Metraipolis › archive › dc_79ea7f1d833e
Unwarping the Lens: A Physics-Grounded Approach to Video Glasses Removal — arXiv:2608.20212
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20212
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:04:50.508Z
- SHA-256 of the archived text
2d271aa83a947572f59da26046c002535a6cb37d298e4747d7d8a4727170cc49- Stable URL of this page
https://metraipolis.com/documento/dc_79ea7f1d833e
How to cite
Unwarping the Lens: A Physics-Grounded Approach to Video Glasses Removal — arXiv:2608.20212 — arXiv (en), https://arxiv.org/abs/2608.20212 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_79ea7f1d833e (Metraipolis archive dc_79ea7f1d833e, sha256 2d271aa83a947572f59da26046c002535a6cb37d298e4747d7d8a4727170cc49)
BibTeX
@misc{dc79ea7f1d833e,
title = {Unwarping the Lens: A Physics-Grounded Approach to Video Glasses Removal — arXiv:2608.20212},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20212},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_79ea7f1d833e; sha256 2d271aa83a947572f59da26046c002535a6cb37d298e4747d7d8a4727170cc49},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20212. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-fidelity removal of eyeglasses from video is a major challenge in facial attribute editing, as the underlying facial geometry is often obscured by complex refractive distortions and view-dependent specular reflections. While large-scale generative priors have shown promise in eye-glasses removal via static image inpainting, they often lack the structural constraints necessary to maintain identity, expression, and pose, leading to visible "identity drift" in both static images and dynamic sequences. In this paper, we propose a novel transfer framework that addresses the stochastic nature of generative priors. Our pipeline first extracts high-fidelity synthetic face images from a commercial-grade generative model (Nano Banana, Gemini 3 Pro Image), regularizes them via a three-stage structural filtering process to preserve identity, expression, and pose, and finally applies physically-based simulation of lens optics during training to provide diverse, paired data. This process transfers Nano Banana's photo-realistic, multi-view knowledge into a specialized restoration architecture, JFSnet (Joint Feature-Spatial network). JFSnet integrates DINOv2-based semantic features with a convolutional decoder for spatial reconstruction, leveraging translation equivariance constraints to improve temporal consistency and high-frequency detail preservation. Evaluations on the curated Flickr-Faces-HQ (FFHQ) subset (12,163 images) show that our approach achieves high fidelity and structural accuracy, while maintaining inference speed of 27.68 FPS. In perceptual studies on CelebV-Text video sequences, our results are consistently preferred over diffusion and GAN-based baselines for ocular consistency, temporal stability, and overall restoration quality. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.20212 — 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 2026-10-18T12:01:57.747Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).