Research map / Video / Video generation
Text2LIVE: Text-Driven Layered Image and Video Editing
Omer Bar-Tal, Dolev Ofri-Amar, Rafail Fridman, Yoni Kasten, Tali Dekel
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 relevancy-based bootstrapping of the opacity map (ablation) | Text2LIVE · Image editing (red hat) | edit localization (qualitative) | Improved |
| add sparsity regularization L_reg (ablation) | Text2LIVE · Image editing (golden mango) | matte accuracy (qualitative) | Improved |
| add structure loss L_structure (ablation) | Text2LIVE · Image editing (golden mango) | shape preservation (qualitative) | Improved |
| add screen loss L_screen (ablation) | Text2LIVE · Image editing (golden mango) | segmentation and texture quality (qualitative) | Improved |
| train on an internal dataset of augmentations instead of test-time optimization on the single input (ablation) | Text2LIVE · Image editing (golden mango) | edit quality (qualitative) | Improved |
| train on video frames mapped from atlas edits instead of the atlas as a single image (ablation) | Text2LIVE video · AMT video editing | fraction of votes in favor: 0.73 ± 0.14 | Improved |
| edit in atlas space instead of per-frame editing (ablation) | Text2LIVE video · AMT video editing | fraction of votes in favor: 0.74 ± 0.15 | Improved |
| use Text2LIVE instead of Diffusion+CLIP | text-driven image editing · AMT 2AFC image editing | fraction of votes in favor: 0.82 ± 0.11 | Improved |
Closest papers by meaning
- Text-Driven Image Editing via Learnable Regions (CVPR 2024 · similarity 0.89)
- LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration (NeurIPS 2025 · similarity 0.87)
- TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control (NeurIPS 2024 · similarity 0.87)
- Text2Relight: Creative Portrait Relighting with Text Guidance (AAAI 2025 · similarity 0.87)
- Textualize Visual Prompt for Image Editing via Diffusion Bridge (AAAI 2025 · similarity 0.87)
- Text-Vision Co-Instructed Image Editing (NeurIPS 2026 · 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.
