Addressing Pose Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)
A novel score-based diffusion method applied to the SE(3) group, marking the first application of diffusion models to SE(3) within the image domain, specifically tailored for pose estimation tasks.
Learning a Category-Level 3D Object Pose Estimator without Requiring Pose Annotations
We propose a method to learn a category-level 3D object pose estimator without requiring any pose annotations. By leveraging diffusion models to generate multiple views of objects and an image encoder to extract robust features, our model can learn the 3D pose correspondence from the generated views and outperform state-of-the-art methods on few-shot category-level pose estimation benchmarks.
Open-Vocabulary 6D Pose Estimation of Novel Objects from Textual Prompts
A novel approach for estimating the 6D pose of novel objects using only a textual prompt, without requiring object models or video sequences.
FreeZe: Training-free Zero-shot 6D Pose Estimation with Geometric and Vision Foundation Models
FreeZe leverages pre-trained geometric and vision foundation models to perform training-free zero-shot 6D pose estimation of unseen objects, outperforming state-of-the-art competitors that require extensive training on synthetic data.
Hierarchical Binary Surface Encoding and Correspondence Pruning for Efficient RGB-D 6DoF Object Pose Estimation
HiPose establishes 3D-3D correspondences in a coarse-to-fine manner with a hierarchical binary surface encoding, enabling efficient and accurate 6DoF object pose estimation from a single RGB-D image without any time-consuming refinement.
TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer
The proposed TransPose framework exploits Transformer Encoder with a geometry-aware module to develop better learning of point cloud feature representations for accurate 6D object pose estimation.
Efficient One-step Pose Estimation for Novel Objects via NeRF and Feature Matching
An efficient NeRF-based pose estimation method is proposed that combines image matching and NeRF to directly solve the pose in one step, avoiding the need for hundreds of optimization steps and overcoming issues with local minima.
CPPF++: Uncertainty-Aware Sim-to-Real 6D Object Pose Estimation by Probabilistic Vote Aggregation
The core message of this paper is to introduce a novel method called CPPF++ that leverages a probabilistic approach to model the uncertainty in the voting process for sim-to-real 6D object pose estimation. CPPF++ builds upon the foundational point-pair voting scheme of CPPF, reformulating it through a probabilistic view to address the challenge of vote collision. It also incorporates several innovative modules, including noisy pair filtering, online alignment optimization, and a tuple feature ensemble, to enhance the robustness and accuracy of the model.
© 2024 by Linnk AI