RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images
This addresses a specific challenge in AI-generated human images, offering an incremental improvement for applications in visual content creation.
The paper tackles the problem of generating realistic human parts like hands and faces in images from diffusion models, proposing a two-stage post-processing method that improves realism with notable gains in qualitative and quantitative metrics.
In recent years, diffusion models have revolutionized visual generation, outperforming traditional frameworks like Generative Adversarial Networks (GANs). However, generating images of humans with realistic semantic parts, such as hands and faces, remains a significant challenge due to their intricate structural complexity. To address this issue, we propose a novel post-processing solution named RealisHuman. The RealisHuman framework operates in two stages. First, it generates realistic human parts, such as hands or faces, using the original malformed parts as references, ensuring consistent details with the original image. Second, it seamlessly integrates the rectified human parts back into their corresponding positions by repainting the surrounding areas to ensure smooth and realistic blending. The RealisHuman framework significantly enhances the realism of human generation, as demonstrated by notable improvements in both qualitative and quantitative metrics. Code is available at https://github.com/Wangbenzhi/RealisHuman.