ASIA: adaptive single-diffusion-stage inference acceleration for diffusion-based virtual try-on

Abstract Virtual try-on synthesises an image of a person wearing a chosen garment. Diffusion models give the most realistic results, but remain too slow for interactive use. The leading method, TPD, runs its diffusion network twice: a first pass predicts a pair-specific mask locating where the garment belongs, and a second pass renders the garment into that region. Each pass takes about 100 denoising steps, so one image needs roughly 200, half of them producing only a binary shape. This first stage does not justify a diffusion model. We propose Adaptive Single-Diffusion-Stage Inference Acceleration (ASIA), which replaces diffusion-based mask generation with a lightweight convolutional network. Using DensePose and the flat garment mask as structural priors, ASIA predicts the pair-specific mask in one forward pass, reducing that stage from seconds to milliseconds. Try-on then needs a single diffusion stage, whose input block alone is finetuned to the new mask distribution. On VITON-HD, inference falls from 15.4 to 7.5 seconds per image, a 2.05-fold speedup. Under a controlled reproduction of TPD, paired structural (SSIM) and perceptual (LPIPS) similarity both improve while the Fréchet Inception Distance rises slightly (9.04 against 8.78). Removing an entire diffusion stage thus trades a small FID increase for a large speedup and improved paired fidelity.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-12
DOI
https://doi.org/10.1038/s41598-026-74469-5
Primary Topic
Generative Adversarial Networks and Image Synthesis
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

ASIA: adaptive single-diffusion-stage inference acceleration for diffusion-based virtual try-on

Asmaa A. E. Osman, Eid Mohamed Elemry, Reda Abdelwahab, Shrouk Mansour
Scientific Reports
Generative Adversarial Networks and Image Synthesis
article

ASIA: adaptive single-diffusion-stage inference acceleration for diffusion-based virtual try-on

Asmaa A. E. Osman, Eid Mohamed Elemry, Reda Abdelwahab, Shrouk Mansour
article en

Abstract

Abstract Virtual try-on synthesises an image of a person wearing a chosen garment. Diffusion models give the most realistic results, but remain too slow for interactive use. The leading method, TPD, runs its diffusion network twice: a first pass predicts a pair-specific mask locating where the garment belongs, and a second pass renders the garment into that region. Each pass takes about 100 denoising steps, so one image needs roughly 200, half of them producing only a binary shape. This first stage does not justify a diffusion model. We propose Adaptive Single-Diffusion-Stage Inference Acceleration (ASIA), which replaces diffusion-based mask generation with a lightweight convolutional network. Using DensePose and the flat garment mask as structural priors, ASIA predicts the pair-specific mask in one forward pass, reducing that stage from seconds to milliseconds. Try-on then needs a single diffusion stage, whose input block alone is finetuned to the new mask distribution. On VITON-HD, inference falls from 15.4 to 7.5 seconds per image, a 2.05-fold speedup. Under a controlled reproduction of TPD, paired structural (SSIM) and perceptual (LPIPS) similarity both improve while the Fréchet Inception Distance rises slightly (9.04 against 8.78). Removing an entire diffusion stage thus trades a small FID increase for a large speedup and improved paired fidelity.

Scientific ReportsVol. 16(1)
Cairo University (EG)
Cairo University
Generative Adversarial Networks and Image Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon