{"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/conffusion-confidence-intervals-for-diffusion","title":"Conffusion: Confidence Intervals for Diffusion Models","arxiv_id":"2211.09795","date":"2022-11-17","proceeding":null,"authors":["Eliahu Horwitz","Yedid Hoshen"],"abstract":"Diffusion models have become the go-to method for many generative tasks, particularly for image-to-image generation tasks such as super-resolution and inpainting. Current diffusion-based methods do not provide statistical guarantees regarding the generated results, often preventing their use in high-stakes situations. To bridge this gap, we construct a confidence interval around each generated pixel such that the true value of the pixel is guaranteed to fall within the interval with a probability set by the user. Since diffusion models parametrize the data distribution, a straightforward way of constructing such intervals is by drawing multiple samples and calculating their bounds. However, this method has several drawbacks: i) slow sampling speeds ii) suboptimal bounds iii) requires training a diffusion model per task. To mitigate these shortcomings we propose Conffusion, wherein we fine-tune a pre-trained diffusion model to predict interval bounds in a single forward pass. We show that Conffusion outperforms the baseline method while being three orders of magnitude faster.","url_abs":"https://arxiv.org/abs/2211.09795v1","url_pdf":"https://arxiv.org/pdf/2211.09795v1.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":"conffusion-confidence-intervals-for-diffusion","repo_url":"https://github.com/eliahuhorwitz/conffusion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"conformal-prediction","task_name":"Conformal Prediction"},{"task_slug":"facial-inpainting","task_name":"Facial Inpainting"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"prediction-intervals","task_name":"Prediction Intervals"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"conffusion","method_name":"Conffusion"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[{"slug":"conffusion","name":"Conffusion","full_name":"Confidence Intervals for Diffusion Models"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.09795","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}