cs.CVNov 8, 2026

CrossLiDAR: Controllable Multi-Sensor LiDAR Sequence Generation

Authors: Khanh Nguyen, Thomas Walker, Hichem Telli, Carlos de la Torre-Ortiz, Stefano Fiorini, Salah Eddine Bekhouche, Mohammed-En-Nadhir Zighem, Wassim Swaileh, 

Organizations: Computer Vision Center, Universitat Aut`onoma de Barcelona, Spain · Independent Researcher · University of the Basque Country, Spain

Abstract

High-fidelity LiDAR simulation remains a bottleneck for scalable development and validation of autonomous systems. Existing generators can synthesize realistic scans, but they are typically constrained to a single sensor configuration, offer limited control over structure and geometry, and drift in long-horizon 4D generation. We present CrossLiDAR, a unified transformer-based framework capable of generating controllable and spatio-temporally consistent multi-sensor LiDAR sequences. Our approach leverages a rectified flow objective with a Multi-Modal Diffusion Transformer (MM-DiT) backbone, within a compact latent space of range images. To support multiple LiDAR sensors, an Inter-sensor Module enables interaction across sensors, while a ControlNet-style branch provides structural conditioning (e.g., BEV priors or 3D bounding boxes). For modeling the temporal consistency, CrossLiDAR generates short NN-frame sequences and extends them autoregressively to improve long-horizon coherence. Our model significantly outperforms state-of-the-art baselines, achieving an average improvement of 29.56% in JSD and 15.36% in MMD evaluated on nuScenes and the Waymo Dataset. CrossLiDAR bridges the gap to modern autonomous-driving simulation by enabling calibration-consistent multi-sensor LiDAR rollouts over long horizons for controllable, scenario-based testing.

Figures & tables

Explore similar work

CardsList
  1. Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors

    Oct 13, 2026Henry Che, Xuanchi Ren, Sanja Fidler +3World ModelsWorld Model Learning

  2. LaGen: Towards Autoregressive LiDAR Scene Generation

    Nov 26, 2025Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang +73D Scene GenerationAutoregressive Generation

  3. OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation

    May 13, 2026Youquan Liu, Weidong Yang, Ao Liang +9Synthetic Data Generation for Robotics3D Scene Generation