In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …

In the context of autonomous driving the significance of effective feature learning is widely
acknowledged. While conventional 3D self-supervised pre-training methods have shown …

This review thoroughly examines the role of semantically-aware Neural Radiance Fields
(NeRFs) in visual scene understanding, covering an analysis of over 250 scholarly papers. It …

In the current state of 3D object detection research, the severe scarcity of annotated 3D data,
substantial disparities across different data modalities, and the absence of a unified …

Neural fields excel in computer vision and robotics due to their ability to understand the 3D
visual world such as inferring semantics, geometry, and dynamics. Given the capabilities of …

We present PARQ-a multi-view 3D object detector with transformer and pixel-aligned
recurrent queries. Unlike previous works that use learnable features or only encode 3D point …

In this work, we propose the use of Neural Radiance Fields (NeRF) as a scene
representation for visual localization. Recently, NeRF has been employed to enhance pose …

To advance the state of the art in the creation of 3D foundation models, this paper introduces
the ConDense framework for 3D pre-training utilizing existing pre-trained 2D networks and …

Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations
of monocular vision in depth estimation. This paper introduces CVT-Occ, a novel approach …

Pre-training is crucial in 3D-related fields such as autonomous driving where point cloud
annotation is costly and challenging. Many recent studies on point cloud pre-training …