-
Yonsei University
- Seoul, Korea
Stars
Official data release for FaceMap, to present in Siggraph Asia 2024
Code for CLIB-FIQA: Face Image Quality Assessment with Confidence Calibration
Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data (CVPR 24); Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer (ECCV 2024)
This is official inference code of PD-FGC
Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians
Official implementation of the paper "HRAvatar: High-Quality and Relightable Gaussian Head Avatar" [CVPR 2025]
real time face swap and one-click video deepfake with only a single image
Official PyTorch implementation of "Authentic Hand Avatar from a Phone Scan via Universal Hand Model", CVPR 2024.
Glasses detection, classification and segmentation
Official Repository of [CVPR'25 Paper Diffportrait360: Consistent portrait diffusion for 360 view synthesis
Official code for the paper "V-LASIK: Consistent Glasses-Removal from Videos Using Synthetic Data"
Official pytorch implementation of paper "Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data" (CVPR 2022).
Add bisenetv2. My implementation of BiSeNet
Fine-Tuning Hybrid Demucs in Cross-Talk scenario with Self-Knowledge Distillation with Progressive Refinement of Targets
Using modified BiSeNet for face parsing in PyTorch
ICT's Vision and Graphics Lab's morphable face model and toolkit
Goliath Dataset and Official PyTorch Implementation of RelightableHands, Relightable Gaussian Codec Avatars, and Driving-Signal Aware Full-Body Avatars.
Zotero plugin to automatically move attachments and link them
[CVPR 2025] The official repo for "FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video"
We propose a framework that accurately derives the 3D tongue shape from single images. A high detailed 3D point cloud of the tongue surface and a full head topology along with the tongue expression…
TensorFlow code for our ECCV'24 Workshop paper "LightAvatar: Efficient Head Avatar as Dynamic NeLF"
[WACV2025] Official repository for "Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities"
[ECCV 2024] HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting.