Explanipedia

CALLIC: Content Adaptive Learning for Lossless Image Compression Open

Daxin Li, Yuanchao Bai, Kai Wang, Junjun Jiang, Xianming Liu , et al. · 2025

Learned lossless image compression has achieved significant advancements in recent years. However, existing methods often rely on training amortized generative models on massive datasets, resulting in sub-optimal probability distribution e…

Accelerating Multi-Task Temporal Difference Learning under Low-Rank Representation Open

Yuanchao Bai, Sihan Zeng, Justin Romberg, Thinh T. Doan · 2025

We study policy evaluation problems in multi-task reinforcement learning (RL) under a low-rank representation setting. In this setting, we are given $N$ learning tasks where the corresponding value function of these tasks lie in an $r$-dim…

Double-channel cyclic image deblurring algorithm based on edge features Open

Jiamin Li, Hongping HU, Yuanchao Bai · 2025

CALLIC: Content Adaptive Learning for Lossless Image Compression Open

Daxin Li, Yuanchao Bai, Kai Wang, Junjun Jiang, Xianming Liu , et al. · 2024

Learned lossless image compression has achieved significant advancements in recent years. However, existing methods often rely on training amortized generative models on massive datasets, resulting in sub-optimal probability distribution e…

Learning Lossless Compression for High Bit-Depth Volumetric Medical Image Open

Kai Wang, Yuanchao Bai, Daxin Li, Deming Zhai, Junjun Jiang , et al. · 2024

Recent advances in learning-based methods have markedly enhanced the capabilities of image compression. However, these methods struggle with high bit-depth volumetric medical images, facing issues such as degraded performance, increased me…

PVContext: Hybrid Context Model for Point Cloud Compression Open

Guoqing Zhang, Wenbo Zhao, Jian Liu, Yuanchao Bai, Junjun Jiang , et al. · 2024

Efficient storage of large-scale point cloud data has become increasingly challenging due to advancements in scanning technology. Recent deep learning techniques have revolutionized this field; However, most existing approaches rely on sin…

Illumination-Aware Low-Light Image Enhancement with Transformer and Auto-Knee Curve Open

Jinwang Pan, Xianming Liu, Yuanchao Bai, Deming Zhai, Junjun Jiang , et al. · 2024

Images captured under low-light conditions suffer from several combined degradation factors, including low brightness, low contrast, noise, and color bias. Many learning-based techniques attempt to learn the low-to-clear mapping between lo…

GroupedMixer: An Entropy Model With Group-Wise Token-Mixers for Learned Image Compression Open

Daxin Li, Yuanchao Bai, Kai Wang, Junjun Jiang, Xianming Liu , et al. · 2024

Transformer-based entropy models have gained prominence in recent years due\nto their superior ability to capture long-range dependencies in probability\ndistribution estimation compared to convolution-based methods. However,\nprevious tra…

Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression Open

Daxin Li, Yuanchao Bai, Kai Wang, Junjun Jiang, Xianming Liu · 2024

Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements. However, at low bit-rates, these methods can introduce visually displeasing artifacts, such as blurring, color shifting, and text…

Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts Open

Hang Guo, Tao Dai, Yuanchao Bai, Bin Chen, Shu‐Tao Xia , et al. · 2023

Designing single-task image restoration models for specific degradation has seen great success in recent years. To achieve generalized image restoration, all-in-one methods have recently been proposed and shown potential for multiple resto…

Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution Open

Gang Wu, Junjun Jiang, Yuanchao Bai, Xianming Liu · 2023

In recent years, the use of large convolutional kernels has become popular in designing convolutional neural networks due to their ability to capture long-range dependencies and provide large receptive fields. However, the increase in kern…

Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation Open

Jialei Xu, Xianming Liu, Yuanchao Bai, Junjun Jiang, Kaixuan Wang , et al. · 2022

Depth map estimation from images is an important task in robotic systems.\nExisting methods can be categorized into two groups including multi-view stereo\nand monocular depth estimation. The former requires cameras to have large\noverlapp…

Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression Open

Yuanchao Bai, Xianming Liu, Kai Wang, Xiangyang Ji, Xiaolin Wu , et al. · 2022

Lossless and near-lossless image compression is of paramount importance to professional users in many technical fields, such as medicine, remote sensing, precision engineering and scientific research. But despite rapidly growing research i…

Learning Spatial-Frequency Transformer for Visual Object Tracking Open

Chuanming Tang, Xiao Wang, Yuanchao Bai, Zhe Wu, Jianlin Zhang , et al. · 2022

Recent trackers adopt the Transformer to combine or replace the widely used ResNet as their new backbone network. Although their trackers work well in regular scenarios, however, they simply flatten the 2D features into a sequence to bette…

Towards End-to-End Image Compression and Analysis with Transformers Open

Yuanchao Bai, Yang Xu, Xianming Liu, Junjun Jiang, Yaowei Wang , et al. · 2022

We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an i…

Towards End-to-End Image Compression and Analysis with Transformers Open

Yuanchao Bai, Yang Xu, Xianming Liu, Junjun Jiang, Yaowei Wang , et al. · 2021

We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an i…

Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data Open

Jialei Xu, Yuanchao Bai, Xianming Liu, Junjun Jiang, Xiangyang Ji · 2021

Depth estimation from a single image is an active research topic in computer vision. The most accurate approaches are based on fully supervised learning models, which rely on a large amount of dense and high-resolution (HR) ground-truth de…

Learning Scalable $\ell_\infty$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression Open

Yuanchao Bai, Xianming Liu, Wangmeng Zuo, Yaowei Wang, Xiangyang Ji · 2021

We propose a novel joint lossy image and residual compression framework for learning $\ell_\infty$-constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through lossy image compression…

FFA-Net: Feature Fusion Attention Network for Single Image Dehazing Open

Qin Xu, Zhilin Wang, Yuanchao Bai, Xiaodong Xie, Huizhu Jia · 2020

In this paper, we propose an end-to-end feature fusion at-tention network (FFA-Net) to directly restore the haze-free image. The FFA-Net architecture consists of three key components:1) A novel Feature Attention (FA) module combines Channe…

Fast Graph Sampling Set Selection Using Gershgorin Disc Alignment Open

Yuanchao Bai, Fen Wang, Gene Cheung, Yuji Nakatsukasa, Wen Gao · 2020

Graph sampling set selection, where a subset of nodes are chosen to collect samples to reconstruct a bandlimited or smooth graph signal, is a fundamental problem in graph signal processing (GSP). Previous works employ an unbiased least squ…

FFA-Net: Feature Fusion Attention Network for Single Image Dehazing Open

Qin Xu, Zhilin Wang, Yuanchao Bai, Xiaodong Xie, Huizhu Jia · 2019

In this paper, we propose an end-to-end feature fusion at-tention network (FFA-Net) to directly restore the haze-free image. The FFA-Net architecture consists of three key components: 1) A novel Feature Attention (FA) module combines Chann…

Single Image Blind Deblurring Using Multi-Scale Latent Structure Prior Open

Yuanchao Bai, Huizhu Jia, Ming Jiang, Xianming Liu, Xiaodong Xie , et al. · 2019

Blind image deblurring is a challenging problem in computer vision, which\naims to restore both the blur kernel and the latent sharp image from only a\nblurry observation. Inspired by the prevalent self-example prior in image\nsuper-resolu…

Reconstruction-Cognizant Graph Sampling using Gershgorin Disc Alignment Open

Yuanchao Bai, Gene Cheung, Fen Wang, Xianming Liu, Wen Gao · 2018

Graph sampling with noise is a fundamental problem in graph signal processing (GSP). Previous works assume an unbiased least square (LS) signal reconstruction scheme and select samples greedily via expensive extreme eigenvector computation…

Blind Image Deblurring via Reweighted Graph Total Variation Open

Yuanchao Bai, Gene Cheung, Xianming Liu, Wen Gao · 2017

Blind image deblurring, i.e., deblurring without knowledge of the blur kernel, is a highly ill-posed problem. The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimated blur kernel, de-…

Yuanchao Bai YOU? Author Swipe