Multi-frame Restoration for High-rate Lissajous Confocal Laser Endomicroscopy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910190442381312 |
|---|---|
| author | Lee, Minhee Lee, Sangyoon Lee, Jiwook Hong, Minki Kim, Kyuyoung Kim, Won Hwa Lee, Jaeho |
| author_facet | Lee, Minhee Lee, Sangyoon Lee, Jiwook Hong, Minki Kim, Kyuyoung Kim, Won Hwa Lee, Jaeho |
| contents | Lissajous confocal laser endomicroscopy (CLE) is a promising solution for high speed in vivo optical biopsy for handheld scenarios. However, Lissajous scanning traces a resonant trajectory and samples only the visited pixels per frame; at high frame rates, many pixels remain unvisited, creating structured holes. In this work, we introduce the first benchmark for high-rate Lissajous CLE, consisting of low-quality video clips paired with high-quality reference images. The reference images are wide-FOV mosaics obtained by stitching stabilized, slow-scan frames of the same tissue, enabling temporally aligned supervision. Using this dataset, we propose MIRA, a lightweight recurrent framework for Lissajous CLE restoration that iteratively aggregates temporal context through feature reuse and displacement alignment. Our experiments demonstrate that MIRA outperforms both lightweight and high-complexity baselines in restoration quality while maintaining a favorable computational efficiency suitable for clinical deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00527 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-frame Restoration for High-rate Lissajous Confocal Laser Endomicroscopy Lee, Minhee Lee, Sangyoon Lee, Jiwook Hong, Minki Kim, Kyuyoung Kim, Won Hwa Lee, Jaeho Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Lissajous confocal laser endomicroscopy (CLE) is a promising solution for high speed in vivo optical biopsy for handheld scenarios. However, Lissajous scanning traces a resonant trajectory and samples only the visited pixels per frame; at high frame rates, many pixels remain unvisited, creating structured holes. In this work, we introduce the first benchmark for high-rate Lissajous CLE, consisting of low-quality video clips paired with high-quality reference images. The reference images are wide-FOV mosaics obtained by stitching stabilized, slow-scan frames of the same tissue, enabling temporally aligned supervision. Using this dataset, we propose MIRA, a lightweight recurrent framework for Lissajous CLE restoration that iteratively aggregates temporal context through feature reuse and displacement alignment. Our experiments demonstrate that MIRA outperforms both lightweight and high-complexity baselines in restoration quality while maintaining a favorable computational efficiency suitable for clinical deployment. |
| title | Multi-frame Restoration for High-rate Lissajous Confocal Laser Endomicroscopy |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2605.00527 |