Learning Effective NeRFs and SDFs Representations with 3D Generative Adversarial Networks for 3D Object Generation
This work addresses the problem of generating complex, textured 3D objects for computer vision applications, but it is incremental, building on existing 3D GAN methods.
The paper tackled 3D object generation by learning effective NeRF and SDF representations with 3D GANs, achieving top-3 results in the ICCV 2023 OmniObject3D Challenge and enabling training with few images per object across multiple classes.
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.