Back to Search
Start Over
Learning a perceptual manifold with deep features for animation video resequencing
- Publication Year :
- 2021
-
Abstract
- We propose a novel deep learning framework for animation video resequencing. Our system produces new video sequences by minimizing a perceptual distance of images from an existing animation video clip. To measure perceptual distance, we utilize the activations of convolutional neural networks and learn a perceptual distance by training these features on a small network with data comprised of human perceptual judgments. We show that with this perceptual metric and graph-based manifold learning techniques, our framework can produce new smooth and visually appealing animation video results for a variety of animation video styles. In contrast to previous work on animation video resequencing, the proposed framework applies to wide range of image styles and does not require hand-crafted feature extraction, background subtraction, or feature correspondence. In addition, we also show that our framework has applications to appealing arrange unordered collections of images.<br />Comment: Under major revision; Project website: http://graphics.csie.ncku.edu.tw/ManifoldAnimationSequence
- Subjects :
- Computer Science - Graphics
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2111.01455
- Document Type :
- Working Paper