	26.73 219	14.85 223	28.43 219	13.69 220	0.79 227	10.35 219	9.10 224	3.83 222	27.64 218	32.87 216	41.17 217	35.81 216

tmp_tt				16.09 218	13.07 224	8.12 227	13.61 224	2.08 222	55.09 122	30.10 188	40.26 152	22.83 215	5.35 220	29.91 217	25.25 219	32.33 221

MVE	15.98 19	14.37 218	16.36 218	12.04 219	7.72 225	20.24 223	5.90 227	29.05 218	8.28 223	3.92 223	4.72 222	2.42 228	9.57 219	18.89 220	31.46 217	16.07 225	28.53 219
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		0.05 219	0.08 221	0.01 220	0.00 228	0.01 228	0.03 229	0.01 224	0.05 224	0.00 229	0.14 225	0.01 231	0.03 225	0.05 223	0.05 222	0.01 226	0.24 224

test123		0.05 219	0.08 221	0.01 220	0.00 228	0.01 228	0.01 230	0.00 225	0.05 224	0.00 229	0.16 224	0.00 232	0.04 223	0.02 224	0.05 222	0.00 227	0.26 223

uanet_test		0.00 221	0.00 223	0.00 222	0.00 228	0.00 230	0.00 231	0.00 225	0.00 226	0.00 229	0.00 226	0.00 232	0.00 226	0.00 225	0.00 224	0.00 227	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 222	0.00 228	0.00 230	0.00 231	0.00 225	0.00 226	0.00 229	0.00 226	0.00 232	0.00 226	0.00 225	0.00 224	0.00 227	0.00 225

sosnet		0.00 221	0.00 223	0.00 222	0.00 228	0.00 230	0.00 231	0.00 225	0.00 226	0.00 229	0.00 226	0.00 232	0.00 226	0.00 225	0.00 224	0.00 227	0.00 225

TPM-MVS					94.34 2	93.91 5	89.34 3			75.49 18	82.52 20	83.34 10	83.53 4			89.62 7	90.78 72
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										31.47 184

9.14												84.47 7

SR-MVS					86.33 46			67.54 45				80.78 21

Anonymous202405211			66.35 123		78.00 90	84.41 86	74.85 79	63.18 76	51.00 135		31.37 191	53.73 124	69.67 65	76.28 97	76.84 94	83.21 154	90.85 70

our_test_3					63.32 179	71.07 186	55.90 186

ambc			42.30 208		50.36 211	49.51 215	35.47 214		32.04 203	23.53 197	17.36 214	8.95 225	29.06 199	64.88 184	56.26 206	61.29 213	67.12 199

MTAPA										78.32 11		79.42 25

MTMP										76.04 15		76.65 29

Patchmatch-RL test							2.17 228

XVS					82.43 55	86.27 71	75.70 69			61.07 62		72.27 39				85.67 102

X-MVStestdata					82.43 55	86.27 71	75.70 69			61.07 62		72.27 39				85.67 102

mPP-MVS					86.96 41							70.61 49

NP-MVS									81.60 34

Patchmtry						78.06 141	67.53 138	43.18 200		41.40 140

DeepMVS_CX						19.81 224	17.01 222	10.02 221	23.61 214	5.85 222	17.21 215	8.03 226	21.13 209	22.60 219		21.42 224	30.01 218

High-resolution multi-view benchmark