{"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/infinite-nature-perpetual-view-generation-of","title":"Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image","arxiv_id":"2012.09855","date":"2020-12-17","proceeding":"ICCV 2021 10","authors":["Andrew Liu","Richard Tucker","Varun Jampani","Ameesh Makadia","Noah Snavely","Angjoo Kanazawa"],"abstract":"We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image. This is a challenging problem that goes far beyond the capabilities of current view synthesis methods, which quickly degenerate when presented with large camera motions. Methods for video generation also have limited ability to produce long sequences and are often agnostic to scene geometry. We take a hybrid approach that integrates both geometry and image synthesis in an iterative `\\emph{render}, \\emph{refine} and \\emph{repeat}' framework, allowing for long-range generation that cover large distances after hundreds of frames. Our approach can be trained from a set of monocular video sequences. We propose a dataset of aerial footage of coastal scenes, and compare our method with recent view synthesis and conditional video generation baselines, showing that it can generate plausible scenes for much longer time horizons over large camera trajectories compared to existing methods. Project page at https://infinite-nature.github.io/.","url_abs":"https://arxiv.org/abs/2012.09855v4","url_pdf":"https://arxiv.org/pdf/2012.09855v4.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":"infinite-nature-perpetual-view-generation-of","repo_url":"https://github.com/google-research/google-research/tree/master/infinite_nature","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"perpetual-view-generation","task_name":"Perpetual View Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"1-bit-adam","method_name":"1-bit Adam"},{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[{"slug":"acid","name":"ACID","full_name":"Aerial Coastline Imagery Dataset"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2012.09855","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}