{"url":"/method/revision-network","slug":"revision-network","name":"Revision Network","full_name":"Revision Network","full_name_withheld":false,"description_markdown":"**Revision Network** is a style transfer module that aims to revise the rough stylized image via generating residual details image $r_{c s}$, while the final stylized image is generated by combining $r\\_{c s}$ and rough stylized image $\\bar{x}\\_{c s}$. This procedure ensures that the distribution of global style pattern in $\\bar{x}\\_{c s}$ is properly kept. Meanwhile, learning to revise local style patterns with residual details image is easier for the Revision Network.\r\n\r\nAs shown in the Figure, the Revision Network is designed as a simple yet effective encoder-decoder architecture, with only one down-sampling and one up-sampling layer. Further, a [patch discriminator](https://paperswithcode.com/method/patchgan) is used to help Revision Network to capture fine patch textures under adversarial learning setting. The patch discriminator $D$ is defined following SinGAN, where $D$ owns 5 convolution layers and 32 hidden channels. A relatively shallow $D$ is chosen to (1) avoid overfitting since we only have one style image and (2) control the receptive field to ensure D can only capture local patterns.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer","paper":"/paper/drafting-and-revision-laplacian-pyramid","first_author":"Tianwei Lin","n_authors":9,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/drafting-and-revision-laplacian-pyramid"},"source":{"url":"https://arxiv.org/abs/2104.05376v2","title":"Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Style Transfer Modules","url":"/methods/category/style-transfer-modules","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/fsc-few-point-shape-completion","title":"FSC: Few-point Shape Completion","date":"2024-03-12","arxiv_id":"2403.07359","n_code_links":1,"syntology":{"ran":6,"of":6,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Attribute Localization and Revision Network for Zero-Shot Learning","date":"2023-10-11","arxiv_id":"2310.07548","n_code_links":0,"syntology":null},{"paper":null,"title":"Arbitrary Style Transfer with Structure Enhancement by Combining the Global and Local Loss","date":"2022-07-23","arxiv_id":"2207.11438","n_code_links":0,"syntology":null},{"paper":"/paper/drafting-and-revision-laplacian-pyramid","title":"Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer","date":"2021-04-12","arxiv_id":"2104.05376","n_code_links":2,"syntology":null}],"papers_shown":4,"tasks":[{"task":"/task/style-transfer","name":"Style Transfer","papers":2},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/zero-shot-learning","name":"Zero-Shot Learning","papers":1}],"tasks_shown":6,"n_tasks":6,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/revision-network"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}