Research map / Image generation / Image restoration
FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior
Zhekai Chen, Wen Wang, Zhen Yang, Zeqing Yuan, Hao Chen, Chunhua Shen
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 mask-guided K,V discarding to the DDS loss for object removal (ablation) | FreeCompose object removal · object removal (qualitative ablation) | object removed completely (qualitative) | Improved |
| add perceptual loss on the background to mask-guided DDS (ablation) | FreeCompose object removal · object removal (qualitative ablation) | background preservation (qualitative) | Improved |
| use plain DDS loss with default prompts for removal (no mask) (ablation) | FreeCompose object removal · object removal (qualitative ablation) | object removed completely (qualitative) | Hurt |
| add separate foreground and background perceptual losses to DDS in harmonization (ablation) | FreeCompose harmonization · image harmonization (qualitative ablation) | harmony and identity trade-off (qualitative) | Improved |
| use FreeCompose instead of LaMa | object removal · Object removal user study | image harmony (1-5): 3.47 -> 3.85 | Improved |
| use FreeCompose instead of DucoNet | image harmonization · Image harmonization user study | object identity preserving (1-5): 4.16 -> 4.11 | Hurt |
| use FreeCompose instead of DucoNet | image harmonization · Image harmonization user study | image harmony (1-5): 3.14 -> 3.69 | Improved |
Later papers that compared with this method
1 later accepted paper reports FreeCompose as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting (ICCV 2025 · better on 6 of 7 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
- RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models (NeurIPS 2024 · similarity 0.89)
- PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor (CVPR 2024 · similarity 0.88)
- Compositional Image Decomposition with Diffusion Models (ICML 2024 · similarity 0.88)
- FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction (NeurIPS 2025 · similarity 0.87)
- High-Fidelity Diffusion-Based Image Editing (AAAI 2024 · similarity 0.87)
- Inversion-Free Image Editing with Language-Guided Diffusion Models (CVPR 2024 · similarity 0.87)
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.
