MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers

Key points

• Prior outdoor LiDAR registration works are commonly limited by the pair-wise input paradigm, which neglects temporal correlations inherent within streaming sequences.1
• The key observation is that long-term temporal LiDAR sequences can provide rich global contextual information to complete sparse measurements, filter outliers, and address low-overlap problems, thereby boosting registration performance.1
• Specifically, two hybrid memory buffers are designed, including an implicit memory feature buffer and an explicit memory pose buffer, to store and dynamically update pose-related temporal features.1
• Extensive experiments on three outdoor datasets, including KITTI, nuScenes, and Apollo-Southbay, demonstrate state-of-the-art performance of MemReg, surpassing all previous pair-wise methods and also multi-frame SLAM systems.1

Sources (1)

• [1]MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 06:44 PM

  In this paper, we propose a novel multi-frame outdoor point cloud registration network for streaming LiDAR scans enhanced with pose-related memory buffers.

  Prior outdoor LiDAR registration works are commonly limited by the pair-wise input paradigm, which neglects temporal correlations inherent within streaming sequences.

Extractive summary: sentences quoted from the sources.