Search Results for author: ErKang Chen

Found 15 papers, 7 papers with code

Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks

1 code implementation ICCV 2023 Sixiang Chen, Tian Ye, Jinbin Bai, ErKang Chen, Jun Shi, Lei Zhu

In the real world, image degradations caused by rain often exhibit a combination of rain streaks and raindrops, thereby increasing the challenges of recovering the underlying clean image.

Rain Removal

NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer

1 code implementation16 May 2023 Yun Liu, Zhongsheng Yan, Sixiang Chen, Tian Ye, Wenqi Ren, ErKang Chen

Extensive experiments on several synthetic and real-world datasets demonstrate the superiority of our NightHazeFormer over state-of-the-art nighttime haze removal methods in terms of both visually and quantitatively.

Image Dehazing

Five A$^{+}$ Network: You Only Need 9K Parameters for Underwater Image Enhancement

1 code implementation15 May 2023 Jingxia Jiang, Tian Ye, Jinbin Bai, Sixiang Chen, Wenhao Chai, Shi Jun, Yun Liu, ErKang Chen

In this work, we propose the Five A$^{+}$ Network (FA$^{+}$Net), a highly efficient and lightweight real-time underwater image enhancement network with only $\sim$ 9k parameters and $\sim$ 0. 01s processing time.

Computational Efficiency Image Enhancement

RSFDM-Net: Real-time Spatial and Frequency Domains Modulation Network for Underwater Image Enhancement

no code implementations23 Feb 2023 Jingxia Jiang, Jinbin Bai, Yun Liu, Junjie Yin, Sixiang Chen, Tian Ye, ErKang Chen

Underwater images typically experience mixed degradations of brightness and structure caused by the absorption and scattering of light by suspended particles.

Image Enhancement

Adverse Weather Removal with Codebook Priors

no code implementations ICCV 2023 Tian Ye, Sixiang Chen, Jinbin Bai, Jun Shi, Chenghao Xue, Jingxia Jiang, Junjie Yin, ErKang Chen, Yun Liu

Inspired by recent advancements in codebook and vector quantization (VQ) techniques, we present a novel Adverse Weather Removal network with Codebook Priors (AWRCP) to address the problem of unified adverse weather removal.

Quantization

Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration

no code implementations3 Oct 2022 Sixiang Chen, Tian Ye, Yun Liu, ErKang Chen

Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs.

Image Dehazing Image Restoration +2

SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowing

1 code implementation20 Aug 2022 Sixiang Chen, Tian Ye, Yun Liu, ErKang Chen

Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task.

Single Image Desnowing

Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture

no code implementations12 Jul 2022 Tian Ye, Sixiang Chen, Yun Liu, Yi Ye, ErKang Chen

In winter scenes, the degradation of images taken under snow can be pretty complex, where the spatial distribution of snowy degradation is varied from image to image.

Snow Removal

Towards Efficient Single Image Dehazing and Desnowing

no code implementations19 Apr 2022 Tian Ye, Sixiang Chen, Yun Liu, ErKang Chen, Yuche Li

A single expert network efficiently addresses specific degradation in nasty winter scenes relying on the compact architecture and three novel components.

Image Dehazing Image Restoration +1

Underwater Light Field Retention : Neural Rendering for Underwater Imaging

1 code implementation21 Mar 2022 Tian Ye, Sixiang Chen, Yun Liu, Yi Ye, ErKang Chen, Yuche Li

To this end, we propose a neural rendering method for underwater imaging, dubbed UWNR (Underwater Neural Rendering).

Image Enhancement Image Generation +1

Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle

no code implementations17 Mar 2022 Tian Ye, Yun Liu, Yunchen Zhang, Sixiang Chen, ErKang Chen

Specifically, we first devise two siamese networks: a teacher network in the synthetic domain and a student network in the real domain, and then optimize them in a mutual learning manner by leveraging EMA and joint loss.

Domain Adaptation Image Dehazing

Perceiving and Modeling Density is All You Need for Image Dehazing

1 code implementation18 Nov 2021 Tian Ye, Mingchao Jiang, Yunchen Zhang, Liang Chen, ErKang Chen, Pen Chen, Zhiyong Lu

However, due to the paradox caused by the variation of real captured haze and the fixed degradation parameters of the current networks, the generalization ability of recent dehazing methods on real-world hazy images is not ideal. To address the problem of modeling real-world haze degradation, we propose to solve this problem by perceiving and modeling density for uneven haze distribution.

Image Dehazing Single Image Dehazing

Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing

1 code implementation12 Sep 2021 Tian Ye, ErKang Chen, XinRui Huang, Peng Chen

This paper proposes an end-to-end Efficient Re-parameterizationResidual Attention Network(ERRA-Net) to directly restore the nonhomogeneous hazy image.

Image Dehazing Nonhomogeneous Image Dehazing

Cannot find the paper you are looking for? You can Submit a new open access paper.