When A Conventional Filter Meets Deep Learning: Basis Composition Learning on Image Filters

• URL: http://arxiv.org/abs/2203.00258v1
• Date: Tue, 1 Mar 2022 06:34:54 GMT
• Title: When A Conventional Filter Meets Deep Learning: Basis Composition Learning on Image Filters
• Authors: Fu Lee Wang, Yidan Feng, Haoran Xie, Gary Cheng, Mingqiang Wei
• Abstract summary: We propose basis composition learning on single image filters to automatically determine their optimal formulas. Our method is simple yet effective in practice; it renders filters to be user-friendly and benefits fundamental low-level vision problems.
• Score: 20.506636435344333
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image filters are fast, lightweight and effective, which make these conventional wisdoms preferable as basic tools in vision tasks. In practical scenarios, users have to tweak parameters multiple times to obtain satisfied results. This inconvenience heavily discounts the efficiency and user experience. We propose basis composition learning on single image filters to automatically determine their optimal formulas. The feasibility is based on a two-step strategy: first, we build a set of filtered basis (FB) consisting of approximations under selected parameter configurations; second, a dual-branch composition module is proposed to learn how the candidates in FB are combined to better approximate the target image. Our method is simple yet effective in practice; it renders filters to be user-friendly and benefits fundamental low-level vision problems including denoising, deraining and texture removal. Extensive experiments demonstrate that our method achieves an appropriate balance among the performance, time complexity and memory efficiency.

Related papers

• Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning [49.275450836604726]
  We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. We employ a two-branch framework empowered by knowledge distillation, enabling the model to take both the filtered and original images as input.
  arXiv  Detail & Related papers  (2024-09-16T15:10:07Z)
• Prompt-Guided Image-Adaptive Neural Implicit Lookup Tables for Interpretable Image Enhancement [4.233370898095789]
  interpretable image enhancement is a technique that enhances image quality by adjusting filter parameters with easily understandable names such as "Exposure" and "Contrast" We introduce an image-adaptive neural implicit lookup table, which uses a multilayer perceptron to implicitly define the transformation from input feature space to output color space. We evaluate visual impressions of enhancement results, such as exposure and contrast, using a vision and language model along with guiding prompts.
  arXiv  Detail & Related papers  (2024-08-20T17:59:01Z)
• Adaptive Image Registration: A Hybrid Approach Integrating Deep Learning and Optimization Functions for Enhanced Precision [13.242184146186974]
  We propose a single framework for image registration based on deep neural networks and optimization. We show improvements of up to 1.6% in test data, while maintaining the same inference time, and a substantial 1.0% points performance gain in deformation field smoothness.
  arXiv  Detail & Related papers  (2023-11-27T02:48:06Z)
• Improving Human-Object Interaction Detection via Virtual Image Learning [68.56682347374422]
  Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects. In this paper, we propose to alleviate the impact of such an unbalanced distribution via Virtual Image Leaning (VIL) A novel label-to-image approach, Multiple Steps Image Creation (MUSIC), is proposed to create a high-quality dataset that has a consistent distribution with real images.
  arXiv  Detail & Related papers  (2023-08-04T10:28:48Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter [42.400427631514596]
  We propose a crowd-powered local enhancement method for content-aware local enhancement. To make it easier to locally optimize the parameters, we propose an active learning based local filter. Our experiments show that the proposed filter outperforms existing filters.
  arXiv  Detail & Related papers  (2023-06-15T17:55:11Z)
• Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling [19.412014102866507]
  We build on learning-based approaches to improve photometric scores by learning patch coplanarity and encourage geometric consistency. We propose an adaptive pixel sampling strategy for candidate propagation that reduces memory to enable training on larger resolution with more views and a larger encoder.
  arXiv  Detail & Related papers  (2022-10-14T07:29:03Z)
• DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization [14.062386668676533]
  We propose a novel Deep Comprehensible Color Filter (DCCF) learning framework for high-resolution image harmonization. DCCF learns four human comprehensible neural filters (i.e. hue, saturation, value and attentive rendering filters) in an end-to-end manner. It outperforms state-of-the-art post-processing method on iHarmony4 dataset on images' full-resolutions by achieving 7.63% and 1.69% relative improvements on MSE and PSNR respectively.
  arXiv  Detail & Related papers  (2022-07-11T11:42:10Z)
• Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment [50.13230641857892]
  We propose a new deep learning framework for the low-light image enhancement (LIE) problem. The proposed framework contains a decomposition network inspired by algorithm unrolling, and adjustment networks considering both global brightness and local brightness sensitivity. Experiments on a series of typical LIE datasets demonstrated the effectiveness of the proposed method, both quantitatively and visually, as compared with existing methods.
  arXiv  Detail & Related papers  (2022-02-12T03:59:38Z)
• Unsharp Mask Guided Filtering [53.14430987860308]
  The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering. We propose a new and simplified formulation of the guided filter inspired by unsharp masking. Our formulation enjoys a filtering prior to a low-pass filter and enables explicit structure transfer by estimating a single coefficient.
  arXiv  Detail & Related papers  (2021-06-02T19:15:34Z)
• Image Matching across Wide Baselines: From Paper to Practice [80.9424750998559]
  We introduce a comprehensive benchmark for local features and robust estimation algorithms. Our pipeline's modular structure allows easy integration, configuration, and combination of different methods. We show that with proper settings, classical solutions may still outperform the perceived state of the art.
  arXiv  Detail & Related papers  (2020-03-03T15:20:57Z)

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.