← Back to all news
arXiv Computer Vision By Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang, Junjie Li, Juyong Zhang, Yukang Feng, Jianwen Sun, Songbur Wong, Junqi You, Junchi Yan

LaGen: Towards Autoregressive LiDAR Scene Generation

Read the original on arXiv Computer Vision →

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.

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

HelloWorld: Towards Practical Applications of Generative Driving World Models

HelloWorld is a 2B-parameter driving world model that learns from diverse video data to generate controllable driving scenarios. It uses ego pose, HD maps, and 3D boxes to produce coherent multi‑sensor outputs, including synchronized seven‑camera RGB and conditional LiDAR. The system is designed for efficient repeated inference and is evaluated on visual quality, control fidelity, cross‑view consistency, robustness, and inference speed.

By Fan Lu, Hanshi Wang, Zijing Wang, Quan Feng, Zhi Wang, Shijie Chen, Xianming Zeng, Yujian Zhang, Jiazhe Wang, Xin Zha, Kai Wang, Zhijie Zhao, Lin Zhu, Tianyi Yang, Yucheng Xu, Tao Ji, Haodong Zhang, Zhipeng Zhang, Peixi Peng, Guang Chen, Xingliang Liu, Lei Yang, Jianyun Xu
More like this →
arXiv Computer Vision
Aug 27

Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models

The paper introduces LiDAR‑SAM2, a framework that converts the 2D video foundation model SAM2 into a scalable source of supervision for 4D LiDAR data. By projecting SAM2 video masks into multi‑view LiDAR space and aggregating them temporally, the method automatically generates temporally coherent LiDAR labels without human annotation. Experiments on SemanticKITTI show that these automatically produced semantic and panoptic labels achieve quality close to full human annotation, enabling models trained on them to approach the performance of fully supervised systems.

By Jihun Kim, Hyun-Kurl Jang, Hyemin Yang, Jinnyeong Yang, Hyeokjun Kweon, Kuk-Jin Yoon
computer-vision
More like this →