Metraipolis › archive › dc_998dadf00982
Learning to read residual images for single-pixel photography — arXiv:2611.03729
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03729
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:35:37.581Z
- SHA-256 of the archived text
8f60d236a13d441edb9f7b45e917207c3b00108a8cbc05deaa6e7c750fa2c226- Stable URL of this page
https://metraipolis.com/documento/dc_998dadf00982
How to cite
Learning to read residual images for single-pixel photography — arXiv:2611.03729 — arXiv (en), https://arxiv.org/abs/2611.03729 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_998dadf00982 (Metraipolis archive dc_998dadf00982, sha256 8f60d236a13d441edb9f7b45e917207c3b00108a8cbc05deaa6e7c750fa2c226)
BibTeX
@misc{dc998dadf00982,
title = {Learning to read residual images for single-pixel photography — arXiv:2611.03729},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03729},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_998dadf00982; sha256 8f60d236a13d441edb9f7b45e917207c3b00108a8cbc05deaa6e7c750fa2c226},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03729. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Continuous video scales in cost with camera count, resolution and recording duration, yet many monitoring tasks seek events rather than complete images and can operate on a compact single-pixel measurement stream. Recovering a chosen interval as video is then desirable, but at 0.24\% of the pixel count the scene correlation image looks like noise and per-clip optimization takes minutes. Correlating the residual of an estimate with the coding patterns nevertheless gives a residual image, the gradient of a centered measurement loss. Lifted through a pretrained video decoder, its agreement with the true error exceeds that of control decoders. Video-latent inversion (VLI) then outperforms frame-wise image-latent reconstruction at 1{,}000 bucket values. Measurement-Gradient-Conditioned Video Flow (MGV-Flow), trained once to read the lifted residual image with preceding frames, reconstructs five frames in 1.55\,s at 22.9\,dB median PSNR, against 398\,s and 18.1\,dB for VLI, with the largest gains in high-motion scenes. Directional fidelity ranks 30 coding configurations and selects one needing a third fewer bucket values. On a physical system, MGV-Flow outperforms per-frame reconstruction without retraining. A sliding window over the bucket-value stream yields 3.2 frames per second on one RTX~4090 and, in theory, 20 frames per second on a data-centre accelerator. Demonstrations are available at this https URL .
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.03729 — 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 2026-11-04T18:32:37.378Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).