Active3D: Active High-Fidelity 3D Reconstruction via Hierarchical Uncertainty Quantification

TL;DR

Active3D introduces a hierarchical uncertainty-based active exploration framework that combines neural fields and Gaussian primitives for high-fidelity 3D reconstruction, optimizing view selection for improved accuracy and completeness.

Contribution

The paper presents a novel hybrid implicit-explicit representation and a hierarchical uncertainty quantification method for active 3D reconstruction, enabling more efficient and accurate exploration.

Findings

Achieves state-of-the-art reconstruction accuracy and completeness.

Demonstrates effective active exploration in challenging benchmarks.

Provides a risk-sensitive planning strategy for safe and efficient view selection.

Abstract

In this paper, we present an active exploration framework for high-fidelity 3D reconstruction that incrementally builds a multi-level uncertainty space and selects next-best-views through an uncertainty-driven motion planner. We introduce a hybrid implicit-explicit representation that fuses neural fields with Gaussian primitives to jointly capture global structural priors and locally observed details. Based on this hybrid state, we derive a hierarchical uncertainty volume that quantifies both implicit global structure quality and explicit local surface confidence. To focus optimization on the most informative regions, we propose an uncertainty-driven keyframe selection strategy that anchors high-entropy viewpoints as sparse attention nodes, coupled with a viewpoint-space sliding window for uncertainty-aware local refinement. The planning module formulates next-best-view selection as an Expected Hybrid Information Gain problem and incorporates a risk-sensitive path planner to ensure efficient and safe exploration. Extensive experiments on challenging benchmarks demonstrate that our approach consistently achieves state-of-the-art accuracy, completeness, and rendering quality, highlighting its effectiveness for real-world active reconstruction and robotic perception tasks.