Search Results for author: Xuanhong Chen

Found 7 papers, 5 papers with code

SimSwap: An Efficient Framework For High Fidelity Face Swapping

2 code implementations11 Jun 2021 Renwang Chen, Xuanhong Chen, Bingbing Ni, Yanhao Ge

In contrast to previous approaches that either lack the ability to generalize to arbitrary identity or fail to preserve attributes like facial expression and gaze direction, our framework is capable of transferring the identity of an arbitrary source face into an arbitrary target face while preserving the attributes of the target face.

 Ranked #1 on Face Swapping on FaceForensics++ (ID retrieval metric)

Face Swapping

X-volution: On the unification of convolution and self-attention

no code implementations4 Jun 2021 Xuanhong Chen, Hang Wang, Bingbing Ni

Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the latter non-locally encodes high-order contextual relationships.

Image Classification Instance Segmentation +1

Image Translation via Fine-grained Knowledge Transfer

1 code implementation21 Dec 2020 Xuanhong Chen, Ziang Liu, Ting Qiu, Bingbing Ni, Naiyuan Liu, XiWei Hu, Yuhan Li

Extensive experiments well demonstrate the effectiveness and feasibility of our framework in different image-translation tasks.

Style Transfer Transfer Learning

RainNet: A Large-Scale Dataset for Spatial Precipitation Downscaling

1 code implementation17 Dec 2020 Xuanhong Chen, Kairui Feng, Naiyuan Liu, Yifan Lu, Zhengyan Tong, Bingbing Ni, Ziang Liu, Ning Lin

In order to facilitate the research on precipitation downscaling for deep learning, we present the first REAL (non-simulated) Large-Scale Spatial Precipitation Downscaling Dataset, RainNet, which contains 62, 424 pairs of low-resolution and high-resolution precipitation maps for 17 years.

Sketch Generation with Drawing Process Guided by Vector Flow and Grayscale

1 code implementation16 Dec 2020 Zhengyan Tong, Xuanhong Chen, Bingbing Ni, Xiaohang Wang

Existing pencil sketch algorithms are based on texture rendering rather than the direct imitation of strokes, making them unable to show the drawing process but only a final result.

CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing

no code implementations ECCV 2020 Xuanhong Chen, Bingbing Ni, Naiyuan Liu, Ziang Liu, Yiliu Jiang, Loc Truong, Qi Tian

In contrast to great success of memory-consuming face editing methods at a low resolution, to manipulate high-resolution (HR) facial images, i. e., typically larger than 7682 pixels, with very limited memory is still challenging.

Image Generation

Anisotropic Stroke Control for Multiple Artists Style Transfer

1 code implementation16 Oct 2020 Xuanhong Chen, Xirui Yan, Naiyuan Liu, Ting Qiu, Bingbing Ni

Furthermore, the results are with distinctive artistic style and retain the anisotropic semantic information.

Style Transfer

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