SAVTrack introduces a selective vote aggregation strategy for 3D single object tracking in LiDAR point clouds. By estimating the reliability of each candidate vote using local seed features and inter‑frame motion context, it removes low‑confidence hypotheses before clustering, thereby reducing noise in proposal formation. The method achieves competitive success and precision on KITTI and nuScenes while operating at 82 FPS and using fewer than one‑sixth of the votes required by dense aggregation.
3D single object tracking (SOT) in LiDAR point clouds is essential for autonomous systems, but remains challenging under sparse and incomplete observations. In such cases, different target points prov...
arXiv:2609.07738v1 Announce Type: cross Abstract: LiDAR-based 3D Single Object Tracking (3D SOT) is critical for robotic perception and navigation and aims to localize dynamic objects across frames i...
arXiv:2506. 22784v2 Announce Type: replace-cross Abstract: Point-pixel registration between LiDAR point clouds and camera images is a fundamental yet challenging task in autonomous driving and robotic perception.
RVLoss introduces a runoff vote mechanism for self‑supervised LiDAR scene flow estimation, addressing motion rigidity by grouping nearest‑neighbor derived motions into dominant flow candidates and selecting the most consistent one through a two‑stage voting process. This approach generates cluster‑wise rigid flows and free‑form flows as pseudo‑labels, enabling seamless integration into existing feedforward architectures. Experiments on the Argoverse2 2026 Challenge demonstrate that models trained with RVLoss outperform baseline self‑supervised methods by 20% and maintain consistent gains across four additional datasets.
TrackCue is a self‑supervised framework that enhances LiDAR scene flow estimation by using dense image‑based point tracking to generate reliable static‑dynamic supervision. It anchors tracking queries to projected LiDAR points, applies a visually consistent motion compensation strategy to isolate true object motion, and lifts image‑space motion cues back to LiDAR points for refined pseudo‑labels. This approach reduces noise from sparse or occluded LiDAR geometry and improves the precision of dynamic pseudo‑labels, leading to better scene flow learning.
The paper presents a method for creating LiDAR-based 3D object detectors that remain accurate under point‑cloud corruptions while meeting strict latency and memory constraints. It achieves robustness by generating corrupted samples that mimic extreme weather and training detectors to focus on hard samples, guided by perturbation sensitivity estimated from an ensemble of seven heterogeneous detectors. Efficiency is improved by narrowing the network and using offline neighborhood‑density measurements to reduce the number of points processed at each sampling stage, resulting in significant gains in AP under corruption and reductions in inference latency and GPU memory usage across multiple datasets and detector architectures.
arXiv:2509. 08421v2 Announce Type: replace-cross Abstract: For multimedia spatial intelligence through time, multi-view multi-object tracking (MVMOT) suffers from persistent challenges in maintaining consistent object identities across different camera views, leading to tracking inaccuracies.
LiDAR-based 3D object detection is a core perception service for autonomous driving, but deployment requires robustness to point-cloud corruption while meeting latency and memory requirements. Existin...
TAPVid-MV is a new benchmark for tracking any point in 3D across multiple synchronized camera views. It comprises 284 sequences, 1,142 calibrated camera streams, and 109,769 point tracks, covering indoor and outdoor domains and derived from various modalities such as depth, LiDAR, SLAM, and simulation. The dataset is visually verified, and evaluation shows that current multi‑view trackers do not consistently outperform monocular trackers, highlighting geometry recovery as a key bottleneck.
TrackEverything is a 3D point tracker that overcomes the trade‑off between sparse long‑horizon tracking and dense short‑clip tracking by representing videos as persistent 3D scene tracks in world coordinates. It introduces voxel‑based de‑duplication at sliding‑window boundaries, a two‑stage refinement process (endpoint refiner and lightweight trajectory refiner), and a 3D WAFT module that replaces memory‑heavy 4D correlation volumes with efficient feature sampling. The method can track all visible points in videos longer than 1000 frames using only 40 GB of GPU memory, outperforming existing dense trackers on short clips and matching sparse trackers on long sequences.
GenTrack3 is an online multi-object tracking framework that blends deterministic tracking-by-detection with stochastic particle-based uncertainty modeling. It introduces a cluster-aware track-to-detection matching strategy to improve scalability and support group tracking, while maintaining a systematic pipeline that tracks identifiers, states, velocities, penalties, and ages. The authors provide reference implementations on GitHub for reproducibility.
arXiv:2607.29237v2 Announce Type: replace Abstract: LiDAR scene flow is the task of estimating point-wise motion from sequential point clouds. It is essential for autonomous driving, as it provides c...