# Third Time's the Charm? Image and Video Editing with StyleGAN3

arXiv: https://arxiv.org/abs/2201.13433 · HTML: https://mlsanity.com/paper/2201.13433/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 94 references that are in the map.
- First posted on arXiv 31 Jan 2022.

## Builds on (most cited first, 30 of 67)

- [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)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [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)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [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)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [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)
- [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)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [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)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [StyleRig: Rigging StyleGAN for 3D Control over Portrait Images](https://mlsanity.com/paper/2004.00121/) (2020)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)

## Built on by (most cited first, 30 of 54)

- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [AltFreezing for More General Video Face Forgery Detection](https://mlsanity.com/paper/2307.08317/) (2023)
- [High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization](https://mlsanity.com/paper/2211.15662/) (2022)
- [Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models](https://mlsanity.com/paper/2303.11073/) (2023)
- [GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations](https://mlsanity.com/paper/2305.19962/) (2023)
- [Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding](https://mlsanity.com/paper/2212.02802/) (2022)
- [3DAvatarGAN: Bridging Domains for Personalized Editable Avatars](https://mlsanity.com/paper/2301.02700/) (2023)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [Temporally Consistent Semantic Video Editing](https://mlsanity.com/paper/2206.10590/) (2022)
- [Face Generation and Editing with StyleGAN: A Survey](https://mlsanity.com/paper/2212.09102/) (2022)
- [Visual Instruction Inversion: Image Editing via Visual Prompting](https://mlsanity.com/paper/2307.14331/) (2023)
- [VToonify: Controllable High-Resolution Portrait Video Style Transfer](https://mlsanity.com/paper/2209.11224/) (2022)
- [StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces](https://mlsanity.com/paper/2303.06146/) (2023)
- [Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color](https://mlsanity.com/paper/2309.05148/) (2023)
- [VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs](https://mlsanity.com/paper/2303.15893/) (2023)
- [Soundini: Sound-Guided Diffusion for Natural Video Editing](https://mlsanity.com/paper/2304.06818/) (2023)
- [RIGID: Recurrent GAN Inversion and Editing of Real Face Videos](https://mlsanity.com/paper/2308.06097/) (2023)
- [Towards Smooth Video Composition](https://mlsanity.com/paper/2212.07413/) (2022)
- [StyleLipSync: Style-based Personalized Lip-sync Video Generation](https://mlsanity.com/paper/2305.00521/) (2023)
- [Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection](https://mlsanity.com/paper/2501.01184/) (2025)
- [Video2StyleGAN: Disentangling Local and Global Variations in a Video](https://mlsanity.com/paper/2205.13996/) (2022)
- [FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations](https://mlsanity.com/paper/2411.10818/) (2024)
- [Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromise](https://mlsanity.com/paper/2510.17372/) (2025)
- [Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Image](https://mlsanity.com/paper/2211.13901/) (2022)
- [Towards Real-time Text-driven Image Manipulation with Unconditional Diffusion Models](https://mlsanity.com/paper/2304.04344/) (2023)
- [Child Face Recognition at Scale: Synthetic Data Generation and Performance Benchmark](https://mlsanity.com/paper/2304.11685/) (2023)
- [Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groups](https://mlsanity.com/paper/2309.08442/) (2023)
- [ReEdit: Multimodal Exemplar-Based Image Editing with Diffusion Models](https://mlsanity.com/paper/2411.03982/) (2024)
- [CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing](https://mlsanity.com/paper/2303.05031/) (2023)
- [Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time](https://mlsanity.com/paper/2309.14022/) (2023)

## Abstract (arXiv)

StyleGAN is arguably one of the most intriguing and well-studied generative models, demonstrating impressive performance in image generation, inversion, and manipulation. In this work, we explore the recent StyleGAN3 architecture, compare it to its predecessor, and investigate its unique advantages, as well as drawbacks. In particular, we demonstrate that while StyleGAN3 can be trained on unaligned data, one can still use aligned data for training, without hindering the ability to generate unaligned imagery. Next, our analysis of the disentanglement of the different latent spaces of StyleGAN3 indicates that the commonly used W/W+ spaces are more entangled than their StyleGAN2 counterparts, underscoring the benefits of using the StyleSpace for fine-grained editing. Considering image inversion, we observe that existing encoder-based techniques struggle when trained on unaligned data. We therefore propose an encoding scheme trained solely on aligned data, yet can still invert unaligned images. Finally, we introduce a novel video inversion and editing workflow that leverages the capabilities of a fine-tuned StyleGAN3 generator to reduce texture sticking and expand the field of view of the edited video.