PySIFT: GPU-Resident Deterministic SIFT for Deep Learning Vision Pipelines

• URL: http://arxiv.org/abs/2605.17869v1
• Date: Mon, 18 May 2026 05:24:55 GMT
• Title: PySIFT: GPU-Resident Deterministic SIFT for Deep Learning Vision Pipelines
• Abstract summary: We show that classical SIFT with DSP multi-scale pooling outperforms neural descriptor and orientation replacements.<n>We present PySIFT, the first fully GPU-resident SIFT, implemented in CuPy/Numba kernels with DLPack zero-copy handoff to downstream DL frameworks.
• Score: 0.22940141855172033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A widespread assumption in local feature research holds that classical handcrafted descriptors are accuracy-limited relics best replaced by learned alternatives. We show this is wrong. Through an 8-configuration ablation spanning four benchmarks (HPatches, ROxford5K, IMC Phototourism, MegaDepth), we demonstrate that classical SIFT with DSP multi-scale pooling outperforms neural descriptor and orientation replacements (HardNet, OriNet) on every accuracy metric--while running 2--18$\times$ faster--and that learned matchers (LightGlue) complement rather than supersede classical features. The conclusion reframes a decade of work: not "replace SIFT" but "compose with SIFT," classical extraction paired with learned matching only where geometric context demands it. This finding was invisible because no prior GPU SIFT kept the complete pipeline in VRAM or offered modularity for controlled classical-vs-learned ablations. We present PySIFT, the first fully GPU-resident SIFT, implemented in CuPy/Numba CUDA kernels with DLPack zero-copy handoff to downstream DL frameworks--submillisecond O(1) metadata swap regardless of keypoint count. On a laptop-grade NVIDIA RTX 3050 (4 GB VRAM), PySIFT achieves: (i) higher Mean Matching Accuracy (MMA) than OpenCV SIFT on HPatches, (ii) 383 ms faster per pair on high-resolution MegaDepth, (iii) higher geometric accuracy on cross-dataset benchmarks (+5.6 pp AUC@10${}^\circ$ on MegaDepth, more inliers on IMC Phototourism), and (iv) bitwise deterministic output--identical keypoints and descriptors across runs, with detection reproducing identically even across GPU architectures: a guarantee that learned extractors cannot match without significant performance sacrifice, and cannot achieve at all across GPU architectures due to cuDNN's architecture-dependent algorithm selection. PySIFT is open-source, requiring no C++ compilation.

Related papers

• Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices [18.428868416628017]
  This paper proposes an efficient inference method for large language models (LLMs) with moderate sparsity.<n>It achieves up to 1.64x-level speedup over SpInfer and up to 1.41x end-to-end speedups over FlashLLM.
  arXiv  Detail & Related papers  (2026-06-13T13:38:27Z)
• ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning [58.54940026861599]
  textscChunkFT is a memory-efficient fine-tuning framework.<n>textscChunkFT enables gradient computation for arbitrary sub-tensors without modifying the network architecture.<n>textscChunkFT consistently outperforms existing memory-efficient baselines.
  arXiv  Detail & Related papers  (2026-05-20T13:44:44Z)
• GPU-Accelerated Quantum Simulation: Empirical Backend Selection, Gate Fusion, and Adaptive Precision [0.0]
  This paper presents a GPU-accelerated quantum circuit simulation framework.<n>An empirical backend selection algorithm benchmarks CuPy, PyTorchCUDA, and NumPy CPU backends at runtime.<n>A gate fusion engine reduces circuit depth through automated identification of gate sequences.<n>A fallback mechanism monitors GPU memory consumption and gracefully degrades to memory execution when resources are exhausted.
  arXiv  Detail & Related papers  (2026-04-04T17:46:37Z)
• Resource-Efficient Iterative LLM-Based NAS with Feedback Memory [49.44875022114861]
  Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources.<n>We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures.
  arXiv  Detail & Related papers  (2026-03-12T16:00:22Z)
• Scalable GPU-Accelerated Euler Characteristic Curves: Optimization and Differentiable Learning for PyTorch [0.0]
  We present optimized GPU kernels for the Euler Characteristic Curve (ECC) achieving 16-2000"O speedups over prior GPU implementations on synthetic grids.<n>We introduce a differentiable PyTorch layer enabling end-to-end learning.
  arXiv  Detail & Related papers  (2025-10-23T06:59:07Z)
• A Parallel CPU-GPU Framework for Cost-Bounded DFS with Applications to IDA* and BTS [13.186524200050957]
  We introduce a method for GPU computations in depth first search.<n>This is used to create algorithms like emphsynchronous IDA*, an extension of the Iterative Deepening A* (IDA*) algorithm.<n>We evaluate the approach on the 3x3's Rubik Cube and 4x4 sliding tile puzzle (STP), showing that GPU operations can be efficiently batched in DFS.
  arXiv  Detail & Related papers  (2025-07-16T05:07:33Z)
• NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding [54.88765757043535]
  This work rethinks data structures for statistical n-gram language models to enable fast and parallel operations for GPU-optimized inference.<n>Our approach, named NGPU-LM, introduces customizable greedy decoding for all major ASR model types with less than 7% computational overhead.<n>The proposed approach can eliminate more than 50% of the accuracy gap between greedy and beam search for out-of-domain scenarios while avoiding significant slowdown caused by beam search.
  arXiv  Detail & Related papers  (2025-05-28T20:43:10Z)
• INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing [66.00729477511219]
  Given a function represented as a computation graph, traditional architectures face challenges in efficiently computing its nth-order gradient. We introduce INR-Arch, a framework that transforms the computation graph of an nth-order gradient into a hardware-optimized dataflow architecture. We present results that demonstrate 1.8-4.8x and 1.5-3.6x speedup compared to CPU and GPU baselines respectively.
  arXiv  Detail & Related papers  (2023-08-11T04:24:39Z)
• EAutoDet: Efficient Architecture Search for Object Detection [110.99532343155073]
  EAutoDet framework can discover practical backbone and FPN architectures for object detection in 1.4 GPU-days. We propose a kernel reusing technique by sharing the weights of candidate operations on one edge and consolidating them into one convolution. In particular, the discovered architectures surpass state-of-the-art object detection NAS methods and achieve 40.1 mAP with 120 FPS and 49.2 mAP with 41.3 FPS on COCO test-dev set.
  arXiv  Detail & Related papers  (2022-03-21T05:56:12Z)
• GPU optimization of the 3D Scale-invariant Feature Transform Algorithm and a Novel BRIEF-inspired 3D Fast Descriptor [5.1537294207900715]
  This work details a highly efficient implementation of the 3D scale-invariant feature transform (SIFT) algorithm, for the purpose of machine learning from large sets of medical image data. The primary operations of the 3D SIFT code are implemented on a graphics processing unit (GPU), including convolution, sub-sampling, and 4D peak detection from scale-space pyramids. The performance improvements are quantified in keypoint detection and image-to-image matching experiments, using 3D MRI human brain volumes of different people.
  arXiv  Detail & Related papers  (2021-12-19T20:56:40Z)
• GhostSR: Learning Ghost Features for Efficient Image Super-Resolution [49.393251361038025]
  Single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs. We propose to use shift operation to generate the redundant features (i.e., Ghost features) of SISR models. We show that both the non-compact and lightweight SISR models embedded in our proposed module can achieve comparable performance to that of their baselines.
  arXiv  Detail & Related papers  (2021-01-21T10:09:47Z)
• 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.