Related papers: FSD-BEV: Foreground Self-Distillation for Multi-vi…
Bird's Eye View (BEV) semantic maps have recently garnered a lot of attention as a useful representation of the environment to tackle assisted and autonomous driving tasks. However, most of the existing work focuses on the fully supervised…
Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…
We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in an unsupervised manner. By exploiting the geometric…
In the field of autonomous driving and mobile robotics, there has been a significant shift in the methods used to create Bird's Eye View (BEV) representations. This shift is characterised by using transformers and learning to fuse…
Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like…
Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features…
In this paper, we present BEVerse, a unified framework for 3D perception and prediction based on multi-camera systems. Unlike existing studies focusing on the improvement of single-task approaches, BEVerse features in producing…
Recent vision-only perception models for autonomous driving achieved promising results by encoding multi-view image features into Bird's-Eye-View (BEV) space. A critical step and the main bottleneck of these methods is transforming image…
Integrating LiDAR and camera information into Bird's-Eye-View (BEV) representation has emerged as a crucial aspect of 3D object detection in autonomous driving. However, existing methods are susceptible to the inaccurate calibration…
Most automated driving systems comprise a diverse sensor set, including several cameras, Radars, and LiDARs, ensuring a complete 360\deg coverage in near and far regions. Unlike Radar and LiDAR, which measure directly in 3D, cameras capture…
3D object detection is one of the fundamental perception tasks for autonomous vehicles. Fulfilling such a task with a 4D millimeter-wave radar is very attractive since the sensor is able to acquire 3D point clouds similar to Lidar while…
This paper proposes an efficient multi-camera to Bird's-Eye-View (BEV) view transformation method for 3D perception, dubbed MatrixVT. Existing view transformers either suffer from poor transformation efficiency or rely on device-specific…
We present BEV-SLD, a LiDAR global localization method building on the Scene Landmark Detection (SLD) concept. Unlike scene-agnostic pipelines, our self-supervised approach leverages bird's-eye-view (BEV) images to discover scene-specific…
Detecting diverse objects within complex indoor 3D point clouds presents significant challenges for robotic perception, particularly with varied object shapes, clutter, and the co-existence of static and dynamic elements where traditional…
As a cornerstone technique for autonomous driving, Bird's Eye View (BEV) segmentation has recently achieved remarkable progress with pinhole cameras. However, it is non-trivial to extend the existing methods to fisheye cameras with severe…
Diffusion-based models have been widely used in various visual generation tasks, showing promising results in image super-resolution (SR), while typically being limited by dozens or even hundreds of sampling steps. Although existing methods…
Existing online knowledge distillation approaches either adopt the student with the best performance or construct an ensemble model for better holistic performance. However, the former strategy ignores other students' information, while the…
The widespread use of multi-sensor systems has increased research in multi-view action recognition. While existing approaches in multi-view setups with fully overlapping sensors benefit from consistent view coverage, partially overlapping…
In recent years, few-shot action recognition has attracted increasing attention. It generally adopts the paradigm of meta-learning. In this field, overcoming the overlapping distribution of classes and outliers is still a challenging…
This paper presents Multi-view Labelling Object Detector (MLOD). The detector takes an RGB image and a LIDAR point cloud as input and follows the two-stage object detection framework. A Region Proposal Network (RPN) generates 3D proposals…