MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving
Instance segmentation is a fundamental research in computer vision, especially in
autonomous driving. However, manual mask annotation for instance segmentation is quite …
autonomous driving. However, manual mask annotation for instance segmentation is quite …
Context-aware transformer for 3d point cloud automatic annotation
Abstract 3D automatic annotation has received increased attention since manually
annotating 3D point clouds is laborious. However, existing methods are usually complicated …
annotating 3D point clouds is laborious. However, existing methods are usually complicated …
Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance
Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation
cost, eg, 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we …
cost, eg, 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we …
MEDL-U: Uncertainty-aware 3D Automatic Annotation based on Evidential Deep Learning
Advancements in deep learning-based 3D object detection necessitate the availability of
large-scale datasets. However, this requirement introduces the challenge of manual …
large-scale datasets. However, this requirement introduces the challenge of manual …
General Geometry-aware Weakly Supervised 3D Object Detection
3D object detection is an indispensable component for scene understanding. However, the
annotation of large-scale 3D datasets requires significant human effort. To tackle this …
annotation of large-scale 3D datasets requires significant human effort. To tackle this …
Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts
This paper proposes an algorithm for automatically labeling 3D objects from 2D point or box
prompts, especially focusing on applications in autonomous driving. Unlike previous arts …
prompts, especially focusing on applications in autonomous driving. Unlike previous arts …
Find n'Propagate: Open-Vocabulary 3D Object Detection in Urban Environments
In this work, we tackle the limitations of current LiDAR-based 3D object detection systems,
which are hindered by a restricted class vocabulary and the high costs associated with …
which are hindered by a restricted class vocabulary and the high costs associated with …
OC3D: Weakly Supervised Outdoor 3D Object Detection with Only Coarse Click Annotation
LiDAR-based outdoor 3D object detection has received widespread attention. However,
training 3D detectors from the LiDAR point cloud typically relies on expensive bounding box …
training 3D detectors from the LiDAR point cloud typically relies on expensive bounding box …
ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only
S Lahlali, N Granger, HL Borgne, QC Pham - arXiv preprint arXiv …, 2024 - arxiv.org
3D object detection plays a crucial role in various applications such as autonomous
vehicles, robotics and augmented reality. However, training 3D detectors requires a costly …
vehicles, robotics and augmented reality. However, training 3D detectors requires a costly …