Pano2Room: Novel View Synthesis from a Single Indoor Panorama

TL;DR

Pano2Room is a novel method that reconstructs high-quality 3D indoor scenes from a single panoramic image, enabling realistic view synthesis even with occlusions, by iteratively refining a mesh and converting it into a 3D Gaussian Splatting field.

Contribution

The paper introduces Pano2Room, a new approach that automatically reconstructs detailed 3D indoor scenes from a single panorama using iterative mesh refinement and Gaussian Splatting.

Findings

Outperforms state-of-the-art in single-panorama indoor view synthesis.

Effectively handles large occlusions in scene reconstruction.

Produces photo-realistic novel views with detailed geometry.

Abstract

Recent single-view 3D generative methods have made significant advancements by leveraging knowledge distilled from extensive 3D object datasets. However, challenges persist in the synthesis of 3D scenes from a single view, primarily due to the complexity of real-world environments and the limited availability of high-quality prior resources. In this paper, we introduce a novel approach called Pano2Room, designed to automatically reconstruct high-quality 3D indoor scenes from a single panoramic image. These panoramic images can be easily generated using a panoramic RGBD inpainter from captures at a single location with any camera. The key idea is to initially construct a preliminary mesh from the input panorama, and iteratively refine this mesh using a panoramic RGBD inpainter while collecting photo-realistic 3D-consistent pseudo novel views. Finally, the refined mesh is converted into a 3D Gaussian Splatting field and trained with the collected pseudo novel views. This pipeline enables the reconstruction of real-world 3D scenes, even in the presence of large occlusions, and facilitates the synthesis of photo-realistic novel views with detailed geometry. Extensive qualitative and quantitative experiments have been conducted to validate the superiority of our method in single-panorama indoor novel synthesis compared to the state-of-the-art. Our code and data are available at \url{https://github.com/TrickyGo/Pano2Room}.