Search Results for author: Rana Hanocka

Found 15 papers, 12 papers with code

GANimator: Neural Motion Synthesis from a Single Sequence

1 code implementation5 May 2022 Peizhuo Li, Kfir Aberman, Zihan Zhang, Rana Hanocka, Olga Sorkine-Hornung

We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence.

Frame motion synthesis +1

DeepMLS: Geometry-Aware Control Point Deformation

no code implementations5 Jan 2022 Meitar Shechter, Rana Hanocka, Gal Metzer, Raja Giryes, Daniel Cohen-Or

In this work, we opt to learn the weighting function, by training a neural network on the control points from a single input shape, and exploit the innate smoothness of neural networks.

Text2Mesh: Text-Driven Neural Stylization for Meshes

1 code implementation6 Dec 2021 Oscar Michel, Roi Bar-On, Richard Liu, Sagie Benaim, Rana Hanocka

In order to modify style, we obtain a similarity score between a text prompt (describing style) and a stylized mesh by harnessing the representational power of CLIP.

Neural Stylization

The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference

1 code implementation22 Jun 2021 R. Kenny Jones, Aalia Habib, Rana Hanocka, Daniel Ritchie

We propose the Neurally-Guided Shape Parser (NGSP), a method that learns how to assign fine-grained semantic labels to regions of a 3D shape.

Semantic Segmentation

Learning Skeletal Articulations with Neural Blend Shapes

1 code implementation6 May 2021 Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, Olga Sorkine-Hornung, Baoquan Chen

Furthermore, we propose neural blend shapes--a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning.

Orienting Point Clouds with Dipole Propagation

1 code implementation4 May 2021 Gal Metzer, Rana Hanocka, Denis Zorin, Raja Giryes, Daniele Panozzo, Daniel Cohen-Or

In the global phase, we propagate the orientation across all coherent patches using a dipole propagation.

Self-Sampling for Neural Point Cloud Consolidation

1 code implementation14 Aug 2020 Gal Metzer, Rana Hanocka, Raja Giryes, Daniel Cohen-Or

We introduce a novel technique for neural point cloud consolidation which learns from only the input point cloud.

Deep Geometric Texture Synthesis

1 code implementation30 Jun 2020 Amir Hertz, Rana Hanocka, Raja Giryes, Daniel Cohen-Or

Learning and synthesizing on local geometric patches enables a genus-oblivious framework, facilitating texture transfer between shapes of different genus.

Image Generation Texture Synthesis

Point2Mesh: A Self-Prior for Deformable Meshes

2 code implementations22 May 2020 Rana Hanocka, Gal Metzer, Raja Giryes, Daniel Cohen-Or

We optimize the network weights to deform an initial mesh to shrink-wrap a single input point cloud.

PointGMM: a Neural GMM Network for Point Clouds

1 code implementation CVPR 2020 Amir Hertz, Rana Hanocka, Raja Giryes, Daniel Cohen-Or

We present PointGMM, a neural network that learns to generate hGMMs which are characteristic of the shape class, and also coincide with the input point cloud.

Blind Visual Motif Removal from a Single Image

1 code implementation CVPR 2019 Amir Hertz, Sharon Fogel, Rana Hanocka, Raja Giryes, Daniel Cohen-Or

Many images shared over the web include overlaid objects, or visual motifs, such as text, symbols or drawings, which add a description or decoration to the image.

MeshCNN: A Network with an Edge

1 code implementation16 Sep 2018 Rana Hanocka, Amir Hertz, Noa Fish, Raja Giryes, Shachar Fleishman, Daniel Cohen-Or

In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes.

3D Part Segmentation Cube Engraving Classification

ALIGNet: Partial-Shape Agnostic Alignment via Unsupervised Learning

1 code implementation23 Apr 2018 Rana Hanocka, Noa Fish, Zhenhua Wang, Raja Giryes, Shachar Fleishman, Daniel Cohen-Or

The process of aligning a pair of shapes is a fundamental operation in computer graphics.

Fast and easy blind deblurring using an inverse filter and PROBE

no code implementations4 Feb 2017 Naftali Zon, Rana Hanocka, Nahum Kiryati

PROBE (Progressive Removal of Blur Residual) is a recursive framework for blind deblurring.


Cannot find the paper you are looking for? You can Submit a new open access paper.