NeRFICG is a flexible PyTorch framework for simple and efficient implementation and evaluation of neural radiance fields and rasterization-based view synthesis methods, including a GUI for interactive rendering.

This project consists of multiple subrepositories. Check out the main repository as a starting point for further instructions.

• efficient-gaussian-appearance - Faster-GS with JIT-compiled view-dependent appearance models and a WebGL viewer.
• stochastic-gaussian-splatting - A CUDA implementation of two sorting-free, stochastic rendering approaches for 3DGS.
• faster-gaussian-splatting - An efficient and research-friendly Gaussian Splatting framework.
• HTGS - A perspective-correct and view-consistent approach for 3D Gaussian splatting accelerated through hybrid transparency.
• DNPC - An efficient high-quality method for dynamic scene reconstruction from monocular video.
• INPC - A method for high-quality novel view synthesis that uses an implicit volumetric model in combination with fast neural point rendering.
• MoNeRF - An extremely fast neural radiance field approach for monocularized sequences like the D-NeRF dataset.

This framework is licensed under the MIT license.

If you use this project in your research code, please consider citing it:

@software{nerficg,
	author = {Kappel, Moritz and Hahlbohm, Florian and Scholz, Timon},
	license = {MIT},
	month = {2},
	title = {NeRFICG},
	url = {https://github.com/nerficg-project},
	version = {2.0},
	year = {2026}
}