activity
20182020
most citedDeep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution

22 citations · 27 across the 5 of their papers we have counts for

collaborators
Showing 2019Show all

5 papers · 1 filter

cs.HC2019

Overt visual attention on rendered 3D objects

Oleksii Sidorov, Joshua S. Harvey, Hannah E. Smithson +1

This work covers multiple aspects of overt visual attention on 3D renders: measurement, projection, visualization, and application to studying the influence of material appearance…

cs.HC2019★ 3 cited

Are all the frames equally important?

Oleksii Sidorov, Marius Pedersen, Nam Wook Kim +1

In this work, we address the problem of measuring and predicting temporal video saliency - a metric which defines the importance of a video frame for human attention. Unlike the co…

cs.CV2019

Craquelure as a Graph: Application of Image Processing and Graph Neural Networks to the Description of Fracture Patterns

Oleksii Sidorov, Jon Yngve Hardeberg

Cracks on a painting is not a defect but an inimitable signature of an artwork which can be used for origin examination, aging monitoring, damage identification, and even forgery d…

cs.CV2019★ 2 cited

Generative Smoke Removal

Oleksii Sidorov, Congcong Wang, Faouzi Alaya Cheikh

In minimally invasive surgery, the use of tissue dissection tools causes smoke, which inevitably degrades the image quality. This could reduce the visibility of the operation field…

cs.CV2019★ 22 cited

Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution

Oleksii Sidorov, Jon Yngve Hardeberg

Deep learning algorithms have demonstrated state-of-the-art performance in various tasks of image restoration. This was made possible through the ability of CNNs to learn from larg…