Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.19257 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908983358390272 |
|---|---|
| author | Liu, Hongyuan Zou, Bochao Liu, Qiankun Yu, Haochen Mei, Qi Jiang, Jianfei Liu, Chen Bi, Cheng Wang, Zhao Zhang, Xueyang Zhan, Yifei Chen, Jiansheng Ma, Huimin |
| author_facet | Liu, Hongyuan Zou, Bochao Liu, Qiankun Yu, Haochen Mei, Qi Jiang, Jianfei Liu, Chen Bi, Cheng Wang, Zhao Zhang, Xueyang Zhan, Yifei Chen, Jiansheng Ma, Huimin |
| contents | Creating realistic and simulation-ready 3D assets is crucial for autonomous driving research and virtual environment construction. However, existing 3D vehicle generation methods are often trained on synthetic data with significant domain gaps from real-world distributions. The generated models often exhibit arbitrary poses and undefined scales, resulting in poor visual consistency when integrated into driving scenes. In this paper, we present Unposed-to-3D, a novel framework that learns to reconstruct 3D vehicles from real-world driving images using image-only supervision. Our approach consists of two stages. In the first stage, we train an image-to-3D reconstruction network using posed images with known camera parameters. In the second stage, we remove camera supervision and use a camera prediction head that directly estimates the camera parameters from unposed images. The predicted pose is then used for differentiable rendering to provide self-supervised photometric feedback, enabling the model to learn 3D geometry purely from unposed images. To ensure simulation readiness, we further introduce a scale-aware module to predict real-world size information, and a harmonization module that adapts the generated vehicles to the target driving scene with consistent lighting and appearance. Extensive experiments demonstrate that Unposed-to-3D effectively reconstructs realistic, pose-consistent, and harmonized 3D vehicle models from real-world images, providing a scalable path toward creating high-quality assets for driving scene simulation and digital twin environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19257 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images Liu, Hongyuan Zou, Bochao Liu, Qiankun Yu, Haochen Mei, Qi Jiang, Jianfei Liu, Chen Bi, Cheng Wang, Zhao Zhang, Xueyang Zhan, Yifei Chen, Jiansheng Ma, Huimin Computer Vision and Pattern Recognition Creating realistic and simulation-ready 3D assets is crucial for autonomous driving research and virtual environment construction. However, existing 3D vehicle generation methods are often trained on synthetic data with significant domain gaps from real-world distributions. The generated models often exhibit arbitrary poses and undefined scales, resulting in poor visual consistency when integrated into driving scenes. In this paper, we present Unposed-to-3D, a novel framework that learns to reconstruct 3D vehicles from real-world driving images using image-only supervision. Our approach consists of two stages. In the first stage, we train an image-to-3D reconstruction network using posed images with known camera parameters. In the second stage, we remove camera supervision and use a camera prediction head that directly estimates the camera parameters from unposed images. The predicted pose is then used for differentiable rendering to provide self-supervised photometric feedback, enabling the model to learn 3D geometry purely from unposed images. To ensure simulation readiness, we further introduce a scale-aware module to predict real-world size information, and a harmonization module that adapts the generated vehicles to the target driving scene with consistent lighting and appearance. Extensive experiments demonstrate that Unposed-to-3D effectively reconstructs realistic, pose-consistent, and harmonized 3D vehicle models from real-world images, providing a scalable path toward creating high-quality assets for driving scene simulation and digital twin environments. |
| title | Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.19257 |