GOLF is a method that won the SHOW3D Interaction Field Estimation Challenge at HANDS@ECCV 2026. It predicts a 3D vector from each of 21 hand joints to the nearest point on a manipulated object using synchronized egocentric stereo views. The approach fuses dense global context, locally sampled hand/object evidence, and Plücker‑ray geometry, and employs a DINOv3 ViT‑H+/16 backbone with LoRA and trainable LayerNorm, achieving top scores on the hidden test set.
arXiv:2605.20992v4 Announce Type: replace Abstract: We ask whether everyday open-world monocular videos can be turned into reusable 4D interaction primitives: articulated hand motion, object shape wi...
ESTHER is an end‑to‑end model for egocentric stereo hand reconstruction that integrates stereo geometry, temporal reasoning, and a suitable output representation for wearable cameras. It is trained on pseudo‑labels from a calibrated pipeline and introduces the ESTHER3D benchmark, which pairs a large in‑the‑wild training set with a motion‑capture test set of true metric ground truth. Experiments demonstrate state‑of‑the‑art accuracy, strong generalization, and robustness to missing views, dropped frames, and extreme lighting or motion blur, while preserving metric scale even when reduced to a single monocular view.
arXiv:2610.01210v1 Announce Type: new Abstract: Egocentric video has become a primary source of supervision for embodied models, and its value rests on recovering hand motion in world coordinates, wh...
EgoHSI3R is a unified feed‑forward framework that reconstructs 4D hand‑scene interactions from egocentric monocular video. It jointly estimates camera motion, dense scene geometry, world‑space bilateral MANO hands, and per‑vertex hand contact by maintaining a recurrent scene representation and using hand‑centric prompts and MANO vertex queries. The method achieves the lowest world‑space hand joint error on ARCTIC while offering faster inference than existing pipelines.
arXiv:2608. 20093v1 Announce Type: new Abstract: In this work, we present HandMvNet, one of the first real-time method designed to estimate 3D hand motion and shape from multi-view camera images.
SituHOI is a large‑scale RGB‑D dataset that captures full‑body human‑object interactions in 16 indoor rooms, comprising 18,429 annotated clips and about 86 hours of activity. The dataset pairs moving‑camera recordings with static scene scans, object geometry, language descriptions, and estimated human and object trajectories, all registered in a shared floor‑aligned frame via a pipeline that integrates camera localization, depth‑based alignment, human mesh recovery, and object tracking. The data enable the FlexHOI‑Bench benchmark for goal‑conditioned joint motion prediction, and a reference predictor, SharedHOI, demonstrates strong performance on world‑space accuracy and human‑object coordination. whyItMatters":"The dataset provides scalable, scene‑aligned supervision for modeling human‑object interaction, addressing a key limitation of existing datasets and enabling more accurate motion prediction benchmarks."
Fast and Accurate Hand Estimation (FAH) is a new family of monocular hand mesh estimators that directly predict 3D joints and surface points, then fit a mesh model such as MANO or MHR-Hand. Built on SAM 3D Body’s hand branch, FAH uses fine‑tuning and feature distillation to produce accurate 2D and 3D keypoints, optional anatomical part segmentation, and contact estimation without requiring object geometry. The models achieve state‑of‑the‑art image‑space alignment, hand geometry, contact estimation, and world‑space tracking, running at 65 fps (ViT‑L) or 125 fps (ViT‑S) on an RTX 4070 Ti SUPER.
arXiv:2610.29936v1 Announce Type: new Abstract: Recovering metric world-space hand motion from egocentric video supports understanding human interactions and transferring them to embodied agents. Thr...
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.
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...
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.
HOPE is a framework that estimates hand‑object pressure from monocular videos by treating pressure estimation as a hand‑centric video prediction task. It lifts diverse pressure and contact annotations into a shared hand vertex space and uses a vertex‑anchored video transformer with a contact‑gated pressure head to predict temporally evolving per‑vertex normal pressure and contact. Experiments on multiple datasets show that HOPE generalizes to bare‑hand egocentric and in‑the‑wild videos, outperforming baselines that rely only on contact or planar pressure.