用单张图生成任意视角3D汽车，解决多视角几何不一致问题。
3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis
- 先合成固定视角图像，再用扩散模型生成任意视角一致图像。
- 在真实和合成数据集上实现高几何一致性与重建保真度。
- 适合自动驾驶仿真、3D资产生成等需要高质量3D车辆的场景。
高质量3D车辆资产对自动驾驶仿真至关重要。尽管基于多视角扩散模型的方法能实现可控单图重建，但通常视角有限且存在跨视角几何不一致，降低了真实场景下的重建精度。本文提出3DCarGen，一种可扩展的单图3D汽车生成框架，通过合成任意数量的3D一致多视角图像来应对真实图像。给定单张输入图像，首先合成一组固定视角图像，再输入前馈重建模型，生成基于3D高斯溅射的粗略3D表示。在此显式3D先验条件下，多视角扩散模型生成任意相机视角下的一致图像。进一步通过引入颜色-法线联合优化，加速网格重建算法，从密集合成视图中恢复细节丰富且连贯的3D车辆模型。在合成与真实世界数据集上的大量实验表明，本方法相比现有方法在几何一致性与重建保真度方面表现更优。
原文摘要 · Abstract (English)
High-quality 3D vehicle assets are essential for autonomous driving simulation. Although multi-view diffusion-based paradigms enable controllable single-image reconstruction, they typically produce limited viewpoints and exhibit cross-view geometric inconsistencies, thereby reducing reconstruction fidelity in real-world scenarios. In this work, we introduce 3DCarGen, a scalable single-view 3D car generation framework designed for real-world images by synthesizing an arbitrary number of 3D-consistent multi-view images. Specifically, given a single image as input, we first synthesize a set of images from fixed viewpoints. These images are then fed into a feed-forward reconstruction model, resulting in a coarse 3D representation based on 3D Gaussian Splatting. Conditioned on this explicit 3D prior, our multi-view diffusion model generates 3D-consistent images from arbitrary camera viewpoints. We further extend a fast mesh reconstruction algorithm by incorporating color-normal joint optimization to recover detailed and coherent 3D vehicle models from the synthesized dense views. Extensive experiments on synthetic and real-world datasets demonstrate that our approach achieves robust geometric consistency and reconstruction fidelity compared to existing methods. Project page: https://honglixiao.github.io/3dcargen.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。