DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion

TL;DR

This work proposes a novel text-driven panoramic generation framework, termed DiffPano, and fine-tune a single-view text-to-panorama diffusion model with LoRA on the established panoramic video-text dataset to achieve scalable, consistent, and diverse panoramic scene generation.

Abstract

Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoramic video-text dataset containing millions of consecutive panoramic keyframes with corresponding panoramic depths, camera poses, and text descriptions. Then, we propose a novel text-driven panoramic generation framework, termed DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation. Specifically, benefiting from the powerful generative capabilities of stable diffusion, we fine-tune a single-view text-to-panorama diffusion model with LoRA on the established panoramic video-text dataset. We further design a spherical epipolar-aware multi-view diffusion model to ensure the multi-view consistency of the generated panoramic images. Extensive experiments demonstrate that DiffPano can generate scalable, consistent, and diverse panoramic images with given unseen text descriptions and camera poses.

Figures (13)

• Figure 1: DiffPano allows scalable and consistent panorama generation (i.e. room switching) with given unseen text descriptions and camera poses. Each column represents the generated multi-view panoramas, switching from one room to another.
• Figure 2: Panoramic Video Construction and Caption Pipeline.
• Figure 3: DiffPano Framework. The DiffPano framework consists of a single-view text-to-panorama diffusion model and a spherical epipolar-aware multi-view diffusion model. It can support text to single-view panorama or multi-view panorama generation.
• Figure 4: Text to Panorama Comparison between TextLight, PanFusion, and Ours.
• Figure 5: Comparisons with MVDream. DiffPano can generate more consistent multi-view panoramas. "MVDream$\times$2" denotes MVDream is trained with twice iteration number relative to our method.