Optical flow estimation is an essential task in self-driving systems, which helps autonomous vehicles perceive temporal continuity information of surrounding scenes. The calculation of all-pair correlation plays an important role in many existing state-of-the-art optical flow estimation methods. However, the reliance on local knowledge often limits the model's accuracy under complex street scenes. In this paper, we propose a new deep network architecture for optical flow estimation in autonomous driving--CSFlow, which consists of two novel modules: Cross Strip Correlation module (CSC) and Correlation Regression Initialization module (CRI). CSC utilizes a striping operation across the target image and the attended image to encode global context into correlation volumes, while maintaining high efficiency. CRI is used to maximally exploit the global context for optical flow initialization. Our method has achieved state-of-the-art accuracy on the public autonomous driving dataset KITTI-2015. Code is publicly available at https://github.com/MasterHow/CSFlow.
Accurate object rearrangement from vision is a crucial problem for a wide variety of real-world robotics applications in unstructured environments. We propose IFOR, Iterative Flow Minimization for Robotic Object Rearrangement, an end-to-end method for the challenging problem of object rearrangement for unknown objects given an RGBD image of the original and final scenes. First, we learn an optical flow model based on RAFT to estimate the relative transformation of the objects purely from synthetic data. This flow is then used in an iterative minimization algorithm to achieve accurate positioning of previously unseen objects. Crucially, we show that our method applies to cluttered scenes, and in the real world, while training only on synthetic data. Videos are available at https://imankgoyal.github.io/ifor.html.
The performance of ultrasound elastography (USE) heavily depends on the accuracy of displacement estimation. Recently, Convolutional Neural Networks (CNN) have shown promising performance in optical flow estimation and have been adopted for USE displacement estimation. Networks trained on computer vision images are not optimized for USE displacement estimation since there is a large gap between the computer vision images and the high-frequency Radio Frequency (RF) ultrasound data. Many researchers tried to adopt the optical flow CNNs to USE by applying transfer learning to improve the performance of CNNs for USE. However, the ground truth displacement in real ultrasound data is unknown, and simulated data exhibits a domain shift compared to the real data and is also computationally expensive to generate. To resolve this issue, semi-supervised methods have been proposed wherein the networks pre-trained on computer vision images are fine-tuned using real ultrasound data. In this paper, we employ a semi-supervised method by exploiting the first and second-order derivatives of the displacement field for the regularization. We also modify the network structure to estimate both forward and backward displacements, and propose to use consistency between the forward and backward strains as an additional regularizer to further enhance the performance. We validate our method using several experimental phantom and in vivo data. We also show that the network fine-tuned by our proposed method using experimental phantom data performs well on in vivo data similar to the network fine-tuned on in vivo data. Our results also show that the proposed method outperforms current deep learning methods and is comparable to computationally expensive optimization-based algorithms.
Event-based cameras can overpass frame-based cameras limitations for important tasks such as high-speed motion detection during self-driving cars navigation in low illumination conditions. The event cameras' high temporal resolution and high dynamic range, allow them to work in fast motion and extreme light scenarios. However, conventional computer vision methods, such as Deep Neural Networks, are not well adapted to work with event data as they are asynchronous and discrete. Moreover, the traditional 2D-encoding representation methods for event data, sacrifice the time resolution. In this paper, we first improve the 2D-encoding representation by expanding it into three dimensions to better preserve the temporal distribution of the events. We then propose 3D-FlowNet, a novel network architecture that can process the 3D input representation and output optical flow estimations according to the new encoding methods. A self-supervised training strategy is adopted to compensate the lack of labeled datasets for the event-based camera. Finally, the proposed network is trained and evaluated with the Multi-Vehicle Stereo Event Camera (MVSEC) dataset. The results show that our 3D-FlowNet outperforms state-of-the-art approaches with less training epoch (30 compared to 100 of Spike-FlowNet).
Applying an image processing algorithm independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our method is only trained on a pair of original and processed videos directly instead of a large dataset. Unlike most previous methods that enforce temporal consistency with optical flow, we show that temporal consistency can be achieved by training a convolutional neural network on a video with Deep Video Prior (DVP). Moreover, a carefully designed iteratively reweighted training strategy is proposed to address the challenging multimodal inconsistency problem. We demonstrate the effectiveness of our approach on 7 computer vision tasks on videos. Extensive quantitative and perceptual experiments show that our approach obtains superior performance than state-of-the-art methods on blind video temporal consistency. We further extend DVP to video propagation and demonstrate its effectiveness in propagating three different types of information (color, artistic style, and object segmentation). A progressive propagation strategy with pseudo labels is also proposed to enhance DVP's performance on video propagation. Our source codes are publicly available at https://github.com/ChenyangLEI/deep-video-prior.
We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost. Existing approaches focus on modifying the architecture of 2D networks (e.g. by including filters in the temporal dimension to turn them into 3D networks, or using optical flow, etc.), which increases computation cost. Instead, we propose a novel sampling strategy, where we re-order the channels of the input video, to capture short-term frame-to-frame changes. We observe that without bells and whistles, the proposed sampling strategy improves performance on multiple architectures (e.g. TSN, TRN, TSM, and MVFNet) and datasets (CATER, Something-Something-V1 and V2), up to 24% over the baseline of using the standard video input. In addition, our sampling strategies do not require training from scratch and do not increase the computational cost of training and testing. Given the generality of the results and the flexibility of the approach, we hope this can be widely useful to the video understanding community. Code is available on our website: https://github.com/kiyoon/channel_sampling.
Traditional media coding schemes typically encode image/video into a semantic-unknown binary stream, which fails to directly support downstream intelligent tasks at the bitstream level. Semantically Structured Image Coding (SSIC) framework makes the first attempt to enable decoding-free or partial-decoding image intelligent task analysis via a Semantically Structured Bitstream (SSB). However, the SSIC only considers image coding and its generated SSB only contains the static object information. In this paper, we extend the idea of semantically structured coding from video coding perspective and propose an advanced Semantically Structured Video Coding (SSVC) framework to support heterogeneous intelligent applications. Video signals contain more rich dynamic motion information and exist more redundancy due to the similarity between adjacent frames. Thus, we present a reformulation of semantically structured bitstream (SSB) in SSVC which contains both static object characteristics and dynamic motion clues. Specifically, we introduce optical flow to encode continuous motion information and reduce cross-frame redundancy via a predictive coding architecture, then the optical flow and residual information are reorganized into SSB, which enables the proposed SSVC could better adaptively support video-based downstream intelligent applications. Extensive experiments demonstrate that the proposed SSVC framework could directly support multiple intelligent tasks just depending on a partially decoded bitstream. This avoids the full bitstream decompression and thus significantly saves bitrate/bandwidth consumption for intelligent analytics. We verify this point on the tasks of image object detection, pose estimation, video action recognition, video object segmentation, etc.
Frame interpolation is an essential video processing technique that adjusts the temporal resolution of an image sequence. While deep learning has brought great improvements to the area of video frame interpolation, techniques that make use of neural networks can typically not easily be deployed in practical applications like a video editor since they are either computationally too demanding or fail at high resolutions. In contrast, we propose a deep learning approach that solely relies on splatting to synthesize interpolated frames. This splatting-based synthesis for video frame interpolation is not only much faster than similar approaches, especially for multi-frame interpolation, but can also yield new state-of-the-art results at high resolutions.
In this paper, we present a parallel architecture for a sensor fusion detection system that combines a camera and 1D light detection and ranging (lidar) sensor for object detection. The system contains two object detection methods, one based on an optical flow, and the other using lidar. The two sensors can effectively complement the defects of the other. The accurate longitudinal accuracy of the object's location and its lateral movement information can be achieved simultaneously. Using a spatio-temporal alignment and a policy of sensor fusion, we completed the development of a fusion detection system with high reliability at distances of up to 20 m. Test results show that the proposed system achieves a high level of accuracy for pedestrian or object detection in front of a vehicle, and has high robustness to special environments.
A range of video modeling tasks, from optical flow to multiple object tracking, share the same fundamental challenge: establishing space-time correspondence. Yet, approaches that dominate each space differ. We take a step towards bridging this gap by extending the recent contrastive random walk formulation to much denser, pixel-level space-time graphs. The main contribution is introducing hierarchy into the search problem by computing the transition matrix between two frames in a coarse-to-fine manner, forming a multiscale contrastive random walk when extended in time. This establishes a unified technique for self-supervised learning of optical flow, keypoint tracking, and video object segmentation. Experiments demonstrate that, for each of these tasks, the unified model achieves performance competitive with strong self-supervised approaches specific to that task. Project webpage: https://jasonbian97.github.io/flowwalk
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.
Unpaired video-to-video translation aims to translate videos between a source and a target domain without the need of paired training data, making it more feasible for real applications. Unfortunately, the translated videos generally suffer from temporal and semantic inconsistency. To address this, many existing works adopt spatiotemporal consistency constraints incorporating temporal information based on motion estimation. However, the inaccuracies in the estimation of motion deteriorate the quality of the guidance towards spatiotemporal consistency, which leads to unstable translation. In this work, we propose a novel paradigm that regularizes the spatiotemporal consistency by synthesizing motions in input videos with the generated optical flow instead of estimating them. Therefore, the synthetic motion can be applied in the regularization paradigm to keep motions consistent across domains without the risk of errors in motion estimation. Thereafter, we utilize our unsupervised recycle and unsupervised spatial loss, guided by the pseudo-supervision provided by the synthetic optical flow, to accurately enforce spatiotemporal consistency in both domains. Experiments show that our method is versatile in various scenarios and achieves state-of-the-art performance in generating temporally and semantically consistent videos. Code is available at: https://github.com/wangkaihong/Unsup_Recycle_GAN/.
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, the first end-to-end video object detection system based on spatial-temporal Transformer architectures. The first goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow model, relation networks. Besides, benefited from the object query design in DETR, our method does not need complicated post-processing methods such as Seq-NMS. In particular, we present a temporal Transformer to aggregate both the spatial object queries and the feature memories of each frame. Our temporal transformer consists of two components: Temporal Query Encoder (TQE) to fuse object queries, and Temporal Deformable Transformer Decoder (TDTD) to obtain current frame detection results. These designs boost the strong baseline deformable DETR by a significant margin (3%-4% mAP) on the ImageNet VID dataset. Then, we present two improved versions of TransVOD including TransVOD++ and TransVOD Lite. The former fuses object-level information into object query via dynamic convolution while the latter models the entire video clips as the output to speed up the inference time. We give detailed analysis of all three models in the experiment part. In particular, our proposed TransVOD++ sets a new state-of-the-art record in terms of accuracy on ImageNet VID with 90.0% mAP. Our proposed TransVOD Lite also achieves the best speed and accuracy trade-off with 83.7% mAP while running at around 30 FPS on a single V100 GPU device.
Motion, as the most distinct phenomenon in a video to involve the changes over time, has been unique and critical to the development of video representation learning. In this paper, we ask the question: how important is the motion particularly for self-supervised video representation learning. To this end, we compose a duet of exploiting the motion for data augmentation and feature learning in the regime of contrastive learning. Specifically, we present a Motion-focused Contrastive Learning (MCL) method that regards such duet as the foundation. On one hand, MCL capitalizes on optical flow of each frame in a video to temporally and spatially sample the tubelets (i.e., sequences of associated frame patches across time) as data augmentations. On the other hand, MCL further aligns gradient maps of the convolutional layers to optical flow maps from spatial, temporal and spatio-temporal perspectives, in order to ground motion information in feature learning. Extensive experiments conducted on R(2+1)D backbone demonstrate the effectiveness of our MCL. On UCF101, the linear classifier trained on the representations learnt by MCL achieves 81.91% top-1 accuracy, outperforming ImageNet supervised pre-training by 6.78%. On Kinetics-400, MCL achieves 66.62% top-1 accuracy under the linear protocol. Code is available at https://github.com/YihengZhang-CV/MCL-Motion-Focused-Contrastive-Learning.
In this paper, we present a CNN-based fully unsupervised method for motion segmentation from optical flow. We assume that the input optical flow can be represented as a piecewise set of parametric motion models, typically, affine or quadratic motion models. The core idea of our work is to leverage the Expectation-Maximization (EM) framework in order to design in a well-founded manner a loss function and a training procedure of our motion segmentation neural network that does not require either ground-truth or manual annotation. However, in contrast to the classical iterative EM, once the network is trained, we can provide a segmentation for any unseen optical flow field in a single inference step and without estimating any motion models. We investigate different loss functions including robust ones and propose a novel efficient data augmentation technique on the optical flow field, applicable to any network taking optical flow as input. In addition, our method is able by design to segment multiple motions. Our motion segmentation network was tested on four benchmarks, DAVIS2016, SegTrackV2, FBMS59, and MoCA, and performed very well, while being fast at test time.
Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range dependencies and modeling non-local self-similarity. In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring. In FGST, we customize a self-attention module, Flow-Guided Sparse Window-based Multi-head Self-Attention (FGSW-MSA). For each $query$ element on the blurry reference frame, FGSW-MSA enjoys the guidance of the estimated optical flow to globally sample spatially sparse yet highly related $key$ elements corresponding to the same scene patch in neighboring frames. Besides, we present a Recurrent Embedding (RE) mechanism to transfer information from past frames and strengthen long-range temporal dependencies. Comprehensive experiments demonstrate that our proposed FGST outperforms state-of-the-art (SOTA) methods on both DVD and GOPRO datasets and even yields more visually pleasing results in real video deblurring. Code and pre-trained models are publicly available at https://github.com/linjing7/VR-Baseline
Group activity recognition has received a great deal of interest because of its broader applications in sports analysis, autonomous vehicles, CCTV surveillance systems and video summarization systems. Most existing methods typically use appearance features and they seldom consider underlying interaction information. In this work, a technology of novel group activity recognition is proposed based on multi-modal relation representation with temporal-spatial attention. First, we introduce an object relation module, which processes all objects in a scene simultaneously through an interaction between their appearance feature and geometry, thus allowing the modeling of their relations. Second, to extract effective motion features, an optical flow network is fine-tuned by using the action loss as the supervised signal. Then, we propose two types of inference models, opt-GRU and relation-GRU, which are used to encode the object relationship and motion representation effectively, and form the discriminative frame-level feature representation. Finally, an attention-based temporal aggregation layer is proposed to integrate frame-level features with different weights and form effective video-level representations. We have performed extensive experiments on two popular datasets, and both have achieved state-of-the-art performance. The datasets are the Volleyball dataset and the Collective Activity dataset, respectively
Antennas are taking design shapes by the orientation of its material and the final structural design they take. Irrespective of the shape, the function and efficiency they produce does not change and vary to much extent. We are trying to simulate a design of antenna which is using the artificial intelligence model to Specific absorption rate minimization. We have successfully used antenna magus and CST suite to produce our improved simulation results. Motion models such as optical flow is used to smartly detect communicating devices inorder to connect and link the devices. The algorithm used by us is closest neighbour algorithm which is connected with antenna to apply it in object detection of mobile devices and antennas. We are trying to have a six second break in which the antenna will operate at minimum frequency but at the same time operating in its functioning. After every six seconds the antenna will radiate its frequency of vibration to detect if there is any new object or mobile device in sight.
Neural video codecs have demonstrated great potential in video transmission and storage applications. Existing neural hybrid video coding approaches rely on optical flow or Gaussian-scale flow for prediction, which cannot support fine-grained adaptation to diverse motion content. Towards more content-adaptive prediction, we propose a novel cross-scale prediction module that achieves more effective motion compensation. Specifically, on the one hand, we produce a reference feature pyramid as prediction sources and then transmit cross-scale flows that leverage the feature scale to control the precision of prediction. On the other hand, for the first time, a weighted prediction mechanism is introduced even if only a single reference frame is available, which can help synthesize a fine prediction result by transmitting cross-scale weight maps. In addition to the cross-scale prediction module, we further propose a multi-stage quantization strategy, which improves the rate-distortion performance with no extra computational penalty during inference. We show the encouraging performance of our efficient neural video codec (ENVC) on several benchmark datasets. In particular, the proposed ENVC can compete with the latest coding standard H.266/VVC in terms of sRGB PSNR on UVG dataset for the low-latency mode. We also analyze in detail the effectiveness of the cross-scale prediction module in handling various video content, and provide a comprehensive ablation study to analyze those important components. Test code is available at https://github.com/USTC-IMCL/ENVC .
Omnidirectional 360{\deg} images have found many promising and exciting applications in computer vision, robotics and other fields, thanks to their increasing affordability, portability and their 360{\deg} field of view. The most common format for storing, processing and visualising 360{\deg} images is equirectangular projection (ERP). However, the distortion introduced by the nonlinear mapping from 360{\deg} image to ERP image is still a barrier that holds back ERP images from being used as easily as conventional perspective images. This is especially relevant when estimating 360{\deg} optical flow, as the distortions need to be mitigated appropriately. In this paper, we propose a 360{\deg} optical flow method based on tangent images. Our method leverages gnomonic projection to locally convert ERP images to perspective images, and uniformly samples the ERP image by projection to a cubemap and regular icosahedron vertices, to incrementally refine the estimated 360{\deg} flow fields even in the presence of large rotations. Our experiments demonstrate the benefits of our proposed method both quantitatively and qualitatively.