检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 4663-4678页

作者： Ma, Boxiao Zalmai, Nour Loeliger, Hans-Andrea Swiss Fed Inst Technol Dept Informat Technol & Elect Engn CH-8092 Zurich Switzerland Renault Software Factory Dept Autonomous Driving ADAS Algorithm & Embedded Software F-06560 Valbonne France

Variations of L1-regularization including, in particular, total variation regularization, have hugely improved computational imaging. However, sharper edges and fewer staircase artifacts can be achieved with convex-concave regularizers. We present a new class of such regularizers using normal priors with unknown variance (NUV), which include smoothed versions of the logarithm function and smoothed versions of L-p norms with p <= 1. All NUV priors allow variational representations that lead to efficient algorithms for image reconstruction by iterative reweighted descent. A preferred such algorithm is iterative reweighted coordinate descent, which has no parameters (in particular, no step size to control) and is empirically robust and efficient. The proposed priors and algorithms are demonstrated with applications to tomography. We also note that the proposed priors come with built-in edge detection, which is demonstrated by an application to image segmentation.

关键词： Image reconstruction NUV sparsity iterative reweighted descent expectation maximization tomography edge detection image segmentation

来源：评论

学校读者我要写书评

暂无评论

FoggyStereo: Stereo Matching with Fog Volume Representation

FoggyStereo: Stereo Matching with Fog Volume Representation

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yao, Chengtang Yu, Lidong Beijing Inst Technol Beijing Lab Intelligent Informat Technol Beijing Peoples R China NIO Autonomous Driving Algorithm Shanghai Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Stereo matching in foggy scenes is challenging as the scattering effect of fog blurs the image and makes the matching ambiguous. Prior methods deem the fog as noise and discard it before matching. Different from them, we propose to explore depth hints from fog and improve stereo matching via these hints. The exploration of depth hints is designed from the perspective of rendering. The rendering is conducted by reversing the atmospheric scattering process and removing the fog within a selected depth range. The quality of the rendered image reflects the correctness of the selected depth, as the closer it is to the real depth, the clearer the rendered image is. We introduce a fog volume representation to collect these depth hints from the fog. We construct the fog volume by stacking images rendered with depths computed from disparity candidates that are also used to build the cost volume. We fuse the fog volume with cost volume to rectify the ambiguous matching caused by fog. Experiments show that our fog volume representation significantly promotes the SOTA result on foggy scenes by 10% similar to 30% while maintaining a comparable performance in clear scenes.

关键词： Computer vision Costs Three-dimensional displays Fuses Stacking Scattering Estimation

来源：评论

学校读者我要写书评

暂无评论

Lane Transformer: A High-Efficiency Trajectory Prediction Model

IEEE OPEN JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS

引用

IEEE OPEN JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS 2023年 4卷 2-13页

作者： Wang, Zhibo Guo, Jiayu Hu, Zhengming Zhang, Haiqiang Zhang, Junping Pu, Jian Fudan Univ Inst Sci & Technol Brain Inspired Intelligence Shanghai 200433 Peoples R China Mogo Auto Intelligence & Telemat Informat Technol Autonomous Driving Gen Algorithm Dept Beijing 100013 Peoples R China Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China

Trajectory prediction is a crucial step in the pipeline for autonomous driving because it not only improves the planning of future routes, but also ensures vehicle safety. On the basis of deep neural networks, numerous trajectory prediction models have been proposed and have already achieved high performance on public datasets due to the well-designed model structure and complex optimization procedure. However, the majority of these methods overlook the fact that vehicles' limited computing resources can be utilized for online real-time inference. We proposed a Lane Transformer to achieve high accuracy and efficiency in trajectory prediction to tackle this problem. On the one hand, inspired by the well-known transformer, we use attention blocks to replace the commonly used Graph Convolution Network (GCN) in trajectory prediction models, thereby drastically reducing the time cost while maintaining the accuracy. In contrast, we construct our prediction model to be compatible with TensorRT, allowing it to be further optimized and easily transformed into a deployment-friendly form of TensorRT. Experiments demonstrate that our model outperforms the baseline LaneGCN model in quantitative prediction accuracy on the Argoverse dataset by a factor of 10x to 25x. Our 7ms inference time is the fastest among all open source methods currently available.

关键词： Trajectory Transformers Predictive models Roads Feature extraction Task analysis Convolution Trajectory prediction transformer multi-head attention TensorRT

来源：评论

学校读者我要写书评

暂无评论

Parameterized Cost Volume for Stereo Matching

Parameterized Cost Volume for Stereo Matching

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Zeng, Jiaxi Yao, Chengtang Yu, Lidong Wu, Yuwei Jia, Yunde Beijing Inst Technol Sch Comp Sci & Technol Beijing Key Lab Intelligent Informat Technol Beijing Peoples R China BIT Univ Guangdong Lab Machine Percept & Intelligent Comp Shenzhen MSU Shenzhen Peoples R China Deeproute Autonomous Driving Algorithm Shenzhen Peoples R China

ISBN: (纸本)9798350307184

Stereo matching becomes computationally challenging when dealing with a large disparity range. Prior methods mainly alleviate the computation through dynamic cost volume by focusing on a local disparity space, but it requires many iterations to get close to the ground truth due to the lack of a global view. We find that the dynamic cost volume approximately encodes the disparity space as a single Gaussian distribution with a fixed and small variance at each iteration, which results in an inadequate global view over disparity space and a small update step at every iteration. In this paper, we propose a parameterized cost volume to encode the entire disparity space using multi-Gaussian distribution. The disparity distribution of each pixel is parameterized by weights, means, and variances. The means and variances are used to sample disparity candidates for cost computation, while the weights and means are used to calculate the disparity output. The above parameters are computed through a JS-divergence-based optimization, which is realized as a gradient descent update in a feed-forward differential module. Experiments show that our method speeds up the runtime of RAFT-Stereo by 4 similar to 15 times, achieving real-time performance and comparable accuracy. The code is available at https://***/jiaxiZeng/Parameterized-Cost-Volume-for-Stereo-Matching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse Point Guided 3D Lane Detection

Sparse Point Guided 3D Lane Detection

引用

IEEE/CVF International Conference on Computer Vision (ICCV)

作者： Yao, Chengtang Yu, Lidong Wu, Yuwei Jia, Yunde Beijing Inst Technol Sch Comp Sci Technol Beijing Key Lab Intelligent Informat Technol Beijing Peoples R China BIT Univ Guangdong Lab Machine Percept & Intelligent Comp Shenzhen MSU Beijing Peoples R China DeepRoute Autonomous Driving Algorithm Shenzhen Peoples R China

ISBN: (纸本)9798350307184

3D lane detection usually builds a dense correspondence between the front-view space and the BEV space to estimate lane points in the 3D space. 3D lanes only occupy a small ratio of the dense correspondence, while most correspondence belongs to the redundant background. This sparsity phenomenon bottlenecks valuable computation and raises the computation cost of building a high-resolution correspondence for accurate results. In this paper, we propose a sparse point-guided 3D lane detection, focusing on points related to 3D lanes. Our method runs in a coarse-to-fine manner, including coarse-level lane detection and iterative fine- level sparse point refinements. In coarse-level lane detection, we build a dense but efficient correspondence between the front view and BEV space at a very low resolution to compute coarse lanes. Then in fine-level sparse point refinement, we sample sparse points around coarse lanes to extract local features from the high-resolution front-view feature map. The high-resolution local information brought by sparse points refines 3D lanes in the BEV space hierarchically from low resolution to high resolution. The sparse point guides a more effective information flow and greatly promotes the SOTA result by 3 points on the overall F1-score and 6 points on several hard situations while reducing almost half memory cost and speeding up 2 times.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parameterized Cost Volume for Stereo Matching

Parameterized Cost Volume for Stereo Matching

引用

International Conference on Computer Vision (ICCV)

作者： Jiaxi Zeng Chengtang Yao Lidong Yu Yuwei Wu Yunde Jia Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Autonomous Driving Algorithm Deeproute Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

Stereo matching becomes computationally challenging when dealing with a large disparity range. Prior methods mainly alleviate the computation through dynamic cost volume by focusing on a local disparity space, but it requires many iterations to get close to the ground truth due to the lack of a global view. We find that the dynamic cost volume approximately encodes the disparity space as a single Gaussian distribution with a fixed and small variance at each iteration, which results in an inadequate global view over disparity space and a small update step at every iteration. In this paper, we propose a parameterized cost volume to encode the entire disparity space using multi-Gaussian distribution. The disparity distribution of each pixel is parameterized by weights, means, and variances. The means and variances are used to sample disparity candidates for cost computation, while the weights and means are used to calculate the disparity output. The above parameters are computed through a JS-divergence-based optimization, which is realized as a gradient descent update in a feed-forward differential module. Experiments show that our method speeds up the runtime of RAFT-Stereo by 4 ~ 15 times, achieving real-time performance and comparable accuracy. The code is available at https://***/jiaxiZeng/Parameterized-Cost-Volume-for-Stereo-Matching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse Point Guided 3D Lane Detection

Sparse Point Guided 3D Lane Detection

引用

International Conference on Computer Vision (ICCV)

作者： Chengtang Yao Lidong Yu Yuwei Wu Yunde Jia School of Computer Science & Technology Beijing Key Laboratory of Intelligent Information Technology Beijing Institute of Technology China Autonomous Driving Algorithm DeepRoute Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China

3D lane detection usually builds a dense correspondence between the front-view space and the BEV space to estimate lane points in the 3D space. 3D lanes only occupy a small ratio of the dense correspondence, while most correspondence belongs to the redundant background. This sparsity phenomenon bottlenecks valuable computation and raises the computation cost of building a high-resolution correspondence for accurate results. In this paper, we propose a sparse point-guided 3D lane detection, focusing on points related to 3D lanes. Our method runs in a coarse-to-fine manner, including coarse-level lane detection and iterative fine-level sparse point refinements. In coarse-level lane detection, we build a dense but efficient correspondence between the front view and BEV space at a very low resolution to compute coarse lanes. Then in fine-level sparse point refinement, we sample sparse points around coarse lanes to extract local features from the high-resolution front-view feature map. The high-resolution local information brought by sparse points refines 3D lanes in the BEV space hierarchically from low resolution to high resolution. The sparse point guides a more effective information flow and greatly promotes the SOTA result by 3 points on the overall F1-score and 6 points on several hard situations while reducing almost half memory cost and speeding up 2 times.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：