Fast Approximation to Large-Kernel Edge-Preserving Filters by Recursive Reconstruction from Image Pyramids
| dc.contributor.author | Xu, Tianchen | en_US |
| dc.contributor.author | Yang, Jiale | en_US |
| dc.contributor.author | Qin, Yiming | en_US |
| dc.contributor.author | Sheng, Bin | en_US |
| dc.contributor.author | Wu, Enhua | en_US |
| dc.contributor.editor | Chen, Renjie | en_US |
| dc.contributor.editor | Ritschel, Tobias | en_US |
| dc.contributor.editor | Whiting, Emily | en_US |
| dc.date.accessioned | 2024-10-13T18:04:43Z | |
| dc.date.available | 2024-10-13T18:04:43Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | Edge-preserving filters, as known as bilateral filters, are fundamental to graphics rendering techniques, providing greater generality and capability of edge preservation than pure convolution filters. However, sampling with a large kernel per pixel for these filters can be computationally intensive in real-time rendering. Existing acceleration methods for approximating edgepreserving filters still struggle to balance blur controllability, edge clarity, and runtime efficiency. In this paper, we propose a novel scheme for approximating edge-preserving filters with large anisotropic kernels by recursively reconstructing them from multi-image pyramid (MIP) layers that are weightedly filtered in a dual 3×3 kernel space. Our approach introduces a concise unified processing pipeline independent of kernel size, which includes upsampling and downsampling on MIP layers and enables the integration of custom edge-stopping functions. We also derive the implicit relations of the sampling weights and formulate a weight template model for inference. Furthermore, we convert the pipeline into a lightweight neural network for numerical solutions through data training. Consequently, our image post-processors achieve high-quality and high-performance edgepreserving filters in real-time, using the same control parameters as the original bilateral filters. These filters are applicable for depth-of-fields, global illumination denoising, and screen-space particle rendering. The simplicity of the reconstruction process in our pipeline makes it user-friendly and cost-effective, saving both runtime and implementation costs. | en_US |
| dc.description.sectionheaders | Image Processing and Filtering I | |
| dc.description.seriesinformation | Pacific Graphics Conference Papers and Posters | |
| dc.identifier.doi | 10.2312/pg.20241302 | |
| dc.identifier.isbn | 978-3-03868-250-9 | |
| dc.identifier.pages | 12 pages | |
| dc.identifier.uri | https://doi.org/10.2312/pg.20241302 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.2312/pg20241302 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies → Rendering; Visibility | |
| dc.subject | Computing methodologies → Rendering | |
| dc.subject | Visibility | |
| dc.title | Fast Approximation to Large-Kernel Edge-Preserving Filters by Recursive Reconstruction from Image Pyramids | en_US |