Unified multi-lateral filter for real-time depth map enhancement
作者：
Highlights：
• New multi-lateral filter to efficiently increase the spatial resolution of low-resolution and noisy depth maps in real-time.
• ToF camera coupled with a 2-D camera of higher resolution to which the low-resolution depth map will upsampled.
• We account for the inaccuracy of depth edges position due to the low-resolution ToF depth maps.
• Unwanted artefacts such as texture copying and edge blurring are almost entirely eliminated.
• The proposed filter is convolution-based and achives a real-time performance by data quantization and downsampling.
• The proposed filter has been effectively and efficiently implemented for dynamic scenes in real-time applications.
• The proposed filter can be easily adapted for alternative depth sensing systems than ToF cameras.
摘要
•New multi-lateral filter to efficiently increase the spatial resolution of low-resolution and noisy depth maps in real-time.•ToF camera coupled with a 2-D camera of higher resolution to which the low-resolution depth map will upsampled.•We account for the inaccuracy of depth edges position due to the low-resolution ToF depth maps.•Unwanted artefacts such as texture copying and edge blurring are almost entirely eliminated.•The proposed filter is convolution-based and achives a real-time performance by data quantization and downsampling.•The proposed filter has been effectively and efficiently implemented for dynamic scenes in real-time applications.•The proposed filter can be easily adapted for alternative depth sensing systems than ToF cameras.
论文关键词：Depth enhancement,Data fusion,Sensor fusion,Multi-modal sensors,Adaptive filters,Active sensing,Time-of-Flight
论文评审过程：Received 25 June 2014, Revised 25 April 2015, Accepted 24 June 2015, Available online 3 July 2015, Version of Record 17 July 2015.
论文官网地址：https://doi.org/10.1016/j.imavis.2015.06.008
