28 citations · 87 across the 12 of their papers we have counts for
12 papers
Multiscale style transfer based on a Laplacian pyramid for traditional Chinese painting
Kunxiao Liu, Guowu Yuan, Hongyu Liu +1
Style transfer is adopted to synthesize appealing stylized images that preserve the structure of a content image but carry the pattern of a style image. Many recently proposed styl…
Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection
Runmin Cong, Hongyu Liu, Chen Zhang +4
By integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved. In recent y…
XFormer: Fast and Accurate Monocular 3D Body Capture
Lihui Qian, Xintong Han, Faqiang Wang +6
We present XFormer, a novel human mesh and motion capture method that achieves real-time performance on consumer CPUs given only monocular images as input. The proposed network arc…
Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding
Ziyang Yuan, Yiming Zhu, Yu Li +2
3D GAN inversion aims to achieve high reconstruction fidelity and reasonable 3D geometry simultaneously from a single image input. However, existing 3D GAN inversion methods rely o…
Human MotionFormer: Transferring Human Motions with Vision Transformers
Hongyu Liu, Xintong Han, Chengbin Jin +8
Human motion transfer aims to transfer motions from a target dynamic person to a source static one for motion synthesis. An accurate matching between the source person and the targ…
Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint
Hongyu Liu, Yibing Song, Qifeng Chen
GAN inversion and editing via StyleGAN maps an input image into the embedding spaces (, , and ) to simultaneously maintain image fidelity a…
One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations
Yiming Zhu, Hongyu Liu, Yibing Song +5
Free-form text prompts allow users to describe their intentions during image manipulation conveniently. Based on the visual latent space of StyleGAN[21] and text embedding space of…
PD-GAN: Probabilistic Diverse GAN for Image Inpainting
Hongyu Liu, Ziyu Wan, Wei Huang +3
We propose PD-GAN, a probabilistic diverse GAN for image inpainting. Given an input image with arbitrary hole regions, PD-GAN produces multiple inpainting results with diverse and…
DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
Hongyu Liu, Ziyu Wan, Wei Huang +5
User-intended visual content fills the hole regions of an input image in the image editing scenario. The coarse low-level inputs, which typically consist of sparse sketch lines and…
Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations
Hongyu Liu, Bin Jiang, Yibing Song +2
Deep encoder-decoder based CNNs have advanced image inpainting methods for hole filling. While existing methods recover structures and textures step-by-step in the hole regions, th…
One-Stage Inpainting with Bilateral Attention and Pyramid Filling Block
Hongyu Liu, Bin Jiang, Wei Huang +1
Recent deep learning based image inpainting methods which utilize contextual information and two-stage architecture have exhibited remarkable performance. However, the two-stage ar…
Coherent Semantic Attention for Image Inpainting
Hongyu Liu, Bin Jiang, Yi Xiao +1
The latest deep learning-based approaches have shown promising results for the challenging task of inpainting missing regions of an image. However, the existing methods often gener…