mlsanityData to 14 Oct 2026

NextBestPath: Efficient 3D Mapping of Unseen Environments

arXiv 2502.05378 ↗First posted 7 Feb 2025cs.CV cs.ROcited by 13

Not on the map. Why?

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.

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

44 of 54 references.

References · 44

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  6. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  7. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  8. 2018Experience Replay for Continual Learningcited by 1,095
  9. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  10. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  11. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  12. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
32 more
  1. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 481
  2. 2023Gaussian Splatting SLAMcited by 415
  3. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 379
  4. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 362
  5. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  6. 2020Learning to Explore using Active Neural SLAMcited by 316
  7. 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 193
  8. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 127
  9. 2022Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scalecited by 117
  10. 2020Occupancy Anticipation for Efficient Exploration and Navigationcited by 106
  11. 2017Boltzmann Exploration Done Rightcited by 69
  12. 2022A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontierscited by 66
  13. 2022NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representationscited by 55
  14. 2022Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fieldscited by 54
  15. 2017Incremental Adversarial Domain Adaptation for Continually Changing Environmentscited by 52
  16. 2020FUEL: Fast UAV Exploration using Incremental Frontier Structure and Hierarchical Planningcited by 48
  17. 2022From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Datacited by 39
  18. 2024GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstructioncited by 39
  19. 2020Next-Best View Policy for 3D Reconstructioncited by 35
  20. 2022Uncertainty-driven Planner for Exploration and Navigationcited by 33
  21. 2023A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstructioncited by 32
  22. 2023Active Neural Mappingcited by 31
  23. 2021Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observationscited by 30
  24. 2022ActiveRMAP: Radiance Field for Active Mapping And Planningcited by 30
  25. 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observationscited by 28
  26. 2019Supervised Learning of the Next-Best-View for 3D Object Reconstructioncited by 24
  27. 2023MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervisioncited by 19
  28. 2022SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integrationcited by 17
  29. 2023Object Goal Navigation with Recursive Implicit Mapscited by 16
  30. 2022SEER: Safe Efficient Exploration for Aerial Robots using Learning to Predict Information Gaincited by 11
  31. 2023SO-NeRF: Active View Planning for NeRF using Surrogate Objectivescited by 5
  32. 2023Heuristic-based Incremental Probabilistic Roadmap for Efficient UAV Exploration in Dynamic Environmentscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 8.

13 papers.

Sort:

By area:

  1. 2025GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenescited by 11
  2. 2025Understanding while Exploring: Semantics-driven Active Mappingcited by 5
  3. 2026MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mappingcited by 5
  4. 2025AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidancecited by 4
  5. 2026ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstructioncited by 2
  6. 2025Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstructioncited by 1
  7. 2025Active View Selection for Scene-level Multi-view Crowd Counting and Localization with Limited Labeling Budgetcited by 0
  8. 2026Paparazzo: Active Mapping of Moving 3D Objectscited by 0
  9. 2026Remember to be Curious: Episodic Context and Persistent Worlds for 3D Explorationcited by 0
  10. 2026DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstructioncited by 0
  11. 2026Diagnosing and Dynamically Filtering Occupancy World Models for Active Mappingcited by 0
  12. 2026Rethinking Learned Occupancy in Autonomous Active Mapping with Observation-Gated Filteringcited by 0
1 more
  1. 2026Multi-Scale Semantic Mapping in Urban Environments via Observation Calibration and Policy Dependence Regularizationcited by 0