# 3D GAN Inversion with Pose Optimization

arXiv: https://arxiv.org/abs/2210.07301 · HTML: https://mlsanity.com/paper/2210.07301/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 58 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [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)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](https://mlsanity.com/paper/1903.08527/) (2019)
- [Learning an Animatable Detailed 3D Face Model from In-The-Wild Images](https://mlsanity.com/paper/2012.04012/) (2020)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [Pivotal Tuning for Latent-based Editing of Real Images](https://mlsanity.com/paper/2106.05744/) (2021)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)

## Built on by (most cited first, 30 of 44)

- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization](https://mlsanity.com/paper/2211.15662/) (2022)
- [Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data](https://mlsanity.com/paper/2311.18729/) (2023)
- [HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors](https://mlsanity.com/paper/2408.06019/) (2024)
- [TriPlaneNet: An Encoder for EG3D Inversion](https://mlsanity.com/paper/2303.13497/) (2023)
- [3D GAN Inversion with Facial Symmetry Prior](https://mlsanity.com/paper/2211.16927/) (2022)
- [Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding](https://mlsanity.com/paper/2303.12326/) (2023)
- [VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment](https://mlsanity.com/paper/2312.04651/) (2023)
- [Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images](https://mlsanity.com/paper/2304.06700/) (2023)
- [Lite2Relight: 3D-aware Single Image Portrait Relighting](https://mlsanity.com/paper/2407.10487/) (2024)
- [LPFF: A Portrait Dataset for Face Generators Across Large Poses](https://mlsanity.com/paper/2303.14407/) (2023)
- [InvertAvatar: Incremental GAN Inversion for Generalized Head Avatars](https://mlsanity.com/paper/2312.02222/) (2023)
- [A Survey on Deep Generative 3D-aware Image Synthesis](https://mlsanity.com/paper/2210.14267/) (2022)
- [VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs](https://mlsanity.com/paper/2303.15893/) (2023)
- [Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization](https://mlsanity.com/paper/2305.03043/) (2023)
- [Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation](https://mlsanity.com/paper/2404.00636/) (2024)
- [Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior](https://mlsanity.com/paper/2404.10394/) (2024)
- [GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar](https://mlsanity.com/paper/2311.13655/) (2023)
- [3D-aware Blending with Generative NeRFs](https://mlsanity.com/paper/2302.06608/) (2023)
- [Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation](https://mlsanity.com/paper/2405.04356/) (2024)
- [Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation](https://mlsanity.com/paper/2304.13681/) (2023)
- [Progressive Learning of 3D Reconstruction Network from 2D GAN Data](https://mlsanity.com/paper/2305.11102/) (2023)
- [Real-time 3D-aware Portrait Editing from a Single Image](https://mlsanity.com/paper/2402.14000/) (2024)
- [Controllable 3D Face Generation with Conditional Style Code Diffusion](https://mlsanity.com/paper/2312.13941/) (2023)
- [My3DGen: A Scalable Personalized 3D Generative Model](https://mlsanity.com/paper/2307.05468/) (2023)
- [3DPortraitGAN: Learning One-Quarter Headshot 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses](https://mlsanity.com/paper/2307.14770/) (2023)
- [PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image](https://mlsanity.com/paper/2509.07552/) (2025)
- [DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs](https://mlsanity.com/paper/2302.12253/) (2023)
- [LatentSwap3D: Semantic Edits on 3D Image GANs](https://mlsanity.com/paper/2212.01381/) (2022)
- [Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images](https://mlsanity.com/paper/2409.20530/) (2024)

## Abstract (arXiv)

With the recent advances in NeRF-based 3D aware GANs quality, projecting an image into the latent space of these 3D-aware GANs has a natural advantage over 2D GAN inversion: not only does it allow multi-view consistent editing of the projected image, but it also enables 3D reconstruction and novel view synthesis when given only a single image. However, the explicit viewpoint control acts as a main hindrance in the 3D GAN inversion process, as both camera pose and latent code have to be optimized simultaneously to reconstruct the given image. Most works that explore the latent space of the 3D-aware GANs rely on ground-truth camera viewpoint or deformable 3D model, thus limiting their applicability. In this work, we introduce a generalizable 3D GAN inversion method that infers camera viewpoint and latent code simultaneously to enable multi-view consistent semantic image editing. The key to our approach is to leverage pre-trained estimators for better initialization and utilize the pixel-wise depth calculated from NeRF parameters to better reconstruct the given image. We conduct extensive experiments on image reconstruction and editing both quantitatively and qualitatively, and further compare our results with 2D GAN-based editing to demonstrate the advantages of utilizing the latent space of 3D GANs. Additional results and visualizations are available at https://3dgan-inversion.github.io .