{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dct-net-domain-calibrated-translation-for","title":"DCT-Net: Domain-Calibrated Translation for Portrait Stylization","arxiv_id":"2207.02426","date":"2022-07-06","proceeding":null,"authors":["Yifang Men","Yuan YAO","Miaomiao Cui","Zhouhui Lian","Xuansong Xie"],"abstract":"This paper introduces DCT-Net, a novel image translation architecture for few-shot portrait stylization. Given limited style exemplars ($\\sim$100), the new architecture can produce high-quality style transfer results with advanced ability to synthesize high-fidelity contents and strong generality to handle complicated scenes (e.g., occlusions and accessories). Moreover, it enables full-body image translation via one elegant evaluation network trained by partial observations (i.e., stylized heads). Few-shot learning based style transfer is challenging since the learned model can easily become overfitted in the target domain, due to the biased distribution formed by only a few training examples. This paper aims to handle the challenge by adopting the key idea of \"calibration first, translation later\" and exploring the augmented global structure with locally-focused translation. Specifically, the proposed DCT-Net consists of three modules: a content adapter borrowing the powerful prior from source photos to calibrate the content distribution of target samples; a geometry expansion module using affine transformations to release spatially semantic constraints; and a texture translation module leveraging samples produced by the calibrated distribution to learn a fine-grained conversion. Experimental results demonstrate the proposed method's superiority over the state of the art in head stylization and its effectiveness on full image translation with adaptive deformations.","url_abs":"https://arxiv.org/abs/2207.02426v1","url_pdf":"https://arxiv.org/pdf/2207.02426v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dct-net-domain-calibrated-translation-for","repo_url":"https://github.com/menyifang/dct-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dct-net-domain-calibrated-translation-for","repo_url":"https://github.com/LeslieZhoa/DCT-NET.Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"dct-net-domain-calibrated-translation-for","repo_url":"https://github.com/modelscope/modelscope","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}