TorchMorph: CUDA-accelerated Morphological Transforms

• URL: http://arxiv.org/abs/2608.24738v1
• Date: Tue, 25 Aug 2026 15:46:45 GMT
• Title: TorchMorph: CUDA-accelerated Morphological Transforms
• Abstract summary: GPU vision libraries built on PyTorch cover a narrow subset of operators.<n>TorchMorph exposes operators covering binary morphology, greyscale morphology and exact and approximate distance transforms.<n> Batched execution reaches up to 1.1e3 times the throughput of scipy.ndimage on greyscale morphology.
• Score: 4.910415354181461
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Morphological transforms are long-standing tools for shape and mask processing, but the de facto reference implementation in the Python ecosystem, i.e. scipy.ndimage, is CPU-only, single-array, and therefore unusable inside a GPU training loop without an expensive device-to-host round trip. GPU vision libraries built on PyTorch cover a narrow subset of these operators, typically restricted to two spatial dimensions and flat structuring elements. We present TorchMorph, a lightweight PyTorch extension that closes this gap. TorchMorph exposes 22 public operators covering binary morphology, greyscale morphology, exact and approximate distance transforms, and entropy-regularised optimal transport, all implemented as fused CUDA kernels that operate directly on (B, C, Spatial...) CUDA tensors with up to eight spatial dimensions. The API deliberately mirrors scipy.ndimage argument-for-argument, including border modes, structuring-element origins and pre-allocated outputs, so that existing pipelines port with a change of import. We describe the layered architecture and the kernel designs behind each operator family. Against single-threaded CPU references, batched execution reaches up to 1.1e3 times the throughput of scipy.ndimage on greyscale morphology and up to 350x on exact Euclidean distance transforms, while the Sinkhorn solver runs up to 42x faster than POT. Binary and chamfer operators reproduce their SciPy counterparts exactly, and every float-valued operator agrees with the CPU reference to within 1.8e-6 absolute error. TorchMorph is released under the MIT licence at https://intcomp.github.io/tm.

Related papers

• A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting [44.78530292755235]
  We present a multi-GPU approach to Gaussian splatting that scales reconstruction to higher resolutions and larger scenes.<n>We propose a PyTorch backend that distributes the parameters and splatting operators across GPUs via unified memory and NVLink.<n>We demonstrate city-scale reconstructions with street-level detail consisting of over 1 billion Gaussian splats, more than 25 times as many as the current state of the art.
  arXiv  Detail & Related papers  (2026-06-09T19:15:39Z)
• Litespark Inference on Consumer CPUs: Custom SIMD Kernels for Ternary Neural Networks [0.00815557531820863]
  Litespark-Inference integrates directly with Hugging-Face, achieving 9.2x faster time-to-first-token, 52x higher throughput, and 14x memory reduction.<n>Our implementation, Litespark-Inference, is pip-installable and integrates directly with Hugging-Face, achieving 9.2x faster time-to-first-token, 52x higher throughput, and 14x memory reduction.
  arXiv  Detail & Related papers  (2026-05-07T16:07:39Z)
• SoftDTW-CUDA-Torch: Memory-Efficient GPU-Accelerated Soft Dynamic Time Warping for PyTorch [11.845589863914851]
  We present softdtw-cuda-torch, an open-source PyTorch library for computing Soft Dynamic Time Warping on GPUs.<n>Our implementation addresses three key limitations of existing GPU implementations of SoftDTW.<n>The library supports arbitrary sequence lengths, full PyTorch autograd integration, and Soft-DTW Barycenter.
  arXiv  Detail & Related papers  (2026-02-19T09:53:03Z)
• scipy.spatial.transform: Differentiable Framework-Agnostic 3D Transformations in Python [49.015684860172975]
  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.
  arXiv  Detail & Related papers  (2025-11-22T18:52:34Z)
• depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers [92.13613958373628]
  textttdepyf is a tool designed to demystify the inner workings of the PyTorch compiler. textttdepyf decompiles bytecode generated by PyTorch back into equivalent source code.
  arXiv  Detail & Related papers  (2024-03-14T16:17:14Z)
• Efficient and Generic 1D Dilated Convolution Layer for Deep Learning [52.899995651639436]
  We introduce our efficient implementation of a generic 1D convolution layer covering a wide range of parameters. It is optimized for x86 CPU architectures, in particular, for architectures containing Intel AVX-512 and AVX-512 BFloat16 instructions. We demonstrate the performance of our optimized 1D convolution layer by utilizing it in the end-to-end neural network training with real genomics datasets.
  arXiv  Detail & Related papers  (2021-04-16T09:54:30Z)
• Hybrid Models for Learning to Branch [81.93868699246214]
  We propose a new hybrid architecture for efficient branching on CPU machines. The proposed architecture combines the expressive power of GNNs with computationally inexpensive multi-layer perceptrons (MLP) for branching.
  arXiv  Detail & Related papers  (2020-06-26T21:03:45Z)
• Kernel Operations on the GPU, with Autodiff, without Memory Overflows [5.669790037378094]
  The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula. KeOps alleviates the major bottleneck of tensor-centric libraries for kernel and geometric applications: memory consumption. KeOps combines optimized C++/CUDA schemes with binders for high-level languages: Python (Numpy and PyTorch), Matlab and R.
  arXiv  Detail & Related papers  (2020-03-27T08:54:10Z)
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning [68.8204255655161]
  We present TorchIO, an open-source Python library to enable efficient loading, preprocessing, augmentation and patch-based sampling of medical images for deep learning. TorchIO follows the style of PyTorch and integrates standard medical image processing libraries to efficiently process images during training of neural networks. It includes a command-line interface which allows users to apply transforms to image files without using Python.
  arXiv  Detail & Related papers  (2020-03-09T13:36:16Z)

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.