Neural Denoising for Deep-Z Monte Carlo Renderings
| dc.contributor.author | Zhang, Xianyao | en_US |
| dc.contributor.author | Röthlin, Gerhard | en_US |
| dc.contributor.author | Zhu, Shilin | en_US |
| dc.contributor.author | Aydin, Tunç Ozan | en_US |
| dc.contributor.author | Salehi, Farnood | en_US |
| dc.contributor.author | Gross, Markus | en_US |
| dc.contributor.author | Papas, Marios | en_US |
| dc.contributor.editor | Bermano, Amit H. | en_US |
| dc.contributor.editor | Kalogerakis, Evangelos | en_US |
| dc.date.accessioned | 2024-04-30T09:09:17Z | |
| dc.date.available | 2024-04-30T09:09:17Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | We present a kernel-predicting neural denoising method for path-traced deep-Z images that facilitates their usage in animation and visual effects production. Deep-Z images provide enhanced flexibility during compositing as they contain color, opacity, and other rendered data at multiple depth-resolved bins within each pixel. However, they are subject to noise, and rendering until convergence is prohibitively expensive. The current state of the art in deep-Z denoising yields objectionable artifacts, and current neural denoising methods are incapable of handling the variable number of depth bins in deep-Z images. Our method extends kernel-predicting convolutional neural networks to address the challenges stemming from denoising deep-Z images. We propose a hybrid reconstruction architecture that combines the depth-resolved reconstruction at each bin with the flattened reconstruction at the pixel level. Moreover, we propose depth-aware neighbor indexing of the depth-resolved inputs to the convolution and denoising kernel application operators, which reduces artifacts caused by depth misalignment present in deep-Z images. We evaluate our method on a production-quality deep-Z dataset, demonstrating significant improvements in denoising quality and performance compared to the current state-of-the-art deep-Z denoiser. By addressing the significant challenge of the cost associated with rendering path-traced deep-Z images, we believe that our approach will pave the way for broader adoption of deep-Z workflows in future productions. | en_US |
| dc.description.number | 2 | |
| dc.description.sectionheaders | Sampling and Image Enhancement | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 43 | |
| dc.identifier.doi | 10.1111/cgf.15050 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 18 pages | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.15050 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.1111/cgf15050 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | CCS Concepts: Computing methodologies->Ray tracing; Image processing | |
| dc.subject | Computing methodologies | |
| dc.subject | >Ray tracing | |
| dc.subject | Image processing | |
| dc.title | Neural Denoising for Deep-Z Monte Carlo Renderings | en_US |
Files
Original bundle
1 - 5 of 7