Search Results for author:
Found 4 papers, 2 papers with code
DD-VNB: A Depth-based Dual-Loop Framework for Real-time Visually Navigated Bronchoscopy
Specifically, the relative pose changes are fed into the registration process as the initial guess to boost its accuracy and speed.
LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors
Instead of directly inverting the triggers, LMSanitator aims to invert the predefined attack vectors (pretrained models' output when the input is embedded with triggers) of the task-agnostic backdoors, which achieves much better convergence performance and backdoor detection accuracy.
GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds
Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation.
Reconstructing A Large Scale 3D Face Dataset for Deep 3D Face Identification
The experimental results show that the reconstructed 3D facial surfaces are useful and our 2D-aided deep 3D face identification framework is meaningful, facing the scarcity of 3D faces.
