Token Manipulation - help me choose one / vote here

[johndpope]

Expression Transfer:

"GANimation: Anatomically-aware Facial Animation from a Single Image" (Pumarola et al., 2018)
"MeshTalk: 3D Face Animation from Speech using Cross-Modal Disentanglement" (Richard et al., 2021)

Age Manipulation:

"HRFAE: High Resolution Face Age Editing" (Yao et al., 2021)
"AgingBooth: A High-Resolution Age Progression and Regression Model" (Duong et al., 2022)

Hair Style/Color Modification:

"MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing" (Tan et al., 2020)
"HairCLIP: Design Your Hair by Text and Reference Image" (Wei et al., 2022)

Accessory Addition/Removal:

"ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes" (Xiao et al., 2018)
"STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing" (Liu et al., 2019)

Lighting Condition Adjustment:

"Portrait Lighting Transfer Using a Mass Transport Approach" (Shu et al., 2017)
"Single Image Portrait Relighting" (Zhou et al., 2019)

Emotion Intensity Control:

"GANimation: Anatomically-aware Facial Animation from a Single Image" (Pumarola et al., 2018)
"EmotionNet: A 3D Convolutional Neural Network for Facial Expression Recognition" (Tuan et al., 2021)

Gaze Direction Manipulation:

"DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation" (Ganin et al., 2016)
"GazeDirector: Fully Articulated Eye Gaze Redirection in Video" (Wood et al., 2018)

Speech-driven Animation:

"MakeItTalk: Speaker-Aware Talking-Head Animation" (Zhou et al., 2020)
"Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose" (Zhang et al., 2021)

View Synthesis:

"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering" (Ren et al., 2021)
"HeadNeRF: A Real-time NeRF-based Parametric Head Model" (Hong et al., 2022)

Attribute Transfer:

"StarGAN v2: Diverse Image Synthesis for Multiple Domains" (Choi et al., 2020)
"AttGAN: Facial Attribute Editing by Only Changing What You Want" (He et al., 2019)

Style Transfer:

"A Style-Based Generator Architecture for Generative Adversarial Networks" (Karras et al., 2019)
"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (Richardson et al., 2021)

Time Lapse Effects:

"Face Aging With Conditional Generative Adversarial Networks" (Antipov et al., 2017)
"LATS: Latent Transformation for Age-Controllable Face Synthesis" (Kim et al., 2021)

[johndpope]

thinking of doing either depth or segment anything - https://x.com/NielsRogge/status/1829896143742124486

this could be done too
https://github.com/FusionBrainLab/StyleFeatureEditor