NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction
This work addresses surface quality issues in neural reconstruction for applications in computer vision and graphics, representing an incremental improvement over existing methods.
The paper tackles the problem of detailed geometric structure loss in SDF-based neural surface reconstruction by introducing NeuRodin, a two-stage framework that achieves high-fidelity results, as demonstrated on Tanks and Temples and ScanNet++ datasets using only posed RGB captures.
Signed Distance Function (SDF)-based volume rendering has demonstrated significant capabilities in surface reconstruction. Although promising, SDF-based methods often fail to capture detailed geometric structures, resulting in visible defects. By comparing SDF-based volume rendering to density-based volume rendering, we identify two main factors within the SDF-based approach that degrade surface quality: SDF-to-density representation and geometric regularization. These factors introduce challenges that hinder the optimization of the SDF field. To address these issues, we introduce NeuRodin, a novel two-stage neural surface reconstruction framework that not only achieves high-fidelity surface reconstruction but also retains the flexible optimization characteristics of density-based methods. NeuRodin incorporates innovative strategies that facilitate transformation of arbitrary topologies and reduce artifacts associated with density bias. Extensive evaluations on the Tanks and Temples and ScanNet++ datasets demonstrate the superiority of NeuRodin, showing strong reconstruction capabilities for both indoor and outdoor environments using solely posed RGB captures. Project website: https://open3dvlab.github.io/NeuRodin/