PixelSR: Efficient Screen Content Super-Resolution via Pixel Classification

• URL: http://arxiv.org/abs/2608.00646v1
• Date: Sat, 01 Aug 2026 13:03:47 GMT
• Title: PixelSR: Efficient Screen Content Super-Resolution via Pixel Classification
• Abstract summary: Existing works in screen content super-resolution underutilize the special characteristics of screen content.<n>We propose PixelSR, a method to improve super-resolution performance but with faster inference speed.<n> Experiments show our PixelSR achieves state-of-the-art performance with shorter inference time in screen content super-resolution.
• Score: 58.92928505513181
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Screen content images are generally composed of texts and graphics. Compared to natural images, these man-made images contain a large quantity of sharp but repetitive structures. However, existing works in screen content super-resolution underutilize the special characteristics of screen content, leaving a large room to improve model performance and speed up. In this paper, we propose PixelSR, a simple yet effective method to improve super-resolution performance but with faster inference speed. To improve model performance, we classify pixels via pixel binning to compute content attention in the training phase. Specifically, after binning pixels into content-dependent groups, content attention is aggregated from pixel features within each group to introduce a content-dependent and non-local receptive field for every pixel. In the testing phase, we utilize the properties of self-repetitiveness and redundancy in screen content to speed up inference without the loss of model performance. We divide targeted high-resolution pixels into three types, which are unique pixels, repeated pixels, and background pixels for each test image. We conduct conventional network processing on unique pixels and cache their predictions in the on-the-fly lookup table. For repeated pixels which have appeared in unique pixels, we directly retrieve prediction results from the lookup table without network processing. For background pixels, we use the nearest neighbor algorithm to generate high-resolution pixels. The on-the-fly lookup table is cleaned and repeats the procedure above for the next test image. Experiments show our PixelSR achieves state-of-the-art performance with shorter inference time in screen content super-resolution.

Related papers

• Square Superpixel Generation and Representation Learning via Granular Ball Computing [97.99956628286243]
  Superpixels provide a compact region-based representation that preserves object boundaries and local structures.<n>Most existing superpixel algorithms produce irregularly shaped regions, which are not well aligned with regular operators such as convolutions.<n>Motivated by the adaptive representation and coverage property of granular-ball computing, we develop a square superpixel generation approach.
  arXiv  Detail & Related papers  (2026-03-31T09:06:58Z)
• From Pixels to Components: Eigenvector Masking for Visual Representation Learning [55.567395509598065]
  Predicting masked from visible parts of an image is a powerful self-supervised approach for visual representation learning.<n>We propose an alternative masking strategy that operates on a suitable transformation of the data rather than on the raw pixels.
  arXiv  Detail & Related papers  (2025-02-10T10:06:46Z)
• Elevating Flow-Guided Video Inpainting with Reference Generation [50.03502211226332]
  Video inpainting (VI) is a challenging task that requires effective propagation of observable content across frames while simultaneously generating new content not present in the original video.<n>We propose a robust and practical VI framework that leverages a large generative model for reference generation in combination with an advanced pixel propagation algorithm.<n>Our method not only significantly enhances frame-level quality for object removal but also synthesizes new content in the missing areas based on user-provided text prompts.
  arXiv  Detail & Related papers  (2024-12-12T06:13:00Z)
• Image Reconstruction using Superpixel Clustering and Tensor Completion [21.088385725444944]
  Our method divides the image into several regions that capture important textures or semantics and selects a representative pixel from each region to store. We propose two smooth tensor completion algorithms that can effectively reconstruct different types of images from the selected pixels.
  arXiv  Detail & Related papers  (2023-05-16T16:00:48Z)
• Saliency Enhancement using Superpixel Similarity [77.34726150561087]
  Saliency Object Detection (SOD) has several applications in image analysis. Deep-learning-based SOD methods are among the most effective, but they may miss foreground parts with similar colors. We introduce a post-processing method, named textitSaliency Enhancement over Superpixel Similarity (SESS) We demonstrate that SESS can consistently and considerably improve the results of three deep-learning-based SOD methods on five image datasets.
  arXiv  Detail & Related papers  (2021-12-01T17:22:54Z)
• Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks [11.696069523681178]
  We propose a way to implicitly integrate a superpixel scheme into CNNs. Our proposed method hierarchically groups pixels at downsampling layers and generates superpixels. We evaluate our method on several tasks such as semantic segmentation, superpixel segmentation, and monocular depth estimation.
  arXiv  Detail & Related papers  (2021-03-05T02:20:26Z)
• Spatially-Adaptive Pixelwise Networks for Fast Image Translation [57.359250882770525]
  We introduce a new generator architecture, aimed at fast and efficient high-resolution image-to-image translation. We use pixel-wise networks; that is, each pixel is processed independently of others. Our model is up to 18x faster than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-12-05T10:02:03Z)
• Superpixel Segmentation with Fully Convolutional Networks [32.878045921919714]
  We present a novel method that employs a simple fully convolutional network to predict superpixels on a regular image grid. Experimental results on benchmark datasets show that our method achieves state-of-the-art superpixel segmentation performance. We modify a popular network architecture for stereo matching to simultaneously predict superpixels and disparities.
  arXiv  Detail & Related papers  (2020-03-29T02:42:07Z)
• Robust superpixels using color and contour features along linear path [5.746869663956391]
  We propose a framework that provides accurate and regular Superpixels with Contour Adherence using Linear Path (SCALP)<n>A contour prior is also used to prevent the crossing of image boundaries when associating a pixel to a superpixel.<n>SCALP is extensively evaluated on standard segmentation dataset, and the obtained results outperform the ones of the state-of-the-art methods.
  arXiv  Detail & Related papers  (2019-03-17T23:00:13Z)
• SCALP: Superpixels with Contour Adherence using Linear Path [5.746869663956391]
  We propose a fast method to compute Superpixels with Contour Adherence using Linear Path (SCALP) in an iterative clustering framework.<n>The proposed framework produces compact and superpixels that adhere to contour contours.
  arXiv  Detail & Related papers  (2019-03-17T19:23:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.