EgoPolice introduces a 185-hour annotated police body-worn camera benchmark showing state-of-the-art video models fail on high-stakes actions due to motion, occlusion, and low inter-class visual separability.
Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (more than 3.7M images) of multi-view RGB/monochrome image streams showing 19 subjects interacting with 33 diverse rigid objects, multi-modal signals such as eye gaze or scene point clouds, as well as comprehensive ground truth annotations including 3D poses of objects, hands, and cameras, and 3D models of hands and objects. In addition to simple pick-up/observe/put-down actions, HOT3D contains scenarios resembling typical actions in a kitchen, office, and living room environment. The dataset is recorded by two head-mounted devices from Meta: Project Aria, a research prototype of light-weight AR/AI glasses, and Quest 3, a production VR headset sold in millions of units. Ground-truth poses were obtained by a professional motion-capture system using small optical markers attached to hands and objects. Hand annotations are provided in the UmeTrack and MANO formats and objects are represented by 3D meshes with PBR materials obtained by an in-house scanner. We aim to accelerate research on egocentric hand-object interaction by making the HOT3D dataset publicly available and by co-organizing public challenges on the dataset at ECCV 2024. The dataset can be downloaded from the project website: https://facebookresearch.github.io/hot3d/.
citation-role summary
background 2
dataset 2
citation-polarity summary
representative citing papers
StableHand introduces a quality-aware flow matching framework conditioned on predicted four-channel per-frame hand observation quality to estimate dual-hand world-space motion from egocentric video, achieving SOTA results with 20-25% W-MPJPE reduction on HOT3D and ARCTIC benchmarks.
EventTrack6D tracks 6D poses of unseen objects from event cameras by reconstructing dense intensity and depth cues between frames, generalizing from synthetic training to real data at high speed.
A 1,362-hour multi-source egocentric human dataset and multi-lab study show co-training improves robot manipulation, but only when aligned human–robot data anchors transfer from diverse human data.
EgoKit is a new toolkit and accessory set that unifies egocentric video collection with wrist views across heterogeneous consumer devices using a consistent interface and log format.
An open-vocabulary pipeline anchors functional edges in 2D visual evidence, associates nodes with multi-cue matching, and optimizes edges over time to recover hierarchical object-carrier-unit graphs that beat prior methods on extended indoor benchmarks.
EgoForce recovers absolute camera-space 3D hand pose from monocular egocentric images using forearm guidance, a unified arm-hand transformer, and a closed-form ray-space solver that handles fisheye, perspective, and wide-FOV cameras.
DexSynRefine couples HOI motion manifold flow primitives with task-space residual RL and proprioceptive adaptation to convert human-object interaction data into executable dexterous robot motions, reporting 50-70 point real-world success rate gains over kinematic retargeting on five tasks.
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
EgoVLA pretrains VLA models on egocentric human videos, retargets predicted actions to robots via IK, and fine-tunes on few robot demos to improve bimanual manipulation performance on a new simulation benchmark.
HumanEgo reports 92.5% average success on four real robot tasks using only 15-30 minutes of human video per task and zero robot data, with zero-shot transfer to new robots and cameras.
VGGT-Ω improves feed-forward reconstruction accuracy and efficiency by architectural simplifications, register-based attention, and training on much larger supervised and unlabeled video data.
citing papers explorer
-
EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage
EgoPolice introduces a 185-hour annotated police body-worn camera benchmark showing state-of-the-art video models fail on high-stakes actions due to motion, occlusion, and low inter-class visual separability.
-
StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video
StableHand introduces a quality-aware flow matching framework conditioned on predicted four-channel per-frame hand observation quality to estimate dual-hand world-space motion from egocentric video, achieving SOTA results with 20-25% W-MPJPE reduction on HOT3D and ARCTIC benchmarks.
-
Event6D: Event-based Novel Object 6D Pose Tracking
EventTrack6D tracks 6D poses of unseen objects from event cameras by reconstructing dense intensity and depth cues between frames, generalizing from synthetic training to real data at high speed.
-
EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
A 1,362-hour multi-source egocentric human dataset and multi-lab study show co-training improves robot manipulation, but only when aligned human–robot data anchors transfer from diverse human data.
-
EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices
EgoKit is a new toolkit and accessory set that unifies egocentric video collection with wrist views across heterogeneous consumer devices using a consistent interface and log format.
-
Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces
An open-vocabulary pipeline anchors functional edges in 2D visual evidence, associates nodes with multi-cue matching, and optimizes edges over time to recover hierarchical object-carrier-unit graphs that beat prior methods on extended indoor benchmarks.
-
EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera
EgoForce recovers absolute camera-space 3D hand pose from monocular egocentric images using forearm guidance, a unified arm-hand transformer, and a closed-form ray-space solver that handles fisheye, perspective, and wide-FOV cameras.
-
DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions
DexSynRefine couples HOI motion manifold flow primitives with task-space residual RL and proprioceptive adaptation to convert human-object interaction data into executable dexterous robot motions, reporting 50-70 point real-world success rate gains over kinematic retargeting on five tasks.
-
HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
-
EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
EgoVLA pretrains VLA models on egocentric human videos, retargets predicted actions to robots via IK, and fine-tunes on few robot demos to improve bimanual manipulation performance on a new simulation benchmark.
-
HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos
HumanEgo reports 92.5% average success on four real robot tasks using only 15-30 minutes of human video per task and zero robot data, with zero-shot transfer to new robots and cameras.
-
VGGT-$\Omega$
VGGT-Ω improves feed-forward reconstruction accuracy and efficiency by architectural simplifications, register-based attention, and training on much larger supervised and unlabeled video data.