← Search

Ning Ni

2 accepted papers

2025

Hazy Low-Quality Satellite Video Restoration Via Learning Optimal Joint Degradation Patterns and Continuous-Scale Super-Resolution Reconstruction

CVPR 2025poster

Currently, the demand for higher video quality has grown significantly. However, satellite video has low resolution, complex motion, and weak textures. Haze interference further exacerbates the loss of motion information and texture details, hindering effective spatiotemporal feature fusion and fine…

Cited by 0SourcePDFScholar
2025

SLVR: Super-Light Visual Reconstruction via Blueprint Controllable Convolutions and Exploring Feature Diversity Representation

CVPR 2025poster

Recently, improving the residual structure and designing efficient convolutions have become important branches of lightweight visual reconstruction model design. We have observed that the feature addition mode (FAM) in existing residual structure tends to lead to slow feature learning or stagnation…