arXiv:2608.20308v2 Announce Type: replace Abstract: Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe ob...
arXiv:2609.38615v1 Announce Type: cross Abstract: Egocentric videos of human manipulation provide valuable visual experience for embodied intelligence, yet collecting such data at scale is costly. Ex...
arXiv:2608. 20308v1 Announce Type: new Abstract: Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object occlusion and frequent out-of-sight gaps.
MINT is a foundation model that directly predicts world-space two-hand trajectories from egocentric RGB video, jointly estimating camera motion, hand states, and hand presence in a single spatiotemporal representation. It uses an open-source labeling pipeline, EGOPIPELINE, to generate large-scale pseudo-labels for pretraining, followed by fine-tuning on a small set of high-quality joint annotations. The model outperforms existing multi-stage approaches in accuracy and speed, and generalizes zero‑shot to unseen egocentric datasets.
MEgoVista is an offline pipeline that converts a single unprepared egocentric video into metric two‑hand and head motion within a gravity‑aligned world frame. It uniquely reconstructs motion in environments beyond studio volumes, uses calibrated stereo for absolute scale, and evaluates its outputs against independent optical capture to audit accuracy. The system thus expands the settings where high‑fidelity hand‑motion labels can be generated from natural, head‑worn recordings.
arXiv:2604. 01001v2 Announce Type: replace-cross Abstract: We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation.
arXiv:2606. 02962v1 Announce Type: cross Abstract: Egocentric Natural Language Query (NLQ) grounding asks a model to localize, in a long first-person video, the temporal interval that answers a free-form text query.
EventEgoHands++ is a new framework for reconstructing 3D hand meshes from egocentric event-based cameras. It introduces a Hand Detector that provides instance-level bounding boxes and masks for left and right hands, and an Adaptive Attention module that uses these detections to model spatial relationships and interactions. The authors extend the synthetic N-HOT3D dataset and create EEH‑R, a large real-world event-based egocentric hand dataset with about 1 million annotated frames, and show that their method outperforms existing baselines on both synthetic and real data.
arXiv:2609.08636v1 Announce Type: cross Abstract: Egocentric 4D interaction forecasting aims to anticipate both where future interactions will occur in 3D and how the human body will move to realize...
arXiv:2608.22449v1 Announce Type: cross Abstract: Forecasting dexterous hand motions from egocentric observations is fundamental to intelligent interactive systems. Existing VLM-based methods typical...
TouchSight is a monocular egocentric vision framework that predicts dense full-hand contact forces from video. It uses 500 hours of pressure‑glove recordings and hand‑object interaction data, and introduces TwinTouch‑20H, a dataset of 20 hours of paired visual data where generative models render gloved recordings as bare‑hand observations while preserving tactile labels. The system outperforms prior methods on OakInk2, generalizes qualitatively to natural bare‑hand egocentric videos from unseen datasets, and improves consistently as glove supervision scales.
arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolvin...