Yiqian Wu's Projects
(Preprint) 3DPortraitGAN: Learning One-Quarter Headshot 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses
The project page of paper "3DPortraitGAN: Learning Canonical Full-Head 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses"
An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)
double-chin-dataset is a high-quality image dataset of double chin removal, based on StyleGAN.
Linear-layer-only decoders and encoders for stable-diffusion (including a linear + bias version and a 3 layer MLP). These all produce RGB images that are the same size as the latents.
The project page of siggraph 2021 paper "Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent Space Classifications"
An unofficial inversion code of eg3d.
(SIGGRAPH 2021) Coarse-to-Fine: Facial Structure Editing of Portrait Images via Latent Space Classifications.
(CVPR 2022) HairMapper: Removing Hair from Portraits Using GANs.
The project page of CVPR2022 paper "HairMapper: Removing Hair from Portraits Using GANs"
Single rgbd-id version of paper "High-Fidelity 3D Digital Human Creation from RGB-D Selfies".
(ICCV2023) A large-pose Flickr face dataset comprised of 19,590 high-quality real large-pose portrait images.
StyleGAN2-ADA - Official PyTorch implementation
The project page of ICCV 2021 paper "LPFF: A Portrait Dataset for Face Generators Across Large Poses"
A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]
A dataset that contains 6,000 non-hair FFHQ portraits.
My GitHub profile.
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
(SIGGRAPH 2024) Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior
The project page of portrait3d