PyTorchKR Papers

최신 논문

총 622편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

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:2211.11293공식 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:2211.09078공식 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:2211.06018공식 코드 · Papers with Code

MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term for continual self-supervision, which has been proved to be effective on difficult matching regions. However, this method also amplify the inevitable mismatch in unsupervised setting, blocking the learning process towards optimal solution. To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement. Concretely, taking estimation of off-the-shelf unsupervised approach as pseudo labels, our insight locates at defining a confidence selection mechanism to extract relative good matches, and then add diverse data augmentation for distilling adequate and reliable knowledge from teacher to student. Thanks to the decouple nature of our method, we can choose a stronger student architecture for sufficient learning. Finally, better student prediction is adopted to transfer knowledge back to the efficient teacher without additional costs in real deployment. Rather than formulating it as a supervised task, we find that introducing an extra unsupervised term for multi-target learning achieves best final results. Extensive experiments show that our approach, termed MDFlow, achieves state-of-the-art real-time accuracy and generalization ability on challenging benchmarks. Code is available at https://github.com/ltkong218/MDFlow.

arXiv:2211.05783공식 코드 · Papers with Code

Unifying Flow, Stereo and Depth Estimation

We present a unified formulation and model for three motion and 3D perception tasks: optical flow, rectified stereo matching and unrectified stereo depth estimation from posed images. Unlike previous specialized architectures for each specific task, we formulate all three tasks as a unified dense correspondence matching problem, which can be solved with a single model by directly comparing feature similarities. Such a formulation calls for discriminative feature representations, which we achieve using a Transformer, in particular the cross-attention mechanism. We demonstrate that cross-attention enables integration of knowledge from another image via cross-view interactions, which greatly improves the quality of the extracted features. Our unified model naturally enables cross-task transfer since the model architecture and parameters are shared across tasks. We outperform RAFT with our unified model on the challenging Sintel dataset, and our final model that uses a few additional task-specific refinement steps outperforms or compares favorably to recent state-of-the-art methods on 10 popular flow, stereo and depth datasets, while being simpler and more efficient in terms of model design and inference speed.

arXiv:2211.05709공식 코드 · Papers with Code

AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies

Existing correspondence datasets for two-dimensional (2D) cartoon suffer from simple frame composition and monotonic movements, making them insufficient to simulate real animations. In this work, we present a new 2D animation visual correspondence dataset, AnimeRun, by converting open source three-dimensional (3D) movies to full scenes in 2D style, including simultaneous moving background and interactions of multiple subjects. Our analyses show that the proposed dataset not only resembles real anime more in image composition, but also possesses richer and more complex motion patterns compared to existing datasets. With this dataset, we establish a comprehensive benchmark by evaluating several existing optical flow and segment matching methods, and analyze shortcomings of these methods on animation data. Data, code and other supplementary materials are available at https://lisiyao21.github.io/projects/AnimeRun.

arXiv:2211.03726공식 코드 · Papers with Code

TAP-Vid: A Benchmark for Tracking Any Point in a Video

Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move. This information is useful to make inferences about 3D shape, physical properties and object interactions. While the problem of tracking arbitrary physical points on surfaces over longer video clips has received some attention, no dataset or benchmark for evaluation existed, until now. In this paper, we first formalize the problem, naming it tracking any point (TAP). We introduce a companion benchmark, TAP-Vid, which is composed of both real-world videos with accurate human annotations of point tracks, and synthetic videos with perfect ground-truth point tracks. Central to the construction of our benchmark is a novel semi-automatic crowdsourced pipeline which uses optical flow estimates to compensate for easier, short-term motion like camera shake, allowing annotators to focus on harder sections of video. We validate our pipeline on synthetic data and propose a simple end-to-end point tracking model TAP-Net, showing that it outperforms all prior methods on our benchmark when trained on synthetic data.

arXiv:2211.03456공식 코드 · Papers with Code

A Unified Pyramid Recurrent Network for Video Frame Interpolation

Flow-guided synthesis provides a common framework for frame interpolation, where optical flow is estimated to guide the synthesis of intermediate frames between consecutive inputs. In this paper, we present UPR-Net, a novel Unified Pyramid Recurrent Network for frame interpolation. Cast in a flexible pyramid framework, UPR-Net exploits lightweight recurrent modules for both bi-directional flow estimation and intermediate frame synthesis. At each pyramid level, it leverages estimated bi-directional flow to generate forward-warped representations for frame synthesis; across pyramid levels, it enables iterative refinement for both optical flow and intermediate frame. In particular, we show that our iterative synthesis strategy can significantly improve the robustness of frame interpolation on large motion cases. Despite being extremely lightweight (1.7M parameters), our base version of UPR-Net achieves excellent performance on a large range of benchmarks. Code and trained models of our UPR-Net series are available at: https://github.com/srcn-ivl/UPR-Net.

arXiv:2211.03019공식 코드 · Papers with Code

Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization

Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the source of the sound. In a video, oftentimes, the objects exhibiting movement are the ones generating the sound. In this work, we capture this characteristic by modeling the optical flow in a video as a prior to better aid in localizing the sound source. We further demonstrate that the addition of flow-based attention substantially improves visual sound source localization. Finally, we benchmark our method on standard sound source localization datasets and achieve state-of-the-art performance on the Soundnet Flickr and VGG Sound Source datasets. Code: https://github.com/denfed/heartheflow.

arXiv:2210.16900공식 코드 · Papers with Code

High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)

In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this method by exploiting an additional finer scale for estimating the flow, which is made feasible by on-demand cost computation. This way, it can not only operate at half the original resolution, but also use MS-RAFT's shared convex upsampler to obtain full resolution flow. Moreover, our approach relies on an adjusted fine-tuning scheme during training. This in turn aims at improving the generalization across benchmarks. Among all participating methods in the Robust Vision Challenge, our approach ranks first on VIPER and second on KITTI, Sintel, and Middlebury, resulting in the first place of the overall ranking.

arXiv:2210.15872공식 코드 · Papers with Code

Exploring Spatial-Temporal Features for Deepfake Detection and Localization

With the continuous research on Deepfake forensics, recent studies have attempted to provide the fine-grained localization of forgeries, in addition to the coarse classification at the video-level. However, the detection and localization performance of existing Deepfake forensic methods still have plenty of room for further improvement. In this work, we propose a Spatial-Temporal Deepfake Detection and Localization (ST-DDL) network that simultaneously explores spatial and temporal features for detecting and localizing forged regions. Specifically, we design a new Anchor-Mesh Motion (AMM) algorithm to extract temporal (motion) features by modeling the precise geometric movements of the facial micro-expression. Compared with traditional motion extraction methods (e.g., optical flow) designed to simulate large-moving objects, our proposed AMM could better capture the small-displacement facial features. The temporal features and the spatial features are then fused in a Fusion Attention (FA) module based on a Transformer architecture for the eventual Deepfake forensic tasks. The superiority of our ST-DDL network is verified by experimental comparisons with several state-of-the-art competitors, in terms of both video- and pixel-level detection and localization performance. Furthermore, to impel the future development of Deepfake forensics, we build a public forgery dataset consisting of 6000 videos, with many new features such as using widely-used commercial software (e.g., After Effects) for the production, providing online social networks transmitted versions, and splicing multi-source videos. The source code and dataset are available at https://github.com/HighwayWu/ST-DDL.

arXiv:2210.15121공식 코드 · Papers with Code

Bootstrapping Human Optical Flow and Pose

We propose a bootstrapping framework to enhance human optical flow and pose. We show that, for videos involving humans in scenes, we can improve both the optical flow and the pose estimation quality of humans by considering the two tasks at the same time. We enhance optical flow estimates by fine-tuning them to fit the human pose estimates and vice versa. In more detail, we optimize the pose and optical flow networks to, at inference time, agree with each other. We show that this results in state-of-the-art results on the Human 3.6M and 3D Poses in the Wild datasets, as well as a human-related subset of the Sintel dataset, both in terms of pose estimation accuracy and the optical flow accuracy at human joint locations. Code available at https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose

arXiv:2210.13769공식 코드 · Papers with Code

GlobalFlowNet: Video Stabilization using Deep Distilled Global Motion Estimates

Videos shot by laymen using hand-held cameras contain undesirable shaky motion. Estimating the global motion between successive frames, in a manner not influenced by moving objects, is central to many video stabilization techniques, but poses significant challenges. A large body of work uses 2D affine transformations or homography for the global motion. However, in this work, we introduce a more general representation scheme, which adapts any existing optical flow network to ignore the moving objects and obtain a spatially smooth approximation of the global motion between video frames. We achieve this by a knowledge distillation approach, where we first introduce a low pass filter module into the optical flow network to constrain the predicted optical flow to be spatially smooth. This becomes our student network, named as \textsc{GlobalFlowNet}. Then, using the original optical flow network as the teacher network, we train the student network using a robust loss function. Given a trained \textsc{GlobalFlowNet}, we stabilize videos using a two stage process. In the first stage, we correct the instability in affine parameters using a quadratic programming approach constrained by a user-specified cropping limit to control loss of field of view. In the second stage, we stabilize the video further by smoothing global motion parameters, expressed using a small number of discrete cosine transform coefficients. In extensive experiments on a variety of different videos, our technique outperforms state of the art techniques in terms of subjective quality and different quantitative measures of video stability. The source code is publicly available at \href{https://github.com/GlobalFlowNet/GlobalFlowNet}{https://github.com/GlobalFlowNet/GlobalFlowNet}

arXiv:2210.10716공식 코드 · Papers with Code

CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible patches as sole input. This pre-training leads to state-of-the-art performance when finetuned for high-level semantic tasks, e.g. image classification and object detection. In this paper we instead seek to learn representations that transfer well to a wide variety of 3D vision and lower-level geometric downstream tasks, such as depth prediction or optical flow estimation. Inspired by MIM, we propose an unsupervised representation learning task trained from pairs of images showing the same scene from different viewpoints. More precisely, we propose the pretext task of cross-view completion where the first input image is partially masked, and this masked content has to be reconstructed from the visible content and the second image. In single-view MIM, the masked content often cannot be inferred precisely from the visible portion only, so the model learns to act as a prior influenced by high-level semantics. In contrast, this ambiguity can be resolved with cross-view completion from the second unmasked image, on the condition that the model is able to understand the spatial relationship between the two images. Our experiments show that our pretext task leads to significantly improved performance for monocular 3D vision downstream tasks such as depth estimation. In addition, our model can be directly applied to binocular downstream tasks like optical flow or relative camera pose estimation, for which we obtain competitive results without bells and whistles, i.e., using a generic architecture without any task-specific design.

arXiv:2210.07400공식 코드 · Papers with Code

Real-time Action Recognition for Fine-Grained Actions and The Hand Wash Dataset

In this paper we present a three-stream algorithm for real-time action recognition and a new dataset of handwash videos, with the intent of aligning action recognition with real-world constraints to yield effective conclusions. A three-stream fusion algorithm is proposed, which runs both accurately and efficiently, in real-time even on low-powered systems such as a Raspberry Pi. The cornerstone of the proposed algorithm is the incorporation of both spatial and temporal information, as well as the information of the objects in a video while using an efficient architecture, and Optical Flow computation to achieve commendable results in real-time. The results achieved by this algorithm are benchmarked on the UCF-101 as well as the HMDB-51 datasets, achieving an accuracy of 92.7% and 64.9% respectively. An important point to note is that the algorithm is novel in the aspect that it is also able to learn the intricate differences between extremely similar actions, which would be difficult even for the human eye. Additionally, noticing a dearth in the number of datasets for the recognition of very similar or fine-grained actions, this paper also introduces a new dataset that is made publicly available, the Hand Wash Dataset with the intent of introducing a new benchmark for fine-grained action recognition tasks in the future.