{"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/steerx-creating-any-camera-free-3d-and-4d","title":"SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering","arxiv_id":"2503.12024","date":"2025-03-15","proceeding":null,"authors":["Byeongjun Park","Hyojun Go","Hyelin Nam","Byung-Hoon Kim","Hyungjin Chung","Changick Kim"],"abstract":"Recent progress in 3D/4D scene generation emphasizes the importance of physical alignment throughout video generation and scene reconstruction. However, existing methods improve the alignment separately at each stage, making it difficult to manage subtle misalignments arising from another stage. Here, we present SteerX, a zero-shot inference-time steering method that unifies scene reconstruction into the generation process, tilting data distributions toward better geometric alignment. To this end, we introduce two geometric reward functions for 3D/4D scene generation by using pose-free feed-forward scene reconstruction models. Through extensive experiments, we demonstrate the effectiveness of SteerX in improving 3D/4D scene generation.","url_abs":"https://arxiv.org/abs/2503.12024v1","url_pdf":"https://arxiv.org/pdf/2503.12024v1.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":"steerx-creating-any-camera-free-3d-and-4d","repo_url":"https://github.com/byeongjun-park/SteerX","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"scene-generation","task_name":"Scene Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.12024","atlas_url":"https://app.syntology.ai/?focus=2503.12024","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}