DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos
This addresses scene comprehension for applications like robotics and augmented reality, though it appears incremental as it builds on existing feature field approaches.
The paper tackles environment understanding in egocentric videos by introducing DIV-FF, a framework that decomposes scenes into components and integrates image and video features, resulting in outperforming state-of-the-art methods in dynamic scenarios.
Environment understanding in egocentric videos is an important step for applications like robotics, augmented reality and assistive technologies. These videos are characterized by dynamic interactions and a strong dependence on the wearer engagement with the environment. Traditional approaches often focus on isolated clips or fail to integrate rich semantic and geometric information, limiting scene comprehension. We introduce Dynamic Image-Video Feature Fields (DIV FF), a framework that decomposes the egocentric scene into persistent, dynamic, and actor based components while integrating both image and video language features. Our model enables detailed segmentation, captures affordances, understands the surroundings and maintains consistent understanding over time. DIV-FF outperforms state-of-the-art methods, particularly in dynamically evolving scenarios, demonstrating its potential to advance long term, spatio temporal scene understanding.