Sorry, you need to enable JavaScript to visit this website.

MAT-NET: REPRESENTING APPEARANCE-IRRELEVANT WARP FIELD BY MULTIPLE AFFINE TRANSFORMATIONS

Citation Author(s):
Jingwei liu,Longquan Dai
Submitted by:
Jingwei Liu
Last updated:
24 September 2021 - 3:53am
Document Type:
Presentation Slides
Document Year:
2021
Event:
Presenters Name:
Jingwei Liu
Paper Code:
2253

Abstract 

Abstract: 

Warp-based methods for image animation estimate a warp
field what do a rearrangement on the pixels of the input image to roughly align with the target image. Current methods
predict accurate warp field by using manually annotated data.
In this paper, we propose a simple method (MAT-net) to predict more precise warp field in self-supervised way. MAT-net
decomposes complex spatial object movement between two
images into multiple simple local motions (i.e. affine transformation) occurring in different areas of images. Sequentially, our model calculates a warp field depicting complex
object movement by combining all local motions. MAT-net
encodes appearance-irrelevant object movement accurately.
Compared to the state-of-the-art method, MAT-net generates
more realistic images with faster inference speed. We published the source code of our project online.

up
0 users have voted:

Dataset Files

presentation.pptx

(8)