mlsanityData to 14 Oct 2026

Persistent Homology Meets Object Unity: Object Recognition in Clutter

arXiv 2305.03815 ↗First posted 5 May 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Recognition of occluded objects in unseen and unstructured indoor environments is a challenging problem for mobile robots. To address this challenge, we propose a new descriptor, TOPS, for point clouds generated from depth images and an accompanying recognition framework, THOR, inspired by human reasoning. The descriptor employs a novel slicing-based approach to compute topological features from filtrations of simplicial complexes using persistent homology, and facilitates reasoning-based recognition using object unity. Apart from a benchmark dataset, we report performance on a new dataset, the UW Indoor Scenes (UW-IS) Occluded dataset, curated using commodity hardware to reflect real-world scenarios with different environmental conditions and degrees of object occlusion. THOR outperforms state-of-the-art methods on both the datasets and achieves substantially higher recognition accuracy for all the scenarios of the UW-IS Occluded dataset. Therefore, THOR, is a promising step toward robust recognition in low-cost robots, meant for everyday use in indoor settings.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 39 of its 74 references that are in the map. First posted on arXiv 5 May 2023.

Builds on

39 of 74 references.

References · 39

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2020Point Transformercited by 1,470
  8. 2020PCT: Point cloud transformercited by 732
  9. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  10. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  11. 2022Kubric: A scalable dataset generatorcited by 381
  12. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 270
27 more
  1. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  2. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  3. 2015Persistence Images: A Stable Vector Representation of Persistent Homologycited by 236
  4. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  5. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  6. 2017An introduction to Topological Data Analysis: fundamental and practical aspects for data scientistscited by 172
  7. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  8. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  9. 2019Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detectioncited by 123
  10. 2019Multi-adversarial Faster-RCNN for Unrestricted Object Detectioncited by 112
  11. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 98
  12. 20226-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmarkcited by 86
  13. 2020Unseen Object Instance Segmentation for Robotic Environmentscited by 85
  14. 2019BlenderProccited by 77
  15. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  16. 2019EasyLabel: A Semi-Automatic Pixel-wise Object Annotation Tool for Creating Robotic RGB-D Datasetscited by 58
  17. 2019PyRobot: An Open-source Robotics Framework for Research and Benchmarkingcited by 39
  18. 2015A Dataset for Improved RGBD-based Object Detection and Pose Estimation for Warehouse Pick-and-Placecited by 35
  19. 2017LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenescited by 32
  20. 2015Dense Human Body Correspondences Using Convolutional Networkscited by 26
  21. 2018Domain Randomization for Scene-Specific Car Detection and Pose Estimationcited by 23
  22. 2022Towards Domain Generalization in Object Detectioncited by 16
  23. 2020Human action recognition with a large-scale brain-inspired photonic computercited by 15
  24. 2017Recognizing Objects In-the-wild: Where Do We Stand?cited by 10
  25. 2020WQT and DG-YOLO: towards domain generalization in underwater object detectioncited by 8
  26. 2020Visual Object Recognition in Indoor Environments Using Topologically Persistent Featurescited by 5
  27. 2022Domain Generalisation for Object Detection under Covariate and Concept Shiftcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 3.

5 papers.

  1. 2025Distracted Robot: How Visual Clutter Undermine Robotic Manipulationcited by 5
  2. 2025Time-Series Forecasting via Topological Information Supervised Framework with Efficient Topological Feature Learningcited by 3
  3. 2025Improving Robotic Manipulation Robustness via NICE Scene Surgerycited by 3
  4. 2023Human-Inspired Topological Representations for Visual Object Recognition in Unseen Environmentscited by 0
  5. 2024Sparse Color-Code Net: Real-Time RGB-Based 6D Object Pose Estimation on Edge Devicescited by 0