Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.12286 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908962043985920 |
|---|---|
| author | Xue, Clara Yan, Zizheng Shi, Zhenning Yu, Yuhang Zhuang, Jingyu Zhang, Qi Chen, Jinwei Fan, Qingnan |
| author_facet | Xue, Clara Yan, Zizheng Shi, Zhenning Yu, Yuhang Zhuang, Jingyu Zhang, Qi Chen, Jinwei Fan, Qingnan |
| contents | Live Photo captures both a high-quality key photo and a short video clip to preserve the precious dynamics around the captured moment. While users may choose alternative frames as the key photo to capture better expressions or timing, these frames often exhibit noticeable quality degradation, as the photo capture ISP pipeline delivers significantly higher image quality than the video pipeline. This quality gap highlights the need for dedicated restoration techniques to enhance the reselected key photo. To this end, we propose LiveMoments, a reference-guided image restoration framework tailored for the reselected key photo in Live Photos. Our method employs a two-branch neural network: a reference branch that extracts structural and textural information from the original high-quality key photo, and a main branch that restores the reselected frame using the guidance provided by the reference branch. Furthermore, we introduce a unified Motion Alignment module that incorporates motion guidance for spatial alignment at both the latent and image levels. Experiments on real and synthetic Live Photos demonstrate that LiveMoments significantly improves perceptual quality and fidelity over existing solutions, especially in scenes with fast motion or complex structures. Our code is available at https://github.com/OpenVeraTeam/LiveMoments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12286 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion Xue, Clara Yan, Zizheng Shi, Zhenning Yu, Yuhang Zhuang, Jingyu Zhang, Qi Chen, Jinwei Fan, Qingnan Computer Vision and Pattern Recognition Live Photo captures both a high-quality key photo and a short video clip to preserve the precious dynamics around the captured moment. While users may choose alternative frames as the key photo to capture better expressions or timing, these frames often exhibit noticeable quality degradation, as the photo capture ISP pipeline delivers significantly higher image quality than the video pipeline. This quality gap highlights the need for dedicated restoration techniques to enhance the reselected key photo. To this end, we propose LiveMoments, a reference-guided image restoration framework tailored for the reselected key photo in Live Photos. Our method employs a two-branch neural network: a reference branch that extracts structural and textural information from the original high-quality key photo, and a main branch that restores the reselected frame using the guidance provided by the reference branch. Furthermore, we introduce a unified Motion Alignment module that incorporates motion guidance for spatial alignment at both the latent and image levels. Experiments on real and synthetic Live Photos demonstrate that LiveMoments significantly improves perceptual quality and fidelity over existing solutions, especially in scenes with fast motion or complex structures. Our code is available at https://github.com/OpenVeraTeam/LiveMoments. |
| title | LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.12286 |