DRDM：一种用于合成逼真人物图像的解耦表示扩散模型
DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images
AI总结：
本文提出DRDM扩散模型，通过姿态编码、身体部位子空间解耦块和基于解析图的解耦无分类器引导采样，解决人物图像合成中的细节缺失、肢体扭曲和服装风格偏离问题，在Deepfashion上实现了有效的姿态迁移与外观控制。
摘要：
由于虚拟试穿、图像编辑和视频制作等实际需求，具有可控身体姿态和外观的人物图像合成是一项重要任务。然而，现有方法在细节缺失、肢体扭曲和服装风格偏离方面面临显著挑战。为解决这些问题，我们提出了一种解耦表示扩散模型（DRDM），用于从源肖像在特定期望姿态和外观下生成照片级逼真图像。首先，姿态编码器负责将姿态特征编码到高维空间，以指导人物图像的生成。其次，身体部位子空间解耦块（BSDB）从源人物的不同身体部位解耦特征，并将其馈送到噪声预测块的各个层，从而为网络提供丰富的解耦特征以生成逼真的目标图像。此外，在推理过程中，我们开发了一种基于解析图的解耦无分类器引导采样方法，该方法放大了纹理和姿态的条件信号。在Deepfashion数据集上的大量实验结果表明，我们的方法在实现姿态迁移和外观控制方面具有有效性。
英文摘要：
Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant challenges with details missing, limbs distortion and the garment style deviation. To address these issues, we propose a Disentangled Representations Diffusion Model (DRDM) to generate photo-realistic images from source portraits in specific desired poses and appearances. First, a pose encoder is responsible for encoding pose features into a high-dimensional space to guide the generation of person images. Second, a body-part subspace decoupling block (BSDB) disentangles features from the different body parts of a source figure and feeds them to the various layers of the noise prediction block, thereby supplying the network with rich disentangled features for generating a realistic target image. Moreover, during inference, we develop a parsing map-based disentangled classifier-free guided sampling method, which amplifies the conditional signals of texture and pose. Extensive experimental results on the Deepfashion dataset demonstrate the effectiveness of our approach in achieving pose transfer and appearance control.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
