X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
This addresses the need for realistic, aligned multi-modality data generation in autonomous driving, though it is an incremental improvement over existing single-modality synthesis methods.
The paper tackles the problem of synthesizing multi-sensor data (LiDAR point clouds and camera images) for driving scenarios by proposing X-DRIVE, a dual-branch latent diffusion model that ensures cross-modality consistency, resulting in high-fidelity synthetic outputs that adhere to input conditions.
Recent advancements have exploited diffusion models for the synthesis of either LiDAR point clouds or camera image data in driving scenarios. Despite their success in modeling single-modality data marginal distribution, there is an under-exploration in the mutual reliance between different modalities to describe complex driving scenes. To fill in this gap, we propose a novel framework, X-DRIVE, to model the joint distribution of point clouds and multi-view images via a dual-branch latent diffusion model architecture. Considering the distinct geometrical spaces of the two modalities, X-DRIVE conditions the synthesis of each modality on the corresponding local regions from the other modality, ensuring better alignment and realism. To further handle the spatial ambiguity during denoising, we design the cross-modality condition module based on epipolar lines to adaptively learn the cross-modality local correspondence. Besides, X-DRIVE allows for controllable generation through multi-level input conditions, including text, bounding box, image, and point clouds. Extensive results demonstrate the high-fidelity synthetic results of X-DRIVE for both point clouds and multi-view images, adhering to input conditions while ensuring reliable cross-modality consistency. Our code will be made publicly available at https://github.com/yichen928/X-Drive.