Point Clouds Are Specialized Images: A Knowledge Transfer Approach for 3D Understanding
Self-supervised representation learning (SSRL) has gained increasing attention in point
cloud understanding, in addressing the challenges posed by 3D data scarcity and high …
cloud understanding, in addressing the challenges posed by 3D data scarcity and high …
Hyperbolic Image-and-Pointcloud Contrastive Learning for 3D Classification
3D contrastive representation learning has exhibited remarkable efficacy across various
downstream tasks. However, existing contrastive learning paradigms based on cosine …
downstream tasks. However, existing contrastive learning paradigms based on cosine …
Parameter-efficient Prompt Learning for 3D Point Cloud Understanding
H Sun, Y Wang, W Chen, H Deng, D Li - arXiv preprint arXiv:2402.15823, 2024 - arxiv.org
This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a
large multi-modal model for 3D point cloud understanding. Existing strategies are quite …
large multi-modal model for 3D point cloud understanding. Existing strategies are quite …
3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
Invariance-based and generative methods have shown a conspicuous performance for 3D
self-supervised representation learning (SSRL). However, the former relies on hand-crafted …
self-supervised representation learning (SSRL). However, the former relies on hand-crafted …
DIVESPOT: Depth Integrated Volume Estimation of Pile of Things Based on Point Cloud
Y Ling, R Zhao, Y Shen, D Li, J Jin, J Liu - arXiv preprint arXiv:2407.05415, 2024 - arxiv.org
Non-contact volume estimation of pile-type objects has considerable potential in industrial
scenarios, including grain, coal, mining, and stone materials. However, using existing …
scenarios, including grain, coal, mining, and stone materials. However, using existing …
Exploiting and Transferring Generalizable Knowledge for 2D/3D Object Recognition
J Kang - 2024 - search.proquest.com
In recent years, deep neural networks have significantly advanced the field of computer
vision. However, these advancements have largely relied on the assumption of independent …
vision. However, these advancements have largely relied on the assumption of independent …