Loading video...

Video Failed to Load

Go Home

DeepMesh is out on Hugging Face Auto-Regressive Artist-mesh Creation with Reinforcement Learning Conditioned on point clouds and images, DeepMesh generates meshes with intricate details and precise topology, outperforming state-of-the-art methods in both precision and quality.

109,201 views • 1 year ago •via X (Twitter)

7 Comments

AK's profile picture
AK1 year ago

discuss:

AK's profile picture
AK1 year ago

model:

Yang's profile picture
Yang1 year ago

Want to learn how practical AI skills and automations for your business and work? Check out our step-by-step video tutorials 100% FREE Hours of AI and Automation goodness absolutely free 🥳

Andrew R's profile picture
Andrew R1 year ago

Get ready for a new 3d printing wave. Text to physical part

Tom Bennet's profile picture
Tom Bennet1 year ago

DeepMesh on Hugging Face? Sounds like AI's new favorite toy! 🤖🎨 Testing a theory: Can this tech revolutionize not just art, but also how we approach complex problem-solving in business? What if we could 'mesh' our ideas with the same precision? Share your thoughts!

Universa's profile picture
Universa1 year ago

@_akhaliq The integration of DeepMesh on Hugging Face is a significant milestone in the field of AI-driven mesh creation. Universa Earth is also exploring innovative applications of AI in various domains, including computer vision and machine learning.

Martin Høst Normark's profile picture
Martin Høst Normark1 year ago

This seems almost identical to NVIDIA’s Meshtron paper by @davidwromero among others.

Related Videos

Introducing ✨RigidFormer: Learning Rigid Dynamics with Transformers - our attempt to scale learning-based physical dynamics with Transformers. RigidFormer learns rigid dynamics with Transformers. It is a mesh-free, object-centric Transformer for multi-object rigid-body contact dynamics from point clouds. Learning physics with purely neural simulators, without relying on traditional physics engines, is an important and widely studied problem. Prior SOTA methods often use graph neural networks for accuracy and generalization, but still struggle with efficient, high-fidelity simulation at scale. RigidFormer uses only point inputs, matches or outperforms mesh-based baselines on standard benchmarks, runs much faster, generalizes across point resolutions and datasets, and scales to 200+ objects. We also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components. RigidFormer is mesh-free: it does not require mesh connectivity, SDFs, or vertex-level message passing, making it well-suited for point-cloud observations and scalable simulation. This architecture can also be adapted to learn soft-body dynamics by replacing the rigid-body module (differentiable Kabsch alignment). 🎬See our video for more details. Many thanks to my amazing collaborators: Minghao Guo Minghao Guo, Haixu Wu Haixu Wu 吴海旭, Doug Roble, Tuur Stuyck Tuur Stuyck, and Wojciech Matusik Wojciech Matusik. Project page: Paper:

Zhiyang (Frank) Dou

571,726 views • 2 months ago