Category Level Object Pose Estimation via Neural Analysis-by-Synthesis
Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances. In this paper we combine a gradient-based fitting procedure with a parametric neural image synthesis module that is capable of implicitly representing the appearance, shape and pose of entire object categories, thus rendering the need for explicit CAD models per object instance unnecessary. The image synthesis network is designed to efficiently span the pose configuration space so that model capacity can be used to capture the shape and local appearance (i.e., texture) variations jointly. At inference time the synthesized images are compared to the target via an appearance based loss and the error signal is backpropagated through the network to the input parameters. Keeping the network parameters fixed, this allows for iterative optimization of the object pose, shape and appearance in a joint manner and we experimentally show that the method can recover orientation of objects with high accuracy from 2D images alone. When provided with depth measurements, to overcome scale ambiguities, the method can accurately recover the full 6DOF pose successfully.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationObjectPose EstimationSimilar Papers 제목 키워드 기반
iCaps: Iterative Category-level Object Pose and Shape Estimation
This paper proposes a category-level 6D object pose and shape estimation approach iCaps, which allows tracking 6D poses of unseen objects in a category and estimating their 3D shapes. We develop a category-level auto-enc…
ObjectSelf-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
Category-level articulated object pose estimation aims to estimate a hierarchy of articulation-aware object poses of an unseen articulated object from a known category. To reduce the heavy annotations needed for supervis…
DisentanglementObjectPose EstimationCAPT: Category-level Articulation Estimation from a Single Point Cloud Using Transformer
The ability to estimate joint parameters is essential for various applications in robotics and computer vision. In this paper, we propose CAPT: category-level articulation estimation from a point cloud using Transformer.…
parameter estimationState EstimationTransNet: Category-Level Transparent Object Pose Estimation
Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. Even…
Depth CompletionObjectPose EstimationSurface Normal Estimation+1RCGNet: RGB-based Category-Level 6D Object Pose Estimation with Geometric Guidance
While most current RGB-D-based category-level object pose estimation methods achieve strong performance, they face significant challenges in scenes lacking depth information. In this paper, we propose a novel category-le…
Pose Estimation