Research Projects
Photorealistic 3D Head Reconstruction via 2D Gaussians
The project investigates state-of-the-art rendering pipelines with 3D face/head models, focused on developing sophisticated and photorealistic virtual avatars. The practical implementation of cutting-edge AI techniques in the creative industries and aims to deliver significant cost, energy and environmental savings in virtual production and 3D scanning.
Radiance fields have greatly advanced novel view synthesis and 3D reconstruction methods. More recently, 3D Gaussian Splatting (3DGS) has emerged as a major breakthrough, introducing compact and differentiable volumetric primitives that enable photorealistic rendering with efficient training. While 3DGS performs exceptionally well in view synthesis, extracting high-quality surface meshes remains difficult because of the loose geometric alignment of its ellipsoidal Gaussians. This limitation becomes especially evident in high-detail applications such as human head reconstruction, where capturing subtle anatomical features and accurate surface geometry is critical.
CfACTs is a Marie Sklodowska-Curie Action (MSCA) COFUND research centre, co-led by Prof Jian Chang and Prof Jian J Zhang, of the Bournemouth University’s National Centre for Computer Animation (BU NCCA); CfACTs runs from October 2020 to December 2025.
