Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction

TL;DR

This paper evaluates the performance of dynamic 3D Gaussian Splatting models on egocentric videos, revealing lower reconstruction quality mainly due to static content, and emphasizes the need for egocentric-specific solutions.

Contribution

It provides the first systematic evaluation of dynamic 3D Gaussian Splatting on egocentric videos, highlighting current limitations and guiding future egocentric-specific development.

Findings

Reconstruction quality is lower in egocentric views.

Static content reconstruction is the main cause of quality difference.

Separate evaluation of static and dynamic regions is valuable.

Abstract

Egocentric video provides a unique view into human perception and interaction, with growing relevance for augmented reality, robotics, and assistive technologies. However, rapid camera motion and complex scene dynamics pose major challenges for 3D reconstruction from this perspective. While 3D Gaussian Splatting (3DGS) has become a state-of-the-art method for efficient, high-quality novel view synthesis, variants, that focus on reconstructing dynamic scenes from monocular video are rarely evaluated on egocentric video. It remains unclear whether existing models generalize to this setting or if egocentric-specific solutions are needed. In this work, we evaluate dynamic monocular 3DGS models on egocentric and exocentric video using paired ego-exo recordings from the EgoExo4D dataset. We find that reconstruction quality is consistently lower in egocentric views. Analysis reveals that the difference in reconstruction quality, measured in peak signal-to-noise ratio, stems from the reconstruction of static, not dynamic, content. Our findings underscore current limitations and motivate the development of egocentric-specific approaches, while also highlighting the value of separately evaluating static and dynamic regions of a video.