From Parts to Whole: A Unified Reference Framework for Controllable Human Image Generation
This work addresses the problem of multi-part controllable human image generation for applications like portrait customization, though it appears incremental as it builds on existing diffusion-based techniques.
The paper tackles the challenge of generating human images conditioned on multiple appearance parts by introducing Parts2Whole, a framework that uses a semantic-aware encoder and enhanced attention to achieve superior multi-part customization compared to existing methods.
Recent advancements in controllable human image generation have led to zero-shot generation using structural signals (e.g., pose, depth) or facial appearance. Yet, generating human images conditioned on multiple parts of human appearance remains challenging. Addressing this, we introduce Parts2Whole, a novel framework designed for generating customized portraits from multiple reference images, including pose images and various aspects of human appearance. To achieve this, we first develop a semantic-aware appearance encoder to retain details of different human parts, which processes each image based on its textual label to a series of multi-scale feature maps rather than one image token, preserving the image dimension. Second, our framework supports multi-image conditioned generation through a shared self-attention mechanism that operates across reference and target features during the diffusion process. We enhance the vanilla attention mechanism by incorporating mask information from the reference human images, allowing for the precise selection of any part. Extensive experiments demonstrate the superiority of our approach over existing alternatives, offering advanced capabilities for multi-part controllable human image customization. See our project page at https://huanngzh.github.io/Parts2Whole/.