GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
This addresses the domain-specific problem of 3D reconstruction for reflective objects in computer vision, with incremental improvements over prior methods.
The paper tackles the problem of reconstructing 3D shapes of reflective objects using neural radiance fields, which is challenging due to specular reflections, and proposes a Gaussian-guided method that outperforms existing approaches by a large margin on reflective scenes.
Learning surfaces from neural radiance field (NeRF) became a rising topic in Multi-View Stereo (MVS). Recent Signed Distance Function (SDF)-based methods demonstrated their ability to reconstruct accurate 3D shapes of Lambertian scenes. However, their results on reflective scenes are unsatisfactory due to the entanglement of specular radiance and complicated geometry. To address the challenges, we propose a Gaussian-based representation of normals in SDF fields. Supervised by polarization priors, this representation guides the learning of geometry behind the specular reflection and captures more details than existing methods. Moreover, we propose a reweighting strategy in the optimization process to alleviate the noise issue of polarization priors. To validate the effectiveness of our design, we capture polarimetric information, and ground truth meshes in additional reflective scenes with various geometry. We also evaluated our framework on the PANDORA dataset. Comparisons prove our method outperforms existing neural 3D reconstruction methods in reflective scenes by a large margin.