UniBlendNet combines UniConvNet for global dependencies, a Scale-Aware Aggregation Module for multi-scale features, and mask-guided refinement to outperform prior methods like IFBlend on ambient lighting normalization benchmarks.
Ffa-net: Feature fusion attention network for single image dehazing
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
HistoFusionNet combines histogram transformer blocks with a frequency-aware refinement branch in a multi-scale encoder-decoder to achieve top performance on nighttime image dehazing, ranking first in the NTIRE 2026 challenge.
citing papers explorer
-
UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization
UniBlendNet combines UniConvNet for global dependencies, a Scale-Aware Aggregation Module for multi-scale features, and mask-guided refinement to outperform prior methods like IFBlend on ambient lighting normalization benchmarks.
-
HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing
HistoFusionNet combines histogram transformer blocks with a frequency-aware refinement branch in a multi-scale encoder-decoder to achieve top performance on nighttime image dehazing, ranking first in the NTIRE 2026 challenge.