← Back to all news
arXiv Computer Vision By Yang Wu, Zhaojiang Liu, Qiang Meng, Youquan Liu, Renliang Weng, Jianjun Qian, Jian Yang, Jin Xie

GEM: Generating LiDAR World Model via Deformable Mamba

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 25

M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera--LiDAR Novel View Synthesis

M3GD introduces a multimodal representation that fuses pre‑trained 2D image and 3D LiDAR foundation models for robotic novel view synthesis, avoiding the need for a separate cross‑modal translator. By projecting LiDAR onto the image latent grid and injecting the resulting geometry‑aware packets via a lightweight residual adapter, the method enhances both RGB and depth synthesis on the GrandTour dataset compared to an image‑only baseline. Ablation studies confirm that pixel‑aligned LiDAR content drives the performance gains, and real‑world deployment on a ground robot demonstrates a tunable quality–cost trade‑off.

By Yang Zhou, Jiuhong Xiao, Shizhao Ye, Long Quang, Carlos Nieto-Granda, Giuseppe Loianno
diffusionroboticsmultimodal
More like this →
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).

By Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson
agentsdiffusioncomputer-visionroboticsefficiencymultimodalbenchmarkssafety
More like this →
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).

By Maciej Wozniak, Jesper Ericsson, Hariprasath Govindarajan, Truls Nyberg, Thomas Gustafsson, Patric Jensfelt, Olov Andersson
agentsdiffusioncomputer-visionroboticsefficiencymultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
Oct 15

LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance

arXiv:2610.19786v1 Announce Type: new Abstract: Generating LiDAR point clouds from multi-view camera images is a valuable task with applications in controllable data synthesis, cross-modal simulation...

By Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang, Qifeng Li, Junjie Li, Zirui Wang, Yukang Feng, Yu Hong, Shaofeng Zhang, Wenlong Liao, Tao He, Juyong Zhang, Junchi Yan
diffusionmultimodalbenchmarks
More like this →