Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesis

TL;DR

This paper introduces JCDM, a diffusion-based framework that leverages multi-view priors and cross-view cues to improve pose-guided person image synthesis, achieving high fidelity and consistency across views.

Contribution

The paper proposes a novel jointly conditioned diffusion model that effectively fuses multi-view information for improved person image synthesis.

Findings

Achieves state-of-the-art fidelity in image generation.

Ensures consistent appearance across multiple views.

Supports variable numbers of reference views.

Abstract

Pose-guided human image generation is limited by incomplete textures from single reference views and the absence of explicit cross-view interaction. We present jointly conditioned diffusion model (JCDM), a jointly conditioned diffusion framework that exploits multi-view priors. The appearance prior module (APM) infers a holistic identity preserving prior from incomplete references, and the joint conditional injection (JCI) mechanism fuses multi-view cues and injects shared conditioning into the denoising backbone to align identity, color, and texture across poses. JCDM supports a variable number of reference views and integrates with standard diffusion backbones with minimal and targeted architectural modifications. Experiments demonstrate state of the art fidelity and cross-view consistency.