Joined Microsoft Research Asia - Tokyo to start a new journey :)
English
shoukang hu
9 posts
Web-scale human video dataset along with an in-the-wild human video annotation pipeline.
Ziwei Liu@liuziwei7
🚀Web-Scale Human Video Dataset🚀 #WildAvatar is a web-scale in-the-wild human avatar creation dataset with 10,000+ diverse human subjects and scenes. Each video is equipped with 🕺SMPL💃 and 🧥mask👚 annotation - Project: wildavatar.github.io - Code: github.com/wildavatar/Wil…
English
MVSGaussian achieves both fast training and real-time rendering for sparse view reconstruction. Welcome to play with our code.
Tianqi Liu@TianqiLiu664
#ECCV2024 We present MVSGaussian for efficient reconstruction from sparse views in a single forward pass. It offers high-quality initialization for fast training and real-time rendering. Project: mvsgaussian.github.io Code: github.com/TQTQliu/MVSGau… Paper: arxiv.org/abs/2405.12218
English
🤩Thrilled to be at #CVPR2024 in Seattle!
💡Join us at our poster session tomorrow!
🕒 10:15-12:00, June 21 PDT
Ziwei Liu@liuziwei7
💃💃We present #GauHuman, which learns articulated Gaussian Splatting from **monocular videos** with both fast training (1~2 minutes) and real-time rendering (up to 189 FPS). - Project: skhu101.github.io/GauHuman/ - Paper: arxiv.org/abs/2312.02973 - Code: github.com/skhu101/GauHum…
English
shoukang hu retweetledi
💃💃We present #GauHuman, which learns articulated Gaussian Splatting from **monocular videos** with both fast training (1~2 minutes) and real-time rendering (up to 189 FPS).
- Project: skhu101.github.io/GauHuman/
- Paper: arxiv.org/abs/2312.02973
- Code: github.com/skhu101/GauHum…
GIF
English
shoukang hu retweetledi
#ICCV2023 We propose 🔥SHERF @ICCVConference, the first *generalizable* Human NeRF model for recovering *animatable* 3D human from a single image.
- Project: skhu101.github.io/SHERF/
- Paper: arxiv.org/abs/2303.12791
- Code: github.com/skhu101/SHERF
- Demo: youtube.com/watch?v=xyiv-c…
YouTube
English
shoukang hu retweetledi
We propose 🔥HumanLiff🔥, a layer-wise 3D human generative model with unified diffusion process, which disentangles and controls the generation of human body and various clothes.
- Project: skhu101.github.io/HumanLiff/
- Paper: arxiv.org/abs/2308.09712
- Code: github.com/skhu101/HumanL…
English
Our GauHuman enjoys fast training (1~2 minutes) and real-time rendering (up to 189 FPS)
Ziwei Liu@liuziwei7
💃💃We present #GauHuman, which learns articulated Gaussian Splatting from **monocular videos** with both fast training (1~2 minutes) and real-time rendering (up to 189 FPS). - Project: skhu101.github.io/GauHuman/ - Paper: arxiv.org/abs/2312.02973 - Code: github.com/skhu101/GauHum…
English
