Metraipolis › archive › dc_fa560bbb4d5d

RTLViT: real-time lensless reconstruction with a lightweight vision transformer — arXiv:2609.21042

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.21042
License (as archived): CC0-1.0
Archived: 2026-10-10T03:15:46.281Z
SHA-256 of the archived text: 84368078b281fa9a920156053e6796a6f709d7eefcbdddf65ea49b081ca3b0d1
Stable URL of this page: https://metraipolis.com/documento/dc_fa560bbb4d5d

How to cite

RTLViT: real-time lensless reconstruction with a lightweight vision transformer — arXiv:2609.21042 — arXiv (en), https://arxiv.org/abs/2609.21042 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa560bbb4d5d (Metraipolis archive dc_fa560bbb4d5d, sha256 84368078b281fa9a920156053e6796a6f709d7eefcbdddf65ea49b081ca3b0d1)

BibTeX

@misc{dcfa560bbb4d5d,
  title = {RTLViT: real-time lensless reconstruction with a lightweight vision transformer — arXiv:2609.21042},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21042},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa560bbb4d5d; sha256 84368078b281fa9a920156053e6796a6f709d7eefcbdddf65ea49b081ca3b0d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21042. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mask-based lensless imagers capture measurements using simple, compact hardware and recover images using a reconstruction algorithm. The reconstruction algorithm affects the image quality, inference speed, and computational requirements of the imaging system, often trading off image quality against computational efficiency. Advancing toward integrated lensless imagers, where encoding and reconstruction occur within a single device (e.g., a mobile phone), requires a fast, high-quality, and practical reconstruction method. We introduce the Real-Time Lensless Vision Transformer (RTLViT), a lightweight, purely data-driven reconstruction architecture for high-quality and real-time lensless reconstruction. With only 1.09 million learnable parameters, RTLViT provides higher-quality reconstructions than both real-time baselines and substantially larger attention-based architectures, including improvements of up to 3.46 dB in peak signal-to-noise ratio over architectures with $15 \times$ more learnable parameters. We demonstrate that RTLViT maintains high-quality reconstructions across a wide range of training dataset sizes and two different mask designs (lenslets and a diffuser). Finally, we implement real-time reconstruction with RTLViT on laptops and smartphones, supporting future integrated lensless imagers for real-time applications.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in eess.IV).
Categorie arXiv: Optics (physics.optics) ; Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2609.21042 — 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 2026-10-10T03:03:36.913Z dalla pagina https://arxiv.org/catchup/eess.IV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).