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 …

Abstract Neural Radiance Field (NeRF) has emerged as a powerful paradigm for scene
representation, offering high-fidelity renderings and reconstructions from a set of sparse and …

Abstract We address outdoor Neural Radiance Fields (NeRF) with LiDAR maps. Existing
NeRF methods usually require specially collected hypersampled source views and do not …

This letter proposes LONER, the first real-time LiDAR SLAM algorithm that uses a neural
implicit scene representation. Existing implicit mapping methods for LiDAR show promising …

Underwater perception and 3D surface reconstruction are challenging problems with broad
applications in construction, security, marine archaeology, and environmental monitoring …

Learning unsupervised world models for autonomous driving has the potential to improve
the reasoning capabilities of today's systems dramatically. However, most work neglects the …

Recent novel view synthesis methods obtain promising results for relatively small scenes,
eg, indoor environments and scenes with a few objects, but tend to fail for unbounded …

Photorealistic simulation plays a crucial role in applications such as autonomous driving
where advances in neural radiance fields (NeRFs) may allow better scalability through the …

Neural implicit fields have been a de facto standard in novel view synthesis. Recently there
exist some methods exploring fusing multiple modalities within a single field aiming to share …

This paper proposes SAD-GS a depth-supervised Gaussian Splatting (GS) method that
provides accurate 3D geometry reconstruction by introducing a shape-aligned depth …