Rana Hanocka (@RanaHanocka) / X

Rana Hanocka

595 posts

Rana Hanocka

@RanaHanocka

Assistant Professor @uchicago. Founder & CEO of Thrixel. PhD from @TelAvivUni. Interested in computer graphics, machine learning, & computer vision 🤖

Chicago, IL

people.cs.uchicago.edu/~ranahanocka/

Joined October 2012

Pinned
Rana Hanocka
@RanaHanocka
Aug 15, 2025
We’ve been building something we’re 𝑟𝑒𝑎𝑙𝑙𝑦 excited about – LL3M: LLM-powered agents that turn text into editable 3D assets. LL3M models shapes as interpretable Blender code, making geometry, appearance, and style easy to modify. 🔗 threedle.github.io/ll3m 1/
00:00
47K
Rana Hanocka
@RanaHanocka
Dec 24, 2022
I asked chatgpt to generate an .obj file of a tetrahedron. It generated a list of vertices/faces in the .obj format. If you paste that into an empty file, it will open up in a 3D viewer, like meshlab! (It's even topologically correct: manifold, correct face normals, etc) 1/
00:00
274K
Rana Hanocka
@RanaHanocka
May 24, 2021
Excited to share that I will be joining the University of Chicago as an assistant professor this July! Recruiting students for PhD / research opportunities in computer graphics + deep learning. Reach out if you're interested! @UChicago @UChicagoCS 🏙️🧠🤖
Rana Hanocka
@RanaHanocka
May 25, 2020
Excited to share our #SIGGRAPH2020 paper Point2Mesh. This work leverages the inductive bias of CNNs to learn a "self-prior" for 3D surface reconstruction. The self-prior learns the reoccurring geometric structures from a single shape. Project page: ranahanocka.github.io/point2mesh/ (1/4)
GIF
Rana Hanocka
@RanaHanocka
May 10, 2021
📢📢 Introducing "Learning Skeletal Articulations with Neural Blend Shapes" #SIGGRAPH2021 We train a network to learn rigging, skinning, and blend shapes using "indirect" supervision: simply observing pairs of joint rotations + deformed shapes 🤯! 1/4 peizhuoli.github.io/neural-blend-s…
GIF
Rana Hanocka
@RanaHanocka
Apr 4, 2022
Excited to share our Text2Mesh [#CVPR2022] paper on 3D mesh stylization 🎨 Our framework stylizes an input mesh by adding color + local geometric details to conform to a user-specified text description. We do this w/o a 3D training dataset 👀💪 1/9 threedle.github.io/text2mesh/
GIF
Rana Hanocka
@RanaHanocka
May 6, 2022
Thrilled to share "GANimator: Neural Motion Synthesis from a Single Sequence", in this upcoming #SIGGRAPH2022 🤩 GANimator can produce novel animations for unique creatures that don't have large motion datasets! For example, this hexapedal crab 🦀(1/4)
GIF
Rana Hanocka
@RanaHanocka
Jul 21, 2021
📣"Self-Sampling for Neural Point Cloud Consolidation" ToG 2021 paper. It doesn't require training data 🙌! TLDR; Training a neural network on the *single* input point cloud gives a sharper, and less noisy version of the input point cloud itself! 1/4 bit.ly/selfsamp
GIF
Rana Hanocka
@RanaHanocka
Jul 9, 2022
This shows the ability to perform localized & semantic edits in a video using CLIP, & looks super cool! We see that CLIP contains semantic part-level understanding when performing synthesis.
00:00
00:49
Tali Dekel
@talidekel
Jul 9, 2022
Billion params text-to-image models are amazing! But...not designed for editing real-world images/videos. Text2LIVE (ECCV oral) trains on 1 example and allows for various semantic, localized editing! text2live.github.io @omerbartal @dolevofri @RafailFridman @yoni_kasten 1/3
Rana Hanocka
@RanaHanocka
Nov 17, 2023
Excited to share 🎨🖌️ 3D Paintbrush - a method for generating local stylized textures on meshes using text as input! Our method predicts a localization map & a highly detailed texture map which conforms to it threedle.github.io/3d-paintbrush/ (1/3)
00:00
49K
Rana Hanocka
@RanaHanocka
Oct 17, 2024
Excited to share MeshUp ⬆️, a framework for deforming a mesh into a blend of various target concepts! MeshUp offers control over the influence of each concept by changing the associated weights. Project page: threedle.github.io/MeshUp/ 🧵1/
00:00
23K
Rana Hanocka
@RanaHanocka
Aug 2, 2020
Workshop on Geometric Deep Learning is starting now ⚛️! You can also watch from the youtube livestream:
iGDL 2020: Israeli Geometric Deep Learning Workshop
From youtube.com
Rana Hanocka
@RanaHanocka
Feb 11, 2022
TIL that you can get a wiki page for any paper posted in arxiv by replacing the .org with .wiki directly in the url link 🤯
Rana Hanocka
@RanaHanocka
Jul 8, 2020
We're excited to announce the first Israeli workshop on geometric deep learning🤖! Come hear talks by @lipmanya @GalChechik and @mmbronstein Aug 2. There will also be talks on some of the cutting edge research coming from Israel. Website: gdl-israel.github.io