mlsanityData to 7 Oct 2026

Semi-Perspective Decoupled Heatmaps for 3D Robot Pose Estimation from Depth Maps

arXiv 2207.02519 ↗First posted 6 Jul 2022cs.CV cs.ROcited by 6

Not on the map. Why?

Abstract (arXiv)

Knowing the exact 3D location of workers and robots in a collaborative environment enables several real applications, such as the detection of unsafe situations or the study of mutual interactions for statistical and social purposes. In this paper, we propose a non-invasive and light-invariant framework based on depth devices and deep neural networks to estimate the 3D pose of robots from an external camera. The method can be applied to any robot without requiring hardware access to the internal states. We introduce a novel representation of the predicted pose, namely Semi-Perspective Decoupled Heatmaps (SPDH), to accurately compute 3D joint locations in world coordinates adapting efficient deep networks designed for the 2D Human Pose Estimation. The proposed approach, which takes as input a depth representation based on XYZ coordinates, can be trained on synthetic depth data and applied to real-world settings without the need for domain adaptation techniques. To this end, we present the SimBa dataset, based on both synthetic and real depth images, and use it for the experimental evaluation. Results show that the proposed approach, made of a specific depth map representation and the SPDH, overcomes the current state of the art.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 6 Jul 2022.

Builds on

20 of 42 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  7. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
  11. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  12. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 205
8 more
  1. 2019Camera-to-Robot Pose Estimation from a Single Imagecited by 48
  2. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  3. 2021Single-view robot pose and joint angle estimation via render & comparecited by 33
  4. 2015Kinect Range Sensing: Structured-Light versus Time-of-Flight Kinectcited by 16
  5. 2019Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimationcited by 6
  6. 2020Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Cameracited by 5
  7. 2019Real-time Convolutional Networks for Depth-based Human Pose Estimationcited by 4
  8. 2017Head Detection with Depth Images in the Wildcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 3.

6 papers.

  1. 2024RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Trainingcited by 10
  2. 2025Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Mapcited by 2
  3. 2024Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGBcited by 1
  4. 20233D Pose Nowcasting: Forecast the Future to Improve the Presentcited by 0
  5. 2025Latent Representations for Visual Proprioception in Inexpensive Robotscited by 0
  6. 2025PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Controlcited by 0