PMMD: A pose-guided multi-view multi-modal diffusion for person generation

📝 Original Info

• Title: PMMD: A pose-guided multi-view multi-modal diffusion for person generation
• ArXiv ID: 2512.15069
• Date: 2025-12-17
• Authors: Ziyu Shang, Haoran Liu, Rongchao Zhang, Zhiqian Wei, Tongtong Feng

📝 Abstract

Generating consistent human images with controllable pose and appearance is essential for applications in virtual try on, image editing, and digital human creation. Current methods often suffer from occlusions, garment style drift, and pose misalignment. We propose Pose-guided Multi-view Multimodal Diffusion (PMMD), a diffusion framework that synthesizes photorealistic person images conditioned on multi-view references, pose maps, and text prompts. A multimodal encoder jointly models visual views, pose features, and semantic descriptions, which reduces cross modal discrepancy and improves identity fidelity. We further design a ResCVA module to enhance local detail while preserving global structure, and a cross modal fusion module that integrates image semantics with text throughout the denoising pipeline. Experiments on the DeepFashion MultiModal dataset show that PMMD outperforms representative baselines in consistency, detail preservation, and controllability.

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)