Behind every domain there is a shift: adapting distortion-aware vision transformers for panoramic semantic segmentation
In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360◦ imagery. To tackle these problems, first, we propose the upgraded Transformer for...
Autori principali: | Zhang, J, Yang, K, Shi, H, Reiß, S, Peng, K, Ma, C, Fu, H, Torr, P, Wang, K, Stiefelhagen, R |
---|---|
Natura: | Conference item |
Lingua: | English |
Pubblicazione: |
IEEE
2024
|
Documenti analoghi
Documenti analoghi
-
Behind every domain there is a shift: adapting distortion-aware vision transformers for panoramic semantic segmentation
di: Zhang, J, et al.
Pubblicazione: (2024) -
Distortions in panoramic radiographs
di: Yeo D.K.L., et al.
Pubblicazione: (2002-11-01) -
Language-aware vision transformer for referring segmentation
di: Yang, Z, et al.
Pubblicazione: (2024) -
Semantics-aware dynamic localization and refinement for referring image segmentation
di: Yang, Z, et al.
Pubblicazione: (2023) -
LAVT: Language-Aware Vision Transformer for referring image segmentation
di: Yang, Z, et al.
Pubblicazione: (2022)