MultiEditor: Controllable Multimodal Object Editing for Driving Scenarios Using 3D Gaussian Splatting Priors
This addresses a safety-critical data scarcity problem for autonomous driving systems, representing a novel method for a known bottleneck.
The paper tackles the problem of limited generalization in autonomous driving perception due to rare vehicle categories by proposing MultiEditor, a dual-branch latent diffusion framework that jointly edits images and LiDAR point clouds using 3D Gaussian Splatting priors, resulting in enhanced detection accuracy for underrepresented classes.
Autonomous driving systems rely heavily on multimodal perception data to understand complex environments. However, the long-tailed distribution of real-world data hinders generalization, especially for rare but safety-critical vehicle categories. To address this challenge, we propose MultiEditor, a dual-branch latent diffusion framework designed to edit images and LiDAR point clouds in driving scenarios jointly. At the core of our approach is introducing 3D Gaussian Splatting (3DGS) as a structural and appearance prior for target objects. Leveraging this prior, we design a multi-level appearance control mechanism--comprising pixel-level pasting, semantic-level guidance, and multi-branch refinement--to achieve high-fidelity reconstruction across modalities. We further propose a depth-guided deformable cross-modality condition module that adaptively enables mutual guidance between modalities using 3DGS-rendered depth, significantly enhancing cross-modality consistency. Extensive experiments demonstrate that MultiEditor achieves superior performance in visual and geometric fidelity, editing controllability, and cross-modality consistency. Furthermore, generating rare-category vehicle data with MultiEditor substantially enhances the detection accuracy of perception models on underrepresented classes.