Research map / Image generation / Editing and style transfer
One-for-All: Towards Universal Domain Translation With a Single StyleGAN
Yong Du, Jiahui Zhan, Xinzhe Li, Junyu Dong, Sheng Chen, Ming–Hsuan Yang, Shengfeng He
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add nonlinear mapping M in the CLIP2P mapper (ablation) | UniTranslator · E621Faces and LSUN-church targets | image quality (qualitative) | Improved |
| add nonlinear mapping M in the CLIP2P mapper (ablation) | UniTranslator · FFHQ target | image quality (qualitative) | Improved |
| add linear layer in the CLIP2P mapper (ablation) | UniTranslator · AFHQ-cat->FFHQ | training stability | Improved |
| add decoupling module (ablation) | UniTranslator · AFHQ-cat->FFHQ | cross-domain correspondence (qualitative) | Improved |
| add decoupling module (ablation) | UniTranslator · varied source-target gaps | translation quality | Improved |
| add L_p loss (ablation) | UniTranslator · AFHQ-cat->LSUN-church | translation quality | Improved |
| add L_cycle loss (ablation) | UniTranslator · semantic correspondence | translation quality | Improved |
| add L_mse loss (ablation) | UniTranslator · color consistency | translation quality | Improved |
| add L_lpips loss (ablation) | UniTranslator · perceptual relations | translation quality | Improved |
| use UniTranslator instead of DiffuseIT | DiffuseIT · Average over 8 translation tasks | LPIPS: 0.45 -> 0.23 | Improved |
| use UniTranslator instead of StarGAN2 | StarGAN2 · Average over 8 translation tasks | NIQE: 4.95 -> 4.19 | Improved |
| use UniTranslator instead of StarGAN2 | StarGAN2 · Average over 8 translation tasks | CLIP similarity: 0.650 -> 0.665 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- GP-UNIT — GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation (TPAMI 2023) · better on 4 of 4 shared results
- PULSE — PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models (CVPR 2020) · better on 3 of 3 shared results
- StarGAN2 — StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018) · better on 3 of 3 shared results
- DiffusionCLIP — DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation (CVPR 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Domain-Scalable Unpaired Image Translation via Latent Space Anchoring (TPAMI 2023 · similarity 0.89)
- GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation (TPAMI 2023 · similarity 0.87)
- UniTranslator: A Unified Multi-modal framework for End-to-end In-Image Machine Translation (ECCV 2026 · similarity 0.87)
- CLIPCEIL: Domain Generalization through CLIP via Channel rEfinement and Image-text aLignment (NeurIPS 2024 · similarity 0.86)
- Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling (NeurIPS 2026 · similarity 0.85)
- UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing (ICLR 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
