no code implementations • 25 Jan 2024 • Daxin Li, Yuanchao Bai, Kai Wang, Junjun Jiang, Xianming Liu
Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements.
1 code implementation • 12 Dec 2023 • Hang Guo, Tao Dai, Yuanchao Bai, Bin Chen, Shu-Tao Xia, Zexuan Zhu
Recently, Parameter Efficient Transfer Learning (PETL) offers an efficient alternative solution to full fine-tuning, yet still faces great challenges for pre-trained image restoration models, due to the diversity of different degradations.
1 code implementation • 25 Mar 2023 • Gang Wu, Junjun Jiang, Yuanchao Bai, Xianming Liu
Building upon the NA module, we propose a lightweight single image super-resolution (SISR) network named TCSR.
no code implementations • 5 Oct 2022 • Jialei Xu, Xianming Liu, Yuanchao Bai, Junjun Jiang, Kaixuan Wang, Xiaozhi Chen, Xiangyang Ji
During the iterative update, the results of depth estimation are compared across cameras and the information of overlapping areas is propagated to the whole depth maps with the help of basis formulation.
1 code implementation • 11 Sep 2022 • Yuanchao Bai, Xianming Liu, Kai Wang, Xiangyang Ji, Xiaolin Wu, Wen Gao
In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals.
1 code implementation • 18 Aug 2022 • Chuanming Tang, Xiao Wang, Yuanchao Bai, Zhe Wu, Jianlin Zhang, YongMei Huang
To handle these issues, in this paper, we propose a unified Spatial-Frequency Transformer that models the Gaussian spatial Prior and High-frequency emphasis Attention (GPHA) simultaneously.
1 code implementation • 17 Dec 2021 • Yuanchao Bai, Xu Yang, Xianming Liu, Junjun Jiang, YaoWei Wang, Xiangyang Ji, Wen Gao
Meanwhile, we propose a feature aggregation module to fuse the compressed features with the selected intermediate features of the Transformer, and feed the aggregated features to a deconvolutional neural network for image reconstruction.
no code implementations • 23 Sep 2021 • Jialei Xu, Yuanchao Bai, Xianming Liu, Junjun Jiang, Xiangyang Ji
In this paper, we propose a novel weakly-supervised framework to train a monocular depth estimation network to generate HR depth maps with resolution-mismatched supervision, i. e., the inputs are HR color images and the ground-truth are low-resolution (LR) depth maps.
no code implementations • CVPR 2021 • Yuanchao Bai, Xianming Liu, WangMeng Zuo, YaoWei Wang, Xiangyang Ji
To achieve scalable compression with the error bound larger than zero, we derive the probability model of the quantized residual by quantizing the learned probability model of the original residual, instead of training multiple networks.
no code implementations • 31 Mar 2021 • Yuanchao Bai, Xianming Liu, WangMeng Zuo, YaoWei Wang, Xiangyang Ji
To achieve scalable compression with the error bound larger than zero, we derive the probability model of the quantized residual by quantizing the learned probability model of the original residual, instead of training multiple networks.
3 code implementations • 18 Nov 2019 • Xu Qin, Zhilin Wang, Yuanchao Bai, Xiaodong Xie, Huizhu Jia
The FFA-Net architecture consists of three key components: 1) A novel Feature Attention (FA) module combines Channel Attention with Pixel Attention mechanism, considering that different channel-wise features contain totally different weighted information and haze distribution is uneven on the different image pixels.
Ranked #1 on Image Dehazing on KITTI
no code implementations • 11 Jun 2019 • Yuanchao Bai, Huizhu Jia, Ming Jiang, Xian-Ming Liu, Xiaodong Xie, Wen Gao
Blind image deblurring is a challenging problem in computer vision, which aims to restore both the blur kernel and the latent sharp image from only a blurry observation.
no code implementations • 22 Feb 2018 • Yuanchao Bai, Gene Cheung, Xian-Ming Liu, Wen Gao
We leverage the new graph spectral interpretation for RGTV to design an efficient algorithm that solves for the skeleton image and the blur kernel alternately.
no code implementations • 24 Dec 2017 • Yuanchao Bai, Gene Cheung, Xian-Ming Liu, Wen Gao
The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimated blur kernel, de-convolve blurry input to restore the target image.