Papers › Side Window Filtering

Side Window Filtering

17 May 2019CVPR 2019 6arXiv:1905.07177archive 2025-07-28

Hui Yin, Yuanhao Gong, Guoping Qiu

Local windows are routinely used in computer vision and almost without exception the center of the window is aligned with the pixels being processed. We show that this conventional wisdom is not universally applicable. When a pixel is on an edge, placing the center of the window on the pixel is one of the fundamental reasons that cause many filtering algorithms to blur the edges. Based on this insight, we propose a new Side Window Filtering (SWF) technique which aligns the window's side or corner with the pixel being processed. The SWF technique is surprisingly simple yet theoretically rooted and very effective in practice. We show that many traditional linear and nonlinear filters can be easily implemented under the SWF framework. Extensive analysis and experiments show that implementing the SWF principle can significantly improve their edge preserving capabilities and achieve state of the art performances in applications such as image smoothing, denoising, enhancement, structure-preserving texture-removing, mutual-structure extraction, and HDR tone mapping. In addition to image filtering, we further show that the SWF principle can be extended to other applications involving the use of a local window. Using colorization by optimization as an example, we demonstrate that implementing the SWF principle can effectively prevent artifacts such as color leakage associated with the conventional implementation. Given the ubiquity of window based operations in computer vision, the new SWF technique is likely to benefit many more applications.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

wang-kangkang/SideWindowFilter-pytorch mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ColorizationDenoisingPoint-interactive Image ColorizationTone Mappingimage smoothing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point-interactive Image Colorization CUB-200-2011 SWF PSNR@1 23.547 #6 of 7 Archive leaderboard report
Point-interactive Image Colorization CUB-200-2011 SWF PSNR@10 25.097 #6 of 7 Archive leaderboard report
Point-interactive Image Colorization CUB-200-2011 SWF PSNR@100 27.623 #6 of 7 Archive leaderboard report
Point-interactive Image Colorization ImageNet ctest10k SWF PSNR@1 23.119 #4 of 4 Archive leaderboard report
Point-interactive Image Colorization ImageNet ctest10k SWF PSNR@10 24.232 #4 of 4 Archive leaderboard report
Point-interactive Image Colorization ImageNet ctest10k SWF PSNR@100 27.099 #4 of 4 Archive leaderboard report
Point-interactive Image Colorization Oxford 102 Flowers SWF PSNR@1 18.452 #5 of 7 Archive leaderboard report
Point-interactive Image Colorization Oxford 102 Flowers SWF PSNR@10 19.445 #5 of 7 Archive leaderboard report
Point-interactive Image Colorization Oxford 102 Flowers SWF PSNR@100 22.362 #5 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Colorization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections