{"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/peekaboo-interactive-video-generation-via","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","arxiv_id":"2312.07509","date":"2023-12-12","proceeding":"CVPR 2024 1","authors":["Yash Jain","Anshul Nasery","Vibhav Vineet","Harkirat Behl"],"abstract":"Modern video generation models like Sora have achieved remarkable success in producing high-quality videos. However, a significant limitation is their inability to offer interactive control to users, a feature that promises to open up unprecedented applications and creativity. In this work, we introduce the first solution to equip diffusion-based video generation models with spatio-temporal control. We present Peekaboo, a novel masked attention module, which seamlessly integrates with current video generation models offering control without the need for additional training or inference overhead. To facilitate future research, we also introduce a comprehensive benchmark for interactive video generation. This benchmark offers a standardized framework for the community to assess the efficacy of emerging interactive video generation models. Our extensive qualitative and quantitative assessments reveal that Peekaboo achieves up to a 3.8x improvement in mIoU over baseline models, all while maintaining the same latency. Code and benchmark are available on the webpage.","url_abs":"https://arxiv.org/abs/2312.07509v2","url_pdf":"https://arxiv.org/pdf/2312.07509v2.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":"peekaboo-interactive-video-generation-via","repo_url":"https://github.com/microsoft/peekaboo","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[{"slug":"ssv2-spatio-temporal","name":"SSv2-Spatio-Temporal","full_name":"Something Someting v2-Spatio-Temporal"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.07509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07509"}},"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/microsoft/peekaboo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":12,"ran":9,"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":0,"samples":[{"code_sha256_prefix":"1566830f72260e5d","entry":"calculate_ap50","repo":"microsoft/peekaboo","repo_kind":"official","path":"eval/get_metrics.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/eval/get_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1566830f72260e5d"}},{"code_sha256_prefix":"26588212300d1a39","entry":"calculate_iou","repo":"microsoft/peekaboo","repo_kind":"official","path":"eval/get_metrics.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/eval/get_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26588212300d1a39"}},{"code_sha256_prefix":"d2ebbed228aeea81","entry":"generate_video","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/app_modelscope.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/app_modelscope.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d2ebbed228aeea81"}},{"code_sha256_prefix":"a9a2ab113db66971","entry":"generate_video","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/generate.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9a2ab113db66971"}},{"code_sha256_prefix":"b4675e3fc23b05c2","entry":"get_centroid","repo":"microsoft/peekaboo","repo_kind":"official","path":"eval/get_metrics.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/eval/get_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4675e3fc23b05c2"}},{"code_sha256_prefix":"c7dedf190706d4fc","entry":"image_mod","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/app_modelscope.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/app_modelscope.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7dedf190706d4fc"}},{"code_sha256_prefix":"31b35eebe3fc998d","entry":"interpolate_points","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/app_modelscope.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/app_modelscope.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31b35eebe3fc998d"}},{"code_sha256_prefix":"bea2d776a332f2b0","entry":"rescale_noise_cfg","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/models/sd_pipeline.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/models/sd_pipeline.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bea2d776a332f2b0"}},{"code_sha256_prefix":"92e264414f3052da","entry":"tensor2vid","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/models/pipelines.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/models/pipelines.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92e264414f3052da"}},{"code_sha256_prefix":"192bc68fdc627de2","entry":"convert","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/gradio_utils.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/gradio_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"192bc68fdc627de2"}},{"code_sha256_prefix":"21887b4a542f7643","entry":"create_video","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/gradio_utils.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/gradio_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21887b4a542f7643"}},{"code_sha256_prefix":"1e153f05cb2ea751","entry":"get_frames","repo":"microsoft/peekaboo","repo_kind":"official","path":"src/gradio_utils.py","file_url":"https://github.com/microsoft/peekaboo/blob/HEAD/src/gradio_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e153f05cb2ea751"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}