RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering

Iwase, Shun; Liu, Xingyu; Khirodkar, Rawal; Yokota, Rio

doi:10.1109/iccv48922.2021.00329

Cited by 44 publications

(38 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DPOD [11] predicted the relative transformation between the input image observed via the RGB sensor and the rendered image using the initial pose proposal, which then were refined iteratively. RePOSE [12] introduced the intermediate representation with a neural network to calculate the relative transformation. In addition to new representation, RNNPose [13] exploited the recurrent neural network in the iteration process.…”

Section: A Single-view-based Pose Refinementmentioning

confidence: 99%

Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation

Jeon

Kim

Ryu

et al. 2023

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

6D object pose estimation aims to infer the relative pose between the object and the camera using a single image or multiple images. Most works have focused on predicting the object pose without associated uncertainty under occlusion and structural ambiguity (symmetricity). However, these works demand prior information about shape attributes, and this condition is hardly satisfied in reality; even asymmetric objects may be symmetric under the viewpoint change. In addition, acquiring and fusing diverse sensor data is challenging when extending them to robotics applications. Tackling these limitations, we present an ambiguity-aware 6D object pose estimation network, PrimA6D++, as a generic uncertainty prediction method. The major challenges in pose estimation, such as occlusion and symmetry, can be handled in a generic manner based on the measured ambiguity of the prediction. Specifically, we devise a network to reconstruct the three rotation axis primitive images of a target object and predict the underlying uncertainty along each primitive axis. Leveraging the estimated uncertainty, we then optimize multi-object poses using visual measurements and camera poses by treating it as an object SLAM problem. The proposed method shows a significant performance improvement in T-LESS and YCB-Video datasets. We further demonstrate real-time scene recognition capability for visually-assisted robot manipulation. Our code and supplementary materials are available at https://github.com/rpmsnu/PrimA6D.

show abstract

Section: A Single-view-based Pose Refinementmentioning

confidence: 99%

Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation

Jeon

Kim

Ryu

et al. 2023

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Occlusion handling is an important challenge for object pose estimation. Figure 1 presents the performance of general purpose methods [45], [75], [80], [78], [93], [94], [112] compared to those designed for occlusion handling [43], [49], [98], [100], [104], [105], [108], [110]. Evaluations on the LM [35] and the LMO [10] dataset are presented.…”

Section: B Occlusion Handlingmentioning

confidence: 99%

“…As such, geometric correspondences are regressed as an intermediate representation and the 6D pose is inferred from them. Training in such an end-to-end manner improves performance over deriving the 6D pose using PnP and alike [44], [105], [93], [100], [49], [77], [11].…”

Section: End-to-end Trainingmentioning

confidence: 99%

“…An input image pair, observation and rendered estimate, is processed by a network to predict the relative transformation. Many recent works build on their iterative refinement approach [53], [43], [62], [110], [49], [31], [4], [109]. Some recent works propose to replace iterative refinement by parallel hypotheses scoring and matching against templates [43], [34].…”

Section: E Refinementmentioning

confidence: 99%

See 1 more Smart Citation

Open Challenges for Monocular Single-shot 6D Object Pose Estimation

Thalhammer¹,

Peter²,

Weibel³

et al. 2023

Preprint

View full text Add to dashboard Cite

Object pose estimation is a non-trivial task that enables robotic manipulation, bin picking, augmented reality, and scene understanding, to name a few use cases. Monocular object pose estimation gained considerable momentum with the rise of high-performing deep learning-based solutions and is particularly interesting for the community since sensors are inexpensive and inference is fast. Prior works establish the comprehensive state of the art for diverse pose estimation problems. Their broad scopes make it difficult to identify promising future directions. We narrow down the scope to the problem of singleshot monocular 6D object pose estimation, which is commonly used in robotics, and thus are able to identify such trends. By reviewing recent publications in robotics and computer vision, the state of the art is established at the union of both fields. Following that, we identify promising research directions in order to help researchers to formulate relevant research ideas and effectively advance the state of the art. Findings include that methods are sophisticated enough to overcome the domain shift and that occlusion handling is a fundamental challenge. We also highlight problems such as novel object pose estimation and challenging materials handling as central challenges to advance robotics.

show abstract

“…Previously, when the CAD model is available, one common way of enhancing pose accuracy is to apply a post-refinement step through matching the rendered results against observed images given initial estimates, which has been widely explored in both traditional [2,44] and learning-based [30,59,27,25] methods. Being motivated by this, we seek to tackle the above problem by investigating object pose refinement at the category level.…”

Section: Introductionmentioning

confidence: 99%

CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement

Liu¹,

Gu²,

Li³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc. Orthogonal to them, this work presents a category-level object pose and size refiner CATRE, which is able to iteratively enhance pose estimate from point clouds to produce accurate results. Given an initial pose estimate, CATRE predicts a relative transformation between the initial pose and ground truth by means of aligning the partially observed point cloud and an abstract shape prior. In specific, we propose a novel disentangled architecture being aware of the inherent distinctions between rotation and translation/size estimation. Extensive experiments show that our approach remarkably outperforms state-ofthe-art methods on REAL275, CAMERA25, and LM benchmarks up to a speed of ≈85.32Hz, and achieves competitive results on categorylevel tracking. We further demonstrate that CATRE can perform pose refinement on unseen category. Code and trained models are available. 1 * Equal contribution.

show abstract

RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering

Cited by 44 publications

References 20 publications

Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation

Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation

Open Challenges for Monocular Single-shot 6D Object Pose Estimation

CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement

Contact Info

Product

Resources

About