mlsanityData to 7 Oct 2026

3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding

arXiv 2103.16397 ↗First posted 30 Mar 2021cs.CVcited by 100

Not on the map. Why?

Abstract (arXiv)

The ability to understand the ways to interact with objects from visual cues, a.k.a. visual affordance, is essential to vision-guided robotic research. This involves categorizing, segmenting and reasoning of visual affordance. Relevant studies in 2D and 2.5D image domains have been made previously, however, a truly functional understanding of object affordance requires learning and prediction in the 3D physical domain, which is still absent in the community. In this work, we present a 3D AffordanceNet dataset, a benchmark of 23k shapes from 23 semantic object categories, annotated with 18 visual affordance categories. Based on this dataset, we provide three benchmarking tasks for evaluating visual affordance understanding, including full-shape, partial-view and rotation-invariant affordance estimations. Three state-of-the-art point cloud deep learning networks are evaluated on all tasks. In addition we also investigate a semi-supervised learning setup to explore the possibility to benefit from unlabeled data. Comprehensive results on our contributed dataset show the promise of visual affordance understanding as a valuable yet challenging benchmark.

Key facts. Cited by 100 papers in the map (data through 7 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

18 of 34 references.

References · 18

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  6. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  7. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  8. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  9. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  10. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  11. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  12. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
6 more
  1. 2017AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detectioncited by 126
  2. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  3. 2017Learning to Act Properly: Predicting and Explaining Affordances from Imagescited by 74
  4. 2019PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentationcited by 44
  5. 2017Predicting Human Activities Using Stochastic Grammarcited by 22
  6. 2018Visual Affordance and Function Understanding: A Surveycited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 10; 2023: 17; 2024: 23; 2025: 22; 2026: 24.

100 papers.

Sort:

By area:

  1. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  2. 2023HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Modelscited by 89
  3. 2024Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordancecited by 79
  4. 2023Grounding 3D Object Affordance from 2D Interactions in Imagescited by 62
  5. 2025Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spacescited by 53
  6. 2023LEMON: Learning 3D Human-Object Interaction Relation from 2D Imagescited by 49
  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. 2023Detecting Human-Object Contact in Imagescited by 41
  11. 2021One-Shot Object Affordance Detection in the Wildcited by 40
  12. 2023Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perceptioncited by 40
38 more
  1. 2023Object pop-up: Can we infer 3D objects and their poses from human interactions alone?cited by 36
  2. 2022PartAfford: Part-level Affordance Discovery from 3D Objectscited by 35
  3. 2023Affordance Grounding from Demonstration Video to Target Imagecited by 34
  4. 2024Learning Precise Affordances from Egocentric Videos for Robotic Manipulationcited by 34
  5. 2023Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objectscited by 33
  6. 2024Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Modelscited by 32
  7. 20253D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worldscited by 29
  8. 2024EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Viewscited by 26
  9. 2024GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Groundingcited by 26
  10. 2025PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understandingcited by 24
  11. 2025UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulationcited by 23
  12. 2021Pose2Room: Understanding 3D Scenes from Human Activitiescited by 22
  13. 2025FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interactioncited by 22
  14. 2022Grounded Affordance from Exocentric Viewcited by 21
  15. 2022Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraintcited by 21
  16. 2024Learning 2D Invariant Affordance Knowledge for 3D Affordance Groundingcited by 21
  17. 2025Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactionscited by 19
  18. 2023Learning 6-DoF Fine-grained Grasp Detection Based on Part Affordance Groundingcited by 17
  19. 2024Composable Part-Based Manipulationcited by 17
  20. 2024Functionality understanding and segmentation in 3D scenescited by 17
  21. 2024GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistencycited by 17
  22. 20213D Compositional Zero-shot Learning with DeCompositional Consensuscited by 16
  23. 2024Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intentioncited by 16
  24. 2022Discovering Human-Object Interaction Concepts via Self-Compositional Learningcited by 15
  25. 2024WorldAfford: Affordance Grounding based on Natural Language Instructionscited by 14
  26. 2024LLM-enhanced Scene Graph Learning for Household Rearrangementcited by 12
  27. 2023Style2Fab: Functionality-Aware Segmentation for Fabricating Personalized 3D Models with Generative AIcited by 11
  28. 2024Grounding 3D Scene Affordance From Egocentric Interactionscited by 11
  29. 2025IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environmentscited by 11
  30. 2026HY3D-Bench: Generation of 3D Assetscited by 11
  31. 2023STRAP: Structured Object Affordance Segmentation with Point Supervisioncited by 10
  32. 20243x2: 3D Object Part Segmentation by 2D Semantic Correspondencescited by 10
  33. 2024Text-driven Affordance Learning from Egocentric Visioncited by 9
  34. 2025Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priorscited by 9
  35. 2024FIction: 4D Future Interaction Prediction from Videocited by 8
  36. 2022A large scale multi-view RGBD visual affordance learning datasetcited by 6
  37. 2025Benchmarking Vision, Language, & Action Models in Procedurally Generated, Open Ended Action Environmentscited by 6
  38. 2025Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scalecited by 6

50 most cited of 100 All 100 (JSON)