On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “demosaicing”

Deep Demosaicing for Edge Implementationcs.CV

Deep learning improves demosaicing but edge devices struggle.

problem Edge devices struggle with deep learning-based demosaicing.

method Exhaustive search of deep neural network architectures to find the best balance between performance and model complexity.

result Found architectures that outperform state-of-the-art demosaicing models on edge devices.

demosaicing deep learning edge devices exhaustive search CPSNR

2019-03-26abs ↗pdf ↗

Pyramid Attention Networks for Image Restorationcs.CV

Pyramid Attention Networks improve image restoration by leveraging self-similarities across scales.

problem Lack of full exploitation of self-similarities in image restoration by recent deep learning methods.

method Introduces a Pyramid Attention module that processes multi-scale feature correspondences to borrow clean signals from coarser levels.

result Pyramid Attention module achieves state-of-the-art results in various image restoration tasks.

image restoration self-similarity multi-scale feature attention mechanism deep learning

2020-04-28abs ↗pdf ↗

A Framework for Fast Image Deconvolution with Incomplete Observationscs.CV

In image deconvolution problems, the diagonalization of the underlying operators by means of the FFT usually yields very large speedups. When there are incomplete observations (e.g., in the case of unknown boundaries), standard deconvolution techniques normally involve non-diagonalizable operators, resulting in rather …

2016-02-03abs ↗pdf ↗