Research map / Image generation / Text-to-image diffusion
HiGarment: Cross-modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image
Junyi Guo, Jingxuan Zhang, Fangyu Wu, Huanda Lu, Qiufeng Wang, Wenmian Yang, Eng Gee Lim, Dongming Lu
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 multi-modal semantic enhancement (MMSE) with fabric retrieval (ablation) | HiGarment · MMDGarment test | FID: 13.7995 -> 8.8109 | Improved |
| add harmonized cross-attention (HCA) instead of plain concatenation (ablation) | HiGarment · MMDGarment test | FID: 11.5491 -> 8.8109 | Improved |
| add harmonized cross-attention (HCA) (ablation) | HiGarment · MMDGarment test | LPIPS: 0.7633 -> 0.6008 | Improved |
| add MMSE (ablation) | HiGarment · MMDGarment test | CLIPScore: 0.7342 -> 0.8054 | Improved |
| train on MMDGarment dataset (ablation) | HiGarment · MMDGarment test | FID: 9.4932 -> 8.8109 | Improved |
| lower the sigmoid floor lambda so alpha falls below 0.6 (ablation) | HiGarment harmonized cross-attention · MMDGarment test | qualitative detail fidelity | Hurt |
| use HiGarment instead of IP-Adapter | flat sketch to garment generation · MMDGarment test | CLIPScore: 0.7768 -> 0.8054 | Improved |
| use DEADiff instead of IP-Adapter for perceptual similarity | baselines · MMDGarment test | LPIPS: 0.7025 -> 0.6780 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DEADiff — DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations (CVPR 2024) · better on 5 of 5 shared results
- Uni-Controlnet — Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models (NeurIPS 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
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.90)
- HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models (AAAI 2025 · similarity 0.90)
- FashionTailor: Controllable Clothing Editing for Human Images with Appearance Preserving (AAAI 2025 · similarity 0.90)
- FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models (NeurIPS 2024 · similarity 0.89)
- DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder (AAAI 2025 · similarity 0.89)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.89)
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.
