Layout-guided Indoor Panorama Inpainting with Plane-aware Normalization

TL;DR

This paper introduces a deep learning framework for indoor panoramic image inpainting that leverages layout edges and plane-aware normalization to improve the recovery of complex indoor structures and textures.

Contribution

It proposes a novel layout-guided inpainting method with plane-aware normalization, enhancing the reconstruction of indoor panorama structures and textures.

Findings

Outperforms state-of-the-art methods on public datasets

Effectively restores complex indoor structures and textures

Demonstrates superior qualitative and quantitative results

Abstract

We present an end-to-end deep learning framework for indoor panoramic image inpainting. Although previous inpainting methods have shown impressive performance on natural perspective images, most fail to handle panoramic images, particularly indoor scenes, which usually contain complex structure and texture content. To achieve better inpainting quality, we propose to exploit both the global and local context of indoor panorama during the inpainting process. Specifically, we take the low-level layout edges estimated from the input panorama as a prior to guide the inpainting model for recovering the global indoor structure. A plane-aware normalization module is employed to embed plane-wise style features derived from the layout into the generator, encouraging local texture restoration from adjacent room structures (i.e., ceiling, floor, and walls). Experimental results show that our work outperforms the current state-of-the-art methods on a public panoramic dataset in both qualitative and quantitative evaluations. Our code is available at https://ericsujw.github.io/LGPN-net/