paper-with-me

Papers

CPNet: A Context Preserver Convolutional Neural Network for Detecting Shadows in Single RGB Images

2018-10-13 · Sorour Mohajerani, Parvaneh Saeedi

Automatic detection of shadow regions in an image is a difficult task due to the lack of prior information about the illumination source and the dynamic of the scene objects. To address this problem, in this paper, a deep-learning based segmentation method is proposed that identifies shadow regions at the pixel-level in a single RGB image. We exploit a novel Convolutional Neural Network (CNN) architecture to identify and extract shadow features in an end-to-end manner. This network preserves learned contexts during the training and observes the entire image to detect global and local shadow patterns simultaneously. The proposed method is evaluated on two publicly available datasets of SBU and UCF. We have improved the state-of-the-art Balanced Error Rate (BER) on these datasets by 22\% and 14\%, respectively.

📄 PDF Abstract BibTeX arXiv:1810.05778

Code (0)

등록된 구현이 없습니다.

Tasks

Detecting Shadows

Similar Papers 제목 키워드 기반

Real-time Semantic Segmentation via Spatial-detail Guided Context Propagation

2020-05-22 · Shijie Hao, Yuan Zhou, Yanrong Guo, Richang Hong 외

Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g. semantic segmentation, are usually computationally expensive, posing a challeng…

GPUReal-Time Semantic SegmentationSegmentationSemantic Segmentation

SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning

2024-07-11 · Runmin Zhang, Jun Ma, Si-Yuan Cao, Lun Luo 외

We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namely SCPNet. The concept of intra-modal sel…

Homography EstimationSelf-Supervised Learning

Copy and Paste GAN: Face Hallucination from Shaded Thumbnails

2020-02-25 · CVPR 2020 6 · Yang Zhang, Ivor Tsang, Yawei Luo, Changhui Hu 외

Existing face hallucination methods based on convolutional neural networks (CNN) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades d…

Face HallucinationGenerative Adversarial NetworkHallucination

Direction-aware Spatial Context Features for Shadow Detection

2017-12-12 · CVPR 2018 6 · Xiaowei Hu, Lei Zhu, Chi-Wing Fu, Jing Qin 외

Shadow detection is a fundamental and challenging task, since it requires an understanding of global image semantics and there are various backgrounds around shadows. This paper presents a novel network for shadow detect…

Detecting ShadowsShadow Detection

Clustered Object Detection in Aerial Images

2019-04-16 · ICCV 2019 10 · Fan Yang, Heng Fan, Peng Chu, Erik Blasch 외

Detecting objects in aerial images is challenging for at least two reasons: (1) target objects like pedestrians are very small in pixels, making them hardly distinguished from surrounding background; and (2) targets are …

ClusteringObjectobject-detectionObject Detection+1