At 3DGS.zip, we're collecting resources around our work on 3D Gaussian Splatting in the Computer Vision & Graphics (CVG) research group at Fraunhofer Heinrich Hertz Institute (HHI). Our focus lies on modelling compact representations and representing humans.
We introduce CGS-GAN, a Gaussian splatting based 3D GAN framework that produces high resolution 3D consistent renderings in real-time. While prior Gaussian splatting GANs either synthesize inconsistent 3D heads or heads that only look realistic from one specific view, CGS-GAN produces 3D consistent and realistic renderings from arbitrary viewpoints.
3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods: We're collecting results and info on methods that reduce the storage size of 3D Gaussian splatting scenes. Contributions welcome!
This interactive viewer allows to display 3D Gaussian Splatting objects stored as .ply files or as compressed objects from Compact 3D Scene Representation via Self-Organizing Gaussian Grids. The viewer is fully written in python, which makes development and debugging very simple.
In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering.
In this work, we present a novel approach that combines the high rendering quality of NeRF-based 3D-aware Generative Adversarial Networks with the flexibility and computational advantages of 3DGS. By training a decoder that maps implicit NeRF representations to explicit 3D Gaussian Splatting attributes, we can integrate the representational diversity and quality of 3D GANs into the ecosystem of 3D Gaussian Splatting for the first time.