A survey of label-efficient deep learning for 3D point clouds

A **ao, X Zhang, L Shao, S Lu - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
In the past decade, deep neural networks have achieved significant progress in point cloud
learning. However, collecting large-scale precisely-annotated point clouds is extremely …

Diff3DETR: Agent-Based Diffusion Model for Semi-supervised 3D Object Detection

J Deng, J Lu, T Zhang - European Conference on Computer Vision, 2024 - Springer
Abstract 3D object detection is essential for understanding 3D scenes. Contemporary
techniques often require extensive annotated training data, yet obtaining point-wise …

Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detection

S Zeng, W Zheng, J Lu, H Yan - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
3D object detection aims to recover the 3D information of concerning objects and serves as
the fundamental task of autonomous driving perception. Its performance greatly depends on …

Exploring Relational Knowledge for Source-free Domain Adaptation

Y Ma, L Chai, S Tu, Q Wang - … on Circuits and Systems for Video …, 2024 - ieeexplore.ieee.org
Standard domain adaptation methods require access to both source and target data.
However, sharing source data is often impractical in real-world scenarios due to data privacy …

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 …