Space-time video super-resolution (STVSR) is the task of interpolating videos with both Low Frame Rate (LFR) and Low Resolution (LR) to produce High-Frame-Rate (HFR) and also High-Resolution (HR) counterparts. The existing methods based on Convolutional Neural Network~(CNN) succeed in achieving visually satisfied results while suffer from slow inference speed due to their heavy architectures. We propose to resolve this issue by using a spatial-temporal transformer that naturally incorporates the spatial and temporal super resolution modules into a single model. Unlike CNN-based methods, we do not explicitly use separated building blocks for temporal interpolations and spatial super-resolutions; instead, we only use a single end-to-end transformer architecture. Specifically, a reusable dictionary is built by encoders based on the input LFR and LR frames, which is then utilized in the decoder part to synthesize the HFR and HR frames. Compared with the state-of-the-art TMNet \cite{xu2021temporal}, our network is $60\%$ smaller (4.5M vs 12.3M parameters) and $80\%$ faster (26.2fps vs 14.3fps on $720\times576$ frames) without sacrificing much performance. The source code is available at https://github.com/llmpass/RSTT.
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-resolution contains a significant component, i.e., motion compensation, which is used to estimate the displacement between successive video frames for temporal alignment. Optical flow, which can supply dense and sub-pixel motion between consecutive frames, is among the most common ways for this task. To obtain a good understanding of the effect that optical flow acts in video super-resolution, in this work, we conduct a comprehensive review on this subject for the first time. This investigation covers the following major topics: the function of super-resolution (i.e., why we require super-resolution); the concept of video super-resolution (i.e., what is video super-resolution); the description of evaluation metrics (i.e., how (video) superresolution performs); the introduction of optical flow based video super-resolution; the investigation of using optical flow to capture temporal dependency for video super-resolution. Prominently, we give an in-depth study of the deep learning based video super-resolution method, where some representative algorithms are analyzed and compared. Additionally, we highlight some promising research directions and open issues that should be further addressed.
The target of space-time video super-resolution (STVSR) is to increase the spatial-temporal resolution of low-resolution (LR) and low frame rate (LFR) videos. Recent approaches based on deep learning have made significant improvements, but most of them only use two adjacent frames, that is, short-term features, to synthesize the missing frame embedding, which cannot fully explore the information flow of consecutive input LR frames. In addition, existing STVSR models hardly exploit the temporal contexts explicitly to assist high-resolution (HR) frame reconstruction. To address these issues, in this paper, we propose a deformable attention network called STDAN for STVSR. First, we devise a long-short term feature interpolation (LSTFI) module, which is capable of excavating abundant content from more neighboring input frames for the interpolation process through a bidirectional RNN structure. Second, we put forward a spatial-temporal deformable feature aggregation (STDFA) module, in which spatial and temporal contexts in dynamic video frames are adaptively captured and aggregated to enhance SR reconstruction. Experimental results on several datasets demonstrate that our approach outperforms state-of-the-art STVSR methods. The code is available at https://github.com/littlewhitesea/STDAN.
Video super-resolution (VSR) refers to the reconstruction of high-resolution (HR) video from the corresponding low-resolution (LR) video. Recently, VSR has received increasing attention. In this paper, we propose a novel dual dense connection network that can generate high-quality super-resolution (SR) results. The input frames are creatively divided into reference frame, pre-temporal group and post-temporal group, representing information in different time periods. This grouping method provides accurate information of different time periods without causing time information disorder. Meanwhile, we produce a new loss function, which is beneficial to enhance the convergence ability of the model. Experiments show that our model is superior to other advanced models in Vid4 datasets and SPMCS-11 datasets.
Structured illumination microscopy (SIM) is an optical super-resolution technique that enables live-cell imaging beyond the diffraction limit. Reconstruction of SIM data is prone to artefacts, which becomes problematic when imaging highly dynamic samples because previous methods rely on the assumption that samples are static. We propose a new transformer-based reconstruction method, VSR-SIM, that uses shifted 3-dimensional window multi-head attention in addition to channel attention mechanism to tackle the problem of video super-resolution (VSR) in SIM. The attention mechanisms are found to capture motion in sequences without the need for common motion estimation techniques such as optical flow. We take an approach to training the network that relies solely on simulated data using videos of natural scenery with a model for SIM image formation. We demonstrate a use case enabled by VSR-SIM referred to as rolling SIM imaging, which increases temporal resolution in SIM by a factor of 9. Our method can be applied to any SIM setup enabling precise recordings of dynamic processes in biomedical research with high temporal resolution.
Video super-resolution (VSR) has many applications that pose strict causal, real-time, and latency constraints, including video streaming and TV. We address the VSR problem under these settings, which poses additional important challenges since information from future frames is unavailable. Importantly, designing efficient, yet effective frame alignment and fusion modules remain central problems. In this work, we propose a recurrent VSR architecture based on a deformable attention pyramid (DAP). Our DAP aligns and integrates information from the recurrent state into the current frame prediction. To circumvent the computational cost of traditional attention-based methods, we only attend to a limited number of spatial locations, which are dynamically predicted by the DAP. Comprehensive experiments and analysis of the proposed key innovations show the effectiveness of our approach. We significantly reduce processing time and computational complexity in comparison to state-of-the-art methods, while maintaining a high performance. We surpass state-of-the-art method EDVR-M on two standard benchmarks with a speed-up of over $3\times$.
Efficiency of gradient propagation in intermediate layers of convolutional neural networks is of key importance for super-resolution task. To this end, we propose a deep architecture for single image super-resolution (SISR), which is built using efficient convolutional units we refer to as mixed-dense connection blocks (MDCB). The design of MDCB combines the strengths of both residual and dense connection strategies, while overcoming their limitations. To enable super-resolution for multiple factors, we propose a scale-recurrent framework which reutilizes the filters learnt for lower scale factors recursively for higher factors. This leads to improved performance and promotes parametric efficiency for higher factors. We train two versions of our network to enhance complementary image qualities using different loss configurations. We further employ our network for video super-resolution task, where our network learns to aggregate information from multiple frames and maintain spatio-temporal consistency. The proposed networks lead to qualitative and quantitative improvements over state-of-the-art techniques on image and video super-resolution benchmarks.
Video restoration (e.g., video super-resolution) aims to restore high-quality frames from low-quality frames. Different from single image restoration, video restoration generally requires to utilize temporal information from multiple adjacent but usually misaligned video frames. Existing deep methods generally tackle with this by exploiting a sliding window strategy or a recurrent architecture, which either is restricted by frame-by-frame restoration or lacks long-range modelling ability. In this paper, we propose a Video Restoration Transformer (VRT) with parallel frame prediction and long-range temporal dependency modelling abilities. More specifically, VRT is composed of multiple scales, each of which consists of two kinds of modules: temporal mutual self attention (TMSA) and parallel warping. TMSA divides the video into small clips, on which mutual attention is applied for joint motion estimation, feature alignment and feature fusion, while self attention is used for feature extraction. To enable cross-clip interactions, the video sequence is shifted for every other layer. Besides, parallel warping is used to further fuse information from neighboring frames by parallel feature warping. Experimental results on five tasks, including video super-resolution, video deblurring, video denoising, video frame interpolation and space-time video super-resolution, demonstrate that VRT outperforms the state-of-the-art methods by large margins ($\textbf{up to 2.16dB}$) on fourteen benchmark datasets.
Existing deep learning-based video super-resolution (SR) methods usually depend on the supervised learning approach, where the training data is usually generated by the blurring operation with known or predefined kernels (e.g., Bicubic kernel) followed by a decimation operation. However, this does not hold for real applications as the degradation process is complex and cannot be approximated by these idea cases well. Moreover, obtaining high-resolution (HR) videos and the corresponding low-resolution (LR) ones in real-world scenarios is difficult. To overcome these problems, we propose a self-supervised learning method to solve the blind video SR problem, which simultaneously estimates blur kernels and HR videos from the LR videos. As directly using LR videos as supervision usually leads to trivial solutions, we develop a simple and effective method to generate auxiliary paired data from original LR videos according to the image formation of video SR, so that the networks can be better constrained by the generated paired data for both blur kernel estimation and latent HR video restoration. In addition, we introduce an optical flow estimation module to exploit the information from adjacent frames for HR video restoration. Experiments show that our method performs favorably against state-of-the-art ones on benchmarks and real-world videos.
Recurrent models have gained popularity in deep learning (DL) based video super-resolution (VSR), due to their increased computational efficiency, temporal receptive field and temporal consistency compared to sliding-window based models. However, when inferring on long video sequences presenting low motion (i.e. in which some parts of the scene barely move), recurrent models diverge through recurrent processing, generating high frequency artifacts. To the best of our knowledge, no study about VSR pointed out this instability problem, which can be critical for some real-world applications. Video surveillance is a typical example where such artifacts would occur, as both the camera and the scene stay static for a long time. In this work, we expose instabilities of existing recurrent VSR networks on long sequences with low motion. We demonstrate it on a new long sequence dataset Quasi-Static Video Set, that we have created. Finally, we introduce a new framework of recurrent VSR networks that is both stable and competitive, based on Lipschitz stability theory. We propose a new recurrent VSR network, coined Middle Recurrent Video Super-Resolution (MRVSR), based on this framework. We empirically show its competitive performance on long sequences with low motion.
The video super-resolution (VSR) method based on the recurrent convolutional network has strong temporal modeling capability for video sequences. However, the temporal receptive field of different recurrent units in the unidirectional recurrent network is unbalanced. Earlier reconstruction frames receive less spatio-temporal information, resulting in fuzziness or artifacts. Although the bidirectional recurrent network can alleviate this problem, it requires more memory space and fails to perform many tasks with low latency requirements. To solve the above problems, we propose an end-to-end information prebuilt recurrent reconstruction network (IPRRN), consisting of an information prebuilt network (IPNet) and a recurrent reconstruction network (RRNet). By integrating sufficient information from the front of the video to build the hidden state needed for the initially recurrent unit to help restore the earlier frames, the information prebuilt network balances the input information difference at different time steps. In addition, we demonstrate an efficient recurrent reconstruction network, which outperforms the existing unidirectional recurrent schemes in all aspects. Many experiments have verified the effectiveness of the network we propose, which can effectively achieve better quantitative and qualitative evaluation performance compared to the existing state-of-the-art methods.
Different from the Single Image Super-Resolution(SISR) task, the key for Video Super-Resolution(VSR) task is to make full use of complementary information across frames to reconstruct the high-resolution sequence. Since images from different frames with diverse motion and scene, accurately aligning multiple frames and effectively fusing different frames has always been the key research work of VSR tasks. To utilize rich complementary information of neighboring frames, in this paper, we propose a multi-stage VSR deep architecture, dubbed as PP-MSVSR, with local fusion module, auxiliary loss and re-align module to refine the enhanced result progressively. Specifically, in order to strengthen the fusion of features across frames in feature propagation, a local fusion module is designed in stage-1 to perform local feature fusion before feature propagation. Moreover, we introduce an auxiliary loss in stage-2 to make the features obtained by the propagation module reserve more correlated information connected to the HR space, and introduce a re-align module in stage-3 to make full use of the feature information of the previous stage. Extensive experiments substantiate that PP-MSVSR achieves a promising performance of Vid4 datasets, which achieves a PSNR of 28.13dB with only 1.45M parameters. And the PP-MSVSR-L exceeds all state of the art method on REDS4 datasets with considerable parameters. Code and models will be released in PaddleGAN\footnote{https://github.com/PaddlePaddle/PaddleGAN.}.
Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is helpful in modeling distant correspondences, error accumulation is inevitable due to the propagation mechanism. In this work, we present a novel, generic iterative alignment module which employs a gradual refinement scheme for sub-alignments, yielding more accurate motion compensation. To further enhance the alignment accuracy and temporal consistency, we develop a non-parametric re-weighting method, where the importance of each neighboring frame is adaptively evaluated in a spatial-wise way for aggregation. By virtue of the proposed strategies, our model achieves state-of-the-art performance on multiple benchmarks across a range of video restoration tasks including video super-resolution, denoising and deblurring. Our project is available in \url{https://github.com/redrock303/Revisiting-Temporal-Alignment-for-Video-Restoration.git}.
The diversity and complexity of degradations in real-world video super-resolution (VSR) pose non-trivial challenges in inference and training. First, while long-term propagation leads to improved performance in cases of mild degradations, severe in-the-wild degradations could be exaggerated through propagation, impairing output quality. To balance the tradeoff between detail synthesis and artifact suppression, we found an image pre-cleaning stage indispensable to reduce noises and artifacts prior to propagation. Equipped with a carefully designed cleaning module, our RealBasicVSR outperforms existing methods in both quality and efficiency. Second, real-world VSR models are often trained with diverse degradations to improve generalizability, requiring increased batch size to produce a stable gradient. Inevitably, the increased computational burden results in various problems, including 1) speed-performance tradeoff and 2) batch-length tradeoff. To alleviate the first tradeoff, we propose a stochastic degradation scheme that reduces up to 40\% of training time without sacrificing performance. We then analyze different training settings and suggest that employing longer sequences rather than larger batches during training allows more effective uses of temporal information, leading to more stable performance during inference. To facilitate fair comparisons, we propose the new VideoLQ dataset, which contains a large variety of real-world low-quality video sequences containing rich textures and patterns. Our dataset can serve as a common ground for benchmarking. Code, models, and the dataset will be made publicly available.
Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional operations. Their goal is to produce downsampled volumes that closely resemble the input volume while, ideally, also being computationally and memory efficient. Meeting both these requirements remains a challenge. To this end, we propose an adaptive and exponentially weighted pooling method: adaPool. Our method learns a regional-specific fusion of two sets of pooling kernels that are based on the exponent of the Dice-Sorensen coefficient and the exponential maximum, respectively. AdaPool improves the preservation of detail on a range of tasks including image and video classification and object detection. A key property of adaPool is its bidirectional nature. In contrast to common pooling methods, the learned weights can also be used to upsample activation maps. We term this method adaUnPool. We evaluate adaUnPool on image and video super-resolution and frame interpolation. For benchmarking, we introduce Inter4K, a novel high-quality, high frame-rate video dataset. Our experiments demonstrate that adaPool systematically achieves better results across tasks and backbones, while introducing a minor additional computational and memory overhead.
Space-time video super-resolution (STVSR) aims to construct a high space-time resolution video sequence from the corresponding low-frame-rate, low-resolution video sequence. Inspired by the recent success to consider spatial-temporal information for space-time super-resolution, our main goal in this work is to take full considerations of spatial and temporal correlations within the video sequences of fast dynamic events. To this end, we propose a novel one-stage memory enhanced graph attention network (MEGAN) for space-time video super-resolution. Specifically, we build a novel long-range memory graph aggregation (LMGA) module to dynamically capture correlations along the channel dimensions of the feature maps and adaptively aggregate channel features to enhance the feature representations. We introduce a non-local residual block, which enables each channel-wise feature to attend global spatial hierarchical features. In addition, we adopt a progressive fusion module to further enhance the representation ability by extensively exploiting spatial-temporal correlations from multiple frames. Experiment results demonstrate that our method achieves better results compared with the state-of-the-art methods quantitatively and visually.
Despite the growing popularity of video super-resolution (VSR), there is still no good way to assess the quality of the restored details in upscaled frames. Some SR methods may produce the wrong digit or an entirely different face. Whether a method's results are trustworthy depends on how well it restores truthful details. Image super-resolution can use natural distributions to produce a high-resolution image that is only somewhat similar to the real one. VSR enables exploration of additional information in neighboring frames to restore details from the original scene. The ERQA metric, which we propose in this paper, aims to estimate a model's ability to restore real details using VSR. On the assumption that edges are significant for detail and character recognition, we chose edge fidelity as the foundation for this metric. Experimental validation of our work is based on the MSU Video Super-Resolution Benchmark, which includes the most difficult patterns for detail restoration and verifies the fidelity of details from the original frame. Code for the proposed metric is publicly available at https://github.com/msu-video-group/ERQA.
In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i.e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence. The existing approaches to RefVSR essentially attempt to align the reference and the input sequence, in the presence of resolution gap and long temporal range. However, they either ignore temporal structure within the input sequence, or suffer accumulative alignment errors. To address these issues, we propose EFENet to exploit simultaneously the visual cues contained in the HR reference and the temporal information contained in the LR sequence. EFENet first globally estimates cross-scale flow between the reference and each LR frame. Then our novel flow refinement module of EFENet refines the flow regarding the furthest frame using all the estimated flows, which leverages the global temporal information within the sequence and therefore effectively reduces the alignment errors. We provide comprehensive evaluations to validate the strengths of our approach, and to demonstrate that the proposed framework outperforms the state-of-the-art methods. Code is available at https://github.com/IndigoPurple/EFENet.
In this paper, we consider the task of space-time video super-resolution (ST-VSR), which can increase the spatial resolution and frame rate for a given video simultaneously. Despite the remarkable progress of recent methods, most of them still suffer from high computational costs and inefficient long-range information usage. To alleviate these problems, we propose a Bidirectional Recurrence Network (BRN) with the optical-flow-reuse strategy to better use temporal knowledge from long-range neighboring frames for high-efficiency reconstruction. Specifically, an efficient and memory-saving multi-frame motion utilization strategy is proposed by reusing the intermediate flow of adjacent frames, which considerably reduces the computation burden of frame alignment compared with traditional LSTM-based designs. In addition, the proposed hidden state in BRN is updated by the reused optical flow and refined by the Feature Refinement Module (FRM) for further optimization. Moreover, by utilizing intermediate flow estimation, the proposed method can inference non-linear motion and restore details better. Extensive experiments demonstrate that our optical-flow-reuse-based bidirectional recurrent network (OFR-BRN) is superior to state-of-the-art methods in accuracy and efficiency.
Face video super-resolution algorithm aims to reconstruct realistic face details through continuous input video sequences. However, existing video processing algorithms usually contain redundant parameters to guarantee different super-resolution scenes. In this work, we focus on super-resolution of face areas in original video scenes, while rest areas are interpolated. This specific super-resolved task makes it possible to cut redundant parameters in general video super-resolution networks. We construct a dataset consisting entirely of face video sequences for network training and evaluation, and conduct hyper-parameter optimization in our experiments. We use three combined strategies to optimize the network parameters with a simultaneous train-evaluation method to accelerate optimization process. Results show that simultaneous train-evaluation method improves the training speed and facilitates the generation of efficient networks. The generated network can reduce at least 52.4% parameters and 20.7% FLOPs, achieve better performance on PSNR, SSIM compared with state-of-art video super-resolution algorithms. When processing 36x36x1x3 input video frame sequences, the efficient network provides 47.62 FPS real-time processing performance. We name our proposal as hyper-parameter optimization for face Video Super-Resolution (HO-FVSR), which is open-sourced at https://github.com/yphone/efficient-network-for-face-VSR.