Event cameras are novel bio-inspired sensors that measure per-pixel brightness differences asynchronously. Recovering brightness from events is appealing since the reconstructed images inherit the high dynamic range (HDR) and high-speed properties of events; hence they can be used in many robotic vision applications and to generate slow-motion HDR videos. However, state-of-the-art methods tackle this problem by training an event-to-image Recurrent Neural Network (RNN), which lacks explainability and is difficult to tune. In this work we show, for the first time, how tackling the combined problem of motion and brightness estimation leads us to formulate event-based image reconstruction as a linear inverse problem that can be solved without training an image reconstruction RNN. Instead, classical and learning-based regularizers are used to solve the problem and remove artifacts from the reconstructed images. The experiments show that the proposed approach generates images with visual quality on par with state-of-the-art methods despite only using data from a short time interval. State-of-the-art results are achieved using an image denoising Convolutional Neural Network (CNN) as the regularization function. The proposed regularized formulation and solvers have a unifying character because they can be applied also to reconstruct brightness from the second derivative. Additionally, the formulation is attractive because it can be naturally combined with super-resolution, motion-segmentation and color demosaicing. Code is available at //github.com/tub-rip/event_based_image_rec_inverse_problem
相關內容
Designing a real-time framework for the spatio-temporal action detection task is still a challenge. In this paper, we propose a novel real-time action detection framework, YOWOv2. In this new framework, YOWOv2 takes advantage of both the 3D backbone and 2D backbone for accurate action detection. A multi-level detection pipeline is designed to detect action instances of different scales. To achieve this goal, we carefully build a simple and efficient 2D backbone with a feature pyramid network to extract different levels of classification features and regression features. For the 3D backbone, we adopt the existing efficient 3D CNN to save development time. By combining 3D backbones and 2D backbones of different sizes, we design a YOWOv2 family including YOWOv2-Tiny, YOWOv2-Medium, and YOWOv2-Large. We also introduce the popular dynamic label assignment strategy and anchor-free mechanism to make the YOWOv2 consistent with the advanced model architecture design. With our improvement, YOWOv2 is significantly superior to YOWO, and can still keep real-time detection. Without any bells and whistles, YOWOv2 achieves 87.0 % frame mAP and 52.8 % video mAP with over 20 FPS on the UCF101-24. On the AVA, YOWOv2 achieves 21.7 % frame mAP with over 20 FPS. Our code is available on //github.com/yjh0410/YOWOv2.
Event-based cameras are raising interest within the computer vision community. These sensors operate with asynchronous pixels, emitting events, or "spikes", when the luminance change at a given pixel since the last event surpasses a certain threshold. Thanks to their inherent qualities, such as their low power consumption, low latency and high dynamic range, they seem particularly tailored to applications with challenging temporal constraints and safety requirements. Event-based sensors are an excellent fit for Spiking Neural Networks (SNNs), since the coupling of an asynchronous sensor with neuromorphic hardware can yield real-time systems with minimal power requirements. In this work, we seek to develop one such system, using both event sensor data from the DSEC dataset and spiking neural networks to estimate optical flow for driving scenarios. We propose a U-Net-like SNN which, after supervised training, is able to make dense optical flow estimations. To do so, we encourage both minimal norm for the error vector and minimal angle between ground-truth and predicted flow, training our model with back-propagation using a surrogate gradient. In addition, the use of 3d convolutions allows us to capture the dynamic nature of the data by increasing the temporal receptive fields. Upsampling after each decoding stage ensures that each decoder's output contributes to the final estimation. Thanks to separable convolutions, we have been able to develop a light model (when compared to competitors) that can nonetheless yield reasonably accurate optical flow estimates.
Deep Unfolding of the DBFB Algorithm with Application to ROI CT Imaging with Limited Angular Density
This paper presents a new method for reconstructing regions of interest (ROI) from a limited number of computed tomography (CT) measurements. Classical model-based iterative reconstruction methods lead to images with predictable features. Still, they often suffer from tedious parameterization and slow convergence. On the contrary, deep learning methods are fast, and they can reach high reconstruction quality by leveraging information from large datasets, but they lack interpretability. At the crossroads of both methods, deep unfolding networks have been recently proposed. Their design includes the physics of the imaging system and the steps of an iterative optimization algorithm. Motivated by the success of these networks for various applications, we introduce an unfolding neural network called U-RDBFB designed for ROI CT reconstruction from limited data. Few-view truncated data are effectively handled thanks to a robust non-convex data fidelity term combined with a sparsity-inducing regularization function. We unfold the Dual Block coordinate Forward-Backward (DBFB) algorithm, embedded in an iterative reweighted scheme, allowing the learning of key parameters in a supervised manner. Our experiments show an improvement over several state-of-the-art methods, including a model-based iterative scheme, a multi-scale deep learning architecture, and deep unfolding methods.
In this paper, we study the local visual modeling with grid features for image captioning, which is critical for generating accurate and detailed captions. To achieve this target, we propose a Locality-Sensitive Transformer Network (LSTNet) with two novel designs, namely Locality-Sensitive Attention (LSA) and Locality-Sensitive Fusion (LSF). LSA is deployed for the intra-layer interaction in Transformer via modeling the relationship between each grid and its neighbors. It reduces the difficulty of local object recognition during captioning. LSF is used for inter-layer information fusion, which aggregates the information of different encoder layers for cross-layer semantical complementarity. With these two novel designs, the proposed LSTNet can model the local visual information of grid features to improve the captioning quality. To validate LSTNet, we conduct extensive experiments on the competitive MS-COCO benchmark. The experimental results show that LSTNet is not only capable of local visual modeling, but also outperforms a bunch of state-of-the-art captioning models on offline and online testings, i.e., 134.8 CIDEr and 136.3 CIDEr, respectively. Besides, the generalization of LSTNet is also verified on the Flickr8k and Flickr30k datasets
Inertial Measurement Units (IMU) are commonly used in inertial attitude estimation from engineering to medical sciences. There may be disturbances and high dynamics in the environment of these applications. Also, their motion characteristics and patterns also may differ. Many conventional filters have been proposed to tackle the inertial attitude estimation problem based on IMU measurements. There is no generalization over motion and environmental characteristics in these filters. As a result, the presented conventional filters will face various motion characteristics and patterns, which will limit filter performance and need to optimize the filter parameters for each situation. In this paper, two end-to-end deep-learning models are proposed to solve the problem of real-time attitude estimation by using inertial sensor measurements, which are generalized to motion patterns, sampling rates, and environmental disturbances. The proposed models incorporate accelerometer and gyroscope readings as inputs, which are collected from a combination of seven public datasets. The models consist of convolutional neural network (CNN) layers combined with Bi-Directional Long-Short Term Memory (LSTM) followed by a Fully Forward Neural Network (FFNN) to estimate the quaternion. To evaluate the validity and reliability, we have performed an extensive and comprehensive evaluation over seven publicly available datasets, which consist of more than 120 hours and 200 kilometers of IMU measurements. The results show that the proposed method outperforms the state-of-the-art methods in terms of accuracy and robustness. Furthermore, it demonstrates that this model generalizes better than other methods over various motion characteristics and sensor sampling rates.
Accurate localization is a core component of a robot's navigation system. To this end, global navigation satellite systems (GNSS) can provide absolute measurements outdoors and, therefore, eliminate long-term drift. However, fusing GNSS data with other sensor data is not trivial, especially when a robot moves between areas with and without sky view. We propose a robust approach that tightly fuses raw GNSS receiver data with inertial measurements and, optionally, lidar observations for precise and smooth mobile robot localization. A factor graph with two types of GNSS factors is proposed. First, factors based on pseudoranges, which allow for global localization on Earth. Second, factors based on carrier phases, which enable highly accurate relative localization, which is useful when other sensing modalities are challenged. Unlike traditional differential GNSS, this approach does not require a connection to a base station. On a public urban driving dataset, our approach achieves accuracy comparable to a state-of-the-art algorithm that fuses visual inertial odometry with GNSS data -- despite our approach not using the camera, just inertial and GNSS data. We also demonstrate the robustness of our approach using data from a car and a quadruped robot moving in environments with little sky visibility, such as a forest. The accuracy in the global Earth frame is still 1-2 m, while the estimated trajectories are discontinuity-free and smooth. We also show how lidar measurements can be tightly integrated. We believe this is the first system that fuses raw GNSS observations (as opposed to fixes) with lidar.
Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably polluted by noise, which may significantly undermine the efficacy of the learned models. Various attempts have been made to reliably train DNNs under data noise, but they separately account for either the noise existing in the labels or that existing in the images. A naive combination of the two lines of works would suffer from the limitations in both sides, and miss the opportunities to handle the two kinds of noise in parallel. This work provides a first, unified framework for reliable learning under the joint (image, label)-noise. Technically, we develop a confidence-based sample filter to progressively filter out noisy data without the need of pre-specifying noise ratio. Then, we penalize the model uncertainty of the detected noisy data instead of letting the model continue over-fitting the misleading information in them. Experimental results on various challenging synthetic and real-world noisy datasets verify that the proposed method can outperform competing baselines in the aspect of classification performance.
We propose a method for 3D shape reconstruction from unoriented point clouds. Our method consists of a novel SE(3)-equivariant coordinate-based network (TF-ONet), that parametrizes the occupancy field of the shape and respects the inherent symmetries of the problem. In contrast to previous shape reconstruction methods that align the input to a regular grid, we operate directly on the irregular point cloud. Our architecture leverages equivariant attention layers that operate on local tokens. This mechanism enables local shape modelling, a crucial property for scalability to large scenes. Given an unoriented, sparse, noisy point cloud as input, we produce equivariant features for each point. These serve as keys and values for the subsequent equivariant cross-attention blocks that parametrize the occupancy field. By querying an arbitrary point in space, we predict its occupancy score. We show that our method outperforms previous SO(3)-equivariant methods, as well as non-equivariant methods trained on SO(3)-augmented datasets. More importantly, local modelling together with SE(3)-equivariance create an ideal setting for SE(3) scene reconstruction. We show that by training only on single, aligned objects and without any pre-segmentation, we can reconstruct novel scenes containing arbitrarily many objects in random poses without any performance loss.
Detection and recognition of text in natural images are two main problems in the field of computer vision that have a wide variety of applications in analysis of sports videos, autonomous driving, industrial automation, to name a few. They face common challenging problems that are factors in how text is represented and affected by several environmental conditions. The current state-of-the-art scene text detection and/or recognition methods have exploited the witnessed advancement in deep learning architectures and reported a superior accuracy on benchmark datasets when tackling multi-resolution and multi-oriented text. However, there are still several remaining challenges affecting text in the wild images that cause existing methods to underperform due to there models are not able to generalize to unseen data and the insufficient labeled data. Thus, unlike previous surveys in this field, the objectives of this survey are as follows: first, offering the reader not only a review on the recent advancement in scene text detection and recognition, but also presenting the results of conducting extensive experiments using a unified evaluation framework that assesses pre-trained models of the selected methods on challenging cases, and applies the same evaluation criteria on these techniques. Second, identifying several existing challenges for detecting or recognizing text in the wild images, namely, in-plane-rotation, multi-oriented and multi-resolution text, perspective distortion, illumination reflection, partial occlusion, complex fonts, and special characters. Finally, the paper also presents insight into the potential research directions in this field to address some of the mentioned challenges that are still encountering scene text detection and recognition techniques.
Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings, and achieved state-of-the-art results in tasks such as node classification and link prediction. However, current GNN methods are inherently flat and do not learn hierarchical representations of graphs---a limitation that is especially problematic for the task of graph classification, where the goal is to predict the label associated with an entire graph. Here we propose DiffPool, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep GNN, mapping nodes to a set of clusters, which then form the coarsened input for the next GNN layer. Our experimental results show that combining existing GNN methods with DiffPool yields an average improvement of 5-10% accuracy on graph classification benchmarks, compared to all existing pooling approaches, achieving a new state-of-the-art on four out of five benchmark data sets.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191