wakaka
28 posts
大家对Manus级别的开源AI agent感兴趣嘛，最近想把Athena开源出来
athenalab.ai
Athena@AthenaAGI
We are considering open sourcing the agent implementation behind Athena. Will you guys be interested?
中文
GeneFace++：通用稳定的实时音频驱动3D人脸动画技术（使用NeRF渲染），口型，表情和头部运动都可以实时跟进语音进行反馈。#AI技术速递
genefaceplusplus.github.io
中文
Check out our new work on sparse pose estimation!
Getting camera poses from limited views is challenging, but learning to iteratively refine poses using DINO features allows for accurate pose estimation from as few as 3 images. Fantastic work led by @_sam_sinha_!
Samarth Sinha@_sam_sinha_
Super excited to share that my first project as a PhD student was accepted at CVPR 2023! #CVPR2023 😄 We show how to recover accurate camera poses from as few as 3 images! More details to come! w/ @jasonyzhang2 @taiyasaki @igilitschenski @DaveLindell arxiv.org/abs/2211.16991
English
Starting to do pre pre production for my next #unrealengine5 #metahuman short. Its amazing that you can get this quality with a $500 @facegood2018 helmet and free software. Testing facial animation from Bryan Seagall with extreme poses #gamedev
Full video on YT!
English
@HongwenZhang_ Hi good job,Is there support for live mode, or is there a plan to support it?
English
PyMAF-X is coming!👋👏👏
As an eXpressive extension, PyMAF-X supports full-body mesh recovery and inherits all the properties and merits of PyMAF: monocular-input, regression-based, more robust, and better aligned.
arXiv: arxiv.org/abs/2207.06400
Project: hongwenzhang.github.io/pymaf-x
GIF
English
@hiro_nym @timmutoke @readyplayerme You signed up for Early Access, did your application go through?
English
Nvidia recently announced the ability to create, customize and deploy interactive avatars via their Omniverse Avatar Cloud Engine (ACE)
I signed up for early access as I think this could be a game changer for pseudonym creators
@timmutoke of @readyplayerme goes on to say:
English
FaceFormer: Speech-Driven 3D Facial Animation with Transformers
abs: arxiv.org/abs/2112.05329
English
Episode 3 - Part 1 of Annie as a Polyglot with her multi-lingual, coding and super hearing abilities! @Scobleizer Using #Metahuman, #GPT3 and #Codex. This episode is split into 2 parts (Part 2 in thread below). Full video to be posted on Youtube.
English
POC #2 of an AI Assistant #Architect using #UE5's #Metahuman, #StableDiffusion, #OpenAI's #GPT3. (Note that certain parts of the video has been sped up to reduce latency in responses and to keep within Twitter's 140s limit on videos. Original video will be posted on Youtube.)
English
Beyond face swapping! We present the Head Swapper (HeSer), which achieves few-shot head swapping in the wild through two delicately designed modules. #CVPR2022 Read more: jmliu88.github.io/HeSer/
English
a @Gradio Demo for Thin-Plate Spline Motion Model for Image Animation on @huggingface Spaces for @CVPR 2022
demo: huggingface.co/spaces/CVPR/Im…
submit CVPR demos here: huggingface.co/CVPR
join the CVPR organization: huggingface.co/organizations/…
GIF
English
AI-generated character + a couple of hours of modelling.
AI saved me several days of work, with looking for references, sketches and coordination with a team.
City of London, London 🇬🇧 English
@freemocap Hi, I would love to use freemocap to link to UE5 for avatar live streaming. When will live mode be supported?
English
I'm now streaming on Twitch! Playing Software and Game Development ift.tt/xAoLuPt
English
"A person with one watch knows what time it is. A person with two watches is never really sure..."
#markerless #motioncapture #opensource #openscience #treadmill #gait #biomechanics #neuroscience
English
Face tracking and some FACS being applied just with a simple RGB webcam. Improving the "shakiness" from 3d pose estimation soon.
#UE4 #UnrealEngine #MetaHuman #AR
English
Finally got the Blendshapes and Eyes working for my #Mediapipe LiveLink Face Tracking experiment. Doesn't need an IPhone like the current only available App. #Unreal #UE4 #metahuman
English
Check out my newly published work on IEEE Robotics and Automation Letters, "Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry" ieeexplore.ieee.org/document/96622…
English