How-To Geek on MSN

Generate realistic test data in Python fast. No dataset required

Learn the NumPy trick for generating synthetic data that actually behaves like real data.
GitHub

Is There a Better Source Distribution than Gaussian?: Exploring Source Distributions for Image Flow Matching

Official implementation of our TMLR submission investigating optimal source distribution choices for flow matching in generative modeling. We introduce a novel 2D simulation framework that captures ...
GitHub

TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors

We present TSGS, a framework for high-fidelity transparent surface reconstruction from multi-views. (a) We introduce TransLab, a novel dataset for evaluating transparent object reconstruction. (b) ...
IEEE

LiDAR-Based Optimized Normal Distribution Transform Localization on 3-D Map for Autonomous Navigation

Abstract: Autonomous navigation has become a topic of immense interest in robotics in recent years. Light detection and ranging (LiDAR) can perceive the environment in 3-D by creating the point cloud ...
IEEE

Concealed Backdoor Attack on Diffusion Models for Smart Devices With Non-Standard Gaussian Distribution Noise

Abstract: Edge AI-driven diffusion models (DMs) are increasingly integrated into consumer devices for high-quality data generation and content creation. This paper introduces InvisibleDiffusion, a ...