Research map / Image generation / Editing and style transfer
GAN inversion for editing
Invert real images into StyleGAN latent spaces for attribute editing.
25 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2019–2026) · an approach in Editing and style transfer, keyword cluster “image editing · edits · inversion”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
9 papers in 2023–24 and 2 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 3.3% to 0.5%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2019 · STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing (CVPR 2019 · 389 citations)
- 2020 · Editing in Style: Uncovering the Local Semantics of GANs (CVPR 2020 · 271 citations)
- 2021 · Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation (ICLR 2021 · 6 citations)
- 2022 · HyperStyle: StyleGAN Inversion With HyperNetworks for Real Image Editing (CVPR 2022 · 259 citations)
- 2023 · StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN (CVPR 2023 · 48 citations)
- 2024 · The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing (CVPR 2024 · 17 citations)
- 2025 · Reference-Based 3D-Aware Image Editing with Triplanes (CVPR 2025 · 1 citation)
- 2026 · FlashIn: Fast and Accurate Image Inversion for Real-time Image Editing (CVPR 2026)
Earliest papers here
- STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing (CVPR 2019 · 389 citations)
- Editing in Style: Uncovering the Local Semantics of GANs (CVPR 2020 · 271 citations)
- The GAN That Warped: Semantic Attribute Editing With Unpaired Data (CVPR 2020 · 5 citations)
What has been tried
24 papers here report 226 measured changes (a component added, removed or swapped, compared with a baseline): helped 70%, no clear effect 6%, hurt 22%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| add Feature Editor H | CelebA-HQ test · LPIPS | 0.016 -> 0.019 | Hurt | The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing (CVPR 2024 · 17 citations) |
| Add attribute-specific editing modules instead of one unified editing module | CelebA-HQ test, + Bangs, latent-guided · FID | 18.41 -> 15.69 | Helped | SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 2024 · 11 citations) |
| remove GAM | Celeba-HQ reconstruction · ID | 0.813 -> 0.708 | Hurt | Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing (AAAI 2024 · 2 citations) |
| Add the two-branch spatial-contextual hourglass module | Face domain · reconstruction fidelity and artifacts | Helped | Spatial-Contextual Discrepancy Information Compensation for GAN Inversion (AAAI 2024 · 2 citations) | |
| add triplane-gradient post-processing | CelebA eyeglasses edit · FID | 79.50 -> 74.46 | Helped | Reference-Based 3D-Aware Image Editing with Triplanes (CVPR 2025 · 1 citation) |
What reviewers will expect
Datasets and baselines named in the 5 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- FFHQ · 4 of 5 papers
- CelebA-HQ · 4 of 5 papers
- Stanford Cars · 3 of 5 papers
Baselines
- HFGI · 4 of 5 papers
- e4e · 3 of 5 papers
- HyperStyle · 3 of 5 papers
- StyleRes · 3 of 5 papers
- ReStyle · 2 of 5 papers
- CLCAE · 2 of 5 papers
- HiSD · 2 of 5 papers
- VecGAN · 2 of 5 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 11 papers; from OpenAlex and the papers' affiliations).
- Bilkent University · 2 papers
Use it
Download BibTeX of 23 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Instruction-based diffusion editing (151 papers)
- Inversion-based diffusion editing (113 papers)
- Localized and attribute-specific editing (73 papers)
Elsewhere in the topic
- Texture and sketch synthesis (130 papers)
- Image-to-image translation (127 papers)
- Arbitrary neural style transfer (124 papers)
- Identity-preserving face manipulation (88 papers)
- Diffusion face generation and editing (61 papers)
- Virtual try-on (46 papers)
- Pose-guided person image synthesis (29 papers)
- Talking face generation (21 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).