{"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/syncammaster-synchronizing-multi-camera-video","title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","arxiv_id":"2412.07760","date":"2024-12-10","proceeding":null,"authors":["Jianhong Bai","Menghan Xia","Xintao Wang","Ziyang Yuan","Xiao Fu","Zuozhu Liu","Haoji Hu","Pengfei Wan","Di Zhang"],"abstract":"Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency. This progress inspires us to investigate the potential of these models to ensure dynamic consistency across various viewpoints, a highly desirable feature for applications such as virtual filming. Unlike existing methods focused on multi-view generation of single objects for 4D reconstruction, our interest lies in generating open-world videos from arbitrary viewpoints, incorporating 6 DoF camera poses. To achieve this, we propose a plug-and-play module that enhances a pre-trained text-to-video model for multi-camera video generation, ensuring consistent content across different viewpoints. Specifically, we introduce a multi-view synchronization module to maintain appearance and geometry consistency across these viewpoints. Given the scarcity of high-quality training data, we design a hybrid training scheme that leverages multi-camera images and monocular videos to supplement Unreal Engine-rendered multi-camera videos. Furthermore, our method enables intriguing extensions, such as re-rendering a video from novel viewpoints. We also release a multi-view synchronized video dataset, named SynCamVideo-Dataset. Project page: https://jianhongbai.github.io/SynCamMaster/.","url_abs":"https://arxiv.org/abs/2412.07760v1","url_pdf":"https://arxiv.org/pdf/2412.07760v1.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":"syncammaster-synchronizing-multi-camera-video","repo_url":"https://github.com/kwaivgi/syncammaster","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"4d-reconstruction","task_name":"4D reconstruction"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.07760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07760"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kwaivgi/syncammaster","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"2529bf081e7d18ba","entry":"get_c2w","repo":"kwaivgi/syncammaster","repo_kind":"official","path":"vis_cam.py","file_url":"https://github.com/kwaivgi/syncammaster/blob/HEAD/vis_cam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2529bf081e7d18ba"}},{"code_sha256_prefix":"1544d2a5dea32efb","entry":"low_version_attention","repo":"kwaivgi/syncammaster","repo_kind":"official","path":"diffsynth/models/attention.py","file_url":"https://github.com/kwaivgi/syncammaster/blob/HEAD/diffsynth/models/attention.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1544d2a5dea32efb"}},{"code_sha256_prefix":"8435018cece09e66","entry":"parse_matrix","repo":"kwaivgi/syncammaster","repo_kind":"official","path":"vis_cam.py","file_url":"https://github.com/kwaivgi/syncammaster/blob/HEAD/vis_cam.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8435018cece09e66"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}