IterDepth: Iterative Residual Refinement for Outdoor Self-Supervised Multi-Frame Monocular Depth Estimation.
Cheng FengZhen ChenCongxuan ZhangWeiming HuBing LiFeng LuPublished in: IEEE Trans. Circuits Syst. Video Technol. (2024)
Keyphrases
- multi frame
- depth estimation
- image sequences
- super resolution
- depth map
- stereo vision
- motion estimation
- optical flow
- stereo matching
- high resolution
- point correspondences
- low resolution
- dynamic scenes
- depth information
- motion analysis
- computationally efficient
- motion segmentation
- stereo pair
- scene understanding
- real scenes
- surveillance system
- d scene
- video sequences
- high quality
- three dimensional
- computer vision
- background subtraction
- single image
- motion field
- pose estimation
- feature points
- spatio temporal
- field of view
- structure from motion
- camera motion
- disparity map
- d objects
- filtering algorithm
- machine learning