Video frame interpolation, the synthesis of novel views in time, is an increasingly popular research direction with many new papers further advancing the state of the art. But as each new method comes with a host of variables that affect the interpolation quality, it can be hard to tell what is actually important for this task. In this work, we show, somewhat surprisingly, that it is possible to achieve near state-of-the-art results with an older, simpler approach, namely adaptive separable convolutions, by a subtle set of low level improvements. In doing so, we propose a number of intuitive but effective techniques to improve the frame interpolation quality, which also have the potential to other related applications of adaptive convolutions such as burst image denoising, joint image filtering, or video prediction.
Image deblurring aims to recover the latent sharp image from its blurry counterpart and has a wide range of applications in computer vision. The Convolution Neural Networks (CNNs) have performed well in this domain for many years, and until recently an alternative network architecture, namely Transformer, has demonstrated even stronger performance. One can attribute its superiority to the multi-head self-attention (MHSA) mechanism, which offers a larger receptive field and better input content adaptability than CNNs. However, as MHSA demands high computational costs that grow quadratically wit…
Application of convolutional neural networks in image super-resolution
Harbin Institute of Technology（哈尔滨工业大学）；National Engineering Laboratory for Big Data Application Technology of Integrated Space, Air, Ground, and Sea（空天地海一体化大数据应用技术国家工程实验室）；Northwestern Polytechnical University（西北工业大学）；Wuhan University（武汉大学）；Guangxi Normal University（广西师范大学）
Image super-resolution (SR) is a fast-moving field with novel architectures attracting the spotlight. However, most SR models were optimized with dated training strategies. In this work, we revisit the popular RCAN model and examine the effect of different training options in SR. Surprisingly (or perhaps as expected), we show that RCAN can outperform or match nearly all the CNN-based SR architectures published after RCAN on standard benchmarks with a proper training strategy and minimal architecture change. Besides, although RCAN is a very large SR architecture with more than four hundred conv…
This paper focuses on visual counting, which aims to predict the number of occurrences given a natural image and a query (e.g. a question or a category). Unlike most prior works that use explicit, symbolic models which can be computationally expensive and limited in generalization, we propose a simple and effective alternative by revisiting modulated convolutions that fuse the query and the image locally. Following the design of residual bottleneck, we call our method MoVie, short for Modulated conVolutional bottlenecks. Notably, MoVie reasons implicitly and holistically and only needs a singl…
University of California San Diego（加利福尼亚大学圣迭戈分校）；Microsoft（微软公司）
Recent research in dynamic convolution shows substantial performance boost for efficient CNNs, due to the adaptive aggregation of K static convolution kernels. It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention and static convolution kernels is challenging. In this paper, we revisit it from a new perspective of matrix decomposition and reveal the key issue is that dynamic convolution applies dynamic attention over channel groups after projecting into a higher dimensional latent space. To address this issu…
UC San Diego（加州大学圣地亚哥分校）；ShanghaiTech University（上海科技大学）；National University of Singapore（新加坡国立大学）；Shanghai AI Laboratory（上海人工智能实验室）；Technical University of Munich（慕尼黑工业大学）
The University of Maryland, College Park（马里兰大学帕克分校）；University of Rochester（罗切斯特大学）；Chinese Academy of Sciences（中国科学院）；Peng Cheng Laboratory（鹏城实验室）
We propose a marginal super-resolution (MSR) approach based on 2D convolutional neural networks (CNNs) for interpolating an anisotropic brain magnetic resonance scan along the highly under-sampled direction, which is assumed to axial without loss of generality. Previous methods for slice interpolation only consider data from pairs of adjacent 2D slices. The possibility of fusing information from the direction orthogonal to the 2D slices remains unexplored. Our approach performs MSR in both sagittal and coronal directions, which provides an initial estimate for slice interpolation. The interpol…
Video frame interpolation typically involves two steps: motion estimation and pixel synthesis. Such a two-step approach heavily depends on the quality of motion estimation. This paper presents a robust video frame interpolation method that combines these two steps into a single process. Specifically, our method considers pixel synthesis for the interpolated frame as local convolution over two input frames. The convolution kernel captures both the local motion between the input frames and the coefficients for pixel synthesis. Our method employs a deep fully convolutional neural network to estim…
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
In the modern world, satellite images play a key role in forest management and degradation monitoring. For a precise quantification of forest land cover changes, the availability of spatially fine resolution data is a necessity. Since 1972, NASAs LANDSAT Satellites are providing terrestrial images covering every corner of the earth, which have been proved to be a highly useful resource for terrestrial change analysis and have been used in numerous other sectors. However, freely accessible satellite images are, generally, of medium to low resolution which is a major hindrance to the precision o…
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Tsinghua-Berkeley Shenzhen Institute (TBSI), Tsinghua University（清华大学清华-伯克利深圳学院）；Harvard University（哈佛大学）；University of California, Berkeley（加州大学伯克利分校）；Ohio State University（俄亥俄州立大学）
Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be expressed by a linear combination of a few elements from a convolutional dictionary, are powerful tools for analyzing natural images with good theoretical interpretability and biological plausibility. However, such principled models have not demonstrated competitive performance when compared with empirically designed deep networks. This paper revisits the s…
UIUC（伊利诺伊大学厄巴纳-香槟分校）；NUS（新加坡国立大学）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Tencent AI Lab（腾讯人工智能实验室）
Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produce high-quality dense object localization maps from image-level supervision. To mitigate such a gap, we revisit the dilated convolution [1] and reveal how it can be utilized in a novel way to effectively overcome this critical limitation of weakly supervised segmentation approaches. Specifically, we find that varying dilation rates can effectively enlarge the receptive fields o…
As Deep Neural Networks are becoming more popular, much of the attention is being devoted to Computer Vision problems that used to be solved with more traditional approaches. Video frame interpolation is one of such challenges that has seen new research involving various techniques in deep learning. In this paper, we replicate the work of Niklaus et al. on Adaptive Separable Convolution, which claims high quality results on the video frame interpolation task. We apply the same network structure trained on a smaller dataset and experiment with various different loss functions, in order to deter…
Video frame interpolation aims at synthesizing intermediate frames from nearby source frames while maintaining spatial and temporal consistencies. The existing deep-learning-based video frame interpolation methods can be roughly divided into two categories: flow-based methods and kernel-based methods. The performance of flow-based methods is often jeopardized by the inaccuracy of flow map estimation due to oversimplified motion models, while that of kernel-based methods tends to be constrained by the rigidity of kernel shape. To address these performance-limiting issues, a novel mechanism name…
Standard video frame interpolation methods first estimate optical flow between input frames and then synthesize an intermediate frame guided by motion. Recent approaches merge these two steps into a single convolution process by convolving input frames with spatially adaptive kernels that account for motion and re-sampling simultaneously. These methods require large kernels to handle large motion, which limits the number of pixels whose kernels can be estimated at once due to the large memory demand. To address this problem, this paper formulates frame interpolation as local separable convolut…
The Chinese University of Hong Kong（香港中文大学）；SmartMore（思谋科技）
Video frame interpolation (VFI), which aims to synthesize intermediate frames of a video, has made remarkable progress with development of deep convolutional networks over past years. Existing methods built upon convolutional networks generally face challenges of handling large motion due to the locality of convolution operations. To overcome this limitation, we introduce a novel framework, which takes advantage of Transformer to model long-range pixel correlation among video frames. Further, our network is equipped with a novel cross-scale window-based attention mechanism, where cross-scale w…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Bigo
Existing video frame interpolation methods can only interpolate the frame at a given intermediate time-step, e.g. 1/2. In this paper, we aim to explore a more generalized kind of video frame interpolation, that at an arbitrary time-step. To this end, we consider processing different time-steps with adaptively generated convolutional kernels in a unified way with the help of meta-learning. Specifically, we develop a dual meta-learned frame interpolation framework to synthesize intermediate frames with the guidance of context information and optical flow as well as taking the time-step as side i…
We present, AdaFNIO - Adaptive Fourier Neural Interpolation Operator, a neural operator-based architecture to perform video frame interpolation. Current deep learning based methods rely on local convolutions for feature learning and suffer from not being scale-invariant, thus requiring training data to be augmented through random flipping and re-scaling. On the other hand, AdaFNIO, learns the features in the frames, independent of input resolution, through token mixing and global convolution in the Fourier space or the spectral domain by using Fast Fourier Transform (FFT). We show that AdaFNIO…
Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Artificial and Natural Intelligence Toulouse Institute (ANITI)（图卢兹人工智能与自然智能研究所）；CerCo UMR 5549, CNRS（法国国家科学研究中心CerCo UMR 5549实验室）；Université Toulouse III（图卢兹第三大学）；IRIT, CNRS（法国国家科学研究中心图卢兹信息学研究所）；Toulouse INP（图卢兹国立综合理工学院）
Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks
Instituto de Investigación en Informática LIDI, Facultad de Informática, Universidad Nacional de La Plata（拉普拉塔国立大学信息学院LIDI信息学研究所）；Universitat Rovira i Virgili（罗维拉-依维尔基里大学）
A major area of growth within deep learning has been the study and implementation of convolutional neural networks. The general explanation within the deep learning community of the robustness of convolutional neural networks (CNNs) within image recognition rests upon the idea that CNNs are able to extract localized features. However, recent developments in fields such as Natural Language Processing are demonstrating that this paradigm may be incorrect. In this paper, we analyze the current state of the field concerning CNN's and present a hypothesis that provides a novel explanation for the r…
The conventional sliced Wasserstein is defined between two probability measures that have realizations as vectors. When comparing two probability measures over images, practitioners first need to vectorize images and then project them to one-dimensional space by using matrix multiplication between the sample matrix and the projection matrix. After that, the sliced Wasserstein is evaluated by averaging the two corresponding one-dimensional projected probability measures. However, this approach has two limitations. The first limitation is that the spatial structure of images is not captured effi…
Indian Institute of Science（印度科学学院）；National Institute of Technology, Warangal（瓦朗加尔国立理工学院）
In this work, we have investigated various style transfer approaches and (i) examined how the stylized reconstruction changes with the change of loss function and (ii) provided a computationally efficient solution for the same. We have used elegant techniques like depth-wise separable convolution in place of convolution and nearest neighbor interpolation in place of transposed convolution. Further, we have also added multiple interpolations in place of transposed convolution. The results obtained are perceptually similar in quality, while being computationally very efficient. The decrease in t…
Many interpolation methods have been developed for high visual quality, but fail for inability to preserve image structures. Edges carry heavy structural information for detection, determination and classification. Edge-adaptive interpolation approaches become a center of focus. In this paper, performance of four edge-directed interpolation methods comparing with two traditional methods is evaluated on two groups of images. These methods include new edge-directed interpolation (NEDI), edge-guided image interpolation (EGII), iterative curvature-based interpolation (ICBI), directional cubic conv…
Video-based person reID is an important task, which has received much attention in recent years due to the increasing demand in surveillance and camera networks. A typical video-based person reID system consists of three parts: an image-level feature extractor (e.g. CNN), a temporal modeling method to aggregate temporal features and a loss function. Although many methods on temporal modeling have been proposed, it is hard to directly compare these methods, because the choice of feature extractor and loss function also have a large impact on the final performance. We comprehensively study and c…
School of Information and Communication Engineering, Beijing University of Posts and Telecommunications（北京邮电大学信息与通信工程学院）；Perelman School of Medicine, University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院）
Deep learning in k-space has demonstrated great potential for image reconstruction from undersampled k-space data in fast magnetic resonance imaging (MRI). However, existing deep learning-based image reconstruction methods typically apply weight-sharing convolutional neural networks (CNNs) to k-space data without taking into consideration the k-space data's spatial frequency properties, leading to ineffective learning of the image reconstruction models. Moreover, complementary information of spatially adjacent slices is often ignored in existing deep learning methods. To overcome such limitati…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）
This work presents a supervised learning based approach to the computer vision problem of frame interpolation. The presented technique could also be used in the cartoon animations since drawing each individual frame consumes a noticeable amount of time. The most existing solutions to this problem use unsupervised methods and focus only on real life videos with already high frame rate. However, the experiments show that such methods do not work as well when the frame rate becomes low and object displacements between frames becomes large. This is due to the fact that interpolation of the large d…
It is commonly believed that high internal resolution combined with expensive operations (e.g. atrous convolutions) are necessary for accurate semantic segmentation, resulting in slow speed and large memory usage. In this paper, we question this belief and demonstrate that neither high internal resolution nor atrous convolutions are necessary. Our intuition is that although segmentation is a dense per-pixel prediction task, the semantics of each pixel often depend on both nearby neighbors and far-away context; therefore, a more powerful multi-scale feature fusion network plays a critical role.…
School of Remote Sensing and Information Engineering, Wuhan University（武汉大学遥感信息工程学院）
Generating non-existing frames from a consecutive video sequence has been an interesting and challenging problem in the video processing field. Typical kernel-based interpolation methods predict pixels with a single convolution process that convolves source frames with spatially adaptive local kernels, which circumvents the time-consuming, explicit motion estimation in the form of optical flow. However, when scene motion is larger than the pre-defined kernel size, these methods are prone to yield less plausible results. In addition, they cannot directly generate a frame at an arbitrary tempora…
This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods suffer from loss of spatial resolution in the estimated depth maps; a typical symptom is distorted and blurry reconstruction of object boundaries. In this paper, toward more accurate estimation with a focus on depth maps with higher spatial resolution, we propose two improvements to existing approaches. One is about the strategy of fusing features extracted at…
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Nanyang Technological University（南洋理工大学）
Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect. However, the large variety of user flavors motivates the possibility of continuous transition among different output effects. Unlike existing methods that require a specific design to achieve one particular transition (e.g., style transfer), we propose a simple yet universal approach to attain a smooth control of diverse imagery effects in many low-level vision tasks, including image restoration, image-to-image translation, and style transfer. Specifically, our …
DTC: A Deformable Transposed Convolution Module for Medical Image Segmentation
Department of Health Outcomes and Biomedical Informatics, University of Florida（健康结果与生物医学信息学系，佛罗里达大学）；Regenstrief Institue, Indiana University, IU Health（Regenstrief研究所，印第安纳大学，IU健康）
Video frame interpolation (VFI) is a fundamental vision task that aims to synthesize several frames between two consecutive original video images. Most algorithms aim to accomplish VFI by using only keyframes, which is an ill-posed problem since the keyframes usually do not yield any accurate precision about the trajectories of the objects in the scene. On the other hand, event-based cameras provide more precise information between the keyframes of a video. Some recent state-of-the-art event-based methods approach this problem by utilizing event data for better optical flow estimation to inter…
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we propose a Transformer-based video interpolation framework that allows content-aware aggregation weights and considers long-range dependencies with the self-attention operations. To avoid the high computational cost of global self-attention, we introduce the concept of local attention into video interpolation and extend it to the spatial-temporal domain. Fur…
Frame interpolation attempts to synthesise frames given one or more consecutive video frames. In recent years, deep learning approaches, and notably convolutional neural networks, have succeeded at tackling low- and high-level computer vision problems including frame interpolation. These techniques often tackle two problems, namely algorithm efficiency and reconstruction quality. In this paper, we present a multi-scale generative adversarial network for frame interpolation (\mbox{FIGAN}). To maximise the efficiency of our network, we propose a novel multi-scale residual estimation module where…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Shenzhen Technology University（深圳技术大学）
Video frame interpolation task has recently become more and more prevalent in the computer vision field. At present, a number of researches based on deep learning have achieved great success. Most of them are either based on optical flow information, or interpolation kernel, or a combination of these two methods. However, these methods have ignored that there are grid restrictions on the position of kernel region during synthesizing each target pixel. These limitations result in that they cannot well adapt to the irregularity of object shape and uncertainty of motion, which may lead to irrelev…
We propose a computationally efficient architecture that learns to segment lesions from CT images of the liver. The proposed architecture uses bilinear interpolation with sub-pixel convolution at the last layer to upscale the course feature in bottle neck architecture. Since bilinear interpolation and sub-pixel convolution do not have any learnable parameter, our overall model is faster and occupies less memory footprint than the traditional U-net. We evaluate our proposed architecture on the highly competitive dataset of 2017 Liver Tumor Segmentation (LiTS) Challenge. Our method achieves comp…
Department of Computer Science, Texas State University, USA（德克萨斯州立大学计算机科学系，美国（注：原机构名中Department of Computer Science属于系级别，按要求提取到大学级别，即Texas State University，美国德克萨斯州立大学））
Nowadays 360 video analysis has become a significant research topic in the field since the appearance of high-quality and low-cost 360 wearable devices. In this paper, we propose a novel LiteFlowNet360 architecture for 360 videos optical flow estimation. We design LiteFlowNet360 as a domain adaptation framework from perspective video domain to 360 video domain. We adapt it from simple kernel transformation techniques inspired by Kernel Transformer Network (KTN) to cope with inherent distortion in 360 videos caused by the sphere-to-plane projection. First, we apply an incremental transformation…
Cornell University（康奈尔大学）；George Washington University（乔治华盛顿大学）
We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolution image transformation. As the name suggests, it relies only on simple linear interpolation of deep convolutional features from pre-trained convnets. We show that despite its simplicity, DFI can perform high-level semantic transformations like "make older/younger", "make bespectacled", "add smile", among others, surprisingly well - sometimes even matching or outperforming the state-of-the-art. This is particularly unexpected as DFI requires no specialized network architecture or even any deep ne…
Revisiting Direct Encoding: Learnable Temporal Dynamics for Static Image Spiking Neural Networks
School of Computer and Information Engineering, Henan University（河南大学计算机与信息工程学院）；Henan Key Laboratory of Big Data Analysis and Processing, Henan University（河南大学大数据分析与处理重点实验室）
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Video frame interpolation aims to synthesize one or multiple frames between two consecutive frames in a video. It has a wide range of applications including slow-motion video generation, frame-rate up-scaling and developing video codecs. Some older works tackled this problem by assuming per-pixel linear motion between video frames. However, objects often follow a non-linear motion pattern in the real domain and some recent methods attempt to model per-pixel motion by non-linear models (e.g., quadratic). A quadratic model can also be inaccurate, especially in the case of motion discontinuities …
Deep Neural Networks are increasingly used in video frame interpolation tasks such as frame rate changes as well as generating fake face videos. Our project aims to apply recent advances in Deep video interpolation to increase the temporal resolution of fluorescent microscopy time-lapse movies. To our knowledge, there is no previous work that uses Convolutional Neural Networks (CNN) to generate frames between two consecutive microscopy images. We propose a fully convolutional autoencoder network that takes as input two images and generates upto seven intermediate images. Our architecture has t…
Univ Rennes（雷恩大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；IRISA（信息与自动化研究所（IRISA））；Key Laboratory of Machine Perception, Cooperative Medianet Innovation Center, Peking University（北京大学机器感知重点实验室、协同媒体网络创新中心）；Department of Control Science and Engineering, Tongji University（同济大学控制科学与工程系）
Crowd counting is the task of estimating people numbers in crowd images. Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions. A major challenge of this task lies in the perspective distortion, which results in drastic person scale change in an image. Density regression on the small person area is in general very hard. In this work, we propose a perspective-aware convolutional neural network (PACNN) for efficient crowd counting, which integrates the perspective information into density regression to provide additional knowledge of the…
Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University（上海交通大学图像通信与网络工程研究所）；University of California, Merced（加州大学默塞德分校）；AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院）；Google（谷歌）
Video frame interpolation aims to synthesize nonexistent frames in-between the original frames. While significant advances have been made from the recent deep convolutional neural networks, the quality of interpolation is often reduced due to large object motion or occlusion. In this work, we propose a video frame interpolation method which explicitly detects the occlusion by exploring the depth information. Specifically, we develop a depth-aware flow projection layer to synthesize intermediate flows that preferably sample closer objects than farther ones. In addition, we learn hierarchical fe…
We propose the first deep learning solution to video frame inpainting, a challenging instance of the general video inpainting problem with applications in video editing, manipulation, and forensics. Our task is less ambiguous than frame interpolation and video prediction because we have access to both the temporal context and a partial glimpse of the future, allowing us to better evaluate the quality of a model's predictions objectively. We devise a pipeline composed of two modules: a bidirectional video prediction module, and a temporally-aware frame interpolation module. The prediction modul…
A majority of methods for video frame interpolation compute bidirectional optical flow between adjacent frames of a video, followed by a suitable warping algorithm to generate the output frames. However, approaches relying on optical flow often fail to model occlusions and complex non-linear motions directly from the video and introduce additional bottlenecks unsuitable for widespread deployment. We address these limitations with FLAVR, a flexible and efficient architecture that uses 3D space-time convolutions to enable end-to-end learning and inference for video frame interpolation. Our metho…
Shanghai Jiao Tong University（上海交通大学）；University of California, Merced（加州大学默塞德分校）
Motion estimation (ME) and motion compensation (MC) have been widely used for classical video frame interpolation systems over the past decades. Recently, a number of data-driven frame interpolation methods based on convolutional neural networks have been proposed. However, existing learning based methods typically estimate either flow or compensation kernels, thereby limiting performance on both computational efficiency and interpolation accuracy. In this work, we propose a motion estimation and compensation driven neural network for video frame interpolation. A novel adaptive warping layer i…
Supersampling Stable Diffusion and Beyond: A Seamless, Training-Free Approach for Scaling Neural Networks Using Common Interpolation Methods
School of Data and Sciences BRAC University, Dhaka（数据与科学学院，布拉克大学，达卡）；Computing for Sustainability and Social Good (C2SG) Research Group Department of Computer Science and Engineering United Internation University, Dhaka（可持续性与社会公益（C2SG）研究组，计算机科学与工程系，联合国际大学，达卡）
Inter prediction is an important module in video coding for temporal redundancy removal, where similar reference blocks are searched from previously coded frames and employed to predict the block to be coded. Although traditional video codecs can estimate and compensate for block-level motions, their inter prediction performance is still heavily affected by the remaining inconsistent pixel-wise displacement caused by irregular rotation and deformation. In this paper, we address the problem by proposing a deep frame interpolation network to generate additional reference frames in coding scenari…
