Memory-Efficient Point Cloud Registration via Overlapping Region Sampling

• URL: http://arxiv.org/abs/2410.21753v1
• Date: Tue, 29 Oct 2024 05:40:03 GMT
• Title: Memory-Efficient Point Cloud Registration via Overlapping Region Sampling
• Abstract summary: Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit memory usage. We propose an overlapping region sampling method to reduce memory usage while maintaining accuracy. Our approach estimates the overlapping region and intensively samples from it, using a k-nearest-neighbor (kNN) based point compression mechanism.
• Score: 0.7806681790324609
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping region sampling method to reduce memory usage while maintaining accuracy. Our approach estimates the overlapping region and intensively samples from it, using a k-nearest-neighbor (kNN) based point compression mechanism with multi layer perceptron (MLP) and transformer architectures. Evaluations on 3DMatch and 3DLoMatch datasets show our method outperforms other sampling methods in registration recall, especially at lower GPU memory levels. For 3DMatch, we achieve 94% recall with 33% reduced memory usage, with greater advantages in 3DLoMatch. Our method enables efficient large-scale point cloud registration in resource-constrained environments, maintaining high accuracy while significantly reducing memory requirements.

Related papers

• Pocket-SLAM: Rendering-Area-Aware Pruning for Memory-Efficient 3DGS-SLAM [7.619292287345112]
  We propose a rendering-area-aware pruning strategy for 3DGS-SLAM.<n>Our method consistently outperforms existing pruning approaches in large-scale outdoor scenes.<n>Results highlight rendering-area-aware pruning as a promising direction for scaling 3DGS-SLAM to real-world autonomous driving scenarios.
  arXiv  Detail & Related papers  (2026-06-23T16:48:58Z)
• GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting [50.2045409672451]
  3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering.<n>It is constrained by the high memory cost due to a huge number of Gaussian points.<n>We propose graph-based spatial distribution optimization for compact 3DGS.
  arXiv  Detail & Related papers  (2026-04-02T10:41:51Z)
• MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation [41.94295877935867]
  MEMFOF is a memory-efficient multi-frame optical flow method.<n>Method requires only 2.09 GB of GPU memory at runtime for 1080p inputs, and 28.5 GB during training.<n>Method ranks first on the Spring benchmark with a 1-pixel (1px) outlier rate of 3.289.
  arXiv  Detail & Related papers  (2025-06-29T09:01:42Z)
• LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering [68.93333348474988]
  We present a novel level-of-detail (LOD) method for 3D Gaussian Splatting on memory-constrained devices.<n>Our approach iteratively selects optimal subsets of Gaussians based on camera distance.<n>Our method achieves state-of-the-art performance on both outdoor (Hierarchical 3DGS) and indoor (Zip-NeRF) datasets.
  arXiv  Detail & Related papers  (2025-05-29T06:50:57Z)
• Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification [50.596077598766975]
  We explore a memory-efficient training strategy for deep speaker embedding learning in resource-constrained scenarios. For activations, we design two types of reversible neural networks which eliminate the need to store intermediate activations. For states, we introduce a dynamic quantization approach that replaces the original 32-bit floating-point values with a dynamic tree-based 8-bit data type.
  arXiv  Detail & Related papers  (2024-12-02T06:57:46Z)
• DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection [42.07920565812081]
  We propose a novel post-training weight pruning scheme for 3D object detection. It determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence. This framework aims to minimize detection distortion of network output to maximally maintain detection precision.
  arXiv  Detail & Related papers  (2024-07-02T09:33:32Z)
• LP-3DGS: Learning to Prune 3D Gaussian Splatting [71.97762528812187]
  We propose learning-to-prune 3DGS, where a trainable binary mask is applied to the importance score that can find optimal pruning ratio automatically. Experiments have shown that LP-3DGS consistently produces a good balance that is both efficient and high quality.
  arXiv  Detail & Related papers  (2024-05-29T05:58:34Z)
• Improved Scene Landmark Detection for Camera Localization [11.56648898250606]
  Method based on scene landmark detection (SLD) was recently proposed to address these limitations. It involves training a convolutional neural network (CNN) to detect a few predetermined, salient, scene-specific 3D points or landmarks. We show that the accuracy gap was due to insufficient model capacity and noisy labels during training.
  arXiv  Detail & Related papers  (2024-01-31T18:59:12Z)
• EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS [40.94643885302646]
  3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Radiance Neural Fields (NeRFs) We present a technique utilizing quantized embeddings to significantly reduce per-point memory storage requirements.
  arXiv  Detail & Related papers  (2023-12-07T18:59:55Z)
• DIPR: Efficient Point Cloud Registration via Dynamic Iteration [4.491867613612359]
  We introduce a novel Efficient Point Cloud Registration via Dynamic It framework, DIPR, that makes the neural network interactively focus on overlapping points based on sparser input points. Our proposed approach achieves superior registration accuracy while significantly reducing computational time and GPU memory consumption compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-05T16:47:46Z)
• Quadric Representations for LiDAR Odometry, Mapping and Localization [93.24140840537912]
  Current LiDAR odometry, mapping and localization methods leverage point-wise representations of 3D scenes. We propose a novel method of describing scenes using quadric surfaces, which are far more compact representations of 3D objects. Our method maintains low latency and memory utility while achieving competitive, and even superior, accuracy.
  arXiv  Detail & Related papers  (2023-04-27T13:52:01Z)
• Memory Replay with Data Compression for Continual Learning [80.95444077825852]
  We propose memory replay with data compression to reduce the storage cost of old training samples. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.
  arXiv  Detail & Related papers  (2022-02-14T10:26:23Z)
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning [72.80896338009579]
  We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs. We propose a generic patch-by-patch inference scheduling, which significantly cuts down the peak memory. We automate the process with neural architecture search to jointly optimize the neural architecture and inference scheduling, leading to MCUNetV2.
  arXiv  Detail & Related papers  (2021-10-28T17:58:45Z)
• Deep Hough Voting for Robust Global Registration [52.40611370293272]
  We present an efficient framework for pairwise registration of real-world 3D scans, leveraging Hough voting in the 6D transformation parameter space. Our method outperforms state-of-the-art methods on 3DMatch and 3DLoMatch benchmarks while achieving comparable performance on KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-09-09T14:38:06Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)

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.