Linearized Multi-Sampling for Differentiable Image Transformation

Wei Jiang, Weiwei Sun, Andrea Tagliasacchi, Eduard Trulls, Kwang Moo Yi


Qualitative Highlights:

We show qualitative examples highlighting the impact of our method on image alignment. To align images, we directly optimize a Spatial Transformer Network [14] to output a 32x32 image, and minimize the L2 distance between the output image and a target image. Please see paper for details.


Video Abstract:

This video is a quick abstract of our method. Please see paper for details.




Supplementary Appendix:

Supplementary appendix is available here


Reference:

[14]  M. Jaderberg, K. Simonyan, A. Zisserman, and K. Kavukcuoglu. "Spatial Transformer Networks."" NIPS, pages 2017-2025, 2015


The supplementary videos are encoded by FFMPEG with h.264 codec.
If you can't play the video, please download the VLC player at: http://www.videolan.org/vlc/index.html