Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs
Image synthesis driven by computer graphics achieved recently a remarkable realism, yet synthetic image data generated this way reveals a significant domain gap with respect to real-world data. This is especially true in autonomous driving scenarios, which represent a critical aspect for overcoming utilizing synthetic data for training neural networks. We propose a method based on domain-invariant scene representation to directly synthesize traffic scene imagery without rendering. Specifically, we rely on synthetic scene graphs as our internal representation and introduce an unsupervised neural network architecture for realistic traffic scene synthesis. We enhance synthetic scene graphs with spatial information about the scene and demonstrate the effectiveness of our approach through scene manipulation.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingImage GenerationScene GenerationSimilar Papers 제목 키워드 기반
SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model
The goal of traffic simulation is to augment a potentially limited amount of manually-driven miles that is available for testing and validation, with a much larger amount of simulated synthetic miles. The culmination…
Scene GenerationTraffic Scene Parsing through the TSP6K Dataset
Traffic scene perception in computer vision is a critically important task to achieve intelligent cities. To date, most existing datasets focus on autonomous driving scenes. We observe that the models trained on those dr…
Autonomous DrivingDecoderDomain AdaptationInstance Segmentation+3Object-Centric Dataset Resources for Constrained-Data Image Generation and Augmentation
Object-centric image generation is important in settings with few labeled examples, including pedestrian analysis in smart-city scenes, traffic-sign inspection, and domain-specific object detection. Synthetic images are …
Scene UnderstandingData AugmentationObject DetectionImage GenerationStructured prototype regularization for synthetic-to-real driving scene parsing
Driving scene parsing is critical for autonomous vehicles to operate reliably in complex real-world traffic environments. To reduce the reliance on costly pixel-level annotations, synthetic datasets with automatically ge…
Unsupervised Domain AdaptationAutonomous VehiclesScene ParsingVisual Traffic Knowledge Graph Generation from Scene Images
Although previous works on traffic scene understanding have achieved great success, most of them stop at a lowlevel perception stage, such as road segmentation and lane detection, and few concern high-level understan…
Graph AttentionGraph GenerationKnowledge GraphsLane Detection+3