This paper proposes a learning-based video codec, specifically used for Challenge on Learned Image Compression (CLIC, CVPRWorkshop) 2020 P-frame coding. More specifically, we designed a compressor network with Refine-Net for coding residual signals and motion vectors. Also, for motion estimation, we introduced a hierarchical, attention-based ME-Net. To verify our design, we conducted an extensive ablation study on our modules and different input formats. Our video codec demonstrates its performance by using the perfect reference frame at the decoder side specified by the CLIC P-frame Challenge. The experimental result shows that our proposed codec is very competitive with the Challenge top performers in terms of quality metrics.
Temporal consistency is crucial for extending image processing pipelines to the video domain, which is often enforced with flow-based warping error over adjacent frames. Yet for human video synthesis, such scheme is less reliable due to the misalignment between source and target video as well as the difficulty in accurate flow estimation. In this paper, we propose an effective intrinsic temporal regularization scheme to mitigate these issues, where an intrinsic confidence map is estimated via the frame generator to regulate motion estimation via temporal loss modulation. This creates a shortcut for back-propagating temporal loss gradients directly to the front-end motion estimator, thus improving training stability and temporal coherence in output videos. We apply our intrinsic temporal regulation to single-image generator, leading to a powerful "INTERnet" capable of generating $512\times512$ resolution human action videos with temporal-coherent, realistic visual details. Extensive experiments demonstrate the superiority of proposed INTERnet over several competitive baselines.
Optical colonoscopy is an essential diagnostic and prognostic tool for many gastrointestinal diseases, including cancer screening and staging, intestinal bleeding, diarrhea, abdominal symptom evaluation, and inflammatory bowel disease assessment. Automated assessment of colonoscopy is of interest considering the subjectivity present in qualitative human interpretations of colonoscopy findings. Localization of the camera is essential to interpreting the meaning and context of findings for diseases evaluated by colonoscopy. In this study, we propose a camera localization system to estimate the relative location of the camera and classify the colon into anatomical segments. The camera localization system begins with non-informative frame detection and removal. Then a self-training end-to-end convolutional neural network is built to estimate the camera motion, where several strategies are proposed to improve its robustness and generalization on endoscopic videos. Using the estimated camera motion a camera trajectory can be derived and a relative location index calculated. Based on the estimated location index, anatomical colon segment classification is performed by constructing a colon template. The proposed motion estimation algorithm was evaluated on an external dataset containing the ground truth for camera pose. The experimental results show that the performance of the proposed method is superior to other published methods. The relative location index estimation and anatomical region classification were further validated using colonoscopy videos collected from routine clinical practice. This validation yielded an average accuracy in classification of 0.754, which is substantially higher than the performances obtained using location indices built from other methods.
Due to the large amount of data that point clouds represent and the differences in geometry of successive frames, the generation of motion vectors for an entire point cloud dataset may require a significant amount of time and computational resources. With that in mind, we provide a 3D motion vector database for all frames of two popular dynamic point cloud datasets. The motion vectors were obtained through translational motion estimation procedure that partitions the point clouds into blocks of dimensions M x M x M , and for each block, a motion vector is estimated. Our database contains motion vectors for M = 8 and M = 16. The goal of this work is to describe this publicly available 3D motion vector database that can be used for different purposes, such as compression of dynamic point clouds.
Motion estimation is a key component of any modern video codec. Our understanding of motion and the estimation of motion from video has come a very long way since 2000. More than 135 different algorithms have been recently reviewed by Scharstein et al http://vision.middlebury.edu/flow/. These new algorithms differ markedly from Block Matching which has been the mainstay of video compression for some time. This paper presents comparisons of H.264 and MP4 compression using different motion estimation methods. In so doing we present as well methods for adapting pre-computed motion fields for use within a codec. We do not observe significant gains to be had with the methods chosen w.r.t. Rate Distortion tradeoffs but the results reflect a significantly more complex interrelationship between motion and compression than would be expected. There remains much more to be done to improve the coverage of this comparison to the emerging standards but these initial results show that there is value in these explorations.
In this paper, authors propose a new procedure to provide a tool for monitoring critical infrastructures. Particularly, through the analysis of COSMO-SkyMed satellite data, a detailed and updated survey is provided, for monitoring the accelerating destabilization process of the Mosul dam, that represents the largest hydraulic facility of Iraq and is located on the Tigris river. The destructive potential of the wave that would be generated, in the event of the dam destruction, could have serious consequences. If the concern for human lives comes first, the concern for cultural heritage protection is not negligible, since several archaeological sites are located around the Mosul dam. The proposed procedure is an in-depth modal assessment based on the micro-motion estimation, through a Doppler sub-apertures tracking and a Multi-Chromatic Analysis (MCA). The method is based initially on the Persistent Scatterers Interferometry (PSI) that is also discussed for completeness and validation. The modal analysis has detected the presence of several areas of resonance that could mean the presence of cracks, and the results have shown that the dam is still in a strong destabilization. Moreover, the dam appears to be divided into two parts: the northern part is accelerating rapidly while the southern part is decelerating and a main crack in this north-south junction is found. The estimated velocities through the PS-InSAR technique show a good agreement with the GNSS in-situ measurements, resulting in a very high correlation coefficient and showing how the proposed procedure works efficiently.
Inter-Prediction is used effectively in multiple standards, including H.264 and HEVC (also known as H.265). It leverages correlation between blocks of consecutive video frames in order to perform motion compensation and thus predict block pixel values and reduce transmission bandwidth. In order to reduce the magnitude of the transmitted Motion Vector (MV) and thus reduce bandwidth, the encoder utilizes Predicted Motion Vector (PMV), which is derived by taking the median vector of the corresponding MVs of the neighboring blocks. In this research, we propose innovative methods, based on neural networks prediction, for improving the accuracy of the calculated PMV. We begin by showing a straightforward approach of calculating the best matching PMV and signaling its neighbor block index value to the decoder while reducing the number of bits required to represent the result without adding any computation complexity. Then we use a classification Fully Connected Neural Networks (FCNN) to estimate from neighbors the PMV without requiring signaling and show the advantage of the approach when employed for high motion movies. We demonstrate the advantages using fast forward movies. However, the same improvements apply to camera streams of autonomous vehicles, drone cameras, Pan-Tilt-Zoom (PTZ) cameras, and similar applications whereas the MVs magnitudes are expected to be large. We also introduce a regression FCNN to predict the PMV. We calculate Huffman coded streams and demonstrate an order of ~34% reduction in number of bits required to transmit the best matching calculated PMV without reducing the quality, for fast forward movies with high motion.
We consider a synthetic aperture imaging configuration, such as synthetic aperture radar (SAR), where we want to first separate reflections from moving targets from those coming from a stationary background, and then to image separately the moving and the stationary reflectors. For this purpose, we introduce a representation of the data as a third order tensor formed from data coming from partially overlapping sub-apertures. We then apply a tensor robust principal component analysis (TRPCA) to the tensor data which separates them into the parts coming from the stationary and moving reflectors. Images are formed with the separated data sets. Our analysis shows a distinctly improved performance of TRPCA, compared to the usual matrix case. In particular, the tensor decomposition can identify motion features that are undetectable when using the conventional motion estimation methods, including matrix RPCA. We illustrate the performance of the method with numerical simulations in the X-band radar regime.
Motion estimation of organs in a sequence of images is important in numerous medical imaging applications. The focus of this paper is the analysis of 4D Respiratory Correlated Computed Tomography (RCCT) Imaging. It is hypothesized that the quasi-periodic breathing induced motion of organs in the thorax can be represented by deformations spanning a very low dimension subspace of the full infinite dimensional space of diffeomorphic transformations. This paper presents a novel motion estimation algorithm that includes the constraint for low-rank motion between the different phases of the RCCT images. Low-rank deformation solutions are necessary for the efficient statistical analysis and improved treatment planning and delivery. Although the application focus of this paper is RCCT the algorithm is quite general and applicable to various motion estimation problems in medical imaging.
Many organisms, from flies to humans, use visual signals to estimate their motion through the world. To explore the motion estimation problem, we have constructed a camera/gyroscope system that allows us to sample, at high temporal resolution, the joint distribution of input images and rotational motions during a long walk in the woods. From these data we construct the optimal estimator of velocity based on spatial and temporal derivatives of image intensity in small patches of the visual world. Over the bulk of the naturally occurring dynamic range, the optimal estimator exhibits the same systematic errors seen in neural and behavioral responses, including the confounding of velocity and contrast. These results suggest that apparent errors of sensory processing may reflect an optimal response to the physical signals in the environment.
In garment manufacturing, an automatic sewing machine is desirable to reduce cost. To accomplish this, a high speed vision system is required to track fabric motions and recognize repetitive weave patterns with high accuracy, from a micro perspective near a sewing zone. In this paper, we present an innovative framework for real-time texture tracking and weave pattern recognition. Our framework includes a module for motion estimation using blob detection and feature matching. It also includes a module for lattice detection to facilitate the weave pattern recognition. Our lattice detection algorithm utilizes blob detection and template matching to assess pair-wise similarity in blobs' appearance. In addition, it extracts information of dominant orientations to obtain a global constraint in the topology. By incorporating both constraints in the appearance similarity and the global topology, the algorithm determines a lattice that characterizes the topological structure of the repetitive weave pattern, thus allowing for thread counting. In our experiments, the proposed thread-based texture tracking system is capable of tracking denim fabric with high accuracy (e.g., 0.03 degree rotation and 0.02 weave-thread' translation errors) and high speed (3 frames per second), demonstrating its high potential for automatic real-time textile manufacturing.
Perceptual video quality assessment models are either frame-based or video-based, i.e., they apply spatiotemporal filtering or motion estimation to capture temporal video distortions. Despite their good performance on video quality databases, video-based approaches are time-consuming and harder to efficiently deploy. To balance between high performance and computational efficiency, Netflix developed the Video Multi-method Assessment Fusion (VMAF) framework, which integrates multiple quality-aware features to predict video quality. Nevertheless, this fusion framework does not fully exploit temporal video quality measurements which are relevant to temporal video distortions. To this end, we propose two improvements to the VMAF framework: SpatioTemporal VMAF and Ensemble VMAF. Both algorithms exploit efficient temporal video features which are fed into a single or multiple regression models. To train our models, we designed a large subjective database and evaluated the proposed models against state-of-the-art approaches. The compared algorithms will be made available as part of the open source package in https://github.com/Netflix/vmaf.
In the popular video coding trend, the encoder has the task to exploit both spatial and temporal redundancies present in the video sequence, which is a complex procedure. As a result almost all video encoders have five to ten times more complexity than their decoders. In a video compression process, one of the main tasks at the encoder side is motion estimation which is to extract the temporal correlation between frames. Distributed video coding (DVC) proposed the idea that can lead to low complexity encoders and higher complexity decoders. DVC is a new paradigm in video compression based on the information theoretic ideas of Slepian-Wolf and Wyner-Ziv theorems. Wyner-Ziv coding is naturally robust against transmission errors and can be used for joint source and channel coding. Side Information is one of the key components of the Wyner-Ziv decoder. Better side information generation will result in better functionality of Wyner-Ziv coder. In this paper we proposed a new method that can generate side information with a better quality and thus better compression. We have used HVS (human visual system) based image quality metrics as our quality criterion. The motion estimation we used in the decoder is modified due to these metrics such that we could obtain finer side information. The motion compensation is optimized for perceptual quality metrics and leads to better side information generation compared to con- ventional MSE (mean squared error) or SAD (sum of absolute difference) based motion compensation currently used in the literature. Better motion compensation means better compression.
Motion estimation is one of the important procedures in the all video encoders. Most of the complexity of the video coder depends on the complexity of the motion estimation step. The original motion estimation algorithm has a remarkable complexity and therefore many improvements were proposed to enhance the crude version of the motion estimation. The basic idea of many of these works were to optimize some distortion function for mean squared error (MSE) or sum of absolute difference (SAD) in block matching But it is shown that these metrics do not conclude the quality as it is, on the other hand, they are not compatible with the human visual system (HVS). In this paper we explored the usage of the image quality metrics in the video coding and more specific in the motion estimation. We have utilized the perceptual image quality metrics instead of MSE or SAD in the block based motion estimation. Three different metrics have used: structural similarity or SSIM, complex wavelet structural similarity or CW-SSIM, visual information fidelity or VIF. Experimental results showed that usage of the quality criterions can improve the compression rate while the quality remains fix and thus better quality in coded video at the same bit budget.
We propose a variational model with diffeomorphic optimal transportation for joint image reconstruction and motion estimation. The proposed model is a production of assembling the Wasserstein distance with the Benamou--Brenier formula in optimal transportation and the flow of diffeomorphisms involved in large deformation diffeomorphic metric mapping, which is suitable for the scenario of spatiotemporal imaging with large diffeomorphic and mass-preserving deformations. Specifically, we first use the Benamou--Brenier formula to characterize the optimal transport cost among the flow of mass-preserving images, and restrict the velocity field into the admissible Hilbert space to guarantee the generated deformation flow being diffeomorphic. We then gain the ODE-constrained equivalent formulation for Benamou--Brenier formula. We finally obtain the proposed model with ODE constraint following the framework that presented in our previous work. We further get the equivalent PDE-constrained optimal control formulation. The proposed model is compared against several existing alternatives theoretically. The alternating minimization algorithm is presented for solving the time-discretized version of the proposed model with ODE constraint. Several important issues on the proposed model and associated algorithms are also discussed. Particularly, we present several potential models based on the proposed diffeomorphic optimal transportation. Under appropriate conditions, the proposed algorithm also provides a new scheme to solve the models using quadratic Wasserstein distance. The performance is finally evaluated by several numerical experiments in space-time tomography, where the data is measured from the concerned sequential images with sparse views and/or various noise levels.
Physics-based optical flow models have been successful in capturing the deformities in fluid motion arising from digital imagery. However, a common theoretical framework analyzing several physics-based models is missing. In this regard, we formulate a general framework for fluid motion estimation using a constraint-based refinement approach. We demonstrate that for a particular choice of constraint, our results closely approximate the classical continuity equation-based method for fluid flow. This closeness is theoretically justified by augmented Lagrangian method in a novel way. The convergence of Uzawa iterates is shown using a modified bounded constraint algorithm. The mathematical wellposedness is studied in a Hilbert space setting. Further, we observe a surprising connection to the Cauchy-Riemann operator that diagonalizes the system leading to a diffusive phenomenon involving the divergence and the curl of the flow. Several numerical experiments are performed and the results are shown on different datasets. Additionally, we demonstrate that a flow-driven refinement process involving the curl of the flow outperforms the classical physics-based optical flow method without any additional assumptions on the image data.
Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion estimation modules due to the lack of a dataset containing pairs of videos with similar perspective but different motion. Therefore, the deep learning approaches for this task have difficulties in the pixel-level synthesis of latent stabilized frames, and resort to motion estimation modules for indirect transformations of the unstable frames to stabilized frames, leading to the loss of visual content near the frame boundaries. In this work, we aim to declutter this over-complicated formulation of video stabilization with the help of a novel dataset that contains pairs of training videos with similar perspective but different motion, and verify its effectiveness by successfully learning motion blind full-frame video stabilization through employing strictly conventional generative techniques and further improve the stability through a curriculum-learning inspired adversarial training strategy. Through extensive experimentation, we show the quantitative and qualitative advantages of the proposed approach to the state-of-the-art video stabilization approaches. Moreover, our method achieves $\sim3\times$ speed-up over the currently available fastest video stabilization methods.
Sequence-based place recognition methods for all-weather navigation are well-known for producing state-of-the-art results under challenging day-night or summer-winter transitions. These systems, however, rely on complex handcrafted heuristics for sequential matching - which are applied on top of a pre-computed pairwise similarity matrix between reference and query image sequences of a single route - to further reduce false-positive rates compared to single-frame retrieval methods. As a result, performing multi-frame place recognition can be extremely slow for deployment on autonomous vehicles or evaluation on large datasets, and fail when using relatively short parameter values such as a sequence length of 2 frames. In this paper, we propose DeepSeqSLAM: a trainable CNN+RNN architecture for jointly learning visual and positional representations from a single monocular image sequence of a route. We demonstrate our approach on two large benchmark datasets, Nordland and Oxford RobotCar - recorded over 728 km and 10 km routes, respectively, each during 1 year with multiple seasons, weather, and lighting conditions. On Nordland, we compare our method to two state-of-the-art sequence-based methods across the entire route under summer-winter changes using a sequence length of 2 and show that our approach can get over 72% AUC compared to 27% AUC for Delta Descriptors and 2% AUC for SeqSLAM; while drastically reducing the deployment time from around 1 hour to 1 minute against both. The framework code and video are available at https://mchancan.github.io/deepseqslam
Visual inspection of solar modules is an important monitoring facility in photovoltaic power plants. Since a single measurement of fast CMOS sensors is limited in spatial resolution and often not sufficient to reliably detect small defects, we apply multi-frame super-resolution (MFSR) to a sequence of low resolution measurements. In addition, the rectification and removal of lens distortion simplifies subsequent analysis. Therefore, we propose to fuse this pre-processing with standard MFSR algorithms. This is advantageous, because we omit a separate processing step, the motion estimation becomes more stable and the spacing of high-resolution (HR) pixels on the rectified module image becomes uniform w. r. t. the module plane, regardless of perspective distortion. We present a comprehensive user study showing that MFSR is beneficial for defect recognition by human experts and that the proposed method performs better than the state of the art. Furthermore, we apply automated crack segmentation and show that the proposed method performs 3x better than bicubic upsampling and 2x better than the state of the art for automated inspection.
Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to the large (ego-) motion of objects. Our work proposes a novel data-driven approach for temporal fusion of scene flow estimates in a multi-frame setup to overcome the issue of occlusion. Contrary to most previous methods, we do not rely on a constant motion model, but instead learn a generic temporal relation of motion from data. In a second step, a neural network combines bi-directional scene flow estimates from a common reference frame, yielding a refined estimate and a natural byproduct of occlusion masks. This way, our approach provides a fast multi-frame extension for a variety of scene flow estimators, which outperforms the underlying dual-frame approaches.