arXiv Machine Learning
EgoNeMo: Transferable Map of Pedestrian Dynamics via Egocentric LiDAR Scan
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 2
DeepIPCv3: Event-Aware Multi-Modal Sensor Fusion for Sudden Pedestrian Crossing Avoidance
arXiv:2606. 01277v1 Announce Type: cross Abstract: Current end-to-end autonomous driving systems predominantly rely on frame-based sensors, which suffer from inherent perception latency and motion blur during highly dynamic encounters, specifically sudden pedestrian crossings.
arXiv AI
Jul 28
AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Models
arXiv:2603. 28963v2 Announce Type: replace-cross Abstract: Simulation with realistic traffic agents is essential for validating autonomous driving systems.
arXiv Computer Vision
Sep 30
Temporal-Aware Fusion for Robust Outdoor LiDAR Localization
The paper introduces TempLoc, a Temporal‑aware Localization framework that improves outdoor LiDAR relocalization by leveraging spatio‑temporal consistency across scans. It first predicts point‑wise global coordinates with uncertainties, then estimates inter‑frame correspondences using an attention‑based Prior Coordinate Generation module, and finally fuses these predictions in an uncertainty‑guided manner to produce a more accurate global 6‑DoF pose. Experiments on the NCLT and Oxford RobotCar datasets show that TempLoc significantly outperforms existing state‑of‑the‑art methods.
arXiv Computer Vision
Oct 12
MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
MemReg introduces a multi-frame outdoor LiDAR point cloud registration network that leverages hybrid memory buffers to capture temporal correlations in streaming sequences. The system uses an implicit memory feature buffer and an explicit memory pose buffer to store and update pose-related temporal features, while a dynamic history weighting module adaptively fuses current and historical information. Experiments on KITTI, nuScenes, and Apollo-Southbay datasets show MemReg surpasses previous pair-wise methods and multi-frame SLAM systems, and it also performs competitively on indoor datasets such as 3DMatch, 3DLoMatch, and ScanNet.
arXiv Computer Vision
Oct 21
SynCalib: Breaking Dataset Shortcuts in LiDAR-Camera Calibration via Extrinsic-Controllable Synthesis
arXiv:2610.27547v1 Announce Type: new Abstract: Online LiDAR-camera calibration remains a fundamental yet challenging task in the field of robotics. Recently, deep learning-based data-driven approach...
arXiv Computer Vision
Sep 30
PhysWAM: Physically Consistent World Action Model for Autonomous Driving
PhysWAM is a unified world-action model for autonomous driving that jointly denoises multiview video, metric depth, and ego motion using a flow‑matching transformer. It introduces Coupled Point Projection (CPP), a geometric constraint that aligns generated depth points with LiDAR data after applying the predicted SE(3) ego motion, thereby enforcing physical consistency. At inference, trajectory selection uses a simple label‑free consensus rule, and the model demonstrates strong planning performance, zero‑shot transfer to unseen environments, and accurate, temporally coherent depth and video predictions.