{"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/flashdepth-real-time-streaming-video-depth","title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","arxiv_id":"2504.07093","date":"2025-04-09","proceeding":null,"authors":["Gene Chou","Wenqi Xian","Guandao Yang","Mohamed Abdelfattah","Bharath Hariharan","Noah Snavely","Ning Yu","Paul Debevec"],"abstract":"A versatile video depth estimation model should (1) be accurate and consistent across frames, (2) produce high-resolution depth maps, and (3) support real-time streaming. We propose FlashDepth, a method that satisfies all three requirements, performing depth estimation on a 2044x1148 streaming video at 24 FPS. We show that, with careful modifications to pretrained single-image depth models, these capabilities are enabled with relatively little data and training. We evaluate our approach across multiple unseen datasets against state-of-the-art depth models, and find that ours outperforms them in terms of boundary sharpness and speed by a significant margin, while maintaining competitive accuracy. We hope our model will enable various applications that require high-resolution depth, such as video editing, and online decision-making, such as robotics.","url_abs":"https://arxiv.org/abs/2504.07093v1","url_pdf":"https://arxiv.org/pdf/2504.07093v1.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":"flashdepth-real-time-streaming-video-depth","repo_url":"https://github.com/Eyeline-Research/FlashDepth","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2k","task_name":"2k"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"video-editing","task_name":"Video Editing"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.07093","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}