NARUTO: Neural Active Reconstruction from Uncertain Target Observations
This addresses the challenge of efficient and accurate 3D reconstruction for robotics and computer vision applications, representing an incremental improvement over existing neural SLAM systems.
The paper tackles the problem of active 3D reconstruction by introducing NARUTO, a system that combines neural representations with uncertainty learning to autonomously explore and reconstruct environments with high completeness and fidelity, achieving state-of-the-art results on benchmarks like Replica and MP3D.
We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction. Our approach leverages a multi-resolution hash-grid as the mapping backbone, chosen for its exceptional convergence speed and capacity to capture high-frequency local features.The centerpiece of our work is the incorporation of an uncertainty learning module that dynamically quantifies reconstruction uncertainty while actively reconstructing the environment. By harnessing learned uncertainty, we propose a novel uncertainty aggregation strategy for goal searching and efficient path planning. Our system autonomously explores by targeting uncertain observations and reconstructs environments with remarkable completeness and fidelity. We also demonstrate the utility of this uncertainty-aware approach by enhancing SOTA neural SLAM systems through an active ray sampling strategy. Extensive evaluations of NARUTO in various environments, using an indoor scene simulator, confirm its superior performance and state-of-the-art status in active reconstruction, as evidenced by its impressive results on benchmark datasets like Replica and MP3D.