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

TL;DR

This paper presents a novel method for generating 3D models by encoding surface details into 64x64 pixel images called 'Object Images', enabling the use of image diffusion models for 3D shape creation.

Contribution

It introduces 'Object Images' as a new 2D representation for 3D shapes, simplifying complex geometry and enabling direct use of image diffusion models for 3D generation.

Findings

Achieves point cloud FID comparable to recent 3D models

Supports PBR material generation naturally

Addresses geometric and semantic irregularity in 3D shapes

Abstract

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.