Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. Existing methods only rely on the features extracted at support keypoints to predict or refine the keypoints on query image, but a few support feature vectors are local and inadequate for CAPE. Considering that human can quickly perceive potential keypoints of arbitrary objects, we propose a novel framework for CAPE based on such potential keypoints (named as meta-points). Specifically, we maintain learnable embeddings to capture inherent information of various keypoints, which interact with image feature maps to produce meta-points without any support. The produced meta-points could serve as meaningful potential keypoints for CAPE. Due to the inevitable gap between inherency and annotation, we finally utilize the identities and details offered by support keypoints to assign and refine meta-points to desired keypoints in query image. In addition, we propose a progressive deformable point decoder and a slacked regression loss for better prediction and supervision. Our novel framework not only reveals the inherency of keypoints but also outperforms existing methods of CAPE. Comprehensive experiments and in-depth studies on large-scale MP-100 dataset demonstrate the effectiveness of our framework.
Code (1)
Tasks
Category-Agnostic Pose EstimationDecoderPose EstimationSimilar Papers 제목 키워드 기반
Category-Agnostic 6D Pose Estimation with Conditional Neural Processes
We present a novel meta-learning approach for 6D pose estimation on unknown objects. In contrast to ``instance-level" and ``category-level" pose estimation methods, our algorithm learns object representation in a categor…
6D Pose EstimationDecoderGraph Neural NetworkMeta-Learning+2CapeNext: Rethinking and Refining Dynamic Support Information for Category-Agnostic Pose Estimation
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…
Category-Agnostic Pose EstimationPointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases …
Point Cloud CompletionTest-time AdaptationStarMap for Category-Agnostic Keypoint and Viewpoint Estimation
Semantic keypoints provide concise abstractions for a variety of visual understanding tasks. Existing methods define semantic keypoints separately for each category with a fixed number of semantic labels in fixed indices…
Keypoint DetectionViewpoint EstimationCapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
Category-agnostic pose estimation (CAPE) has traditionally relied on support images with annotated keypoints, a process that is often cumbersome and may fail to fully capture the necessary correspondences across diverse …
2D Pose EstimationCategory-Agnostic Pose EstimationLanguage ModelingLanguage Modelling+4