mlsanityData to 14 Oct 2026

Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects

arXiv 2203.08472 ↗First posted 16 Mar 2022cs.CV cs.ROcited by 17

Not on the map. Why?

Abstract (arXiv)

In this paper, we tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images. This task contrasts with the one considered by most existing deep learning methods which typically assume that the testing objects have been observed during training. To handle the unseen objects, we follow a retrieval-based strategy and prevent the network from learning object-specific features by computing multi-scale local similarities between the query image and synthetically-generated reference images. We then introduce an adaptive fusion module that robustly aggregates the local similarities into a global similarity score of pairwise images. Furthermore, we speed up the retrieval process by developing a fast retrieval strategy. Our experiments on the LineMOD, LineMOD-Occluded, and T-LESS datasets show that our method yields a significantly better generalization to unseen objects than previous works. Our code and pre-trained models are available at https://sailor-z.github.io/projects/Unseen_Object_Pose.html.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

29 of 42 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  8. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  9. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  10. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  11. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  12. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
17 more
  1. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  2. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  3. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 241
  4. 2022Generalized Category Discoverycited by 211
  5. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  6. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  7. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  8. 2019Category-Level Articulated Object Pose Estimationcited by 159
  9. 2019kPAM: KeyPoint Affordances for Category-Level Robotic Manipulationcited by 153
  10. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  11. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 89
  12. 2019Single-Stage 6D Object Pose Estimationcited by 88
  13. 20196-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypointscited by 78
  14. 2015Learning Descriptors for Object Recognition and 3D Pose Estimationcited by 60
  15. 2019Multi-path Learning for Object Pose Estimation Across Domainscited by 52
  16. 2019Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objectscited by 39
  17. 2021PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learningcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 7; 2025: 3; 2026: 1.

17 papers.

Sort:

By area:

  1. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 121
  2. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  3. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  4. 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
  5. 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
  6. 2024Object Pose Estimation via the Aggregation of Diffusion Featurescited by 12
  7. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  8. 20233D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimationcited by 11
  9. 2024OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimationcited by 10
  10. 20256D Object Pose Tracking in Internet Videos for Robotic Manipulationcited by 10
  11. 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimationcited by 9
  12. 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
5 more
  1. 2025Reasoning and Learning a Perceptual Metric for Self-Training of Reflective Objects in Bin-Picking with a Low-cost Cameracited by 2
  2. 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matchingcited by 1
  3. 2024DVMNet++: Rethinking Relative Pose Estimation for Unseen Objectscited by 0
  4. 2025Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformerscited by 0
  5. 2026MixRI: Mixing Features of Reference Images for Novel Object Pose Estimationcited by 0