mlsanityData to 7 Oct 2026

Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation

arXiv 2007.09841 ↗First posted 20 Jul 2020cs.CV cs.ROcited by 34

Not on the map. Why?

Abstract (arXiv)

We introduce a learning-based approach for room navigation using semantic maps. Our proposed architecture learns to predict top-down belief maps of regions that lie beyond the agent's field of view while modeling architectural and stylistic regularities in houses. First, we train a model to generate amodal semantic top-down maps indicating beliefs of location, size, and shape of rooms by learning the underlying architectural patterns in houses. Next, we use these maps to predict a point that lies in the target room and train a policy to navigate to the point. We empirically demonstrate that by predicting semantic maps, the model learns common correlations found in houses and generalizes to novel environments. We also demonstrate that reducing the task of room navigation to point navigation improves the performance further.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 12; 2023: 6; 2024: 4; 2025: 1; 2026: 2.

34 papers.

Sort:

By area:

  1. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  2. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  3. 2021Pathdreamer: A World Model for Indoor Navigationcited by 117
  4. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 117
  5. 2022Cross-modal Map Learning for Vision and Language Navigationcited by 91
  6. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  7. 2022Housekeep: Tidying Virtual Households using Commonsense Reasoningcited by 57
  8. 2022ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hintscited by 55
  9. 2021SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environmentscited by 48
  10. 2021Learning to Map for Active Semantic Goal Navigationcited by 47
  11. 2021Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modelingcited by 43
  12. 2022Uncertainty-driven Planner for Exploration and Navigationcited by 31
22 more
  1. 2021The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigationcited by 27
  2. 2022PEANUT: Predicting and Navigating to Unseen Targetscited by 22
  3. 2022Image Amodal Completion: A Surveycited by 18
  4. 2024Object-level Scene Deocclusioncited by 17
  5. 2022Navigating to Objects in Unseen Environments by Distance Predictioncited by 15
  6. 2021Environment Predictive Coding for Embodied Agentscited by 12
  7. 2023Chat2Map: Efficient Scene Mapping from Multi-Ego Conversationscited by 8
  8. 2024WAFFLE: Multimodal Floorplan Understanding in the Wildcited by 5
  9. 2023Probable Object Location (POLo) Score Estimation for Efficient Object Goal Navigationcited by 4
  10. 20263D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigationcited by 4
  11. 2021Deep Learning for Embodied Vision Navigation: A Surveycited by 2
  12. 2022Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluationcited by 2
  13. 2023Boosting Semantic Segmentation with Semantic Boundariescited by 2
  14. 2023What Is Near?: Room Locality Learning for Enhanced Robot Vision-Language-Navigation in Indoor Living Environmentscited by 2
  15. 2024Mapping High-level Semantic Regions in Indoor Environments without Object Recognitioncited by 2
  16. 2023Cross-Dimensional Refined Learning for Real-Time 3D Visual Perception from Monocular Videocited by 1
  17. 2026Raster2Seq: Polygon Sequence Generation for Floorplan Reconstructioncited by 1
  18. 2021Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneckcited by 0
  19. 2022Structured Exploration Through Instruction Enhancement for Object Navigationcited by 0
  20. 2022Predicting Topological Maps for Visual Navigation in Unexplored Environmentscited by 0
  21. 2024Semantic Environment Atlas for Object-Goal Navigationcited by 0
  22. 2025BoundMatch: Boundary detection applied to semi-supervised segmentationcited by 0