RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement

arXiv:2404.01889v2 Announce Type: replace
Abstract: In this paper we propose a novel modification of Contrastive Language-Image Pre-Training (CLIP) guidance for the task of unsupervised backlit image enhancement. Our work builds on the state-of-the-art CLIP-LIT approach, which learns a prompt pair by constraining the text-image similarity between a prompt (negative/positive sample) and a corresponding image (backlit image/well-lit image) in the CLIP embedding space. Learned prompts then guide an image enhancement network. Based on the CLIP-LIT framework, we propose two novel methods …

abstract art arxiv clip cs.ai cs.cv embedding guidance image language lit negative novel paper positive pre-training prompt residual sample state text text-image training type unsupervised vector work