Related papers: OccFeat: Self-supervised Occupancy Feature Predict…

Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale. In this paper, we…

We present TinyBEV, a unified, camera only Bird's Eye View (BEV) framework that distills the full-stack capabilities of a large planning-oriented teacher (UniAD [19]) into a compact, real-time student model. Unlike prior efficient camera…

In advanced paradigms of autonomous driving, learning Bird's Eye View (BEV) representation from surrounding views is crucial for multi-task framework. However, existing methods based on depth estimation or camera-driven attention are not…

Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to other 3D detectors for autonomous driving and robotics. However, transforming image features into BEV necessitates special operators to conduct feature sampling. These…

Efficient and high-accuracy 3D occupancy prediction is vital for the performance of autonomous driving systems. However, existing methods struggle to balance precision and efficiency: high-accuracy approaches are often hindered by heavy…

Bird's Eye View (BEV) map prediction is essential for downstream autonomous driving tasks like trajectory prediction. In the past, this was accomplished through the use of a sophisticated sensor configuration that captured a surround view…

Pre-training is a dominant paradigm in computer vision. For example, supervised ImageNet pre-training is commonly used to initialize the backbones of object detection and segmentation models. He et al., however, show a surprising result…

We propose a self-supervised learning framework that uses unlabeled monocular video sequences to generate large-scale supervision for training a Visual Odometry (VO) frontend, a network which computes pointwise data associations across…

3D semantic occupancy prediction networks have demonstrated remarkable capabilities in reconstructing the geometric and semantic structure of 3D scenes, providing crucial information for robot navigation and autonomous driving systems.…

This paper describes recent developments in object specific pose and shape prediction from single images. The main contribution is a new approach to camera pose prediction by self-supervised learning of keypoints corresponding to locations…

Unsupervised 3D object detection leverages heuristic algorithms to discover potential objects, offering a promising route to reduce annotation costs in autonomous driving. Existing approaches mainly generate pseudo labels and refine them…

Semantic segmentation in autonomous driving has been undergoing an evolution from sparse point segmentation to dense voxel segmentation, where the objective is to predict the semantic occupancy of each voxel in the concerned 3D space. The…

Estimating the 3D world from 2D monocular images is a fundamental yet challenging task due to the labour-intensive nature of 3D annotations. To simplify label acquisition, this work proposes a novel approach that bridges 2D vision…

Inferring the 3D structure from a single image, particularly in occluded regions, remains a fundamental yet unsolved challenge in vision-centric autonomous driving. Existing unsupervised approaches typically train a neural radiance field…

Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes. Traditional approaches typically rely on dense, regular grid representations, which often leads to excessive…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities. To achieve this, current works try to construct a…

We present BEVCon, a simple yet effective contrastive learning framework designed to improve Bird's Eye View (BEV) perception in autonomous driving. BEV perception offers a top-down-view representation of the surrounding environment, making…

The ability to reliably perceive the environmental states, particularly the existence of objects and their motion behavior, is crucial for autonomous driving. In this work, we propose an efficient deep model, called MotionNet, to jointly…

Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision…