PhD & Prior Research

PhD Research

During my PhD in the Jug Lab, I worked on image decomposition tasks for microscopy data. Here are the main projects:

• uSplit: A HVAE inspired architecture for efficient image decomposition (ICCV 23).
• denoiSplit: An architecture for unsupervised denoising together with decomposition, supporting multi-prediction and model calibration (ECCV 24).
• microSSIM: A variant of SSIM suited for unsupervised denoising tasks on microscopy data (BIC workshop, ECCV 24).
• Latent Space Splitting: Structural noise removal using contrastive learning on the latent space.

Prior Research & Work

Before my PhD, I worked as a Research Assistant in Taipei, and as a Data Scientist:

• Gaze Estimation: My work on 3D Gaze estimation in the wild at Vision-lab, NTU (BMVC 2021).
• Qplum: My experience and learnings working as a Data Scientist at the online investment advisory firm Qplum.