CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment

arXiv:2404.01123v1 Announce Type: new
Abstract: Recent image tone adjustment (or enhancement) approaches have predominantly adopted supervised learning for learning human-centric perceptual assessment. However, these approaches are constrained by intrinsic challenges of supervised learning. Primarily, the requirement for expertly-curated or retouched images escalates the data acquisition expenses. Moreover, their coverage of target style is confined to stylistic variants inferred from the training data. To surmount the above challenges, we propose an unsupervised learning-based approach for text-based image tone adjustment method, CLIPtone, …

abstract acquisition arxiv assessment challenges coverage cs.cv cs.gr data eess.iv however human human-centric image images intrinsic style supervised learning text type unsupervised unsupervised learning