In this paper, we address panoramic semantic segmentation, which provides a full-view and dense-pixel understanding of surroundings in a holistic way. Panoramic segmentation is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of annotations for training panoramic segmenters. To tackle these problems, we propose a Transformer for Panoramic Semantic Segmentation (Trans4PASS) architecture. First, to enhance distortion awareness, Trans4PASS, equipped with Deformable Patch Embedding (DPE) and Deformable MLP (DMLP) modules, is capable of handling object deformations and image distortions whenever (before or after adaptation) and wherever (shallow or deep levels) by design. We further introduce the upgraded Trans4PASS+ model, featuring DMLPv2 with parallel token mixing to improve the flexibility and generalizability in modeling discriminative cues. Second, we propose a Mutual Prototypical Adaptation (MPA) strategy for unsupervised domain adaptation. Third, aside from Pinhole-to-Panoramic (Pin2Pan) adaptation, we create a new dataset (SynPASS) with 9,080 panoramic images to explore a Synthetic-to-Real (Syn2Real) adaptation scheme in 360{\deg} imagery. Extensive experiments are conducted, which cover indoor and outdoor scenarios, and each of them is investigated with Pin2Pan and Syn2Real regimens. Trans4PASS+ achieves state-of-the-art performances on four domain adaptive panoramic semantic segmentation benchmarks. Code is available at https://github.com/jamycheung/Trans4PASS.

翻译：在本文中,我们处理的是全色语义分解,它以整体方式提供全视和密集的对周围环境的了解。全色分解由于以下两个重大挑战而未得到充分探索:(1) 整形图像扭曲和物体变形;(2) 缺乏用于培训全色分解器的说明;为解决这些问题,我们提议了全色语义分解(Trans4PASS)结构的变异器。首先,为了提高扭曲意识, Trans4PASS, 配有可变补丁嵌入模块(DPE)和可变MLP(DMLP)模块。由于两种关键挑战:(1) 整形偏差的图像扭曲和物体变形;(2) 缺乏用于培训全色分解分解的描述说明;(2) 更升级的 Transad4PASS+模型,由DMLPv2 和平行的代号混合,以提高制导信号的灵活度和通用性能。第二,我们提议采用可变现的S-Retooral S-S-S-S-Silental Syal Syal-deal Syal Syal Syal-deal-deal-deal-deal-deal-deal-deal-deal-tototototototo sweal-tototo sweal-weal-s