This paper introduces Camera-free Diffusion (CamFreeDiff) model for 360-degree image outpainting from a single camera-free image and text description. This method distinguishes itself from existing strategies, such as MVDiffusion, by eliminating the requirement for predefined camera poses. Instead, our model incorporates a mechanism for predicting homography directly within the multi-view diffusion framework. The core of our approach is to formulate camera estimation by predicting the homography transformation from the input view to a predefined canonical view. The homography provides point-level correspondences between the input image and targeting panoramic images, allowing connections enforced by correspondence-aware attention in a fully differentiable manner. Qualitative and quantitative experimental results demonstrate our model's strong robustness and generalization ability for 360-degree image outpainting in the challenging context of camera-free inputs.
@article{arxiv.2407.07174,
title = {CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model},
author = {Xiaoding Yuan and Shitao Tang and Kejie Li and Alan Yuille and Peng Wang},
journal= {arXiv preprint arXiv:2407.07174},
year = {2024}
}