Scholar
Junhyuk Heo
Google Scholar ID: FIhe-wcAAAAJ
Telepix
Citations & Impact
Citations
2
H-index
1
i10-index
0
Publications
5
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 2025: Paper 'Fourier-Modulated Implicit Neural Representation for Multispectral Satellite Image Compression' accepted at IGARSS 2025 (Oral).
- 2025: Paper 'Tackling Few-Shot Segmentation in Remote Sensing via Inpainting Diffusion Model' accepted at ICLRw 2025 with Best Paper Award.
- 2024: Paper 'Neural Compression for Multispectral Satellite Images' accepted at NeurIPSw 2024.
- Co-developed MANGO: Mangrove Global Observations – a dataset and benchmark for global mangrove monitoring (under review, 2025).
- Preprint: 'Self-Supervised Score-Based Despeckling for SAR Imagery via Log-Domain Transformation' (2025).
Background
- AI researcher at TelePIX.
- Research focuses on solving real-world problems from an AI perspective.
- Addresses complex image restoration and data-efficient few-shot segmentation using generative models (diffusion-based, score-based, translation models).
- Explores Implicit Neural Representations (INRs) for continuous signal modeling, applied to neural image compression and spatial-spectral super-resolution.
- Recently shifted interest toward Vision-Language Models (VLMs), aiming to build a unified model for diverse complex tasks in earth science.
Co-authors