MonoSelfRecon：基于单目RGB视图的纯自监督显式可泛化室内场景三维重建
MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views
AI总结：
本文提出MonoSelfRecon框架，利用体素-SDF、可泛化NeRF和新型自监督损失，首次从单目RGB实现纯自监督、显式且可泛化的室内三维网格重建。
摘要：
当前的单目三维场景重建（3DR）工作要么是全监督的，要么不具备泛化能力，要么采用隐式三维表示。我们提出了一个新颖框架——MonoSelfRecon，它首次通过在体素-SDF（有符号距离函数）上进行纯自监督，实现了利用单目RGB视图对可泛化室内场景进行显式三维网格重建。MonoSelfRecon采用基于自编码器的架构，解码体素-SDF和一个可泛化的神经辐射场（NeRF），后者用于在自监督中引导体素-SDF。我们提出了新颖的自监督损失，不仅支持纯自监督，还可以与监督信号结合使用，以进一步增强监督训练。实验表明，以纯自监督方式训练的“MonoSelfRecon”优于当前最佳的自监督室内深度估计模型，并且可与使用深度标注进行全监督训练的3DR模型相媲美。MonoSelfRecon不受特定模型设计的限制，可用于任何具有体素-SDF的模型，以纯自监督方式运行。
英文摘要：
Current monocular 3D scene reconstruction (3DR) works are either fully-supervised, or not generalizable, or implicit in 3D representation. We propose a novel framework - MonoSelfRecon that for the first time achieves explicit 3D mesh reconstruction for generalizable indoor scenes with monocular RGB views by purely self-supervision on voxel-SDF (signed distance function). MonoSelfRecon follows an Autoencoder-based architecture, decodes voxel-SDF and a generalizable Neural Radiance Field (NeRF), which is used to guide voxel-SDF in self-supervision. We propose novel self-supervised losses, which not only support pure self-supervision, but can be used together with supervised signals to further boost supervised training. Our experiments show that "MonoSelfRecon" trained in pure self-supervision outperforms current best self-supervised indoor depth estimation models and is comparable to 3DR models trained in fully supervision with depth annotations. MonoSelfRecon is not restricted by specific model design, which can be used to any models with voxel-SDF for purely self-supervised manner.
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。
