3 papers
cs.CV2025
Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding
Wencan Huang, Daizong Liu, Wei Hu
While 3D Multi-modal Large Language Models (MLLMs) demonstrate remarkable scene understanding capabilities, their practical deployment faces critical challenges due to computationa…
cs.CV2024
Improving the Transferability of 3D Point Cloud Attack via Spectral-aware Admix and Optimization Designs
Shiyu Hu, Daizong Liu, Wei Hu
Deep learning models for point clouds have shown to be vulnerable to adversarial attacks, which have received increasing attention in various safety-critical applications such as a…
cs.CV2024
Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding
Yang Liu, Daizong Liu, Wei Hu
This paper tackles the challenging task of 3D visual grounding-locating a specific object in a 3D point cloud scene based on text descriptions. Existing methods fall into two categ…