Let RGB Be the Language of Vision
For the vision community, RINO offers a new paradigm that simplifies multi-task learning by unifying diverse visual tasks under a single RGB interface, potentially reducing the need for task-specific architectures.
This work proposes RINO, a unified formulation where all visual tasks are treated as RGB-to-RGB image editing, enabling a single model to perform zero-shot on tasks like segmentation, depth estimation, and pose-to-image generation without task-specific fine-tuning.
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 this paradigm, different types of visual information internally share the same encoding and decoding architecture and parameters as natural images, enabling a single model to transfer across tasks through a unified visual interface, in a way analogous to how language models operate over text. We refer to this formulation as RGB In and RGB Out (RINO). Built upon a generic image editing backbone without task-specific fine-tuning, RINO demonstrates robust and competitive zero-shot performance on both dense understanding tasks such as segmentation and depth estimation (where we unify outputs as RGB), and dense-conditioned generation tasks such as pose-to-image generation (where we unify inputs as RGB). We hope this study provides useful insights toward general unified vision-language systems, where diverse visual tasks can be expressed, interpreted, and solved through a shared visual language. Code is available at https://github.com/yangtiming/RINO.