Advancing 3D point cloud understanding through deep transfer learning: A comprehensive survey

SS Sohail, Y Himeur, H Kheddar, A Amira, F Fadli… - Information …, 2024 - Elsevier
The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of
deep learning (DL). However, the latter faces various issues, including the lack of data or …

Dg-pic: Domain generalized point-in-context learning for point cloud understanding

J Jiang, Q Zhou, Y Li, X Lu, M Wang, L Ma… - … on Computer Vision, 2024 - Springer
Recent point cloud understanding research suffers from performance drops on unseen data,
due to the distribution shifts across different domains. While recent studies use Domain …

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 …

Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting

H Lu, J Tang, X Xu, X Cao, Y Zhang, G Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
The emergence of Multi-Camera 3D Object Detection (MC3D-Det), facilitated by bird's-eye
view (BEV) representation, signifies a notable progression in 3D object detection. Scaling …

DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning

S Yogamani, D Unger, V Narayanan… - arxiv preprint arxiv …, 2024 - arxiv.org
Semantic segmentation is an effective way to perform scene understanding. Recently,
segmentation in 3D Bird's Eye View (BEV) space has become popular as its directly used by …

OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity

J Wang, W Yin, X Long, X Zhang, Z **ng, X Guo… - arxiv preprint arxiv …, 2024 - arxiv.org
3D semantic occupancy prediction networks have demonstrated remarkable capabilities in
reconstructing the geometric and semantic structure of 3D scenes, providing crucial …

Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains

J Kim, J Woo, J Kim, S Im - European Conference on Computer Vision, 2024 - Springer
In the realm of LiDAR-based perception, significant strides have been made, yet domain
generalization remains a substantial challenge. The performance often deteriorates when …

Instance-wise Domain Generalization for Cross-scene Wetland Classification with Hyperspectral and LiDAR Data

F Guo, Z Li, G Ren, L Wang, J Zhang… - … on Geoscience and …, 2024 - ieeexplore.ieee.org
Wetland is one of the three ecosystems in the world, and collaborative monitoring using
hyperspectral images (HSIs) and light detection and ranging (LiDAR) has been important for …

Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction

B Li, X **, J Deng, Y Sun, X Wang, W Zeng - arxiv preprint arxiv …, 2024 - arxiv.org
Camera-based 3D Semantic Occupancy Prediction (SOP) is crucial for understanding
complex 3D scenes from limited 2D image observations. Existing SOP methods typically …

Density-aware Domain Generalization for LiDAR Semantic Segmentation

J Kim, J Woo, U Shin, J Oh, S Im - 2024 IEEE/RSJ International …, 2024 - ieeexplore.ieee.org
3D LiDAR-based perception has made remarkable advancements, leading to the
widespread adoption of LiDAR in autonomous driving systems. Despite these technological …