Code & Data

Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications.

Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on th...

Modern end-to-end driving policies excel in routine scenarios, but their reliability is limited by the scarcity of safety-critical long-tail events in real driving datasets. We ...

Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmar...

Masked Generative Image Transformers (MaskGIT) deliver high-quality images at low inference cost, but their token-unmasking scheduler has received little attention. We analyze M...

The popular CLIP model displays impressive zero-shot capabilities thanks to its seamless interaction with arbitrary text prompts. However, its lack of spatial awareness makes it...