Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending
and drawing extensive attention both from industry and academia. Conventional …

The grid-centric perception is a crucial field for mobile robot perception and navigation.
Nonetheless, the grid-centric perception is less prevalent than object-centric perception as …

In this paper, we propose a long-sequence modeling framework, named StreamPETR, for
multi-view 3D object detection. Built upon the sparse query design in the PETR series, we …

We present a novel bird's-eye-view (BEV) detector with perspective supervision, which
converges faster and better suits modern image backbones. Existing state-of-the-art BEV …

In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view
images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which …

Restricted by the ability of depth perception, all Multi-view 3D object detection methods fall
into the bottleneck of depth accuracy. By constructing temporal stereo, depth estimation is …

In recent years, vision-centric Bird's Eye View (BEV) perception has garnered significant
interest from both industry and academia due to its inherent advantages, such as providing …

In contrast to extensive studies on general vision pre-training for scalable visual
autonomous driving remains seldom explored. Visual autonomous driving applications …

3D object detection from multiple image views is a fundamental and challenging task for
visual scene understanding. Owing to its low cost and high efficiency, multi-view 3D object …

3D object detection plays a pivotal role in autonomous driving and robotics, demanding
precise interpretation of Bird's Eye View (BEV) images. The dynamic nature of real-world …