mlsanityData to 14 Oct 2026

Shape Anchor Guided Holistic Indoor Scene Understanding

arXiv 2309.11133 ↗First posted 20 Sep 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper proposes a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene understanding. We observe that the search space constructed by current methods for proposal feature grouping and instance point sampling often introduces massive noise to instance detection and mesh reconstruction. Accordingly, we develop AncLearn to generate anchors that dynamically fit instance surfaces to (i) unmix noise and target-related features for offering reliable proposals at the detection stage, and (ii) reduce outliers in object point sampling for directly providing well-structured geometry priors without segmentation during reconstruction. We embed AncLearn into a reconstruction-from-detection learning system (AncRec) to generate high-quality semantic scene models in a purely instance-oriented manner. Experiments conducted on the challenging ScanNetv2 dataset demonstrate that our shape anchor-based method consistently achieves state-of-the-art performance in terms of 3D object detection, layout estimation, and shape reconstruction. The code will be available at https://github.com/Geo-Tell/AncRec.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 35 of its 42 references that are in the map. First posted on arXiv 20 Sep 2023.

Builds on

35 of 42 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  8. 2019Object Detection in 20 Years: A Surveycited by 531
  9. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  10. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  11. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 217
  12. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
23 more
  1. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  2. 2020Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Imagecited by 172
  3. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  4. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 141
  5. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  6. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  7. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  8. 2020MLCVNet: Multi-Level Context VoteNet for 3D Object Detectioncited by 80
  9. 2016IM2CADcited by 78
  10. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  11. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  12. 20214DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understandingcited by 54
  13. 2019VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentationcited by 44
  14. 2020SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scanscited by 44
  15. 2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
  16. 2019End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scanscited by 40
  17. 2020RfD-Net: Point Scene Understanding by Semantic Instance Reconstructioncited by 36
  18. 2019RevealNet: Seeing Behind Objects in RGB-D Scanscited by 30
  19. 2021PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Cloudscited by 26
  20. 2022Point Scene Understanding via Disentangled Instance Mesh Reconstructioncited by 20
  21. 2019Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Imagecited by 15
  22. 2020Towards Part-Based Understanding of RGB-D Scanscited by 9
  23. 2022Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scanscited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2024ROOT: VLM based System for Indoor Scene Understanding and Beyondcited by 6
  2. 2023LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Datasetcited by 5