arXiv Computer Vision
Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Oct 13
Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors
We present LidarVerse, a real-time unified LiDAR world model for sensor simulation across tasks and sensors. Existing LiDAR simulators largely follow one of two complementary paradigms: reconstruction...
arXiv Computer Vision
Aug 27
LaGen: Towards Autoregressive LiDAR Scene Generation
LaGen is an autoregressive framework that generates long‑horizon LiDAR scenes frame by frame, using a single‑frame input and bounding‑box conditions to produce high‑fidelity 4D scenes. It introduces a scene decoupling estimation module for better object‑level interaction and a noise modulation module to reduce error accumulation over time. Evaluations on the nuScenes dataset show that LaGen outperforms existing methods, especially on later frames.
arXiv Computer Vision
Sep 3
GEM: Generating LiDAR World Model via Deformable Mamba
GEM is a Generative LiDAR world model that uses a deformable Mamba architecture to better handle the disorder of LiDAR point clouds and distinguish dynamic objects from static structures. The model tokenizes LiDAR sweeps, unsupervisedly disentangles dynamic and static features, and applies a tri‑path deformable Mamba for selective scanning and adaptive gating fusion, improving spatial‑temporal understanding. Experiments show GEM outperforms existing methods across multiple benchmarks, and it can be paired with a planner and BEV controller for autonomous rollout and "what‑if" scenario generation.
arXiv AI
Jul 31
FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows
arXiv:2607. 26645v1 Announce Type: cross Abstract: Existing point-based generative methods for outdoor scenes primarily focus on LiDAR-conditioned completion.
arXiv AI
Jun 24
HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
arXiv:2606. 20189v3 Announce Type: replace-cross Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD).
arXiv AI
Jun 19
HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-trainin
arXiv:2606. 20189v1 Announce Type: cross Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data needed to represent the immense geometric and kinematic diversity of real-world autonomous driving (AD).