DAME-Net decouples explicit per-factor degradation perception from conditioned reconstruction via a Mixture-of-Experts architecture, achieving better compositional UAV image restoration than unified methods on the new MDUR benchmark with 43 degradation configurations.
Learning transferable visual models from natural language supervi- sion,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compositional-Degradation UAV Image Restoration: Conditional Decoupled MoE Network and A Benchmark
DAME-Net decouples explicit per-factor degradation perception from conditioned reconstruction via a Mixture-of-Experts architecture, achieving better compositional UAV image restoration than unified methods on the new MDUR benchmark with 43 degradation configurations.