Charlie Nash: Excited to share PolyGen, a generative model of 3D meshes. PolyGen sequentially generate meshes vertex-by-vertex, and face-by-face using Transformers.
With @yaroslav_ganin @arkitus @PeterWBattaglia @DeepMind
13 replies, 898 likes
Charlie Nash: We've just released code for PolyGen, our generative model of 3D meshes
github: https://github.com/deepmind/deepmind-research/tree/master/polygen https://t.co/fSZgdTqUR3
6 replies, 451 likes
DeepMind: PolyGen: an autoregressive generative model of 3D meshes. PolyGen sequentially generates meshes vertex-by-vertex and face-by-face, using Transformers and Pointer Networks.
@charlietcnash @yaroslav_ganin @arkitus @PeterWBattaglia https://t.co/qWLv9A3Fdj
2 replies, 401 likes
Ali Eslami: Introducing PolyGen: an autoregressive model of 3D meshes.
Transformers + Pointer Nets = train on raw mesh data (i.e. variable-length lists of vertices and faces). No need to voxelise or rasterise!
with @charlietcnash @yaroslav_ganin @PeterWBattaglia https://t.co/oaSluTXEay
5 replies, 308 likes
Oriol Vinyals: Mesh generation will keep pushing the boundaries of the Deep Learning Toolbox. Very happy to see code released from @charlietcnash et al, as it will help anyone interested in pushing the field further!
Paper: https://arxiv.org/abs/2002.10880 https://t.co/zyWIMBtW9u
1 replies, 157 likes
Eric Jang 🇺🇸🇹🇼: Wow! I used to think that we needed RL agents to learn structured synthesis with non-differentiable objectives/constraints (e.g. obeying mesh closure). but maybe all you really need is max likelihood and a clever factorization of the problem.
3 replies, 126 likes
Oriol Vinyals: Amazing how far mesh generation has been pushed! I post a video from Pointer Networks (2015), in which results like the one below by @charlietcnash et al seemed impossible. https://t.co/pPkwczl1NO
0 replies, 99 likes
Yaroslav Ganin: PolyGen: a generative model for 3D meshes
• Outputs vertices one by one then generates faces (all using Transformers)
• Faces are polygons; more structure 👉 better results
• Pointer nets to select vertices for each face
Led by @charlietcnash. w/ @arkitus @PeterWBattaglia
1 replies, 64 likes
Meire Fortunato: Impressive results by @charlietcnash et al. Mesh generation by solving numerical PDEs (no ML) was my PhD thesis topic. Pointer Networks(2015) was my first paper in ML, there we only attempted generating very simple 2D triangulations in a seq2seq fashion - progress is exciting! :)
0 replies, 39 likes
Andrew Davison: Generative models of meshes look promising for modelling complicated objects and I'll read this one properly.
1 replies, 32 likes
Xander Steenbrugge: Some amazing new 3D-modelling tools incoming 👌 #Blender3d
0 replies, 26 likes
Daisuke Okanohara: PolyGen is a generative model of 3D polygon meshes. It uses an autoregressive model with a transformer and pointer network, which generates vertices and faces sequentially. Generation can condition on class and images. https://arxiv.org/abs/2002.10880
0 replies, 7 likes
Alexandre Moufarek: PolyGen, a generative model of 3D meshes by @DeepMind. It sequentially outputs mesh vertices and faces.
Code is available on GitHub & the paper by @charlietcnash @yaroslav_ganin @arkitus @PeterWBattaglia is on arXiv.
Paper: http://arxiv.org/abs/2002.10880 https://t.co/yswovDzGnl
0 replies, 3 likes
Toni Rosinol: I’m just amazed at what has been achieved by @charlietcnash et al., seems like we are getting closer to having a 3D mesh reconstruction of the world, would be interesting to see how these principles apply to SLAM though.
0 replies, 2 likes
AI Core: Humans are constrained to thinking in simple shapes when designing hence everyday objects take very simple, non optimal shapes. PolyGen+Reinforcement Learning combined with 3d printing is going to revolutionize the design of these forms.
0 replies, 2 likes
Matthew Vowels: Using graph NNs effectively for CAD furniture design design
0 replies, 1 likes
Found on Feb 26 2020 at https://arxiv.org/pdf/2002.10880.pdf