HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos

We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (3.7M+ images) of recordings that feature 19 subjects interacting with 33 diverse rigid objects. In addition to simple pickup, observe, and put-down actions, the subjec...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 7061 - 7071
Hlavní autoři: Banerjee, Prithviraj, Shkodrani, Sindi, Moulon, Pierre, Hampali, Shreyas, Han, Shangchen, Zhang, Fan, Zhang, Linguang, Fountain, Jade, Miller, Edward, Basol, Selen, Newcombe, Richard, Wang, Robert, Engel, Jakob Julian, Hodan, Tomas
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 10.06.2025
Témata:
3d lifting of in-hand objects
6dof object pose
aria
Artificial intelligence
augmented reality
Benchmark testing
contextual ai
dataset
hand tracking
hand-object interaction
Hands
Headphones
in-hand object segmentation
Object tracking
Pose estimation
smart glasses
Synchronization
Three-dimensional displays
Training
Videos
virtual reality
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (3.7M+ images) of recordings that feature 19 subjects interacting with 33 diverse rigid objects. In addition to simple pickup, observe, and put-down actions, the subjects perform actions typical for a kitchen, office, and living room environment. The recordings include multiple synchronized data streams containing egocentric multi-view RGB/monochrome images, eye gaze signal, scene point clouds, and 3D poses of cameras, hands, and objects. The dataset is recorded with two headsets from Meta: Project Aria, which is a research prototype of AI glasses, and Quest 3, a virtual-reality headset that has shipped millions of units. Ground-truth poses were obtained by a 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. In our experiments, we demonstrate the effectiveness of multi-view egocentric data for three popular tasks: 3D hand tracking, model-based 6DoF object pose estimation, and 3D lifting of unknown in-hand objects. The evaluated multi-view methods, whose benchmarking is uniquely enabled by HOT3D, significantly outperform their single-view counterparts.
ISSN:1063-6919
DOI:10.1109/CVPR52734.2025.00662