Metraipolis › archive › dc_3a2f303db987
From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video — arXiv:2609.08636
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08636
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:12:19.296Z
- SHA-256 of the archived text
e743323de6fe46b65c8d355608d0f6a6c8631b9aa97768932bc0f24554008f77- Stable URL of this page
https://metraipolis.com/documento/dc_3a2f303db987
How to cite
From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video — arXiv:2609.08636 — arXiv (en), https://arxiv.org/abs/2609.08636 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a2f303db987 (Metraipolis archive dc_3a2f303db987, sha256 e743323de6fe46b65c8d355608d0f6a6c8631b9aa97768932bc0f24554008f77)
BibTeX
@misc{dc3a2f303db987,
title = {From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video — arXiv:2609.08636},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08636},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a2f303db987; sha256 e743323de6fe46b65c8d355608d0f6a6c8631b9aa97768932bc0f24554008f77},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08636. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Egocentric 4D interaction forecasting aims to anticipate both where future interactions will occur in 3D and how the human body will move to realize them, providing an important capability for assistive robotics and human-computer interaction. Existing methods struggle to translate semantic understanding into precise continuous 3D localization and to balance motion diversity with structural consistency in pose forecasting. More fundamentally, these tasks are often modeled separately, leaving the continuous geometric and temporal correspondence between interaction locations and body motion insufficiently captured. To address these challenges, we introduce Coherent4D, a large-scale egocentric dataset for continuous 4D interaction forecasting, comprising approximately 233K samples across three domains. Each sample pairs a sequence of future 3D interaction locations with corresponding full-body poses, aligned in time and expressed in a shared coordinate system. We also provide evaluation metrics in continuous space. Building on this formulation, we propose HIGFlow, a Hand Interaction Guided Residual Flow framework that models forecasting as a cascaded where-to-how process. HIGFlow first forecasts continuous future interaction locations by combining semantic grounding with short-horizon visual dynamics, and then uses the predicted location sequence to condition a deterministic motion anchor and residual Flow Matching for diverse yet structurally consistent full-body motion forecasting. Extensive experiments across all three domains demonstrate consistent improvements over representative baselines on both location and pose forecasting, while ablations validate the contributions of the proposed components. The project page is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.08636 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T14:49:57.331Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).