paper-with-me

Papers

AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning

2026-07-09 · Iaroslav Kolomiets, Miguel Altamirano Cabrera, Artem Lykov, Jeffrin Sam, Dmitrii Iarchuk, Yara Mahmoud, Daniia Zinniatullina, Mikhail Konenkov, Dzmitry Tsetserukou arxiv

Human egocentric video is a scalable supervision source for humanoid policy learning, but current pipelines struggle with hand-object occlusion, oversimplified motion, or specialized capture hardware. We introduce AgenticFocus, a Mixed Reality synthesis pipeline that converts ordinary first-person-view human videos into robot-trainable demonstrations by restoring occluded object geometry, reconstructing full-hand motion, and retargeting it to a humanoid embodiment through camera-relative alignment and layered compositing. The resulting dataset pairs focused visual observations with synchronized robot actions and states. AgenticFocus achieves lower trajectory error and smoother wrist motion than cross-embodiment baselines, with SPARC scores of -5.18 versus -5.56 and -6.05.

📄 PDF Abstract BibTeX arXiv:2607.08857

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mutual Scene Synthesis for Mixed Reality Telepresence

2022-04-01 · Mohammad Keshavarzi, Michael Zollhoefer, Allen Y. Yang, Patrick Peluse 외

Remote telepresence via next-generation mixed reality platforms can provide higher levels of immersion for computer-mediated communications, allowing participants to engage in a wide spectrum of activities, previously no…

Mixed Reality

Multi-layer Visualization for Medical Mixed Reality

2017-09-26 · Séverine Habert, Ma Meng, Pascal Fallavollita, Nassir Navab

Medical Mixed Reality helps surgeons to contextualize intraoperative data with video of the surgical scene. Nonetheless, the surgical scene and anatomical target are often occluded by surgical instruments and surgeon han…

Mixed Reality

A Real-Time Diminished Reality Approach to Privacy in MR Collaboration

2025-08-21 · Christian Fane arxiv

Diminished reality (DR) refers to the digital removal of real-world objects by compositing background content in their place. This thesis presents a real-time, inpainting-based DR system designed to enable privacy contro…

Semantic SegmentationObject DetectionVideo Inpainting

LLMR: Real-time Prompting of Interactive Worlds using Large Language Models

2023-09-21 · Fernanda De La Torre, Cathy Mengying Fang, Han Huang, Andrzej Banburski-Fahey 외

We present Large Language Model for Mixed Reality (LLMR), a framework for the real-time creation and modification of interactive Mixed Reality experiences using LLMs. LLMR leverages novel strategies to tackle difficult c…

Language ModelingLanguage ModellingLarge Language ModelManagement+4

Point Cloud Registration of non-rigid objects in sparse 3D Scans with applications in Mixed Reality

2022-12-07 · Manorama Jha

Point Cloud Registration is the problem of aligning the corresponding points of two 3D point clouds referring to the same object. The challenges include dealing with noise and partial match of real-world 3D scans. For no…

Mixed RealityObjectPoint Cloud Registration