Neural Temporal Denoising for Indirect Illumination

Yan Zeng, Lu Wang, Yanning Xu, Xiangxu Meng

Abstract

Various temporal denoising methods have been proposed to clean up the noise for real-time ray tracing (RTRT). These methods rely on the temporal correspondences of pixels between the current and previous frames, i.e. per-pixel screen-space motion vectors. However, the state-of-the-art temporal reuse methods with traditional motion vectors cause artifacts in motion occlusions. We accordingly propose a novel neural temporal denoising method for indirect illumination of Monte Carlo (MC) ray tracing at 1 sample per pixel. Based on end-to-end multi-scale kernel-based reconstruction, we apply temporally reliable dual motion vectors to facilitate better reconstruction of the occlusions, and also introduce additional motion occlusion loss to reduce ghosting artifacts. Experiments show that our method significantly reduces the over-blurring and ghosting artifacts while generating high-quality images at real-time rates.
BibTeX
@article{zeng2023neural,
  author = {Yan Zeng and Lu Wang and Yanning Xu and Xiangxu Meng},
  title = {{Neural Temporal Denoising for Indirect Illumination}},
  journal = {IEEE Trans. Vis. Comput. Graph.},
  year = {2023},
  doi = {10.1109/tvcg.2022.3217305},
}

Loading related content...

Figure