Metraipolis › archive › dc_dbdb14de36ab
ZoomDiff: A High-Fidelity Diffusion Model for Dual-Camera Smooth Zooming — arXiv:2609.28083
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28083
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:35:12.175Z
- SHA-256 of the archived text
9dc3c0fed150498151e5caa4fe21b109e85016ebf7af40fcaf1cb8732e44c71b- Stable URL of this page
https://metraipolis.com/documento/dc_dbdb14de36ab
How to cite
ZoomDiff: A High-Fidelity Diffusion Model for Dual-Camera Smooth Zooming — arXiv:2609.28083 — arXiv (en), https://arxiv.org/abs/2609.28083 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbdb14de36ab (Metraipolis archive dc_dbdb14de36ab, sha256 9dc3c0fed150498151e5caa4fe21b109e85016ebf7af40fcaf1cb8732e44c71b)
BibTeX
@misc{dcdbdb14de36ab,
title = {ZoomDiff: A High-Fidelity Diffusion Model for Dual-Camera Smooth Zooming — arXiv:2609.28083},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28083},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbdb14de36ab; sha256 9dc3c0fed150498151e5caa4fe21b109e85016ebf7af40fcaf1cb8732e44c71b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28083. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Digital zoom transitions between dual cameras often exhibit conspicuous discontinuities in geometric structure and chromatic consistency, degrading the user experience. While recent dual-camera smooth zoom (DCSZ) methods attempt to mitigate this by fine-tuning frame interpolation (FI) models on DCSZ data, they struggle with the large cross-view disparities and complex geometric transformations. Considering that the generative prior of diffusion models is suitable for addressing this problem, we explore their application to DCSZ. However, naively applying existing diffusion-based FI models still yields low-fidelity transitions due to insufficient conditional guidance, high-frequency information loss during VAE encoding, as well as inadequate temporal consistency. To address this, we propose ZoomDiff, a high-fidelity diffusion model that leverages dual-camera inputs in both latent and pixel spaces for photo-realistic transitions. Specifically, we first strengthen dual-image conditional guidance during the multi-step denoising process to improve geometric consistency. Then we inject flow-aligned multi-scale features from the VAE encoder into the VAE decoder to recover high-frequency details, where flow-guided temporal consistency supervision are introduced to produce more smooth transitions. Extensive experiments on both synthetic and real-world datasets demonstrate that ZoomDiff outperforms state-of-the-art methods quantitatively and qualitatively. Project page: this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.28083 — 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 2026-10-08T12:12:35.766Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).