Minghua Liu @ CVPR26's banner
Minghua Liu @ CVPR26's profile picture

Minghua Liu @ CVPR26

@MinghuaLiu_ • 2,261 subscribers

PhD student @UCSD_CSE. AI, 3D Vision, Embodied AI | research intern @NVIDIA | past: @Qualcomm @Waymo @Adobe @Tsinghua_Uni

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

In Hong Kong until Thursday! 🇭🇰✨ I’ll be presenting three works at SIGGRAPH Asia: PartUV (Monday afternoon) and FreeArt3D & LARM (Thursday morning), all in meeting room S421! Let me know if you’re nearby! Can’t wait to catch up, chat, and hang out! 🌃🧋🍖🦆🍻🍜
0:20
MinghuaLiu_'s profile picture

In Hong Kong until Thursday! 🇭🇰✨ I’ll be presenting three works at SIGGRAPH Asia: PartUV (Monday afternoon) and FreeArt3D & LARM (Thursday morning), all in meeting room S421! Let me know if you’re nearby! Can’t wait to catch up, chat, and hang out! 🌃🧋🍖🦆🍻🍜

Minghua Liu @ CVPR26

13,918 görüntüleme • 7 ay önce

🚀Excited to release PartField—a feedforward model that learns part-based feature fields for 3D shapes! It enables lightning-fast⚡️, robust, open-world hierarchical 3D part seg and unlocks cross-shape applications like co-seg and correspondence! 🔗 1/n
2:21
MinghuaLiu_'s profile picture

🚀Excited to release PartField—a feedforward model that learns part-based feature fields for 3D shapes! It enables lightning-fast⚡️, robust, open-world hierarchical 3D part seg and unlocks cross-shape applications like co-seg and correspondence! 🔗 1/n

Minghua Liu

17,292 görüntüleme • 1 yıl önce

Want high-quality 3D meshes with sharp geometric details? Try our newly released MeshFormer! It only takes 8 GPUs for two days of training, outperforming state-of-the-art models that use over a hundred GPUs! With 3D-native input guidance, representations, supervision, and post-processing, we significantly improve the training efficiency and geometric quality of feed-forward reconstruction models! Project page: Chong Zeng
0:21
MinghuaLiu_'s profile picture

Want high-quality 3D meshes with sharp geometric details? Try our newly released MeshFormer! It only takes 8 GPUs for two days of training, outperforming state-of-the-art models that use over a hundred GPUs! With 3D-native input guidance, representations, supervision, and post-processing, we significantly improve the training efficiency and geometric quality of feed-forward reconstruction models! Project page: Chong Zeng

Minghua Liu

16,350 görüntüleme • 2 yıl önce

Daha fazla içerik yok.