NeRFahedron: A Primitive for Animatable Neural Rendering with Interactive Speed

SIGGRAPH i3D'23 (best paper)

The Hong Kong Polytechnic University

We propose NeRFahedron, a candidate primitive for neural rendering. By animating the proxy formed by NeRFahedtrons via skinning, our novel method enables animatable content in real-time.


Neural rendering is an exciting topic injecting machine learning methodologies into the classical computer graphics rendering pipeline. Although recent works have achieved remarkable fidelity, discussion on how to enable it for interactive scenarios like video games seems to be lacking. Aside from an editable 3D model and UV-mapping, an interactive application will demand the neural rendering to handle animatable 3D content with interactive speed. This is currently a gap in neural rendering and our solution to this problem is a novel neural rendering pipeline involving a primitive named NeRFahedron. It localizes a NeRF field and as such effectively reduces the number of expensive network sampling operations to improve speed. Our pipeline involves tetrahedron rasterization, localized ray marching and near-surface particle sampling. The result is a method that can enable animatable content for neural rendering with interactive speed, which has been shown to be competitive in rendering animation. We will also showcase its ability to enable interactive applications via a real-time demo.



  author    = {Sin, Zackary P. T. and Ng, Peter H. F. and Leong, Hong Va},
  title     = {NeRFahedron: A Primitive for Animatable Neural Rendering with Interactive Speed},
  journal   = {Proceedings of the ACM on Computer Graphics and Interactive Techniques},
  volume    = {6},
  number    = {1},
  pages     = {1--20},
  articleno = {2},
  year      = {2023},