mlsanityData to 7 Oct 2026

YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regression

arXiv 2205.02536 ↗First posted 5 May 2022cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications. The state-of-the-art models for pose estimation are convolutional neural network (CNN)-based. Lately, Transformers, an architecture originally proposed for natural language processing, is achieving state-of-the-art results in many computer vision tasks as well. Equipped with the multi-head self-attention mechanism, Transformers enable simple single-stage end-to-end architectures for learning object detection and 6D object pose estimation jointly. In this work, we propose YOLOPose (short form for You Only Look Once Pose estimation), a Transformer-based multi-object 6D pose estimation method based on keypoint regression. In contrast to the standard heatmaps for predicting keypoints in an image, we directly regress the keypoints. Additionally, we employ a learnable orientation estimation module to predict the orientation from the keypoints. Along with a separate translation estimation module, our model is end-to-end differentiable. Our method is suitable for real-time applications and achieves results comparable to state-of-the-art methods.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 5 May 2022.

Builds on

23 of 31 references.

References · 23

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  6. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  7. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  8. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  9. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  10. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  11. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  12. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
11 more
  1. 2015End-to-end people detection in crowded scenescited by 140
  2. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  3. 2019Single-Stage 6D Object Pose Estimationcited by 88
  4. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  5. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  6. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  7. 2016Inductive Bias of Deep Convolutional Networks through Pooling Geometrycited by 53
  8. 2021PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimationcited by 14
  9. 2020Exploring intermediate representation for monocular vehicle pose estimationcited by 12
  10. 2019Refining 6D Object Pose Predictions using Abstract Render-and-Comparecited by 8
  11. 2018Robust 6D Object Pose Estimation in Cluttered Scenes using Semantic Segmentation and Pose Regression Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 7; 2025: 0; 2026: 1.

17 papers.

Sort:

  1. 2023Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)cited by 17
  2. 2022CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformerscited by 15
  3. 2024Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenescited by 12
  4. 2023TransPose: 6D Object Pose Estimation with Geometry-Aware Transformercited by 7
  5. 2024GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidancecited by 7
  6. 2024ASDF: Assembly State Detection Utilizing Late Fusion by Integrating 6D Pose Estimationcited by 6
  7. 2022Video based Object 6D Pose Estimation using Transformerscited by 5
  8. 2024RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Imagescited by 5
  9. 2023External Camera-based Mobile Robot Pose Estimation for Collaborative Perception with Smart Edge Sensorscited by 4
  10. 2023YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimationcited by 3
  11. 2022Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labelscited by 2
  12. 2024Deep Transformer Network for Monocular Pose Estimation of Shipborne Unmanned Aerial Vehiclecited by 1
5 more
  1. 2023KVN: Keypoints Voting Network with Differentiable RANSAC for Stereo Pose Estimationcited by 0
  2. 2023Efficient Multi-Object Pose Estimation using Multi-Resolution Deformable Attention and Query Aggregationcited by 0
  3. 2024Sparse Color-Code Net: Real-Time RGB-Based 6D Object Pose Estimation on Edge Devicescited by 0
  4. 2024A Novel Convolution and Attention Mechanism-based Model for 6D Object Pose Estimationcited by 0
  5. 2026TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformerscited by 0