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

arXiv: https://arxiv.org/abs/2309.16110 · HTML: https://mlsanity.com/paper/2309.16110/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 28 Sep 2023.

## Builds on (most cited first, 20 of 20)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [DiffRF: Rendering-Guided 3D Radiance Field Diffusion](https://mlsanity.com/paper/2212.01206/) (2022)
- [3D Shape Induction from 2D Views of Multiple Objects](https://mlsanity.com/paper/1612.05872/) (2016)
- [Voxel-based Network for Shape Completion by Leveraging Edge Generation](https://mlsanity.com/paper/2108.09936/) (2021)
- [Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data](https://mlsanity.com/paper/2002.12674/) (2020)
- [Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion](https://mlsanity.com/paper/2211.11674/) (2022)
- [Multi-chart Generative Surface Modeling](https://mlsanity.com/paper/1806.02143/) (2018)
- [MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Driving](https://mlsanity.com/paper/2309.16715/) (2023)
- [SDF-3DGAN: A 3D Object Generative Method Based on Implicit Signed Distance Function](https://mlsanity.com/paper/2303.06821/) (2023)
- [TMO: Textured Mesh Acquisition of Objects with a Mobile Device by using Differentiable Rendering](https://mlsanity.com/paper/2303.15060/) (2023)

## Built on by (most cited first, 3 of 3)

- [4D-Editor: Interactive Object-level Editing in Dynamic Neural Radiance Fields via Semantic Distillation](https://mlsanity.com/paper/2310.16858/) (2023)
- [HIPPo: Harnessing Image-to-3D Priors for Model-free Zero-shot 6D Pose Estimation](https://mlsanity.com/paper/2502.10606/) (2025)
- [L-PR: Exploiting LiDAR Fiducial Marker for Unordered Low Overlap Multiview Point Cloud Registration](https://mlsanity.com/paper/2406.03298/) (2024)

## Abstract (arXiv)

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.