AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation

Shengqi Liu, Yuhao Cheng, Zhuo Chen, Xingyu Ren, Wenhan Zhu, Lincheng Li, Mengxiao Bi, Xiaokang Yang, Yichao Yan

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 13 citations (OpenAlex)

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 changedWhereMeasuredEffect
compress sewing pattern latent to 256*6 with n=2 instead of 256*8 n=2 (ablation)SewingLDM · Latent compression ablationclothes-to-body distance (cm): 2.87 cm -> 2.20 cmImproved
compress sewing pattern latent to 256*6 with n=2 instead of 256*8 n=2 (ablation)SewingLDM · Latent compression ablationcodebook usage (%): 91% -> 100%Improved
add compact quantized latent (256*8, n=2) instead of no compression (ablation)SewingLDM · Latent compression ablationgeneration abilityImproved
use more compressed 256*4 latent with n=2 (ablation)SewingLDM · Latent compression ablationreconstructionHurt
use larger quantization n=32 or n=8 with 256*32 or 256*12 latents (ablation)SewingLDM · Latent compression ablationcodebook usage (%): 0%Hurt
fine-tune output layers of both self- and cross-attention instead of only one (ablation)SewingLDM · multi-modal conditioning (qualitative)sketch alignmentImproved
inject body and sketch condition at shallower layers (after block 0) rather than block 5, 10, 15, 20 (ablation)SewingLDM · multi-modal conditioning (qualitative)garment completenessImproved
use two-step training instead of one-step training (ablation)SewingLDM · sketch-only generation (qualitative)garment fidelityImproved
use extended sewing pattern representation instead of original (ablation)SewingLDM · representation ablation (qualitative)garment diversityImproved
use SewingLDM instead of DressCodesewing pattern generation · Sewing pattern generation comparisonclothes-to-body distance (cm): 3.69 cm -> 2.20 cmImproved
use SewingLDM instead of Sewformersewing pattern generation · Sewing pattern generation comparisonuser value (1-5): 2.10 -> 4.60Improved
use SewingLDM instead of fine-tuned SewFormersewing pattern generation · GarmentCode test set reconstructionStitch Acc: 2.8 -> 84.2Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy