X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis
Imaging factor disentanglement in text-to-image generation aims to independently control image acquisition properties such as types of camera lenses, sensor types, viewpoints, and domains to enable combinatorial generalization. This should let the model synthesize novel factor combinations unobserved in the training data, such as pairing a fisheye lens with an event sensor never observed in training data. Recent work, MULTI, introduced learnable, factor-specific embeddings to disentangle imaging factors, along with the Factor Alignment Accuracy (FAA) metric to evaluate disentanglement quality.
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): “X-MULTI: VLM-based Imaging Factor Disentanglement for Factor” ≈ “Tongyi-MAI/Z-Image-Turbo””
- LinkedLinked via arxiv author · 85%Sonali Godavarthy →
“X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis”
- LinkedLinked via arxiv author · 85%Matthias Neuwirth-Trapp →
“X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis”
- LinkedLinked via arxiv author · 85%Tim-Felix Faasch →
“X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis”
- LinkedLinked via arxiv author · 85%Maarten Bieshaar →
“X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis”
- LinkedLinked via arxiv author · 85%Michael Moeller →
“X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis”
- LinkedLinked via arxiv author · 85%Kristof Van Laerhoven →
“X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis”
- LinkedLinked via arxiv author · 85%Danda Pani Paudel →
“X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis”