Shapellm: Universal 3d object understanding for embodied interaction

Z Qi, R Dong, S Zhang, H Geng, C Han, Z Ge… - … on Computer Vision, 2024 - Springer
This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM)
designed for embodied interaction, exploring a universal 3D object understanding with 3D …

[HTML][HTML] DILF: Differentiable rendering-based multi-view Image–Language Fusion for zero-shot 3D shape understanding

X Ning, Z Yu, L Li, W Li, P Tiwari - Information Fusion, 2024 - Elsevier
Zero-shot 3D shape understanding aims to recognize “unseen” 3D categories that are not
present in training data. Recently, Contrastive Language–Image Pre-training (CLIP) has …

Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model

X Han, Y Tang, Z Wang, X Li - … of the 32nd ACM International Conference …, 2024 - dl.acm.org
Existing Transformer-based models for point cloud analysis suffer from quadratic complexity,
leading to compromised point cloud resolution and information loss. In contrast, the newly …

ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images

X Zhang, Z Wang, H Zhou, S Ghosh… - … on Computer Vision, 2024 - Springer
To advance the state of the art in the creation of 3D foundation models, this paper introduces
the ConDense framework for 3D pre-training utilizing existing pre-trained 2D networks and …

Point-jepa: A joint embedding predictive architecture for self-supervised learning on point cloud

A Saito, P Kudeshia, J Poovvancheri - ar** Network for 3D Object Recognition
X Ning, L Jiang, W Li, Z Yu, J **e, L Li… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Recent developments in Swin Transformer have shown its great potential in various
computer vision tasks, including image classification, semantic segmentation, and object …

[HTML][HTML] PosE-Enhanced Point Transformer with Local Surface Features (LSF) for Wood–Leaf Separation

X Lu, R Wang, H Zhang, J Zhou, T Yun - Forests, 2024 - mdpi.com
Wood–leaf separation from forest LiDAR point clouds is a challenging task due to the
complex and irregular structures of tree canopies. Traditional machine vision and deep …

Intelligent Construction Activity Identification for All-Weather Site Monitoring Using 4D Millimeter-Wave Technology

J Wang, G Wang, H Li, S Han… - Journal of Construction …, 2024 - ascelibrary.org
Site monitoring is indispensable for modern construction management. Contact approaches,
represented by wearable devices, have problems such as privacy leaks and hindering …