R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ljungbergh, William, Taveira, Bernardo, Zheng, Wenzhao, Tonderski, Adam, Peng, Chensheng, Kahl, Fredrik, Petersson, Christoffer, Felsberg, Michael, Keutzer, Kurt, Tomizuka, Masayoshi, Zhan, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917418777968640
author Ljungbergh, William
Taveira, Bernardo
Zheng, Wenzhao
Tonderski, Adam
Peng, Chensheng
Kahl, Fredrik
Petersson, Christoffer
Felsberg, Michael
Keutzer, Kurt
Tomizuka, Masayoshi
Zhan, Wei
author_facet Ljungbergh, William
Taveira, Bernardo
Zheng, Wenzhao
Tonderski, Adam
Peng, Chensheng
Kahl, Fredrik
Petersson, Christoffer
Felsberg, Michael
Keutzer, Kurt
Tomizuka, Masayoshi
Zhan, Wei
contents Validating autonomous driving (AD) systems requires diverse and safety-critical testing, making photorealistic virtual environments essential. Traditional simulation platforms, while controllable, are resource-intensive to scale and often suffer from a domain gap with real-world data. In contrast, neural reconstruction methods like 3D Gaussian Splatting (3DGS) offer a scalable solution for creating photorealistic digital twins of real-world driving scenes. However, they struggle with dynamic object manipulation and reusability as their per-scene optimization-based methodology tends to result in incomplete object models with integrated illumination effects. This paper introduces R3D2, a lightweight, one-step diffusion model designed to overcome these limitations and enable realistic insertion of complete 3D assets into existing scenes by generating plausible rendering effects-such as shadows and consistent lighting-in real time. This is achieved by training R3D2 on a novel dataset: 3DGS object assets are generated from in-the-wild AD data using an image-conditioned 3D generative model, and then synthetically placed into neural rendering-based virtual environments, allowing R3D2 to learn realistic integration. Quantitative and qualitative evaluations demonstrate that R3D2 significantly enhances the realism of inserted assets, enabling use-cases like text-to-3D asset insertion and cross-scene/dataset object transfer, allowing for true scalability in AD validation. To promote further research in scalable and realistic AD simulation, we release our code, see https://research.zenseact.com/publications/R3D2/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
Ljungbergh, William
Taveira, Bernardo
Zheng, Wenzhao
Tonderski, Adam
Peng, Chensheng
Kahl, Fredrik
Petersson, Christoffer
Felsberg, Michael
Keutzer, Kurt
Tomizuka, Masayoshi
Zhan, Wei
Computer Vision and Pattern Recognition
Machine Learning
Robotics
Validating autonomous driving (AD) systems requires diverse and safety-critical testing, making photorealistic virtual environments essential. Traditional simulation platforms, while controllable, are resource-intensive to scale and often suffer from a domain gap with real-world data. In contrast, neural reconstruction methods like 3D Gaussian Splatting (3DGS) offer a scalable solution for creating photorealistic digital twins of real-world driving scenes. However, they struggle with dynamic object manipulation and reusability as their per-scene optimization-based methodology tends to result in incomplete object models with integrated illumination effects. This paper introduces R3D2, a lightweight, one-step diffusion model designed to overcome these limitations and enable realistic insertion of complete 3D assets into existing scenes by generating plausible rendering effects-such as shadows and consistent lighting-in real time. This is achieved by training R3D2 on a novel dataset: 3DGS object assets are generated from in-the-wild AD data using an image-conditioned 3D generative model, and then synthetically placed into neural rendering-based virtual environments, allowing R3D2 to learn realistic integration. Quantitative and qualitative evaluations demonstrate that R3D2 significantly enhances the realism of inserted assets, enabling use-cases like text-to-3D asset insertion and cross-scene/dataset object transfer, allowing for true scalability in AD validation. To promote further research in scalable and realistic AD simulation, we release our code, see https://research.zenseact.com/publications/R3D2/.
title R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
topic Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2506.07826