SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
This addresses the challenge of 3D reconstruction from images for computer vision and graphics applications, offering a novel method with broad applicability.
The paper tackles the problem of image-based 3D shape optimization by proposing SDFDiff, a differentiable rendering method for signed distance fields, which achieves high reconstruction quality and state-of-the-art results in single-view 3D reconstruction.
We propose SDFDiff, a novel approach for image-based shape optimization using differentiable rendering of 3D shapes represented by signed distance functions (SDFs). Compared to other representations, SDFs have the advantage that they can represent shapes with arbitrary topology, and that they guarantee watertight surfaces. We apply our approach to the problem of multi-view 3D reconstruction, where we achieve high reconstruction quality and can capture complex topology of 3D objects. In addition, we employ a multi-resolution strategy to obtain a robust optimization algorithm. We further demonstrate that our SDF-based differentiable renderer can be integrated with deep learning models, which opens up options for learning approaches on 3D objects without 3D supervision. In particular, we apply our method to single-view 3D reconstruction and achieve state-of-the-art results.