This paper provides a comprehensive survey of deep learning-based object pose estimation, covering instance-level, category-level, and unseen object pose estimation. It discusses various input data modalities, degrees of freedom (DoF) in output poses, object properties, and downstream tasks. The survey also covers training paradigms, inference modes, application areas, evaluation metrics, and benchmark datasets, reporting the performance of state-of-the-art methods on these benchmarks. Key challenges, prevailing trends, and future research directions are identified, highlighting the need for more robust and generalizable methods. The survey aims to provide a holistic understanding of the field, addressing the limitations of existing reviews that often focus on specific aspects or problem formulations.This paper provides a comprehensive survey of deep learning-based object pose estimation, covering instance-level, category-level, and unseen object pose estimation. It discusses various input data modalities, degrees of freedom (DoF) in output poses, object properties, and downstream tasks. The survey also covers training paradigms, inference modes, application areas, evaluation metrics, and benchmark datasets, reporting the performance of state-of-the-art methods on these benchmarks. Key challenges, prevailing trends, and future research directions are identified, highlighting the need for more robust and generalizable methods. The survey aims to provide a holistic understanding of the field, addressing the limitations of existing reviews that often focus on specific aspects or problem formulations.