Related papers: T2Net: Synthetic-to-Realistic Translation for Solv…
Neural networks need big annotated datasets for training. However, manual annotation can be too expensive or even unfeasible for certain tasks, like multi-person 2D pose estimation with severe occlusions. A remedy for this is synthetic data…
We present the Hue-Net - a novel Deep Learning framework for Intensity-based Image-to-Image Translation. The key idea is a new technique termed network augmentation which allows a differentiable construction of intensity histograms from…
Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…
How to design proper training pairs is critical for super-resolving real-world low-quality (LQ) images, which suffers from the difficulties in either acquiring paired ground-truth high-quality (HQ) images or synthesizing photo-realistic…
Deep convolutional neural networks perform better on images containing spatially invariant degradations, also known as synthetic degradations; however, their performance is limited on real-degraded photographs and requires multiple-stage…
Successfully training end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images. Obtaining such datasets remains…
This paper considers image change detection with only a small number of samples, which is a significant problem in terms of a few annotations available. A major impediment of image change detection task is the lack of large annotated…
We present a technique for synthesizing a motion blurred image from a pair of unblurred images captured in succession. To build this system we motivate and design a differentiable "line prediction" layer to be used as part of a neural…
Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree geometric sensing, traditional stereo matching algorithms for…
Machine learning techniques work best when the data used for training resembles the data used for evaluation. This holds true for learned single-image denoising algorithms, which are applied to real raw camera sensor readings but, due to…
Recently, deep learning-based single image reflection separation methods have been exploited widely. To benefit the learning approach, a large number of training image pairs (i.e., with and without reflections) were synthesized in various…
Traditional denoising methods for noise removal have largely relied on handcrafted priors, often perform well in controlled environments but struggle to address the complexity and variability of real noise. In contrast, deep learning-based…
The generation of smooth and continuous images between domains has recently drawn much attention in image-to-image (I2I) translation. Linear relationship acts as the basic assumption in most existing approaches, while applied to different…
End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications since (1) they are memory-hungry and unable to process even…
Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…
Images captured in weak illumination conditions could seriously degrade the image quality. Solving a series of degradation of low-light images can effectively improve the visual quality of images and the performance of high-level visual…
The applicability of computer vision to real paintings and artworks has been rarely investigated, even though a vast heritage would greatly benefit from techniques which can understand and process data from the artistic domain. This is…
Image translation across different domains has attracted much attention in both machine learning and computer vision communities. Taking the translation from source domain $\mathcal{D}_s$ to target domain $\mathcal{D}_t$ as an example,…
Structural guidance in an image-to-image translation allows intricate control over the shapes of synthesized images. Generating high-quality realistic images from user-specified rough hand-drawn sketches is one such task that aims to impose…
We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency while supporting large appearance changes during unpaired image-to-image (I2I) translation. Previous…