From the 1 of 11 linked papers with an AI index.
11 papers
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…
Lossy compression of weighted graph adjacency matrices by transform coding
Kenta Yanagiya, Junya Hara, Hiroshi Higashi +2
The paper introduces a framework that losslessly transmits graph topology while lossy‑compressing edge weights using a line‑graph transform and graph filter bank, and provides a sm…
Multimodal Signal Restoration with Signed Twofold Graph Learning
Haruki Yokota, Hiroshi Higashi, Yuichi Tanaka
Multimodal signals on sensor networks are commonly modeled under the twofold graph assumption (TGA), which represents spatial structure and inter-modality relations as two separate…
Joint Alignment and Denoising for Event-Based Vision Sensors Using Regret-based Pareto Optimization
Shimpei Harada, Junya Hara, Hiroshi Higashi +1
This paper proposes a joint alignment and denoising method for event-based vision sensors (EVSs). Existing signal processing methods for EVSs typically perform event alignment (EA)…
Denoising for Neuromorphic Cameras Based on Graph Spectral Features
Shimpei Harada, Junya Hara, Hiroshi Higashi +1
Neuromorphic cameras, also known as event-based cameras, can detect changes in the environmental brightness asynchronously and independently for each pixel. They output the brightn…
Graph Signal Denoising Using Regularization by Denoising and Its Parameter Estimation
Hayate Kojima, Hiroshi Higashi, Yuichi Tanaka
In this paper, we propose an interpretable denoising method for graph signals using regularization by denoising (RED). RED is a technique developed for image restoration that uses…