Tatiana Gaintseva*

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

"In this paper we propose a novel modification of Contrastive Language-Image Pre-Training (CLIP) guidance for the task of 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 (negat…