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

2026-04-26

AI Summary

This study addresses the degradation in 3D reconstruction quality caused by severe camera motion and complex dynamic scenes in egocentric videos. It presents the first systematic evaluation of dynamic 3D Gaussian Splatting (3DGS) performance under both egocentric and exocentric viewpoints, leveraging paired videos from the EgoExo4D dataset for quantitative comparison. The analysis reveals that reconstruction quality in egocentric views is significantly inferior to that in exocentric views, primarily due to poor reconstruction of static content. These findings highlight the limitations of current methods in first-person scenarios and advocate for decoupled evaluation of static and dynamic regions, thereby providing a foundation for designing specialized 3D reconstruction approaches tailored to egocentric video.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Learning with Manifolds

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Large-scale security measurements

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.

Problem

• egocentric video
• 3D reconstruction
• dynamic scenes
• 3D Gaussian Splatting
• scene dynamics

Innovation

• Egocentric Reconstruction
• Dynamic 3D Gaussian Splatting
• Monocular Video
• Static-Dynamic Scene Analysis
• EgoExo4D