GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints.
Anqi ChengZhiyuan YangHaiyue ZhuKezhi MaoPublished in: CoRR (2024)
Keyphrases
- depth estimation
- semantic constraints
- depth map
- stereo vision
- stereo matching
- semantic representation
- depth information
- dynamic scenes
- semantic knowledge
- dense depth maps
- real scenes
- scene understanding
- stereo pair
- knowledge sources
- multi view
- disparity map
- three dimensional
- relational schema
- noun phrases
- super resolution
- feature matching
- specular reflection
- stereo images
- high quality
- high resolution
- d scene
- input data
- dynamic programming
- domain knowledge
- expert systems
- depth from defocus
- depth estimates