PyTorchKR Papers

최신 논문

총 2,031편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2212.04679

Motion and Context-Aware Audio-Visual Conditioned Video Prediction

The existing state-of-the-art method for audio-visual conditioned video prediction uses the latent codes of the audio-visual frames from a multimodal stochastic network and a frame encoder to predict the next visual frame. However, a direct inference of per-pixel intensity for the next visual frame is extremely challenging because of the high-dimensional image space. To this end, we decouple the audio-visual conditioned video prediction into motion and appearance modeling. The multimodal motion estimation predicts future optical flow based on the audio-motion correlation. The visual branch recalls from the motion memory built from the audio features to enable better long term prediction. We further propose context-aware refinement to address the diminishing of the global appearance context in the long-term continuous warping. The global appearance context is extracted by the context encoder and manipulated by motion-conditioned affine transformation before fusion with features of warped frames. Experimental results show that our method achieves competitive results on existing benchmarks.

arXiv:2212.03384

DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition

Human activity recognition (HAR) using drone-mounted cameras has attracted considerable interest from the computer vision research community in recent years. A robust and efficient HAR system has a pivotal role in fields like video surveillance, crowd behavior analysis, sports analysis, and human-computer interaction. What makes it challenging are the complex poses, understanding different viewpoints, and the environmental scenarios where the action is taking place. To address such complexities, in this paper, we propose a novel Sparse Weighted Temporal Attention (SWTA) module to utilize sparsely sampled video frames for obtaining global weighted temporal attention. The proposed SWTA is comprised of two parts. First, temporal segment network that sparsely samples a given set of frames. Second, weighted temporal attention, which incorporates a fusion of attention maps derived from optical flow, with raw RGB images. This is followed by a basenet network, which comprises a convolutional neural network (CNN) module along with fully connected layers that provide us with activity recognition. The SWTA network can be used as a plug-in module to the existing deep CNN architectures, for optimizing them to learn temporal information by eliminating the need for a separate temporal stream. It has been evaluated on three publicly available benchmark datasets, namely Okutama, MOD20, and Drone-Action. The proposed model has received an accuracy of 72.76%, 92.56%, and 78.86% on the respective datasets thereby surpassing the previous state-of-the-art performances by a margin of 25.26%, 18.56%, and 2.94%, respectively.

arXiv:2212.03250

Neural Cell Video Synthesis via Optical-Flow Diffusion

The biomedical imaging world is notorious for working with small amounts of data, frustrating state-of-the-art efforts in the computer vision and deep learning worlds. With large datasets, it is easier to make progress we have seen from the natural image distribution. It is the same with microscopy videos of neuron cells moving in a culture. This problem presents several challenges as it can be difficult to grow and maintain the culture for days, and it is expensive to acquire the materials and equipment. In this work, we explore how to alleviate this data scarcity problem by synthesizing the videos. We, therefore, take the recent work of the video diffusion model to synthesize videos of cells from our training dataset. We then analyze the model's strengths and consistent shortcomings to guide us on improving video generation to be as high-quality as possible. To improve on such a task, we propose modifying the denoising function and adding motion information (dense optical flow) so that the model has more context regarding how video frames transition over time and how each pixel changes over time.

arXiv:2212.01762

Self-supervised AutoFlow

Recently, AutoFlow has shown promising results on learning a training set for optical flow, but requires ground truth labels in the target domain to compute its search metric. Observing a strong correlation between the ground truth search metric and self-supervised losses, we introduce self-supervised AutoFlow to handle real-world videos without ground truth labels. Using self-supervised loss as the search metric, our self-supervised AutoFlow performs on par with AutoFlow on Sintel and KITTI where ground truth is available, and performs better on the real-world DAVIS dataset. We further explore using self-supervised AutoFlow in the (semi-)supervised setting and obtain competitive results against the state of the art.

arXiv:2212.00256

Face Animation with Multiple Source Images

Face animation has received a lot of attention from researchers in recent years due to its wide range of promising applications. Many face animation models based on optical flow or deep neural networks have achieved great success. However, these models are likely to fail in animated scenarios with significant view changes, resulting in unrealistic or distorted faces. One of the possible reasons is that such models lack prior knowledge of human faces and are not proficient to imagine facial regions they have never seen before. In this paper, we propose a flexible and generic approach to improve the performance of face animation without additional training. We use multiple source images as input as compensation for the lack of prior knowledge of faces. The effectiveness of our method is experimentally demonstrated, where the proposed method successfully supplements the baseline method.

arXiv:2211.16922공식 코드 · Papers with Code

Learning Motion-Robust Remote Photoplethysmography through Arbitrary Resolution Videos

Remote photoplethysmography (rPPG) enables non-contact heart rate (HR) estimation from facial videos which gives significant convenience compared with traditional contact-based measurements. In the real-world long-term health monitoring scenario, the distance of the participants and their head movements usually vary by time, resulting in the inaccurate rPPG measurement due to the varying face resolution and complex motion artifacts. Different from the previous rPPG models designed for a constant distance between camera and participants, in this paper, we propose two plug-and-play blocks (i.e., physiological signal feature extraction block (PFE) and temporal face alignment block (TFA)) to alleviate the degradation of changing distance and head motion. On one side, guided with representative-area information, PFE adaptively encodes the arbitrary resolution facial frames to the fixed-resolution facial structure features. On the other side, leveraging the estimated optical flow, TFA is able to counteract the rPPG signal confusion caused by the head movement thus benefit the motion-robust rPPG signal recovery. Besides, we also train the model with a cross-resolution constraint using a two-stream dual-resolution framework, which further helps PFE learn resolution-robust facial rPPG features. Extensive experiments on three benchmark datasets (UBFC-rPPG, COHFACE and PURE) demonstrate the superior performance of the proposed method. One highlight is that with PFE and TFA, the off-the-shelf spatio-temporal rPPG models can predict more robust rPPG signals under both varying face resolution and severe head movement scenarios. The codes are available at https://github.com/LJW-GIT/Arbitrary_Resolution_rPPG.

arXiv:2211.15894

HashEncoding: Autoencoding with Multiscale Coordinate Hashing

We present HashEncoding, a novel autoencoding architecture that leverages a non-parametric multiscale coordinate hash function to facilitate a per-pixel decoder without convolutions. By leveraging the space-folding behaviour of hashing functions, HashEncoding allows for an inherently multiscale embedding space that remains much smaller than the original image. As a result, the decoder requires very few parameters compared with decoders in traditional autoencoders, approaching a non-parametric reconstruction of the original image and allowing for greater generalizability. Finally, by allowing backpropagation directly to the coordinate space, we show that HashEncoding can be exploited for geometric tasks such as optical flow.

arXiv:2211.14502공식 코드 · Papers with Code

Learning Single Image Defocus Deblurring with Misaligned Training Pairs

By adopting popular pixel-wise loss, existing methods for defocus deblurring heavily rely on well aligned training image pairs. Although training pairs of ground-truth and blurry images are carefully collected, e.g., DPDD dataset, misalignment is inevitable between training pairs, making existing methods possibly suffer from deformation artifacts. In this paper, we propose a joint deblurring and reblurring learning (JDRL) framework for single image defocus deblurring with misaligned training pairs. Generally, JDRL consists of a deblurring module and a spatially invariant reblurring module, by which deblurred result can be adaptively supervised by ground-truth image to recover sharp textures while maintaining spatial consistency with the blurry image. First, in the deblurring module, a bi-directional optical flow-based deformation is introduced to tolerate spatial misalignment between deblurred and ground-truth images. Second, in the reblurring module, deblurred result is reblurred to be spatially aligned with blurry image, by predicting a set of isotropic blur kernels and weighting maps. Moreover, we establish a new single image defocus deblurring (SDD) dataset, further validating our JDRL and also benefiting future research. Our JDRL can be applied to boost defocus deblurring networks in terms of both quantitative metrics and visual quality on DPDD, RealDOF and our SDD datasets.

arXiv:2211.15059공식 코드 · Papers with Code

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

A hallmark of the deep learning era for computer vision is the successful use of large-scale labeled datasets to train feature representations for tasks ranging from object recognition and semantic segmentation to optical flow estimation and novel view synthesis of 3D scenes. In this work, we aim to learn dense discriminative object representations for low-shot category recognition without requiring any category labels. To this end, we propose Deep Object Patch Encodings (DOPE), which can be trained from multiple views of object instances without any category or semantic object part labels. To train DOPE, we assume access to sparse depths, foreground masks and known cameras, to obtain pixel-level correspondences between views of an object, and use this to formulate a self-supervised learning task to learn discriminative object patches. We find that DOPE can directly be used for low-shot classification of novel categories using local-part matching, and is competitive with and outperforms supervised and self-supervised learning baselines. Code and data available at https://github.com/rehg-lab/dope_selfsup.

arXiv:2211.13726공식 코드 · Papers with Code

Lightweight Event-based Optical Flow Estimation via Iterative Deblurring

Inspired by frame-based methods, state-of-the-art event-based optical flow networks rely on the explicit construction of correlation volumes, which are expensive to compute and store, rendering them unsuitable for robotic applications with limited compute and energy budget. Moreover, correlation volumes scale poorly with resolution, prohibiting them from estimating high-resolution flow. We observe that the spatiotemporally continuous traces of events provide a natural search direction for seeking pixel correspondences, obviating the need to rely on gradients of explicit correlation volumes as such search directions. We introduce IDNet (Iterative Deblurring Network), a lightweight yet high-performing event-based optical flow network directly estimating flow from event traces without using correlation volumes. We further propose two iterative update schemes: "ID" which iterates over the same batch of events, and "TID" which iterates over time with streaming events in an online fashion. Our top-performing ID model sets a new state of the art on DSEC benchmark. Meanwhile, the base ID model is competitive with prior arts while using 80% fewer parameters, consuming 20x less memory footprint and running 40% faster on the NVidia Jetson Xavier NX. Furthermore, the TID model is even more efficient offering an additional 5x faster inference speed and 8 ms ultra-low latency at the cost of only a 9% performance drop, making it the only model among current literature capable of real-time operation while maintaining decent performance.

arXiv:2211.11988

Vision-based localization methods under GPS-denied conditions

This paper reviews vision-based localization methods in GPS-denied environments and classifies the mainstream methods into Relative Vision Localization (RVL) and Absolute Vision Localization (AVL). For RVL, we discuss the broad application of optical flow in feature extraction-based Visual Odometry (VO) solutions and introduce advanced optical flow estimation methods. For AVL, we review recent advances in Visual Simultaneous Localization and Mapping (VSLAM) techniques, from optimization-based methods to Extended Kalman Filter (EKF) based methods. We also introduce the application of offline map registration and lane vision detection schemes to achieve Absolute Visual Localization. This paper compares the performance and applications of mainstream methods for visual localization and provides suggestions for future studies.

arXiv:2211.11293공식 코드 · Papers with Code

Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer

Vision sensors are widely applied in vehicles, robots, and roadside infrastructure. However, due to limitations in hardware cost and system size, camera Field-of-View (FoV) is often restricted and may not provide sufficient coverage. Nevertheless, from a spatiotemporal perspective, it is possible to obtain information beyond the camera's physical FoV from past video streams. In this paper, we propose the concept of online video inpainting for autonomous vehicles to expand the field of view, thereby enhancing scene visibility, perception, and system safety. To achieve this, we introduce the FlowLens architecture, which explicitly employs optical flow and implicitly incorporates a novel clip-recurrent transformer for feature propagation. FlowLens offers two key features: 1) FlowLens includes a newly designed Clip-Recurrent Hub with 3D-Decoupled Cross Attention (DDCA) to progressively process global information accumulated over time. 2) It integrates a multi-branch Mix Fusion Feed Forward Network (MixF3N) to enhance the precise spatial flow of local features. To facilitate training and evaluation, we derive the KITTI360 dataset with various FoV mask, which covers both outer- and inner FoV expansion scenarios. We also conduct both quantitative assessments and qualitative comparisons of beyond-FoV semantics and beyond-FoV object detection across different models. We illustrate that employing FlowLens to reconstruct unseen scenes even enhances perception within the field of view by providing reliable semantic context. Extensive experiments and user studies involving offline and online video inpainting, as well as beyond-FoV perception tasks, demonstrate that FlowLens achieves state-of-the-art performance. The source code and dataset are made publicly available at https://github.com/MasterHow/FlowLens.

arXiv:2211.10408공식 코드 · Papers with Code

CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow

Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching or optical flow. The application of self-supervised concepts, such as instance discrimination or masked image modeling, to geometric tasks is an active area of research. In this work, we build on the recent cross-view completion framework, a variation of masked image modeling that leverages a second view from the same scene which makes it well suited for binocular downstream tasks. The applicability of this concept has so far been limited in at least two ways: (a) by the difficulty of collecting real-world image pairs -- in practice only synthetic data have been used -- and (b) by the lack of generalization of vanilla transformers to dense downstream tasks for which relative position is more meaningful than absolute position. We explore three avenues of improvement. First, we introduce a method to collect suitable real-world image pairs at large scale. Second, we experiment with relative positional embeddings and show that they enable vision transformers to perform substantially better. Third, we scale up vision transformer based cross-completion architectures, which is made possible by the use of large amounts of data. With these improvements, we show for the first time that state-of-the-art results on stereo matching and optical flow can be reached without using any classical task-specific techniques like correlation volume, iterative estimation, image warping or multi-scale reasoning, thus paving the way towards universal vision models.

arXiv:2211.10226공식 코드 · Papers with Code

Leveraging Multi-stream Information Fusion for Trajectory Prediction in Low-illumination Scenarios: A Multi-channel Graph Convolutional Approach

Trajectory prediction is a fundamental problem and challenge for autonomous vehicles. Early works mainly focused on designing complicated architectures for deep-learning-based prediction models in normal-illumination environments, which fail in dealing with low-light conditions. This paper proposes a novel approach for trajectory prediction in low-illumination scenarios by leveraging multi-stream information fusion, which flexibly integrates image, optical flow, and object trajectory information. The image channel employs Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) networks to extract temporal information from the camera. The optical flow channel is applied to capture the pattern of relative motion between adjacent camera frames and modelled by Spatial-Temporal Graph Convolutional Network (ST-GCN). The trajectory channel is used to recognize high-level interactions between vehicles. Finally, information from all the three channels is effectively fused in the prediction module to generate future trajectories of surrounding vehicles in low-illumination conditions. The proposed multi-channel graph convolutional approach is validated on HEV-I and newly generated Dark-HEV-I, egocentric vision datasets that primarily focus on urban intersection scenarios. The results demonstrate that our method outperforms the baselines, in standard and low-illumination scenarios. Additionally, our approach is generic and applicable to scenarios with different types of perception data. The source code of the proposed approach is available at https://github.com/TommyGong08/MSIF}{https://github.com/TommyGong08/MSIF.

arXiv:2211.09771공식 코드 · Papers with Code

Boosting Object Representation Learning via Motion and Object Continuity

Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they may produce suboptimal object encodings for downstream tasks. To overcome this, we propose to exploit object motion and continuity, i.e., objects do not pop in and out of existence. This is accomplished through two mechanisms: (i) providing priors on the location of objects through integration of optical flow, and (ii) a contrastive object continuity loss across consecutive image frames. Rather than developing an explicit deep architecture, the resulting Motion and Object Continuity (MOC) scheme can be instantiated using any baseline object detection model. Our results show large improvements in the performances of a SOTA model in terms of object discovery, convergence speed and overall latent object representations, particularly for playing Atari games. Overall, we show clear benefits of integrating motion and object continuity for downstream tasks, moving beyond object representation learning based only on reconstruction.

arXiv:2211.08703

SATVSR: Scenario Adaptive Transformer for Cross Scenarios Video Super-Resolution

Video Super-Resolution (VSR) aims to recover sequences of high-resolution (HR) frames from low-resolution (LR) frames. Previous methods mainly utilize temporally adjacent frames to assist the reconstruction of target frames. However, in the real world, there is a lot of irrelevant information in adjacent frames of videos with fast scene switching, these VSR methods cannot adaptively distinguish and select useful information. In contrast, with a transformer structure suitable for temporal tasks, we devise a novel adaptive scenario video super-resolution method. Specifically, we use optical flow to label the patches in each video frame, only calculate the attention of patches with the same label. Then select the most relevant label among them to supplement the spatial-temporal information of the target frame. This design can directly make the supplementary information come from the same scene as much as possible. We further propose a cross-scale feature aggregation module to better handle the scale variation problem. Compared with other video super-resolution methods, our method not only achieves significant performance gains on single-scene videos but also has better robustness on cross-scene datasets.

arXiv:2211.09078공식 코드 · Papers with Code

Learning Dense and Continuous Optical Flow from an Event Camera

Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical flow estimation methods are based on two consecutive image frames and can only estimate discrete flow at a fixed time interval. Previous work has shown that continuous flow estimation can be achieved by changing the quantities or time intervals of events. However, they are difficult to estimate reliable dense flow , especially in the regions without any triggered events. In this paper, we propose a novel deep learning-based dense and continuous optical flow estimation framework from a single image with event streams, which facilitates the accurate perception of high-speed motion. Specifically, we first propose an event-image fusion and correlation module to effectively exploit the internal motion from two different modalities of data. Then we propose an iterative update network structure with bidirectional training for optical flow prediction. Therefore, our model can estimate reliable dense flow as two-frame-based methods, as well as estimate temporal continuous flow as event-based methods. Extensive experimental results on both synthetic and real captured datasets demonstrate that our model outperforms existing event-based state-of-the-art methods and our designed baselines for accurate dense and continuous optical flow estimation.

arXiv:2211.08367공식 코드 · Papers with Code

FlowGrad: Using Motion for Visual Sound Source Localization

Most recent work in visual sound source localization relies on semantic audio-visual representations learned in a self-supervised manner, and by design excludes temporal information present in videos. While it proves to be effective for widely used benchmark datasets, the method falls short for challenging scenarios like urban traffic. This work introduces temporal context into the state-of-the-art methods for sound source localization in urban scenes using optical flow as a means to encode motion information. An analysis of the strengths and weaknesses of our methods helps us better understand the problem of visual sound source localization and sheds light on open challenges for audio-visual scene understanding.

arXiv:2211.08049

Forecasting Future Instance Segmentation with Learned Optical Flow and Warping

For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others. This can be done using different sensors and modalities. In this paper we investigate the usage of optical flow for predicting future semantic segmentations. To do so we propose a model that forecasts flow fields autoregressively. Such predictions are then used to guide the inference of a learned warping function that moves instance segmentations on to future frames. Results on the Cityscapes dataset demonstrate the effectiveness of optical-flow methods.

arXiv:2211.06024

Progressive Motion Context Refine Network for Efficient Video Frame Interpolation

Recently, flow-based frame interpolation methods have achieved great success by first modeling optical flow between target and input frames, and then building synthesis network for target frame generation. However, above cascaded architecture can lead to large model size and inference delay, hindering them from mobile and real-time applications. To solve this problem, we propose a novel Progressive Motion Context Refine Network (PMCRNet) to predict motion fields and image context jointly for higher efficiency. Different from others that directly synthesize target frame from deep feature, we explore to simplify frame interpolation task by borrowing existing texture from adjacent input frames, which means that decoder in each pyramid level of our PMCRNet only needs to update easier intermediate optical flow, occlusion merge mask and image residual. Moreover, we introduce a new annealed multi-scale reconstruction loss to better guide the learning process of this efficient PMCRNet. Experiments on multiple benchmarks show that proposed approaches not only achieve favorable quantitative and qualitative results but also reduces current model size and running time significantly.