Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing

Xiao, Yunxuan; Li, Yikai; Wu, Yuwei; Zhu, Li-Zhen

doi:10.48550/arxiv.1901.03954

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this line of work is very important since it can inspire or enable many practical tasks such as image editing [31,39,23], medical image analysis [4], etc. Specifically, when served as a pre-processing step of background replacement and depth-of-field, high-resolution salient object detection should be as accurate as possible to provide users with realistic composite images [29].…”

Section: Introductionmentioning

confidence: 99%

Towards High-Resolution Salient Object Detection

Zeng

Zhang

Lin

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

174

View full text Add to dashboard Cite

Deep neural network based methods have made a significant breakthrough in salient object detection. However, they are typically limited to input images with low resolutions (400 × 400 pixels or less). Little effort has been made to train deep neural networks to directly handle salient object detection in very high-resolution images. This paper pushes forward high-resolution saliency detection, and contributes a new dataset, named High-Resolution Salient Object Detection (HRSOD). To our best knowledge, HRSOD is the first high-resolution saliency detection dataset to date. As another contribution, we also propose a novel approach, which incorporates both global semantic information and local high-resolution details, to address this challenging task. More specifically, our approach consists of a Global Semantic Network (GSN), a Local Refinement Network (LRN) and a Global-Local Fusion Network (GLFN). GSN extracts the global semantic information based on down-sampled entire image. Guided by the results of GSN, LRN focuses on some local regions and progressively produces high-resolution predictions. GLFN is further proposed to enforce spatial consistency and boost performance. Experiments illustrate that our method outperforms existing state-of-the-art methods on high-resolution saliency datasets by a large margin, and achieves comparable or even better performance than them on widely-used saliency benchmarks. The HRSOD dataset is available at https://github.com/yi94code/HRSOD.

show abstract