الملخص
Egocentric video has become a primary source of supervision for embodied models, and its value rests on recovering hand motion in world coordinates, which camera motion and hand occlusion make difficult. Existing reconstruction pipelines typically separate hand and scene estimation, leave interaction attributes to separate task-specific models, and invoke several models per video, so no prior reconstruction model estimates these attributes and throughput becomes a practical constraint on large-scale annotation. We therefore introduce EgoFound3R, a unified end-to-end model that estimates world-space hand geometry in a metric scale shared with the scene, and predicts point-wise interaction attributes, including visibility, contact, and distance. The model integrates three designs: (i) structured hand prompts that transfer pretrained geometric priors to world-space hand reconstruction; (ii) an explicit hand representation that decodes hand geometry and interaction attributes; and (iii) a shared-parameter multi-rate design that lowers inference cost. Together, these designs predict hand geometry and point-wise attributes in one pass. On OakInk-v2, TACO, and HOI4D, EgoFound3R reduces the mean per-joint position error (MPJPE) by 43.2%, 22.4%, and 11.6% over previous methods and predicts point-wise contact and distance alongside the geometry in the same pass, while attaining approximately 6x higher throughput.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Fu, H., Shi, J., Wang, W., Zuo, B., & Zhao, B. (2026). EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes. https://omanscience.com/ar/articles/egofound3r-end-to-end-egocentric-hand-reconstruction-in-world-space-with-point-wise-interaction-attributes
MLA 9
Fu, Hongming, et al. "EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes." https://omanscience.com/ar/articles/egofound3r-end-to-end-egocentric-hand-reconstruction-in-world-space-with-point-wise-interaction-attributes.
شيكاغو (المؤلف–التاريخ)
Fu, Hongming, Jingcheng Shi, Wenjia Wang, Binhua Zuo, and Bo Zhao. 2026. "EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes." https://omanscience.com/ar/articles/egofound3r-end-to-end-egocentric-hand-reconstruction-in-world-space-with-point-wise-interaction-attributes.
هارفارد
Fu, H., Shi, J., Wang, W., Zuo, B. and Zhao, B. (2026) 'EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes', Available at: https://omanscience.com/ar/articles/egofound3r-end-to-end-egocentric-hand-reconstruction-in-world-space-with-point-wise-interaction-attributes.
فانكوفر
Fu H, Shi J, Wang W, Zuo B, Zhao B. EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes. https://omanscience.com/ar/articles/egofound3r-end-to-end-egocentric-hand-reconstruction-in-world-space-with-point-wise-interaction-attributes
IEEE
H. Fu, J. Shi, W. Wang, B. Zuo, and B. Zhao, "EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes," https://omanscience.com/ar/articles/egofound3r-end-to-end-egocentric-hand-reconstruction-in-world-space-with-point-wise-interaction-attributes.