Metraipolis › archive › dc_7da17a102f13

PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video — arXiv:2610.01279

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01279
License (as archived)
CC0-1.0
Archived
2026-10-06T12:13:25.728Z
SHA-256 of the archived text
17161b84fda7b67eabad1787862147946125f12514e96d9d8181696cedda91f5
Stable URL of this page
https://metraipolis.com/documento/dc_7da17a102f13

How to cite

PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video — arXiv:2610.01279 — arXiv (en), https://arxiv.org/abs/2610.01279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7da17a102f13 (Metraipolis archive dc_7da17a102f13, sha256 17161b84fda7b67eabad1787862147946125f12514e96d9d8181696cedda91f5)
BibTeX
@misc{dc7da17a102f13,
  title = {PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video — arXiv:2610.01279},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01279},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7da17a102f13; sha256 17161b84fda7b67eabad1787862147946125f12514e96d9d8181696cedda91f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Motion blur arises from the temporal integration of a continuous sharp signal over a finite exposure window, yet existing learning-based methods sidestep this physical model and predict only the sharp signal itself: most single-image deblurring methods recover a single frame at the exposure center, while blur-to-video methods predict a fixed set of frames. We introduce PickMoment, a continuous-time reformulation that directly learns the interval-mean blur over arbitrary sub-intervals of the exposure with a single deterministic model. Drawing an analogy to MeanFlow's average-velocity formulation, we train the model with three supervisions derived from the blur integral: an empirical reconstruction loss from available subframes, an additivity loss that enforces self-consistency across overlapping sub-intervals, and a sharp-frame loss anchored at the zero-interval limit. A single trained model unifies single-image deblurring, blur-to-video generation, and continuous-time pick-a-moment recovery as different queries to the same network, with no separate training for each task. Our PickMoment achieves state-of-the-art performance among generative-based deblurring methods on GoPro and HIDE while competitive against restoration-based methods on RealBlur, and the highest per-frame fidelity on GoPro-7 blur-to-video, all in a single forward pass without iterative sampling.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.01279 — 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 2026-10-06T10:21:28.173Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).