{"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/texttt-dino-foresight-looking-into-the-future","title":"$\\texttt{DINO-Foresight}$: Looking into the Future with DINO","arxiv_id":"2412.11673","date":"2024-12-16","proceeding":null,"authors":["Efstathios Karypidis","Ioannis Kakogeorgiou","Spyros Gidaris","Nikos Komodakis"],"abstract":"Predicting future dynamics is crucial for applications like autonomous driving and robotics, where understanding the environment is key. Existing pixel-level methods are computationally expensive and often focus on irrelevant details. To address these challenges, we introduce $\\texttt{DINO-Foresight}$, a novel framework that operates in the semantic feature space of pretrained Vision Foundation Models (VFMs). Our approach trains a masked feature transformer in a self-supervised manner to predict the evolution of VFM features over time. By forecasting these features, we can apply off-the-shelf, task-specific heads for various scene understanding tasks. In this framework, VFM features are treated as a latent space, to which different heads attach to perform specific tasks for future-frame analysis. Extensive experiments show that our framework outperforms existing methods, demonstrating its robustness and scalability. Additionally, we highlight how intermediate transformer representations in $\\texttt{DINO-Foresight}$ improve downstream task performance, offering a promising path for the self-supervised enhancement of VFM features. We provide the implementation code at https://github.com/Sta8is/DINO-Foresight .","url_abs":"https://arxiv.org/abs/2412.11673v1","url_pdf":"https://arxiv.org/pdf/2412.11673v1.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":"texttt-dino-foresight-looking-into-the-future","repo_url":"https://github.com/sta8is/dino-foresight","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.11673","atlas_url":"https://app.syntology.ai/?focus=2412.11673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11673"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/sta8is/dino-foresight","reach":null}],"summary":{"ran":1,"ran_honours":2,"unverified":7},"by_repo_kind":{"official":{"samples":10,"ran":3,"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":"a5d1c8b433623f9d","entry":"AddBroadcastPosEmbed","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5d1c8b433623f9d"}},{"code_sha256_prefix":"9647212f40af1789","entry":"compute_depth_metrics","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9647212f40af1789"}},{"code_sha256_prefix":"1ddac064686a8021","entry":"compute_normal_metrics","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ddac064686a8021"}},{"code_sha256_prefix":"4107e3b3305e9452","entry":"DPTHead","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.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":"4107e3b3305e9452"}},{"code_sha256_prefix":"ad89576b6df002d9","entry":"Dino_f","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.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":"ad89576b6df002d9"}},{"code_sha256_prefix":"0ec469a5039f384d","entry":"MaskTransformer","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.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":"0ec469a5039f384d"}},{"code_sha256_prefix":"0f7a80d0fe355d88","entry":"reset_depth_metrics","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.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":"0f7a80d0fe355d88"}},{"code_sha256_prefix":"812540a84a99f16c","entry":"reset_normal_metrics","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.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":"812540a84a99f16c"}},{"code_sha256_prefix":"cc7f93b1ea98f3b6","entry":"update_depth_metrics","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.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":"cc7f93b1ea98f3b6"}},{"code_sha256_prefix":"fdbc405da9b53f2c","entry":"update_normal_metrics","repo":"sta8is/dino-foresight","repo_kind":"official","path":"src/dino_f.py","file_url":"https://github.com/sta8is/dino-foresight/blob/HEAD/src/dino_f.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":"fdbc405da9b53f2c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}