Compression Artifacts Reduction for Depth Map by Deep Intensity Guidance
文献类型：会议论文
| 作者 | Pingping Zhang; Xu Wang; Yun Zhang; Lin Ma; Jianmin Jiang; Sam Kwong |
| 出版日期 | 2017 |
| 会议日期 | 2017 |
| 会议地点 | 哈尔滨 |
| 英文摘要 | In this paper, we propose a intensity guided CNN (IG-Net) model, which learns an end-to-end mapping between the intensity image and distorted depth map to the uncompressed depth map. To eliminate the undesired blocking artifacts such as discontinuities around object boundary, two branches are designed to extract the high-frequency in- formation from intensity image and depth map, respectively. Multi-scale feature fusion and enhancement layers are introduced in the main branch to strength the edge information of the restored depth map. Performance evaluation on JPEG compression artifacts shows the effectiveness and su- periority of our proposed model compared with state-of-the-art methods. |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/12641]  |
| 专题 | 深圳先进技术研究院_数字所 |
| 作者单位 | 2017 |
| 推荐引用方式 GB/T 7714 | Pingping Zhang,Xu Wang,Yun Zhang,et al. Compression Artifacts Reduction for Depth Map by Deep Intensity Guidance[C]. 见:. 哈尔滨. 2017. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。