PyTorchKR Papers

최신 논문

총 2,031편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2108.04103

End-to-end Neural Video Coding Using a Compound Spatiotemporal Representation

Recent years have witnessed rapid advances in learnt video coding. Most algorithms have solely relied on the vector-based motion representation and resampling (e.g., optical flow based bilinear sampling) for exploiting the inter frame redundancy. In spite of the great success of adaptive kernel-based resampling (e.g., adaptive convolutions and deformable convolutions) in video prediction for uncompressed videos, integrating such approaches with rate-distortion optimization for inter frame coding has been less successful. Recognizing that each resampling solution offers unique advantages in regions with different motion and texture characteristics, we propose a hybrid motion compensation (HMC) method that adaptively combines the predictions generated by these two approaches. Specifically, we generate a compound spatiotemporal representation (CSTR) through a recurrent information aggregation (RIA) module using information from the current and multiple past frames. We further design a one-to-many decoder pipeline to generate multiple predictions from the CSTR, including vector-based resampling, adaptive kernel-based resampling, compensation mode selection maps and texture enhancements, and combines them adaptively to achieve more accurate inter prediction. Experiments show that our proposed inter coding system can provide better motion-compensated prediction and is more robust to occlusions and complex motions. Together with jointly trained intra coder and residual coder, the overall learnt hybrid coder yields the state-of-the-art coding efficiency in low-delay scenario, compared to the traditional H.264/AVC and H.265/HEVC, as well as recently published learning-based methods, in terms of both PSNR and MS-SSIM metrics.

arXiv:2108.03329

Feature-Supervised Action Modality Transfer

This paper strives for action recognition and detection in video modalities like RGB, depth maps or 3D-skeleton sequences when only limited modality-specific labeled examples are available. For the RGB, and derived optical-flow, modality many large-scale labeled datasets have been made available. They have become the de facto pre-training choice when recognizing or detecting new actions from RGB datasets that have limited amounts of labeled examples available. Unfortunately, large-scale labeled action datasets for other modalities are unavailable for pre-training. In this paper, our goal is to recognize actions from limited examples in non-RGB video modalities, by learning from large-scale labeled RGB data. To this end, we propose a two-step training process: (i) we extract action representation knowledge from an RGB-trained teacher network and adapt it to a non-RGB student network. (ii) we then fine-tune the transfer model with available labeled examples of the target modality. For the knowledge transfer we introduce feature-supervision strategies, which rely on unlabeled pairs of two modalities (the RGB and the target modality) to transfer feature level representations from the teacher to the student network. Ablations and generalizations with two RGB source datasets and two non-RGB target datasets demonstrate that an optical-flow teacher provides better action transfer features than RGB for both depth maps and 3D-skeletons, even when evaluated on a different target domain, or for a different task. Compared to alternative cross-modal action transfer methods we show a good improvement in performance especially when labeled non-RGB examples to learn from are scarce

arXiv:2108.03893

Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos

Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major limitations. In this paper, we explore the learnable occlusion aware optical flow guided self-supervised depth and camera pose estimation by an adaptive cross weighted loss to address the above limitations. Firstly, we explore to train the learnable occlusion mask fused optical flow network by an occlusion-aware photometric loss with the temporally supplemental information and backward-forward consistency of adjacent views. And then, we design an adaptive cross-weighted loss between the depth-pose and optical flow loss of the geometric and photometric error to distinguish the moving objects which violate the static scene assumption. Our method shows promising results on KITTI, Make3D, and Cityscapes datasets under multiple tasks. We also show good generalization ability under a variety of challenging scenarios.

arXiv:2108.02356공식 코드 · Papers with Code

Video Abnormal Event Detection by Learning to Complete Visual Cloze Tests

Although deep neural networks (DNNs) enable great progress in video abnormal event detection (VAD), existing solutions typically suffer from two issues: (1) The localization of video events cannot be both precious and comprehensive. (2) The semantics and temporal context are under-explored. To tackle those issues, we are motivated by the prevalent cloze test in education and propose a novel approach named Visual Cloze Completion (VCC), which conducts VAD by learning to complete "visual cloze tests" (VCTs). Specifically, VCC first localizes each video event and encloses it into a spatio-temporal cube (STC). To achieve both precise and comprehensive localization, appearance and motion are used as complementary cues to mark the object region associated with each event. For each marked region, a normalized patch sequence is extracted from current and adjacent frames and stacked into a STC. With each patch and the patch sequence of a STC compared to a visual "word" and "sentence" respectively, we deliberately erase a certain "word" (patch) to yield a VCT. Then, the VCT is completed by training DNNs to infer the erased patch and its optical flow via video semantics. Meanwhile, VCC fully exploits temporal context by alternatively erasing each patch in temporal context and creating multiple VCTs. Furthermore, we propose localization-level, event-level, model-level and decision-level solutions to enhance VCC, which can further exploit VCC's potential and produce significant performance improvement gain. Extensive experiments demonstrate that VCC achieves state-of-the-art VAD performance. Our codes and results are open at https://github.com/yuguangnudt/VEC_VAD/tree/VCC.

arXiv:2108.01912공식 코드 · Papers with Code

Internal Video Inpainting by Implicit Long-range Propagation

We propose a novel framework for video inpainting by adopting an internal learning strategy. Unlike previous methods that use optical flow for cross-frame context propagation to inpaint unknown regions, we show that this can be achieved implicitly by fitting a convolutional neural network to known regions. Moreover, to handle challenging sequences with ambiguous backgrounds or long-term occlusion, we design two regularization terms to preserve high-frequency details and long-term temporal consistency. Extensive experiments on the DAVIS dataset demonstrate that the proposed method achieves state-of-the-art inpainting quality quantitatively and qualitatively. We further extend the proposed method to another challenging task: learning to remove an object from a video giving a single object mask in only one frame in a 4K video.

arXiv:2108.01199

Neural Image Representations for Multi-Image Fusion and Layer Separation

We propose a framework for aligning and fusing multiple images into a single view using neural image representations (NIRs), also known as implicit or coordinate-based neural representations. Our framework targets burst images that exhibit camera ego motion and potential changes in the scene. We describe different strategies for alignment depending on the nature of the scene motion -- namely, perspective planar (i.e., homography), optical flow with minimal scene change, and optical flow with notable occlusion and disocclusion. With the neural image representation, our framework effectively combines multiple inputs into a single canonical view without the need for selecting one of the images as a reference frame. We demonstrate how to use this multi-frame fusion framework for various layer separation tasks. The code and results are available at https://shnnam.github.io/research/nir.

arXiv:2108.01434공식 코드 · Papers with Code

Wavelet-Based Network For High Dynamic Range Imaging

High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion. Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. Comprehensive empirical evidence shows that ghosting artifacts caused by large foreground motion are mainly low-frequency signals and the details are mainly high-frequency signals. In this work, we propose a novel frequency-guided end-to-end deep neural network (FHDRNet) to conduct HDR fusion in the frequency domain, and Discrete Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details. Using a U-Net as the backbone, we propose two novel modules: merging module and frequency-guided upsampling module. The merging module applies the attention mechanism to the low-frequency components to deal with the ghost caused by large foreground motion. The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details. In addition, a new RAW dataset is created for training and evaluating multi-frame HDR imaging algorithms in the RAW domain. Extensive experiments are conducted on public datasets and our RAW dataset, showing that the proposed FHDRNet achieves state-of-the-art performance.

arXiv:2107.14795공식 코드 · Papers with Code

Perceiver IO: A General Architecture for Structured Inputs & Outputs

A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied beyond a small set of stereotyped settings, as they bake in domain & task assumptions or scale poorly to large inputs or outputs. In this work, we propose Perceiver IO, a general-purpose architecture that handles data from arbitrary settings while scaling linearly with the size of inputs and outputs. Our model augments the Perceiver with a flexible querying mechanism that enables outputs of various sizes and semantics, doing away with the need for task-specific architecture engineering. The same architecture achieves strong results on tasks spanning natural language and visual understanding, multi-task and multi-modal reasoning, and StarCraft II. As highlights, Perceiver IO outperforms a Transformer-based BERT baseline on the GLUE language benchmark despite removing input tokenization and achieves state-of-the-art performance on Sintel optical flow estimation with no explicit mechanisms for multiscale correspondence.

arXiv:2107.14399

Self-Supervised Regional and Temporal Auxiliary Tasks for Facial Action Unit Recognition

Automatic facial action unit (AU) recognition is a challenging task due to the scarcity of manual annotations. To alleviate this problem, a large amount of efforts has been dedicated to exploiting various methods which leverage numerous unlabeled data. However, many aspects with regard to some unique properties of AUs, such as the regional and relational characteristics, are not sufficiently explored in previous works. Motivated by this, we take the AU properties into consideration and propose two auxiliary AU related tasks to bridge the gap between limited annotations and the model performance in a self-supervised manner via the unlabeled data. Specifically, to enhance the discrimination of regional features with AU relation embedding, we design a task of RoI inpainting to recover the randomly cropped AU patches. Meanwhile, a single image based optical flow estimation task is proposed to leverage the dynamic change of facial muscles and encode the motion information into the global feature representation. Based on these two self-supervised auxiliary tasks, local features, mutual relation and motion cues of AUs are better captured in the backbone network with the proposed regional and temporal based auxiliary task learning (RTATL) framework. Extensive experiments on BP4D and DISFA demonstrate the superiority of our method and new state-of-the-art performances are achieved.

arXiv:2107.14287

Temporal Feature Warping for Video Shadow Detection

While single image shadow detection has been improving rapidly in recent years, video shadow detection remains a challenging task due to data scarcity and the difficulty in modelling temporal consistency. The current video shadow detection method achieves this goal via co-attention, which mostly exploits information that is temporally coherent but is not robust in detecting moving shadows and small shadow regions. In this paper, we propose a simple but powerful method to better aggregate information temporally. We use an optical flow based warping module to align and then combine features between frames. We apply this warping module across multiple deep-network layers to retrieve information from neighboring frames including both local details and high-level semantic information. We train and test our framework on the ViSha dataset. Experimental results show that our model outperforms the state-of-the-art video shadow detection method by 28%, reducing BER from 16.7 to 12.0.

arXiv:2107.13648공식 코드 · Papers with Code

Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action Detection

The dominant paradigm in spatiotemporal action detection is to classify actions using spatiotemporal features learned by 2D or 3D Convolutional Networks. We argue that several actions are characterized by their context, such as relevant objects and actors present in the video. To this end, we introduce an architecture based on self-attention and Graph Convolutional Networks in order to model contextual cues, such as actor-actor and actor-object interactions, to improve human action detection in video. We are interested in achieving this in a weakly-supervised setting, i.e. using as less annotations as possible in terms of action bounding boxes. Our model aids explainability by visualizing the learned context as an attention map, even for actions and objects unseen during training. We evaluate how well our model highlights the relevant context by introducing a quantitative metric based on recall of objects retrieved by attention maps. Our model relies on a 3D convolutional RGB stream, and does not require expensive optical flow computation. We evaluate our models on the DALY dataset, which consists of human-object interaction actions. Experimental results show that our contextualized approach outperforms a baseline action detection approach by more than 2 points in Video-mAP. Code is available at \url{https://github.com/micts/acgcn}

arXiv:2107.14206공식 코드 · Papers with Code

Using Visual Anomaly Detection for Task Execution Monitoring

Execution monitoring is essential for robots to detect and respond to failures. Since it is impossible to enumerate all failures for a given task, we learn from successful executions of the task to detect visual anomalies during runtime. Our method learns to predict the motions that occur during the nominal execution of a task, including camera and robot body motion. A probabilistic U-Net architecture is used to learn to predict optical flow, and the robot's kinematics and 3D model are used to model camera and body motion. The errors between the observed and predicted motion are used to calculate an anomaly score. We evaluate our method on a dataset of a robot placing a book on a shelf, which includes anomalies such as falling books, camera occlusions, and robot disturbances. We find that modeling camera and body motion, in addition to the learning-based optical flow prediction, results in an improvement of the area under the receiver operating characteristic curve from 0.752 to 0.804, and the area under the precision-recall curve from 0.467 to 0.549.

논문 ID: document/9203860

Local-Global Fusion Network for Video Super-Resolution

The goal of video super-resolution technique is to address the problem of effectively restoring high-resolution (HR) videos from low-resolution (LR) ones. Previous methods commonly used optical flow to perform frame alignment and designed a framework from the perspective of space and time. However, inaccurate optical flow estimation may occur easily which leads to inferior restoration effects. In addition, how to effectively fuse the features of various video frames remains a challenging problem. In this paper, we propose a Local-Global Fusion Network (LGFN) to solve the above issues from a novel viewpoint. As an alternative to optical flow, deformable convolutions (DCs) with decreased multi-dilation convolution units (DMDCUs) are applied for efficient implicit alignment. Moreover, a structure with two branches, consisting of a Local Fusion Module (LFM) and a Global Fusion Module (GFM), is proposed to combine information from two different aspects. Specifically, LFM focuses on the relationship between adjacent frames and maintains the temporal consistency while GFM attempts to take advantage of all related features globally with a video shuffle strategy. Benefiting from our advanced network, experimental results on several datasets demonstrate that our LGFN can not only achieve comparative performance with state-of-the-art methods but also possess reliable ability on restoring a variety of video frames. The results on benchmark datasets of our LGFN are presented on https://github.com/BIOINSu/LGFN and the source code will be released as soon as the paper is accepted.

arXiv:2107.10990

Detail Preserving Residual Feature Pyramid Modules for Optical Flow

Feature pyramids and iterative refinement have recently led to great progress in optical flow estimation. However, downsampling in feature pyramids can cause blending of foreground objects with the background, which will mislead subsequent decisions in the iterative processing. The results are missing details especially in the flow of thin and of small structures. We propose a novel Residual Feature Pyramid Module (RFPM) which retains important details in the feature map without changing the overall iterative refinement design of the optical flow estimation. RFPM incorporates a residual structure between multiple feature pyramids into a downsampling module that corrects the blending of objects across boundaries. We demonstrate how to integrate our module with two state-of-the-art iterative refinement architectures. Results show that our RFPM visibly reduces flow errors and improves state-of-art performance in the clean pass of Sintel, and is one of the top-performing methods in KITTI. According to the particular modular structure of RFPM, we introduce a special transfer learning approach that can dramatically decrease the training time compared to a typical full optical flow training schedule on multiple datasets.

arXiv:2107.10004

Deep Iterative 2D/3D Registration

Deep Learning-based 2D/3D registration methods are highly robust but often lack the necessary registration accuracy for clinical application. A refinement step using the classical optimization-based 2D/3D registration method applied in combination with Deep Learning-based techniques can provide the required accuracy. However, it also increases the runtime. In this work, we propose a novel Deep Learning driven 2D/3D registration framework that can be used end-to-end for iterative registration tasks without relying on any further refinement step. We accomplish this by learning the update step of the 2D/3D registration framework using Point-to-Plane Correspondences. The update step is learned using iterative residual refinement-based optical flow estimation, in combination with the Point-to-Plane correspondence solver embedded as a known operator. Our proposed method achieves an average runtime of around 8s, a mean re-projection distance error of 0.60 $\pm$ 0.40 mm with a success ratio of 97 percent and a capture range of 60 mm. The combination of high registration accuracy, high robustness, and fast runtime makes our solution ideal for clinical applications.

arXiv:2107.09060공식 코드 · Papers with Code

LAPNet: Non-rigid Registration derived in k-space for Magnetic Resonance Imaging

Physiological motion, such as cardiac and respiratory motion, during Magnetic Resonance (MR) image acquisition can cause image artifacts. Motion correction techniques have been proposed to compensate for these types of motion during thoracic scans, relying on accurate motion estimation from undersampled motion-resolved reconstruction. A particular interest and challenge lie in the derivation of reliable non-rigid motion fields from the undersampled motion-resolved data. Motion estimation is usually formulated in image space via diffusion, parametric-spline, or optical flow methods. However, image-based registration can be impaired by remaining aliasing artifacts due to the undersampled motion-resolved reconstruction. In this work, we describe a formalism to perform non-rigid registration directly in the sampled Fourier space, i.e. k-space. We propose a deep-learning based approach to perform fast and accurate non-rigid registration from the undersampled k-space data. The basic working principle originates from the Local All-Pass (LAP) technique, a recently introduced optical flow-based registration. The proposed LAPNet is compared against traditional and deep learning image-based registrations and tested on fully-sampled and highly-accelerated (with two undersampling strategies) 3D respiratory motion-resolved MR images in a cohort of 40 patients with suspected liver or lung metastases and 25 healthy subjects. The proposed LAPNet provided consistent and superior performance to image-based approaches throughout different sampling trajectories and acceleration factors.

arXiv:2107.08037공식 코드 · Papers with Code

CCVS: Context-aware Controllable Video Synthesis

This presentation introduces a self-supervised learning approach to the synthesis of new video clips from old ones, with several new key elements for improved spatial resolution and realism: It conditions the synthesis process on contextual information for temporal continuity and ancillary information for fine control. The prediction model is doubly autoregressive, in the latent space of an autoencoder for forecasting, and in image space for updating contextual information, which is also used to enforce spatio-temporal consistency through a learnable optical flow module. Adversarial training of the autoencoder in the appearance and temporal domains is used to further improve the realism of its output. A quantizer inserted between the encoder and the transformer in charge of forecasting future frames in latent space (and its inverse inserted between the transformer and the decoder) adds even more flexibility by affording simple mechanisms for handling multimodal ancillary information for controlling the synthesis process (eg, a few sample frames, an audio track, a trajectory in image space) and taking into account the intrinsically uncertain nature of the future by allowing multiple predictions. Experiments with an implementation of the proposed approach give very good qualitative and quantitative results on multiple tasks and standard benchmarks.

arXiv:2107.07837

Progressive Deep Video Dehazing without Explicit Alignment Estimation

To solve the issue of video dehazing, there are two main tasks to attain: how to align adjacent frames to the reference frame; how to restore the reference frame. Some papers adopt explicit approaches (e.g., the Markov random field, optical flow, deformable convolution, 3D convolution) to align neighboring frames with the reference frame in feature space or image space, they then use various restoration methods to achieve the final dehazing results. In this paper, we propose a progressive alignment and restoration method for video dehazing. The alignment process aligns consecutive neighboring frames stage by stage without using the optical flow estimation. The restoration process is not only implemented under the alignment process but also uses a refinement network to improve the dehazing performance of the whole network. The proposed networks include four fusion networks and one refinement network. To decrease the parameters of networks, three fusion networks in the first fusion stage share the same parameters. Extensive experiments demonstrate that the proposed video dehazing method achieves outstanding performance against the-state-of-art methods.

arXiv:2107.07067

MeNToS: Tracklets Association with a Space-Time Memory Network

We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection. The proposed method addresses particularly the data association problem. Indeed, the recently introduced HOTA metric, that has a better alignment with the human visual assessment by evenly balancing detections and associations quality, has shown that improvements are still needed for data association. After creating tracklets using instance segmentation and optical flow, the proposed method relies on a space-time memory network (STM) developed for one-shot video object segmentation to improve the association of tracklets with temporal gaps. To the best of our knowledge, our method, named MeNToS, is the first to use the STM network to track object masks for MOTS. We took the 4th place in the RobMOTS challenge. The project page is https://mehdimiah.com/mentos.html.

arXiv:2107.05634

DDCNet-Multires: Effective Receptive Field Guided Multiresolution CNN for Dense Prediction

Dense optical flow estimation is challenging when there are large displacements in a scene with heterogeneous motion dynamics, occlusion, and scene homogeneity. Traditional approaches to handle these challenges include hierarchical and multiresolution processing methods. Learning-based optical flow methods typically use a multiresolution approach with image warping when a broad range of flow velocities and heterogeneous motion is present. Accuracy of such coarse-to-fine methods is affected by the ghosting artifacts when images are warped across multiple resolutions and by the vanishing problem in smaller scene extents with higher motion contrast. Previously, we devised strategies for building compact dense prediction networks guided by the effective receptive field (ERF) characteristics of the network (DDCNet). The DDCNet design was intentionally simple and compact allowing it to be used as a building block for designing more complex yet compact networks. In this work, we extend the DDCNet strategies to handle heterogeneous motion dynamics by cascading DDCNet based sub-nets with decreasing extents of their ERF. Our DDCNet with multiresolution capability (DDCNet-Multires) is compact without any specialized network layers. We evaluate the performance of the DDCNet-Multires network using standard optical flow benchmark datasets. Our experiments demonstrate that DDCNet-Multires improves over the DDCNet-B0 and -B1 and provides optical flow estimates with accuracy comparable to similar lightweight learning-based methods.