PixelSpline: Continuous Space-Time Video Super-Resolution via Endpoint-Anchored Shared Pixel Trajectories

Wanqi Yuan, Nianyi Li

YAYIN:4 Kas 2026 ALAN:cs.CV

Özet

Existing continuous space-time video super-resolution methods often infer motion from only two endpoint frames and model the two motion directions independently, making them vulnerable to ambiguous correspondence and inconsistent trajectories. We introduce a continuous STVSR framework that combines long-context encoding, continuous HR feature lifting, and an endpoint-anchored PixelSpline. Long-range observations provide more reliable endpoint representations, while continuous upsampling constructs detailed appearance features directly on the requested HR grid. PixelSpline explicitly models each pixel's motion as a single continuous trajectory shared by both endpoints. Using this trajectory, our method warps endpoint colors into a coarse intermediate frame and aligns the HR features for residual reconstruction. Experiments across spatial and temporal upsampling settings demonstrate that the proposed framework offers a favorable quality--efficiency trade-off.

Özetle: Existing continuous space-time video super-resolution methods often infer motion from only two endpoint frames and model the two motion directions independently, making them vulnerable to ambiguous correspondence and in…

Özet

Orijinal Özet (İngilizce)

Existing continuous space-time video super-resolution methods often infer motion from only two endpoint frames and model the two motion directions independently, making them vulnerable to ambiguous correspondence and inconsistent trajectories. We introduce a continuous STVSR framework that combines long-context encoding, continuous HR feature lifting, and an endpoint-anchored PixelSpline. Long-range observations provide more reliable endpoint representations, while continuous upsampling constructs detailed appearance features directly on the requested HR grid. PixelSpline explicitly models each pixel's motion as a single continuous trajectory shared by both endpoints. Using this trajectory, our method warps endpoint colors into a coarse intermediate frame and aligns the HR features for residual reconstruction. Experiments across spatial and temporal upsampling settings demonstrate that the proposed framework offers a favorable quality–efficiency trade-off.

Kaynak: arXiv:2611.06870 · PDF

BibTeX

@article{yuan2026pixelspline,
  title   = {PixelSpline: Continuous Space-Time Video Super-Resolution via Endpoint-Anchored Shared Pixel Trajectories},
  author  = {Wanqi Yuan and Nianyi Li},
  journal = {arXiv preprint arXiv:2611.06870},
  year    = {2026},
  url     = {https://arxiv.org/abs/2611.06870}
}

Tartışma

Bu habere emoji ile tepki ver

İptal

Hizli:

Henüz yorum yok. İlk yorumu siz yapın!

Yapıcı ve saygılı yorumlar bekliyoruz. Topluluk kuralları