SparseDR: Differentiable Rendering of Sparse Signed Distance Fields

Alexey Budak; Albert Garifullin; Vladimir Frolov

IJCAI 20260 citations

SparseDR: Differentiable Rendering of Sparse Signed Distance Fields

Alexey Budak, Albert Garifullin, Vladimir Frolov

Abstract

We present SparseDR, a novel differentiable rendering algorithm designed for sparse representations based on Signed Distance Fields (SDF). We leverage the Sparse Brick Set representation and propose an adaptation of redistancing for sparse SDFs. This enables SparseDR to surpass existing works in accuracy of surface reconstruction by increasing the effective resolution of the SDF representation. SparseDR is efficiently implemented in C++ and Vulkan, achieving several times shorter reconstruction time than other methods.

AI: Computer VisionAI: Machine Learning

BibTeX

@inproceedings{ijcai2026_sparsedrdifferen,
  title = {SparseDR: Differentiable Rendering of Sparse Signed Distance Fields},
  author = {Alexey Budak and Albert Garifullin and Vladimir Frolov},
  booktitle = {IJCAI 2026},
  year = {2026}
}