Search Results for author: Hao Ouyang

Found 7 papers, 5 papers with code

Real-Time Neural Character Rendering with Pose-Guided Multiplane Images

no code implementations25 Apr 2022 Hao Ouyang, Bo Zhang, Pan Zhang, Hao Yang, Jiaolong Yang, Dong Chen, Qifeng Chen, Fang Wen

We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality.

Image-to-Image Translation Novel View Synthesis

Deep Video Prior for Video Consistency and Propagation

1 code implementation27 Jan 2022 Chenyang Lei, Yazhou Xing, Hao Ouyang, Qifeng Chen

A progressive propagation strategy with pseudo labels is also proposed to enhance DVP's performance on video propagation.

Computer Vision Optical Flow Estimation +2

Image Inpainting with External-internal Learning and Monochromic Bottleneck

1 code implementation CVPR 2021 Tengfei Wang, Hao Ouyang, Qifeng Chen

Although recent inpainting approaches have demonstrated significant improvements with deep neural networks, they still suffer from artifacts such as blunt structures and abrupt colors when filling in the missing regions.

Image Inpainting

Neural Camera Simulators

1 code implementation CVPR 2021 Hao Ouyang, Zifan Shi, Chenyang Lei, Ka Lung Law, Qifeng Chen

To facilitate the learning of a simulator model, we collect a dataset of the 10, 000 raw images of 450 scenes with different exposure settings.

Data Augmentation

Human Pose Estimation with Spatial Contextual Information

no code implementations7 Jan 2019 Hong Zhang, Hao Ouyang, Shu Liu, Xiaojuan Qi, Xiaoyong Shen, Ruigang Yang, Jiaya Jia

With this principle, we present two conceptually simple and yet computational efficient modules, namely Cascade Prediction Fusion (CPF) and Pose Graph Neural Network (PGNN), to exploit underlying contextual information.

Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.