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

• URL: http://arxiv.org/abs/2601.19850v1
• Date: Tue, 27 Jan 2026 17:58:12 GMT
• Title: EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning
• Authors: Binzhu Xie, Shi Qiu, Sicheng Zhang, Yinqiao Wang, Hao Xu, Muzammal Naseer, Chi-Wing Fu, Pheng-Ann Heng,
• Abstract summary: We present EgoHandICL, the first in-context learning framework for 3D hand reconstruction.<n>EgoHandICL improves semantic alignment, visual consistency, and robustness under challenging egocentric conditions.<n> Experiments on ARCTIC and EgoExo4D show consistent gains over state-of-the-art methods.
• Score: 96.36520341018267
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention [58.05340906967343]
  Egocentric Referring Video Object (Ego-RVOS) aims to segment the specific object actively involved in a human action, as described by a language query, within first-person videos.<n>Existing methods often struggle, learning spurious correlations from skewed object-action pairings in datasets.<n>We introduce Causal-REferring (CERES), a plug-in causal framework that adapts strong, pre-trained RVOSs to the egocentric domain.
  arXiv  Detail & Related papers  (2025-12-30T16:22:14Z)
• EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations [4.252119151012245]
  We introduce EgoWorld, a novel framework that reconstructs an egocentric view from rich exocentric observations.<n>Our approach reconstructs a point cloud from estimated exocentric depth maps, reprojects it into the egocentric perspective, and then applies diffusion-based inpainting to produce dense, semantically coherent egocentric images.<n>EgoWorld achieves state-of-the-art performance and demonstrates robust generalization to new objects, actions, scenes, and subjects.
  arXiv  Detail & Related papers  (2025-06-22T04:21:48Z)
• Egocentric Human-Object Interaction Detection: A New Benchmark and Method [15.271558280695631]
  Egocentric human-object interaction (Ego-HOI) detection is crucial for intelligent agents to understand and assist human activities from a first-person perspective.<n>We introduce the real-world Ego-HOI detection task and Ego-HOIBench, a new dataset with over 27K egocentric images and explicit, fine-grained hand-verb-object triplet annotations.<n>We propose Hand Geometry and Interactivity Refinement (HGIR), a lightweight, plug-and-play scheme that leverages hand pose and geometric cues to enhance interaction representations.
  arXiv  Detail & Related papers  (2025-06-17T05:03:42Z)
• MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation [28.75149480374178]
  MEgoHand is a framework that synthesizes physically plausible hand-object interactions from egocentric RGB, text, and initial hand pose.<n>It achieves substantial reductions in wrist translation error and joint rotation error, highlighting its capacity to accurately model fine-grained hand joint structures.
  arXiv  Detail & Related papers  (2025-05-22T12:37:47Z)
• Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects [89.95728475983263]
  holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation. We design the HANDS23 challenge based on the AssemblyHands and ARCTIC datasets with carefully designed training and testing splits. Based on the results of the top submitted methods and more recent baselines on the leaderboards, we perform a thorough analysis on 3D hand(-object) reconstruction tasks.
  arXiv  Detail & Related papers  (2024-03-25T05:12:21Z)
• HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video [70.11702620562889]
  HOLD -- the first category-agnostic method that reconstructs an articulated hand and object jointly from a monocular interaction video. We develop a compositional articulated implicit model that can disentangled 3D hand and object from 2D images. Our method does not rely on 3D hand-object annotations while outperforming fully-supervised baselines in both in-the-lab and challenging in-the-wild settings.
  arXiv  Detail & Related papers  (2023-11-30T10:50:35Z)
• Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution [49.10497573378427]
  Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality. Our algorithm is optimisation to object models, and it learns the physical rules governing hand-object interaction. Experiments using four widely-used benchmarks show that our framework achieves beyond state-of-the-art accuracy in 3D pose estimation, as well as recovers dense 3D hand and object shapes.
  arXiv  Detail & Related papers  (2022-04-27T17:00:54Z)
• Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion [78.98074380040838]
  We propose to consider hand and object jointly in feature space and explore the reciprocity of the two branches. We employ an auxiliary depth estimation module to augment the input RGB image with the estimated depth map. Our approach significantly outperforms existing approaches in terms of the reconstruction accuracy of objects.
  arXiv  Detail & Related papers  (2020-06-28T09:50:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.