PyTorchKR Papers

최신 논문

총 2,031편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2206.08585

HairFIT: Pose-Invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-Region-Aware Inpainting

Hairstyle transfer is the task of modifying a source hairstyle to a target one. Although recent hairstyle transfer models can reflect the delicate features of hairstyles, they still have two major limitations. First, the existing methods fail to transfer hairstyles when a source and a target image have different poses (e.g., viewing direction or face size), which is prevalent in the real world. Also, the previous models generate unrealistic images when there is a non-trivial amount of regions in the source image occluded by its original hair. When modifying long hair to short hair, shoulders or backgrounds occluded by the long hair need to be inpainted. To address these issues, we propose a novel framework for pose-invariant hairstyle transfer, HairFIT. Our model consists of two stages: 1) flow-based hair alignment and 2) hair synthesis. In the hair alignment stage, we leverage a keypoint-based optical flow estimator to align a target hairstyle with a source pose. Then, we generate a final hairstyle-transferred image in the hair synthesis stage based on Semantic-region-aware Inpainting Mask (SIM) estimator. Our SIM estimator divides the occluded regions in the source image into different semantic regions to reflect their distinct features during the inpainting. To demonstrate the effectiveness of our model, we conduct quantitative and qualitative evaluations using multi-view datasets, K-hairstyle and VoxCeleb. The results indicate that HairFIT achieves a state-of-the-art performance by successfully transferring hairstyles between images of different poses, which has never been achieved before.

arXiv:2206.08572공식 코드 · Papers with Code

Enhanced Bi-directional Motion Estimation for Video Frame Interpolation

We present a novel simple yet effective algorithm for motion-based video frame interpolation. Existing motion-based interpolation methods typically rely on a pre-trained optical flow model or a U-Net based pyramid network for motion estimation, which either suffer from large model size or limited capacity in handling complex and large motion cases. In this work, by carefully integrating intermediateoriented forward-warping, lightweight feature encoder, and correlation volume into a pyramid recurrent framework, we derive a compact model to simultaneously estimate the bidirectional motion between input frames. It is 15 times smaller in size than PWC-Net, yet enables more reliable and flexible handling of challenging motion cases. Based on estimated bi-directional motion, we forward-warp input frames and their context features to intermediate frame, and employ a synthesis network to estimate the intermediate frame from warped representations. Our method achieves excellent performance on a broad range of video frame interpolation benchmarks. Code and trained models are available at \url{https://github.com/srcn-ivl/EBME}.

arXiv:2206.05897공식 코드 · Papers with Code

$\texttt{GradICON}$: Approximate Diffeomorphisms via Gradient Inverse Consistency

We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration. Contrary to optimization-based registration techniques and many modern learning-based methods, we do not directly penalize transformation irregularities but instead promote transformation regularity via an inverse consistency penalty. We use a neural network to predict a map between a source and a target image as well as the map when swapping the source and target images. Different from existing approaches, we compose these two resulting maps and regularize deviations of the $\bf{Jacobian}$ of this composition from the identity matrix. This regularizer -- $\texttt{GradICON}$ -- results in much better convergence when training registration models compared to promoting inverse consistency of the composition of maps directly while retaining the desirable implicit regularization effects of the latter. We achieve state-of-the-art registration performance on a variety of real-world medical image datasets using a single set of hyperparameters and a single non-dataset-specific training protocol.

arXiv:2206.04668

GateHUB: Gated History Unit with Background Suppression for Online Action Detection

Online action detection is the task of predicting the action as soon as it happens in a streaming video. A major challenge is that the model does not have access to the future and has to solely rely on the history, i.e., the frames observed so far, to make predictions. It is therefore important to accentuate parts of the history that are more informative to the prediction of the current frame. We present GateHUB, Gated History Unit with Background Suppression, that comprises a novel position-guided gated cross-attention mechanism to enhance or suppress parts of the history as per how informative they are for current frame prediction. GateHUB further proposes Future-augmented History (FaH) to make history features more informative by using subsequently observed frames when available. In a single unified framework, GateHUB integrates the transformer's ability of long-range temporal modeling and the recurrent model's capacity to selectively encode relevant information. GateHUB also introduces a background suppression objective to further mitigate false positive background frames that closely resemble the action frames. Extensive validation on three benchmark datasets, THUMOS, TVSeries, and HDD, demonstrates that GateHUB significantly outperforms all existing methods and is also more efficient than the existing best work. Furthermore, a flow-free version of GateHUB is able to achieve higher or close accuracy at 2.8x higher frame rate compared to all existing methods that require both RGB and optical flow information for prediction.

arXiv:2206.03673공식 코드 · Papers with Code

Unsupervised Learning of 3D Scene Flow from Monocular Camera

Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real scenes, and recent studies are based on synthetic data for training. Therefore, how to train a scene flow network with unsupervised methods based on real-world data shows crucial significance. A novel unsupervised learning method for scene flow is proposed in this paper, which utilizes the images of two consecutive frames taken by monocular camera without the ground truth of scene flow for training. Our method realizes the goal that training scene flow network with real-world data, which bridges the gap between training data and test data and broadens the scope of available data for training. Unsupervised learning of scene flow in this paper mainly consists of two parts: (i) depth estimation and camera pose estimation, and (ii) scene flow estimation based on four different loss functions. Depth estimation and camera pose estimation obtain the depth maps and camera pose between two consecutive frames, which provide further information for the next scene flow estimation. After that, we used depth consistency loss, dynamic-static consistency loss, Chamfer loss, and Laplacian regularization loss to carry out unsupervised training of the scene flow network. To our knowledge, this is the first paper that realizes the unsupervised learning of 3D scene flow from monocular camera. The experiment results on KITTI show that our method for unsupervised learning of scene flow meets great performance compared to traditional methods Iterative Closest Point (ICP) and Fast Global Registration (FGR). The source code is available at: https://github.com/IRMVLab/3DUnMonoFlow.

arXiv:2206.02997공식 코드 · Papers with Code

TadML: A fast temporal action detection with Mechanics-MLP

Temporal Action Detection(TAD) is a crucial but challenging task in video understanding.It is aimed at detecting both the type and start-end frame for each action instance in a long, untrimmed video.Most current models adopt both RGB and Optical-Flow streams for the TAD task. Thus, original RGB frames must be converted manually into Optical-Flow frames with additional computation and time cost, which is an obstacle to achieve real-time processing. At present, many models adopt two-stage strategies, which would slow the inference speed down and complicatedly tuning on proposals generating.By comparison, we propose a one-stage anchor-free temporal localization method with RGB stream only, in which a novel Newtonian Mechanics-MLP architecture is established. It has comparable accuracy with all existing state-of-the-art models, while surpasses the inference speed of these methods by a large margin. The typical inference speed in this paper is astounding 4.44 video per second on THUMOS14. In applications, because there is no need to convert optical flow, the inference speed will be faster.It also proves that MLP has great potential in downstream tasks such as TAD. The source code is available at https://github.com/BonedDeng/TadML

arXiv:2206.02203

3D Convolutional with Attention for Action Recognition

Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels and optical flow separately, models using a two-stream fusion technique, and models consisting of both convolutional neural network (CNN) and long-short term memory (LSTM) network are few examples of such complex models. Moreover, fine-tuning such complex models is computationally expensive as well. This paper proposes a deep neural network architecture for learning such dependencies consisting of a 3D convolutional layer, fully connected (FC) layers, and attention layer, which is simpler to implement and gives a competitive performance on the UCF-101 dataset. The proposed method first learns spatial and temporal features of actions through 3D-CNN, and then the attention mechanism helps the model to locate attention to essential features for recognition.

arXiv:2206.02573

Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021

In this report, we present the technical details of our approach to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition. The EPIC-KITCHENS-100 dataset consists of daily kitchen activities focusing on the interaction between human hands and their surrounding objects. It is very challenging to accurately recognize these fine-grained activities, due to the presence of distracting objects and visually similar action classes, especially in the unlabelled target domain. Based on an existing method for video domain adaptation, i.e., TA3N, we propose to learn hand-centric features by leveraging the hand bounding box information for UDA on fine-grained action recognition. This helps reduce the distraction from background as well as facilitate the learning of domain-invariant features. To achieve high quality hand localization, we adopt an uncertainty-aware domain adaptation network, i.e., MEAA, to train a domain-adaptive hand detector, which only uses very limited hand bounding box annotations in the source domain but can generalize well to the unlabelled target domain. Our submission achieved the 1st place in terms of top-1 action recognition accuracy, using only RGB and optical flow modalities as input.

arXiv:2206.02225

Physically Inspired Constraint for Unsupervised Regularized Ultrasound Elastography

Displacement estimation is a critical step of virtually all Ultrasound Elastography (USE) techniques. Two main features make this task unique compared to the general optical flow problem: the high-frequency nature of ultrasound radio-frequency (RF) data and the governing laws of physics on the displacement field. Recently, the architecture of the optical flow networks has been modified to be able to use RF data. Also, semi-supervised and unsupervised techniques have been employed for USE by considering prior knowledge of displacement continuity in the form of the first- and second-derivative regularizers. Despite these attempts, no work has considered the tissue compression pattern, and displacements in axial and lateral directions have been assumed to be independent. However, tissue motion pattern is governed by laws of physics in USE, rendering the axial and the lateral displacements highly correlated. In this paper, we propose Physically Inspired ConsTraint for Unsupervised Regularized Elastography (PICTURE), where we impose constraints on the Poisson's ratio to improve lateral displacement estimates. Experiments on phantom and in vivo data show that PICTURE substantially improves the quality of the lateral displacement estimation.

arXiv:2205.14620공식 코드 · Papers with Code

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation

Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications. In this work, we devise an efficient encoder-decoder based network, termed IFRNet, for fast intermediate frame synthesizing. It first extracts pyramid features from given inputs, and then refines the bilateral intermediate flow fields together with a powerful intermediate feature until generating the desired output. The gradually refined intermediate feature can not only facilitate intermediate flow estimation, but also compensate for contextual details, making IFRNet do not need additional synthesis or refinement module. To fully release its potential, we further propose a novel task-oriented optical flow distillation loss to focus on learning the useful teacher knowledge towards frame synthesizing. Meanwhile, a new geometry consistency regularization term is imposed on the gradually refined intermediate features to keep better structure layout. Experiments on various benchmarks demonstrate the excellent performance and fast inference speed of proposed approaches. Code is available at https://github.com/ltkong218/IFRNet.

arXiv:2205.14474

DeepRM: Deep Recurrent Matching for 6D Pose Refinement

Precise 6D pose estimation of rigid objects from RGB images is a critical but challenging task in robotics, augmented reality and human-computer interaction. To address this problem, we propose DeepRM, a novel recurrent network architecture for 6D pose refinement. DeepRM leverages initial coarse pose estimates to render synthetic images of target objects. The rendered images are then matched with the observed images to predict a rigid transform for updating the previous pose estimate. This process is repeated to incrementally refine the estimate at each iteration. The DeepRM architecture incorporates LSTM units to propagate information through each refinement step, significantly improving overall performance. In contrast to current 2-stage Perspective-n-Point based solutions, DeepRM is trained end-to-end, and uses a scalable backbone that can be tuned via a single parameter for accuracy and efficiency. During training, a multi-scale optical flow head is added to predict the optical flow between the observed and synthetic images. Optical flow prediction stabilizes the training process, and enforces the learning of features that are relevant to the task of pose estimation. Our results demonstrate that DeepRM achieves state-of-the-art performance on two widely accepted challenging datasets.

arXiv:2205.14147공식 코드 · Papers with Code

FlowNet-PET: Unsupervised Learning to Perform Respiratory Motion Correction in PET Imaging

To correct for respiratory motion in PET imaging, an interpretable and unsupervised deep learning technique, FlowNet-PET, was constructed. The network was trained to predict the optical flow between two PET frames from different breathing amplitude ranges. The trained model aligns different retrospectively-gated PET images, providing a final image with similar counting statistics as a non-gated image, but without the blurring effects. FlowNet-PET was applied to anthropomorphic digital phantom data, which provided the possibility to design robust metrics to quantify the corrections. When comparing the predicted optical flows to the ground truths, the median absolute error was found to be smaller than the pixel and slice widths. The improvements were illustrated by comparing against images without motion and computing the intersection over union (IoU) of the tumors as well as the enclosed activity and coefficient of variation (CoV) within the no-motion tumor volume before and after the corrections were applied. The average relative improvements provided by the network were 64%, 89%, and 75% for the IoU, total activity, and CoV, respectively. FlowNet-PET achieved similar results as the conventional retrospective phase binning approach, but only required one sixth of the scan duration. The code and data have been made publicly available (https://github.com/teaghan/FlowNet_PET).

arXiv:2205.14623공식 코드 · Papers with Code

SKFlow: Learning Optical Flow with Super Kernels

Optical flow estimation is a classical yet challenging task in computer vision. One of the essential factors in accurately predicting optical flow is to alleviate occlusions between frames. However, it is still a thorny problem for current top-performing optical flow estimation methods due to insufficient local evidence to model occluded areas. In this paper, we propose the Super Kernel Flow Network (SKFlow), a CNN architecture to ameliorate the impacts of occlusions on optical flow estimation. SKFlow benefits from the super kernels which bring enlarged receptive fields to complement the absent matching information and recover the occluded motions. We present efficient super kernel designs by utilizing conical connections and hybrid depth-wise convolutions. Extensive experiments demonstrate the effectiveness of SKFlow on multiple benchmarks, especially in the occluded areas. Without pre-trained backbones on ImageNet and with a modest increase in computation, SKFlow achieves compelling performance and ranks $\textbf{1st}$ among currently published methods on the Sintel benchmark. On the challenging Sintel clean and final passes (test), SKFlow surpasses the best-published result in the unmatched areas ($7.96$ and $12.50$) by $9.09\%$ and $7.92\%$. The code is available at \href{https://github.com/littlespray/SKFlow}{https://github.com/littlespray/SKFlow}.

arXiv:2205.14574

Feature-Aligned Video Raindrop Removal with Temporal Constraints

Existing adherent raindrop removal methods focus on the detection of the raindrop locations, and then use inpainting techniques or generative networks to recover the background behind raindrops. Yet, as adherent raindrops are diverse in sizes and appearances, the detection is challenging for both single image and video. Moreover, unlike rain streaks, adherent raindrops tend to cover the same area in several frames. Addressing these problems, our method employs a two-stage video-based raindrop removal method. The first stage is the single image module, which generates initial clean results. The second stage is the multiple frame module, which further refines the initial results using temporal constraints, namely, by utilizing multiple input frames in our process and applying temporal consistency between adjacent output frames. Our single image module employs a raindrop removal network to generate initial raindrop removal results, and create a mask representing the differences between the input and initial output. Once the masks and initial results for consecutive frames are obtained, our multiple-frame module aligns the frames in both the image and feature levels and then obtains the clean background. Our method initially employs optical flow to align the frames, and then utilizes deformable convolution layers further to achieve feature-level frame alignment. To remove small raindrops and recover correct backgrounds, a target frame is predicted from adjacent frames. A series of unsupervised losses are proposed so that our second stage, which is the video raindrop removal module, can self-learn from video data without ground truths. Experimental results on real videos demonstrate the state-of-art performance of our method both quantitatively and qualitatively.

arXiv:2205.10195공식 코드 · Papers with Code

Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration

How to properly model the inter-frame relation within the video sequence is an important but unsolved challenge for video restoration (VR). In this work, we propose an unsupervised flow-aligned sequence-to-sequence model (S2SVR) to address this problem. On the one hand, the sequence-to-sequence model, which has proven capable of sequence modeling in the field of natural language processing, is explored for the first time in VR. Optimized serialization modeling shows potential in capturing long-range dependencies among frames. On the other hand, we equip the sequence-to-sequence model with an unsupervised optical flow estimator to maximize its potential. The flow estimator is trained with our proposed unsupervised distillation loss, which can alleviate the data discrepancy and inaccurate degraded optical flow issues of previous flow-based methods. With reliable optical flow, we can establish accurate correspondence among multiple frames, narrowing the domain difference between 1D language and 2D misaligned frames and improving the potential of the sequence-to-sequence model. S2SVR shows superior performance in multiple VR tasks, including video deblurring, video super-resolution, and compressed video quality enhancement. Code and models are publicly available at https://github.com/linjing7/VR-Baseline

arXiv:2205.09821

Unsupervised Learning of Depth, Camera Pose and Optical Flow from Monocular Video

We propose DFPNet -- an unsupervised, joint learning system for monocular Depth, Optical Flow and egomotion (Camera Pose) estimation from monocular image sequences. Due to the nature of 3D scene geometry these three components are coupled. We leverage this fact to jointly train all the three components in an end-to-end manner. A single composite loss function -- which involves image reconstruction-based loss for depth & optical flow, bidirectional consistency checks and smoothness loss components -- is used to train the network. Using hyperparameter tuning, we are able to reduce the model size to less than 5% (8.4M parameters) of state-of-the-art DFP models. Evaluation on KITTI and Cityscapes driving datasets reveals that our model achieves results comparable to state-of-the-art in all of the three tasks, even with the significantly smaller model size.

arXiv:2205.08515공식 코드 · Papers with Code

Unsupervised Segmentation in Real-World Images via Spelke Object Inference

Self-supervised, category-agnostic segmentation of real-world images is a challenging open problem in computer vision. Here, we show how to learn static grouping priors from motion self-supervision by building on the cognitive science concept of a Spelke Object: a set of physical stuff that moves together. We introduce the Excitatory-Inhibitory Segment Extraction Network (EISEN), which learns to extract pairwise affinity graphs for static scenes from motion-based training signals. EISEN then produces segments from affinities using a novel graph propagation and competition network. During training, objects that undergo correlated motion (such as robot arms and the objects they move) are decoupled by a bootstrapping process: EISEN explains away the motion of objects it has already learned to segment. We show that EISEN achieves a substantial improvement in the state of the art for self-supervised image segmentation on challenging synthetic and real-world robotics datasets.

arXiv:2205.07844

Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion

Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos. However, compared to using appearance, it has some blind spots, such as the fact that objects become invisible if they do not move. In this work, we propose an approach that combines the strengths of motion-based and appearance-based segmentation. We propose to supervise an image segmentation network with the pretext task of predicting regions that are likely to contain simple motion patterns, and thus likely to correspond to objects. As the model only uses a single image as input, we can apply it in two settings: unsupervised video segmentation, and unsupervised image segmentation. We achieve state-of-the-art results for videos, and demonstrate the viability of our approach on still images containing novel objects. Additionally we experiment with different motion models and optical flow backbones and find the method to be robust to these change. Project page and code available at https://www.robots.ox.ac.uk/~vgg/research/gwm.

arXiv:2205.06836공식 코드 · Papers with Code

A Framework for Event-based Computer Vision on a Mobile Device

We present the first publicly available Android framework to stream data from an event camera directly to a mobile phone. Today's mobile devices handle a wider range of workloads than ever before and they incorporate a growing gamut of sensors that make devices smarter, more user friendly and secure. Conventional cameras in particular play a central role in such tasks, but they cannot record continuously, as the amount of redundant information recorded is costly to process. Bio-inspired event cameras on the other hand only record changes in a visual scene and have shown promising low-power applications that specifically suit mobile tasks such as face detection, gesture recognition or gaze tracking. Our prototype device is the first step towards embedding such an event camera into a battery-powered handheld device. The mobile framework allows us to stream events in real-time and opens up the possibilities for always-on and on-demand sensing on mobile phones. To liaise the asynchronous event camera output with synchronous von Neumann hardware, we look at how buffering events and processing them in batches can benefit mobile applications. We evaluate our framework in terms of latency and throughput and show examples of computer vision tasks that involve both event-by-event and pre-trained neural network methods for gesture recognition, aperture robust optical flow and grey-level image reconstruction from events. The code is available at https://github.com/neuromorphic-paris/frog

arXiv:2205.05916

Dynamic Dense RGB-D SLAM using Learning-based Visual Odometry

We propose a dense dynamic RGB-D SLAM pipeline based on a learning-based visual odometry, TartanVO. TartanVO, like other direct methods rather than feature-based, estimates camera pose through dense optical flow, which only applies to static scenes and disregards dynamic objects. Due to the color constancy assumption, optical flow is not able to differentiate between dynamic and static pixels. Therefore, to reconstruct a static map through such direct methods, our pipeline resolves dynamic/static segmentation by leveraging the optical flow output, and only fuse static points into the map. Moreover, we rerender the input frames such that the dynamic pixels are removed and iteratively pass them back into the visual odometry to refine the pose estimate.