Research map / Video / Video generation
iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation
Zhoujie Fu, Xianfang Zeng, Jinghong Lan, Xinyao Liao, Cheng Chen, Junyi Chen, Jiacheng Wei, Wei Cheng, Shiyu Liu, Yunuo Chen, Gang Yu, Guosheng Lin
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 |
|---|---|---|---|
| use CocktailMix difficulty-ordered SFT instead of StageMix (ablation) | iMontage SFT · OmniContext (Multi CRef) | score: 12.6% gain | Improved |
| use CocktailMix instead of FlatMix joint training (ablation) | iMontage SFT · training loss stability | training loss | Improved |
| use CocktailMix instead of StageMix (ablation) | iMontage SFT · all tasks (harder settings) | qualitative | Improved |
| use Marginal RoPE (inputs at head, outputs at tail) instead of Even RoPE (ablation) | iMontage · editing data subset (low resolution) | convergence | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StoryDiffusion — StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation (NeurIPS 2024) · better on 2 of 2 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
- UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics (CVPR 2025 · similarity 0.86)
- CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation (AAAI 2025 · similarity 0.86)
- WeGen: A Unified Model for Interactive Multimodal Generation as We Chat (CVPR 2025 · similarity 0.86)
- VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models (ICML 2025 · similarity 0.86)
- Generative Inbetweening through Frame-wise Conditions-Driven Video Generation (CVPR 2025 · similarity 0.86)
- WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception (NeurIPS 2025 · similarity 0.86)
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.
