Scalable and High-Quality Neural Implicit Representation for 3D Reconstruction
This addresses scalability and quality issues in 3D reconstruction for applications like computer vision and graphics, representing an incremental improvement over existing SDF-based methods.
The paper tackles the limited accuracy and scale of neural implicit surface reconstruction by proposing a method that models objects or scenes as a fusion of multiple local neural SDFs with overlapping regions, achieving high-fidelity and scalable reconstruction.
Various SDF-based neural implicit surface reconstruction methods have been proposed recently, and have demonstrated remarkable modeling capabilities. However, due to the global nature and limited representation ability of a single network, existing methods still suffer from many drawbacks, such as limited accuracy and scale of the reconstruction. In this paper, we propose a versatile, scalable and high-quality neural implicit representation to address these issues. We integrate a divide-and-conquer approach into the neural SDF-based reconstruction. Specifically, we model the object or scene as a fusion of multiple independent local neural SDFs with overlapping regions. The construction of our representation involves three key steps: (1) constructing the distribution and overlap relationship of the local radiance fields based on object structure or data distribution, (2) relative pose registration for adjacent local SDFs, and (3) SDF blending. Thanks to the independent representation of each local region, our approach can not only achieve high-fidelity surface reconstruction, but also enable scalable scene reconstruction. Extensive experimental results demonstrate the effectiveness and practicality of our proposed method.