Research map / Image generation / Autoregressive and latent generation
GarmentGPT: Compositional Garment Pattern Generation via Discrete Latent Tokenization
Fangsheng Weng, Junhao Chen, Xiang Li, Jie Qin, Hanzhong Guo, ShaochunHao, Xiaoguang Han
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 text input to image input (ablation) | GarmentGPT (LLaVA-1.5) · GarmentCode dataset | Panel Accuracy: 93.53% -> 95.62% | Improved |
| add image input to text input (ablation) | GarmentGPT (LLaVA-1.5) · GarmentCode dataset | Panel Accuracy: 64.03% -> 95.62% | Improved |
| replace AIpparel continuous regression with discrete tokens | GarmentGPT · GarmentCode dataset | Panel Accuracy: 78.92% -> 95.62% | Improved |
| replace AIpparel continuous regression with discrete tokens | GarmentGPT · GarmentCode dataset | Stitch Accuracy: 56.57% -> 81.84% | Improved |
| scale Qwen backbone from 3B to 7B (ablation) | GarmentGPT · GarmentCode dataset | Panel Accuracy: 85.56% -> 90.31% | Improved |
| scale Qwen backbone from 7B to 32B (ablation) | GarmentGPT · GarmentCode dataset | Panel Accuracy: 90.31% -> 91.05% | No clear effect |
| use LLaVA-1.5 backbone instead of Qwen-7B (ablation) | GarmentGPT · GarmentCode dataset | Panel Accuracy: 90.31% -> 95.62% | Improved |
| train on real-photo data and evaluate on real photos | GarmentGPT vs AIpparel · Real-Garments Benchmark | Panel Accuracy: 38.76% -> 90.84% | Improved |
| increase residual quantizers from 1 to 8 (ablation) | RVQ-VAE · RVQ-VAE codec reconstruction | Total loss: 3.72 -> 0.08 | Improved |
| increase residual quantizers from 1 to 8 (ablation) | RVQ-VAE · RVQ-VAE codec reconstruction | Curve accuracy: 93.3 -> 99.8 | Improved |
| add multi-stage quality filtering to data pipeline | RealGarment-1M pipeline · alignment acceptability | acceptability: 64.3% -> 99.6% | Improved |
Closest papers by meaning
- ChatGarment: Garment Estimation, Generation and Editing via Large Language Models (CVPR 2025 · similarity 0.91)
- AIpparel: A Multimodal Foundation Model for Digital Garments (CVPR 2025 · similarity 0.91)
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images (NeurIPS 2026 · similarity 0.90)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.89)
- DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder (AAAI 2025 · similarity 0.89)
- Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis (CVPR 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.
