| title | collection | permalink | excerpt | date | venue | paperurl | citation | code | video | supplementary_materials | project_page | year |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
Deep Real-time Volumetric Rendering Using Multi-feature Fusion |
publications |
/publication/mrpnn |
Jinkai Hu, Chengzhong Yu, Hongli Liu, [Ling-qi Yan](https://sites.cs.ucsb.edu/~lingqi/index.html), **Yiqian Wu**, [Xiaogang Jin](http://www.cad.zju.edu.cn/home/jin) |
2023-08-30 |
Proceedings of Siggraph'2023, Los Angeles, 6-10 August. |
coming soon |
coming soon |
coming soon |
coming soon |
coming soon |
2023 |
Abstract:
We present Multi-feature Radiance-Predicting Neural Networks (MRPNN), a practical framework with a lightweight feature fusion neural network for rendering high-order scattered radiance of participating media in real time. By reformulating the Radiative Transfer Equation (RTE) through theoretical examination, we propose transmittance fields, generated at a low cost, as auxiliary information to help the network better approximate the RTE, drastically reducing the size of the neural network. The light weight network efficiently estimates the difficult-to-solve in-scattering term and allows for configurable shading parameters while improving prediction accuracy. In addition, we propose a frequency-sensitive stencil design in order to handle non-cloud shapes, resulting in accurate shadow boundaries. Results show that our MRPNN is able to synthesize indistinguishable output compared to the ground truth. Most importantly, MRPNN achieves a speedup of two orders of magnitude compared to the state-of-the-art, and is able to render high-quality participating material in real time.
[Video](coming soon)
[Suppl](coming soon)
[Project Page](coming soon)
Recommended citation:
coming soon