ββTransferring Dense Pose to Proximal Animal Classes
Article on how to train DensePose for animals withiout labels
DensePose approach predicts the pose of humans densely and accurately given a large dataset of poses annotated in detail. It's super expensive to collect DensePose annotations for all different classes of animals. So authors show that, at least for proximal animal classes such as chimpanzees, it is possible to transfer the knowledge existing in DensePose for humans. They propose to utilize the existing annotations of humans and do self-training on unlabeled images of animals.
Link: https://asanakoy.github.io/densepose-evolution/
YouTube: https://youtu.be/OU3Ayg_l4QM
Paper: https://arxiv.org/pdf/2003.00080.pdf
#Facebook #FAIR #CVPR #CVPR2020 #posetransfer #dl
Article on how to train DensePose for animals withiout labels
DensePose approach predicts the pose of humans densely and accurately given a large dataset of poses annotated in detail. It's super expensive to collect DensePose annotations for all different classes of animals. So authors show that, at least for proximal animal classes such as chimpanzees, it is possible to transfer the knowledge existing in DensePose for humans. They propose to utilize the existing annotations of humans and do self-training on unlabeled images of animals.
Link: https://asanakoy.github.io/densepose-evolution/
YouTube: https://youtu.be/OU3Ayg_l4QM
Paper: https://arxiv.org/pdf/2003.00080.pdf
#Facebook #FAIR #CVPR #CVPR2020 #posetransfer #dl
YouTube
DensePose applied on chimps: comparison of our method before self-training (left) and after (right)
Frame-by-frame predictions produced by our model before (teacher) and after self-training (student).
After self training the 24-class body part segmentation is more accurate and stable.
Project page: https://asanakoy.github.io/densepose-evolution/
After self training the 24-class body part segmentation is more accurate and stable.
Project page: https://asanakoy.github.io/densepose-evolution/
ββBackground Matting: The World is Your Green Screen
ThΡ authors propose a method for creating a matte β the per-pixel foreground color and alpha β of a person by taking photos or videos in an everyday setting with a handheld camera. Most existing matting methods require a green screen background or a manually created trimap to produce a good matte.
Automatic, trimap-free methods are appearing, but are not of comparable quality. In them trimap free approach, they ask the user to take an additional photo of the background without the subject at the time of capture. This step requires a small amount of foresight but is far less timeconsuming than creating a trimap.
They train a deep network with an adversarial loss to predict the matte. At first, they train a matting network with the supervised loss on ground truth data with synthetic composites. To bridge the domain gap to real imagery with no labeling, train another matting network guided by the first network and by a discriminator that judges the quality of composites.
paper: https://arxiv.org/abs/2004.00626
blog post: http://grail.cs.washington.edu/projects/background-matting/
github (training code coming soon): https://github.com/senguptaumd/Background-Matting
#CVPR2020 #background #matte
ThΡ authors propose a method for creating a matte β the per-pixel foreground color and alpha β of a person by taking photos or videos in an everyday setting with a handheld camera. Most existing matting methods require a green screen background or a manually created trimap to produce a good matte.
Automatic, trimap-free methods are appearing, but are not of comparable quality. In them trimap free approach, they ask the user to take an additional photo of the background without the subject at the time of capture. This step requires a small amount of foresight but is far less timeconsuming than creating a trimap.
They train a deep network with an adversarial loss to predict the matte. At first, they train a matting network with the supervised loss on ground truth data with synthetic composites. To bridge the domain gap to real imagery with no labeling, train another matting network guided by the first network and by a discriminator that judges the quality of composites.
paper: https://arxiv.org/abs/2004.00626
blog post: http://grail.cs.washington.edu/projects/background-matting/
github (training code coming soon): https://github.com/senguptaumd/Background-Matting
#CVPR2020 #background #matte
