# CrossLiDAR: Controllable Multi-Sensor LiDAR Sequence Generation

DevFeed: [CrossLiDAR: Controllable Multi-Sensor LiDAR Sequence Generation](<https://devfeed.tech/articles/crosslidar-controllable-multi-sensor-lidar-sequence-generation-126073.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11131>)

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

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [diffusion-transformers](<https://devfeed.tech/topics/diffusion-transformers.md>), [autonomous vehicles](<https://devfeed.tech/topics/autonomous-vehicles.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [autonomous-systems](<https://devfeed.tech/tags/autonomous-systems.md>), [coherence](<https://devfeed.tech/tags/coherence.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [development](<https://devfeed.tech/tags/development.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [driving](<https://devfeed.tech/tags/driving.md>), [flow](<https://devfeed.tech/tags/flow.md>), [frame](<https://devfeed.tech/tags/frame.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generators](<https://devfeed.tech/tags/generators.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [lidar](<https://devfeed.tech/tags/lidar.md>), [sensor](<https://devfeed.tech/tags/sensor.md>), [sequence](<https://devfeed.tech/tags/sequence.md>)

## AI overview

CrossLiDAR generates controllable, temporally consistent LiDAR sequences across multiple sensor configurations, addressing limited structural control and long-horizon drift in existing generators. It uses a rectified-flow objective with an MM-DiT backbone in a range-image latent space. An Inter-sensor Module connects sensor streams, while a ControlNet-style branch accepts structural inputs such as BEV priors or 3D bounding boxes. The model generates short N-frame sequences and extends them autoregressively for longer rollouts. On nuScenes and Waymo, the authors report average improvements of 29.56% in JSD and 15.36% in MMD over state-of-the-art baselines.

## Source excerpt

arXiv:2611.11131v1 Announce Type: cross 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 $N$-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.