An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion
66,863 次观看
An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion
discuss:
We introduce a new approach for generating realistic 3D models with UV maps through a representation termed "Object Images." This approach encapsulates surface geometry, appearance, and patch structures within a 64x64 pixel image, effectively converting complex 3D shapes into a more manageable 2D format. By doing so, we address the challenges of both geometric and semantic irregularity inherent in polygonal meshes. This method allows us to use image generation models, such as Diffusion Transformers, directly for 3D shape generation. Evaluated on the ABO dataset, our generated shapes with patch structures achieve point cloud FID comparable to recent 3D generative models, while naturally supporting PBR material generation.
9 条评论
评论来自 X (Twitter) 上的原帖

@jaakkolehtinen
Classic Geometry Images make a comeback?
15 个赞

@WaveTruths
SO NO CODE?
5 个赞

@andy_yx27
what? Amazing
1 个赞

@fogside1
It's a smart idea, I love it.
1 个赞

@Nicolas_C418
It's a great idea!
1 个赞

@WolfeRaviv
Absolutely fascinating the new ways these tools continue to be applied to problem solving
1 个赞

@PowerOfAI137915
So cool 👍🏻👏🏻
1 个赞

@chazz_gold
I “think” I understand what I just read
1 个赞

@yan_xg
Thanks for the post! The code and data is now live at:
1 个赞
