Self-supervised Event-based Monocular Depth Estimation using Cross-modal Consistency.
Junyu ZhuLina LiuBofeng JiangFeng WenHongbo ZhangWanlong LiYong LiuPublished in: CoRR (2024)
Keyphrases
- cross modal
- depth estimation
- stereo vision
- depth map
- multi modal
- stereo matching
- image sequences
- depth information
- scene understanding
- real scenes
- visual recognition
- dynamic scenes
- multimedia retrieval
- stereo pair
- pose estimation
- feature matching
- super resolution
- event detection
- image retrieval
- multi view
- specular reflection
- object recognition
- three dimensional
- visual data
- d scene
- visual similarity
- multimedia databases
- stereo images
- optical flow
- computer vision
- data sets
- visual features
- vision system
- object detection
- image data
- high quality
- multimedia