Search papers, labs, and topics across Lattice.
This paper introduces a generative framework for synthesizing animatable 3D Gaussian vehicle models from single or multi-view images, addressing the limitations of current rigid-body vehicle simulations used in autonomous driving. The method incorporates a part-edge refinement module to ensure clear separation between vehicle parts represented by 3D Gaussians and a kinematic reasoning head to predict joint positions and hinge axes. By jointly optimizing for part segmentation and kinematic parameters, the framework generates realistic, animatable vehicle models suitable for advanced autonomous driving simulations.
Animatable 3D vehicle models can now be generated from single images, enabling more realistic autonomous driving simulations that capture part-level articulation like wheel steering and door opening.
Simulation is essential for autonomous driving, yet current frameworks often model vehicles as rigid assets and fail to capture part-level articulation. With perception algorithms increasingly leveraging dynamics such as wheel steering or door opening, realistic simulation requires animatable vehicle representations. Existing CAD-based pipelines are limited by library coverage and fixed templates, preventing faithful reconstruction of in-the-wild instances. We propose a generative framework that, from a single image or sparse multi-view input, synthesizes an animatable 3D Gaussian vehicle. Our method addresses two challenges: (i) large 3D asset generators are optimized for static quality but not articulation, leading to distortions at part boundaries when animated; and (ii) segmentation alone cannot provide the kinematic parameters required for motion. To overcome this, we introduce a part-edge refinement module that enforces exclusive Gaussian ownership and a kinematic reasoning head that predicts joint positions and hinge axes of movable parts. Together, these components enable faithful part-aware simulation, bridging the gap between static generation and animatable vehicle models.