A curated list of resources for makeup and hairstyle transfer research using computer vision and generative AI.
Awesome Makeup Transfer is a curated GitHub repository listing academic papers, datasets, and resources related to makeup transfer and hairstyle transfer in computer vision. It compiles research on using generative models like GANs and diffusion models to realistically apply or remove makeup and hairstyles from facial images. The project organizes the latest advancements from top conferences and provides links to code and datasets.
Computer vision researchers, AI engineers, and students working on facial image synthesis, generative models, or virtual try-on applications. It's particularly useful for those exploring makeup/hairstyle transfer, face beautification, or adversarial attacks on face recognition.
It saves significant time in literature review by aggregating scattered resources into a single, well-structured list. The inclusion of datasets and code links lowers the barrier to entry for experimenting with state-of-the-art methods, fostering reproducibility and collaboration in the research community.
A curated list of Awesome Makeup Transfer resources
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Aggregates academic papers from top-tier conferences like CVPR and NeurIPS with direct links to papers and code, saving hours of literature search.
Lists key datasets such as Makeup-Wild and LADN Makeup with download links and usage notes, facilitating experimental setup for model training.
Includes dedicated sections on hairstyle transfer and practical applications like face verification attacks, providing a holistic view beyond basic makeup transfer.
Actively encourages pull requests and issues, as stated in the README, ensuring the list stays current with the latest advancements from the research community.
Merely lists resources without assessing their performance, reproducibility, or practical utility, leaving critical evaluation entirely to the user.
Relies heavily on external links to papers and code that may become outdated or broken over time, reducing reliability without constant active maintenance.
Provides code repository links but no tutorials, setup help, or integration examples, making it challenging for beginners or practitioners to apply the methods directly.