PyTorchKR Papers

최신 논문

총 2,031편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2012.00452공식 코드 · Papers with Code

Counting People by Estimating People Flows

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing them. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it allows us to exploit the correlation between people flow and optical flow to further improve the results. We also show that leveraging people conservation constraints in both a spatial and temporal manner makes it possible to train a deep crowd counting model in an active learning setting with much fewer annotations. This significantly reduces the annotation cost while still leading to similar performance to the full supervision case.

arXiv:2012.00212공식 코드 · Papers with Code

UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning

We present an unsupervised learning approach for optical flow estimation by improving the upsampling and learning of pyramid network. We design a self-guided upsample module to tackle the interpolation blur problem caused by bilinear upsampling between pyramid levels. Moreover, we propose a pyramid distillation loss to add supervision for intermediate levels via distilling the finest flow as pseudo labels. By integrating these two components together, our method achieves the best performance for unsupervised optical flow learning on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015. In particular, we achieve EPE=1.4 on KITTI 2012 and F1=9.38% on KITTI 2015, which outperform the previous state-of-the-art methods by 22.2% and 15.7%, respectively.

arXiv:2012.00726공식 코드 · Papers with Code

RAFT-3D: Scene Flow using Rigid-Motion Embeddings

We address the problem of scene flow: given a pair of stereo or RGB-D video frames, estimate pixelwise 3D motion. We introduce RAFT-3D, a new deep architecture for scene flow. RAFT-3D is based on the RAFT model developed for optical flow but iteratively updates a dense field of pixelwise SE3 motion instead of 2D motion. A key innovation of RAFT-3D is rigid-motion embeddings, which represent a soft grouping of pixels into rigid objects. Integral to rigid-motion embeddings is Dense-SE3, a differentiable layer that enforces geometric consistency of the embeddings. Experiments show that RAFT-3D achieves state-of-the-art performance. On FlyingThings3D, under the two-view evaluation, we improved the best published accuracy (d < 0.05) from 34.3% to 83.7%. On KITTI, we achieve an error of 5.77, outperforming the best published method (6.31), despite using no object instance supervision. Code is available at https://github.com/princeton-vl/RAFT-3D.

arXiv:2011.14284공식 코드 · Papers with Code

UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information

Semantic segmentation of aerial videos has been extensively used for decision making in monitoring environmental changes, urban planning, and disaster management. The reliability of these decision support systems is dependent on the accuracy of the video semantic segmentation algorithms. The existing CNN based video semantic segmentation methods have enhanced the image semantic segmentation methods by incorporating an additional module such as LSTM or optical flow for computing temporal dynamics of the video which is a computational overhead. The proposed research work modifies the CNN architecture by incorporating temporal information to improve the efficiency of video semantic segmentation. In this work, an enhanced encoder-decoder based CNN architecture (UVid-Net) is proposed for UAV video semantic segmentation. The encoder of the proposed architecture embeds temporal information for temporally consistent labelling. The decoder is enhanced by introducing the feature-refiner module, which aids in accurate localization of the class labels. The proposed UVid-Net architecture for UAV video semantic segmentation is quantitatively evaluated on extended ManipalUAVid dataset. The performance metric mIoU of 0.79 has been observed which is significantly greater than the other state-of-the-art algorithms. Further, the proposed work produced promising results even for the pre-trained model of UVid-Net on urban street scene with fine tuning the final layer on UAV aerial videos.

arXiv:2011.14814공식 코드 · Papers with Code

Cost Function Unrolling in Unsupervised Optical Flow

Steepest descent algorithms, which are commonly used in deep learning, use the gradient as the descent direction, either as-is or after a direction shift using preconditioning. In many scenarios calculating the gradient is numerically hard due to complex or non-differentiable cost functions, specifically next to singular points. In this work we focus on the derivation of the Total Variation semi-norm commonly used in unsupervised cost functions. Specifically, we derive a differentiable proxy to the hard L1 smoothness constraint in a novel iterative scheme which we refer to as Cost Unrolling. Producing more accurate gradients during training, our method enables finer predictions of a given DNN model through improved convergence, without modifying its architecture or increasing computational complexity. We demonstrate our method in the unsupervised optical flow task. Replacing the L1 smoothness constraint with our unrolled cost during the training of a well known baseline, we report improved results on both MPI Sintel and KITTI 2015 unsupervised optical flow benchmarks. Particularly, we report EPE reduced by up to 15.82% on occluded pixels, where the smoothness constraint is dominant, enabling the detection of much sharper motion edges.

arXiv:2011.14880공식 코드 · Papers with Code

Occlusion Guided Scene Flow Estimation on 3D Point Clouds

3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a new scene flow architecture called OGSF-Net which tightly couples the learning for both flow and occlusions between frames. Their coupled symbiosis results in a more accurate prediction of flow in space. Unlike a traditional multi-action network, our unified approach is fused throughout the network, boosting performances for both occlusion detection and flow estimation. Our architecture is the first to gauge the occlusion in 3D scene flow estimation on point clouds. In key datasets such as Flyingthings3D and KITTI, we achieve the state-of-the-art results.

arXiv:2011.12267

A Framework for Fluid Motion Estimation using a Constraint-Based Refinement Approach

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.

arXiv:2011.12222

Discovering Hidden Physics Behind Transport Dynamics

Transport processes are ubiquitous. They are, for example, at the heart of optical flow approaches; or of perfusion imaging, where blood transport is assessed, most commonly by injecting a tracer. An advection-diffusion equation is widely used to describe these transport phenomena. Our goal is estimating the underlying physics of advection-diffusion equations, expressed as velocity and diffusion tensor fields. We propose a learning framework (YETI) building on an auto-encoder structure between 2D and 3D image time-series, which incorporates the advection-diffusion model. To help with identifiability, we develop an advection-diffusion simulator which allows pre-training of our model by supervised learning using the velocity and diffusion tensor fields. Instead of directly learning these velocity and diffusion tensor fields, we introduce representations that assure incompressible flow and symmetric positive semi-definite diffusion fields and demonstrate the additional benefits of these representations on improving estimation accuracy. We further use transfer learning to apply YETI on a public brain magnetic resonance (MR) perfusion dataset of stroke patients and show its ability to successfully distinguish stroke lesions from normal brain regions via the estimated velocity and diffusion tensor fields.

arXiv:2011.10486공식 코드 · Papers with Code

Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins

Deploying off-the-shelf segmentation networks on biomedical data has become common practice, yet if structures of interest in an image sequence are visible only temporarily, existing frame-by-frame methods fail. In this paper, we provide a solution to segmentation of imperfect data through time based on temporal propagation and uncertainty estimation. We integrate uncertainty estimation into Mask R-CNN network and propagate motion-corrected segmentation masks from frames with low uncertainty to those frames with high uncertainty to handle temporary loss of signal for segmentation. We demonstrate the value of this approach over frame-by-frame segmentation and regular temporal propagation on data from human embryonic kidney (HEK293T) cells transiently transfected with a fluorescent protein that moves in and out of the nucleus over time. The method presented here will empower microscopic experiments aimed at understanding molecular and cellular function.

arXiv:2011.09697공식 코드 · Papers with Code

Deep Motion Blind Video Stabilization

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.

arXiv:2011.09654

HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects

In optical flow estimation task, coarse-to-fine (C2F) warping strategy is widely used to deal with the large displacement problem and provides efficiency and speed. However, limited by the small search range between the first images and warped second images, current coarse-to-fine optical flow networks fail to capture small and fast-moving objects which disappear at coarse resolution levels. To address this problem, we introduce a lightweight but effective Global Matching Component (GMC) to grab global matching features. We propose a new Hybrid Matching Optical Flow Network (HMFlow) by integrating GMC into existing coarse-to-fine networks seamlessly. Besides keeping in high accuracy and small model size, our proposed HMFlow can apply global matching features to guide the network to discover the small and fast-moving objects mismatched by local matching features. We also build a new dataset, named Small and Fast-Moving Chairs (SFChairs), for evaluation. The experimental results show that our proposed network achieves considerable performance, especially at regions with small and fast-moving objects.

arXiv:2011.09619

Abnormal Event Detection in Urban Surveillance Videos Using GAN and Transfer Learning

Abnormal event detection (AED) in urban surveillance videos has multiple challenges. Unlike other computer vision problems, the AED is not solely dependent on the content of frames. It also depends on the appearance of the objects and their movements in the scene. Various methods have been proposed to address the AED problem. Among those, deep learning based methods show the best results. This paper is based on deep learning methods and provides an effective way to detect and locate abnormal events in videos by handling spatio temporal data. This paper uses generative adversarial networks (GANs) and performs transfer learning algorithms on pre trained convolutional neural network (CNN) which result in an accurate and efficient model. The efficiency of the model is further improved by processing the optical flow information of the video. This paper runs experiments on two benchmark datasets for AED problem (UCSD Peds1 and UCSD Peds2) and compares the results with other previous methods. The comparisons are based on various criteria such as area under curve (AUC) and true positive rate (TPR). Experimental results show that the proposed method can effectively detect and locate abnormal events in crowd scenes.

arXiv:2011.09594공식 코드 · Papers with Code

Deep Multi-view Depth Estimation with Predicted Uncertainty

In this paper, we address the problem of estimating dense depth from a sequence of images using deep neural networks. Specifically, we employ a dense-optical-flow network to compute correspondences and then triangulate the point cloud to obtain an initial depth map.Parts of the point cloud, however, may be less accurate than others due to lack of common observations or small parallax. To further increase the triangulation accuracy, we introduce a depth-refinement network (DRN) that optimizes the initial depth map based on the image's contextual cues. In particular, the DRN contains an iterative refinement module (IRM) that improves the depth accuracy over iterations by refining the deep features. Lastly, the DRN also predicts the uncertainty in the refined depths, which is desirable in applications such as measurement selection for scene reconstruction. We show experimentally that our algorithm outperforms state-of-the-art approaches in terms of depth accuracy, and verify that our predicted uncertainty is highly correlated to the actual depth error.

arXiv:2011.08332

EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation

This paper addresses the challenging unsupervised scene flow estimation problem by jointly learning four low-level vision sub-tasks: optical flow $\textbf{F}$, stereo-depth $\textbf{D}$, camera pose $\textbf{P}$ and motion segmentation $\textbf{S}$. Our key insight is that the rigidity of the scene shares the same inherent geometrical structure with object movements and scene depth. Hence, rigidity from $\textbf{S}$ can be inferred by jointly coupling $\textbf{F}$, $\textbf{D}$ and $\textbf{P}$ to achieve more robust estimation. To this end, we propose a novel scene flow framework named EffiScene with efficient joint rigidity learning, going beyond the existing pipeline with independent auxiliary structures. In EffiScene, we first estimate optical flow and depth at the coarse level and then compute camera pose by Perspective-$n$-Points method. To jointly learn local rigidity, we design a novel Rigidity From Motion (RfM) layer with three principal components: \emph{}{(i)} correlation extraction; \emph{}{(ii)} boundary learning; and \emph{}{(iii)} outlier exclusion. Final outputs are fused based on the rigid map $M_R$ from RfM at finer levels. To efficiently train EffiScene, two new losses $\mathcal{L}_{bnd}$ and $\mathcal{L}_{unc}$ are designed to prevent trivial solutions and to regularize the flow boundary discontinuity. Extensive experiments on scene flow benchmark KITTI show that our method is effective and significantly improves the state-of-the-art approaches for all sub-tasks, i.e. optical flow ($5.19 \rightarrow 4.20$), depth estimation ($3.78 \rightarrow 3.46$), visual odometry ($0.012 \rightarrow 0.011$) and motion segmentation ($0.57 \rightarrow 0.62$).

arXiv:2011.08634

Exploring Self-Attention for Visual Odometry

Visual odometry networks commonly use pretrained optical flow networks in order to derive the ego-motion between consecutive frames. The features extracted by these networks represent the motion of all the pixels between frames. However, due to the existence of dynamic objects and texture-less surfaces in the scene, the motion information for every image region might not be reliable for inferring odometry due to the ineffectiveness of dynamic objects in derivation of the incremental changes in position. Recent works in this area lack attention mechanisms in their structures to facilitate dynamic reweighing of the feature maps for extracting more refined egomotion information. In this paper, we explore the effectiveness of self-attention in visual odometry. We report qualitative and quantitative results against the SOTA methods. Furthermore, saliency-based studies alongside specially designed experiments are utilized to investigate the effect of self-attention on VO. Our experiments show that using self-attention allows for the extraction of better features while achieving a better odometry performance compared to networks that lack such structures.

arXiv:2011.07188

Duality-Gated Mutual Condition Network for RGBT Tracking

Low-quality modalities contain not only a lot of noisy information but also some discriminative features in RGBT tracking. However, the potentials of low-quality modalities are not well explored in existing RGBT tracking algorithms. In this work, we propose a novel duality-gated mutual condition network to fully exploit the discriminative information of all modalities while suppressing the effects of data noise. In specific, we design a mutual condition module, which takes the discriminative information of a modality as the condition to guide feature learning of target appearance in another modality. Such module can effectively enhance target representations of all modalities even in the presence of low-quality modalities. To improve the quality of conditions and further reduce data noise, we propose a duality-gated mechanism and integrate it into the mutual condition module. To deal with the tracking failure caused by sudden camera motion, which often occurs in RGBT tracking, we design a resampling strategy based on optical flow algorithms. It does not increase much computational cost since we perform optical flow calculation only when the model prediction is unreliable and then execute resampling when the sudden camera motion is detected. Extensive experiments on four RGBT tracking benchmark datasets show that our method performs favorably against the state-of-the-art tracking algorithms

arXiv:2011.07787

JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition

Skeleton-based action recognition has attracted research attentions in recent years. One common drawback in currently popular skeleton-based human action recognition methods is that the sparse skeleton information alone is not sufficient to fully characterize human motion. This limitation makes several existing methods incapable of correctly classifying action categories which exhibit only subtle motion differences. In this paper, we propose a novel framework for employing human pose skeleton and joint-centered light-weight information jointly in a two-stream graph convolutional network, namely, JOLO-GCN. Specifically, we use Joint-aligned optical Flow Patches (JFP) to capture the local subtle motion around each joint as the pivotal joint-centered visual information. Compared to the pure skeleton-based baseline, this hybrid scheme effectively boosts performance, while keeping the computational and memory overheads low. Experiments on the NTU RGB+D, NTU RGB+D 120, and the Kinetics-Skeleton dataset demonstrate clear accuracy improvements attained by the proposed method over the state-of-the-art skeleton-based methods.

arXiv:2011.06294공식 코드 · Papers with Code

RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation

We propose RIFE, a Real-time Intermediate Flow Estimation algorithm for Video Frame Interpolation (VFI). Many recent flow-based VFI methods first estimate the bi-directional optical flows, then scale and reverse them to approximate intermediate flows, leading to artifacts on motion boundaries and complex pipelines. RIFE uses a neural network named IFNet that can directly estimate the intermediate flows from coarse-to-fine with much better speed. We design a privileged distillation scheme for training IFNet, resulting in a large performance improvement. RIFE does not rely on pre-trained optical flow models and can support arbitrary-timestep frame interpolation with the temporal encoding input. Experiments demonstrate that RIFE achieves state-of-the-art performance on several public benchmarks. Compared with the popular SuperSlomo and DAIN methods, RIFE is 4--27 times faster and produces better results. The code is available at https://github.com/hzwer/arXiv2020-RIFE.

arXiv:2011.05653

Skeleton-based Relational Reasoning for Group Activity Analysis

Research on group activity recognition mostly leans on the standard two-stream approach (RGB and Optical Flow) as their input features. Few have explored explicit pose information, with none using it directly to reason about the persons interactions. In this paper, we leverage the skeleton information to learn the interactions between the individuals straight from it. With our proposed method GIRN, multiple relationship types are inferred from independent modules, that describe the relations between the body joints pair-by-pair. Additionally to the joints relations, we also experiment with the previously unexplored relationship between individuals and relevant objects (e.g. volleyball). The individuals distinct relations are then merged through an attention mechanism, that gives more importance to those individuals more relevant for distinguishing the group activity. We evaluate our method in the Volleyball dataset, obtaining competitive results to the state-of-the-art. Our experiments demonstrate the potential of skeleton-based approaches for modeling multi-person interactions.

arXiv:2011.03958

FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition

Capsule networks (CapsNets) have recently shown promise to excel in most computer vision tasks, especially pertaining to scene understanding. In this paper, we explore CapsNet's capabilities in optical flow estimation, a task at which convolutional neural networks (CNNs) have already outperformed other approaches. We propose a CapsNet-based architecture, termed FlowCaps, which attempts to a) achieve better correspondence matching via finer-grained, motion-specific, and more-interpretable encoding crucial for optical flow estimation, b) perform better-generalizable optical flow estimation, c) utilize lesser ground truth data, and d) significantly reduce the computational complexity in achieving good performance, in comparison to its CNN-counterparts.