activity
20242026
collaborators

14 papers

cs.CV2026

Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach

Xincheng Wang, Hanchi Sun, Wenjun Sun +8

Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles, but also introduce copyright and secur…

eess.IV2026

Surveillance Facial Image Quality Assessment: A Multi-dimensional Dataset and Lightweight Model

Yanwei Jiang, Wei Sun, Yingjie Zhou +8

Surveillance facial images are often captured under unconstrained conditions, resulting in severe quality degradation due to factors such as low resolution, motion blur, occlusion,…

cs.CV2026

VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning

Linhan Cao, Wei Sun, Weixia Zhang +6

Video quality assessment (VQA) aims to objectively quantify perceptual quality degradation in alignment with human visual perception. Despite recent advances, existing VQA models s…

cs.CV2026

QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding

Linhan Cao, Wei Sun, Weixia Zhang +6

Visual quality assessment (VQA) is increasingly shifting from scalar score prediction toward interpretable quality understanding -- a paradigm that demands \textit{fine-grained spa…

cs.CV2025

Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation

Jun Jia, Hongyi Miao, Yingjie Zhou +8

With the rapid progress in diffusion models, image synthesis has advanced to the stage of zero-shot image-to-image generation, where high-fidelity replication of facial identities…

eess.IV2025

DLADiff: A Dual-Layer Defense Framework against Fine-Tuning and Zero-Shot Customization of Diffusion Models

Jun Jia, Hongyi Miao, Yingjie Zhou +8

With the rapid advancement of diffusion models, a variety of fine-tuning methods have been developed, enabling high-fidelity image generation with high similarity to the target con…