Low-Light Image and Video Enhancement Using Deep Learning : A Survey

Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by …

Path-Restore : Learning Network Path Selection for Image Restoration

Very deep Convolutional Neural Networks (CNNs) have greatly improved the performance on various image restoration tasks. However, this comes at a price of increasing computational burden, hence lim…

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipula…

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps t…

CARAFE++ : Unified Content-Aware ReAssembly of FEatures

Feature reassembly, i.e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e.g., residual networks and feature pyramids. Its design …

Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation

This paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method …

A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization

Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the pro…

Deep Imbalanced Learning for Face Recognition and Attribute Prediction

Faceness-Net: Face Detection through Deep Facial Part Responses

Deep Learning Markov Random Field for Semantic Segmentation

DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural …