17 papers
Accurate Motion Estimation with Bézier Control Point for Efficient Frame Interpolation
Shuhao Han, Chenyang Wu, Chun-Le Guo +4
In frame interpolation tasks, motion ambiguity in the training set causes models to generate blurry intermediate frames. Moreover, the assumption of uniform motion between frames d…
Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement
Chujie Qin, Zilong Zhang, Zewei Chang +5
Image retouching is commonly formulated as enhancing overall visual quality through color adjustment, but in practice, it also serves to emphasize visual focus by guiding viewers'…
FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion
Yuang Meng, Chenyang Wu, Xianshun Liu +7
Existing optical flow methods broadly follow two paradigms: iterative optimization and diffusion-based estimation. Iterative methods, exemplified by RAFT, achieve high accuracy thr…
YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal
Chenyang Wu, Lina Lei, Fan Li +6
Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, these methods still suffer from…
Improving Reconstruction of Representation Autoencoder
Siyu Liu, Chujie Qin, Hubery Yin +6
Recent work leverages Vision Foundation Models as image encoders to boost the generative performance of latent diffusion models (LDMs), as their semantic feature distributions are…
FlowConsist: Make Your Flow Consistent with Real Trajectory
Tianyi Zhang, Chengcheng Liu, Jinwei Chen +5
Fast flow models accelerate the iterative sampling process by learning to directly predict ODE path integrals, enabling one-step or few-step generation. However, we argue that curr…
PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching
Zewei Chang, Zheng-Peng Duan, Jianxing Zhang +6
Image retouching aims to enhance visual quality while aligning with users' personalized aesthetic preferences. To address the challenge of balancing controllability and subjectivit…
VTinker: Guided Flow Upsampling and Texture Mapping for High-Resolution Video Frame Interpolation
Chenyang Wu, Jiayi Fu, Chun-Le Guo +2
Due to large pixel movement and high computational cost, estimating the motion of high-resolution frames is challenging. Thus, most flow-based Video Frame Interpolation (VFI) metho…
UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes
Yuang Meng, Xin Jin, Lina Lei +2
Ultra-high dynamic range (UHDR) scenes exhibit significant exposure disparities between bright and dark regions. Such conditions are commonly encountered in nighttime scenes with l…
DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models
Jiachen Fu, Chun-Le Guo, Chongyi Li
The rapid advancement of large language models (LLMs) has drawn urgent attention to the task of machine-generated text detection (MGTD). However, existing approaches struggle in co…
Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution
Tianyi Zhang, Zheng-Peng Duan, Peng-Tao Jiang +4
Diffusion-based real-world image super-resolution (Real-ISR) methods have demonstrated impressive performance.To achieve efficient Real-ISR, many works employ Variational Score Dis…
NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results
Sangmin Lee, Eunpil Park, Angel Canelo +33
This paper reviews the NTIRE 2025 Efficient Burst HDR and Restoration Challenge, which aims to advance efficient multi-frame high dynamic range (HDR) and restoration techniques. Th…
A Diffusion-Based Framework for Occluded Object Movement
Zheng-Peng Duan, Jiawei Zhang, Siyu Liu +5
Seamlessly moving objects within a scene is a common requirement for image editing, but it is still a challenge for existing editing methods. Especially for real-world images, the…
Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing
Jiayi Fu, Siyu Liu, Zikun Liu +5
We propose a novel Iterative Predictor-Critic Code Decoding framework for real-world image dehazing, abbreviated as IPC-Dehaze, which leverages the high-quality codebook prior enca…
DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution
Zheng-Peng Duan, Jiawei Zhang, Xin Jin +6
Large-scale pre-trained diffusion models are becoming increasingly popular in solving the Real-World Image Super-Resolution (Real-ISR) problem because of their rich generative prio…
FaceMe: Robust Blind Face Restoration with Personal Identification
Siyu Liu, Zheng-Peng Duan, Jia OuYang +5
Blind face restoration is a highly ill-posed problem due to the lack of necessary context. Although existing methods produce high-quality outputs, they often fail to faithfully pre…
Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration
Chu-Jie Qin, Rui-Qi Wu, Zikun Liu +4
All-in-one image restoration aims to handle multiple degradation types using one model. This paper proposes a simple pipeline for all-in-one blind image restoration to Restore Anyt…