Professional Documents
Culture Documents
Unsup3D
5
Photo-Geometric Autoencoding
input 𝐈
decoder decoder
Reconstruction
Loss
Renderer
reconstruction 𝐈መ
6
Photo-Geometric Autoencoding
Q1: How to avoid degenerate solutions?
input 𝐈
decoder decoder
Reconstruction
Loss
Renderer
reconstruction 𝐈መ
7
Photo-Geometric Autoencoding
Q1: How to avoid degenerate solutions? A1: Enforce symmetry
input 𝐈
decoder decoder
Reconstruction
Loss
Renderer
reconstruction 𝐈መ
8
Photo-Geometric Autoencoding
Q1: How to avoid degenerate solutions? A1: Enforce symmetry by flipping
: horizontal flip
input 𝐈
decoder decoder
? ?
view 𝑤 depth 𝑑 depth 𝑑′ texture flipped
9
Photo-Geometric Autoencoding
Q1: How to avoid degenerate solutions? A1: Enforce symmetry by flipping
: horizontal flip
input 𝐈
decoder decoder
? ?
view 𝑤 depth 𝑑 depth 𝑑′ texture flipped
flip switch
Reconstruction
Loss
? Renderer
reconstruction 𝐈መ
10
Photo-Geometric Autoencoding
Q1: How to avoid degenerate solutions? A1: Enforce symmetry by flipping
: horizontal flip
input 𝐈
decoder decoder
? ?
view 𝑤 depth 𝑑 depth 𝑑′ texture flipped
flip switch
Reconstruction
Loss
Renderer
reconstruction 𝐈መ
11
Photo-Geometric Autoencoding
Q1: How to avoid degenerate solutions? A1: Enforce symmetry by flipping
: horizontal flip
input 𝐈
decoder decoder
? ?
view 𝑤 depth 𝑑 depth 𝑑′ texture flipped
flip switch
Reconstruction
Loss
? Renderer
reconstruction 𝐈መ
12
Photo-Geometric Autoencoding
Q1: How to avoid degenerate solutions? A1: Enforce symmetry by flipping
: horizontal flip
input 𝐈
decoder decoder
flip switch
Reconstruction
Loss
Renderer
reconstruction 𝐈መ
13
Photo-Geometric Autoencoding
Q2: What about non-symmetric lighting?
: horizontal flip
input 𝐈
decoder decoder
14
Photo-Geometric Autoencoding
Q2: What about non-symmetric lighting? A2: Enforce symmetry on albedo
: horizontal flip
input 𝐈
decoder decoder
flip switch
Reconstruction
Loss
shading
Renderer
decoder decoder
flip switch
Reconstruction
Loss
shading
Renderer
flip switch
Reconstruction
Loss
shading
Renderer
24
input reconstruction input reconstruction 25
Results on face paintings
Images taken from [1]
[1] Elliot J. Crowley, Omkar M. Parkhi, and Andrew Zisserman. Face painting: querying art with photos. In Proc. BMVC, 2015. 26
input reconstruction input reconstruction 27
Results on abstract faces
Images taken from [1] and the Internet
[1] Elliot J. Crowley, Omkar M. Parkhi, and Andrew Zisserman. Face painting: querying art with photos. In Proc. BMVC, 2015. 28
input reconstruction input reconstruction 29
Results on video frames
Video clips taken from VoxCeleb2
We do not use videos for training or fine-tuning. These results are obtained
by applying our model trained on CelebA frame by frame.
30
31
input
input
Relighting effects
Video clips taken from CelebA
32
input reconstruction input reconstruction 33
Results on cat faces
Images taken from [2] and [3]
[2] Weiwei Zhang, Jian Sun, and Xiaoou Tang. Cat head detection - how to effectively exploit shape and texture features. In Proc. ECCV, 2008.
[3] Omkar M. Parkhi, Andrea Vedaldi, Andrew Zisserman, and C. V. Jawahar. Cats and dogs. In Proc. CVPR, 2012. 34
input reconstruction input reconstruction 35
Thank you!
Demo: https://bit.ly/2zBNjXx
Code: https://github.com/elliottwu/unsup3d
38