Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation

arXiv:2403.12505v1 Announce Type: new
Abstract: This paper addresses an interesting yet challenging problem -- source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation -- given only a pinhole image-trained model (i.e., source) and unlabeled panoramic images (i.e., target). Tackling this problem is nontrivial due to the semantic mismatches, style discrepancies, and inevitable distortion of panoramic images. To this end, we propose a novel method that utilizes Tangent Projection (TP) as it has less distortion and meanwhile slits the equirectangular projection …

abstract arxiv cs.cv domain domain adaptation free image images matter paper segmentation semantic semantics style type unsupervised