EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views
This addresses a fundamental problem in human-centric perception for applications like AR/VR and embodied AI, but it is incremental as it builds on existing methods by adapting them to the egocentric view.
The paper tackles the problem of capturing 3D human-object interaction regions from egocentric views, which is ambiguous due to incomplete observations, by proposing EgoChoir to harmonize visual appearance, head motion, and 3D objects to jointly infer 3D human contact and object affordance. The method demonstrates effectiveness and superiority in experiments on annotated datasets like Ego-Exo4D and GIMO.
Understanding egocentric human-object interaction (HOI) is a fundamental aspect of human-centric perception, facilitating applications like AR/VR and embodied AI. For the egocentric HOI, in addition to perceiving semantics e.g., ''what'' interaction is occurring, capturing ''where'' the interaction specifically manifests in 3D space is also crucial, which links the perception and operation. Existing methods primarily leverage observations of HOI to capture interaction regions from an exocentric view. However, incomplete observations of interacting parties in the egocentric view introduce ambiguity between visual observations and interaction contents, impairing their efficacy. From the egocentric view, humans integrate the visual cortex, cerebellum, and brain to internalize their intentions and interaction concepts of objects, allowing for the pre-formulation of interactions and making behaviors even when interaction regions are out of sight. In light of this, we propose harmonizing the visual appearance, head motion, and 3D object to excavate the object interaction concept and subject intention, jointly inferring 3D human contact and object affordance from egocentric videos. To achieve this, we present EgoChoir, which links object structures with interaction contexts inherent in appearance and head motion to reveal object affordance, further utilizing it to model human contact. Additionally, a gradient modulation is employed to adopt appropriate clues for capturing interaction regions across various egocentric scenarios. Moreover, 3D contact and affordance are annotated for egocentric videos collected from Ego-Exo4D and GIMO to support the task. Extensive experiments on them demonstrate the effectiveness and superiority of EgoChoir.