Spatial Attention Improves Iterative 6D Object Pose Estimation

• URL: http://arxiv.org/abs/2101.01659v1
• Date: Tue, 5 Jan 2021 17:18:52 GMT
• Title: Spatial Attention Improves Iterative 6D Object Pose Estimation
• Authors: Stefan Stevsic, Otmar Hilliges
• Abstract summary: We propose a new method for 6D pose estimation refinement from RGB images. Our main insight is that after the initial pose estimate, it is important to pay attention to distinct spatial features of the object. We experimentally show that this approach learns to attend to salient spatial features and learns to ignore occluded parts of the object, leading to better pose estimation across datasets.
• Score: 52.365075652976735
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The task of estimating the 6D pose of an object from RGB images can be broken down into two main steps: an initial pose estimation step, followed by a refinement procedure to correctly register the object and its observation. In this paper, we propose a new method for 6D pose estimation refinement from RGB images. To achieve high accuracy of the final estimate, the observation and a rendered model need to be aligned. Our main insight is that after the initial pose estimate, it is important to pay attention to distinct spatial features of the object in order to improve the estimation accuracy during alignment. Furthermore, parts of the object that are occluded in the image should be given less weight during the alignment process. Most state-of-the-art refinement approaches do not allow for this fine-grained reasoning and can not fully leverage the structure of the problem. In contrast, we propose a novel neural network architecture built around a spatial attention mechanism that identifies and leverages information about spatial details during pose refinement. We experimentally show that this approach learns to attend to salient spatial features and learns to ignore occluded parts of the object, leading to better pose estimation across datasets. We conduct experiments on standard benchmark datasets for 6D pose estimation (LineMOD and Occlusion LineMOD) and outperform previous state-of-the-art methods.

Related papers

• End-to-End Probabilistic Geometry-Guided Regression for 6DoF Object Pose Estimation [5.21401636701889]
  State-of-the-art 6D object pose estimators directly predict an object pose given an object observation. We reformulate the state-of-the-art algorithm GDRNPP and introduce EPRO-GDR. Our solution shows that predicting a pose distribution instead of a single pose can improve state-of-the-art single-view pose estimation.
  arXiv  Detail & Related papers  (2024-09-18T09:11:31Z)
• Rigidity-Aware Detection for 6D Object Pose Estimation [60.88857851869196]
  Most recent 6D object pose estimation methods first use object detection to obtain 2D bounding boxes before actually regressing the pose. We propose a rigidity-aware detection method exploiting the fact that, in 6D pose estimation, the target objects are rigid. Key to the success of our approach is a visibility map, which we propose to build using a minimum barrier distance between every pixel in the bounding box and the box boundary.
  arXiv  Detail & Related papers  (2023-03-22T09:02:54Z)
• Unseen Object 6D Pose Estimation: A Benchmark and Baselines [62.8809734237213]
  We propose a new task that enables and facilitates algorithms to estimate the 6D pose estimation of novel objects during testing. We collect a dataset with both real and synthetic images and up to 48 unseen objects in the test set. By training an end-to-end 3D correspondences network, our method finds corresponding points between an unseen object and a partial view RGBD image accurately and efficiently.
  arXiv  Detail & Related papers  (2022-06-23T16:29:53Z)
• Coupled Iterative Refinement for 6D Multi-Object Pose Estimation [64.7198752089041]
  Given a set of known 3D objects and an RGB or RGB-D input image, we detect and estimate the 6D pose of each object. Our approach iteratively refines both pose and correspondence in a tightly coupled manner, allowing us to dynamically remove outliers to improve accuracy.
  arXiv  Detail & Related papers  (2022-04-26T18:00:08Z)
• RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization [46.144194562841435]
  We propose a framework based on a recurrent neural network (RNN) for object pose refinement. The problem is formulated as a non-linear least squares problem based on the estimated correspondence field. The correspondence field estimation and pose refinement are conducted alternatively in each iteration to recover accurate object poses.
  arXiv  Detail & Related papers  (2022-03-24T06:24:55Z)
• PrimA6D: Rotational Primitive Reconstruction for Enhanced and Robust 6D Pose Estimation [11.873744190924599]
  We introduce a rotational primitive prediction based 6D object pose estimation using a single image as an input. We leverage a Variational AutoEncoder (VAE) to learn this underlying primitive and its associated keypoints. When evaluated over public datasets, our method yields a notable improvement over LINEMOD, Occlusion LINEMOD, and the Y-induced dataset.
  arXiv  Detail & Related papers  (2020-06-14T03:55:42Z)
• Self6D: Self-Supervised Monocular 6D Object Pose Estimation [114.18496727590481]
  We propose the idea of monocular 6D pose estimation by means of self-supervised learning. We leverage recent advances in neural rendering to further self-supervise the model on unannotated real RGB-D data.
  arXiv  Detail & Related papers  (2020-04-14T13:16:36Z)
• Object 6D Pose Estimation with Non-local Attention [29.929911622127502]
  We propose a network that integrate 6D object pose parameter estimation into the object detection framework. The proposed method reaches the state-of-the-art performance on the YCB-video and the Linemod datasets.
  arXiv  Detail & Related papers  (2020-02-20T14:23:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.