Multi-focal Conditioned Latent Diffusion for Person Image Synthesis
This work addresses detail preservation in person image synthesis for applications like virtual try-on, but it is incremental as it builds on existing latent diffusion models.
The paper tackles the problem of detail deterioration in pose-guided person image synthesis by proposing a Multi-focal Conditioned Latent Diffusion method, which improves identity consistency and appearance realism on the DeepFashion dataset.
The Latent Diffusion Model (LDM) has demonstrated strong capabilities in high-resolution image generation and has been widely employed for Pose-Guided Person Image Synthesis (PGPIS), yielding promising results. However, the compression process of LDM often results in the deterioration of details, particularly in sensitive areas such as facial features and clothing textures. In this paper, we propose a Multi-focal Conditioned Latent Diffusion (MCLD) method to address these limitations by conditioning the model on disentangled, pose-invariant features from these sensitive regions. Our approach utilizes a multi-focal condition aggregation module, which effectively integrates facial identity and texture-specific information, enhancing the model's ability to produce appearance realistic and identity-consistent images. Our method demonstrates consistent identity and appearance generation on the DeepFashion dataset and enables flexible person image editing due to its generation consistency. The code is available at https://github.com/jqliu09/mcld.