Author

Cihang Xie

h-index 35 View on Semantic Scholar

We have 1 of 78 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

Let RGB Be the Language of Vision

This work introduces a unified formulation for vision models, where diverse forms of visual information beyond natural images, such as masks, depth maps, and other structured visual signals, are all represented as RGB images, while general visual tasks can be converted into a common RGB-to-RGB image editing problem. In...

Ti-Ming Yang, Jinrui Yang, Xinlong Li et al. · 0 citations