P
Pengcheng Huang
Researcher at Wenzhou University
Publications - 10
Citations - 163
Pengcheng Huang is an academic researcher from Wenzhou University. The author has contributed to research in topics: Feature extraction & Image restoration. The author has an hindex of 4, co-authored 8 publications receiving 80 citations.
Papers
More filters
Journal ArticleDOI
Multi-Level Fusion and Attention-Guided CNN for Image Dehazing
TL;DR: This paper develops a multi-level fusion module to utilize both low-level and high-level features and has an end-to-end network without explicitly estimating the atmospheric light intensity and the transmission map in the classical atmosphere scattering model.
Journal ArticleDOI
Haze concentration adaptive network for image dehazing
TL;DR: An end-to-end Haze Concentration Adaptive Network, including a pyramid feature extractor (PFE), a feature enhancement module (FEM), and a multi-scale feature attention module (MSFAM) for image dehazing is proposed.
Journal ArticleDOI
Self-filtering image dehazing with self-supporting module
TL;DR: Experimental results demonstrate that the proposed self-supporting dehazing network (SSDN) outperforms state-of-the-art dehazed methods in terms of both quantitative accuracy and qualitative visual effect.
Journal ArticleDOI
Attention-based interpolation network for video deblurring
TL;DR: An attention-based interframe compensation scheme that replaces frames in blurry sequences with newly restored frames, and estimates temporal patterns among the replaced sequence to restore the whole sequence and propose an adaptive residual block that dynamically fuses multi-level features via learning location-specific weights.
Journal ArticleDOI
Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals
TL;DR: This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based on deep learning, and introduces basic knowledge of deep visual tracking, including fundamental concepts, existing algorithms, and previous reviews.