arXiv 2301.117522023-01-27cs.CVcs.MMeess.IV

Inter-View Depth Consistency Testing in Depth Difference Subspace

Tobii AB (publ)（托比股份公司）；KTH Royal Institute of Technology（KTH皇家理工学院）

Pravin Kumar Rana, Markus Flierl

英文摘要：

Multiview depth imagery will play a critical role in free-viewpoint television. This technology requires high quality virtual view synthesis to enable viewers to move freely in a dynamic real world scene. Depth imagery at different viewpoints is used to synthesize an arbitrary number of novel views. Usually, depth images at multiple viewpoints are estimated individually by stereo-matching algorithms, and hence, show lack of interview consistency. This inconsistency affects the quality of view synthesis negatively. This paper proposes a method for depth consistency testing in depth difference subspace to enhance the depth representation of a scene across multiple viewpoints. Furthermore, we propose a view synthesis algorithm that uses the obtained consistency information to improve the visual quality of virtual views at arbitrary viewpoints. Our method helps us to find a linear subspace for our depth difference measurements in which we can test the inter-view consistency efficiently. With this, our approach is able to enhance the depth information for real world scenes. In combination with our consistency-adaptive view synthesis, we improve the visual experience of the free-viewpoint user. The experiments show that our approach enhances the objective quality of virtual views by up to 1.4 dB. The advantage for the subjective quality is also demonstrated.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

测量子空间一致性：加速MRI重建中扩散后验采样的即插即用算子

Measured-Subspace Consistency: A Plug-and-Play Operator for Diffusion Posterior Sampling in Accelerated MRI Reconstruction

Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine（首尔国立大学医学院癌症生物学跨学科项目）；Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital（首尔国立大学医学院放射科，首尔国立大学医院）；Healthcare AI Research Institute, Seoul National University Hospital（首尔国立大学医院医疗人工智能研究机构）

针对加速MRI中扩散后验采样在已测量k空间上产生不一致的问题，提出测量子空间一致性（MSC）作为无训练的后验修正算子，通过经典一致性锁减少测量子空间泄漏，保持未测量子空间多样性，无需重新训练或调参。

2026-06-26cs.CVeess.IV

让你的潜变量起舞：通过运动流引导的时空子空间注意力实现一致的舞蹈生成

Dance Your Latents: Consistent Dance Generation through Spatial-temporal Subspace Attention Guided by Motion Flow

Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）

提出Dance-Your-Latents框架，通过时空子空间注意力模块和运动流引导的子空间对齐与恢复方法，有效缓解长程注意力分散问题，显著提升生成舞蹈视频的时空一致性。

2023-10-20cs.CV

Cut-ViT：基于Gram锚定子空间一致性的任务特定模型剪枝

Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency

Nanjing University of Science and Technology（南京理工大学）；State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery（先进工程机械智能制造国家重点实验室）；Zhejiang University（浙江大学）；Nanjing Normal University（南京师范大学）

Cut-ViT是一种基于Gram锚定子空间一致性的任务特定视觉模型剪枝方法，可高效生成高鲁棒性子网络，在6项任务9个数据集上达SOTA性能，耗时与内存开销仅为旧方法的约五分之一和近一半。

2026-08-31cs.CV

用于并行磁共振成像重建的Hankel子空间自监督学习

Hankel Subspace Self-Supervised Learning for Parallel MRI Reconstruction

针对并行磁共振成像重建的数据泄露问题，本文提出HSSRecon框架，通过物理组拆分与多重性归一化分离Hankel域结构学习与物理域数据一致性，在fastMRI脑部数据上取得了竞争力的重建性能。

2026-10-09cs.CV

Consistency and Diversity induced Human Motion Segmentation

Nanjing University of Science and Technology（南京理工大学）；Agency for Science, Technology and Research（新加坡科技研究局）；Saudi Data and Artificial Intelligence Authority（沙特数据与人工智能局）；Australian National University（澳大利亚国立大学）；Stony Brook University（石溪大学）

Subspace clustering is a classical technique that has been widely used for human motion segmentation and other related tasks. However, existing segmentation methods often cluster data without guidance from prior knowledge, resulting in unsatisfactory segmentation results. To this end, we propose a novel Consistency and Diversity induced human Motion Segmentation (CDMS) algorithm. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces, in which transfer subspace learning is conducted on different layers to capture multi-level information. A multi-…

2022-02-10cs.CV

Multi-view Subspace Adaptive Learning via Autoencoder and Attention

China University of Petroleum, Beijing Campus (CUP)（中国石油大学（北京））

Multi-view learning can cover all features of data samples more comprehensively, so multi-view learning has attracted widespread attention. Traditional subspace clustering methods, such as sparse subspace clustering (SSC) and low-ranking subspace clustering (LRSC), cluster the affinity matrix for a single view, thus ignoring the problem of fusion between views. In our article, we propose a new Multiview Subspace Adaptive Learning based on Attention and Autoencoder (MSALAA). This method combines a deep autoencoder and a method for aligning the self-representations of various views in Multi-view…

2022-01-01cs.CVcs.LG

更多相关论文收起更多论文

Joint Featurewise Weighting and Lobal Structure Learning for Multi-view Subspace Clustering

Zhaotong University（昭通学院）；University of Macau（澳门大学）；The University of Queensland（昆士兰大学）

Multi-view clustering integrates multiple feature sets, which reveal distinct aspects of the data and provide complementary information to each other, to improve the clustering performance. It remains challenging to effectively exploit complementary information across multiple views since the original data often contain noise and are highly redundant. Moreover, most existing multi-view clustering methods only aim to explore the consistency of all views while ignoring the local structure of each view. However, it is necessary to take the local structure of each view into consideration, because …

2020-07-25cs.CVcs.LGstat.ML

Attentive Multi-View Deep Subspace Clustering Net

China University of Petroleum, Beijing（中国石油大学（北京））

In this paper, we propose a novel Attentive Multi-View Deep Subspace Nets (AMVDSN), which deeply explores underlying consistent and view-specific information from multiple views and fuse them by considering each view's dynamic contribution obtained by attention mechanism. Unlike most multi-view subspace learning methods that they directly reconstruct data points on raw data or only consider consistency or complementarity when learning representation in deep or shallow space, our proposed method seeks to find a joint latent representation that explicitly considers both consensus and view-specif…

2021-12-23cs.CVcs.LG

Seeking Commonness and Inconsistencies: A Jointly Smoothed Approach to Multi-view Subspace Clustering

South China Agricultural University（华南农业大学）；Sun Yat-sen University（中山大学）

Multi-view subspace clustering aims to discover the hidden subspace structures from multiple views for robust clustering, and has been attracting considerable attention in recent years. Despite significant progress, most of the previous multi-view subspace clustering algorithms are still faced with two limitations. First, they usually focus on the consistency (or commonness) of multiple views, yet often lack the ability to capture the cross-view inconsistencies in subspace representations. Second, many of them overlook the local structures of multiple views and cannot jointly leverage multiple…

2022-10-31cs.CVcs.LG

基于图卷积网络的高光谱图像对比多视图子空间聚类

Contrastive Multi-view Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks

China University of Geosciences（中国地质大学）；National University of Defense Technology（国防科技大学）

针对高光谱图像单视图子空间聚类未能充分利用空间与纹理信息的问题，提出基于图卷积网络的对比多视图方法，通过双视图亲和学习、对比一致性和注意力融合提升聚类精度。

2023-12-11cs.AIcs.CV

子空间引导的语义与拓扑不变配准用于无标注超声平面质量控制

Subspace-Guided Semantic and Topological Invariant Registration for Annotation-Free Ultrasound Plane Quality Control

Hunan University（湖南大学）；Shenzhen Maternity and Child Healthcare Hospital（深圳妇幼保健医院）

提出STRIQ框架，通过子空间引导的配准一致性度量，实现无标注超声平面质量控制，达到与临床质量评分的最优相关性。

2026-05-25cs.AIcs.CV

Complex Background Subtraction by Pursuing Dynamic Spatio-Temporal Models

Sun Yat-Sen University（中山大学）；SYSU-CMU Shunde International Joint Research Institute（中山大学-卡内基梅隆大学顺德国际联合研究院）

Although it has been widely discussed in video surveillance, background subtraction is still an open problem in the context of complex scenarios, e.g., dynamic backgrounds, illumination variations, and indistinct foreground objects. To address these challenges, we propose an effective background subtraction method by learning and maintaining an array of dynamic texture models within the spatio-temporal representations. At any location of the scene, we extract a sequence of regular video bricks, i.e. video volumes spanning over both spatial and temporal domain. The background modeling is thus p…

2015-02-02cs.CV