mlsanityData to 7 Oct 2026

Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding

arXiv 2303.15417 ↗First posted 27 Mar 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Hands, one of the most dynamic parts of our body, suffer from blur due to their active movements. However, previous 3D hand mesh recovery methods have mainly focused on sharp hand images rather than considering blur due to the absence of datasets providing blurry hand images. We first present a novel dataset BlurHand, which contains blurry hand images with 3D groundtruths. The BlurHand is constructed by synthesizing motion blur from sequential sharp hand images, imitating realistic and natural motion blurs. In addition to the new dataset, we propose BlurHandNet, a baseline network for accurate 3D hand mesh recovery from a blurry hand image. Our BlurHandNet unfolds a blurry input image to a 3D hand mesh sequence to utilize temporal information in the blurry input image, while previous works output a static single hand mesh. We demonstrate the usefulness of BlurHand for the 3D hand mesh recovery from blurry images in our experiments. The proposed BlurHandNet produces much more robust results on blurry images while generalizing well to in-the-wild images. The training codes and BlurHand dataset are available at https://github.com/JaehaKim97/BlurHand_RELEASE.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 41 of its 51 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

41 of 51 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  5. 2015Spatial Transformer Networkscited by 1,423
  6. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  7. 2022Simple Baselines for Image Restorationcited by 701
  8. 2013Network In Networkcited by 600
  9. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  10. 2016Convolutional Pose Machinescited by 325
  11. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  12. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
29 more
  1. 2021Mesh Graphormercited by 264
  2. 2017Integral Human Pose Regressioncited by 255
  3. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  4. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 244
  5. 2017Video Frame Interpolation via Adaptive Separable Convolutioncited by 211
  6. 2020Deblurring by Realistic Blurringcited by 187
  7. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 179
  8. 2020Human-Aware Motion Deblurringcited by 174
  9. 2020Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wildcited by 146
  10. 2018Bringing a Blurry Frame Alive at High Frame-Rate with an Event Cameracited by 141
  11. 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 95
  12. 2018Cross-modal Deep Variational Hand Pose Estimationcited by 89
  13. 2020Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimationcited by 81
  14. 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
  15. 2021Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimationcited by 62
  16. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  17. 2018Learning to Extract a Video Sequence from a Single Motion-Blurred Imagecited by 56
  18. 2021I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modelingcited by 52
  19. 2022Realistic Blur Synthesis for Learning Image Deblurringcited by 51
  20. 2018Bringing Alive Blurred Momentscited by 44
  21. 2019DAVANet: Stereo Deblurring with View Aggregationcited by 37
  22. 20223D Interacting Hand Pose Estimation by Hand De-occlusion and Removalcited by 36
  23. 2020SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimationcited by 34
  24. 2020DeFMO: Deblurring and Shape Recovery of Fast Moving Objectscited by 16
  25. 2021Restoration of Video Frames from a Single Blurred Image with Motion Understandingcited by 10
  26. 2022Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimationcited by 8
  27. 2020AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Resultscited by 3
  28. 2022Recurrence-in-Recurrence Networks for Video Deblurringcited by 3
  29. 2022Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attentioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 3; 2026: 3.

10 papers.

  1. 2023Reconstructing Hands in 3D with Transformerscited by 298
  2. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
  3. 2023A Dataset of Relighted 3D Interacting Handscited by 35
  4. 2025The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimationcited by 16
  5. 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Imagecited by 9
  6. 2026EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learningcited by 2
  7. 2026AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimationcited by 1
  8. 2025Learning Transformation-Isomorphic Latent Space for Accurate Hand Pose Estimationcited by 0
  9. 2025Learning Correlation-aware Aleatoric Uncertainty for 3D Hand Pose Estimationcited by 0
  10. 2026UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimationcited by 0