# Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator

arXiv: https://arxiv.org/abs/2209.15637 · HTML: https://mlsanity.com/paper/2209.15637/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 30 Sep 2022.

## Builds on (most cited first, 30 of 31)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation](https://mlsanity.com/paper/2112.11427/) (2021)
- [GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation](https://mlsanity.com/paper/2112.08867/) (2021)
- [Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image](https://mlsanity.com/paper/1905.02722/) (2019)
- [Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild](https://mlsanity.com/paper/1911.11130/) (2019)
- [CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis](https://mlsanity.com/paper/2110.09788/) (2021)
- [Visual Object Networks: Image Generation with Disentangled 3D Representation](https://mlsanity.com/paper/1812.02725/) (2018)
- [3D-aware Image Synthesis via Learning Structural and Textural Representations](https://mlsanity.com/paper/2112.10759/) (2021)
- [Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting](https://mlsanity.com/paper/2109.06061/) (2021)
- [A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis](https://mlsanity.com/paper/2110.15678/) (2021)
- [Gradient descent GAN optimization is locally stable](https://mlsanity.com/paper/1706.04156/) (2017)
- [Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images](https://mlsanity.com/paper/2203.15926/) (2022)

## Built on by (most cited first, 16 of 16)

- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization](https://mlsanity.com/paper/2211.15662/) (2022)
- [DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis](https://mlsanity.com/paper/2212.11984/) (2022)
- [CAD: Photorealistic 3D Generation via Adversarial Distillation](https://mlsanity.com/paper/2312.06663/) (2023)
- [A Survey on Deep Generative 3D-aware Image Synthesis](https://mlsanity.com/paper/2210.14267/) (2022)
- [Learning 3D-aware Image Synthesis with Unknown Pose Distribution](https://mlsanity.com/paper/2301.07702/) (2023)
- [Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis](https://mlsanity.com/paper/2309.03904/) (2023)
- [Real-time 3D-aware Portrait Editing from a Single Image](https://mlsanity.com/paper/2402.14000/) (2024)
- [SMaRt: Improving GANs with Score Matching Regularity](https://mlsanity.com/paper/2311.18208/) (2023)
- [GLeaD: Improving GANs with A Generator-Leading Task](https://mlsanity.com/paper/2212.03752/) (2022)
- [BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation](https://mlsanity.com/paper/2312.02136/) (2023)
- [INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fields](https://mlsanity.com/paper/2312.16197/) (2023)
- [FLNeRF: 3D Facial Landmarks Estimation in Neural Radiance Fields](https://mlsanity.com/paper/2211.11202/) (2022)
- [G3FA: Geometry-guided GAN for Face Animation](https://mlsanity.com/paper/2408.13049/) (2024)
- [Deep Generative Models on 3D Representations: A Survey](https://mlsanity.com/paper/2210.15663/) (2022)
- [Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN](https://mlsanity.com/paper/2606.27305/) (2026)

## Abstract (arXiv)

3D-aware image synthesis aims at learning a generative model that can render photo-realistic 2D images while capturing decent underlying 3D shapes. A popular solution is to adopt the generative adversarial network (GAN) and replace the generator with a 3D renderer, where volume rendering with neural radiance field (NeRF) is commonly used. Despite the advancement of synthesis quality, existing methods fail to obtain moderate 3D shapes. We argue that, considering the two-player game in the formulation of GANs, only making the generator 3D-aware is not enough. In other words, displacing the generative mechanism only offers the capability, but not the guarantee, of producing 3D-aware images, because the supervision of the generator primarily comes from the discriminator. To address this issue, we propose GeoD through learning a geometry-aware discriminator to improve 3D-aware GANs. Concretely, besides differentiating real and fake samples from the 2D image space, the discriminator is additionally asked to derive the geometry information from the inputs, which is then applied as the guidance of the generator. Such a simple yet effective design facilitates learning substantially more accurate 3D shapes. Extensive experiments on various generator architectures and training datasets verify the superiority of GeoD over state-of-the-art alternatives. Moreover, our approach is registered as a general framework such that a more capable discriminator (i.e., with a third task of novel view synthesis beyond domain classification and geometry extraction) can further assist the generator with a better multi-view consistency.