165 citations · 492 across the 21 of their papers we have counts for
21 papers
Practical Lossless Volumetric Medical Image Compression via Tri-plane Context Tree Learning
Yuanchao Bai, Yifan Zhao, Kai Wang +5
Lossless compression of volumetric medical images is of paramount importance for clinical and research applications where data fidelity is essential. Traditional compression method…
Focus-Scan-Refine: From Human Visual Perception to Efficient Visual Token Pruning
Enwei Tong, Yuanchao Bai, Yao Zhu +2
Vision-language models (VLMs) often generate massive visual tokens that greatly increase inference latency and memory footprint; while training-free token pruning offers a practica…
Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation
Daxin Li, Yuanchao Bai, Kai Wang +3
Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost.…
CALLIC: Content Adaptive Learning for Lossless Image Compression
Daxin Li, Yuanchao Bai, Kai Wang +3
Learned lossless image compression has achieved significant advancements in recent years. However, existing methods often rely on training amortized generative models on massive da…
Learning Lossless Compression for High Bit-Depth Volumetric Medical Image
Kai Wang, Yuanchao Bai, Daxin Li +3
Recent advances in learning-based methods have markedly enhanced the capabilities of image compression. However, these methods struggle with high bit-depth volumetric medical image…
PVContext: Hybrid Context Model for Point Cloud Compression
Guoqing Zhang, Wenbo Zhao, Jian Liu +3
Efficient storage of large-scale point cloud data has become increasingly challenging due to advancements in scanning technology. Recent deep learning techniques have revolutionize…
GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression
Daxin Li, Yuanchao Bai, Kai Wang +3
Transformer-based entropy models have gained prominence in recent years due to their superior ability to capture long-range dependencies in probability distribution estimation comp…
Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression
Daxin Li, Yuanchao Bai, Kai Wang +2
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 disple…
Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution
Gang Wu, Junjun Jiang, Yuanchao Bai +1
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 pr…
Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation
Jialei Xu, Xianming Liu, Yuanchao Bai +4
Depth map estimation from images is an important task in robotic systems. Existing methods can be categorized into two groups including multi-view stereo and monocular depth estima…
Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression
Yuanchao Bai, Xianming Liu, Kai Wang +3
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…
Learning Spatial-Frequency Transformer for Visual Object Tracking
Chuanming Tang, Xiao Wang, Yuanchao Bai +3
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, t…
Towards End-to-End Image Compression and Analysis with Transformers
Yuanchao Bai, Xu Yang, Xianming Liu +4
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 Trans…
Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data
Jialei Xu, Yuanchao Bai, Xianming Liu +2
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 lar…
Learning Scalable -constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression
Yuanchao Bai, Xianming Liu, Wangmeng Zuo +2
We propose a novel joint lossy image and residual compression framework for learning -constrained near-lossless image compression. Specifically, we obtain a lossy reco…
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
Xu Qin, Zhilin Wang, Yuanchao Bai +2
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 componen…
Fast Graph Sampling Set Selection Using Gershgorin Disc Alignment
Yuanchao Bai, Fen Wang, Gene Cheung +2
Graph sampling set selection, where a subset of nodes are chosen to collect samples to reconstruct a smooth graph signal, is a fundamental problem in graph signal processing (GSP).…
Single Image Blind Deblurring Using Multi-Scale Latent Structure Prior
Yuanchao Bai, Huizhu Jia, Ming Jiang +3
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. Inspired b…
Reconstruction-Cognizant Graph Sampling using Gershgorin Disc Alignment
Yuanchao Bai, Gene Cheung, Fen Wang +2
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 sam…
Graph-Based Blind Image Deblurring From a Single Photograph
Yuanchao Bai, Gene Cheung, Xianming Liu +1
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…
Blind Image Deblurring via Reweighted Graph Total Variation
Yuanchao Bai, Gene Cheung, Xianming Liu +1
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…