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

翻译：在以自我为中心的视觉中，由于深度模糊性、自遮挡以及复杂的手-物交互作用，实现鲁棒的三维手部重建具有挑战性。现有方法通过扩大训练数据或添加辅助线索来缓解这些问题，但在未见过的场景中往往表现不佳。我们提出了EgoHandICL，这是首个用于三维手部重建的上下文学习框架，旨在提升在具有挑战性的以自我为中心条件下的语义对齐性、视觉一致性和鲁棒性。EgoHandICL引入了由视觉-语言模型引导的互补范例检索、一个为多模态上下文定制的ICL分词器，以及一个基于掩码自编码器的架构，该架构通过手部引导的几何与感知目标进行训练。在ARCTIC和EgoExo4D数据集上的实验表明，本方法相较于现有最先进方法取得了持续的性能提升。我们还展示了其在真实世界中的泛化能力，并通过将重建的手部作为视觉提示，提升了EgoVLM在手-物交互推理上的表现。代码与数据：https://github.com/Nicous20/EgoHandICL