Roadside camera-driven 3D object detection is a crucial task in intelligent transportation
systems, which extends the perception range beyond the limitations of vision-centric …

Abstract Panoramic images, capturing a 360\(^\circ\) field of view (FoV), encompass
omnidirectional spatial information crucial for scene understanding. However, it is not only …

We present a novel holistic deep-learning approach for multi-task learning from a single
indoor panoramic image. Our framework named MultiPanoWise extends vision transformers …

This paper aims at achieving fine-grained building attribute segmentation in a cross-view
scenario ie using satellite and street-view image pairs. The main challenge lies in …

This survey provides a comprehensive evaluation of various deep learning-based
segmentation architectures. It covers a wide range of models, from traditional ones like FCN …

Street-to-satellite image synthesis focuses on generating realistic satellite images from
corresponding ground street-view images while maintaining a consistent content layout …

Panoramic images can broaden the Field of View (FoV), occlusion-aware prediction can
deepen the understanding of the scene, and domain adaptation can transfer across viewing …

In the field of autonomous driving, Bird's-Eye-View (BEV) perception has attracted
increasing attention in the community since it provides more comprehensive information …

Scene understanding–a process of parsing visual perception of surrounding environment
into human-readable information–can be processed via pixel-wise image semantic …