FlashReg: GPU-Accelerated 3-Clique Point Cloud Registration for Real-Time Correspondence-to-Pose Estimation

• URL: http://arxiv.org/abs/2608.21804v1
• Date: Sat, 22 Aug 2026 06:53:42 GMT
• Title: FlashReg: GPU-Accelerated 3-Clique Point Cloud Registration for Real-Time Correspondence-to-Pose Estimation
• Abstract summary: FlashReg is a GPU-oriented correspondence-to-pose estimator for point cloud registration.<n>Its construction builds a capacity-bounded sparse second-order graph directly from the binary first-order graph.<n>It reduces correspondence-to-pose latency by 2--3x relative to TurboReg at comparable registration recall.
• Score: 7.454629583409613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph-based point cloud registration achieves high robustness by identifying geometrically consistent correspondence sets, but constructing second-order compatibility graphs and enumerating candidate cliques remain compute- and memory-intensive. This work presents FlashReg, a GPU-oriented correspondence-to-pose estimator that avoids materializing the dense scored second-order graph. Its Fast First- and Second-Order Graph (FFSOG) construction builds a capacity-bounded sparse second-order graph directly from the binary first-order graph. A dataflow-optimized three-node clique (3-clique) search then selects pivots from compact per-row candidate pools and enumerates triples through sorted sparse-neighborhood intersections. Across indoor and outdoor benchmarks, FlashReg reduces correspondence-to-pose latency by 2--3x relative to TurboReg at comparable registration recall, while using about 50% of its peak allocated tensor memory on an embedded GPU. These results make FlashReg suitable as a high-throughput registration backend within onboard perception pipelines.

Related papers

• Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs [26.54962387458329]
  Image-to-point-cloud (I2P) registration aims to align 2D images with 3D point clouds by establishing reliable 2D-3D correspondences.<n>We propose a heterogeneous graph embedded I2P registration method, termed Hg-I2P.<n> Experiments on six indoor and outdoor benchmarks under cross-domain setups demonstrate that Hg-I2P significantly outperforms existing methods in both generalization and accuracy.
  arXiv  Detail & Related papers  (2026-03-30T02:45:27Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [79.75818239774952]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• LiDAR Loop Closure Detection using Semantic Graphs with Graph Attention Networks [12.33137981696787]
  We propose a novel loop closure detection algorithm that uses graph attention neural networks to encode semantic graphs.<n>We then use semantic registration to estimate the 6 DoF relative pose constraint.<n>For the benefit of the community, we open-source the complete implementation of our proposed algorithm.
  arXiv  Detail & Related papers  (2025-01-31T18:36:04Z)
• FastMAC: Stochastic Spectral Sampling of Correspondence Graph [55.75524096647733]
  We present the first study that introduces graph signal processing into the domain of correspondence graph. We exploit the generalized degree signal on correspondence graph and pursue sampling strategies that preserve high-frequency components. As an application, we build a complete 3D registration algorithm termed FastMAC, that reaches real-time speed.
  arXiv  Detail & Related papers  (2024-03-13T17:59:56Z)
• An FPGA-Based Accelerator for Graph Embedding using Sequential Training Algorithm [0.8403582577557918]
  We propose to combine an online sequential training algorithm with node2vec to handle the changes of graph structures after the deployment. The proposed FPGA implementation achieves up to 205.25 times speedup compared to the original model on ARM Cortex-A53 CPU.
  arXiv  Detail & Related papers  (2023-12-23T02:24:59Z)
• ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models [77.84408427496025]
  State-of-the-art 3D point cloud registration methods rely on labeled 3D datasets for training.<n>We introduce ZeroReg, a zero-shot registration approach that utilizes 2D foundation models to predict 3D correspondences.
  arXiv  Detail & Related papers  (2023-12-05T11:33:16Z)
• 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)
• Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version) [13.286247750893681]
  3D point cloud registration is a fundamental problem in computer vision and robotics. We propose a novel deep graph matching-based framework for point cloud registration.
  arXiv  Detail & Related papers  (2022-11-09T06:05:25Z)
• Sketch-Based Anomaly Detection in Streaming Graphs [89.52200264469364]
  Given a stream of graph edges from a dynamic graph, how can we assign anomaly scores to edges and subgraphs in an online manner? Our method is the first streaming approach that incorporates dense subgraph search to detect graph anomalies in constant memory and time.
  arXiv  Detail & Related papers  (2021-06-08T16:10:36Z)
• Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking [79.80401607146987]
  Existing object tracking usually learns a bounding-box based template to match visual targets across frames, which cannot accurately learn a pixel-wise representation. This paper presents a novel segmentation-based tracking architecture, which is equipped with a local-temporal memory network to learn accurate-temporal correspondence.
  arXiv  Detail & Related papers  (2020-09-21T08:12:02Z)
• Accelerating Graph Sampling for Graph Machine Learning using GPUs [2.9383911860380127]
  NextDoor is a system designed to perform graph sampling on GPU resources. NextDoor employs a new approach to graph sampling that we call transit-parallelism. We implement several graph sampling applications, and show that NextDoor runs them orders of magnitude faster than existing systems.
  arXiv  Detail & Related papers  (2020-09-14T19:03:33Z)

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.