HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors
For 3D vehicle generation, this work addresses the problem of low geometric fidelity and blurry textures in a training-free manner, offering a practical solution for downstream applications.
HiFiVe is a training-free framework for high-fidelity 3D vehicle generation that jointly enhances texture and geometry by imposing 3D geometric constraints on 2D generative priors. It achieves significant improvements in geometric detail and texture quality over state-of-the-art baselines on synthetic and real-world datasets.
Existing 3D vehicle generation methods often suffer from low geometric fidelity and blurry textures, hindering their downstream applications. While recent works adopt multi-view diffusion models for high-fidelity texture, they are often constrained by fixed viewpoints, limited resolution, and a reliance on costly fine-tuning to achieve cross-view consistency. In this paper, we propose HiFiVe, a training-free framework for high-fidelity vehicle modeling through joint texture and geometry enhancement by imposing 3D geometric constraints to anchor 2D generative priors. Specifically, we propose an auto-regressive texture refinement pipeline that progressively synthesizes high-resolution textures from arbitrary viewpoints. To ensure cross-view consistency, the coarse geometry serves as a synchronization prior, conditioning each generation step on previously synthesized frames via depth-based warping and multi-view texture fusion. Moreover, the inherent symmetry of vehicles is exploited to mitigate error accumulation. Finally, high-frequency surface details are recovered by refining the mesh geometry using normal maps estimated from the enhanced textures. Extensive experiments on synthetic and real-world vehicle datasets demonstrate that our method significantly improves both geometric detail and texture quality compared to state-of-the-art baselines.