activity
20172021
most citedPoint2Mesh: A Self-Prior for Deformable Meshes

235 citations · 1k across the 29 of their papers we have counts for

collaborators

76 papers

cs.CV2022

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…

cs.CV2022

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…

cs.CV20229 cited

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…

cs.CV2022

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…

cs.CV20221 cited

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…

cs.CV20223 cited

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…