Related papers: OccNeRF: Advancing 3D Occupancy Prediction in LiDA…

Understanding world dynamics is crucial for planning in autonomous driving. Recent methods attempt to achieve this by learning a 3D occupancy world model that forecasts future surrounding scenes based on current observation. However, 3D…

The completion, extension, and generation of 3D semantic scenes are an interrelated set of capabilities that are useful for robotic navigation and exploration. Existing approaches seek to decouple these problems and solve them one-off.…

Recent progress in self- and weakly supervised occupancy estimation has largely relied on 2D projection or rendering-based supervision, which suffers from geometric inconsistencies and severe depth bleeding. We thus introduce ShelfOcc, a…

3D occupancy prediction aims to infer dense, voxel-wise scene semantics from sensor observations, where the 2D-to-3D view transformation serves as a crucial step in bridging image features and volumetric representations. Most previous…

World models envision potential future states based on various ego actions. They embed extensive knowledge about the driving environment, facilitating safe and scalable autonomous driving. Most existing methods primarily focus on either…

Implicit representations such as Neural Radiance Fields (NeRF) have been shown to be very effective at novel view synthesis. However, these models typically require manual and careful human data collection for training. In this paper, we…

Multi-view implicit scene reconstruction methods have become increasingly popular due to their ability to represent complex scene details. Recent efforts have been devoted to improving the representation of input information and to reducing…

Steering estimation is a critical task in autonomous driving, traditionally relying on 2D image-based models. In this work, we explore the advantages of incorporating 3D spatial information through hybrid architectures that combine 3D…

Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations. However, training dense occupancy decoders to capture fine-grained geometry and semantics…

3D semantic occupancy prediction in the past was considered to require precise geometric relationships in order to enable effective training. However, in complex indoor environments, the large-scale and widespread collection of data, along…

In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable road users such as pedestrians and cyclists. Previous representation methods, such as Bird's…

We introduce a Generalizable Neural Radiance Field approach for predicting 3D workspace occupancy from egocentric robot observations. Unlike prior methods operating in camera-centric coordinates, our model constructs occupancy…

Implicit neural representations have shown compelling results in offline 3D reconstruction and also recently demonstrated the potential for online SLAM systems. However, applying them to autonomous 3D reconstruction, where a robot is…

Multi-camera 3D perception has emerged as a prominent research field in autonomous driving, offering a viable and cost-effective alternative to LiDAR-based solutions. The existing multi-camera algorithms primarily rely on monocular 2D…

While multi-modal 3D semantic occupancy prediction typically enhances robustness by fusing camera and LiDAR inputs, its effectiveness is fundamentally constrained by environmental variability. Specifically, camera sensors suffer from severe…

Accurate prediction of 3D semantic occupancy from 2D visual images is vital in enabling autonomous agents to comprehend their surroundings for planning and navigation. State-of-the-art methods typically employ fully supervised approaches,…

Weakly-supervised 3D occupancy perception is crucial for vision-based autonomous driving in outdoor environments. Previous methods based on NeRF often face a challenge in balancing the number of samples used. Too many samples can decrease…

3D instance segmentation, with a variety of applications in robotics and augmented reality, is in large demands these days. Unlike 2D images that are projective observations of the environment, 3D models provide metric reconstruction of the…

3D reconstruction from images has wide applications in Virtual Reality and Automatic Driving, where the precision requirement is very high. Ground-breaking research in the neural radiance field (NeRF) by utilizing Multi-Layer Perceptions…

This paper describes a system whereby a robot detects and track human-meaningful navigational cues as it navigates in an indoor environment. It is intended as the sensor front-end for a mobile robot system that can communicate its…