GitHub

Self-Supervised Head Geometry Predictor Learned via 2D Gaussians

SHeaP learns to predict head geometry (FLAME parameters) from a single image, by predicting and rendering 2D Gaussians. This repository contains code and models for the FLAME parameter inference only.
GitHub

Geometry Dash 2.2 Leak Editor

This repository contains reverse engineered structures and reimplemented editor code needed for my restoration of the editor in the 2019 Geometry Dash 2.2 leaks. In the commit history you can find ...
IEEE

Autoencoder Architectures for Low-Rate Sparse Point Cloud Geometry Coding

Abstract: Efficient compression of sparse point cloud geometry remains a critical challenge in 3D content processing, particularly for low-rate scenarios where conventional codecs struggle to maintain ...
IEEE

Layer-based Rate-Distortion Optimized Attribute Coding for Solid Geometry-based Point Cloud Compression

Abstract: In recent years, three-dimensional (3D) point clouds, which are applicable in various fields such as the metaverse and immersive communication, are attracting increasing attention. Under ...