Monocular Occupancy Prediction for Scalable Indoor Scenes

TL;DR

This paper introduces ISO, a monocular indoor scene occupancy prediction method utilizing a pretrained depth model and a novel D-FLoSP module, along with a large-scale benchmark dataset, Occ-ScanNet, to advance indoor scene analysis.

Contribution

The paper presents a novel monocular occupancy prediction method for indoor scenes, incorporating a new D-FLoSP module and a large-scale dataset, Occ-ScanNet, to enable scalable indoor scene research.

Findings

Achieves state-of-the-art performance on NYUv2 and Occ-ScanNet datasets.

Introduces a large-scale indoor occupancy benchmark dataset.

Demonstrates the effectiveness of the D-FLoSP module in learning 3D voxel features.

Abstract

Camera-based 3D occupancy prediction has recently garnered increasing attention in outdoor driving scenes. However, research in indoor scenes remains relatively unexplored. The core differences in indoor scenes lie in the complexity of scene scale and the variance in object size. In this paper, we propose a novel method, named ISO, for predicting indoor scene occupancy using monocular images. ISO harnesses the advantages of a pretrained depth model to achieve accurate depth predictions. Furthermore, we introduce the Dual Feature Line of Sight Projection (D-FLoSP) module within ISO, which enhances the learning of 3D voxel features. To foster further research in this domain, we introduce Occ-ScanNet, a large-scale occupancy benchmark for indoor scenes. With a dataset size 40 times larger than the NYUv2 dataset, it facilitates future scalable research in indoor scene analysis. Experimental results on both NYUv2 and Occ-ScanNet demonstrate that our method achieves state-of-the-art performance. The dataset and code are made publicly at https://github.com/hongxiaoy/ISO.git.