mlsanityData to 7 Oct 2026

Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes

arXiv 2504.18355 ↗First posted 25 Apr 2025cs.CV cs.ROcited by 3

Not on the map. Why?

Abstract (arXiv)

Robotic agents need to understand how to interact with objects in their environment, both autonomously and during human-robot interactions. Affordance detection on 3D point clouds, which identifies object regions that allow specific interactions, has traditionally relied on deep learning models like PointNet++, DGCNN, or PointTransformerV3. However, these models operate as black boxes, offering no insight into their decision-making processes. Prototypical Learning methods, such as ProtoPNet, provide an interpretable alternative to black-box models by employing a "this looks like that" case-based reasoning approach. However, they have been primarily applied to image-based tasks. In this work, we apply prototypical learning to models for affordance detection on 3D point clouds. Experiments on the 3D-AffordanceNet benchmark dataset show that prototypical models achieve competitive performance with state-of-the-art black-box models and offer inherent interpretability. This makes prototypical models a promising candidate for human-robot interaction scenarios that require increased trust and safety.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 25 Apr 2025.

Builds on

36 of 53 references.

References · 36

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  5. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  6. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  7. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  8. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  9. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
  10. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  11. 2017AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detectioncited by 126
  12. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
24 more
  1. 20213D AffordanceNet: A Benchmark for Visual Object Affordance Understandingcited by 100
  2. 2021Interpretable Image Classification with Differentiable Prototypes Assignmentcited by 97
  3. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  4. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  5. 2017Learning to Act Properly: Predicting and Explaining Affordances from Imagescited by 74
  6. 2019Putting Humans in a Scene: Learning Affordance in 3D Indoor Environmentscited by 72
  7. 2023AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Posecited by 47
  8. 2023One-Shot Open Affordance Learning with Foundation Modelscited by 45
  9. 2023Open-Vocabulary Affordance Detection in 3D Point Cloudscited by 41
  10. 2023Affordance Grounding from Demonstration Video to Target Imagecited by 34
  11. 2023ProtoSeg: Interpretable Semantic Segmentation with Prototypical Partscited by 33
  12. 2021Dual Transformer for Point Cloud Analysiscited by 26
  13. 2023Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentationcited by 26
  14. 2021Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsingcited by 22
  15. 2022Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detectioncited by 14
  16. 2022Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learningcited by 13
  17. 2020Affordance-Aware Handovers with Human Arm Mobility Constraintscited by 8
  18. 2022Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentationcited by 7
  19. 2021Affordance-Based Mobile Robot Navigation Among Movable Obstaclescited by 6
  20. 2022A large scale multi-view RGBD visual affordance learning datasetcited by 6
  21. 2024ProtoGMM: Multi-prototype Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentationcited by 5
  22. 2024An Overview of Prototype Formulations for Interpretable Deep Learningcited by 4
  23. 2022Explaining Deep Neural Networks for Point Clouds using Gradient-based Visualisationscited by 3
  24. 2024ProtoSeg: A Prototype-Based Point Cloud Instance Segmentation Methodcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objectscited by 1
  2. 2026ProtoPointNet: Prototype-Based Interpretable Classification of 3D Dental Point Clouds with Verifiable Spatial Activationscited by 0
  3. 2026Beyond L2: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architecturescited by 0