Point Cloud
Point clouds are collections of 3D data points representing objects or scenes, primarily used for tasks like 3D reconstruction, object recognition, and autonomous navigation. Current research focuses on improving the efficiency and robustness of point cloud processing, employing techniques like deep learning (e.g., transformers, convolutional neural networks), optimal transport, and Gaussian splatting for tasks such as registration, completion, and compression. These advancements are crucial for applications ranging from robotics and autonomous driving to medical imaging and cultural heritage preservation, enabling more accurate and efficient analysis of complex 3D data.
Papers
Learning-Based Biharmonic Augmentation for Point Cloud Classification
Jiacheng Wei, Guosheng Lin, Henghui Ding, Jie Hu, Kim-Hui Yap
Refining the ONCE Benchmark with Hyperparameter Tuning
Maksim Golyadkin, Alexander Gambashidze, Ildar Nurgaliev, Ilya Makarov
U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation
Jiaxu Liu, Zhengdi Yu, Toby P. Breckon, Hubert P. H. Shum
Automatic extraction and 3D reconstruction of split wire from point cloud data based on improved DPC algorithm
Jia Cheng
Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook
Huang Zhang, Changshuo Wang, Shengwei Tian, Baoli Lu, Liping Zhang, Xin Ning, Xiao Bai
Optimizing Implicit Neural Representations from Point Clouds via Energy-Based Models
Ryutaro Yamauchi, Jinya Sakurai, Ryo Furukawa, Tatsushi Matsubayashi
MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory
Enxu Li, Sergio Casas, Raquel Urtasun
Lightweight super resolution network for point cloud geometry compression
Wei Zhang, Dingquan Li, Ge Li, Wen Gao
Quatro++: Robust Global Registration Exploiting Ground Segmentation for Loop Closing in LiDAR SLAM
Hyungtae Lim, Beomsoo Kim, Daebeom Kim, Eungchang Mason Lee, Hyun Myung