Hui Zhang (@hui_zhang_eth) 's Twitter Profile
Hui Zhang

@hui_zhang_eth

PhD student at ETH. Working on dexterous manipulation & hand-object motion generation

ID: 1714973905486516224

linkhttps://zdchan.github.io/ calendar_today19-10-2023 11:57:05

35 Tweet

125 Followers

106 Following

AIT Lab (@ait_eth) 's Twitter Profile Photo

Are you interested in hair reconstruction, human pose and shape estimation, digital human with clothing deformation, and hand-object interaction? Checkout our ECCV papers in the poster session at #ECCV2024! See 🧵.

Sammy Joe Christen (@sammy_j_c) 's Twitter Profile Photo

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

Xueyi Liu (@xymeow7) 's Twitter Profile Photo

🤖🧐Can human data be leveraged to advance robots' dexterous manipulation capabilities? #ICLR We introduce DexTrack🍀 (meowuu7.github.io/DexTrack/), a generalizable controller able to track diverse, complex, and even noisy human manipulation references, with transferability to real.

Wanyue Zhang (@wanyue__z) 's Twitter Profile Photo

🚀 Check out our #CVPR2025 paper BimArt! 👐🔧 We generate 3D bimanual interactions with articulated objects by: ✅ Predicting contact maps from object trajectories ✅ Using an articulation-aware feature representation Project Webpage: vcai.mpi-inf.mpg.de/projects/bimar… VCAI - MPI for Informatics

Hui Zhang (@hui_zhang_eth) 's Twitter Profile Photo

🎉 Excited to share that FunGrasp has been accepted to RA-L! We will present it at #IROS2025 in Hangzhou. See you there!

Hui Zhang (@hui_zhang_eth) 's Twitter Profile Photo

I feel like a demo should serve to intuitively show what becomes possible with a fundamental research problem solved, rather than aiming the whole work to producing the final demo. Of course companies may choose different for investment, but in academia, it shouldn’t be this way.

Ilir Aliu - eu/acc (@iliraliu_) 's Twitter Profile Photo

A robot hand grasp over 500 totally new objects without fail? Zero-shot, single-view & super reliable ⬇️ + Paper Grasping random objects is hard for robots, especially when shapes, weights, and materials vary. RobustDexGrasp solves this with a smart new way of seeing and