The field of digital human and image editing technologies is rapidly evolving, with a focus on improving the quality and realism of digital human avatars and edited images. Recent developments have centered around the creation of large-scale datasets and novel models that can assess and enhance the quality of digital human meshes and edited images. These advancements have significant implications for various applications, including game production, animation generation, remote immersive communication, and e-commerce. Notably, the development of multimodal models and diffusion transformer frameworks has enabled more accurate and robust image editing and virtual try-on capabilities. Noteworthy papers include: DHQA-4D, which proposes a large-scale dynamic digital human quality assessment dataset and a novel approach for assessing the quality of textured and non-textured 4D meshes. TBStar-Edit, which introduces a new image editing model tailored for the e-commerce domain, achieving precise and high-fidelity image editing while maintaining the integrity of product appearance and layout. AvatarVTON, which proposes a 4D virtual try-on framework that generates realistic try-on results from a single in-shop garment image, enabling free pose control and novel-view rendering. DiT-VTON, which presents a novel virtual try-on framework that leverages a diffusion transformer to achieve robust and detailed image editing capabilities.