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

arXiv: https://arxiv.org/abs/2510.23928 · HTML: https://mlsanity.com/paper/2510.23928/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals](https://mlsanity.com/paper/1905.02082/) (2019)
- [Adaptive Keyframe Sampling for Long Video Understanding](https://mlsanity.com/paper/2502.21271/) (2025)
- [RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement](https://mlsanity.com/paper/2505.24705/) (2025)
- [Event Cameras Meet SPADs for High-Speed, Low-Bandwidth Imaging](https://mlsanity.com/paper/2404.11511/) (2024)

## Built on by (most cited first, 4 of 4)

- [ANTIC: Adaptive Neural Temporal In-situ Compressor](https://mlsanity.com/paper/2604.09543/) (2026)
- [Diversity-aware View Partitioning for Scalable VGGT](https://mlsanity.com/paper/2607.01885/) (2026)
- [VCS-SLAM: Geometry-Validated Semantic Evidence Fusion for 3D Gaussian SLAM](https://mlsanity.com/paper/2606.29494/) (2026)
- [Sharper Frames, Worse Rooms: Viewpoint Coverage Dominates Image Quality in Feed-Forward 3D Reconstruction](https://mlsanity.com/paper/2610.15854/) (2026)

## Abstract (arXiv)

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.