Research map / Image generation / Text-to-image diffusion
General Image-to-Image Translation with One-Shot Image Guidance
Bin Cheng, Zuhao Liu, Yunbo Peng, Yue Lin
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 multi-concept inversion (learned reference embedding instead of the word 'dog') (ablation) | VCT · general I2I (leopard to dog) | visual fidelity to reference | Improved |
| add pivotal turning inversion (ablation) | VCT · general I2I | source reconstruction | Improved |
| add attention control from content matching branch (ablation) | VCT · general I2I | structure preservation | Improved |
| use 3 concept embeddings instead of fewer or more (ablation) | multi-concept inversion · general I2I | visual concept translation | Improved |
| drop negative embeddings from DreamArtist-style inversion, use single positive embedding | multi-concept inversion · general I2I | design choice | No clear effect |
| move reconstruction constraint from image space to latent space | multi-concept inversion · general I2I | resource cost | Improved |
| use VCT instead of GAN-based and prior diffusion style transfer methods | style transfer · 800 generated images | LPIPS: 0.42 (best baseline) -> 0.35 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- StyTR2 — StyTr2: Image Style Transfer With Transformers (CVPR 2022) · better on 2 of 2 shared results
- Artflow — ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows (CVPR 2021) · better on 2 of 2 shared results
- StyleFormer — StyleFormer: Real-Time Arbitrary Style Transfer via Parametric Style Composition (ICCV 2021) · 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
- ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models (AAAI 2024 · similarity 0.85)
- Concept Lancet: Image Editing with Compositional Representation Transplant (CVPR 2025 · similarity 0.85)
- Text-to-Image Generation for Abstract Concepts (AAAI 2024 · similarity 0.84)
- Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models (CVPR 2024 · similarity 0.84)
- Bridging the gap to real-world language-grounded visual concept learning (NeurIPS 2025 · similarity 0.84)
- MC^2: Multi-concept Guidance for Customized Multi-concept Generation (CVPR 2025 · similarity 0.84)
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.
