23 citations · 30 across the 4 of their papers we have counts for
4 papers · 1 filter
VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models
Chaohao Xie, Kai Han, Kwan-Yee K. Wong
Recent video inpainting methods have achieved encouraging improvements by leveraging optical flow to guide pixel propagation from reference frames either in the image space or feat…
Image Inpainting with Edge-guided Learnable Bidirectional Attention Maps
Dongsheng Wang, Chaohao Xie, Shaohui Liu +2
For image inpainting, the convolutional neural networks (CNN) in previous methods often adopt standard convolutional operator, which treats valid pixels and holes indistinguishably…
Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
Chaohao Xie, Dongwei Ren, Lei Wang +1
Recently, several weakly supervised learning methods have been devoted to utilize bounding box supervision for training deep semantic segmentation models. Most existing methods usu…
Image Inpainting with Learnable Bidirectional Attention Maps
Chaohao Xie, Shaohui Liu, Chao Li +5
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular ho…