We are a computer graphics collective at UChicago led by Rana Hanocka, pursuing innovation at the intersection of 3D and Deep Learning.

People

News

2023-06-18

3DL attends CVPR 2023

3DL presents 2 papers

2023-03-31

3DL @ MSI

National Robotics Week

2023-02-27

Congrats to Dale and Richard!

Highlighter & DA Wand accepted to CVPR 2023

2023-01-09

Hackathon on 3D Representations

3DL & PALS Hackathon

Research

Our research is focused on building artificial intelligence for 3D data, spanning the fields of computer graphics, machine learning, and computer vision. Deep Learning, the most popular form of artificial intelligence, has unlocked remarkable success on structured data (such as text, images, and video), and we are interested in harnessing the potential of these techniques to enable effective operation on unstructured 3D geometric data.

We have developed a convolutional neural network designed specifically for meshes, and also explored how to learn from the internal data within a single shape (for surface reconstruction, geometric texture synthesis, and point cloud consolidation) - and are interested in broader applications related to these areas. Additional research directions that we are aiming to explore include: intertwining human and machine-based creativity to advance our capabilities in 3D shape modeling and animation; learning with less supervision, for example to extract patterns and relationships from large shape collections; and making 3D neural networks more interpretable and explainable.

Follow our github organization for updates on our latest research.

TextDeformer: Geometry Manipulation using Text Guidance
William Gao, Noam Aigerman, Thibault Groueix, Vladimir G. Kim, and Rana Hanocka
SIGGRAPH 2023
DA Wand: Distortion-Aware Selection using Neural Mesh Parameterization
Richard Liu, Noam Aigerman, Vladimir G. Kim, and Rana Hanocka
CVPR 2023
3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions
Dale Decatur, Itai Lang, and Rana Hanocka
CVPR 2023
GeoCode: Interpretable Shape Programs
Ofek Pearl, Itai Lang, Yuhua Hu, Raymond A. Yeh, and Rana Hanocka
ArXiv 2022
LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing
Nam Anh Dinh, Haochen Wang, Greg Shakhnarovich, and Rana Hanocka
ArXiv 2022
GLAZE: Protecting Artists from Style Mimicry by Text-to-Image Models
Shawn Shan, Jenna Cryan, Emily Wenger, Haitao Zheng, Rana Hanocka, Ben Y. Zhao
ArXiv 2023
TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation
William Gao, April Wang, Gal Metzer, Raymond A. Yeh, and Rana Hanocka
BMVC 2022 (Oral)
GANimator: Neural Motion Synthesis from a Single Sequence
Peizhuo Li, Kfir Aberman, Zihan Zhang, Rana Hanocka and Olga Sorkine-Hornung
SIGGRAPH 2022
Text2Mesh: Text-Driven Neural Stylization for Meshes
Oscar Michel*, Roi Bar-On*, Richard Liu*, Sagie Benaim, and Rana Hanocka (* equal contribution)
CVPR 2022 (Oral)
The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference
Russel K. Jones, Aalia Habib, Rana Hanocka, and Daniel Ritchie
CVPR 2022
Z2P: Instant Visualization of Point Clouds
Gal Metzer, Rana Hanocka, Raja Giryes, Niloy J. Mitra, and Daniel Cohen-Or
Eurographics 2022
NeuralMLS: Geometry-Aware Control Point Deformation
Meitar Shechter, Rana Hanocka, Gal Metzer, Raja Giryes, and Daniel Cohen-Or
Eurographics Short Paper 2022
Orienting Point Clouds With Dipole Propagation
Gal Metzer, Rana Hanocka, Denis Zorin, Raja Giryes, Daniele Panozzo, and Daniel Cohen-Or
ACM Transactions on Graphics (Proc. SIGGRAPH) 2021
Learning Skeletal Articulations With Neural Blend Shapes
Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, Olga Sorkine-Hornung, and Baoquan Chen
ACM Transactions on Graphics (Proc. SIGGRAPH) 2021
Self-Sampling for Neural Point Cloud Consolidation
Gal Metzer, Rana Hanocka, Raja Giryes, and Daniel Cohen-Or
ACM Transactions on Graphics (TOG) 2021
Point2Mesh: A Self-Prior for Deformable Meshes
Rana Hanocka, Gal Metzer, Raja Giryes, and Daniel Cohen-Or
ACM Transactions on Graphics (Proc. SIGGRAPH) 2020
Deep Geometric Texture Synthesis
Amir Hertz*, Rana Hanocka*, Raja Giryes, and Daniel Cohen-Or (* joint first authors)
ACM Transactions on Graphics (Proc. SIGGRAPH) 2020
PointGMM: a Neural GMM Network for Point Clouds
Amir Hertz, Rana Hanocka, Raja Giryes, and Daniel Cohen-Or
CVPR 2020
MeshCNN: A Network with an Edge
Rana Hanocka, Amir Hertz, Noa Fish, Raja Giryes, Shachar Fleishman and Daniel Cohen-Or
ACM Transactions on Graphics (Proc. SIGGRAPH) 2019
Blind Visual Motif Removal from a Single Image
Amir Hertz, Sharon Fogel, Rana Hanocka, Raja Giryes, and Daniel Cohen-Or
CVPR 2019 (Oral)
ALIGNet: Partial-Shape Agnostic Alignment via Unsupervised Learning
Rana Hanocka, Noa Fish, Zhenhua Wang, Raja Giryes, Shachar Fleishman and Daniel Cohen-Or
ACM Transactions on Graphics (TOG) 2018
Fast and Easy Blind Deblurring Using an Inverse Filter and PROBE
Naftali Zon*, Rana Hanocka*, Nahum Kiryati (* joint first authors)
Proc. 17th International Conference on Computer Analysis of Images and Patterns (CAIP 2017)
Progressive Blind Deconvolution
Rana Hanocka, Nahum Kiryati
Proc. 16th International Conference on Computer Analysis of Images and Patterns (CAIP 2015)

Courses

Blog

2022-04-07

How to run blender on the cluster

a Threedle guide to running blender headlessly