scipy.spatial.transform: Differentiable Framework-Agnostic 3D Transformations in Python

• URL: http://arxiv.org/abs/2511.18157v2
• Date: Wed, 26 Nov 2025 09:37:48 GMT
• Title: scipy.spatial.transform: Differentiable Framework-Agnostic 3D Transformations in Python
• Authors: Martin Schuck, Alexander von Rohr, Angela P. Schoellig,
• Abstract summary: Three-dimensional rigid-body transforms, i.e. rotations and translations, are central to modern differentiable machine learning pipelines.<n> SciPy's spatial$.$diff module is a rigorously tested Python implementation.<n>We present a complete overhaul of SciPy's spatial$.$transform functionality that makes it compatible with any array library implementing the Python array API.
• Score: 49.015684860172975
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Three-dimensional rigid-body transforms, i.e. rotations and translations, are central to modern differentiable machine learning pipelines in robotics, vision, and simulation. However, numerically robust and mathematically correct implementations, particularly on SO(3), are error-prone due to issues such as axis conventions, normalizations, composition consistency and subtle errors that only appear in edge cases. SciPy's spatial$.$transform module is a rigorously tested Python implementation. However, it historically only supported NumPy, limiting adoption in GPU-accelerated and autodiff-based workflows. We present a complete overhaul of SciPy's spatial$.$transform functionality that makes it compatible with any array library implementing the Python array API, including JAX, PyTorch, and CuPy. The revised implementation preserves the established SciPy interface while enabling GPU/TPU execution, JIT compilation, vectorized batching, and differentiation via native autodiff of the chosen backend. We demonstrate how this foundation supports differentiable scientific computing through two case studies: (i) scalability of 3D transforms and rotations and (ii) a JAX drone simulation that leverages SciPy's Rotation for accurate integration of rotational dynamics. Our contributions have been merged into SciPy main and will ship in the next release, providing a framework-agnostic, production-grade basis for 3D spatial math in differentiable systems and ML.

Related papers

• torch-sla: Differentiable Sparse Linear Algebra with Adjoint Solvers and Sparse Tensor Parallelism for PyTorch [0.2960141730774496]
  We present torchsla, an open-source PyTorch library that enables GPU-accelerated, scalable, and differentiable sparse linear algebra.<n>torchsla supports multiple backends (SciPy, cuDSS, PyTorch-native) and seamlessly integrates with PyTorch autograd for end-to-end differentiable simulations.
  arXiv  Detail & Related papers  (2026-01-20T14:06:01Z)
• FFTArray: A Python Library for the Implementation of Discretized Multi-Dimensional Fourier Transforms [0.0]
  We present FFTArray, a Python library that automates the general discretization of Fourier transforms.<n>Built on the Python Array API Standard, FFTArray integrates seamlessly with array backends like NumPy, JAX and PyTorch.
  arXiv  Detail & Related papers  (2025-07-17T17:05:39Z)
• PyHySCO: GPU-Enabled Susceptibility Artifact Distortion Correction in Seconds [1.831735742288489]
  We introduce PyHySCO, a user-friendly EPI distortion correction tool implemented in PyTorch that enables multi-threading and efficient use of graphics processing units (GPUs) PyHySCO uses time-tested physical distortion model and mathematical formulation and is, therefore, reliable without training. Our extensive validation using 3T and 7T data from the Human Connectome Project suggests PyHySCO achieves accuracy comparable to that of leading RGP tools at a fraction of the cost.
  arXiv  Detail & Related papers  (2024-03-15T21:49:13Z)
• UncertaintyPlayground: A Fast and Simplified Python Library for Uncertainty Estimation [0.0]
  UncertaintyPlayground is a Python library built on PyTorch and GPyTorch for uncertainty estimation in supervised learning tasks. The library offers fast training for Gaussian and multi-modal outcome distributions. It can visualize the prediction intervals of one or more instances.
  arXiv  Detail & Related papers  (2023-10-23T18:36:54Z)
• Stochastic Gradient Descent without Full Data Shuffle [65.97105896033815]
  CorgiPile is a hierarchical data shuffling strategy that avoids a full data shuffle while maintaining comparable convergence rate of SGD as if a full shuffle were performed. Our results show that CorgiPile can achieve comparable convergence rate with the full shuffle based SGD for both deep learning and generalized linear models.
  arXiv  Detail & Related papers  (2022-06-12T20:04:31Z)
• Focal Sparse Convolutional Networks for 3D Object Detection [121.45950754511021]
  We introduce two new modules to enhance the capability of Sparse CNNs. They are focal sparse convolution (Focals Conv) and its multi-modal variant of focal sparse convolution with fusion. For the first time, we show that spatially learnable sparsity in sparse convolution is essential for sophisticated 3D object detection.
  arXiv  Detail & Related papers  (2022-04-26T17:34:10Z)
• Mesh Convolution with Continuous Filters for 3D Surface Parsing [101.25796935464648]
  We propose a series of modular operations for effective geometric feature learning from 3D triangle meshes. Our mesh convolutions exploit spherical harmonics as orthonormal bases to create continuous convolutional filters. We further contribute a novel hierarchical neural network for perceptual parsing of 3D surfaces, named PicassoNet++.
  arXiv  Detail & Related papers  (2021-12-03T09:16:49Z)
• Tangent Space Backpropagation for 3D Transformation Groups [71.41252518419486]
  3D transformation groups are widely used in 3D vision and robotics. Standard backpropagation approach, which embeds 3D transformations in Euclidean spaces, suffers from numerical difficulties. We introduce a new library, which exploits the group structure of 3D transformations.
  arXiv  Detail & Related papers  (2021-03-22T17:33:30Z)
• DFTpy: An efficient and object-oriented platform for orbital-free DFT simulations [55.41644538483948]
  In this work, we present DFTpy, an open source software implementing OFDFT written entirely in Python 3. We showcase the electronic structure of a million-atom system of aluminum metal which was computed on a single CPU. DFTpy is released under the MIT license.
  arXiv  Detail & Related papers  (2020-02-07T19:07:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.