Research map / Image generation / Text-to-image diffusion
GarmentAligner: Text-to-Garment Generation via Retrieval-augmented Multi-level Corrections
Shiyue Zhang, Zheng Chong, Xujie Zhang, Hanhui Li, Yuhao Cheng, yiqiang yan, Xiaodan Liang
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 retrieval-augmented contrastive learning to the three corrections (ablation) | GarmentAligner · CM-Fashion | Aesthetic score: 5.4190 -> 5.8776 | Improved |
| add retrieval-augmented contrastive learning to the three corrections (ablation) | GarmentAligner · CM-Fashion | FID: 8.924 -> 8.735 | Improved |
| add multi-level corrections to retrieval-augmented contrastive learning (ablation) | GarmentAligner · CM-Fashion | CLIPScore: 0.8984 -> 0.9245 | Improved |
| add visual correction alone (ablation) | GarmentAligner · CM-Fashion | CLIPScore: 0.9136 (visual only) vs 0.8840 (quantitative only) | Improved |
| combine visual, spatial and quantitative corrections (ablation) | GarmentAligner · CM-Fashion | FID: 9.143 -> 8.924 versus spatial alone | Improved |
| apply multi-level corrections | GarmentAligner · component-level quantity and spatial accuracy | accuracy | Improved |
| use GarmentAligner instead of SDXL and other baselines | GarmentAligner · CM-Fashion | FID: 9.091 -> 8.735 | Improved |
| use GarmentAligner instead of baselines for component accuracy | GarmentAligner · 1000 captions, 100 images each | quantity and spatial accuracy: 20-45% higher accuracy | 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.
- DiffCloth — DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment (ICCV 2023) · 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
- FashionTailor: Controllable Clothing Editing for Human Images with Appearance Preserving (AAAI 2025 · similarity 0.88)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.88)
- ChatGarment: Garment Estimation, Generation and Editing via Large Language Models (CVPR 2025 · similarity 0.87)
- AIpparel: A Multimodal Foundation Model for Digital Garments (CVPR 2025 · similarity 0.87)
- DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder (AAAI 2025 · similarity 0.87)
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · 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.
