Yuhang Song

Yuhang Song

Auto-generated profile, based on publicly available information

Yuhang Song

University of Southern California

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 October 2018
Verified
Book Chapter
Closed access
PDF file
YSYuhang Song
Yuhang Song
CYChao Yang
Chao Yang
ZLZhe Lin
Zhe Lin
Xiaofeng LiuXiaofeng Liu
Xiaofeng Liu
QHQin Huang
Qin Huang
CKC.-C. Jay Kuo
C.-C. Jay Kuo

23 January 2019
Verified
Book Chapter
Closed access
PDF file
Xiaofeng LiuXiaofeng Liu
Xiaofeng Liu
YZYang Zou
Yang Zou
YSYuhang Song
Yuhang Song
CYChao Yang
Chao Yang
Jane YouJane You
Jane You
BKB. V. K. Vijaya Kumar
B. V. K. Vijaya Kumar

6 August 2018 in arXiv
Verified
Preprint
Open access
PDF file
YSYuhang Song
Yuhang Song
CYChao Yang
Chao Yang
YSYeji Shen
Yeji Shen
PWPeng Wang
Peng Wang
QHQin Huang
Qin Huang
CKC.-C. Jay Kuo
C.-C. Jay Kuo
In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information. Recent development in deep generative models enables an efficient end-to-end framework for image synthesis and inpainting tasks, but existing methods based on generative models don't exploit the segmentation information to constrain the object shapes, which usually lead to blurry results on the boundary. To tackle this problem, we propose to introduce the semantic segmentation information, which disentangles the inter-class difference and intra-class variation for image inpainting. This leads to much clearer recovered boundary between semantically different regions and better texture within semantically consistent segments. Our model factorizes the image inpainting process into segmentation prediction (SP-Net) and segmentation guidance (SG-Net) as two steps, which predict the segmentation labels in the missing area first, and then generate segmentation guided inpainting results. Experiments on multiple public datasets show that our approach outperforms existing methods in optimizing the image inpainting quality, and the interactive segmentation guidance provides possibilities for multi-modal predictions of image inpainting.

20 July 2017 in arXiv
Verified
Preprint
Open access
PDF file
QHQin Huang
Qin Huang
CXChunyang Xia
Chunyang Xia
CWChihao Wu
Chihao Wu
SLSiyang Li
Siyang Li
YWYe Wang
Ye Wang
CKC.-C. Jay Kuo
C.-C. Jay Kuo
Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation. Traditionally, the convolutional classifiers are taught to learn the representative semantic features of labeled semantic objects. In this work, we propose a reverse attention network (RAN) architecture that trains the network to capture the opposite concept (i.e., what are not associated with a target class) as well. The RAN is a three-branch network that performs the direct, reverse and reverse-attention learning processes simultaneously. Extensive experiments are conducted to show the effectiveness of the RAN in semantic segmentation. Being built upon the DeepLabv2-LargeFOV, the RAN achieves the state-of-the-art mIoU score (48.1%) for the challenging PASCAL-Context dataset. Significant performance improvements are also observed for the PASCAL-VOC, Person-Part, NYUDv2 and ADE20K datasets.

28 March 2018 in arXiv
Verified
Preprint
Open access
PDF file
CYChao Yang
Chao Yang
YSYuhang Song
Yuhang Song
Xiaofeng LiuXiaofeng Liu
Xiaofeng Liu
QTQingming Tang
Qingming Tang
CKC.-C. Jay Kuo
C.-C. Jay Kuo
Recent advances in deep generative models have shown promising potential in image inpanting, which refers to the task of predicting missing pixel values of an incomplete image using the known context. However, existing methods can be slow or generate unsatisfying results with easily detectable flaws. In addition, there is often perceivable discontinuity near the holes and require further post-processing to blend the results. We present a new approach to address the difficulty of training a very deep generative model to synthesize high-quality photo-realistic inpainting. Our model uses conditional generative adversarial networks (conditional GANs) as the backbone, and we introduce a novel block-wise procedural training scheme to stabilize the training while we increase the network depth. We also propose a new strategy called adversarial loss annealing to reduce the artifacts. We further describe several losses specifically designed for inpainting and show their effectiveness. Extensive experiments and user-study show that our approach outperforms existing methods in several tasks such as inpainting, face completion and image harmonization. Finally, we show our framework can be easily used as a tool for interactive guided inpainting, demonstrating its practical value to solve common real-world challenges.

28 November 2019 in arXiv
Verified
Preprint
Open access
PDF file
RZRong Zhang
Rong Zhang
WLWei Li
Wei Li
PWPeng Wang
Peng Wang
CGChenye Guan
Chenye Guan
JFJin Fang
Jin Fang
RYRuigang Yang
Ruigang Yang
Motivated by the need for photo-realistic simulation in autonomous driving, in this paper we present a video inpainting algorithm \emph{AutoRemover}, designed specifically for generating street-view videos without any moving objects. In our setup we have two challenges: the first is the shadow, shadows are usually unlabeled but tightly coupled with the moving objects. The second is the large ego-motion in the videos. To deal with shadows, we build up an autonomous driving shadow dataset and design a deep neural network to detect shadows automatically. To deal with large ego-motion, we take advantage of the multi-source data, in particular the 3D data, in autonomous driving. More specifically, the geometric relationship between frames is incorporated into an inpainting deep neural network to produce high-quality structurally consistent video output. Experiments show that our method outperforms other state-of-the-art (SOTA) object removal algorithms, reducing the RMSE by over $19\%$.