RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluation
Not on the map. Why?
Abstract (arXiv)
Recently, various methods for 6D pose and shape estimation of objects at a per-category level have been proposed. This work provides an overview of the field in terms of methods, datasets, and evaluation protocols. First, an overview of existing works and their commonalities and differences is provided. Second, we take a critical look at the predominant evaluation protocol, including metrics and datasets. Based on the findings, we propose a new set of metrics, contribute new annotations for the Redwood dataset, and evaluate state-of-the-art methods in a fair comparison. The results indicate that existing methods do not generalize well to unconstrained orientations and are actually heavily biased towards objects being upright. We provide an easy-to-use evaluation toolbox with well-defined metrics, methods, and dataset interfaces, which allows evaluation and comparison with various state-of-the-art approaches (https://github.com/roym899/pose_and_shape_evaluation).
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 65 of its 83 references that are in the map. First posted on arXiv 19 Jan 2023.
Builds on
65 of 83 references.
References · 65
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2017Mask R-CNNcited by 7,259
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
- 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
- 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
- 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
- 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
- 2018Open3D: A Modern Library for 3D Data Processingcited by 717
38 more
- 2021Neural Fields in Visual Computing and Beyondcited by 539
- 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
- 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
- 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
- 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
- 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
- 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
- 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
- 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
- 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
- 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
- 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
- 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
- 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
- 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
- 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
- 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
- 2021CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloudscited by 83
- 2020DualSDF: Semantic Shape Manipulation using a Two-Level Representationcited by 82
- 2016Shape Completion Enabled Robotic Graspingcited by 79
- 20196-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypointscited by 78
- 2019KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objectscited by 75
- 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
- 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 70
- 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
- 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 69
- 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
- 2016A Large Dataset of Object Scanscited by 64
- 2020NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstructioncited by 61
- 2022Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Datasetcited by 59
- 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
- 2020FroDO: From Detections to 3D Objectscited by 51
- 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
- 2022PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objectscited by 45
- 2020Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimationcited by 43
- 2022RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimationcited by 43
- 2022SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimationcited by 41
- 2021Category-Level Metric Scale Object Shape and Pose Estimationcited by 40
50 most cited of 65 All 65 (JSON)
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.