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.
1 code implementation • 16 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.
1 code implementation • 15 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.
no code implementations • 13 Mar 2023 • Sixiang Chen, Tian Ye, Jun Shi, Yun Liu, Jingxia Jiang, ErKang Chen, Peng Chen
Varicolored haze caused by chromatic casts poses haze removal and depth estimation challenges.
no code implementations • 23 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.
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.
no code implementations • 3 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.
1 code implementation • 20 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.
no code implementations • 12 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.
no code implementations • 12 Jul 2022 • Sixiang Chen, Tian Ye, Yun Liu, Taodong Liao, Jingxia Jiang, ErKang Chen, Peng Chen
Snow removal causes challenges due to its characteristic of complex degradations.
no code implementations • 19 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.
1 code implementation • 21 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).
no code implementations • 17 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.
1 code implementation • 18 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.
Ranked #5 on Image Dehazing on Haze4k
1 code implementation • 12 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.