Research map / Image generation / Autoregressive and latent generation
Semi-supervised Latent Disentangled Diffusion Model for Textile Pattern Generation
Chenggong Hu, Yi Wang, Mengqi Xue, Haofei Zhang, Jie Song, Li Sun
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 the full LDN (disentangled features) in place of entangled features (ablation) | SLDDM-TPG · CTP-HD (with GT) | FID: 27.15 -> 15.59 | Improved |
| add the textile pattern content feature from SCM (ablation) | SLDDM-TPG · CTP-HD (with GT) | FID: 23.59 -> 15.59 | Improved |
| add the SAT structured feature (ablation) | SLDDM-TPG · CTP-HD (with GT) | FID: 16.04 -> 15.59 | Improved |
| add the RAM texture defect feature (ablation) | SLDDM-TPG · CTP-HD (with GT) | FID: 16.89 -> 15.59 | Improved |
| add the alignment process in S-LDM (ablation) | SLDDM-TPG · CTP-HD (with GT) | FID: 18.61 -> 15.59 | Improved |
| add the CLS module (ablation) | SLDDM-TPG · CTP-HD (with GT) | FPS: 0.727 -> 0.875 | Improved |
| add the STD loss (ablation) | SLDDM-TPG · CTP-HD (with GT) | FID: 16.86 -> 15.59 | Improved |
| add the CLS module (ablation) | SLDDM-TPG · CTP-HD (with GT) | FID: 16.23 -> 15.59 | Improved |
| SLDDM-TPG versus best baseline SSR-Encoder | image-to-image generation · CTP-HD (with GT) | FID: 19.69 -> 15.59 | Improved |
| SLDDM-TPG versus best baseline SSR-Encoder | image-to-image generation · CTP-HD (with GT) | SSIM: 0.278 -> 0.394 | Improved |
| SLDDM-TPG versus SSR-Encoder on VITON-HD | generalization · VITON-HD (1000 images, without GT) | CTS: 0.641 -> 0.736 | Improved |
Closest papers by meaning
- Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation (ICCV 2025 · similarity 0.90)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.89)
- HiGarment: Cross-modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image (ICCV 2025 · similarity 0.88)
- GarmentGPT: Compositional Garment Pattern Generation via Discrete Latent Tokenization (ICLR 2026 · similarity 0.87)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.86)
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (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.
