Resolving Symmetry Ambiguity in Correspondence-based Methods for Instance-level Object Pose Estimation
Not on the map. Why?
Abstract (arXiv)
Estimating the 6D pose of an object from a single RGB image is a critical task that becomes additionally challenging when dealing with symmetric objects. Recent approaches typically establish one-to-one correspondences between image pixels and 3D object surface vertices. However, the utilization of one-to-one correspondences introduces ambiguity for symmetric objects. To address this, we propose SymCode, a symmetry-aware surface encoding that encodes the object surface vertices based on one-to-many correspondences, eliminating the problem of one-to-one correspondence ambiguity. We also introduce SymNet, a fast end-to-end network that directly regresses the 6D pose parameters without solving a PnP problem. We demonstrate faster runtime and comparable accuracy achieved by our method on the T-LESS and IC-BIN benchmarks of mostly symmetric objects. Our source code will be released upon acceptance.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 17 May 2024.
Builds on
33 of 51 references.
References · 33
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
- 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
- 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
- 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
- 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
- 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
- 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
- 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
- 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
- 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
- 2019DPOD: 6D Pose Object Detector and Refinercited by 189
21 more
- 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
- 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
- 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
- 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
- 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
- 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
- 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
- 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
- 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
- 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
- 2020EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approachcited by 46
- 2019On Object Symmetries and 6D Pose Estimation from Imagescited by 33
- 2022DPODv2: Dense Correspondence-Based 6 DoF Pose Estimationcited by 32
- 2018Deep-6DPose: Recovering 6D Object Pose from a Single RGB Imagecited by 26
- 2022OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detectioncited by 23
- 20216D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learningcited by 20
- 2022ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Frameworkcited by 19
- 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
- 2022CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformerscited by 15
- 2018SilhoNet: An RGB Method for 6D Object Pose Estimationcited by 14
- 2020Handling Object Symmetries in CNN-based Pose Estimationcited by 8
Built on by
Citing papers per year: 2026: 1.
1 paper.