Cristian Sminchisescu

@TensorFlow Great to see our BlazePoseGHUM model released in TensorFlow.js! Try it!

💃 Try our new model that enables 3D Pose Detection live in your web browser with MediaPipe BlazePose GHUM + TensorFlow.js. Share your creations with #MadeWithTFJS. Get started → goo.gle/3gKAYmy Read the blog → goo.gle/2WCS3bb

@SkyLi0n Thanks for catching that! github.com/google-researc…

@CSminchisescu Github URL is broken.

Our full body implicit generative human model is available. Give it a try! imGHUM: Implicit generative models of 3d human shape and articulated pose (joint work with Thiemo Alldieck and Hongyi Xu) will appear at ICCV2021. arxiv.org/pdf/2108.10842… github.com/goo.../google-…

Corrected Github link: github.com/google-researc…

Join us in 10 minutes (10:55 am EDT, 16:55 cet) at #CVPR2021 and exercise! Find out about our AIFIT: Automatic 3D Human-Interpretable Feedback Models for Fitness Training. Paper/data: vision.imar.ro/fit3d/.

New monocular (full-body) 3d human pose and shape estimation (a.k.a. HUND) Neural Descent for Visual 3D Human Pose and Shape Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir, William T. Freeman, Rahul Sukthankar, Cristian Sminchisescu, CVPR2021.

Excited to share our #CVPR2020 paper on "Three-Dimensional Reconstruction of Human Interactions". We model and learn physical contact between humans for more accurate 3d reconstruction of interacting people. Project Page: vision.imar.ro/ci3d PDF: openaccess.thecvf.com/content_CVPR_2…

#MediaPipe BlazePose GHUM 3D (goo.gle/2PObiaO) is now 3x more accurate, achieving state-of-the-art performance while offering new lite and heavy versions to cover every device and use case! Try it out at solutions.mediapipe.dev/pose for Python, JS, Android and iOS!

BlazePoseGHUM3D is now available (Blog Post developers.googleblog.com/2021/03/ml-kit…) in MLKit and MediaPipe (google.github.io/mediapipe/solu…)

Our statistical 3d human pose and shape models (GHUM) are available at github.com/google-researc….