HIGHLIGHTS
- who: Chenxi Liao et al. from the Department of Neuroscience, American University, Washington, DC, District of Columbia, United States of have published the research: Unsupervised learning reveals interpretable latent representations for translucency perception, in the Journal: (JOURNAL)
- what: The authors develop an unsupervised stylebased image generation model to identify perceptually relevant dimensions for translucent material appearances from photographs. The authors provide a systematic framework to discover perceptually relevant image features from natural stimuli for perceptual inference tasks and therefore valuable for understanding both human and computer vision. The authors aim to learn, unsupervised, a compact . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.