Warp-Geo: Differentiable Geometry Representation for Dynamic-Boundary Simulation and Shape Optimization
Abstract
Modern inverse problems and adaptive simulations require efficient and differentiable representations of complex geometries that can be updated frequently for gradient-based optimization. Existing methods cannot simultaneously achieve both. We present Warp-Geo, a differentiable GPU-accelerated framework for reconstructing signed distance fields and evaluating surface normals from point clouds of complex 3D geometries. Warp-Geo combines uniform grids for GPU parallelism with implicit differentiation through the Poisson solve, enabling frequent geometry recomputation while maintaining full differentiability. We demonstrate Warp-Geo on forward SDF reconstruction, dynamic fluid--structure interaction with moving boundaries, and inverse shape optimization via automatic differentiation with gradient validation. GPU scalability analysis confirms practical feasibility for frequent geometry updates. The framework, implemented in Warp and JAX, enables seamless integration with differentiable physics solvers for end-to-end shape optimization.
Related
- Differentiable Schwarz-Coupled Solvers for Thin Boundary Layer Transport: Inverse Modeling via Agentic AI Optimization
- Fully differentiable framework for inverse identification of geometry and material parameters with application to determining stress-free configuration of soft tissues
- diff-soup: GPU-native Differentiable Simulation and Inference for Large-scale Stiff Dynamical Systems
- A differentiable Lagrangian-coupled 3D Gaussian Splatting-SPH model for forward simulation and inverse analysis in solid mechanics
- Measurement-Efficient Differentiable Quantum Architecture Search for Combinatorial Optimization
BibTeX
@misc{zhang2026warpgeo,
title = {{Warp-Geo: Differentiable Geometry Representation for Dynamic-Boundary Simulation and Shape Optimization}},
author = {Weijie Zhang and Xiantao Fan and Jian-Xun Wang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.20964},
eprint = {2609.20964},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.20964},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Warp-Geo: Differentiable Geometry Representation for Dynamic-Boundary Simulation and Shape Optimization
AU - Weijie Zhang
AU - Xiantao Fan
AU - Jian-Xun Wang
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.20964
UR - https://arxiv.org/abs/2609.20964
AB - Modern inverse problems and adaptive simulations require efficient and differentiable representations of complex geometries that can be updated frequently for gradient-based optimization. Existing methods cannot simultaneously achieve both. We present Warp-Geo, a differentiable GPU-accelerated framework for reconstructing signed distance fields and evaluating surface normals from point clouds of complex 3D geometries. Warp-Geo combines uniform grids for GPU parallelism with implicit differentiation through the Poisson solve, enabling frequent geometry recomputation while maintaining full differentiability. We demonstrate Warp-Geo on forward SDF reconstruction, dynamic fluid--structure interaction with moving boundaries, and inverse shape optimization via automatic differentiation with gradient validation. GPU scalability analysis confirms practical feasibility for frequent geometry updates. The framework, implemented in Warp and JAX, enables seamless integration with differentiable physics solvers for end-to-end shape optimization.
ER -