X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
Yichen Xie, Chenfeng Xu, Chensheng Peng, Shuqi Zhao, Nhat Ho,, Alexander T. Pham, Mingyu Ding, Masayoshi Tomizuka, Wei Zhan

TL;DR
X-DRIVE introduces a dual-branch latent diffusion framework that models joint distributions of LiDAR point clouds and multi-view images, enabling high-fidelity, cross-modality consistent scene synthesis with controllable inputs.
Contribution
It is the first to jointly model point clouds and images with a dual-branch diffusion architecture, incorporating local cross-modality conditioning and spatial correspondence for driving scene synthesis.
Findings
High-fidelity synthetic point clouds and images
Effective cross-modality consistency and realism
Controllable generation with multiple input conditions
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsAutonomous Vehicle Technology and Safety · Time Series Analysis and Forecasting · Data Management and Algorithms
MethodsDiffusion · Latent Diffusion Model
