no code implementations • 29 May 2023 • Mengtian Li, Yi Dong, Minxuan Lin, Haibin Huang, Pengfei Wan, Chongyang Ma
We also introduce a two-stage training strategy, where we train the encoder in the first stage to align the feature maps with StyleGAN and enable a faithful reconstruction of input faces.
no code implementations • 10 Oct 2022 • Wanfeng Zheng, Qiang Li, Xiaoyan Guo, Pengfei Wan, Zhongyuan Wang
More specifically, our efforts consist of three parts: 1) a data-free training strategy to train latent mappers to bridge the latent space of CLIP and StyleGAN; 2) for more precise mapping, temporal relative consistency is proposed to address the knowledge distribution bias problem among different latent spaces; 3) to refine the mapped latent in s space, adaptive style mixing is also proposed.
no code implementations • 31 May 2022 • Liang Hou, Qi Cao, Yige Yuan, Songtao Zhao, Chongyang Ma, Siyuan Pan, Pengfei Wan, Zhongyuan Wang, HuaWei Shen, Xueqi Cheng
Training generative adversarial networks (GANs) with limited data is challenging because discriminator is prone to overfitting.
no code implementations • 30 Mar 2022 • Wanfeng Zheng, Qiang Li, Guoxin Zhang, Pengfei Wan, Zhongyuan Wang
Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data.
no code implementations • CVPR 2022 • Linfeng Zhang, Xin Chen, Xiaobing Tu, Pengfei Wan, Ning Xu, Kaisheng Ma
Instead of directly distilling the generated images of teachers, wavelet knowledge distillation first decomposes the images into different frequency bands with discrete wavelet transformation and then only distills the high frequency bands.
1 code implementation • 19 Feb 2022 • Xin Wen, Peng Xiang, Zhizhong Han, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Yu-Shen Liu
It moves each point of incomplete input to obtain a complete point cloud, where total distance of point moving paths (PMPs) should be the shortest.
1 code implementation • 18 Feb 2022 • Peng Xiang, Xin Wen, Yu-Shen Liu, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Zhizhong Han
Our insight into the detailed geometry is to introduce a skip-transformer in the SPD to learn the point splitting patterns that can best fit the local regions.
Ranked #2 on Point Cloud Completion on ShapeNet
1 code implementation • 15 Feb 2022 • Baixu Chen, Junguang Jiang, Ximei Wang, Pengfei Wan, Jianmin Wang, Mingsheng Long
Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks.
no code implementations • 8 Dec 2021 • Jiayi Guo, Chaoqun Du, Jiangshan Wang, Huijuan Huang, Pengfei Wan, Gao Huang
For Reference-guided Image Synthesis (RIS) tasks, i. e., rendering a source image in the style of another reference image, where assessing the quality of a single generated image is crucial, these metrics are not applicable.
3 code implementations • NeurIPS 2021 • Mingcong Liu, Qiang Li, Zekui Qin, Guoxin Zhang, Pengfei Wan, Wen Zheng
Specifically, we first train a self-supervised style encoder on the generic artistic dataset to extract the representations of arbitrary styles.
2 code implementations • ICCV 2021 • Peng Xiang, Xin Wen, Yu-Shen Liu, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Zhizhong Han
However, previous methods usually suffered from discrete nature of point cloud and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details on the complete shape.
no code implementations • CVPR 2022 • Zhaoqing Wang, Qiang Li, Guoxin Zhang, Pengfei Wan, Wen Zheng, Nannan Wang, Mingming Gong, Tongliang Liu
By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks.
1 code implementation • CVPR 2021 • Xin Wen, Zhizhong Han, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Yu-Shen Liu
We provide a comprehensive evaluation in experiments, which shows that our model with the learned bidirectional geometry correspondence outperforms state-of-the-art unpaired completion methods.
1 code implementation • CVPR 2021 • Xingyu Chen, Yufeng Liu, Chongyang Ma, Jianlong Chang, Huayan Wang, Tian Chen, Xiaoyan Guo, Pengfei Wan, Wen Zheng
In the root-relative mesh recovery task, we exploit semantic relations among joints to generate a 3D mesh from the extracted 2D cues.
1 code implementation • CVPR 2021 • Xin Wen, Peng Xiang, Zhizhong Han, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Yu-Shen Liu
As a result, the network learns a strict and unique correspondence on point-level, which can capture the detailed topology and structure relationships between the incomplete shape and the complete target, and thus improves the quality of the predicted complete shape.
no code implementations • 25 Feb 2014 • Pengfei Wan, Gene Cheung, Philip A. Chou, Dinei Florencio, Cha Zhang, Oscar C. Au
In texture-plus-depth representation of a 3D scene, depth maps from different camera viewpoints are typically lossily compressed via the classical transform coding / coefficient quantization paradigm.