The field of human parsing and virtual try-on is moving towards more accurate and detailed representations of human body parts and clothing. Recent developments have focused on improving the ability to parse diverse human clothing and body parts, as well as generating realistic garment previews on personal photos. Notable advancements include the use of 3D texture-aware representations and diffusion-based models to enhance the accuracy and realism of human parsing and virtual try-on. Noteworthy papers include: Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts, which proposes a unified network for part-level pixel parsing and instance-level grouping. MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human Erasing, which introduces a novel strategy for human erasing using semantically separated pathways for each instance and the background. Undress to Redress: A Training-Free Framework for Virtual Try-On, which proposes a novel framework that can be seamlessly integrated with any existing VTON method to address the challenge of long-sleeve-to-short-sleeve conversions. MuGa-VTON: Multi-Garment Virtual Try-On via Diffusion Transformers with Prompt Customization, which introduces a unified multi-garment diffusion framework that jointly models upper and lower garments together with person identity in a shared latent space.