# Fast End-to-End Trainable Guided Filter

arXiv: https://arxiv.org/abs/1803.05619 · HTML: https://mlsanity.com/paper/1803.05619/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2018.

## Built on by (most cited first, 30 of 50)

- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [FeatUp: A Model-Agnostic Framework for Features at Any Resolution](https://mlsanity.com/paper/2403.10516/) (2024)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [Discrete Cosine Transform Network for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2104.06977/) (2021)
- [Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables](https://mlsanity.com/paper/2108.08697/) (2021)
- [DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization](https://mlsanity.com/paper/2207.04788/) (2022)
- [Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation](https://mlsanity.com/paper/2109.02749/) (2021)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2303.08942/) (2023)
- [PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation](https://mlsanity.com/paper/2308.03979/) (2023)
- [Memory-augmented Deep Unfolding Network for Guided Image Super-resolution](https://mlsanity.com/paper/2203.04960/) (2022)
- [Depth Completion using Plane-Residual Representation](https://mlsanity.com/paper/2104.07350/) (2021)
- [Guided Depth Map Super-resolution: A Survey](https://mlsanity.com/paper/2302.09598/) (2023)
- [Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations](https://mlsanity.com/paper/2407.12511/) (2024)
- [High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusion](https://mlsanity.com/paper/2104.01530/) (2021)
- [Deep Attentional Guided Image Filtering](https://mlsanity.com/paper/2112.06401/) (2021)
- [Interactive Image Synthesis with Panoptic Layout Generation](https://mlsanity.com/paper/2203.02104/) (2022)
- [Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters](https://mlsanity.com/paper/2207.01331/) (2022)
- [Guided Patch-Grouping Wavelet Transformer with Spatial Congruence for Ultra-High Resolution Segmentation](https://mlsanity.com/paper/2307.00711/) (2023)
- [PalGAN: Image Colorization with Palette Generative Adversarial Networks](https://mlsanity.com/paper/2210.11204/) (2022)
- [Exploiting Raw Images for Real-Scene Super-Resolution](https://mlsanity.com/paper/2102.01579/) (2021)
- [Unsharp Mask Guided Filtering](https://mlsanity.com/paper/2106.01428/) (2021)
- [ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling](https://mlsanity.com/paper/2104.03560/) (2021)
- [AIM 2024 Challenge on Efficient Video Super-Resolution for AV1 Compressed Content](https://mlsanity.com/paper/2409.17256/) (2024)
- [A Lightweight Low-Light Image Enhancement Network via Channel Prior and Gamma Correction](https://mlsanity.com/paper/2402.18147/) (2024)
- [Trainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT](https://mlsanity.com/paper/2207.07368/) (2022)
- [From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement](https://mlsanity.com/paper/2307.16783/) (2023)
- [Unsupervised Image Denoising with Frequency Domain Knowledge](https://mlsanity.com/paper/2111.14362/) (2021)
- [Revisiting Deformable Convolution for Depth Completion](https://mlsanity.com/paper/2308.01905/) (2023)
- [Normalized Convolution Upsampling for Refined Optical Flow Estimation](https://mlsanity.com/paper/2102.06979/) (2021)

## Abstract (arXiv)

Dense pixel-wise image prediction has been advanced by harnessing the capabilities of Fully Convolutional Networks (FCNs). One central issue of FCNs is the limited capacity to handle joint upsampling. To address the problem, we present a novel building block for FCNs, namely guided filtering layer, which is designed for efficiently generating a high-resolution output given the corresponding low-resolution one and a high-resolution guidance map. Such a layer contains learnable parameters, which can be integrated with FCNs and jointly optimized through end-to-end training. To further take advantage of end-to-end training, we plug in a trainable transformation function for generating the task-specific guidance map. Based on the proposed layer, we present a general framework for pixel-wise image prediction, named deep guided filtering network (DGF). The proposed network is evaluated on five image processing tasks. Experiments on MIT-Adobe FiveK Dataset demonstrate that DGF runs 10-100 times faster and achieves the state-of-the-art performance. We also show that DGF helps to improve the performance of multiple computer vision tasks.