AIT Lab
@ait_eth
The Advanced Interactive Technologies Lab at @ETH does research at the intersection of Machine Learning, Computer Vision and Human Computer Interaction (HCI).
This year we have 4 challenges using GigaHand, OakInk-v2, ARCTIC, HOT3D and GraspM3! Join our mailing list here (forms.gle/jJVHSQdE9ETuWm…) to be notified when the challenge registration opens! @Michael_J_Black @drsrinathsridha
Our @ICCVConference HANDS workshop will be on Oct. 20, PM! We focus on hand-related areas, e.g., hand pose est., hand-object interaction, robotics hand manipulation. hands-workshop.org @NUSingapore @CSatETH @unibirmingham @RealityLabs @AIatMeta @UTokyo_News @meshcapade
How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.
📢📢Introducing "Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models" TL;DR: We show that with a few modifications to how the CFG update is applied, we can vastly mitigate the oversaturation and artifacts of high guidance scales. See the 🧵
🎉🎉Thrilled to share that we have two papers accepted at ICLR 2025! 🎉🎉 Looking forward to meeting everyone in Singapore 🇸🇬 Details are in the following threads 🧵👇
LiteVAE is a lightweight variational autoencoder for latent diffusion models. It will be presented next week at @NeurIPSConf
Excited to present our recent work "LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models" next week at #NeurIPS2024. Please join us at our poster session next Thursday (December 12th) from 11:00 - 14:00 at East Exhibit Hall A-C #2604. 👇🧵
#3DV2025AMA Fourth guest on the Ask Me Anything series: Jia-Bin Huang @jbhuang0604 from University of Maryland & Meta! Jia-Bin was the engine behind all the fun tweets of last year 3DV 🌟 🕒 You have now 24 HOURS to ask him anything — drop your questions in the comments below!
Yesterday, we presented Cafca---our latest work on casual few-shot face captures---at @SIGGRAPHAsia in Tokyo. Check out our talk: youtu.be/soNSzodOUvs We release a dataset of 1.7 Mio. multi-view, multi-environment, multi-expression face images for research.
A model that generates hand-object interactions based on text prompts! I'm happy to share our @SIGGRAPHAsiapaper “DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions”. diffh2o.github.io
Cafca reconstructs faces with only a few images! Check out Marcel’s talk at @SIGGRAPHAsia !
Yesterday, we presented Cafca---our latest work on casual few-shot face captures---at @SIGGRAPHAsia in Tokyo. Check out our talk: youtu.be/soNSzodOUvs We release a dataset of 1.7 Mio. multi-view, multi-environment, multi-expression face images for research.