Metraipolis › archive › dc_29bbbc181af8

Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues — arXiv:2608.11075

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.11075
License (as archived): CC0-1.0
Archived: 2026-10-19T06:30:38.319Z
SHA-256 of the archived text: 5394e98b5050acbd7672c5664119af5159b87a95b6845f65510faca7dbbf5912
Stable URL of this page: https://metraipolis.com/documento/dc_29bbbc181af8

How to cite

Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues — arXiv:2608.11075 — arXiv (en), https://arxiv.org/abs/2608.11075 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29bbbc181af8 (Metraipolis archive dc_29bbbc181af8, sha256 5394e98b5050acbd7672c5664119af5159b87a95b6845f65510faca7dbbf5912)

BibTeX

@misc{dc29bbbc181af8,
  title = {Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues — arXiv:2608.11075},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11075},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29bbbc181af8; sha256 5394e98b5050acbd7672c5664119af5159b87a95b6845f65510faca7dbbf5912},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11075. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Event cameras capture intensity changes asynchronously with high temporal resolution, requiring novel preprocessing methods for downstream tasks. Unlike static intensity snapshots, event data inherently encode information about scene dynamics and object motion, meaning that features derived from events can exhibit behaviors with no direct analogue in frame-based vision. In this paper, we analyze two features used in event-based corner detection---the eigenvalues of the structure tensor and the spatiotemporal density values---and show that they are \emph{motion cues}. We hypothesize that these features, combined with local geometric information, can enhance motion estimation tasks. To validate this, we first theoretically analyze how the eigenvalues of the structure tensor at moving corner points relate to the direction of motion. We then design controlled experiments on a synthetic dataset, confirming that extending local geometric features with eigenvalues and density values provides complementary motion information and is robust to texture and shot noise. Finally, we integrate the proposed features into a state-of-the-art event-based optical flow network and evaluate on the real-world DSEC benchmark, where the added features consistently improve accuracy, with the largest gains in data-scarce scenarios and for lower-capacity models. The code for this paper can be found at: \href{ this https URL }{ this https URL }.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.11075 — 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 2026-10-19T06:25:27.314Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).