.png){kind=icon}
Return
Video Enhancement with Task-Oriented Flow
.png){kind=icon}
OA
AI
DOI：10.1007/s11263-018-01144-2.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Video processing
Optical flow
Neural network
Video dataset
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.3
Papers:
3.9K
Citations:
2.8W
Organization
Cited Papers
ShareSaveShareSave
ShareSaveNonlocal video denoising, simplification and inpainting using discrete regularization on graphs.png)
SIGNAL PROCESSING
SIGNAL PROCESSINGIF3.6
PREAI
ShareSaveShareSave
View more