Predicting Perceived Gloss: Do Weak Labels Suffice?

arXiv:2403.17672v1 Announce Type: cross
Abstract: 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 shown to outperform traditional approaches, but rely on large datasets of human-annotated images for accurate perception predictions. Obtaining reliable annotations is a costly endeavor, aggravated by the limited ability of these models to generalise to different aspects of appearance. In this …

abstract arxiv cs.cv cs.gr datasets deep learning geometry human images interactions labels large datasets lighting materials type