Reliable Multi-view 3D Reconstruction for `Just-in-time' Edge Environments

2025-08-20

AI Summary

To address quality degradation in multi-view 3D reconstruction under dynamic edge environments—caused by spatiotemporally correlated camera failures—this paper proposes a robust resource management framework inspired by modern portfolio theory. Camera selection is formulated as a risk–return optimization problem, explicitly modeling failure correlations and enabling interference-resilient configuration; a genetic algorithm is employed to solve for the optimal subset. Evaluations on public and custom 3D datasets demonstrate significant improvements: +28.6% reconstruction success rate and 41.3% reduction in PSNR variance, alongside rapid convergence and compatibility with edge-device resource constraints. The key contribution is the first application of portfolio-theoretic principles to multi-view reconstruction scheduling, yielding a deployable, reliability-aware solution tailored for time-critical scenarios such as emergency response.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Learning & Optimization for CV
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

Multi-view 3D reconstruction applications are revolutionizing critical use cases that require rapid situational-awareness, such as emergency response, tactical scenarios, and public safety. In many cases, their near-real-time latency requirements and ad-hoc needs for compute resources necessitate adoption of `Just-in-time' edge environments where the system is set up on the fly to support the applications during the mission lifetime. However, reliability issues can arise from the inherent dynamism and operational adversities of such edge environments, resulting in spatiotemporally correlated disruptions that impact the camera operations, which can lead to sustained degradation of reconstruction quality. In this paper, we propose a novel portfolio theory inspired edge resource management strategy for reliable multi-view 3D reconstruction against possible system disruptions. Our proposed methodology can guarantee reconstruction quality satisfaction even when the cameras are prone to spatiotemporally correlated disruptions. The portfolio theoretic optimization problem is solved using a genetic algorithm that converges quickly for realistic system settings. Using publicly available and customized 3D datasets, we demonstrate the proposed camera selection strategy's benefits in guaranteeing reliable 3D reconstruction against traditional baseline strategies, under spatiotemporal disruptions.

Problem

• Ensuring reliable multi-view 3D reconstruction in dynamic edge environments
• Mitigating spatiotemporally correlated disruptions affecting camera operations
• Maintaining reconstruction quality under adverse operational conditions

Innovation

• Portfolio theory inspired edge resource management
• Genetic algorithm for optimization problem solving
• Camera selection strategy against spatiotemporal disruptions