International journal of computer vision, 2019-08, Vol.127 (8), p.1106-1125
2019
Details
- Autor(en) / Beteiligte
- Titel
- Video Enhancement with Task-Oriented Flow
- Ist Teil von
- International journal of computer vision, 2019-08, Vol.127 (8), p.1106-1125
- Ort / Verlag
- New York: Springer US
- Erscheinungsjahr
- 2019
- Link zum Volltext
- Quelle
- Alma/SFX Local Collection
- Beschreibungen/Notizen
- Many video enhancement algorithms rely on optical flow to register frames in a video sequence. Precise flow estimation is however intractable; and optical flow itself is often a sub-optimal representation for particular video processing tasks. In this paper, we propose task-oriented flow (TOFlow), a motion representation learned in a self-supervised, task-specific manner. We design a neural network with a trainable motion estimation component and a video processing component, and train them jointly to learn the task-oriented flow. For evaluation, we build Vimeo-90K, a large-scale, high-quality video dataset for low-level video processing. TOFlow outperforms traditional optical flow on standard benchmarks as well as our Vimeo-90K dataset in three video processing tasks: frame interpolation, video denoising/deblocking, and video super-resolution.
- Sprache
- Englisch
- Identifikatoren
- ISSN: 0920-5691eISSN: 1573-1405DOI: 10.1007/s11263-018-01144-2Titel-ID: cdi_proquest_journals_2178841239
- Format
- –
- Schlagworte
- Algorithms, Artificial Intelligence, Computer Imaging, Computer Science, Image processing, Image Processing and Computer Vision, Interpolation, Licensed products, Motion simulation, Neural networks, Noise reduction, Optical flow (image analysis), Pattern Recognition, Pattern Recognition and Graphics, Representations, Video, Vision, VLSI