HyperPhys-LRGS
Physics-aware low-rank hyperspectral Gaussian splatting for spectral reconstruction and super-resolution. The direction combines compact spectral bases with differentiable Gaussian representations.
From generative image restoration to hyperspectral sensing, my projects combine representation learning with real-world data and interdisciplinary collaboration.
Physics-aware low-rank hyperspectral Gaussian splatting for spectral reconstruction and super-resolution. The direction combines compact spectral bases with differentiable Gaussian representations.
Exploring Gaussian representations for hyperspectral denoising and reconstruction, including spectral bases and residual restoration strategies.
Adapting implicit neural representations to continuous hyperspectral reconstruction so that spatial queries can recover spectrally consistent high-resolution signals.
Developing latent-space and training-free approaches for difficult real-world image degradations, with emphasis on robustness and faithful reconstruction.
Interdisciplinary problem formulation, generative modelling and communication between geological interpretation and computer-vision representations.
The repeated multi-altitude observations follow the same field across a full cotton growth cycle, connecting acquisition strategy with downstream visual analysis.





