AIT Lab

@hohs_ETH will present GaussianWardrobe at #3DV2026 Come and chat with us on March-21 morning. ▷ Linkedin post: linkedin.com/posts/hohs_3dv… 📷 Website: eth-ait.github.io/GaussianWardro… 📷 Paper: arxiv.org/abs/2603.04290

🎥 Some example visualizations / demo results (baseline outputs):

Interested in football ⚽ and AI? The FIFA Skeletal Light Challenge is back with its 2nd Edition! Updated baselines and sequences -- time to continue the journey of monocular skeletal tracking! 🗓️ Runs until Apr 30, 2026 🏆 Prize: FIFA World Cup 2026 tickets🔥 See 🧵

📊 Benchmark portals (Codabench): Validation: codabench.org/competitions/1… Challenge: codabench.org/competitions/1…

🏠 Homepage: inside.fifa.com/innovation/inn… 💻 Dev kit & baseline code: github.com/FIFA-Skeletal-…

The BEDLAM2.0 dataset (B2) is here, just in time to train your 3D human pose and shape estimation methods for CVPR. B2 goes beyond BEDLAM (B1) to include widely varied and natural camera motions and fields of view, more diverse body shapes, strand-based hair, more garments, shoes, more body motions, and more 3D scenes. Compared with B1, training on B2 produces more accurate 3D human pose, resulting in SOTA accuracy, particularly for estimates in world coordinates. B2 lets you jointly train camera motion and human motion regressors, and we also provide depth maps. Check out bedlam2.is.tuebingen.mpg.de/for data, code, dataset statistics, and much more. BEDLAM2.0 will appear in the 2025 NeurIPS Datasets and Benchmarks Track. Joint work with Joachim Tesch, @gfgbec, Prerana Achar, @AYiannakidis, @mkocab_, @PriyankaP1201.

SMPL is 10 years old and has done what we hoped — it changed the way the field estimates and models 3D humans and their motion. I’m delighted that the original team has been recognized today at @ICCVConference with the Mark Everingham Prize. The prize is given to individuals or teams who have worked to further progress in the computer vision community as a whole. Mark Everingham understood that to have an impact, it is not enough to simply publish a paper. SMPL’s success is due to lots of hard work to provide the community with code, data, and support. My deepest thanks go out to all the members of the @PerceivingSys department who have supported SMPL and related technology over the years. It has been a team effort of many dedicated people and we share this award with you. Mark understood that big changes require community effort. Consequently my big thanks go to all the users of SMPL and related tools. You have pushed the field forward as a community in ways that no small team could. I’m constantly inspired by your work. Computer vision has changed a lot in 10 years but people keep finding new uses for SMPL, most recently in training humanoid robots. There are many more applications to come in games, interactive entertainment, sports, and biomechanics. Congratulations to my coauthors Matt Loper, @naureenmahmood, Javier Romero and @GerardPonsMoll1. smpl.is.tue.mpg.de

I will be soon heading to #ICCV2025 ▷ Linkedin post about my paper and award linkedin.com/posts/hohs_icc…

@ICCVConference @NUSingapore @CSatETH @unibirmingham @RealityLabs @AIatMeta @UTokyo_News @meshcapade 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

Check out the workshop website for schedule details! g3p-workshop.github.io

Organizers: Tianjian Jiang, Manuel Kaufmann(@ETH_AI_Center), Jie Song, @soyong_shin, @jiyewise, @_ye_yuan, and @ChenGuo96. Big thanks to our collaborators in @FIFAcom side as well: Johsan Billingham, Katie Mills and Nikolas Evans, and everyone who helped make this happen!

We are happy to introduce the first installment of the Global 3D Human Poses Workshop (G3P) at #CVPR2025! 🥳 🗣️ We are excited to host an amazing line-up of speakers: @Michael_J_Black, @akanazawa, @jhugestar, and @kkitani. Join us from 08:45-12:30 in room 105 B!

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.

Our challenge provides: 1) Access to high-quality FIFA datasets; 2) A platform to showcase research in computer vision and sports analytics It is an opportunity to contribute to AI-driven sports technology #ComputerVision #AI #PoseEstimation #SportsAnalytics

Participants will develop robust tracking models that handle occlusions, fast movements, and team interactions in human pose and shape recovery. Dataset: eth-ait.github.io/WorldPoseDatas… Kaggle: kaggle.com/competitions/f…

Interested in football ⚽ and AI? We announce the FIFA Skeletal Light Challenge (inside.fifa.com/innovation/inn…), an opportunity to advance global 3D human pose tracking in football research. See 🧵

📢📢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 🧵👇