HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video.
Zicong FanMaria ParelliMaria Eleni KadoglouMuhammed KocabasXu ChenMichael J. BlackOtmar HilligesPublished in: CoRR (2023)
Keyphrases
- multimedia objects
- visual data
- video images
- video sequences
- multimedia
- video streams
- video content
- video analysis
- multiple objects
- real time
- video data
- objects in video sequences
- multimedia data
- d scene
- dynamic scenes
- moving objects
- structure from motion
- space time
- semantic labels
- urban scenes
- three dimensional
- video objects
- scene understanding
- complex scenes
- video frames
- object model
- video clips
- data objects
- human activities
- spatial and temporal