Multi-Axis Feature Diversity Enhancement for Remote Sensing Video Super-Resolution
Wuhan University · Harbin Institute of Technology · +2 more institutions
Abstract
How to aggregate spatial-temporal information plays an essential role in video super-resolution (VSR) tasks. Despite the remarkable success, existing methods adopt static convolution to encode spatial-temporal information, which lacks flexibility in aggregating information in large-scale remote sensing scenes, as they often contain heterogeneous features (e.g., diverse textures). In this paper, we propose a spatial feature diversity enhancement module (SDE) and channel diversity enhancement module (CDE), which explore the diverse representation of different local patterns while aggregating the global response with compactly channel-wise embedding representation. Specifically, SDE introduces multiple learnable…
Citation impact
- FWCI
- 48.73
- Percentile
- 100%
- References
- 66
Authors
6Topics & keywords
- Remote sensing
- Computer science
- Computer vision
- Artificial intelligence
- Image resolution
- Feature (linguistics)
- Image enhancement
- Feature extraction