Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation.
Jiaming ZhangKailun YangChaoxiang MaSimon ReißKunyu PengRainer StiefelhagenPublished in: CoRR (2022)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- label transfer
- superpixels
- scene classification
- weakly supervised
- image understanding
- object categories
- pascal voc
- object detection
- object class
- object recognition
- stereo vision
- information extraction
- viewpoint
- image set
- natural scenes
- object classes
- named entities
- bag of features
- natural images
- input image
- small number
- multiscale