Choi, Yeji Kim, Haksub Sohn, Kwanghoon Kim, Ig-Jae 2025-04-25T08:02:39Z 2025-04-25T08:02:39Z 2025-04-25 2025-03 https://pubs.kist.re.kr/handle/201004/152353 Face sketch-to-photo synthesis is crucial in law enforcement, converting forensic sketches into RGB images for criminal database matching. A major challenge is ensuring accurate color representation in synthesized images to avoid identification error caused by mismatched skin or eye color. However, direct sketch-to-photo translation struggles with proper color representation as it relies solely on grayscale sketches. While recent text-guided generative methods show promise for style adjustment based on text descriptions, they often produce mixed or exaggerated colors due to using a single representation for text prompts containing multiple entangled attributes. To address these challenges, we propose Hierarchical Text-guided Stylization (HiTS), a novel identity-preserving face sketch-to-photo synthesis method. HiTS categorizes text descriptions into intrinsic and mutable attributes, capturing both global and local color features. Using an encoder-decoder architecture, the encoder extracts global features from intrinsic attributes, while the decoder refines local styles via a semantic-textual embedding map. This map integrates text embeddings with facial parsing masks, enabling precise style adjustments for each facial component, even in small regions. Both quantitative and qualitative results demonstrate that HiTS achieves fine-grained stylization while preserving identity, leading to improved face recognition accuracy. English Institute of Electrical and Electronics Engineers Inc. HiTS: Hierarchical Text-Guided Stylization for Face Sketch-to-Photo Synthesis Article 10.1109/ACCESS.2025.3549102 1 IEEE Access, v.13, pp.50885 - 50894 IEEE Access 13 50885 50894 Y scie scopus 001453187200050 2-s2.0-105001543741 Computer Science, Information Systems Engineering, Electrical & Electronic Telecommunications Computer Science Engineering Telecommunications Article Image color analysis Face recognition Skin Hair Image synthesis Translation Accuracy Visualization Generative adversarial networks Faces Face sketch-to-photo synthesis generative adversarial network (GAN) text-guided image generation