activity
20242026
collaborators

9 papers

cs.CV2026

ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement

Yufeng Yang, Jianzhuang Liu, Jisheng Chu +4

Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability a…

cs.CV2026

RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

Yufeng Yang, Xianfang Zeng, Zhangqi Jiang +8

Image restoration under real-world degradations is critical for downstream tasks such as autonomous driving and object detection. However, existing restoration models are often lim…

cs.CV2026

MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation

Kaixin Cai, Pengzhen Ren, Jianhua Han +4

Open-world semantic segmentation presently relies significantly on extensive image-text pair datasets, which often suffer from a lack of fine-grained pixel annotations on sufficien…

cs.CV2025

TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models

Yuqi Peng, Lingtao Zheng, Yufeng Yang +4

Personalized text-to-image generation aims to synthesize novel images of a specific subject or style using only a few reference images. Recent methods based on Low-Rank Adaptation…

cs.CV2025

DIVE: Taming DINO for Subject-Driven Video Editing

Yi Huang, Wei Xiong, He Zhang +4

Building on the success of diffusion models in image generation and editing, video editing has recently gained substantial attention. However, maintaining temporal consistency and…

cs.CV2025

GLAD: Generalizable Tuning for Vision-Language Models

Yuqi Peng, Pengfei Wang, Jianzhuang Liu +1

Pre-trained vision-language models, such as CLIP, show impressive zero-shot recognition ability and can be easily transferred to specific downstream tasks via prompt tuning, even w…