# NARUTO: Neural Active Reconstruction from Uncertain Target Observations

arXiv: https://arxiv.org/abs/2402.18771 · HTML: https://mlsanity.com/paper/2402.18771/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 88 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 30 of 56)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM](https://mlsanity.com/paper/2304.14377/) (2023)
- [NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM](https://mlsanity.com/paper/2302.03594/) (2023)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018)
- [NeRF--: Neural Radiance Fields Without Known Camera Parameters](https://mlsanity.com/paper/2102.07064/) (2021)

## Built on by (most cited first, 28 of 28)

- [ActiveGS: Active Scene Reconstruction Using Gaussian Splatting](https://mlsanity.com/paper/2412.17769/) (2024)
- [ActiveSplat: High-Fidelity Scene Reconstruction through Active Gaussian Splatting](https://mlsanity.com/paper/2410.21955/) (2024)
- [ActiveGAMER: Active GAussian Mapping through Efficient Rendering](https://mlsanity.com/paper/2501.06897/) (2025)
- [GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction](https://mlsanity.com/paper/2504.21067/) (2025)
- [NextBestPath: Efficient 3D Mapping of Unseen Environments](https://mlsanity.com/paper/2502.05378/) (2025)
- [GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes](https://mlsanity.com/paper/2505.20294/) (2025)
- [Multimodal LLM Guided Exploration and Active Mapping using Fisher Information](https://mlsanity.com/paper/2410.17422/) (2024)
- [Active Neural Mapping at Scale](https://mlsanity.com/paper/2409.20276/) (2024)
- [Understanding while Exploring: Semantics-driven Active Mapping](https://mlsanity.com/paper/2506.00225/) (2025)
- [MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping](https://mlsanity.com/paper/2603.22650/) (2026)
- [Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field](https://mlsanity.com/paper/2605.30342/) (2026)
- [Multimodal 3D Fusion and In-Situ Learning for Spatially Aware AI](https://mlsanity.com/paper/2410.04652/) (2024)
- [AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance](https://mlsanity.com/paper/2512.05131/) (2025)
- [Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction](https://mlsanity.com/paper/2412.00242/) (2024)
- [SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection](https://mlsanity.com/paper/2601.03024/) (2026)
- [Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction](https://mlsanity.com/paper/2603.06852/) (2026)
- [Informative Object-centric Next Best View for Object-aware 3D Gaussian Splatting in Cluttered Scenes](https://mlsanity.com/paper/2602.08266/) (2026)
- [3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models](https://mlsanity.com/paper/2609.06535/) (2026)
- [Surface-Based Visibility-Guided Uncertainty for Continuous Active 3D Neural Reconstruction](https://mlsanity.com/paper/2405.02568/) (2024)
- [Online 3D Gaussian Splatting Modeling with Novel View Selection](https://mlsanity.com/paper/2508.14014/) (2025)
- [HERE: Hierarchical Active Exploration of Radiance Field with Epistemic Uncertainty Minimization](https://mlsanity.com/paper/2601.07242/) (2026)
- [Paparazzo: Active Mapping of Moving 3D Objects](https://mlsanity.com/paper/2604.19556/) (2026)
- [ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo](https://mlsanity.com/paper/2606.01367/) (2026)
- [TRACE: Ergodic Trajectory Optimization for Active Scene Reconstruction](https://mlsanity.com/paper/2608.02304/) (2026)
- [Diagnosing and Dynamically Filtering Occupancy World Models for Active Mapping](https://mlsanity.com/paper/2609.06820/) (2026)
- [Rethinking Learned Occupancy in Autonomous Active Mapping with Observation-Gated Filtering](https://mlsanity.com/paper/2609.09069/) (2026)
- [Matisse: Evidence-Space Reasoning for Active 3D Reconstruction](https://mlsanity.com/paper/2609.38746/) (2026)
- [VCURF: Virtual Camera-based Uncertainty of Radiance Fields](https://mlsanity.com/paper/2610.04076/) (2026)

## Abstract (arXiv)

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.