A Finite Difference Approximation of Second Order Regularization of Neural-SDFs

November 12, 2025 Β· Declared Dead Β· πŸ› Proceedings of the SIGGRAPH Asia 2025 Technical Communications

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Haotian Yin, Aleksander Plocharski, Michal Jan Wlodarczyk, Przemyslaw Musialski arXiv ID 2511.08980 Category cs.GR: Graphics Cross-listed cs.CV, cs.LG Citations 2 Venue Proceedings of the SIGGRAPH Asia 2025 Technical Communications Last Checked 5 months ago
Abstract
We introduce a finite-difference framework for curvature regularization in neural signed distance field (SDF) learning. Existing approaches enforce curvature priors using full Hessian information obtained via second-order automatic differentiation, which is accurate but computationally expensive. Others reduced this overhead by avoiding explicit Hessian assembly, but still required higher-order differentiation. In contrast, our method replaces these operations with lightweight finite-difference stencils that approximate second derivatives using the well known Taylor expansion with a truncation error of O(h^2), and can serve as drop-in replacements for Gaussian curvature and rank-deficiency losses. Experiments demonstrate that our finite-difference variants achieve reconstruction fidelity comparable to their automatic-differentiation counterparts, while reducing GPU memory usage and training time by up to a factor of two. Additional tests on sparse, incomplete, and non-CAD data confirm that the proposed formulation is robust and general, offering an efficient and scalable alternative for curvature-aware SDF learning.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Graphics

R.I.P. πŸ‘» Ghosted

Everybody Dance Now

Caroline Chan, Shiry Ginosar, ... (+2 more)

cs.GR πŸ› ICCV πŸ“š 820 cites 7 years ago
R.I.P. πŸ‘» Ghosted

Animating Human Athletics

Jessica K. Hodgins, Wayne L. Wooten, ... (+2 more)

cs.GR πŸ› SIGGRAPH πŸ“š 765 cites 3 years ago

Died the same way β€” πŸ‘» Ghosted