NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images
This addresses a practical challenge in computer vision for applications like robotics or AR/VR, though it is incremental in combining existing techniques.
The paper tackles the problem of 3D reconstruction for reflective objects from sparse images, achieving state-of-the-art results with only 6 views as input.
We present NeRSP, a Neural 3D reconstruction technique for Reflective surfaces with Sparse Polarized images. Reflective surface reconstruction is extremely challenging as specular reflections are view-dependent and thus violate the multiview consistency for multiview stereo. On the other hand, sparse image inputs, as a practical capture setting, commonly cause incomplete or distorted results due to the lack of correspondence matching. This paper jointly handles the challenges from sparse inputs and reflective surfaces by leveraging polarized images. We derive photometric and geometric cues from the polarimetric image formation model and multiview azimuth consistency, which jointly optimize the surface geometry modeled via implicit neural representation. Based on the experiments on our synthetic and real datasets, we achieve the state-of-the-art surface reconstruction results with only 6 views as input.