17 citations · 41 across the 4 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CV2023★ 17 cited
Towards Interactive Image Inpainting via Sketch Refinement
Chang Liu, Shunxin Xu, Jialun Peng +2
One tough problem of image inpainting is to restore complex structures in the corrupted regions. It motivates interactive image inpainting which leverages additional hints, e.g., s…
cs.CV2023★ 14 cited
Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting
Kaidong Zhang, Jialun Peng, Jingjing Fu +1
Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for…