基于双向引导学习的深度统一深度感知全景分割
Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
AI总结：
针对深度感知全景分割中分割与深度估计任务割裂的问题，提出共享对象查询的深度统一框架，并结合几何查询增强与双向引导学习，在两个基准上达到新SOTA且适用于不完整监督。
摘要：
深度感知全景分割是计算机视觉中的一个新兴课题，它结合语义理解与几何理解，以实现更鲁棒的场景解释。近期工作致力于采用统一框架应对这一挑战，但大多仍将其视为两个独立的学习任务，从而限制了其挖掘跨域信息的潜力。我们提出了一种用于深度感知全景分割的深度统一框架，该框架以相同的对象查询，按逐片段方式联合执行分割与深度估计。为缩小两个任务之间的差距，我们进一步设计了一种几何查询增强方法，该方法能够利用潜在表示将场景几何信息整合到对象查询中。此外，我们提出了一种双向引导学习方法，通过利用两个任务之间的相互关系来促进跨任务特征学习。我们的方法在 Cityscapes-DVPS 和 SemKITTI-DVPS 数据集上均创造了深度感知全景分割的最新水平。此外，实验表明，即使在监督标签不完整的情况下，我们的引导学习方法也能带来性能提升。
英文摘要：
Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly still treat it as two individual learning tasks, which limits their potential for exploring cross-domain information. We propose a deeply unified framework for depth-aware panoptic segmentation, which performs joint segmentation and depth estimation both in a per-segment manner with identical object queries. To narrow the gap between the two tasks, we further design a geometric query enhancement method, which is able to integrate scene geometry into object queries using latent representations. In addition, we propose a bi-directional guidance learning approach to facilitate cross-task feature learning by taking advantage of their mutual relations. Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets. Moreover, our guidance learning approach is shown to deliver performance improvement even under incomplete supervision labels.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
