I'm a passionate working at the intersection of physics, computer vision, and perception,
developing efficient and interpretable deep models for image reconstruction and super-resolution.
My current work explores:
- 🌀 Diffusion models and optimal transport (OT) for generative learning
- 🌈 Spectral–spatial transformers for hyperspectral image reconstruction (HSI)
- 🌊 Wavelet-based sparse representations and learnable thresholding
- 🧩 Low-rank approximation and structured attention for efficient architectures
- ⚡ Integration of physical priors into data-driven deep learning
- 🌀 Riemannian Geometry · Geometric analysis of manifolds, curvature, and metric learning in physical and perceptual spaces
- Physics-Inspired Deep Learning
- Diffusion & Optimal Transport for visual perception
- Riemannian Geometry
- Wavelet-Based Neural Architectures
- Sparse & Low-Rank Representations
- Hyperspectral Image Reconstruction (HSI)
- Super-Resolution and Denoising
⭐ "Bridging physics, perception, and computation — making AI see beyond RGB."