1 citations · 1 across the 16 of their papers we have counts for
3 papers · 1 filter
WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structures
Reina Kaneko, Junya Hara, Hiroshi Higashi +1
This paper proposes a neural network for low light image enhancement (LLIE) based on retinex theory to make LLIE robust for various dynamic range scenes. The retinex theory is an i…
Multiscale Graph Construction Using Non-local Cluster Features
Reina Kaneko, Hayate Kojima, Kenta Yanagiya +3
This paper presents a multiscale graph construction method using both graph and signal features. Multiscale graph is a hierarchical representation of the graph, where a node at eac…
PHISWID: Physics-Inspired Underwater Image Dataset Synthesized from RGB-D Images
Reina Kaneko, Takumi Ueda, Hiroshi Higashi +1
This paper introduces the physics-inspired synthesized underwater image dataset (PHISWID), a dataset tailored for enhancing underwater image processing through physics-inspired ima…