Metraipolis › archive › dc_8b387697227a

Recurrent Dynamic Range Extension — arXiv:2609.13135

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13135
License (as archived)
CC0-1.0
Archived
2026-10-16T03:57:54.542Z
SHA-256 of the archived text
c7bf3d32594c1848c0221c65894dd7b3a966193f9f56f3566eb3a047c726d35f
Stable URL of this page
https://metraipolis.com/documento/dc_8b387697227a

How to cite

Recurrent Dynamic Range Extension — arXiv:2609.13135 — arXiv (en), https://arxiv.org/abs/2609.13135 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b387697227a (Metraipolis archive dc_8b387697227a, sha256 c7bf3d32594c1848c0221c65894dd7b3a966193f9f56f3566eb3a047c726d35f)
BibTeX
@misc{dc8b387697227a,
  title = {Recurrent Dynamic Range Extension — arXiv:2609.13135},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13135},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b387697227a; sha256 c7bf3d32594c1848c0221c65894dd7b3a966193f9f56f3566eb3a047c726d35f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13135. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present an approach to progressively extend the highlights of an image. Instead of reconstructing the full dynamic range of a complex scene directly, we learn a simpler task first: We extend the dynamic range of an input image by a single exposure value. Once this is mastered, we retrieve the full HDR image for the scene by executing our network recurrently, progressively increasing the dynamic range of the input. Our formulation is agnostic to the input dynamic range and targets a bounded output domain. This enables us to use widely available RAW images for the reconstruction task and adapt adversarial losses to construct realistic images. By incorporating Memory Replay for backpropagation, we can train our network recurrently over multiple inference stages and reduce reconstruction errors. As a consequence, our system reconstructs challenging long-tailed HDR scenes robustly and shows powerful recovery of bright light sources and highlights.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.13135 — 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 2026-10-16T03:44:26.348Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).