Optimal depth recovery using image guided TGV with depth confidence for high-quality view synthesis
详细信息 查看全文
- 作者：Pongsak Lasanga ; b ; pongsak.lasang@sg.panasonic.com" class="auth_mail" title="E-mail the corresponding author ; Wuttipong Kumwilaisakc ; wuttipong.kum@kmutt.ac.th" class="auth_mail" title="E-mail the corresponding author ; Yazhou Liud ; yazhouliu@njust.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Sheng Mei Shena ; shengmei.shen@sg.panasonic.com" class="auth_mail" title="E-mail the corresponding author
- 关键词：RGB-D sensors ; Depth confidence ; Depth recovery ; Depth Image Based Rendering (DIBR) ; View synthesis ; Hole filling
- 刊名：Journal of Visual Communication and Image Representation
- 出版年：2016
- 出版时间：August 2016
- 年：2016
- 卷：39
- 期：Complete
- 页码：24-39
- 全文大小：4472 K
文摘
- •
A confidence-based depth recovery and high quality 3D view synthesis are proposed.
- •
The depth recovery relies on image edges and high depth confidence pixels.
- •
Texture directions of background are effective in hole filling for view synthesis.