Face Photo-Sketch Synthesis Via Domain-Invariant Feature Embedding
- Resource Type
- Conference
- Authors
- Choi, Yeji; Sohn, Kwanghoon; Kim, Ig-Jae
- Source
- 2023 IEEE International Conference on Image Processing (ICIP) Image Processing (ICIP), 2023 IEEE International Conference on. :66-70 Oct, 2023
- Subject
- Computing and Processing
Signal Processing and Analysis
Image recognition
Face recognition
Decoding
Task analysis
face photo-sketch synthesis
face recognition
domain-invariant feature
identity preservation
- Language
Face photo-sketch synthesis involves transforming photos into sketches and vice versa. A well-transformed image should preserve its original identity characteristics and naturalness. However, identity preservation remains a challenge because of the large discrepancy between the photo and sketch domains. To this end, we propose a novel face photo-sketch synthesis framework that uses domain-invariant feature embedding (DIFE). The DIFE framework generates images assuming the domain-invariant feature of an image pair for the same person to be the identity information. A joint feature embedding module considers latent features from two different domains as input and transfers them into the domain-invariant latent space. Subsequently, a semantic-aware decoder completes the desired image guided by multiscale facial parsing masks. Experimental results demonstrate that the DIFE method outperforms state-of-the-art approaches visually and perceptually.