Browse Proceedings

This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor $\times$4 based on a set of prior ...

Recent advances in single image super-resolution (SISR) explored the power of convolutional neural network (CNN) to achieve a better performance. Despite the great success of CNN-based methods, it is not easy to apply these methods to edge devices ...

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention ...

In recent years, image super-resolution (SR) methods using convolutional neural networks (CNNs) have achieved successful results. Nevertheless, it is often difficult to apply them in resource-constrained environments due to the requirement of ...

Deep learning methods for super-resolution (SR) have been dominating in terms of performance in recent years. Such methods can potentially improve the digital zoom capabilities of most modern mobile phones, but are not directly applicable on ...

Lightweight image super-resolution (SR) networks have the utmost significance for real-world applications. There are several deep learning based SR methods with remarkable performance, but their memory and computational cost are hindrances in ...

In recent years, remarkable progress has been made in single image super-resolution due to the powerful representation capabilities of deep neural networks. However, the superior performance is at the expense of excessive computation costs, ...

In recent years, deep learning approaches have achieved impressive results in single image super-resolution (SISR). However, most of these models require high computational and memory resources beyond the capability of most mobile and embedded ...$$$$$$

This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-...

Image Signal Processor (ISP) plays a core rule in camera systems. However, ISP tuning is highly complicated and requires professional skills and advanced imaging experiences. To skip the painful ISP tuning process, we introduce EEDNet in this ...

As the revolutionary improvement being made on the performance of smartphones over the last decade, mobile photography becomes one of the most common practices among the majority of smartphone users. However, due to the limited size of camera ...

Reconstructing RGB image from RAW data obtained with a mobile device is related to a number of image signal processing (ISP) tasks, such as demosaicing, denoising, etc. Deep neural networks have shown promising results over hand-crafted ISP ...

This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world bokeh simulation problem, where the goal was to ...

A photo captured with bokeh effect often means objects in focus are sharp while the out-of-focus areas are all blurred. DSLR can easily render this kind of effect naturally. However, due to the limitation of sensors, smartphones cannot capture ...$\mathrm{}\mathrm{}$

In this paper, we study realistic bokeh rendering from a single all-in-focus image. Existing computational bokeh rendering methods generate bokeh effects by adding a simple flat background blur. As a result, the rendering results are different ...

In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated poses are ...

While existing makeup style transfer models perform an image synthesis whose results cannot be explicitly controlled, the ability to modify makeup color continuously is a desirable property for virtual try-on applications. We propose a new ...

Automatic kinship verification using face images involves analyzing features and computing similarities between two input images to establish kin-relationship. It has gained significant interest from the research community and several approaches ...

Synthesizing an interpolated image between two real images can be achieved by a simple interpolation on the latent space of the images, so that the resulting image inherits features from both. The task becomes more difficult when two images are in ...

It is extremely challenging to acquire perceptually plausible images under low-light conditions due to low SNR. Most recently, U-Nets have shown promising results for low-light imaging. However, vanilla U-Nets generate images with artifacts such ...

We propose the first practical multitask image enhancement network, that is able to learn one-to-many and many-to-one image mappings. We show that our model outperforms the current state of the art in learning a single enhancement mapping, while ...

Burst Color Constancy (CC) is a recently proposed approach that challenges the conventional single-frame color constancy. The conventional approach is to use a single frame - shot frame - to estimate the scene illumination color. In burst CC, ...

A near-optimal reconstruction of the radiance of a High Dynamic Range scene from an exposure stack can be obtained by modeling the camera noise distribution. The latent radiance is then estimated using Maximum Likelihood Estimation. But this ...

This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for $\times$...$$$$

With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image super-resolution (SR) methods have achieved impressive performance using deep residual network with dense skip connections. While these models perform well on ...

Increasing model size often results in improved performance on super-resolution reconstruction. However, at some point large model cannot SR huge images due to GPU/TPU memory limitations. In this paper, to address this problem, we present Block-...

Single Image Super-Resolution in practical scenarios is quite challenging, because of more complex degradation than bicubic downsampling and diverse degradation differences among devices. To solve this problem, we develop a novel super resolution ...$$$$