The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation.
Xinni JiangZengsheng KuangChunle GuoRuixun ZhangLei CaiXiao FanChongyi LiPublished in: CoRR (2024)
Keyphrases
- super resolution
- cross modal
- depth map
- low resolution face images
- multi modal
- low resolution
- high resolution
- low resolution images
- motion estimation
- multimedia retrieval
- super resolved
- high quality
- multimedia databases
- image retrieval
- super resolution reconstruction
- machine learning
- visual recognition
- visual data
- visual similarity
- light field
- high dimensional
- multi view
- image sequences
- image database
- co occurrence
- three dimensional