Structure Aware Image Downscaling
G B Kevin Arjun, Suvrojit Mitra, and Sanjay Ghosh

TL;DR
This paper introduces a structure-aware image downscaling method that preserves edges and textures effectively, outperforming existing techniques in visual quality and metrics across multiple datasets.
Contribution
A novel edge-guided, structure-informed downscaling algorithm that maintains fine details and reduces artifacts through edge detection, guided interpolation, and texture enhancement.
Findings
Achieves up to 39.07 dB PSNR on DIV2K for 4x downscaling.
Outperforms recent methods in visual quality and metrics.
Preserves edges and textures without blurring or loss.
Abstract
Image downscaling is one of the key operations in recent display technology and visualization tools. By this process, the dimension of an image is reduced, aiming to preserve structural integrity and visual fidelity. In this paper, we propose a new image downscaling method which is built on the core ideas of image filtering and edge detection. In particular, we present a structure-informed downscaling algorithm that maintains fine details through edge-aware processing. The proposed method comprises three steps: (i) edge map computation, (ii) edge-guided interpolation, and (iii) texture enhancement. To faithfully retain the strong structures in an image, we first compute the edge maps by applying an efficient edge detection operator. This is followed by an edge-guided interpolation to preserve fine details after resizing. Finally, we fuse local texture enriched component of the original…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
