Metraipolis › archive › dc_5258cd920525

ReX-Shot: Single-Image Rephotography via Geometry- and Camera-Grounded Generation — arXiv:2608.18593

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18593
License (as archived)
CC0-1.0
Archived
2026-10-18T14:06:17.620Z
SHA-256 of the archived text
673bbcace7ae23c6f77550ba944047707e0cf62511f325e7c627c9ad11b28e3c
Stable URL of this page
https://metraipolis.com/documento/dc_5258cd920525

How to cite

ReX-Shot: Single-Image Rephotography via Geometry- and Camera-Grounded Generation — arXiv:2608.18593 — arXiv (en), https://arxiv.org/abs/2608.18593 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5258cd920525 (Metraipolis archive dc_5258cd920525, sha256 673bbcace7ae23c6f77550ba944047707e0cf62511f325e7c627c9ad11b28e3c)
BibTeX
@misc{dc5258cd920525,
  title = {ReX-Shot: Single-Image Rephotography via Geometry- and Camera-Grounded Generation — arXiv:2608.18593},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18593},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5258cd920525; sha256 673bbcace7ae23c6f77550ba944047707e0cf62511f325e7c627c9ad11b28e3c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18593. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Single-image rephotography aims to synthesize new shots of a scene from a single reference image with specified viewpoints, focal lengths, and photographic effects, which are intrinsically coupled in imaging. Existing methods typically treat these factors separately and struggle under joint control: novel-view synthesis may introduce geometric distortions under focal-length changes, while super-resolution and instruction-guided editing remain confined to 2D and cannot reliably extend detail restoration or appearance control to novel viewpoints. We attribute these limitations to imperfect single-image 3D reconstruction and the sampling limit of continuous focal-length enlargement. To reduce projection bias from geometric errors, we use implicitly transformed foundation-model features for robust target-view guidance. We further formulate focal-length enlargement as a geometry-guided super-resolution problem and exploit generative detail priors to recover details lost during sparse 3D resampling. Built on this 3D-aware generative backbone, we lift photographic-effect control from 2D filtering to 3D-aware appearance editing, preserving content consistency across viewpoints and focal lengths. These components form ReX-Shot, a geometry- and camera-grounded generative framework for single-image rephotography. To our knowledge, ReX-Shot is the first unified framework to jointly control viewpoint, focal length, and parameterized photographic effects from a single image. Experiments show that ReX-Shot outperforms representative baselines across all three controls while enabling near-real-time interactive rephotography.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.18593 — 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 2026-10-18T14:00:22.559Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).