paper-with-me

Papers

Generating Driving Scenes with Diffusion

2023-05-29 · Ethan Pronovost, Kai Wang, Nick Roy

In this paper we describe a learned method of traffic scene generation designed to simulate the output of the perception system of a self-driving car. In our "Scene Diffusion" system, inspired by latent diffusion, we use a novel combination of diffusion and object detection to directly create realistic and physically plausible arrangements of discrete bounding boxes for agents. We show that our scene generation model is able to adapt to different regions in the US, producing scenarios that capture the intricacies of each region.

📄 PDF Abstract BibTeX arXiv:2305.18452

Code (0)

등록된 구현이 없습니다.

Tasks

object-detectionObject DetectionScene Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Adverse Weather Conditions Augmentation of LiDAR Scenes with Latent Diffusion Models

2025-01-03 · Andrea Matteazzi, Pascal Colling, Michael Arnold, Dietmar Tutsch

LiDAR scenes constitute a fundamental source for several autonomous driving applications. Despite the existence of several datasets, scenes from adverse weather conditions are rarely available. This limits the robustness…

Autonomous Driving

AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion

2024-10-11 · Yuting Xie, Xianda Guo, Cong Wang, Kunhua Liu 외

Safety-critical scenarios are infrequent in natural driving environments but hold significant importance for the training and testing of autonomous driving systems. The prevailing approach involves generating safety-crit…

Autonomous DrivingDiversity

Urban Scene Diffusion through Semantic Occupancy Map

2024-03-18 · Junge Zhang, Qihang Zhang, Li Zhang, Ramana Rao Kompella 외

Generating unbounded 3D scenes is crucial for large-scale scene understanding and simulation. Urban scenes, unlike natural landscapes, consist of various complex man-made objects and structures such as roads, traffic sig…

Image GenerationScene Understanding

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

2024-11-22 · CVPR 2025 1 · Bencheng Liao, Shaoyu Chen, Haoran Yin, Bo Jiang 외

Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for end-to-end autonomous driving i…

Autonomous DrivingDenoisingNavSim

DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion

2025-10-17 · Weijie Wang, Jiagang Zhu, Zeyu Zhang, Xiaofeng Wang 외 arxiv

We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene sy…

Scene GenerationVideo Generation