Sense–Assess–eXplain (SAX): Building trust in autonomous vehicles in challenging real-world driving scenarios
M Gadd, D De Martini, L Marchegiani… - 2020 IEEE Intelligent …, 2020 - ieeexplore.ieee.org
This paper discusses ongoing work in demonstrating research in mobile autonomy in
challenging driving scenarios. In our approach, we address fundamental technical issues to …
challenging driving scenarios. In our approach, we address fundamental technical issues to …
Joint feature modulation mechanism for driving scene image synthesis by instance texture edge and spatial depth priors
Y Xie, H Qin, G Chen, J Yang, B Feng - International Journal of Machine …, 2024 - Springer
In this paper, we study Conditional Image Synthesis (CIS) task towards producing
photorealistic driving scenes, which plays a significant role in designing perception …
photorealistic driving scenes, which plays a significant role in designing perception …
NeuralFloors: Conditional street-level scene generation from BEV semantic maps via Neural Fields
Semantic Bird's Eye View (BEV) representations are a popular format, being easily
interpretable and editable. However, synthesising ground-view images from BEVs is a …
interpretable and editable. However, synthesising ground-view images from BEVs is a …
NeuralFloors++: Consistent Street-Level Scene Generation From BEV Semantic Maps
Learning autonomous driving capabilities requires diverse and realistic training data. This
has led to exploring generative techniques as an alternative to real-world data collection. In …
has led to exploring generative techniques as an alternative to real-world data collection. In …
CERES: Critical-Event Reconstruction via Temporal Scene Graph Completion
This paper proposes a method for on-demand scenario generation in simulation, grounded
on real-world data. Evaluating the behaviour of Autonomous Vehicles (AVs) in both safety …
on real-world data. Evaluating the behaviour of Autonomous Vehicles (AVs) in both safety …
Day-to-Night Image Translation with Local Controllable Vehicle Light Effect for Data Synthesis in Autonomous Driving
W Shi, C Meng, T Wang, K Gu, S Zhang, J Mei - 2023 - sae.org
In the field of autonomous driving, in order to guaranteerobust perception performance at
night and to reduce cost of data collection and annotation, there are many day-tonight image …
night and to reduce cost of data collection and annotation, there are many day-tonight image …
Improving quality and controllability in GAN-based image synthesis
E Schönfeld - 2022 - publikationen.sulb.uni-saarland.de
The goal of the field of deep learning-based image generation is to synthesize images that
are indistinguishable from real ones, and to precisely control the content of these images …
are indistinguishable from real ones, and to precisely control the content of these images …