Computer vision, Computer Graphics. Specialized in technologies for digital humans, from 3D avatar estimation to motion capture
crack_segmentation. This repository contains code and dataset for the task crack segmentation using two architectures UNet_VGG16, UNet_Resnet and DenseNet-Tiramusu
448photogrammetry. This repository holds my experiments about fundamental algorithms in photogrammetry
30digital_sculpting. An open source digital suclpting application that provides artists with many types of digital brush, dynamic topology and meshing tools
28temporal_inverse_kinematics. a learning-based human inverse kinemtics. A graph convolution network is constructed to predict SMPLx joint angles from a tepmoral sequence of relative 3d poses in COCO format.
27multiview_motion_capture. A prototype implementation in python of the paper "Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS ", with inverse kinematics and bone length optimziation
15human_avatar_reconstruction. reconstruct 3D human avatar from a pair of front and side images
15image_inpainting. Jupyter Notebook
5clothes_try_on. Python
4haskell. this repository holds my haskell code on my journey of learning functional programming
1crack_detection. this repository contains my code for crack detection project
1virtual_reality. this repository holds lab assignments in the virtual reality class
1