235 citations · 1k across the 29 of their papers we have counts for
76 papers
Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons
Oren Katzir, Dani Lischinski, Daniel Cohen-Or
We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose. Our encoder is stable and consistent, meani…
MotionCLIP: Exposing Human Motion Generation to CLIP Space
Guy Tevet, Brian Gordon, Amir Hertz +2
We introduce MotionCLIP, a 3D human motion auto-encoder featuring a latent embedding that is disentangled, well behaved, and supports highly semantic textual descriptions. MotionCL…
State-of-the-Art in the Architecture, Methods and Applications of StyleGAN
Amit H. Bermano, Rinon Gal, Yuval Alaluf +5
Generative Adversarial Networks (GANs) have established themselves as a prevalent approach to image synthesis. Of these, StyleGAN offers a fascinating case study, owing to its rema…
Self-Distilled StyleGAN: Towards Generation from Internet Photos
Ron Mokady, Michal Yarom, Omer Tov +5
StyleGAN is known to produce high-fidelity images, while also offering unprecedented semantic editing. However, these fascinating abilities have been demonstrated only on a limited…
Multi-level Latent Space Structuring for Generative Control
Oren Katzir, Vicky Perepelook, Dani Lischinski +1
Truncation is widely used in generative models for improving the quality of the generated samples, at the expense of reducing their diversity. We propose to leverage the StyleGAN g…
Self-Conditioned Generative Adversarial Networks for Image Editing
Yunzhe Liu, Rinon Gal, Amit H. Bermano +2
Generative Adversarial Networks (GANs) are susceptible to bias, learned from either the unbalanced data, or through mode collapse. The networks focus on the core of the data distri…