CT perfusion imaging (CTP) plays an important role in decision making for the treatment of acute ischemic stroke with large vessel occlusion. Since the CT perfusion scan time is approximately one minute, the patient is exposed to a non-negligible dose of ionizing radiation. However, further dose reduction increases the level of noise in the data and the resulting perfusion maps. We present a method for reducing noise in perfusion data based on dimension reduction of time attenuation curves. For dimension reduction, we use either the fit of the first five terms of the trigonometric polynomial or the first five terms of the SVD decomposition of the time attenuation profiles. CTP data from four patients with large vessel occlusion and three control subjects were studied. To compare the noise level in the perfusion maps, we use the wavelet estimation of the noise standard deviation implemented in the scikit-image package. We show that both methods significantly reduce noise in the data while preserving important information about the perfusion deficits. These methods can be used to further reduce the dose in CT perfusion protocols or in perfusion studies using C-arm CT, which are burdened by high noise levels.
Although recent works based on deep learning have made progress in improving recognition accuracy on scene text recognition, how to handle low-quality text images in end-to-end deep networks remains a research challenge. In this paper, we propose an Iterative Fusion based Recognizer (IFR) for low quality scene text recognition, taking advantage of refined text images input and robust feature representation. IFR contains two branches which focus on scene text recognition and low quality scene text image recovery respectively. We utilize an iterative collaboration between two branches, which can effectively alleviate the impact of low quality input. A feature fusion module is proposed to strengthen the feature representation of the two branches, where the features from the Recognizer are Fused with image Restoration branch, referred to as RRF. Without changing the recognition network structure, extensive quantitative and qualitative experimental results show that the proposed method significantly outperforms the baseline methods in boosting the recognition accuracy of benchmark datasets and low resolution images in TextZoom dataset.
In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources. OPT is constructed in an encoder-decoder framework, including three single-modal encoders to generate token-based embeddings for each modality, a cross-modal encoder to encode the correlations among the three modalities, and two cross-modal decoders to generate text and image respectively. For the OPT's pre-training, we design a multi-task pretext learning scheme to model multi-modal resources from three different data granularities, \ie, token-, modality-, and sample-level modeling, through which OPT learns to align and translate among different modalities. The pre-training task is carried out on a large amount of image-text-audio triplets from Open Images. Experimental results show that OPT can learn strong image-text-audio multi-modal representations and achieve promising results on a variety of cross-modal understanding and generation tasks.
Decomposing a scene into its shape, reflectance and illumination is a fundamental problem in computer vision and graphics. Neural approaches such as NeRF have achieved remarkable success in view synthesis, but do not explicitly perform decomposition and instead operate exclusively on radiance (the product of reflectance and illumination). Extensions to NeRF, such as NeRD, can perform decomposition but struggle to accurately recover detailed illumination, thereby significantly limiting realism. We propose a novel reflectance decomposition network that can estimate shape, BRDF, and per-image illumination given a set of object images captured under varying illumination. Our key technique is a novel illumination integration network called Neural-PIL that replaces a costly illumination integral operation in the rendering with a simple network query. In addition, we also learn deep low-dimensional priors on BRDF and illumination representations using novel smooth manifold auto-encoders. Our decompositions can result in considerably better BRDF and light estimates enabling more accurate novel view-synthesis and relighting compared to prior art. Project page: https://markboss.me/publication/2021-neural-pil/
In traffic management, it is a very important issue to shorten the response time by detecting the incidents (accident, vehicle breakdown, an object falling on the road, etc.) and informing the corresponding personnel. In this study, an anomaly detection framework for road junctions is proposed. The final judgment is based on the trajectories followed by the vehicles. Trajectory information is provided by vehicle detection and tracking algorithms on visual data streamed from a fisheye camera. Deep learning algorithms are used for vehicle detection, and Kalman Filter is used for tracking. To observe the trajectories more accurately, the detected vehicle coordinates are transferred to the bird's eye view coordinates using the lens distortion model prediction algorithm. The system determines whether there is an abnormality in trajectories by comparing historical trajectory data and instantaneous incoming data. The proposed system has achieved 84.6% success in vehicle detection and 96.8% success in abnormality detection on synthetic data. The system also works with a 97.3% success rate in detecting abnormalities on real data.
In this paper, we propose $\tau$GAN a tensor-based method for modeling the latent space of generative models. The objective is to identify semantic directions in latent space. To this end, we propose to fit a multilinear tensor model on a structured facial expression database, which is initially embedded into latent space. We validate our approach on StyleGAN trained on FFHQ using BU-3DFE as a structured facial expression database. We show how the parameters of the multilinear tensor model can be approximated by Alternating Least Squares. Further, we introduce a tacked style-separated tensor model, defined as an ensemble of style-specific models to integrate our approach with the extended latent space of StyleGAN. We show that taking the individual styles of the extended latent space into account leads to higher model flexibility and lower reconstruction error. Finally, we do several experiments comparing our approach to former work on both GANs and multilinear models. Concretely, we analyze the expression subspace and find that the expression trajectories meet at an apathetic face that is consistent with earlier work. We also show that by changing the pose of a person, the generated image from our approach is closer to the ground truth than results from two competing approaches.
Semantic segmentation has attracted a large amount of attention in recent years. In robotics, segmentation can be used to identify a region of interest, or \emph{target area}. For example, in the RoboCup Standard Platform League (SPL), segmentation separates the soccer field from the background and from players on the field. For satellite or vehicle applications, it is often necessary to find certain regions such as roads, bodies of water or kinds of terrain. In this paper, we propose a novel approach to real-time target area segmentation based on a newly designed spatial temporal network. The method operates under domain constraints defined by both the robot's hardware and its operating environment . The proposed network is able to run in real-time, working within the constraints of limited run time and computing power. This work is compared against other real time segmentation methods on a dataset generated by a Nao V6 humanoid robot simulating the RoboCup SPL competition. In this case, the target area is defined as the artificial grass field. The method is also tested on a maritime dataset collected by a moving vessel, where the aim is to separate the ocean region from the rest of the image. This dataset demonstrates that the proposed model can generalise to a variety of vision problems.
Quantifying segmentation uncertainty has become an important issue in medical image analysis due to the inherent ambiguity of anatomical structures and its pathologies. Recently, neural network-based uncertainty quantification methods have been successfully applied to various problems. One of the main limitations of the existing techniques is the high memory requirement during training; which limits their application to processing smaller field-of-views (FOVs) and/or using shallower architectures. In this paper, we investigate the effect of using reversible blocks for building memory-efficient neural network architectures for quantification of segmentation uncertainty. The reversible architecture achieves memory saving by exactly computing the activations from the outputs of the subsequent layers during backpropagation instead of storing the activations for each layer. We incorporate the reversible blocks into a recently proposed architecture called PHiSeg that is developed for uncertainty quantification in medical image segmentation. The reversible architecture, RevPHiSeg, allows training neural networks for quantifying segmentation uncertainty on GPUs with limited memory and processing larger FOVs. We perform experiments on the LIDC-IDRI dataset and an in-house prostate dataset, and present comparisons with PHiSeg. The results demonstrate that RevPHiSeg consumes ~30% less memory compared to PHiSeg while achieving very similar segmentation accuracy.
Camera arrays provide spatial and angular information within a single snapshot. With refocusing methods, focal planes can be altered after exposure. In this letter, we propose a light field refocusing method to improve the imaging quality of camera arrays. In our method, the disparity is first estimated. Then, the unfocused region (bokeh) is rendered by using a depth-based anisotropic filter. Finally, the refocused image is produced by a reconstruction-based superresolution approach where the bokeh image is used as a regularization term. Our method can selectively refocus images with focused region being superresolved and bokeh being aesthetically rendered. Our method also enables postadjustment of depth of field. We conduct experiments on both public and self-developed datasets. Our method achieves superior visual performance with acceptable computational cost as compared to other state-of-the-art methods. Code is available at https://github.com/YingqianWang/Selective-LF-Refocusing.
Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements have been largely made possible by Generative Adversarial Networks (GANs). While these deep fake images have been thoroughly investigated in the image domain-a classical approach from the area of image forensics-an analysis in the frequency domain has been missing so far. In this paper, we address this shortcoming and our results reveal that in frequency space, GAN-generated images exhibit severe artifacts that can be easily identified. We perform a comprehensive analysis, showing that these artifacts are consistent across different neural network architectures, data sets, and resolutions. In a further investigation, we demonstrate that these artifacts are caused by upsampling operations found in all current GAN architectures, indicating a structural and fundamental problem in the way images are generated via GANs. Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.