Lune

SIGGRAPH2026Top-tier venue

Iskra: A System for Inverse Geometry Processing

Ana Dodik, Ahmed H. Mahmoud, Justin Solomon

Abstract

We propose a system for differentiating through solutions to geometry processing problems. Our system differentiates a broad class of geometric algorithms, exploiting existing fast problem-specific schemes common to geometry processing, including local-global and ADMM solvers. It is compatible with machine learning frameworks, opening doors to new classes of inverse geometry processing applications. We marry the scatter-gather approach to mesh processing with tensor-based workflows and rely on the adjoint method applied to user-specified imperative code to generate an efficient backward pass behind the scenes. We demonstrate our approach by differentiating through mean curvature flow, spectral conformal parameterization, geodesic distance computation, and as-rigid-as-possible deformation, examining usability and performance on these applications. Our system allows practitioners to differentiate through existing geometry processing algorithms without needing to reformulate them, resulting in low implementation effort, fast runtimes, and lower memory requirements than differentiable optimization tools not tailored to geometry processing.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on14

  1. AMASS: Archive of Motion Capture As Surface ShapesNaureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll et al.ICCV 2019 · 1,784 citations
  2. PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph CompilationJason Ansel, Edward Z. Yang, Horace He, Natalia Gimelshein et al.ASPLOS 2024 · 693 citations
  3. DiffTaichi: Differentiable Programming for Physical SimulationYuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun et al.ICLR 2020 · 479 citations
  4. Theseus: A Library for Differentiable Nonlinear OptimizationLuis Pineda, Taosha Fan, Maurizio Monge, Shobha Venkataraman et al.NeurIPS 2022 · 124 citations
  5. HodgeNet: learning spectral geometry on triangle meshesDmitriy Smirnov, Justin SolomonSIGGRAPH 2021 · 68 citations

Related papers

  1. Locality-Aware Automatic Differentiation on the GPU for Mesh-Based ComputationsAhmed H. Mahmoud, Rahul Goel, Jonathan Ragan-Kelley, Justin SolomonSIGGRAPH 2026
  2. Differentiable Geodesic Distance for Intrinsic Minimization on Triangle MeshesYue Li, Logan Numerow, Bernhard Thomaszewski, Stelian CorosSIGGRAPH 2024 · 5 citations
  3. Parallelised Differentiable Straightest Geodesics for 3D MeshesHippolyte Verninas, Caner Korkmaz, Stefanos Zafeiriou, Tolga Birdal et al.CVPR 2026 · 4 citations
  4. Aδ: autodiff for discontinuous programs - applied to shadersYuting Yang, Connelly Barnes, Andrew Adams, Adam FinkelsteinSIGGRAPH 2022 · 17 citations
  5. Differentiable Heightfield Path Tracing with Accelerated DiscontinuitiesXiaochun Tong, Hsueh-Ti Derek Liu, Yotam I. Gingold, Alec JacobsonSIGGRAPH 2023 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines