# NextBestPath: Efficient 3D Mapping of Unseen Environments arXiv: https://arxiv.org/abs/2502.05378 ยท HTML: https://mlsanity.com/paper/2502.05378/ ## Key facts - Cited by 13 papers in the map (data through 14 Oct 2026). - Builds on 44 of its 54 references that are in the map. - First posted on arXiv 7 Feb 2025. ## Builds on (most cited first, 30 of 44) - [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013) - [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017) - [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015) - [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018) - [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017) - [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017) - [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019) - [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018) - [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019) - [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020) - [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018) - [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021) - [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018) - [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023) - [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019) - [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019) - [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023) - [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020) - [RoboTHOR: An Open Simulation-to-Real Embodied AI Platform](https://mlsanity.com/paper/2004.06799/) (2020) - [ActiveNeRF: Learning where to See with Uncertainty Estimation](https://mlsanity.com/paper/2209.08546/) (2022) - [Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale](https://mlsanity.com/paper/2204.03514/) (2022) - [Occupancy Anticipation for Efficient Exploration and Navigation](https://mlsanity.com/paper/2008.09285/) (2020) - [Boltzmann Exploration Done Right](https://mlsanity.com/paper/1705.10257/) (2017) - [A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers](https://mlsanity.com/paper/2207.00254/) (2022) - [NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representations](https://mlsanity.com/paper/2207.10985/) (2022) - [Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields](https://mlsanity.com/paper/2209.08409/) (2022) - [Incremental Adversarial Domain Adaptation for Continually Changing Environments](https://mlsanity.com/paper/1712.07436/) (2017) - [FUEL: Fast UAV Exploration using Incremental Frontier Structure and Hierarchical Planning](https://mlsanity.com/paper/2010.11561/) (2020) - [From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data](https://mlsanity.com/paper/2205.03147/) (2022) - [GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction](https://mlsanity.com/paper/2402.16174/) (2024) ## Built on by (most cited first, 13 of 13) - [GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes](https://mlsanity.com/paper/2505.20294/) (2025) - [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) - [AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance](https://mlsanity.com/paper/2512.05131/) (2025) - [ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction](https://mlsanity.com/paper/2601.06997/) (2026) - [Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction](https://mlsanity.com/paper/2508.01014/) (2025) - [Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labeling Budget](https://mlsanity.com/paper/2509.16684/) (2025) - [Paparazzo: Active Mapping of Moving 3D Objects](https://mlsanity.com/paper/2604.19556/) (2026) - [Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration](https://mlsanity.com/paper/2605.22814/) (2026) - [DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2608.01178/) (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) - [Multi-Scale Semantic Mapping in Urban Environments via Observation Calibration and Policy Dependence Regularization](https://mlsanity.com/paper/2609.34833/) (2026) ## Abstract (arXiv) This work addresses the problem of active 3D mapping, where an agent must find an efficient trajectory to exhaustively reconstruct a new scene. Previous approaches mainly predict the next best view near the agent's location, which is prone to getting stuck in local areas. Additionally, existing indoor datasets are insufficient due to limited geometric complexity and inaccurate ground truth meshes. To overcome these limitations, we introduce a novel dataset AiMDoom with a map generator for the Doom video game, enabling to better benchmark active 3D mapping in diverse indoor environments. Moreover, we propose a new method we call next-best-path (NBP), which predicts long-term goals rather than focusing solely on short-sighted views. The model jointly predicts accumulated surface coverage gains for long-term goals and obstacle maps, allowing it to efficiently plan optimal paths with a unified model. By leveraging online data collection, data augmentation and curriculum learning, NBP significantly outperforms state-of-the-art methods on both the existing MP3D dataset and our AiMDoom dataset, achieving more efficient mapping in indoor environments of varying complexity.