SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020) (Oral), Seattle, WA.

Download Video(MP4, 57.7 MB)

Download Video(MP4, 18.0 MB)

Abstract

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.

Resources and Downloads


Citation

BibTeX, 1 KB

@InProceedings{jiang2020sdfdiff,
    author = {Jiang, Yue and Ji, Dantong and Han, Zhizhong and Zwicker, Matthias},
    title = {SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization},
    booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month = {June},
    year = {2020}
}

Contact

For questions and clarifications, please get in touch with:
Yue Jiang yuejiang@cs.umd.edu

Template from GVV Group at MPI.