This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020. Common scaling factors for learned video super-resolution (VSR) do not go beyond factor 4. Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details. The task in this challenge is to upscale videos with an extreme factor of 16, which results in more serious degradations that also affect the structural integrity of the videos. A single pixel in the low-resolution (LR) domain corresponds to 256 pixels in the high-resolution (HR) domain. Due to this massive information loss, it is hard to accurately restore the missing information. Track 1 is set up to gauge the state-of-the-art for such a demanding task, where fidelity to the ground truth is measured by PSNR and SSIM. Perceptually higher quality can be achieved in trade-off for fidelity by generating plausible high-frequency content. Track 2 therefore aims at generating visually pleasing results, which are ranked according to human perception, evaluated by a user study. In contrast to single image super-resolution (SISR), VSR can benefit from additional information in the temporal domain. However, this also imposes an additional requirement, as the generated frames need to be consistent along time.
In the learning based video compression approaches, it is an essential issue to compress pixel-level optical flow maps by developing new motion vector (MV) encoders. In this work, we propose a new framework called Resolution-adaptive Flow Coding (RaFC) to effectively compress the flow maps globally and locally, in which we use multi-resolution representations instead of single-resolution representations for both the input flow maps and the output motion features of the MV encoder. To handle complex or simple motion patterns globally, our frame-level scheme RaFC-frame automatically decides the optimal flow map resolution for each video frame. To cope different types of motion patterns locally, our block-level scheme called RaFC-block can also select the optimal resolution for each local block of motion features. In addition, the rate-distortion criterion is applied to both RaFC-frame and RaFC-block and select the optimal motion coding mode for effective flow coding. Comprehensive experiments on four benchmark datasets HEVC, VTL, UVG and MCL-JCV clearly demonstrate the effectiveness of our overall RaFC framework after combing RaFC-frame and RaFC-block for video compression.
Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. They are less efficient compared to the recurrent-based methods. In this work, we propose a novel recurrent video super-resolution method which is both effective and efficient in exploiting previous frames to super-resolve the current frame. It divides the input into structure and detail components which are fed to a recurrent unit composed of several proposed two-stream structure-detail blocks. In addition, a hidden state adaptation module that allows the current frame to selectively use information from hidden state is introduced to enhance its robustness to appearance change and error accumulation. Extensive ablation study validate the effectiveness of the proposed modules. Experiments on several benchmark datasets demonstrate the superior performance of the proposed method compared to state-of-the-art methods on video super-resolution.
In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve image dehazing without training on the ground-truth clean image (unsupervised) and a image collection (untrained). An unsupervised neural network will avoid the intensive labor collection of hazy-clean image pairs, and an untrained model is a ``real'' single image dehazing approach which could remove haze based on only the observed hazy image itself and no extra images is used. Motivated by the layer disentanglement idea, we propose a novel method, called you only look yourself (\textbf{YOLY}) which could be one of the first unsupervised and untrained neural networks for image dehazing. In brief, YOLY employs three jointly subnetworks to separate the observed hazy image into several latent layers, \textit{i.e.}, scene radiance layer, transmission map layer, and atmospheric light layer. After that, these three layers are further composed to the hazy image in a self-supervised manner. Thanks to the unsupervised and untrained characteristics of YOLY, our method bypasses the conventional training paradigm of deep models on hazy-clean pairs or a large scale dataset, thus avoids the labor-intensive data collection and the domain shift issue. Besides, our method also provides an effective learning-based haze transfer solution thanks to its layer disentanglement mechanism. Extensive experiments show the promising performance of our method in image dehazing compared with 14 methods on four databases.
In this paper, we tackle the problem of convolutional neural network design. Instead of focusing on the overall architecture design, we investigate a design space that is usually overlooked, \ie adjusting the channel configurations of predefined networks. We find that this adjustment can be achieved by pruning widened baseline networks and leads to superior performance. Base on that, we articulate the ``heterogeneity hypothesis'': with the same training protocol, there exists a layer-wise dissimilated network architecture (LW-DNA) that can outperform the original network with regular channel configurations under lower level of model complexity. The LW-DNA models are identified without added computational cost and training time compared with the original network. This constraint leads to controlled experiment which directs the focus to the importance of layer-wise specific channel configurations. Multiple sources of hints relate the benefits of LW-DNA models to overfitting, \ie the relative relationship between model complexity and dataset size. Experiments are conducted on various networks and datasets for image classification, visual tracking and image restoration. The resultant LW-DNA models consistently outperform the compared baseline models.
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 having significantly fewer parameters than its competitors. Furthermore, the model achieves even higher performance on learning multiple mappings simultaneously, by taking advantage of shared representations. Our network is based on the recently proposed SGN architecture, with modifications targeted at incorporating global features and style adaption. Finally, we present an unpaired learning method for multitask image enhancement, that is based on generative adversarial networks (GANs).
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and 19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.
Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consistent. In this work, we propose UVIT, a novel unsupervised video-to-video translation model. Our model decomposes the style and the content, uses the specialized encoder-decoder structure and propagates the inter-frame information through bidirectional recurrent neural network (RNN) units. The style-content decomposition mechanism enables us to achieve style consistent video translation results as well as provides us with a good interface for modality flexible translation. In addition, by changing the input frames and style codes incorporated in our translation, we propose a video interpolation loss, which captures temporal information within the sequence to train our building blocks in a self-supervised manner. Our model can produce photo-realistic, spatio-temporal consistent translated videos in a multimodal way. Subjective and objective experimental results validate the superiority of our model over existing methods. More details can be found on our project website: https://uvit.netlify.com
These days, unsupervised super-resolution (SR) has been soaring due to its practical and promising potential in real scenarios. The philosophy of off-the-shelf approaches lies in the augmentation of unpaired data, i.e. first generating synthetic low-resolution (LR) images $\mathcal{Y}^g$ corresponding to real-world high-resolution (HR) images $\mathcal{X}^r$ in the real-world LR domain $\mathcal{Y}^r$, and then utilizing the pseudo pairs $\{\mathcal{Y}^g, \mathcal{X}^r\}$ for training in a supervised manner. Unfortunately, since image translation itself is an extremely challenging task, the SR performance of these approaches are severely limited by the domain gap between generated synthetic LR images and real LR images. In this paper, we propose a novel domain-distance aware super-resolution (DASR) approach for unsupervised real-world image SR. The domain gap between training data (e.g. $\mathcal{Y}^g$) and testing data (e.g. $\mathcal{Y}^r$) is addressed with our \textbf{domain-gap aware training} and \textbf{domain-distance weighted supervision} strategies. Domain-gap aware training takes additional benefit from real data in the target domain while domain-distance weighted supervision brings forward the more rational use of labeled source domain data. The proposed method is validated on synthetic and real datasets and the experimental results show that DASR consistently outperforms state-of-the-art unsupervised SR approaches in generating SR outputs with more realistic and natural textures.
Network pruning has been the driving force for the efficient inference of neural networks and the alleviation of model storage and transmission burden. Traditional network pruning methods focus on the per-filter influence on the network accuracy by analyzing the filter distribution. With the advent of AutoML and neural architecture search (NAS), pruning has become topical with automatic mechanism and searching based architecture optimization. However, current automatic designs rely on either reinforcement learning or evolutionary algorithm, which often do not have a theoretical convergence guarantee or do not converge in a meaningful time limit. In this paper, we propose a differentiable pruning method via hypernetworks for automatic network pruning and layer-wise configuration optimization. A hypernetwork is designed to generate the weights of the backbone network. The input of the hypernetwork, namely, the latent vectors control the output channels of the layers of backbone network. By applying $\ell_1$ sparsity regularization to the latent vectors and utilizing proximal gradient, sparse latent vectors can be obtained with removed zero elements. Thus, the corresponding elements of the hypernetwork outputs can also be removed, achieving the effect of network pruning. The latent vectors of all the layers are pruned together, resulting in an automatic layer configuration. Extensive experiments are conducted on various networks for image classification, single image super-resolution, and denoising. And the experimental results validate the proposed method.