To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

In unsupervised domain adaptation (UDA), a model trained on source data (eg synthetic) is
adapted to target data (eg real-world) without access to target annotation. Most previous …

Modern perception systems of autonomous vehicles are known to be sensitive to occlusions
and lack the capability of long perceiving range. It has been one of the key bottlenecks that …

We investigate the potential of learning visual representations using synthetic images
generated by text-to-image models. This is a natural question in the light of the excellent …

Abstract We present Block-NeRF, a variant of Neural Radiance Fields that can represent
large-scale environments. Specifically, we demonstrate that when scaling NeRF to render …

Autonomous driving faces great safety challenges for a lack of global perspective and the
limitation of long-range perception capabilities. It has been widely agreed that vehicle …

As acquiring pixel-wise annotations of real-world images for semantic segmentation is a
costly process, a model can instead be trained with more accessible synthetic data and …

How should we integrate representations from complementary sensors for autonomous
driving? Geometry-based fusion has shown promise for perception (eg, object detection …

For the last few decades, several major subfields of artificial intelligence including computer
vision, graphics, and robotics have progressed largely independently from each other …