{"url":"/method/pulse","slug":"pulse","name":"PULSE","full_name":"PULSE","full_name_withheld":false,"description_markdown":"**PULSE** is a self-supervised photo upsampling algorithm. Instead of starting with the LR image and slowly adding detail, PULSE traverses the high-resolution natural image manifold, searching for images that downscale to the original LR image. This is formalized through the downscaling loss, which guides exploration through the latent space of a generative model. By leveraging properties of high-dimensional Gaussians, the authors aim to restrict the search space to guarantee realistic outputs.","description_state":"present","introduced_year":null,"introduced_by":{"title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","paper":"/paper/pulse-self-supervised-photo-upsampling-via","first_author":"Sachit Menon","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pulse-self-supervised-photo-upsampling-via"},"source":{"url":"https://arxiv.org/abs/2003.03808v3","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","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":"Image Super-Resolution Models","url":"/methods/category/image-super-resolution-models","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":null,"title":"Teach Multimodal LLMs to Comprehend Electrocardiographic Images","date":"2024-10-21","arxiv_id":"2410.19008","n_code_links":0,"syntology":null},{"paper":null,"title":"Detecting Toxic Flow","date":"2023-12-10","arxiv_id":"2312.05827","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-Head Cross-Attentional PPG and Motion Signal Fusion for Heart Rate Estimation","date":"2022-10-14","arxiv_id":"2210.11415","n_code_links":0,"syntology":null},{"paper":"/paper/intermediate-layer-optimization-for-inverse","title":"Intermediate Layer Optimization for Inverse Problems using Deep Generative Models","date":"2021-02-15","arxiv_id":"2102.07364","n_code_links":2,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":1}},{"paper":"/paper/pulse-self-supervised-photo-upsampling-via","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","date":"2020-03-08","arxiv_id":"2003.03808","n_code_links":16,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":0}}],"papers_shown":5,"tasks":[{"task":"/task/super-resolution","name":"Super-Resolution","papers":2},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/face-hallucination","name":"Face Hallucination","papers":1},{"task":"/task/hallucination","name":"Hallucination","papers":1},{"task":"/task/heart-rate-estimation","name":"Heart rate estimation","papers":1},{"task":"/task/image-comprehension","name":"Image Comprehension","papers":1},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":1},{"task":"/task/photoplethysmography-ppg","name":"Photoplethysmography (PPG)","papers":1},{"task":"/task/compressed-sensing","name":"compressed sensing","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2020","papers":1},{"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/pulse"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}