Back to search

Article

Unsupervised learning reveals interpretable latent representations for translucency perception

2022-08-15

Abstract excerpt

<h4>ABSTRACT</h4> Humans constantly assess the appearance of materials to plan actions, such as stepping on icy roads without slipping. Visual inference of materials is challenging because a given material can appear dramatically different in various scenes. This problem especially stands out for translucent materials (e.g., skin, soap), whose appearance strongly depends on lighting, geometry, and viewpoint. Desp...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
92ebcb01-79ef-5893-bd4c-43d4c3fb4659
DOI
10.1101/2022.08.12.503662
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Unsupervised learning reveals interpretable latent representations for translucency perceptionDOI 10.1101/2022.08.12.503662
Probing the Link Between Vision and Language in Material Perception Using Psychophysics and Unsupervised LearningSemantic proximity
From visual appearance to material categoriesSemantic proximity
From visual appearance to material categoriesSemantic proximity
Unsupervised learning predicts human perception and misperception of glossSemantic proximity
Automatic Classification and Style Analysis ofLandscape Architecture Images Based on DeepLearningSemantic proximity
Decoupling lower-level and higher-level visual features in naturalistic scenesSemantic proximity
Modeling Metallicity: Low Level Visual Features Support Robust Material PerceptionSemantic proximity
Imaginique Expressions: Tailoring Personalized Short-Text to Image Generation Through Aesthetic Assessment and Human InsightsSemantic proximity
Generative AI for Architectural Façade Design: Measuring Perceptual Alignment Across Geographical, Objective, and Affective DescriptorsSemantic proximity
The SPOT Grid: Naturalistic Images with Predefined Settings, Patterns, Objects, and TexturesSemantic proximity
The SPOT Grid: Naturalistic Images with Predefined Settings, Patterns, Objects, and TexturesSemantic proximity
Human texture synthesis: Observers reproduce chromatic and achromatic contrast differently in glossy vs. matte texturesSemantic proximity
Select a neighboring publication to make it the new centre.