Adaptive Keyframe Selection for Scalable 3D Scene Reconstruction in Dynamic Environments

TL;DR

This paper introduces an adaptive keyframe selection method that dynamically chooses the most informative frames for 3D scene reconstruction in dynamic environments, improving quality and scalability.

Contribution

It presents a novel adaptive keyframe selection approach combining error-based and momentum-based modules, enhancing real-time 3D reconstruction in complex scenes.

Findings

Significant improvement over static keyframe strategies

Consistent quality gains across two state-of-the-art networks

Effective ablation of individual components

Abstract

In this paper, we propose an adaptive keyframe selection method for improved 3D scene reconstruction in dynamic environments. The proposed method integrates two complementary modules: an error-based selection module utilizing photometric and structural similarity (SSIM) errors, and a momentum-based update module that dynamically adjusts keyframe selection thresholds according to scene motion dynamics. By dynamically curating the most informative frames, our approach addresses a key data bottleneck in real-time perception. This allows for the creation of high-quality 3D world representations from a compressed data stream, a critical step towards scalable robot learning and deployment in complex, dynamic environments. Experimental results demonstrate significant improvements over traditional static keyframe selection strategies, such as fixed temporal intervals or uniform frame skipping. These findings highlight a meaningful advancement toward adaptive perception systems that can dynamically respond to complex and evolving visual scenes. We evaluate our proposed adaptive keyframe selection module on two recent state-of-the-art 3D reconstruction networks, Spann3r and CUT3R, and observe consistent improvements in reconstruction quality across both frameworks. Furthermore, an extensive ablation study confirms the effectiveness of each individual component in our method, underlining their contribution to the overall performance gains.