{"url":"/method/pixel2style2pixel","slug":"pixel2style2pixel","name":"pixel2style2pixel","full_name":"pixel2style2pixel","full_name_withheld":false,"description_markdown":"**Pixel2Style2Pixel**, or **pSp**, is an image-to-image translation framework that is based on a novel encoder that directly generates a series of style vectors which are fed into a pretrained [StyleGAN](https://paperswithcode.com/method/stylegan) generator, forming the extended $\\mathcal{W+}$ latent space. Feature maps are first extracted using a standard feature pyramid over a [ResNet](https://paperswithcode.com/method/resnet) backbone. Then, for each of $18$ target styles, a small mapping network is trained to extract the learned styles from the corresponding feature map, where styles $(0-2)$ are generated from the small feature map, $(3-6)$ from the medium feature map, and $(7-18)$ from the largest feature map. The mapping network, map2style, is a small fully convolutional network, which gradually reduces spatial size using a set of 2-strided convolutions followed by [LeakyReLU](https://paperswithcode.com/method/leaky-relu) activations. Each generated 512 vector, is fed into [StyleGAN](https://paperswithcode.com/method/stylegan), starting from its matching affine transformation, $A$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","paper":"/paper/encoding-in-style-a-stylegan-encoder-for","first_author":"Elad Richardson","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/encoding-in-style-a-stylegan-encoder-for"},"source":{"url":"https://arxiv.org/abs/2008.00951v2","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","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":"Unpaired Image-to-Image Translation","url":"/methods/category/unpaired-image-to-image-translation","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":null,"title":"Subsurface Depths Structure Maps Reconstruction with Generative Adversarial Networks","date":"2022-06-15","arxiv_id":"2206.07388","n_code_links":0,"syntology":null},{"paper":"/paper/encoding-in-style-a-stylegan-encoder-for","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","date":"2020-08-03","arxiv_id":"2008.00951","n_code_links":10,"syntology":{"ran":6,"of":16,"unverified":10,"pointer_only":1}}],"papers_shown":2,"tasks":[{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":1},{"task":"/task/face-generation","name":"Face Generation","papers":1},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":1},{"task":"/task/super-resolution","name":"Super-Resolution","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/translation","name":"Translation","papers":1}],"tasks_shown":6,"n_tasks":6,"usage_by_year":[{"year":"2020","papers":1},{"year":"2022","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/pixel2style2pixel"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}