Metraipolis › archive › dc_a9bdd07e595c

LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation — arXiv:2610.12442

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12442
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:58.005Z
SHA-256 of the archived text
6b5c801887ec4774be8f2ad60d8b14c0055ccd334efddb8bb40a309c399811d7
Stable URL of this page
https://metraipolis.com/documento/dc_a9bdd07e595c

How to cite

LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation — arXiv:2610.12442 — arXiv (en), https://arxiv.org/abs/2610.12442 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a9bdd07e595c (Metraipolis archive dc_a9bdd07e595c, sha256 6b5c801887ec4774be8f2ad60d8b14c0055ccd334efddb8bb40a309c399811d7)
BibTeX
@misc{dca9bdd07e595c,
  title = {LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation — arXiv:2610.12442},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12442},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a9bdd07e595c; sha256 6b5c801887ec4774be8f2ad60d8b14c0055ccd334efddb8bb40a309c399811d7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12442. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating an egocentric video from a single exocentric recording is a challenging case of novel view synthesis, as the two cameras share little overlap and much of the target view is unobserved. Current state-of-the-art methods reconstruct the scene explicitly by estimating depth, lifting the video into a point cloud, and re-rendering it from the egocentric camera to condition a video diffusion model. This deterministic mapping assigns each pixel to a single reprojected location, which preserves texture but translates depth errors into misplaced content. We ask what a video diffusion model should receive as its condition and propose a lifting-free answer: a learned view synthesizer, an LVSM-style transformer fine-tuned to render the egocentric view directly without depth, point clouds, or reprojection, resolving cross-view correspondence internally. In contrast, its probabilistic mapping averages each region over candidate source locations according to a learned correspondence distribution, preserving structure while fine texture is averaged away. We argue that this trade-off suits a diffusion generator, whose denoising training excels at restoring detail, so an effective condition should prioritize structural alignment over sharpness. This distribution's concentration also yields a per-region confidence, used both to mask low-confidence regions and to guide the generator toward high-confidence areas during early layout-forming denoising steps. Our approach consistently outperforms the state-of-the-art explicit pipeline and generalizes to other datasets without retraining. The synthesizer thus supplies view structure, and the diffusion model its detail.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.12442 — 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 2026-10-09T05:55:07.713Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).