International Conference on Information and Knowledge Technology

فارسی

Home / شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

PC-MCLD: Pose-Constrained and Multi-focal Conditioned Latent Diffusion for Person Image Synthesis

Authors :

Hanieh Fazli¹ Reza Azmi²

1- دانشگاه الزهرا(س) 2- دانشگاه الزهرا(س)

Keywords :

pose-guided person image synthesis،latent diffusion model،texture consistency،adaptive feature fusion،fashion image generation

Abstract :

Pose-guided person image synthesis (PGPIS) aims to generate a person in a target pose while preserving identity and garment details, yet large pose variations often cause texture misalignment and loss of facial fidelity in existing diffusion models. We propose PC-MCLD, a latent diffusion framework that introduces (i) a pose-aware texture transfer constraint ensuring anatomically consistent correspondence between source and target regions, and (ii) an adaptive weighting mechanism that balances global appearance, garment texture, and facial identity cues during generation. Experiments on the DeepFashion In-Shop benchmark show clear improvements over a reproduced MCLD baseline. At 176×256, PC-MCLD reduces FID by 1.39% and LPIPS by 8.24%; at 352×512, the gains increase to 2.53% in FID and 19.48% in LPIPS. These results demonstrate that PC-MCLD enhances both perceptual quality and structural fidelity under challenging pose changes.

List of archived papers

Recommendation Systems in Smart Agriculture: Pathway to a well-designed system

Ahmad Nameni - Amir Ghafarian Daneshmand - Omid Mahdi Ebadati E

IoT-Based Model in Smart Urban Traffic Control: Graph theory and Genetic Algorithm

Saeed Doostali - Seyed Morteza Babamir - Mohammad Shiralizadeh Dezfoli - Behzad Soleimani Neysiani

Exploring the Relationship Between Gameplay Log Data and Depression & Anxiety

Soroush Elyasi - Arya Varasteh Nezhad - Fattaneh Taghiyareh

Knowledge Extraction from Technical Reports Based on Large Language Models: An Exploratory Study

Parsa Bakhtiari - Hassan Bashiri - Alireza Khalilipour - Masoud Nasiripour - Moharram Challenger

A parallel approach to the fractional time delay model for predicting the spread of COVID-19

Mahdi Movahedian Moghaddam - Kourosh Parand

طراحی و پیاده سازی بستر اجرای بازی جنگ سایبری

مریم نصراصفهانی - بهروز ترک لادانی - بهروز شاهقلی قهفرخی - حسین قجاوند بلتیجه - نوید شیرمحمدی - مهدی شمس - محمدامین آقاکبیری

AI-Powered Beauty Insights: Sentiment Analysis in a Low-Resource Language

Sajedeh Talebi - Neda Abdolvand - Fatemeh Mahdian

ارائه یک سیستم توصیه‌گر آگاه به زمینه مبتنی بر رفتار کاربر در شبکه اجتماعی با استفاده از پیام‌های برچسب شده جغرافیایی

زهرا امینی - سید علیرضا هاشمی گلپایگانی - علی میرزائی

Web Service Ranking based on QoS and Use Prefer

Seyed Hossein Siadat - Danial Ramezani - Fatemeh Ahani

A Comparative Evaluation of Machine Learning Models for Anomaly-Based IDS in IoT Networks

Seyed Amir Mousavi - Mostafa Sadeghi - Mohammad Sadeq Sirjani

more

Samin Hamayesh - Version 43.8.0