Advanced techniques using Neural Radiance Fields (NeRF), Signed Distance Fields (SDF), and Occupancy Fields have recently emerged as solutions for 3D indoor scene reconstruction. We introduce a novel two-phase learning approach, H2O-SDF, that discriminates between object and non-object regions within indoor environments. This method achieves a nuanced balance, carefully preserving the geometric integrity of room layouts while also capturing intricate surface details of specific objects. A cornerstone of our two-phase learning framework is the introduction of the Object Surface Field (OSF), a novel concept designed to mitigate the persistent vanishing gradient problem that has previously hindered the capture of high-frequency details in other methods. Our proposed approach is validated through several experiments that include ablation studies.

翻译：利用神经辐射场（NeRF）、符号距离场（SDF）和占据场的高级技术近来已作为三维室内场景重建的解决方案出现。我们提出了一种新颖的两阶段学习方法H2O-SDF，该方法能够区分室内环境中的物体区域与非物体区域。该方法实现了精细的平衡，既谨慎保留了房间布局的几何完整性，又同时捕捉了特定物体的复杂表面细节。我们的两阶段学习框架的核心是引入了物体表面场（OSF）这一创新概念，旨在缓解之前方法在捕捉高频细节时一直存在的梯度消失问题。通过包含消融研究的若干实验，我们提出的方法得到了验证。