mlsanityData to 14 Oct 2026

Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation

arXiv 2111.06500 ↗First posted 11 Nov 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

While hand pose estimation is a critical component of most interactive extended reality and gesture recognition systems, contemporary approaches are not optimized for computational and memory efficiency. In this paper, we propose a tiny deep neural network of which partial layers are recursively exploited for refining its previous estimations. During its iterative refinements, we employ learned gating criteria to decide whether to exit from the weight-sharing loop, allowing per-sample adaptation in our model. Our network is trained to be aware of the uncertainty in its current predictions to efficiently gate at each iteration, estimating variances after each loop for its keypoint estimates. Additionally, we investigate the effectiveness of end-to-end and progressive training protocols for our recursive structure on maximizing the model capacity. With the proposed setting, our method consistently outperforms state-of-the-art 2D/3D hand pose estimation approaches in terms of both accuracy and efficiency for widely used benchmarks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 11 Nov 2021.

Builds on

37 of 56 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2015Fast R-CNNcited by 2,933
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  6. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  7. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  8. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  9. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
  10. 2016Adaptive Computation Time for Recurrent Neural Networkscited by 506
  11. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 332
  12. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
25 more
  1. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  2. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 230
  3. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  4. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 189
  5. 2017Convolutional Networks with Adaptive Inference Graphscited by 148
  6. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
  7. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  8. 2019H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactionscited by 141
  9. 2019End-to-end Hand Mesh Recovery from a Monocular RGB Imagecited by 124
  10. 2019Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Renderingcited by 115
  11. 2018Hand Pose Estimation via Latent 2.5D Heatmap Regressioncited by 111
  12. 2018Cross-modal Deep Variational Hand Pose Estimationcited by 89
  13. 2015Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognitioncited by 67
  14. 2018Adaptive Neural Treescited by 64
  15. 2017Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Executioncited by 59
  16. 2020Domain-Adaptive Few-Shot Learningcited by 40
  17. 2017Using a single RGB frame for real time 3D hand pose estimation in the wildcited by 39
  18. 20163D Hand Pose Tracking and Estimation Using Stereo Matchingcited by 35
  19. 2020SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimationcited by 34
  20. 2019Feature Boosting Network For 3D Pose Estimationcited by 26
  21. 2020RNNPool: Efficient Non-linear Pooling for RAM Constrained Inferencecited by 21
  22. 2019EXTD: Extremely Tiny Face Detector via Iterative Filter Reusecited by 18
  23. 2018IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classificationcited by 12
  24. 2019URNet : User-Resizable Residual Networks with Conditional Gating Modulecited by 6
  25. 2020KL-Divergence-Based Region Proposal Network for Object Detectioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

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

3 papers.

  1. 2023An Outlook into the Future of Egocentric Visioncited by 84
  2. 2022Interacting Hand-Object Pose Estimation via Dense Mutual Attentioncited by 22
  3. 2026Rethinking Graph Convolution for 2D-to-3D Hand Pose Liftingcited by 0