Guowei Zhang

🧩#CVPR2025🌷Introducing Two By Two✌️: The First Large-Scale Daily Pairwise Assembly Dataset with SE(3)-Equivariant Pose Estimation. 🤖2BY2 helps robots master daily 3D assembly tasks—like plugging sockets or arranging flowers—across diverse objects! 🐨Co-lead by @yuqi_Beijing

@ju_yuanchen Cool!

🍌We present DenseMatcher！ 🤖️DenseMatcher enables robots to acquire generalizable skills across diverse object categories by only seeing one demo, by finding correspondences between 3D objects even with different types, shapes, and appearances.

How to make your robot handle diverse visual scenarios?🤔 Introduce our recent work: Learning to 𝑴𝒂𝒏𝒊pulate Any𝒘𝒉𝒆𝒓𝒆: 𝐌𝐚𝐧𝐢𝐰𝐡𝐞𝐫𝐞. It enables your robot to manage multiple visual disturbance types 🌈and step out of simulation to achieve sim2real transfer.🤖

#ECCV2024 🧸Exciting news! Our Robo-ABC🤖️has been accepted by ECCV2024! We aim to achieve cross-category affordance generalization without additional training！ Huge thanks to my advisor @HarryXu12 and my collaborators @hkz222 @MalcomX920676 @Gu__Zhang for their support!🥰

Proud to be involved in this creative work, and really hope it brings inspiration in the research of robot manipulation.

Imagine a world where robots adapt to and manipulate unfamiliar objects as effortlessly as humans do - this isn't science fiction, it's the reality we've achieved with our Robo-ABC🤖️🦾🌍. Project site 🍿: tea-lab.github.io/Robo-ABC