Research map / Image generation / Autoregressive and latent generation
Mixture of Global and Local Experts With Diffusion Transformer for Controllable Face Generation
Xuechao Zou, Shun Zhang, Xing Fu, Yue Li, Kai Li, Yushe Cao, Congyan Lang, Pin Tao, Junliang Xing
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 local experts to the global expert (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | FID: 30.36 -> 22.24 | Improved |
| add global expert to local experts (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | FID: 33.62 -> 22.24 | Improved |
| add local experts to the global expert (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | mask distance: 2.47 -> 2.44 | Improved |
| use local experts instead of only global expert (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | CLIP text score: 26.30 -> 27.07 | Improved |
| use matrix gating instead of static weights (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | FID: 25.74 -> 22.24 | Improved |
| use matrix gating instead of scalar gating (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | FID: 43.48 -> 22.24 | Improved |
| add global-local experts without gating (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | FID: 33.25 -> 26.55 | Improved |
| add dynamic gating without experts (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | FID: 33.25 -> 31.30 | Improved |
| add gating on top of experts (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | FID: 26.55 -> 22.24 | Improved |
| add experts to the baseline (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | mask distance: 2.49 -> 3.20 | Hurt |
| add experts and gating to the baseline (ablation) | Face-MoGLE · MM-CelebA-HQ multimodal ablation | CLIP text score: 26.71 -> 26.32 | No clear effect |
| replace Collaborative with Face-MoGLE | multimodal face generation · MM-CelebA-HQ multimodal face generation | FID: 24.48 -> 22.24 | 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.
- TediGAN — TediGAN: Text-Guided Diverse Face Image Generation and Manipulation (CVPR 2021) · 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
- Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts (ICML 2025 · similarity 0.85)
- When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation (CVPR 2024 · similarity 0.85)
- FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network (AAAI 2025 · similarity 0.85)
- CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation (ICLR 2025 · similarity 0.85)
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation (CVPR 2024 · similarity 0.85)
- CapHuman: Capture Your Moments in Parallel Universes (CVPR 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.
