5 papers
Agentic Retoucher for Text-To-Image Generation
Shaocheng Shen, Jianfeng Liang, Chunlei Cai +5
Text-to-image (T2I) diffusion models such as SDXL and FLUX have achieved impressive photorealism, yet small-scale distortions remain pervasive in limbs, face, text and so on. Exist…
MoA-VR: A Mixture-of-Agents System Towards All-in-One Video Restoration
Lu Liu, Chunlei Cai, Shaocheng Shen +9
Real-world videos often suffer from complex degradations, such as noise, compression artifacts, and low-light distortions, due to diverse acquisition and transmission conditions. E…
Instance-aware Image Colorization with Controllable Textual Descriptions and Segmentation Masks
Yanru An, Ling Gui, Chunlei Cai +5
Recently, the application of deep learning in image colorization has received widespread attention. The maturation of diffusion models has further advanced the development of image…
F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration
Lu Liu, Huiyu Duan, Qiang Hu +6
Artificial intelligence generative models exhibit remarkable capabilities in content creation, particularly in face image generation, customization, and restoration. However, curre…
FineVQ: Fine-Grained User Generated Content Video Quality Assessment
Huiyu Duan, Qiang Hu, Jiarui Wang +8
The rapid growth of user-generated content (UGC) videos has produced an urgent need for effective video quality assessment (VQA) algorithms to monitor video quality and guide optim…