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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
