704 citations · 4.1k across the 112 of their papers we have counts for
16 papers · 2 filters
Hausdorff Point Convolution with Geometric Priors
Pengdi Huang, Liqiang Lin, Fuyou Xue +3
Without a shape-aware response, it is hard to characterize the 3D geometry of a point cloud efficiently with a compact set of kernels. In this paper, we advocate the use of Hausdor…
BalaGAN: Image Translation Between Imbalanced Domains via Cross-Modal Transfer
Or Patashnik, Dov Danon, Hao Zhang +1
State-of-the-art image-to-image translation methods tend to struggle in an imbalanced domain setting, where one image domain lacks richness and diversity. We introduce a new unsupe…
Neural Alignment for Face De-pixelization
Maayan Shuvi, Noa Fish, Kfir Aberman +2
We present a simple method to reconstruct a high-resolution video from a face-video, where the identity of a person is obscured by pixelization. This concealment method is popular…
Object Properties Inferring from and Transfer for Human Interaction Motions
Qian Zheng, Weikai Wu, Hanting Pan +3
Humans regularly interact with their surrounding objects. Such interactions often result in strongly correlated motion between humans and the interacting objects. We thus ask: "Is…
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
Elad Richardson, Yuval Alaluf, Or Patashnik +4
We present a generic image-to-image translation framework, pixel2style2pixel (pSp). Our pSp framework is based on a novel encoder network that directly generates a series of style…
MRGAN: Multi-Rooted 3D Shape Generation with Unsupervised Part Disentanglement
Rinon Gal, Amit Bermano, Hao Zhang +1
We present MRGAN, a multi-rooted adversarial network which generates part-disentangled 3D point-cloud shapes without part-based shape supervision. The network fuses multiple branch…
MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency
Mingyi Shi, Kfir Aberman, Andreas Aristidou +4
We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video.While previous methods rely on either rigging or inve…
DO-Conv: Depthwise Over-parameterized Convolutional Layer
Jinming Cao, Yangyan Li, Mingchao Sun +5
Convolutional layers are the core building blocks of Convolutional Neural Networks (CNNs). In this paper, we propose to augment a convolutional layer with an additional depthwise c…
Towards a Neural Graphics Pipeline for Controllable Image Generation
Xuelin Chen, Daniel Cohen-Or, Baoquan Chen +1
In this paper, we leverage advances in neural networks towards forming a neural rendering for controllable image generation, and thereby bypassing the need for detailed modeling in…
Skeleton-Aware Networks for Deep Motion Retargeting
Kfir Aberman, Peizhuo Li, Dani Lischinski +3
We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, yet corresponding to homeomorphic graphs. Imp…
Face Identity Disentanglement via Latent Space Mapping
Yotam Nitzan, Amit Bermano, Yangyan Li +1
Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to cont…
Single Pair Cross-Modality Super Resolution
Guy Shacht, Sharon Fogel, Dov Danon +2
Non-visual imaging sensors are widely used in the industry for different purposes. Those sensors are more expensive than visual (RGB) sensors, and usually produce images with lower…
Structural-analogy from a Single Image Pair
Sagie Benaim, Ron Mokady, Amit Bermano +2
The task of unsupervised image-to-image translation has seen substantial advancements in recent years through the use of deep neural networks. Typically, the proposed solutions lea…
Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
Moab Arar, Yiftach Ginger, Dov Danon +3
Many applications, such as autonomous driving, heavily rely on multi-modal data where spatial alignment between the modalities is required. Most multi-modal registration methods st…
A Rotation-Invariant Framework for Deep Point Cloud Analysis
Xianzhi Li, Ruihui Li, Guangyong Chen +3
Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to ar…
GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation
Wallace Lira, Johannes Merz, Daniel Ritchie +2
We introduce GANHopper, an unsupervised image-to-image translation network that transforms images gradually between two domains, through multiple hops. Instead of executing transla…