In Proceedings of ECCV (33)

Unbiased Gradient Estimation for Differentiable Surface Splatting via Poisson Sampling

Jan U. Müller, Michael Weinmann, and Reinhard Klein

Publisher Cite More

We propose an efficient and GPU-accelerated sampling framework which enables unbiased gradient approximation for differentiable point cloud rendering based on surface splatting. Our framework models the contribution of a point to the rendered image as a probability distribution. We derive an unbiased approximative gradient for the rendering function within this model. To efficiently evaluate the proposed sample estimate, we introduce a tree-based data-structure which employs multipole methods to draw samples in near linear time. Our gradient estimator allows us to avoid regularization required by previous methods, leading to a more faithful shape recovery from images. Furthermore, we validate that these improvements are applicable to real-world applications by refining the camera poses and point cloud obtained from a real-time SLAM system. Finally, employing our framework in a neural rendering setting optimizes both the point cloud and network parameters, highlighting the framework’s ability to enhance data driven approaches.

More Information

Citation

BibTex

@inproceedings{bib:müller:2022,
    author       = { Müller, Jan U. and Weinmann, Michael and Klein, Reinhard },    
    title        = { Unbiased Gradient Estimation for Differentiable Surface Splatting via Poisson Sampling },
    booktitle    = { In Proceedings of ECCV (33) },
    year         = { 2022 },
    pages        = { 281--299 },
    publisher    = { Springer Nature Switzerland },
    doi          = { 10.1007/978-3-031-19827-4_17 },
    dblp         = { conf/eccv/MullerWK22 },
    url          = { https://publications.graphics.tudelft.nl/papers/60 },
}