Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images

TL;DR

Unposed-to-3D is a novel framework that reconstructs realistic, pose-consistent, and harmonized 3D vehicle models from real-world images using image-only supervision, advancing simulation asset creation.

Contribution

It introduces a two-stage learning approach that removes the need for posed images, enabling scalable 3D vehicle reconstruction from unposed real-world images.

Findings

Successfully reconstructs realistic 3D vehicles from real-world images.

Produces pose-consistent and harmonized models suitable for simulation.

Demonstrates effectiveness through extensive experiments.

Abstract

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.