单目占用预测用于可扩展室内场景
Monocular Occupancy Prediction for Scalable Indoor Scenes
AI总结：
本文提出ISO方法，利用预训练深度模型和双特征视线投影模块，实现室内场景单目占用预测，并构建大规模基准Occ-ScanNet，在NYUv2和Occ-ScanNet上达到最先进性能。
摘要：
基于相机的三维占用预测近年来在室外驾驶场景中引起了越来越多的关注。然而，室内场景的研究仍相对较少。室内场景的核心差异在于场景尺度的复杂性和物体尺寸的变异性。在本文中，我们提出了一种名为ISO的新方法，用于使用单目图像预测室内场景占用。ISO利用预训练深度模型的优势，实现准确的深度预测。此外，我们在ISO中引入了双特征视线投影（D-FLoSP）模块，该模块增强了三维体素特征的学习。为了促进该领域的进一步研究，我们引入了Occ-ScanNet，一个用于室内场景的大规模占用基准。其数据集规模比NYUv2数据集大40倍，有助于未来室内场景分析的可扩展研究。在NYUv2和Occ-ScanNet上的实验结果表明，我们的方法达到了最先进的性能。数据集和代码已在https://github.com/hongxiaoy/ISO.git公开提供。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
