DAEANet: Dual auto-encoder attention network for depth map super-resolution.
Xiang CaoYihao LuoXianyi ZhuLiangqi ZhangYan XuHaibo ShenTianjiang WangQi FengPublished in: Neurocomputing (2021)
Keyphrases
- super resolution
- depth map
- low resolution
- high resolution
- motion estimation
- super resolved
- depth information
- d scene
- high quality
- stereo matching
- image restoration
- low resolution images
- multi view
- depth estimation
- motion blur
- multi frame
- single image
- super resolution reconstruction
- image super resolution
- stereo pair
- three dimensional
- high resolution images
- image sequences
- view synthesis
- bit rate
- light field
- machine learning