Metraipolis › archive › dc_258a05d00840
Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation — arXiv:2609.35368
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35368
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:54:44.796Z
- SHA-256 of the archived text
7768ea91c1a8b098e6e6619472e4cb4045c639974a9a72b27d5e5c3d837098fe- Stable URL of this page
https://metraipolis.com/documento/dc_258a05d00840
How to cite
Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation — arXiv:2609.35368 — arXiv (en), https://arxiv.org/abs/2609.35368 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_258a05d00840 (Metraipolis archive dc_258a05d00840, sha256 7768ea91c1a8b098e6e6619472e4cb4045c639974a9a72b27d5e5c3d837098fe)
BibTeX
@misc{dc258a05d00840,
title = {Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation — arXiv:2609.35368},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35368},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_258a05d00840; sha256 7768ea91c1a8b098e6e6619472e4cb4045c639974a9a72b27d5e5c3d837098fe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35368. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Exo-to-egocentric video generation aims to synthesize what a person sees from their own viewpoint given third-person footage and a target head trajectory. The task requires transferring appearance and semantics across large viewpoint changes while hallucinating content never observed by the exocentric camera. Existing approaches either impose additional input requirements, such as a ground-truth initial egocentric frame or multiple synchronized exocentric views, or remain limited to category-specific settings. EgoX is the first to address cross-activity and in-the-wild generalization, but requires a human-provided caption of the non-existent egocentric view at inference and introduces a computationally expensive geometry-guided attention bias that can propagate reconstruction errors and suppress textual and visual context. We therefore propose \textbf{Ego-Forge}, a caption-free and bias-free framework for exo-to-egocentric generation. It introduces \textit{Dynamic Captioning}, which derives conditioning tokens directly from the model's hidden states and adapts them to the diffusion timestep and network depth, replacing external text conditioning. By scaling training by an order of magnitude and using all available exocentric viewpoints, Ego-Forge learns cross-view correspondence implicitly and eliminates the need for geometry-guided attention, requiring only a lightweight depth prior. Ego-Forge achieves state-of-the-art performance on Ego-Exo4D, runs faster end-to-end, requires no external annotation at inference, and generalizes to in-the-wild scenes, including cases where over-reliance on geometry blocks appearance inference. Our model and source code will be made publicly available.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.35368 — 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 2026-10-07T23:29:27.556Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).