{"paper":{"title":"EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"A diffusion model with temporally asymmetric noise schedule reconstructs full-body motion online from egocentric inputs.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donggeun Lim, Hojun Jang, Inwoo Hwang, Young Min Kim","submitted_at":"2026-05-13T05:53:26Z","abstract_excerpt":"With recent advances in embodied agents and AR devices, egocentric observations are readily available as input for real-world interactive online applications. However, egocentric viewpoints can only sporadically observe hands, in addition to the estimated head trajectory. We propose EgoForce, an online framework for reconstructing long-term full-body motion from noisy egocentric input. While existing generative frameworks can robustly handle noisy and sparse measurements, they assume a fixed-length observation window is available and are thus not suitable for real-time applications. Faster inf"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments demonstrate that our online framework outperforms existing online and offline methods, enabling long-horizon, full-body motion reconstruction in challenging egocentric scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the temporally asymmetric noise schedule combined with noise-robust imputation will produce stable coherent motion under strict causal constraints when observations of hands are sporadic and noisy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EgoForce reconstructs long-horizon full-body motion online from sparse noisy egocentric views by incrementally denoising with a temporally asymmetric diffusion schedule and noise-robust imputation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A diffusion model with temporally asymmetric noise schedule reconstructs full-body motion online from egocentric inputs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0657c42c4667ed0bf091177f04571db55b39aef571e2d77c65d9b081355a19e8"},"source":{"id":"2605.13041","kind":"arxiv","version":1},"verdict":{"id":"b42db5f2-7117-4486-aa70-bde2c40b43fa","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:36:17.430054Z","strongest_claim":"Experiments demonstrate that our online framework outperforms existing online and offline methods, enabling long-horizon, full-body motion reconstruction in challenging egocentric scenarios.","one_line_summary":"EgoForce reconstructs long-horizon full-body motion online from sparse noisy egocentric views by incrementally denoising with a temporally asymmetric diffusion schedule and noise-robust imputation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the temporally asymmetric noise schedule combined with noise-robust imputation will produce stable coherent motion under strict causal constraints when observations of hands are sporadic and noisy.","pith_extraction_headline":"A diffusion model with temporally asymmetric noise schedule reconstructs full-body motion online from egocentric inputs."},"references":{"count":51,"sample":[{"doi":"","year":2025,"title":"HOT3D: Hand and object tracking in 3D from egocentric multi-view videos.CVPR, 2025","work_id":"799d954b-d0db-4f61-8239-6312daee5430","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"From sparse signal to smooth motion: Real-time motion generation with rolling prediction models","work_id":"85dfa5e2-5299-4a9f-bb22-75b50d9ff6f7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Diffusion forcing: Next-token prediction meets full-sequence diffusion, 2024","work_id":"a58cb8d8-4270-4f67-baa2-556f65df2f90","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Taming diffusion probabilistic models for character control","work_id":"e2942cfa-d5a5-4bfc-82ce-baf2b430949d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Diffusion policy: Visuomotor policy learning via action diffusion","work_id":"d58a2d3e-38bd-4131-970c-fa4683c3e46e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":51,"snapshot_sha256":"84761ee0aaf5196e80dd87dafa0e9a9bf9ef7430c7c3b4d966e2422e196ec567","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}