Laformer: Vision Transformer for Panoramic Image Semantic Segmentation.
Zheng YuanJunhua WangYuxin LvDing WangYi FangPublished in: IEEE Signal Process. Lett. (2023)
Keyphrases
- semantic segmentation
- panoramic images
- superpixels
- conditional random fields
- multiple images
- field of view
- weakly supervised
- computer vision
- scene classification
- object categories
- video camera
- vision system
- dynamic scenes
- object classes
- epipolar geometry
- image processing
- image set
- object detection
- ground truth
- probabilistic model
- multiscale
- object segmentation
- high quality