Papers
arxiv:2506.20703

Generative Blocks World: Moving Things Around in Pictures

Published on Jun 25
· Submitted by vv1233 on Jun 27
Authors:
,
,
,

Abstract

A generative method that edits 3D scenes using convex primitives and regenerates images with enhanced texture consistency and visual fidelity.

AI-generated summary

We describe Generative Blocks World to interact with the scene of a generated image by manipulating simple geometric abstractions. Our method represents scenes as assemblies of convex 3D primitives, and the same scene can be represented by different numbers of primitives, allowing an editor to move either whole structures or small details. Once the scene geometry has been edited, the image is generated by a flow-based method which is conditioned on depth and a texture hint. Our texture hint takes into account the modified 3D primitives, exceeding texture-consistency provided by existing key-value caching techniques. These texture hints (a) allow accurate object and camera moves and (b) largely preserve the identity of objects depicted. Quantitative and qualitative experiments demonstrate that our approach outperforms prior works in visual fidelity, editability, and compositional generalization.

Community

Paper author Paper submitter

We can fit 3D primitives to any image and use them to control image synthesis.

Hi, thank you for sharing your interesting work. As someone who is not an expert in this field, I was curious about your choice of LAION images for training—was there a specific reason you selected this dataset? Also, since Table 1 is the only quantitative metric reported, do you think these numbers alone are enough for general readers to trust the method’s performance, or have you considered ways to make the results more convincing to a broader audience, such as through human evaluation? Thank you!

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.20703 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.20703 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.20703 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.