SDIR is a dual-path iterative refinement model using scale-adaptive transformers and Fourier operators plus a physically consistent spectral loss to improve both spatial accuracy and turbulence-consistent frequency content in precipitation nowcasting.
In: arXiv Preprint Arxiv:2410.04733 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
method 1polarities
extend 1representative citing papers
BEVPredFormer uses attention-based temporal processing and 3D camera projection to match or exceed prior methods on nuScenes for BEV instance prediction.
Upgrades to WeatherGFT PCNNs with WENO-5 solver, unified autoregressive block, and two new neural backbones yield 8-22% lower RMSE at 1-12 h leads on WeatherBench South Pacific data while improving physical consistency.
citing papers explorer
-
BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving
BEVPredFormer uses attention-based temporal processing and 3D camera projection to match or exceed prior methods on nuScenes for BEV instance prediction.