Search Results for author: Naofumi Akimoto

Found 4 papers, 2 papers with code

Document Shadow Removal with Foreground Detection Learning From Fully Synthetic Images

1 code implementation 2022 2022 Yuhi Matsuo, Naofumi Akimoto, Yoshimitsu Aoki

In this paper, we present a large-scale and diverse dataset called fully synthetic document shadow removal dataset (FSDSRD) that does not require capturing documents.

Document Shadow Removal

Reference-Based Video Colorization with Spatiotemporal Correspondence

no code implementations25 Nov 2020 Naofumi Akimoto, Akio Hayakawa, Andrew Shin, Takuya Narihira

To address this issue, we warp colors only from the regions on the reference frame restricted by correspondence in time.

Colorization Semantic correspondence

Fast Soft Color Segmentation

no code implementations CVPR 2020 Naofumi Akimoto, Huachun Zhu, Yanghua Jin, Yoshimitsu Aoki

We address the problem of soft color segmentation, defined as decomposing a given image into several RGBA layers, each containing only homogeneous color regions.

Segmentation Video Editing

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