FU Shi-yang

Hi! I'm FU Shi-yang, a phD at CUGB in Beijing.

My research interests include computer vision, remote sensing image processing, planetary remote sensing, and the application of deep learning in quantitative remote sensing.

Email  /  CV  /  Github

We assessed the performance of ERA5 and MERRA-2 water vapor products during heavy rainfall in the Guangxi region of China.

We use SDFs to bake a NeRF-like model into a high quality mesh and do real-time view synthesis.

We use volumetric rendering with a sparse 3D feature grid and 2D feature planes to do real-time view synthesis.

Shadows cast by unobserved occluders provide a high-frequency cue for recovering illumination and materials.

Combining mip-NeRF 360 and grid-based models like Instant NGP lets us reduce error rates by 8%–77% and accelerate training by 24x.

NeRF is aliased, but we can anti-alias it by casting cones and prefiltering the positional encoding function.

mip-NeRF can be extended to produce realistic results on unbounded scenes.

A model and feature representation that allows for sub-linear coarse-to-fine semantic segmentation.

Markov Decision Problems which lie in a low-dimensional latent space can be decomposed, allowing modified RL algorithms to run orders of magnitude faster in parallel.

Using the relative motions of stars we can accurately estimate the date of origin of historical astronomical images.

We use computer vision techniques to identify and remove diffraction spikes and reflection halos in the USNO-B Catalog.

In use at Astrometry.net

You probably want this website template, thanks to Jon Barron.
Last updated: 13th July, 2023.