Abstract: Diffusion models are a powerful class of techniques in ML for generating realistic data, but they are highly prone to overfitting, especially with limited training data. While data ...

Official implementation of Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image, ICCV 2025 (Oral). To run a minimal example, we provide run.py which takes in a single ...

One of my clients, takes many photos as part of their data entry process using a Canvas app. We need to compress the photos ...

Abstract: Deep learning has attracted wide attention recently because of its excellent feature representation ability and end-to-end automatic learning method. Especially in clinical medical imaging ...