Výsledky vyhledávání - "Fleming, Roland W."

Report

Material Fingerprinting: Identifying and Predicting Perceptual Attributes of Material Appearance

Autor: Filip, Jiri, Dechterenko, Filip, Schmidt, Filipp, Lukavsky, Jiri, Vilimovska, Veronika, Kotera, Jan, Fleming, Roland W.

The world is abundant with diverse materials, each possessing unique surface appearances that play a crucial role in our daily perception and understanding of their properties. Despite advancements in technology enabling the capture and realistic rep

Externí odkaz: http://arxiv.org/abs/2410.13615

Zobrazit plný text záznamu

Report

Self-Supervised Learning of Color Constancy

Autor: Ernst, Markus R., López, Francisco M., Aubret, Arthur, Fleming, Roland W., Triesch, Jochen

Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions. While CC and its limitations have been carefully characterized in humans, it is still

Externí odkaz: http://arxiv.org/abs/2404.08127

Zobrazit plný text záznamu

Report

Predicting Perceived Gloss: Do Weak Labels Suffice?

Autor: Guerrero-Viu, Julia, Subias, J. Daniel, Serrano, Ana, Storrs, Katherine R., Fleming, Roland W., Masia, Belen, Gutierrez, Diego

Estimating perceptual attributes of materials directly from images is a challenging task due to their complex, not fully-understood interactions with external factors, such as geometry and lighting. Supervised deep learning models have recently been

Externí odkaz: http://arxiv.org/abs/2403.17672

Zobrazit plný text záznamu

Report

Deep Neural Models for color discrimination and color constancy

Autor: Flachot, Alban, Akbarinia, Arash, Schütt, Heiko H., Fleming, Roland W., Wichmann, Felix A., Gegenfurtner, Karl R.

Color constancy is our ability to perceive constant colors across varying illuminations. Here, we trained deep neural networks to be color constant and evaluated their performance with varying cues. Inputs to the networks consisted of the cone excita

Externí odkaz: http://arxiv.org/abs/2012.14402

Zobrazit plný text záznamu

Report

Distinguishing mirror from glass: A 'big data' approach to material perception

Autor: Tamura, Hideki, Prokott, Konrad E., Fleming, Roland W.

Publikováno v: Journal of Vision (2022) 22(4):4

Visually identifying materials is crucial for many tasks, yet material perception remains poorly understood. Distinguishing mirror from glass is particularly challenging as both materials derive their appearance from their surroundings, yet we rarely

Externí odkaz: http://arxiv.org/abs/1903.01671

Zobrazit plný text záznamu