Loading video...

Video Failed to Load

Go Home

The code, dataset and demos for our #SIGGRAPH2024 work on generating embodied avatar movements with Codebook Matching are now available! Everything can be found on the project page, including a precompiled binary that you can play around with!

blacksquirrel__'s profile picture

Sebastian Starke

3,298 subscribers

18,418 views • 2 years ago •via X (Twitter)

Science & Technology#SIGGRAPH2024
LIVE

Anya Rossi• Live Now

Private livecam show

1 Comments

Frank Carey's profile picture
Frank Carey2 years ago

Nice, looking forward to checking it out!

Related Videos

Today we presented our work on Action Recognition with 3D pose and tracking at #CVPR. We also released our code, models, and dataset of 1.5 million human trajectories. Code: Project Page:
0:26

Today we presented our work on Action Recognition with 3D pose and tracking at #CVPR. We also released our code, models, and dataset of 1.5 million human trajectories. Code: Project Page:

Jathushan Rajasegaran

132,016 views • 3 years ago

We are excited to share EMDB, a novel dataset of 3D human poses for in-the-wild monocular videos, including global trajectories. Data and toolkit code is now available. More details in the thread below. Project Page:
0:36

We are excited to share EMDB, a novel dataset of 3D human poses for in-the-wild monocular videos, including global trajectories. Data and toolkit code is now available. More details in the thread below. Project Page:

AIT Lab

14,625 views • 3 years ago

We are releasing a dataset of the lifeforms found by ASAL from our large scale searches! You can view the datasets here: To load them up and play around with them visit the ASAL github repo or this colab notebook:
0:25

We are releasing a dataset of the lifeforms found by ASAL from our large scale searches! You can view the datasets here: To load them up and play around with them visit the ASAL github repo or this colab notebook:

Sakana AI

19,140 views • 1 year ago

The Munchkins avatar is a cute chibi / toony furry avatar for VRChat that has a mix-and-match function! All parts are compatible with each texture, meaning you can swap out parts as you like through the menus. Available on Gumroad and VRC Marketplace!
0:59

The Munchkins avatar is a cute chibi / toony furry avatar for VRChat that has a mix-and-match function! All parts are compatible with each texture, meaning you can swap out parts as you like through the menus. Available on Gumroad and VRC Marketplace!

Teevz🌸

31,832 views • 6 months ago

Introducing Axis Dataset V1 - the simulation dataset for scalable robot manipulation. Can noisy, crowdsourced simulation data support embodied pretraining? Yes—with enough coverage and diversity. Continual pretraining on AXIS dataset V1 lifts π0.5 from 83.9% to 88.8% on LIBERO-Plus, with performance improving consistently as the pretraining data scales from 25% to 100% of the full dataset, showing no clear saturation. Built with researchers from Georgia Tech UC Berkeley Texas A&M University Johns Hopkins University Penn University of Michigan NUS NTU Singapore. ➡️Related links: Paper: Dataset: Project Page: GitHub Codebase:
0:34

Introducing Axis Dataset V1 - the simulation dataset for scalable robot manipulation. Can noisy, crowdsourced simulation data support embodied pretraining? Yes—with enough coverage and diversity. Continual pretraining on AXIS dataset V1 lifts π0.5 from 83.9% to 88.8% on LIBERO-Plus, with performance improving consistently as the pretraining data scales from 25% to 100% of the full dataset, showing no clear saturation. Built with researchers from Georgia Tech UC Berkeley Texas A&M University Johns Hopkins University Penn University of Michigan NUS NTU Singapore. ➡️Related links: Paper: Dataset: Project Page: GitHub Codebase:

Axis Robotics

95,292 views • 1 month ago

New: Our Live Voice Translator! Are you traveling and having trouble communicating? With the Lia 27 app, Lia will translate everything for you! Now available on the App Store and Google Play!
0:30

New: Our Live Voice Translator! Are you traveling and having trouble communicating? With the Lia 27 app, Lia will translate everything for you! Now available on the App Store and Google Play!

Lia

40,371 views • 2 years ago

I helped Skamps with a new Jynx avatar update, adding a customizable latex outfit and Rogue inspired texture set! The avatar is also 20% off with code BATFRIDAY! You can also get the latex outfit separately for free on their store, link will be in the reply :3
0:31

I helped Skamps with a new Jynx avatar update, adding a customizable latex outfit and Rogue inspired texture set! The avatar is also 20% off with code BATFRIDAY! You can also get the latex outfit separately for free on their store, link will be in the reply :3

Arkoren Art 🎀

10,189 views • 9 months ago

JOJŌSHĪKA 💿 OUT NOW 👉 Spotify link will be up Wed midnight but you can listen on Bandcamp NOW! With English translation on site. Album purchase comes with [untitled] link for the sequel [JOJŌSHĪKA II] so you can track the demos until its completion!
1:05

JOJŌSHĪKA 💿 OUT NOW 👉 Spotify link will be up Wed midnight but you can listen on Bandcamp NOW! With English translation on site. Album purchase comes with [untitled] link for the sequel [JOJŌSHĪKA II] so you can track the demos until its completion!

Shing02

10,059 views • 1 year ago

The Steam Endless Replayability Fest is on from now until next Monday, featuring games that you can play again... again... and again! With nigh infinite runs, each one different, these games can keep you playing - forever! Check out the deals and demos:
1:13

The Steam Endless Replayability Fest is on from now until next Monday, featuring games that you can play again... again... and again! With nigh infinite runs, each one different, these games can keep you playing - forever! Check out the deals and demos:

Steam

225,217 views • 2 years ago

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:
0:27

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:

Yuan Liu

79,610 views • 1 year ago

Shadergradient 1.0 — the complete suite of Framer component, Figma plugin, and React package is now available! You can find the link on our website, or our Product Hunt page. Find us on PH and support us with retweets and upvotes!
0:52

Shadergradient 1.0 — the complete suite of Framer component, Figma plugin, and React package is now available! You can find the link on our website, or our Product Hunt page. Find us on PH and support us with retweets and upvotes!

shadergradient

13,688 views • 3 years ago

i built this card-hover effect for Posthearts 🌸 active billing page on V2. designed 3 types, so you can just play around with it when you visit the page.😅
0:22

i built this card-hover effect for Posthearts 🌸 active billing page on V2. designed 3 types, so you can just play around with it when you visit the page.😅

Ayomidé Daniel

13,843 views • 11 months ago

Haven't seen any demos of using vibe coding to prototype gadgets like this So I made one. Everything here is generated with code Parts of the code and logic can even be reused on a Raspberry Pi to build the real thing Some tips ↓
0:40

Haven't seen any demos of using vibe coding to prototype gadgets like this So I made one. Everything here is generated with code Parts of the code and logic can even be reused on a Raspberry Pi to build the real thing Some tips ↓

Dilum Sanjaya

117,541 views • 2 months ago

With today's launch of Avatar Makeup, you can add high-fidelity cosmetics, face paint, team decals, and battle scars to your avatar. These layers work on any avatar and show up in every game you play.
1:58

With today's launch of Avatar Makeup, you can add high-fidelity cosmetics, face paint, team decals, and battle scars to your avatar. These layers work on any avatar and show up in every game you play.

David Baszucki

79,924 views • 5 months ago

Kyutai TTS and Unmute are now open source! The text-to-speech is natural, customizable, and fast: it can serve 32 users with a 350ms latency on a single L40S. Try it out and get started on the project page:
1:12

Kyutai TTS and Unmute are now open source! The text-to-speech is natural, customizable, and fast: it can serve 32 users with a 350ms latency on a single L40S. Try it out and get started on the project page:

kyutai

172,287 views • 1 year ago

What work can you do that keeps working for you after the work is done? (James Clear on The Knowledge Project)
2:16

What work can you do that keeps working for you after the work is done? (James Clear on The Knowledge Project)

Shane Parrish

33,104 views • 8 months ago