mlsanityData to 14 Oct 2026

EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning

arXiv 2601.19850 ↗First posted 27 Jan 2026cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Robust 3D hand reconstruction in egocentric vision is challenging due to depth ambiguity, self-occlusion, and complex hand-object interactions. Prior methods mitigate these issues by scaling training data or adding auxiliary cues, but they often struggle in unseen contexts. We present EgoHandICL, the first in-context learning (ICL) framework for 3D hand reconstruction that improves semantic alignment, visual consistency, and robustness under challenging egocentric conditions. EgoHandICL introduces complementary exemplar retrieval guided by vision-language models (VLMs), an ICL-tailored tokenizer for multimodal context, and a masked autoencoder (MAE)-based architecture trained with hand-guided geometric and perceptual objectives. Experiments on ARCTIC and EgoExo4D show consistent gains over state-of-the-art methods. We also demonstrate real-world generalization and improve EgoVLM hand-object interaction reasoning by using reconstructed hands as visual prompts. Code and data: https://github.com/Nicous20/EgoHandICL

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 60 of its 69 references that are in the map. First posted on arXiv 27 Jan 2026.

Builds on

60 of 69 references.

References · 60

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  8. 2017Decoupled Weight Decay Regularizationcited by 1,831
  9. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  10. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  11. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  12. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 490
38 more
  1. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  2. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 318
  3. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 312
  4. 2023Reconstructing Hands in 3D with Transformerscited by 306
  5. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  6. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  7. 2022Visual Prompting via Image Inpaintingcited by 250
  8. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  9. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 245
  10. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 237
  11. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  12. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  13. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
  14. 2023What Makes Good Examples for Visual In-Context Learning?cited by 150
  15. 2020Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wildcited by 146
  16. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 124
  17. 2019Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Renderingcited by 115
  18. 2018Hand Pose Estimation via Latent 2.5D Heatmap Regressioncited by 111
  19. 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 96
  20. 2025EgoLife: Towards Egocentric Life Assistantcited by 91
  21. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  22. 2025HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videoscited by 66
  23. 2021Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registrationcited by 59
  24. 2016Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Inputcited by 56
  25. 2023Visual In-Context Promptingcited by 52
  26. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  27. 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
  28. 2023Explore In-Context Learning for 3D Point Cloud Understandingcited by 40
  29. 2024In-context learning enables multimodal large language models to classify cancer pathology imagescited by 38
  30. 2024VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learningcited by 36
  31. 20233D Hand Pose Estimation in Everyday Egocentric Imagescited by 34
  32. 2019Single Image 3D Hand Reconstruction with Mesh Convolutionscited by 32
  33. 2023A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Imagecited by 32
  34. 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recoverycited by 31
  35. 2016Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNscited by 29
  36. 2023Sampling is Matter: Point-guided 3D Human Mesh Reconstructioncited by 24
  37. 20143D Hand Pose Detection in Egocentric RGB-D Imagescited by 17
  38. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Robot Learning from Human Videos: A Surveycited by 5
  2. 2026EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentationcited by 3
  3. 2026CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ESTHER: Egocentric Stereo Hand Estimation and Reconstruction in the Wild
  2. 2026Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting
  3. 2026EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting
  4. 2026ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery
  5. 2024HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision
  6. 2026Vision-Language Models for Egocentric Video: From Hand-Object Interaction to Embodied AI
  7. 2026EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos
  8. 2025MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation