Event cameras capture changes of illumination in the observed scene rather than accumulating light to create images. Thus, they allow for applications under high-speed motion and complex lighting conditions, where traditional framebased sensors show their limits with blur and over- or underexposed pixels. Thanks to these unique properties, they represent nowadays an highly attractive sensor for ITS-related applications. Event-based optical flow (EBOF) has been studied following the rise in popularity of these neuromorphic cameras. The recent arrival of high-definition neuromorphic sensors, however, challenges the existing approaches, because of the increased resolution of the events pixel array and a much higher throughput. As an answer to these points, we propose an optimized framework for computing optical flow in real-time with both low- and high-resolution event cameras. We formulate a novel dense representation for the sparse events flow, in the form of the "inverse exponential distance surface". It serves as an interim frame, designed for the use of proven, state-of-the-art frame-based optical flow computation methods. We evaluate our approach on both low- and high-resolution driving sequences, and show that it often achieves better results than the current state of the art, while also reaching higher frame rates, 250Hz at 346 x 260 pixels and 77Hz at 1280 x 720 pixels.
相關內容
For robotic interaction in environments shared with other agents, access to volumetric and semantic maps of the scene is crucial. However, such environments are inevitably subject to long-term changes, which the map needs to account for. We thus propose panoptic multi-TSDFs as a novel representation for multi-resolution volumetric mapping in changing environments. By leveraging high-level information for 3D reconstruction, our proposed system allocates high resolution only where needed. Through reasoning on the object level, semantic consistency over time is achieved. This enables our method to maintain up-to-date reconstructions with high accuracy while improving coverage by incorporating previous data. We show in thorough experimental evaluation that our map can be efficiently constructed, maintained, and queried during online operation, and that the presented approach can operate robustly on real depth sensors using non-optimized panoptic segmentation as input.
While the evolution of mobile computing is experiencing a considerable growth, it is at the same time seriously threatened by the limitations of the battery technology, which does not keep pace with the evergrowing increase in energy requirements of mobile applications. A novel approach for reducing the energy appetite of mobile apps comes from the approximate computing field, which proposes techniques that in a controlled manner sacrifice computation accuracy for higher energy savings. Building on this philosophy we propose a context-aware mobile video quality adaptation that reduces the energy needed for video playback, while ensuring that a user's quality expectations with respect to the mobile video are met. We confirm that the decoding resolution can play a significant role in reducing the overall power consumption of a mobile device and conduct two user studies to investigate how the context in which a video is played, its content, and the user's personality, modulate a user's quality expectations. We discover that a user's physical activity, the spatial/temporal properties of the video, and the user's personality traits interact and jointly influence the minimal acceptable playback resolution, paving the way for context-adaptable approximate mobile computing.
In this paper, we introduce 'Coarse-Fine Networks', a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process inputs at one (or few) fixed temporal resolution without any dynamic frame selection. However, we argue that, processing multiple temporal resolutions of the input and doing so dynamically by learning to estimate the importance of each frame can largely improve video representations, specially in the domain of temporal activity localization. To this end, we propose (1) `Grid Pool', a learned temporal downsampling layer to extract coarse features, and, (2) `Multi-stage Fusion', a spatio-temporal attention mechanism to fuse a fine-grained context with the coarse features. We show that our method can outperform the state-of-the-arts for action detection in public datasets including Charades with a significantly reduced compute and memory footprint.
We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is based on background matting, where an additional frame of the background is captured and used in recovering the alpha matte and the foreground layer. The main challenge is to compute a high-quality alpha matte, preserving strand-level hair details, while processing high-resolution images in real-time. To achieve this goal, we employ two neural networks; a base network computes a low-resolution result which is refined by a second network operating at high-resolution on selective patches. We introduce two largescale video and image matting datasets: VideoMatte240K and PhotoMatte13K/85. Our approach yields higher quality results compared to the previous state-of-the-art in background matting, while simultaneously yielding a dramatic boost in both speed and resolution.
In this paper, we propose a residual non-local attention network for high-quality image restoration. Without considering the uneven distribution of information in the corrupted images, previous methods are restricted by local convolutional operation and equal treatment of spatial- and channel-wise features. To address this issue, we design local and non-local attention blocks to extract features that capture the long-range dependencies between pixels and pay more attention to the challenging parts. Specifically, we design trunk branch and (non-)local mask branch in each (non-)local attention block. The trunk branch is used to extract hierarchical features. Local and non-local mask branches aim to adaptively rescale these hierarchical features with mixed attentions. The local mask branch concentrates on more local structures with convolutional operations, while non-local attention considers more about long-range dependencies in the whole feature map. Furthermore, we propose residual local and non-local attention learning to train the very deep network, which further enhance the representation ability of the network. Our proposed method can be generalized for various image restoration applications, such as image denoising, demosaicing, compression artifacts reduction, and super-resolution. Experiments demonstrate that our method obtains comparable or better results compared with recently leading methods quantitatively and visually.
Transferring image-based object detectors to domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between performance and computational complexity. However, introducing an extra model to estimate optical flow would significantly increase the overall model size. The gap between optical flow and high-level features can hinder it from establishing the spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressive sparse strides and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense feature Transforming (DFT) are introduced to model temporal appearance and enrich feature representation respectively. Finally, a novel framework for video object detection is proposed. Experiments on ImageNet VID are conducted. Our framework achieves a state-of-the-art speed-accuracy trade-off with significantly reduced model capacity.
This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. The code and models have been publicly available at \url{//github.com/leoxiaobin/deep-high-resolution-net.pytorch}.
Modern inexpensive imaging sensors suffer from inherent hardware constraints which often result in captured images of poor quality. Among the most common ways to deal with such limitations is to rely on burst photography, which nowadays acts as the backbone of all modern smartphone imaging applications. In this work, we focus on the fact that every frame of a burst sequence can be accurately described by a forward (physical) model. This in turn allows us to restore a single image of higher quality from a sequence of low quality images as the solution of an optimization problem. Inspired by an extension of the gradient descent method that can handle non-smooth functions, namely the proximal gradient descent, and modern deep learning techniques, we propose a convolutional iterative network with a transparent architecture. Our network, uses a burst of low quality image frames and is able to produce an output of higher image quality recovering fine details which are not distinguishable in any of the original burst frames. We focus both on the burst photography pipeline as a whole, i.e. burst demosaicking and denoising, as well as on the traditional Gaussian denoising task. The developed method demonstrates consistent state-of-the art performance across the two tasks and as opposed to other recent deep learning approaches does not have any inherent restrictions either to the number of frames or their ordering.
Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most research working on semantic segmentation focuses on accuracy with little consideration for efficiency. Several existing studies that emphasize high-speed inference often cannot produce high-accuracy segmentation results. In this paper, we propose a novel convolutional network named Efficient Dense modules with Asymmetric convolution (EDANet), which employs an asymmetric convolution structure incorporating the dilated convolution and the dense connectivity to attain high efficiency at low computational cost, inference time, and model size. Compared to FCN, EDANet is 11 times faster and has 196 times fewer parameters, while it achieves a higher the mean of intersection-over-union (mIoU) score without any additional decoder structure, context module, post-processing scheme, and pretrained model. We evaluate EDANet on Cityscapes and CamVid datasets to evaluate its performance and compare it with the other state-of-art systems. Our network can run on resolution 512x1024 inputs at the speed of 108 and 81 frames per second on a single GTX 1080Ti and Titan X, respectively.
We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of applications, but the results are often limited to low-resolution and still far from realistic. In this work, we generate 2048x1024 visually appealing results with a novel adversarial loss, as well as new multi-scale generator and discriminator architectures. Furthermore, we extend our framework to interactive visual manipulation with two additional features. First, we incorporate object instance segmentation information, which enables object manipulations such as removing/adding objects and changing the object category. Second, we propose a method to generate diverse results given the same input, allowing users to edit the object appearance interactively. Human opinion studies demonstrate that our method significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191