Papers › Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs

Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs

4 Dec 2017arXiv:1712.00899archive 2025-07-28

Jun Yu, Xingxin Xu, Fei Gao, Shengjie Shi, Meng Wang, DaCheng Tao, Qingming Huang

Face photo-sketch synthesis aims at generating a facial sketch/photo conditioned on a given photo/sketch. It is of wide applications including digital entertainment and law enforcement. Precisely depicting face photos/sketches remains challenging due to the restrictions on structural realism and textural consistency. While existing methods achieve compelling results, they mostly yield blurred effects and great deformation over various facial components, leading to the unrealistic feeling of synthesized images. To tackle this challenge, in this work, we propose to use the facial composition information to help the synthesis of face sketch/photo. Specially, we propose a novel composition-aided generative adversarial network (CA-GAN) for face photo-sketch synthesis. In CA-GAN, we utilize paired inputs including a face photo/sketch and the corresponding pixel-wise face labels for generating a sketch/photo. In addition, to focus training on hard-generated components and delicate facial structures, we propose a compositional reconstruction loss. Finally, we use stacked CA-GANs (SCA-GAN) to further rectify defects and add compelling details. Experimental results show that our method is capable of generating both visually comfortable and identity-preserving face sketches/photos over a wide range of challenging data. Our method achieves the state-of-the-art quality, reducing best previous Frechet Inception distance (FID) by a large margin. Besides, we demonstrate that the proposed method is of considerable generalization ability. We have made our code and results publicly available: https://fei-hdu.github.io/ca-gan/.

PaperPDFCode

Code

fei-hdu/ca-gan officialmentioned in papermentioned on GitHubpytorch report
jehovahxu/ca-gan mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Face Sketch Synthesis

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Sketch Synthesis CUFS SCA-GAN FID 34.2 #2 of 4 Archive leaderboard report
Face Sketch Synthesis CUFS SCA-GAN FSIM 71.6% #2 of 4 Archive leaderboard report
Face Sketch Synthesis CUFS SCA-GAN NLDA 95.7 #2 of 4 Archive leaderboard report
Face Sketch Synthesis CUFS CA-GAN FID 39.7 #3 of 4 Archive leaderboard report
Face Sketch Synthesis CUFS CA-GAN FSIM 71.2% #3 of 4 Archive leaderboard report
Face Sketch Synthesis CUFS CA-GAN NLDA 95.6 #3 of 4 Archive leaderboard report
Face Sketch Synthesis CUFS SCA-GAN4 FID 32.8 #4 of 4 Archive leaderboard report
Face Sketch Synthesis CUFSF SCA-GAN FID 18.2 #1 of 3 Archive leaderboard report
Face Sketch Synthesis CUFSF SCA-GAN FSIM 72.9% #1 of 3 Archive leaderboard report
Face Sketch Synthesis CUFSF SCA-GAN NLDA 78 #1 of 3 Archive leaderboard report
Face Sketch Synthesis CUFSF CA-GAN FID 19.6 #2 of 3 Archive leaderboard report
Face Sketch Synthesis CUFSF CA-GAN FSIM 72.7% #2 of 3 Archive leaderboard report
Face Sketch Synthesis CUFSF CA-GAN NLDA 78.1 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections