U²Mamba proposes a two-level nested U-structure with multiscale Mamba U-blocks and hierarchical supervision to achieve competitive results on salient object detection benchmarks.
U-shaped vision mamba for single image dehazing,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PGL-Net decouples dehazing into global distribution rectification and local structural refinement via PAF and DAM modules, claiming SOTA quality on real-world benchmarks with over 10x lower latency than prior SOTA.
citing papers explorer
-
U$^2$Mamba: A Two-level Nested U-structure Mamba for Salient Object Detection
U²Mamba proposes a two-level nested U-structure with multiscale Mamba U-blocks and hierarchical supervision to achieve competitive results on salient object detection benchmarks.
-
Efficient Real-World Dehazing via Physics-Inspired Global-Local Decoupling
PGL-Net decouples dehazing into global distribution rectification and local structural refinement via PAF and DAM modules, claiming SOTA quality on real-world benchmarks with over 10x lower latency than prior SOTA.