360$^\circ$ panoramas are extensively utilized as environmental light sources
in computer graphics. However, capturing a 360$^\circ$ $\times$ 180$^\circ$
panorama poses challenges due to the necessity of specialized and costly
equipment, and additional human resources. Prior studies develop various
learning-based generative methods to synthesize panoramas from a single Narrow
Field-of-View (NFoV) image, but they are limited in alterable input patterns,
generation quality, and controllability. To address these issues, we propose a
novel pipeline called PanoDiff, which efficiently generates complete
360$^\circ$ panoramas using one or more unregistered NFoV images captured from
arbitrary angles. Our approach has two primary components to overcome the
limitations. Firstly, a two-stage angle prediction module to handle various
numbers of NFoV inputs. Secondly, a novel latent diffusion-based panorama
generation model uses incomplete panorama and text prompts as control signals
and utilizes several geometric augmentation schemes to ensure geometric
properties in generated panoramas. Experiments show that PanoDiff achieves
state-of-the-art panoramic generation quality and high controllability, making
it suitable for applications such as content editing.

使用一种称为 PanoDiff 的新型方法，通过使用一个或多个未注册的 Narrow Field-of-View (NFoV) 图像，高效地生成完整的 360° 全景图，该方法通过两个主要组件来克服以往方法中的局限性，包括两阶段的角度预测模块和一种基于潜在扩散的全景生成模型，实验表明 PanoDiff 实现了最先进的全景生成质量和高可控性，适用于内容编辑等应用。