Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision
Existing image editing frameworks predominantly follow the training paradigm of text-to-image diffusion models. However, extending this paradigm to image editing highlights two inherent discrepancies, specifically, the insufficient attention to edit concept granularity and the training inefficiency caused by sparse supervision signals. To address these issues, we establish a comprehensive hierarchical taxonomy featuring over 1,000 fine-grained edit concepts and build ConceptEdit-12M, a massive dataset of 12 million high-quality editing pairs via an improved synthesis framework. This library-dr
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “Unlocking the Potential of Image Editing via Concept Scaling” ≈ “Tongyi-MAI/Z-Image-Turbo””
- FuzzySimilar title/name (fuzzy) · 84%roboflow/supervision →
“Fuzzy title match (0.92): “Unlocking the Potential of Image Editing via Concept Scaling” ≈ “roboflow/supervision””
- FuzzyOverlapping authors or contributors · 62%Zeyi-Lin/HivisionIDPhotos →
“Shared author/contributor keys: lin”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzyOverlapping authors or contributors · 62%hiyouga/LlamaFactory →
“Shared author/contributor keys: lin”
- LinkedLinked via arxiv author · 85%Long Cui →
“Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision”
- LinkedLinked via arxiv author · 85%Xiaoqian Liu →
“Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision”
- LinkedLinked via arxiv author · 85%Qi Qin →
“Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision”