mlsanityData to 7 Oct 2026

Monocular Occupancy Prediction for Scalable Indoor Scenes

arXiv 2407.11730 ↗First posted 16 Jul 2024cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

Camera-based 3D occupancy prediction has recently garnered increasing attention in outdoor driving scenes. However, research in indoor scenes remains relatively unexplored. The core differences in indoor scenes lie in the complexity of scene scale and the variance in object size. In this paper, we propose a novel method, named ISO, for predicting indoor scene occupancy using monocular images. ISO harnesses the advantages of a pretrained depth model to achieve accurate depth predictions. Furthermore, we introduce the Dual Feature Line of Sight Projection (D-FLoSP) module within ISO, which enhances the learning of 3D voxel features. To foster further research in this domain, we introduce Occ-ScanNet, a large-scale occupancy benchmark for indoor scenes. With a dataset size 40 times larger than the NYUv2 dataset, it facilitates future scalable research in indoor scene analysis. Experimental results on both NYUv2 and Occ-ScanNet demonstrate that our method achieves state-of-the-art performance. The dataset and code are made publicly at https://github.com/hongxiaoy/ISO.git.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 44 of its 52 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

44 of 52 references.

References · 44

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  5. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  6. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  8. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  9. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  10. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  11. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  12. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
32 more
  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  2. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 373
  3. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  4. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  5. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  6. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  7. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  8. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  9. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  10. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  11. 2023Scene as Occupancycited by 208
  12. 2020Atlas: End-to-End 3D Scene Reconstruction from Posed Imagescited by 206
  13. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 187
  14. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  15. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  16. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 162
  17. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  18. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 126
  19. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 126
  20. 20203D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Priorcited by 124
  21. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 114
  22. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 101
  23. 2022NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstructioncited by 99
  24. 2023NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Spacecited by 88
  25. 2021Panoptic 3D Scene Reconstruction From a Single RGB Imagecited by 70
  26. 2019Efficient Semantic Scene Completion Network with Spatial Group Convolutioncited by 66
  27. 2023ObjectSDF++: Improved Object-Compositional Neural Implicit Surfacescited by 38
  28. 2020Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understandingcited by 25
  29. 2020SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completioncited by 25
  30. 2023FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detectioncited by 21
  31. 2023Reconstructing Three-Dimensional Models of Interacting Humanscited by 14
  32. 2023LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstructioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 18.

29 papers.

Sort:

By area:

  1. 2024EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understandingcited by 43
  2. 2024OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generationcited by 10
  3. 2026Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Predictioncited by 9
  4. 2025SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representationcited by 8
  5. 2025Occupancy World Model for Robotscited by 8
  6. 2025SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completioncited by 7
  7. 2026Monocular Open Vocabulary Occupancy Prediction for Indoor Scenescited by 5
  8. 2025Terra: Explorable Native 3D World Model with Point Latentscited by 4
  9. 2026Enhancing Indoor Occupancy Prediction via Sparse Query-Based Multi-Level Consistent Knowledge Distillationcited by 3
  10. 2026AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environmentscited by 3
  11. 2025Fake It To Make It: Virtual Multiviews to Enhance Monocular Indoor Semantic Scene Completioncited by 2
  12. 2025Global-Aware Monocular Semantic Scene Completion with State Space Modelscited by 2
17 more
  1. 2025TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completioncited by 2
  2. 2026Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robotscited by 2
  3. 2026FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Predictioncited by 2
  4. 2025BePo: Dual Representation for 3D Occupancy Predictioncited by 1
  5. 2025YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videoscited by 1
  6. 2026VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understandingcited by 1
  7. 2026Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AIcited by 1
  8. 2026Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Imagescited by 1
  9. 2026Adaptive Multi-Scale Channel-Spatial Attention Aggregation Framework for 3D Indoor Semantic Scene Completion Toward Assisting Visually Impairedcited by 0
  10. 2026SGR-OCC: Evolving Monocular Priors for Embodied 3D Occupancy Prediction via Soft-Gating Lifting and Semantic-Adaptive Geometric Refinementcited by 0
  11. 2026World2Minecraft: Occupancy-Driven Simulated Scenes Constructioncited by 0
  12. 2026FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Predictioncited by 0
  13. 2026GPOcc++: Unified Sparse Gaussian Occupancy Prediction with Visual Geometry Priorscited by 0
  14. 2026Group-wise Supervision with Focal-Dice Loss for Long-Tailed Indoor Semantic Occupancy Predictioncited by 0
  15. 2026SR-JEPA: Learning Predictive Latent State in 3D Scenescited by 0
  16. 2026OccAnyScene: Towards Unified Indoor-Outdoor 3D Occupancy Predictioncited by 0
  17. 2026AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Taskscited by 0