MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909776202432512 |
|---|---|
| author | Ciubotariu, George Zhou, Zhuyun Wu, Zongwei Timofte, Radu |
| author_facet | Ciubotariu, George Zhou, Zhuyun Wu, Zongwei Timofte, Radu |
| contents | We introduce MIORe and VAR-MIORe, two novel multi-task datasets that address critical limitations in current motion restoration benchmarks. Designed with high-frame-rate (1000 FPS) acquisition and professional-grade optics, our datasets capture a broad spectrum of motion scenarios, which include complex ego-camera movements, dynamic multi-subject interactions, and depth-dependent blur effects. By adaptively averaging frames based on computed optical flow metrics, MIORe generates consistent motion blur, and preserves sharp inputs for video frame interpolation and optical flow estimation. VAR-MIORe further extends by spanning a variable range of motion magnitudes, from minimal to extreme, establishing the first benchmark to offer explicit control over motion amplitude. We provide high-resolution, scalable ground truths that challenge existing algorithms under both controlled and adverse conditions, paving the way for next-generation research of various image and video restoration tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration Ciubotariu, George Zhou, Zhuyun Wu, Zongwei Timofte, Radu Computer Vision and Pattern Recognition We introduce MIORe and VAR-MIORe, two novel multi-task datasets that address critical limitations in current motion restoration benchmarks. Designed with high-frame-rate (1000 FPS) acquisition and professional-grade optics, our datasets capture a broad spectrum of motion scenarios, which include complex ego-camera movements, dynamic multi-subject interactions, and depth-dependent blur effects. By adaptively averaging frames based on computed optical flow metrics, MIORe generates consistent motion blur, and preserves sharp inputs for video frame interpolation and optical flow estimation. VAR-MIORe further extends by spanning a variable range of motion magnitudes, from minimal to extreme, establishing the first benchmark to offer explicit control over motion amplitude. We provide high-resolution, scalable ground truths that challenge existing algorithms under both controlled and adverse conditions, paving the way for next-generation research of various image and video restoration tasks. |
| title | MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.06803 |