Zobrazeno 1 - 10
of 75
pro vyhledávání: '"Wu, Gaochang"'
Anomaly detection in complex industrial processes plays a pivotal role in ensuring efficient, stable, and secure operation. Existing anomaly detection methods primarily focus on analyzing dominant anomalies using the process variables (such as arc cu
Externí odkaz:
http://arxiv.org/abs/2406.09016
Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain. The majority of existing UDA-SS works typically consider images whilst recent attempts have exten
Externí odkaz:
http://arxiv.org/abs/2311.13254
In this paper, we present a Geometry-aware Neural Interpolation (Geo-NI) framework for light field rendering. Previous learning-based approaches either rely on the capability of neural networks to perform direct interpolation, which we dubbed Neural
Externí odkaz:
http://arxiv.org/abs/2206.09736
Autor:
Wang, Yingqian, Wang, Longguang, Wu, Gaochang, Yang, Jungang, An, Wei, Yu, Jingyi, Guo, Yulan
Light field (LF) cameras record both intensity and directions of light rays, and encode 3D scenes into 4D LF images. Recently, many convolutional neural networks (CNNs) have been proposed for various LF image processing tasks. However, it is challeng
Externí odkaz:
http://arxiv.org/abs/2202.10603
Cross-resolution image alignment is a key problem in multiscale gigapixel photography, which requires to estimate homography matrix using images with large resolution gap. Existing deep homography methods concatenate the input images or features, neg
Externí odkaz:
http://arxiv.org/abs/2106.04067
Publikováno v:
IEEE TPAMI, 2021
The light field (LF) reconstruction is mainly confronted with two challenges, large disparity and the non-Lambertian effect. Typical approaches either address the large disparity challenge using depth estimation followed by view synthesis or eschew e
Externí odkaz:
http://arxiv.org/abs/2104.06797
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
In this paper, a novel convolutional neural network (CNN)-based framework is developed for light field reconstruction from a sparse set of views. We indicate that the reconstruction can be efficiently modeled as angular restoration on an epipolar pla
Externí odkaz:
http://arxiv.org/abs/2103.13043
Various combinations of cameras enrich computational photography, among which reference-based superresolution (RefSR) plays a critical role in multiscale imaging systems. However, existing RefSR approaches fail to accomplish high-fidelity super-resol
Externí odkaz:
http://arxiv.org/abs/2011.14631
Publikováno v:
IEEE Transactions on Image Processing, 2021
Typical learning-based light field reconstruction methods demand in constructing a large receptive field by deepening the network to capture correspondences between input views. In this paper, we propose a spatial-angular attention network to perceiv
Externí odkaz:
http://arxiv.org/abs/2007.02252
Publikováno v:
In Fuel 15 November 2023 352
