Model Based Augmentation and Testing of an Annotated Hand Pose Dataset

Bellon, Richárd; Choi, Younggeon; Ekker, Nikoletta; Lepetit, Vincent; Olasz, L. Mike; Sonntag, Daniel; TźSér, Zoltán; Yoo, Kyounghwan; LźRincz, András

doi:10.1007/978-3-319-46073-4_2

Cited by 5 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other more complex augmentation methods could be model-based, use learned generative models, and even GANs [24,5,22,3,26,8,19,20].…”

Section: Related Workmentioning

confidence: 99%

Implicit Pairs for Boosting Unpaired Image-to-Image Translation

Ginger,

Danon,

Averbuch-Elor

et al. 2019

Preprint

View full text Add to dashboard Cite

In image-to-image translation the goal is to learn a mapping from one image domain to another. In the case of supervised approaches the mapping is learned from paired samples. However, collecting large sets of image pairs is often either prohibitively expensive or not possible. As a result, in recent years more attention has been given to techniques that learn the mapping from unpaired sets.In our work, we show that injecting implicit pairs into unpaired sets strengthens the mapping between the two domains, improves the compatibility of their distributions, and leads to performance boosting of unsupervised techniques by over 14% across several measurements.The competence of the implicit pairs is further pronounced with the use of pseudo-pairs, i.e., paired samples which only approximate a real pair. We demonstrate the effect of the approximated implicit samples on image-toimage translation problems, where such pseudo-pairs may be synthesized in one direction, but not in the other. We further show that pseudo-pairs are significantly more effective as implicit pairs in an unpaired setting, than directly using them explicitly in a paired setting.

show abstract

“…Other more complex augmentation methods could be model-based, use learned generative models, and even GANs [24,5,22,3,26,8,19,20].…”

Section: Related Workmentioning

confidence: 99%

Implicit Pairs for Boosting Unpaired Image-to-Image Translation

Ginger,

Danon,

Averbuch-Elor

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, data augmentation is important. Though expensive, commercial digital gloves have been used to get hand motion data, and the rigged hand mesh model is rendered as training images [23,5]. Comparatively affordable, model based tracking [22] and 2D based annotation [11] have been used to generate synthetic data more efficiently.…”

Section: Related Workmentioning

confidence: 99%

Hand3D: Hand Pose Estimation using 3D Neural Network

Deng,

Yang,

Zhang

et al. 2017

Preprint

View full text Add to dashboard Cite

We propose a novel 3D neural network architecture for 3D hand pose estimation from a single depth image. Different from previous works that mostly run on 2D depth image domain and require intermediate or post process to bring in the supervision from 3D space, we convert the depth map to a 3D volumetric representation, and feed it into a 3D convolutional neural network(CNN) to directly produce the pose in 3D requiring no further process. Our system does not require the ground truth reference point for initialization, and our network architecture naturally integrates both local feature and global context in 3D space. To increase the coverage of the hand pose space of the training data, we render synthetic depth image by transferring hand pose from existing real image datasets. We evaluation our algorithm on two public benchmarks and achieve the state-ofthe-art performance. The synthetic hand pose dataset will be available. * indicates equal contribution. and optimized by a predefined hand model to reduce error that is significant in 3D space but not apparent in 2D image domain. Such post-process has been thoroughly studied but far from optimal, and [20] shows that even a directly searching of nearest neighbors pose in 3D space could also achieve performance close to the state of the art, which shows the benefits of directly solving pose estimation in 3D space.

show abstract