55 citations · 96 across the 19 of their papers we have counts for
21 papers
T3HG-Editor: Text-driven 3D Human Garment Editing with Body Priors Embedded in SMPL-X
Shaoru Sun, Xingtao Wang, Zihan Ma +4
While 3D Gaussian Editing (3DGE) has seen substantial progress, text-driven 3D human garment editing remains largely underexplored. Existing 3DGE works typically follow a paradigm…
DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration
Yanjie Tu, Qingsen Yan, Axi Niu +3
All-in-One image restoration aims to develop a unified restoration framework for handling diverse degradation types. Existing end-to-end methods usually regard the restoration proc…
SwiftVR: Real-Time One-Step Generative Video Restoration
Jiaqi Yan, Xiangyu Chen, Xinlin Zhong +5
Real-time video restoration (VR) for live streams requires high-resolution outputs under strict per-frame latency constraints. Existing one-step diffusion-based VR models remain di…
PaAgent: Portrait-Aware Image Restoration Agent via Subjective-Objective Reinforcement Learning
Yijian Wang, Qingsen Yan, Jiantao Zhou +2
Image Restoration (IR) agents, leveraging multimodal large language models to perceive degradation and invoke restoration tools, have shown promise in automating IR tasks. However,…
Exploring Scalable Unified Modeling for General Low-Level Vision
Xiangyu Chen, Kaiwen Zhu, Yuandong Pu +7
Low-level vision involves a wide spectrum of tasks, including image restoration, enhancement, stylization, and feature extraction, which differ significantly in both task formulati…
SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution
Liangbin Xie, Yu Li, Shian Du +7
Latent diffusion models have emerged as a leading paradigm for efficient video generation. However, as user expectations shift toward higher-resolution outputs, relying solely on l…
TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting
Liangbin Xie, Daniil Pakhomov, Zhonghao Wang +8
This paper introduces TurboFill, a fast image inpainting model that enhances a few-step text-to-image diffusion model with an inpainting adapter for high-quality and efficient inpa…
Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based Models
Zheng Li, Liangbin Xie, Jiantao Zhou +3
Although diffusion-based techniques have shown remarkable success in image generation and editing tasks, their abuse can lead to severe negative social impacts. Recently, some work…
Learning A Low-Level Vision Generalist via Visual Task Prompt
Xiangyu Chen, Yihao Liu, Yuandong Pu +4
Building a unified model for general low-level vision tasks holds significant research and practical value. Current methods encounter several critical issues. Multi-task restoratio…
Alignment-free Raw Video Demoireing
Shuning Xu, Xina Liu, Binbin Song +3
Video demoireing aims to remove undesirable interference patterns that arise during the capture of screen content, restoring artifact-free frames while maintaining temporal consist…
SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
Yuzhou Huang, Liangbin Xie, Xintao Wang +8
Current instruction-based editing methods, such as InstructPix2Pix, often fail to produce satisfactory results in complex scenarios due to their dependence on the simple CLIP text…
Image Demoireing in RAW and sRGB Domains
Shuning Xu, Binbin Song, Xiangyu Chen +2
Moire patterns frequently appear when capturing screens with smartphones or cameras, potentially compromising image quality. Previous studies suggest that moire pattern elimination…
A Comparative Study of Image Restoration Networks for General Backbone Network Design
Xiangyu Chen, Zheyuan Li, Yuandong Pu +4
Despite the significant progress made by deep models in various image restoration tasks, existing image restoration networks still face challenges in terms of task generality. An i…
Unifying Image Processing as Visual Prompting Question Answering
Yihao Liu, Xiangyu Chen, Xianzheng Ma +4
Image processing is a fundamental task in computer vision, which aims at enhancing image quality and extracting essential features for subsequent vision applications. Traditionally…
CNN Injected Transformer for Image Exposure Correction
Shuning Xu, Xiangyu Chen, Binbin Song +1
Capturing images with incorrect exposure settings fails to deliver a satisfactory visual experience. Only when the exposure is properly set, can the color and details of the images…
HAT: Hybrid Attention Transformer for Image Restoration
Xiangyu Chen, Xintao Wang, Wenlong Zhang +4
Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only…
Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation
Xiangyu Chen, Zheyuan Li, Zhengwen Zhang +6
Modern displays can render video content with high dynamic range (HDR) and wide color gamut (WCG). However, most resources are still in standard dynamic range (SDR). Therefore, tra…
Under-Display Camera Image Restoration with Scattering Effect
Binbin Song, Xiangyu Chen, Shuning Xu +1
The under-display camera (UDC) provides consumers with a full-screen visual experience without any obstruction due to notches or punched holes. However, the semi-transparent nature…
Direction-aware Video Demoireing with Temporal-guided Bilateral Learning
Shuning Xu, Binbin Song, Xiangyu Chen +1
Moire patterns occur when capturing images or videos on screens, severely degrading the quality of the captured images or videos. Despite the recent progresses, existing video demo…
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
Liangbin Xie, Xintao Wang, Xiangyu Chen +4
Image super-resolution (SR) with generative adversarial networks (GAN) has achieved great success in restoring realistic details. However, it is notorious that GAN-based SR models…
Activating More Pixels in Image Super-Resolution Transformer
Xiangyu Chen, Xintao Wang, Jiantao Zhou +2
Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limit…