跳过导航
An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion
0:00 / 0:34

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion

AK

@_akhaliq54万 位关注者

在 X 上查看
804 个赞下载原帖

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

  • Jaakko Lehtinen 的头像

    @jaakkolehtinen

    Classic Geometry Images make a comeback?

    15 个赞

  • Darwin Miller 的头像

    @WaveTruths

    SO NO CODE?

    5 个赞

  • Xin Yu (Andy) 的头像

    @andy_yx27

    what? Amazing

    1 个赞

  • Genia Cheskidova 的头像

    @fogside1

    It's a smart idea, I love it.

    1 个赞

  • Nicolas 的头像

    @Nicolas_C418

    It's a great idea!

    1 个赞

  • Raviv Wolfe 的头像

    @WolfeRaviv

    Absolutely fascinating the new ways these tools continue to be applied to problem solving

    1 个赞

  • Power Of AI 的头像

    @PowerOfAI137915

    So cool 👍🏻👏🏻

    1 个赞

  • Chazz Gold 的头像

    @chazz_gold

    I “think” I understand what I just read

    1 个赞

  • 𝕏ingguang Yan 的头像

    @yan_xg

    Thanks for the post! The code and data is now live at:

    1 个赞