Metraipolis › archive › dc_4fece0bea24c
ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction — arXiv:2609.39624
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39624
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:46:17.722Z
- SHA-256 of the archived text
b011d3675d1925c7e3611efabf175163172214439175d8ae8e24bb770cd08c97- Stable URL of this page
https://metraipolis.com/documento/dc_4fece0bea24c
How to cite
ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction — arXiv:2609.39624 — arXiv (en), https://arxiv.org/abs/2609.39624 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fece0bea24c (Metraipolis archive dc_4fece0bea24c, sha256 b011d3675d1925c7e3611efabf175163172214439175d8ae8e24bb770cd08c97)
BibTeX
@misc{dc4fece0bea24c,
title = {ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction — arXiv:2609.39624},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39624},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fece0bea24c; sha256 b011d3675d1925c7e3611efabf175163172214439175d8ae8e24bb770cd08c97},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39624. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Single-image HDR reconstruction requires inferring missing detail while preserving the visible content of an LDR image. Differences in sensor dynamic range and exposure cause LDR images to lose varying amounts of information in shadows and highlights. We present ExpandDiff, a conditional diffusion pipeline that jointly reconstructs clipped shadows and highlights. To account for this variation, we introduce Dynamic Clipping Synthesis (DCS), which randomly samples shadow and highlight clipping percentiles when constructing training inputs from HDR targets. A pixel-space diffusion model guided by spatially-adaptive normalization then predicts perceptually encoded HDR through a bounded output head, reconstructing both clipping directions in one sampling trajectory. On the SI-HDR benchmark, ExpandDiff variants improve HDR reconstruction accuracy by 3.43 dB in PU21-PSNR over the strongest evaluated competing method, and by 7.34 dB under two-sided clipping. The code and supplementary material are available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2609.39624 — 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 2026-10-07T14:19:00.780Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).