Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations
- URL: http://arxiv.org/abs/2008.08391v1
- Date: Wed, 19 Aug 2020 12:07:01 GMT
- Title: Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations
- Authors: Zhigang Li, Yinlin Hu, Mathieu Salzmann, and Xiangyang Ji
- Abstract summary: We introduce an approach to robustly and accurately estimate the 6-DoF pose in challenging conditions without using any real pose annotations.
We achieve state of the art performance on LINEMOD, and OccludedLINEMOD in without real-pose setting, even outperforming methods that rely on real annotations during training on Occluded-LINEMOD.
- Score: 92.5075742765229
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While much progress has been made in 6-DoF object pose estimation from a
single RGB image, the current leading approaches heavily rely on
real-annotation data. As such, they remain sensitive to severe occlusions,
because covering all possible occlusions with annotated data is intractable. In
this paper, we introduce an approach to robustly and accurately estimate the
6-DoF pose in challenging conditions and without using any real pose
annotations. To this end, we leverage the intuition that the poses predicted by
a network from an image and from its counterpart synthetically altered to mimic
occlusion should be consistent, and translate this to a self-supervised loss
function. Our experiments on LINEMOD, Occluded-LINEMOD, YCB and new
Randomization LINEMOD dataset evidence the robustness of our approach. We
achieve state of the art performance on LINEMOD, and OccludedLINEMOD in without
real-pose setting, even outperforming methods that rely on real annotations
during training on Occluded-LINEMOD.
Related papers
- MSDA: Monocular Self-supervised Domain Adaptation for 6D Object Pose
Estimation [12.773040823634908]
We propose a self-supervised domain adaptation approach to acquire labeled 6D poses from real images.
We first pre-train the model with synthetic RGB images and then utilize real RGB(-D) images to fine-tune the pre-trained model.
We experimentally demonstrate that our method achieves comparable performance against its fully-supervised counterpart.
arXiv Detail & Related papers (2023-02-14T19:34:41Z) - 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) - Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation [88.8963330073454]
We propose a novel monocular 6D pose estimation approach by means of self-supervised learning.
We leverage current trends in noisy student training and differentiable rendering to further self-supervise the model.
Our proposed self-supervision outperforms all other methods relying on synthetic data.
arXiv Detail & Related papers (2022-03-19T15:12:06Z) - SporeAgent: Reinforced Scene-level Plausibility for Object Pose
Refinement [28.244027792644097]
While depth- and RGB-based pose refinement approaches increase the accuracy of the resulting pose estimates, they are susceptible to ambiguity as they consider visual alignment.
We show that considering plausibility reduces ambiguity and, in consequence, allows poses to be more accurately predicted in cluttered environments.
Experiments on the LINEMOD and YCB-VIDEO datasets demonstrate the state-of-the-art performance of our depth-based refinement approach.
arXiv Detail & Related papers (2022-01-01T20:26:19Z) - SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation [98.83762558394345]
SO-Pose is a framework for regressing all 6 degrees-of-freedom (6DoF) for the object pose in a cluttered environment from a single RGB image.
We introduce a novel reasoning about self-occlusion, in order to establish a two-layer representation for 3D objects.
Cross-layer consistencies that align correspondences, self-occlusion and 6D pose, we can further improve accuracy and robustness.
arXiv Detail & Related papers (2021-08-18T19:49:29Z) - Spatial Attention Improves Iterative 6D Object Pose Estimation [52.365075652976735]
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.
arXiv Detail & Related papers (2021-01-05T17:18:52Z) - 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)
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.