CVPR2025

CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model

Xiaoding Yuan, Shitao Tang, Kejie Li, Peng Wang

Abstract

Figure 1 . We propose CamFreeDiff that can generate text-guided 360-degree panoramic image with plausible layout and canonical viewpoint from a camera-free input. CamFreeD iff eliminates the restriction on the camera parameters including viewpoints of inputs, showing strong robustness to non-canonical inputs and generates high-quality 360 • panoramic image.