A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps.
Xiaowen JiangValerio CambareriGianluca AgrestiCynthia Ifeyinwa UgwuAdriano SimonettoFabien CardinauxPietro ZanuttighPublished in: CVPR Workshops (2022)
Keyphrases
- time of flight
- low memory
- depth map
- depth information
- multi view
- d scene
- depth images
- high quality
- stereo matching
- three dimensional
- tof camera
- depth data
- depth video
- depth estimation
- depth cameras
- real scenes
- view synthesis
- input image
- high resolution
- super resolution
- image sequences
- stereo pair
- low resolution
- high accuracy
- viewpoint
- pose estimation
- input data
- color images
- range data
- depth values
- depth estimates