5 papers
Revisiting Model Stitching In the Foundation Model Era
Zheda Mai, Ke Zhang, Fu-En Wang +6
Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility…
Towards Training-Free Scene Text Editing
Yubo Li, Xugong Qin, Peng Zhang +3
Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require task-specific trainin…
OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution
Shijie Zhao, Xuanyu Zhang, Bin Chen +8
Aligning generative real-world image super-resolution models with human visual preference is challenging due to the perception--fidelity trade-off and diverse, unknown degradations…
GenDR: Lighten Generative Detail Restoration
Yan Wang, Shijie Zhao, Kexin Zhang +2
Although recent research applying text-to-image (T2I) diffusion models to real-world super-resolution (SR) has achieved remarkable progress, the misalignment of their targets leads…
UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement
Weiqi Li, Xuanyu Zhang, Bin Chen +7
Image quality assessment (IQA) and image restoration are fundamental problems in low-level vision. Although IQA and restoration are closely connected conceptually, most existing wo…