PyTorchKR Papers

최신 논문

총 2,031편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2109.05509공식 코드 · Papers with Code

Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions

In the future, extraterrestrial expeditions will not only be conducted by rovers but also by flying robots. The technical demonstration drone Ingenuity, that just landed on Mars, will mark the beginning of a new era of exploration unhindered by terrain traversability. Robust self-localization is crucial for that. Cameras that are lightweight, cheap and information-rich sensors are already used to estimate the ego-motion of vehicles. However, methods proven to work in man-made environments cannot simply be deployed on other planets. The highly repetitive textures present in the wastelands of Mars pose a huge challenge to descriptor matching based approaches. In this paper, we present an advanced robust monocular odometry algorithm that uses efficient optical flow tracking to obtain feature correspondences between images and a refined keyframe selection criterion. In contrast to most other approaches, our framework can also handle rotation-only motions that are particularly challenging for monocular odometry systems. Furthermore, we present a novel approach to estimate the current risk of scale drift based on a principal component analysis of the relative translation information matrix. This way we obtain an implicit measure of uncertainty. We evaluate the validity of our approach on all sequences of a challenging real-world dataset captured in a Mars-like environment and show that it outperforms state-of-the-art approaches.

arXiv:2109.05457

What happens in Face during a facial expression? Using data mining techniques to analyze facial expression motion vectors

One of the most common problems encountered in human-computer interaction is automatic facial expression recognition. Although it is easy for human observer to recognize facial expressions, automatic recognition remains difficult for machines. One of the methods that machines can recognize facial expression is analyzing the changes in face during facial expression presentation. In this paper, optical flow algorithm was used to extract deformation or motion vectors created in the face because of facial expressions. Then, these extracted motion vectors are used to be analyzed. Their positions and directions were exploited for automatic facial expression recognition using different data mining techniques. It means that by employing motion vector features used as our data, facial expressions were recognized. Some of the most state-of-the-art classification algorithms such as C5.0, CRT, QUEST, CHAID, Deep Learning (DL), SVM and Discriminant algorithms were used to classify the extracted motion vectors. Using 10-fold cross validation, their performances were calculated. To compare their performance more precisely, the test was repeated 50 times. Meanwhile, the deformation of face was also analyzed in this research. For example, what exactly happened in each part of face when a person showed fear? Experimental results on Extended Cohen-Kanade (CK+) facial expression dataset demonstrated that the best methods were DL, SVM and C5.0, with the accuracy of 95.3%, 92.8% and 90.2% respectively.

arXiv:2109.05287공식 코드 · Papers with Code

Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network

Dual-view snapshot compressive imaging (SCI) aims to capture videos from two field-of-views (FoVs) using a 2D sensor (detector) in a single snapshot, achieving joint FoV and temporal compressive sensing, and thus enjoying the advantages of low-bandwidth, low-power, and low-cost. However, it is challenging for existing model-based decoding algorithms to reconstruct each individual scene, which usually require exhaustive parameter tuning with extremely long running time for large scale data. In this paper, we propose an optical flow-aided recurrent neural network for dual video SCI systems, which provides high-quality decoding in seconds. Firstly, we develop a diversity amplification method to enlarge the differences between scenes of two FoVs, and design a deep convolutional neural network with dual branches to separate different scenes from the single measurement. Secondly, we integrate the bidirectional optical flow extracted from adjacent frames with the recurrent neural network to jointly reconstruct each video in a sequential manner. Extensive results on both simulation and real data demonstrate the superior performance of our proposed model in a short inference time. The code and data are available at https://github.com/RuiyingLu/OFaNet-for-Dual-view-SCI.

arXiv:2109.04871공식 코드 · Papers with Code

Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation

Event camera has offered promising alternative for visual perception, especially in high speed and high dynamic range scenes. Recently, many deep learning methods have shown great success in providing promising solutions to many event-based problems, such as optical flow estimation. However, existing deep learning methods did not address the importance of temporal information well from the perspective of architecture design and cannot effectively extract spatio-temporal features. Another line of research that utilizes Spiking Neural Network suffers from training issues for deeper architecture.To address these points, a novel input representation is proposed that captures the events' temporal distribution for signal enhancement. Moreover, we introduce a spatio-temporal recurrent encoding-decoding neural network architecture for event-based optical flow estimation, which utilizes Convolutional Gated Recurrent Units to extract feature maps from a series of event images. Besides, our architecture allows some traditional frame-based core modules, such as correlation layer and iterative residual refine scheme, to be incorporated. The network is end-to-end trained with self-supervised learning on the Multi-Vehicle Stereo Event Camera dataset. We have shown that it outperforms all the existing state-of-the-art methods by a large margin. The code link is https://github.com/ruizhao26/STE-FlowNet.

arXiv:2109.04843

Temporally Coherent Person Matting Trained on Fake-Motion Dataset

We propose a novel neural-network-based method to perform matting of videos depicting people that does not require additional user input such as trimaps. Our architecture achieves temporal stability of the resulting alpha mattes by using motion-estimation-based smoothing of image-segmentation algorithm outputs, combined with convolutional-LSTM modules on U-Net skip connections. We also propose a fake-motion algorithm that generates training clips for the video-matting network given photos with ground-truth alpha mattes and background videos. We apply random motion to photos and their mattes to simulate movement one would find in real videos and composite the result with the background clips. It lets us train a deep neural network operating on videos in an absence of a large annotated video dataset and provides ground-truth training-clip foreground optical flow for use in loss functions.

arXiv:2109.04598

Automatic Portrait Video Matting via Context Motion Network

Automatic portrait video matting is an under-constrained problem. Most state-of-the-art methods only exploit the semantic information and process each frame individually. Their performance is compromised due to the lack of temporal information between the frames. To solve this problem, we propose the context motion network to leverage semantic information and motion information. To capture the motion information, we estimate the optical flow and design a context-motion updating operator to integrate features between frames recurrently. Our experiments show that our network outperforms state-of-the-art matting methods significantly on the Video240K SD dataset.

arXiv:2109.00829

SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos

Action anticipation in egocentric videos is a difficult task due to the inherently multi-modal nature of human actions. Additionally, some actions happen faster or slower than others depending on the actor or surrounding context which could vary each time and lead to different predictions. Based on this idea, we build upon RULSTM architecture, which is specifically designed for anticipating human actions, and propose a novel attention-based technique to evaluate, simultaneously, slow and fast features extracted from three different modalities, namely RGB, optical flow, and extracted objects. Two branches process information at different time scales, i.e., frame-rates, and several fusion schemes are considered to improve prediction accuracy. We perform extensive experiments on EpicKitchens-55 and EGTEA Gaze+ datasets, and demonstrate that our technique systematically improves the results of RULSTM architecture for Top-5 accuracy metric at different anticipation times.

arXiv:2108.12711공식 코드 · Papers with Code

Learning to Track Objects from Unlabeled Videos

In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch. We identify that three major challenges, i.e., moving object discovery, rich temporal variation exploitation, and online update, are the central causes of the performance bottleneck of existing unsupervised trackers. To narrow the gap between unsupervised trackers and supervised counterparts, we propose an effective unsupervised learning approach composed of three stages. First, we sample sequentially moving objects with unsupervised optical flow and dynamic programming, instead of random cropping. Second, we train a naive Siamese tracker from scratch using single-frame pairs. Third, we continue training the tracker with a novel cycle memory learning scheme, which is conducted in longer temporal spans and also enables our tracker to update online. Extensive experiments show that the proposed USOT learned from unlabeled videos performs well over the state-of-the-art unsupervised trackers by large margins, and on par with recent supervised deep trackers. Code is available at https://github.com/VISION-SJTU/USOT.

arXiv:2108.11974

Learning Cross-modal Contrastive Features for Video Domain Adaptation

Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has been derived from the RGB image space. However, video data is usually associated with multi-modal information, e.g., RGB and optical flow, and thus it remains a challenge to design a better method that considers the cross-modal inputs under the cross-domain adaptation setting. To this end, we propose a unified framework for video domain adaptation, which simultaneously regularizes cross-modal and cross-domain feature representations. Specifically, we treat each modality in a domain as a view and leverage the contrastive learning technique with properly designed sampling strategies. As a result, our objectives regularize feature spaces, which originally lack the connection across modalities or have less alignment across domains. We conduct experiments on domain adaptive action recognition benchmark datasets, i.e., UCF, HMDB, and EPIC-Kitchens, and demonstrate the effectiveness of our components against state-of-the-art algorithms.

arXiv:2108.12375

A Pedestrian Detection and Tracking Framework for Autonomous Cars: Efficient Fusion of Camera and LiDAR Data

This paper presents a novel method for pedestrian detection and tracking by fusing camera and LiDAR sensor data. To deal with the challenges associated with the autonomous driving scenarios, an integrated tracking and detection framework is proposed. The detection phase is performed by converting LiDAR streams to computationally tractable depth images, and then, a deep neural network is developed to identify pedestrian candidates both in RGB and depth images. To provide accurate information, the detection phase is further enhanced by fusing multi-modal sensor information using the Kalman filter. The tracking phase is a combination of the Kalman filter prediction and an optical flow algorithm to track multiple pedestrians in a scene. We evaluate our framework on a real public driving dataset. Experimental results demonstrate that the proposed method achieves significant performance improvement over a baseline method that solely uses image-based pedestrian detection.

arXiv:2108.10637

Full-Velocity Radar Returns by Radar-Camera Fusion

A distinctive feature of Doppler radar is the measurement of velocity in the radial direction for radar points. However, the missing tangential velocity component hampers object velocity estimation as well as temporal integration of radar sweeps in dynamic scenes. Recognizing that fusing camera with radar provides complementary information to radar, in this paper we present a closed-form solution for the point-wise, full-velocity estimate of Doppler returns using the corresponding optical flow from camera images. Additionally, we address the association problem between radar returns and camera images with a neural network that is trained to estimate radar-camera correspondences. Experimental results on the nuScenes dataset verify the validity of the method and show significant improvements over the state-of-the-art in velocity estimation and accumulation of radar points.

arXiv:2108.10552공식 코드 · Papers with Code

E-RAFT: Dense Optical Flow from Event Cameras

We propose to incorporate feature correlation and sequential processing into dense optical flow estimation from event cameras. Modern frame-based optical flow methods heavily rely on matching costs computed from feature correlation. In contrast, there exists no optical flow method for event cameras that explicitly computes matching costs. Instead, learning-based approaches using events usually resort to the U-Net architecture to estimate optical flow sparsely. Our key finding is that the introduction of correlation features significantly improves results compared to previous methods that solely rely on convolution layers. Compared to the state-of-the-art, our proposed approach computes dense optical flow and reduces the end-point error by 23% on MVSEC. Furthermore, we show that all existing optical flow methods developed so far for event cameras have been evaluated on datasets with very small displacement fields with a maximum flow magnitude of 10 pixels. Based on this observation, we introduce a new real-world dataset that exhibits displacement fields with magnitudes up to 210 pixels and 3 times higher camera resolution. Our proposed approach reduces the end-point error on this dataset by 66%.

arXiv:2108.09322

MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition

This paper presents a pure transformer-based approach, dubbed the Multi-Modal Video Transformer (MM-ViT), for video action recognition. Different from other schemes which solely utilize the decoded RGB frames, MM-ViT operates exclusively in the compressed video domain and exploits all readily available modalities, i.e., I-frames, motion vectors, residuals and audio waveform. In order to handle the large number of spatiotemporal tokens extracted from multiple modalities, we develop several scalable model variants which factorize self-attention across the space, time and modality dimensions. In addition, to further explore the rich inter-modal interactions and their effects, we develop and compare three distinct cross-modal attention mechanisms that can be seamlessly integrated into the transformer building block. Extensive experiments on three public action recognition benchmarks (UCF-101, Something-Something-v2, Kinetics-600) demonstrate that MM-ViT outperforms the state-of-the-art video transformers in both efficiency and accuracy, and performs better or equally well to the state-of-the-art CNN counterparts with computationally-heavy optical flow.

arXiv:2108.09041공식 코드 · Papers with Code

Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization

Warping-based video stabilizers smooth camera trajectory by constraining each pixel's displacement and warp stabilized frames from unstable ones accordingly. However, since the view outside the boundary is not available during warping, the resulting holes around the boundary of the stabilized frame must be discarded (i.e., cropping) to maintain visual consistency, and thus does leads to a tradeoff between stability and cropping ratio. In this paper, we make a first attempt to address this issue by proposing a new Out-of-boundary View Synthesis (OVS) method. By the nature of spatial coherence between adjacent frames and within each frame, OVS extrapolates the out-of-boundary view by aligning adjacent frames to each reference one. Technically, it first calculates the optical flow and propagates it to the outer boundary region according to the affinity, and then warps pixels accordingly. OVS can be integrated into existing warping-based stabilizers as a plug-and-play module to significantly improve the cropping ratio of the stabilized results. In addition, stability is improved because the jitter amplification effect caused by cropping and resizing is reduced. Experimental results on the NUS benchmark show that OVS can improve the performance of five representative state-of-the-art methods in terms of objective metrics and subjective visual quality. The code is publicly available at https://github.com/Annbless/OVS_Stabilization.

arXiv:2108.08119공식 코드 · Papers with Code

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision

Learning RAW-to-sRGB mapping has drawn increasing attention in recent years, wherein an input raw image is trained to imitate the target sRGB image captured by another camera. However, the severe color inconsistency makes it very challenging to generate well-aligned training pairs of input raw and target sRGB images. While learning with inaccurately aligned supervision is prone to causing pixel shift and producing blurry results. In this paper, we circumvent such issue by presenting a joint learning model for image alignment and RAW-to-sRGB mapping. To diminish the effect of color inconsistency in image alignment, we introduce to use a global color mapping (GCM) module to generate an initial sRGB image given the input raw image, which can keep the spatial location of the pixels unchanged, and the target sRGB image is utilized to guide GCM for converting the color towards it. Then a pre-trained optical flow estimation network (e.g., PWC-Net) is deployed to warp the target sRGB image to align with the GCM output. To alleviate the effect of inaccurately aligned supervision, the warped target sRGB image is leveraged to learn RAW-to-sRGB mapping. When training is done, the GCM module and optical flow network can be detached, thereby bringing no extra computation cost for inference. Experiments show that our method performs favorably against state-of-the-arts on ZRR and SR-RAW datasets. With our joint learning model, a light-weight backbone can achieve better quantitative and qualitative performance on ZRR dataset. Codes are available at https://github.com/cszhilu1998/RAW-to-sRGB.

arXiv:2108.07438공식 코드 · Papers with Code

Diffeomorphic Particle Image Velocimetry

The existing particle image velocimetry (PIV) do not consider the curvature effect of the non-straight particle trajectory, because it seems to be impossible to obtain the curvature information from a pair of particle images. As a result, the computed vector underestimates the real velocity due to the straight-line approximation, that further causes a systematic error for the PIV instrument. In this work, the particle curved trajectory between two recordings is firstly explained with the streamline segment of a steady flow (diffeomorphic transformation) instead of a single vector, and this idea is termed as diffeomorphic PIV. Specifically, a deformation field is introduced to describe the particle displacement, i.e., we try to find the optimal velocity field, of which the corresponding deformation vector field agrees with the particle displacement. Because the variation of the deformation function can be approximated with the variation of the velocity function, the diffeomorphic PIV can be implemented as iterative PIV. That says, the diffeomorphic PIV warps the images with deformation vector field instead of the velocity, and keeps the rest as same as iterative PIVs. Two diffeomorphic deformation schemes -- forward diffeomorphic deformation interrogation (FDDI) and central diffeomorphic deformation interrogation (CDDI) -- are proposed. Tested on synthetic images, the FDDI achieves significant accuracy improvement across different one-pass displacement estimators (cross-correlation, optical flow, deep learning flow). Besides, the results on three real PIV image pairs demonstrate the non-negligible curvature effect for CDI-based PIV, and our FDDI provides larger velocity estimation (more accurate) in the fast curvy streamline areas. The accuracy improvement of the combination of FDDI and accurate dense estimator means that our diffeomorphic PIV paves a new way for complex flow measurement.

arXiv:2108.06852공식 코드 · Papers with Code

A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction

In this paper, we propose $\text{HF}^2$-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules in an Autoencoder with Skip Connections) to memorize normal patterns for optical flow reconstruction so that abnormal events can be sensitively identified with larger flow reconstruction errors. More importantly, conditioned on the reconstructed flows, we then employ a Conditional Variational Autoencoder (CVAE), which captures the high correlation between video frame and optical flow, to predict the next frame given several previous frames. By CVAE, the quality of flow reconstruction essentially influences that of frame prediction. Therefore, poorly reconstructed optical flows of abnormal events further deteriorate the quality of the final predicted future frame, making the anomalies more detectable. Experimental results demonstrate the effectiveness of the proposed method. Code is available at \href{https://github.com/LiUzHiAn/hf2vad}{https://github.com/LiUzHiAn/hf2vad}.

arXiv:2108.06819공식 코드 · Papers with Code

EventHPE: Event-based 3D Human Pose and Shape Estimation

Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on the other hand, have their unique challenges: rather than capturing static body postures, the event signals are best at capturing local motions. This leads us to propose a two-stage deep learning approach, called EventHPE. The first-stage, FlowNet, is trained by unsupervised learning to infer optical flow from events. Both events and optical flow are closely related to human body dynamics, which are fed as input to the ShapeNet in the second stage, to estimate 3D human shapes. To mitigate the discrepancy between image-based flow (optical flow) and shape-based flow (vertices movement of human body shape), a novel flow coherence loss is introduced by exploiting the fact that both flows are originated from the identical human motion. An in-house event-based 3D human dataset is curated that comes with 3D pose and shape annotations, which is by far the largest one to our knowledge. Empirical evaluations on DHP19 dataset and our in-house dataset demonstrate the effectiveness of our approach.

arXiv:2108.05882

An optical flow approach to tracking ship track behavior using GOES-R satellite imagery

Ship emissions can form linear cloud structures, or ship tracks, when atmospheric water vapor condenses on aerosols in the ship exhaust. These structures are of interest because they are observable and traceable examples of marine cloud brightening, a mechanism that has been studied as a potential approach for solar climate intervention. Ship tracks can be observed throughout the diurnal cycle via space-borne assets like the Advanced Baseline Imagers on the National Oceanic and Atmospheric Administration Geostationary Operational Environmental Satellites, the GOES-R series. Due to complex atmospheric dynamics, it can be difficult to track these aerosol perturbations over space and time to precisely characterize how long a single emission source can significantly contribute to indirect radiative forcing. We propose an optical flow approach to estimate the trajectories of ship-emitted aerosols after they begin mixing with low boundary layer clouds using GOES-17 satellite imagery. Most optical flow estimation methods have only been used to estimate large scale atmospheric motion. We demonstrate the ability of our approach to precisely isolate the movement of ship tracks in low-lying clouds from the movement of large swaths of high clouds that often dominate the scene. This efficient approach shows that ship tracks persist as visible, linear features beyond 9 hours and sometimes longer than 24 hours.

arXiv:2108.05607

Deep Motion Prior for Weakly-Supervised Temporal Action Localization

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods follow a Multi-Instance Learning (MIL) pipeline: producing snippet-level predictions first and then aggregating to the video-level prediction. However, we argue that existing methods have overlooked two important drawbacks: 1) inadequate use of motion information and 2) the incompatibility of prevailing cross-entropy training loss. In this paper, we analyze that the motion cues behind the optical flow features are complementary informative. Inspired by this, we propose to build a context-dependent motion prior, termed as motionness. Specifically, a motion graph is introduced to model motionness based on the local motion carrier (e.g., optical flow). In addition, to highlight more informative video snippets, a motion-guided loss is proposed to modulate the network training conditioned on motionness scores. Extensive ablation studies confirm that motionness efficaciously models action-of-interest, and the motion-guided loss leads to more accurate results. Besides, our motion-guided loss is a plug-and-play loss function and is applicable with existing WSTAL methods. Without loss of generality, based on the standard MIL pipeline, our method achieves new state-of-the-art performance on three challenging benchmarks, including THUMOS'14, ActivityNet v1.2 and v1.3.