Qingqing Zhao
@qingqing_zhao_
Followers
986
Following
473
Media
6
Statuses
63
PhD candidate at Stanford
Palo Alto
Joined January 2018
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Colorado
• 133022 Tweets
Notre Dame
• 115160 Tweets
Kentucky
• 67807 Tweets
#仮面ライダーガヴ
• 56513 Tweets
The Weeknd
• 55885 Tweets
#AEWAllOut
• 52537 Tweets
Northern Illinois
• 38507 Tweets
Nebraska
• 35411 Tweets
Abel
• 29945 Tweets
Carti
• 29475 Tweets
#ブンブンジャー
• 25101 Tweets
Auburn
• 24168 Tweets
Talleres
• 24055 Tweets
#UFCVegas97
• 18724 Tweets
Medina
• 15765 Tweets
Willow
• 15755 Tweets
Bama
• 13979 Tweets
#ニノさん
• 13680 Tweets
Skullduggery
• 13293 Tweets
ショウマ
• 12907 Tweets
Herrera
• 12867 Tweets
ひろプリ
• 11876 Tweets
Pinned Tweet
How do we create realistic models of dressed humans directly from visual data?
We introduce PhysAvatar, a framework that estimates the shape, appearance, and physical parameters of dressed human avatars from multi-view videos.
Page:
(1/6)
9
46
242
PhysAvatar has been accepted into
#ECCV2024
! 🎉 We create virtual avatars with realistic garment dynamics and lighting, with a physics simulator in the loop.
How do we create realistic models of dressed humans directly from visual data?
We introduce PhysAvatar, a framework that estimates the shape, appearance, and physical parameters of dressed human avatars from multi-view videos.
Page:
(1/6)
9
46
242
7
20
199
🚀 Introducing HumanPlus! A full-stack system for humanoids to learn motion and autonomous skills from human data.
Our real-time shadowing system uses a single RGB camera & whole-body policy to clone human motion for tasks like boxing🥊, ping pong🏓, playing piano🎹, and more.
Introduce HumanPlus - Shadowing part
Humanoids are born for using human data. We build a real-time shadowing system using a single RGB camera and a whole-body policy for cloning human motion. Examples:
- boxing🥊
- playing the piano🎹/ping pong
- tossing
- typing
Open-sourced!
17
166
770
2
12
72
Through imitation, our humanoid learns to fold clothes👕, unload warehouse racks📦, greet other robots🤖, and more!
Check out our project website for more:
Introduce HumanPlus - Autonomous Skills part
Humanoids are born for using human data. Imitating humans, our humanoid learns:
- fold sweatshirts
- unload objects from warehouse racks
- diverse locomotion skills (squatting, jumping, standing)
- greet another robot
Open-sourced!
11
121
582
0
9
52
Have you seen a humanoid wearing a shoe? Our 6ft humanoid at Stanford can put on a Nike shoe, tie shoelaces, stand up, and walk autonomously! It’s been a super fun project to work on.
Our 6ft humanoid HumanPlus at Stanford can autonomously put on a Nike skateboard shoe, tie shoelaces, stand up and walk.
Using two transformers & dual RGB vision, it integrates two recipes of general robotics end-to-end:
- imitating humans in real world
- large-scale RL in sim
27
192
876
3
8
44
Filming this was a blast, and it seems our cat's a big fan of the new robot buddy! 😸🤖
Mobile ALOHA's hardware is very capable. We brought it home yesterday and tried more tasks! It can:
- do laundry👔👖
- self-charge⚡️
- use a vacuum
- water plants🌳
- load and unload a dishwasher
- use a coffee machine☕️
- obtain drinks from the fridge and open a beer🍺
- open
409
2K
7K
2
2
26
amazing effort 🔥🔥🔥
Excited to announce 🚀gsplat v1.0🚀: a ⏩efficient⏩ CUDA backend for 3D Gaussian Splatting!
A drop-in replacement of the official impl. with:
- Up to 2x faster training;
- Up to 4x less GPU memory;
- Render millions of GSs in real-time;
- And more;
10
108
506
0
0
8
PhysAvatar can simulate realistic garment dynamics across a range of diverse and challenging motions, such as dancing and spinning.
(2/6)
1
0
7
PhysAvatar enables redressing for virtual garment fitting.
(4/6)
1
0
5
Real-time is so cool! Proteus 0.1 takes it to the next level. Congrats
@willbokuishen
@connorzl
@linqi_zhou
Introducing Proteus 0.1, REAL-TIME video generation that brings life to your AI.
Proteus can laugh, rap, sing, blink, smile, talk, and more. From a single image!
Come meet Proteus on Twitch in real-time. ↓
Sign up for API waitlist:
1/11
25
114
394
0
0
4
We can repaint and edit the garment's texture using PhysAvatar.
(5/6)
1
1
3
classic
1
0
3
Work done with the amazing team:
@yang_zheng18
(co-lead),
@stevenygd
,
@toomanyyifans
,
@DonglaiXiang
,
@fpgDubost
,
@DmitryLagun
, Thabo Beeler,
@fedassa
, Leonidas Guibas,
@GordonWetzstein
(6/6)
1
0
2
How do we create realistic models of dressed humans directly from visual data?
We introduce PhysAvatar, a framework that estimates the shape, appearance, and physical parameters of dressed human avatars from multi-view videos.
Page:
(1/6)
9
46
242
0
0
2
PhysAvatars can be realistically relit when placed in different environments.
(3/6)
1
0
2