mlsanityData to 7 Oct 2026

How Robust is 3D Human Pose Estimation to Occlusion?

arXiv 1808.09316 ↗First posted 28 Aug 2018cs.CV cs.ROcited by 23

Not on the map. Why?

Abstract (arXiv)

Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks. This leaves the question open: how robust are state-of-the-art 3D pose estimation methods against partial occlusions? We study several types of synthetic occlusions over the Human3.6M dataset and find a method with state-of-the-art benchmark performance to be sensitive even to low amounts of occlusion. Addressing this issue is key to progress in applications such as collaborative and service robotics. We take a first step in this direction by improving occlusion-robustness through training data augmentation with synthetic occlusions. This also turns out to be an effective regularizer that is beneficial even for non-occluded test cases.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 7; 2023: 5; 2024: 4; 2025: 2; 2026: 1.

23 papers.

Sort:

By area:

  1. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  2. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  3. 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 95
  4. 2021Body Meshes as Pointscited by 45
  5. 20233D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimationcited by 28
  6. 2022Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Priorcited by 15
  7. 2023Rendering Humans from Object-Occluded Monocular Videoscited by 14
  8. 2022Domain Adaptive 3D Pose Augmentation for In-the-wild Human Mesh Recoverycited by 12
  9. 2022The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimationcited by 8
  10. 2024Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose Estimationcited by 5
  11. 2023Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Inputcited by 4
  12. 2024HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Imagescited by 4
11 more
  1. 2021Real-Time Human Pose Estimation on a Smart Walker using Convolutional Neural Networkscited by 2
  2. 2021PONet: Robust 3D Human Pose Estimation via Learning Orientations Onlycited by 2
  3. 2022Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimationcited by 2
  4. 2022Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentationcited by 2
  5. 2023Geometry-Biased Transformer for Robust Multi-View 3D Human Pose Reconstructioncited by 2
  6. 20243D Human Pose Estimation with Occlusions: Introducing BlendMimic3D Dataset and GCN Refinementcited by 2
  7. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
  8. 2025Benchmarking 3D Human Pose Estimation Models under Occlusionscited by 2
  9. 2023Error Estimation for Single-Image Human Body Mesh Reconstructioncited by 0
  10. 2025DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusioncited by 0
  11. 2026RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmarkcited by 0