CapeNext: Rethinking and refining dynamic support information for category-agnostic pose estimation
It addresses robustness and flexibility issues in pose estimation for various categories, representing an incremental advancement in the field.
The paper tackled limitations in category-agnostic pose estimation, such as ambiguity from polysemous keypoint descriptions and insufficient discriminability for fine-grained variations, by proposing a new framework that integrates hierarchical cross-modal interaction and dual-stream feature refinement, achieving state-of-the-art performance on the MP-100 dataset with consistent large-margin improvements.
Recent research in Category-Agnostic Pose Estimation (CAPE) has adopted fixed textual keypoint description as semantic prior for two-stage pose matching frameworks. While this paradigm enhances robustness and flexibility by disentangling the dependency of support images, our critical analysis reveals two inherent limitations of static joint embedding: (1) polysemy-induced cross-category ambiguity during the matching process(e.g., the concept "leg" exhibiting divergent visual manifestations across humans and furniture), and (2) insufficient discriminability for fine-grained intra-category variations (e.g., posture and fur discrepancies between a sleeping white cat and a standing black cat). To overcome these challenges, we propose a new framework that innovatively integrates hierarchical cross-modal interaction with dual-stream feature refinement, enhancing the joint embedding with both class-level and instance-specific cues from textual description and specific images. Experiments on the MP-100 dataset demonstrate that, regardless of the network backbone, CapeNext consistently outperforms state-of-the-art CAPE methods by a large margin.