Related papers: Closing the Loop: Joint Rain Generation and Remova…

Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly…

Defocus deblurring is a challenging task due to the spatially varying nature of defocus blur. While deep learning approach shows great promise in solving image restoration problems, defocus deblurring demands accurate training data that…

Image deraining is an essential vision technique that removes rain streaks and water droplets, enhancing clarity for critical vision tasks like autonomous driving. However, current single-scale models struggle with fine-grained recovery and…

Restoring clear frames from rainy videos presents a significant challenge due to the rapid motion of rain streaks. Traditional frame-based visual sensors, which capture scene content synchronously, struggle to capture the fast-moving…

Existing adherent raindrop removal methods focus on the detection of the raindrop locations, and then use inpainting techniques or generative networks to recover the background behind raindrops. Yet, as adherent raindrops are diverse in…

Single image deraining regards an input image as a fusion of a background image, a transmission map, rain streaks, and atmosphere light. While advanced models are proposed for image restoration (i.e., background image generation), they…

Severe weather conditions such as rain and snow adversely affect the visual quality of images captured under such conditions thus rendering them useless for further usage and sharing. In addition, such degraded images drastically affect…

Existing vision systems for autonomous driving or robots are sensitive to waterdrops adhered to windows or camera lenses. Most recent waterdrop removal approaches take a single image as input and often fail to recover the missing content…

Synthesizing photo-realistic images from text descriptions is a challenging problem. Previous studies have shown remarkable progresses on visual quality of the generated images. In this paper, we consider semantics from the input text…

Recently, deep image deraining models based on paired datasets have made a series of remarkable progress. However, they cannot be well applied in real-world applications due to the difficulty of obtaining real paired datasets and the poor…

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…

Autonomous driving simulators provide an effective and low-cost alternative for evaluating or enhancing visual perception models. However, the reliability of evaluation depends on the diversity and realism of the generated scenes. Extreme…

Generative models have made significant progress in the tasks of modeling complex data distributions such as natural images. The introduction of Generative Adversarial Networks (GANs) and auto-encoders lead to the possibility of training on…

We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as…

In this paper, we examine the problem of real-world image deblurring and take into account two key factors for improving the performance of the deep image deblurring model, namely, training data synthesis and network architecture design.…

Deep image denoising networks have achieved impressive success with the help of a considerably large number of synthetic train datasets. However, real-world denoising is a still challenging problem due to the dissimilarity between…

Due to distribution shift, the performance of deep learning-based method for image dehazing is adversely affected when applied to real-world hazy images. In this paper, we find that such deviation in dehazing task between real and synthetic…

Cross-domain image-to-image translation should satisfy two requirements: (1) preserve the information that is common to both domains, and (2) generate convincing images covering variations that appear in the target domain. This is…

Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images,…

When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be…