Learning Effective NeRFs and SDFs Representations with 3D Generative Adversarial Networks for 3D Object Generation

TL;DR

This paper introduces a novel approach combining 3D GANs with NeRFs and SDFs to generate high-fidelity 3D objects efficiently, requiring only a few images per object, and achieved top results in a major challenge.

Contribution

The paper proposes a new method integrating 3D GANs with NeRFs and SDFs for effective 3D object generation from limited images, advancing the state-of-the-art.

Findings

Achieved top 3 placement in ICCV 2023 OmniObject3D Challenge.

Enabled 3D object generation with few images per object.

Produced high-fidelity textured 3D objects.

Abstract

We present a solution for 3D object generation of ICCV 2023 OmniObject3D Challenge. In recent years, 3D object generation has made great process and achieved promising results, but it remains a challenging task due to the difficulty of generating complex, textured, and high-fidelity results. To resolve this problem, we study learning effective NeRFs and SDFs representations with 3D Generative Adversarial Networks (GANs) for 3D object generation. Specifically, inspired by recent works, we use the efficient geometry-aware 3D GANs as the backbone incorporating with label embedding and color mapping, which enables to train the model on different taxonomies simultaneously. Then, through a decoder, we aggregate the resulting features to generate Neural Radiance Fields (NeRFs) based representations for rendering high-fidelity synthetic images. Meanwhile, we optimize Signed Distance Functions (SDFs) to effectively represent objects with 3D meshes. Besides, we observe that this model can be effectively trained with only a few images of each object from a variety of classes, instead of using a great number of images per object or training one model per class. With this pipeline, we can optimize an effective model for 3D object generation. This solution is among the top 3 in the ICCV 2023 OmniObject3D Challenge.