CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
This work addresses pose estimation for robotics and AR/VR by improving accuracy with multi-modal learning, though it is incremental as it builds on existing CLIP models.
The authors tackled category-level object pose estimation by leveraging pre-trained vision-language knowledge to overcome limited 3D data, achieving state-of-the-art performance on REAL275 and CAMERA25 benchmarks with real-time inference at 40FPS.
Most of existing category-level object pose estimation methods devote to learning the object category information from point cloud modality. However, the scale of 3D datasets is limited due to the high cost of 3D data collection and annotation. Consequently, the category features extracted from these limited point cloud samples may not be comprehensive. This motivates us to investigate whether we can draw on knowledge of other modalities to obtain category information. Inspired by this motivation, we propose CLIPose, a novel 6D pose framework that employs the pre-trained vision-language model to develop better learning of object category information, which can fully leverage abundant semantic knowledge in image and text modalities. To make the 3D encoder learn category-specific features more efficiently, we align representations of three modalities in feature space via multi-modal contrastive learning. In addition to exploiting the pre-trained knowledge of the CLIP's model, we also expect it to be more sensitive with pose parameters. Therefore, we introduce a prompt tuning approach to fine-tune image encoder while we incorporate rotations and translations information in the text descriptions. CLIPose achieves state-of-the-art performance on two mainstream benchmark datasets, REAL275 and CAMERA25, and runs in real-time during inference (40FPS).