# From Continuity to Editability: Inverting GANs with Consecutive Images

arXiv: https://arxiv.org/abs/2107.13812 · HTML: https://mlsanity.com/paper/2107.13812/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 29 Jul 2021.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (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)
- [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)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (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)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Inverting The Generator Of A Generative Adversarial Network](https://mlsanity.com/paper/1611.05644/) (2016)
- [Invertible Conditional GANs for image editing](https://mlsanity.com/paper/1611.06355/) (2016)

## Built on by (most cited first, 25 of 25)

- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [Stitch it in Time: GAN-Based Facial Editing of Real Videos](https://mlsanity.com/paper/2201.08361/) (2022)
- [High-resolution Face Swapping via Latent Semantics Disentanglement](https://mlsanity.com/paper/2203.15958/) (2022)
- [Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation](https://mlsanity.com/paper/2404.01050/) (2024)
- [Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing](https://mlsanity.com/paper/2206.08357/) (2022)
- [Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Exploration](https://mlsanity.com/paper/2207.09855/) (2022)
- [StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation](https://mlsanity.com/paper/2308.16909/) (2023)
- [Feature-Style Encoder for Style-Based GAN Inversion](https://mlsanity.com/paper/2202.02183/) (2022)
- [Editing Out-of-domain GAN Inversion via Differential Activations](https://mlsanity.com/paper/2207.08134/) (2022)
- [D4-VTON: Dynamic Semantics Disentangling for Differential Diffusion based Virtual Try-On](https://mlsanity.com/paper/2407.15111/) (2024)
- [RIGID: Recurrent GAN Inversion and Editing of Real Face Videos](https://mlsanity.com/paper/2308.06097/) (2023)
- [Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis](https://mlsanity.com/paper/2504.14470/) (2025)
- [Make It So: Steering StyleGAN for Any Image Inversion and Editing](https://mlsanity.com/paper/2304.14403/) (2023)
- [IA-FaceS: A Bidirectional Method for Semantic Face Editing](https://mlsanity.com/paper/2203.13097/) (2022)
- [StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer](https://mlsanity.com/paper/2304.02744/) (2023)
- [One-for-All: Towards Universal Domain Translation with a Single StyleGAN](https://mlsanity.com/paper/2310.14222/) (2023)
- [Overparameterization Improves StyleGAN Inversion](https://mlsanity.com/paper/2205.06304/) (2022)
- [Leveraging GAN Priors for Few-Shot Part Segmentation](https://mlsanity.com/paper/2207.13428/) (2022)
- [Self-supervised Matting-specific Portrait Enhancement and Generation](https://mlsanity.com/paper/2208.06601/) (2022)
- [Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing](https://mlsanity.com/paper/2408.13395/) (2024)
- [A naive method to discover directions in the StyleGAN2 latent space](https://mlsanity.com/paper/2203.10373/) (2022)
- [A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration](https://mlsanity.com/paper/2207.10309/) (2022)
- [CoIE: Chain-of-Instruct Editing for Multi-Attribute Face Manipulation](https://mlsanity.com/paper/2312.07879/) (2023)
- [Modelling Latent Dynamics of StyleGAN using Neural ODEs](https://mlsanity.com/paper/2208.11197/) (2022)
- [One Style is All you Need to Generate a Video](https://mlsanity.com/paper/2310.17835/) (2023)

## Abstract (arXiv)

Existing GAN inversion methods are stuck in a paradox that the inverted codes can either achieve high-fidelity reconstruction, or retain the editing capability. Having only one of them clearly cannot realize real image editing. In this paper, we resolve this paradox by introducing consecutive images (eg, video frames or the same person with different poses) into the inversion process. The rationale behind our solution is that the continuity of consecutive images leads to inherent editable directions. This inborn property is used for two unique purposes: 1) regularizing the joint inversion process, such that each of the inverted code is semantically accessible from one of the other and fastened in a editable domain; 2) enforcing inter-image coherence, such that the fidelity of each inverted code can be maximized with the complement of other images. Extensive experiments demonstrate that our alternative significantly outperforms state-of-the-art methods in terms of reconstruction fidelity and editability on both the real image dataset and synthesis dataset. Furthermore, our method provides the first support of video-based GAN inversion, and an interesting application of unsupervised semantic transfer from consecutive images. Source code can be found at: urlhttps://github.com/cnnlstm/InvertingGANswithConsecutiveImgs.