Research map / Vision-language and multimodal / CLIP and zero-shot
Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the predicted-attribute entanglement loss to StyleCLIP's latent mapper | StyleCLIP latent mapper · CelebA-HQ face commands in the reported comparison | indicator (lower is better): 0.3359 -> 0.0071 (grey hair); 0.5553 -> 0.1411 (black hair); 0.4022 -> 0.1691 (wavy hair); 0.3870 -> 0.1266 (with bangs) | Helped |
| Add the predicted-attribute entanglement loss to StyleCLIP's latent mapper | StyleCLIP latent mapper · CelebA-HQ face commands in the reported comparison | normalized command change (Δd_c'): 0.4878 -> 0.3519 (grey hair); 0.3628 -> 0.1898 (black hair); 0.2877 -> 0.1442 (wavy hair); 0.3451 -> 0.2384 (with bangs) | Hurt |
| Increase the entanglement-loss coefficient λ_E (ablation) | PPE · Blue eyes and with earrings | manipulation effect and attribute preservation | Mixed |
| Vary the number N of constraining attributes (ablation) | PPE · Blue eyes and with earrings | qualitative manipulation result | No clear effect |
Closest papers by meaning
- An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control (AAAI 2025 · similarity 0.88)
- PairEdit: Learning Semantic Variations for Exemplar-based Image Editing (NeurIPS 2025 · similarity 0.86)
- 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting (ICLR 2025 · similarity 0.85)
- IDseq: Decoupled and Sequentially Detecting and Grounding Multi-Modal Media Manipulation (AAAI 2025 · similarity 0.85)
- Learning to Manipulate Artistic Images (AAAI 2024 · similarity 0.85)
- SDGAN: Disentangling Semantic Manipulation for Facial Attribute Editing (AAAI 2024 · 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.