Research map / Image generation / Editing and style transfer
Texture and sketch synthesis
Synthesize stylized images, sketches, and textures with controllable disentanglement.
130 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2026) · an approach in Editing and style transfer, keyword cluster “translation · style transfer · image image”
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.
32 papers in 2023–24 and 51 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 11.7% to 13.0%.
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
- 2017 · Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis (CVPR 2017 · 873 citations)
- 2018 · Multi-Content GAN for Few-Shot Font Style Transfer (CVPR 2018 · 351 citations)
- 2019 · SCFont: Structure-Guided Chinese Font Generation via Deep Stacked Networks (AAAI 2019 · 122 citations)
- 2020 · Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic Correspondence (CVPR 2020 · 175 citations)
- 2021 · DG-Font: Deformable Generative Networks for Unsupervised Font Generation (CVPR 2021 · 138 citations)
- 2022 · Thin-Plate Spline Motion Model for Image Animation (CVPR 2022 · 217 citations)
- 2023 · CF-Font: Content Fusion for Few-Shot Font Generation (CVPR 2023 · 79 citations)
- 2024 · FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning (AAAI 2024 · 82 citations)
- 2025 · MangaNinja: Line Art Colorization with Precise Reference Following (CVPR 2025 · 11 citations)
- 2026 · Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration (ICML 2026 · 0 citations)
Earliest papers here
- Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis (CVPR 2017 · 873 citations)
- Deep Image Harmonization (CVPR 2017 · 257 citations)
- Awesome Typography: Statistics-Based Text Effects Transfer (CVPR 2017 · 80 citations)
What has been tried
101 papers here report 995 measured changes (a component added, removed or swapped, compared with a baseline): helped 75%, no clear effect 4%, hurt 18%, mixed 3%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| add MCA to the baseline | UFUC average · FID | 8.1153 -> 7.8419 | Helped | FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning (AAAI 2024 · 82 citations) |
| add direct shading, including cast-shadow information, instead of N-dot-L shading | Lighting control test set · L-PSNR | 6.43 ± 2.20 -> 13.04 ± 3.57 | Helped | LightIt: Illumination Modeling and Control for Diffusion Models (CVPR 2024 · 26 citations) |
| replace the traditional DDPM process with the proposed latent diffusion process | UFUC · RMSE | 0.2676 -> 0.2475 | Helped | Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models (CVPR 2024 · 23 citations) |
| Add SPN with λSPN=0.1 instead of omitting SPN | stylization evaluation · ArtFID | 36.41 -> 34.89 | Helped | One-Shot Structure-Aware Stylized Image Synthesis (CVPR 2024 · 17 citations) |
| Add PCEM to the baseline generation model | 40 real IDs, open-set train:test = 1:1 · TAR@FAR=1e-6 | 0.4144 -> 0.5525 | Helped | PCE-Palm: Palm Crease Energy Based Two-Stage Realistic Pseudo-Palmprint Generation (AAAI 2024 · 14 citations) |
| combine Canny and HED conditions rather than use either condition alone | COCO-stuff validation · CF | 46.99, 45.28 -> 47.18 | Helped | Automatic Controllable Colorization via Imagination (CVPR 2024 · 13 citations) |
| add progressive patch shuffle | MangaNinja benchmark · PSNR | 18.02 -> 19.72 | Helped | MangaNinja: Line Art Colorization with Precise Reference Following (CVPR 2025 · 11 citations) |
| Add the cascaded module using the global mask instead of only the base network | iHarmony4 test · PSNR | 36.82 -> 36.98 | Helped | FRIH: Fine-Grained Region-Aware Image Harmonization (AAAI 2024 · 11 citations) |
| Add the Emotion adapter | AIM image editing · image editing quality | Helped | EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025 · 9 citations) | |
| replace TPS transformations with CPAB transformations | TaiChiHD · AED | 0.151 -> 0.123 | Helped | Continuous Piecewise-Affine Based Motion Model for Image Animation (AAAI 2024 · 9 citations) |
| Add Img2Img refinement | Texture refinement evaluation · FID (↓) | 86.25 -> 82.05 | Helped | GenesisTex: Adapting Image Denoising Diffusion to Texture Space (CVPR 2024 · 9 citations) |
| add IHA, SSA, and SCE to the baseline | UFSC and UFUC, 3-shot · FID | 8.2656 -> 8.4922 | Hurt | IF-Font: Ideographic Description Sequence-Following Font Generation (NeurIPS 2024 · 7 citations) |
What reviewers will expect
Datasets and baselines named in the 30 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- 4SKST · 2 of 30 papers
- WikiArt · 2 of 30 papers
Baselines
- InstantStyle · 5 of 30 papers
- IP-Adapter · 5 of 30 papers
- StyleID · 3 of 30 papers
- MUNIT · 2 of 30 papers
- VCT · 2 of 30 papers
- PowerPaint · 2 of 30 papers
- BLIP-Diffusion · 2 of 30 papers
- ControlNet · 2 of 30 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 83 papers; from OpenAlex and the papers' affiliations).
- Alibaba Group · 7 papers
- Tencent · 5 papers
- Chinese Academy of Sciences · 4 papers
- Shanghai Jiao Tong University · 4 papers
- Zhejiang University · 4 papers
- Tsinghua University · 3 papers
- University of Chinese Academy of Sciences · 2 papers
- Fudan University · 2 papers
- Nanyang Technological University · 2 papers
- South China University of Technology · 2 papers
Use it
Download BibTeX of 39 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
- Image-to-image translation (127 papers)
- Arbitrary neural style transfer (124 papers)
- Virtual try-on (46 papers)
- Pose-guided person image synthesis (29 papers)
Elsewhere in the topic
- Instruction-based diffusion editing (151 papers)
- Inversion-based diffusion editing (113 papers)
- Identity-preserving face manipulation (88 papers)
- Localized and attribute-specific editing (73 papers)
- Diffusion face generation and editing (61 papers)
- GAN inversion for editing (25 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).