# Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding

arXiv: https://arxiv.org/abs/2408.13024 · HTML: https://mlsanity.com/paper/2408.13024/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 68 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving](https://mlsanity.com/paper/2311.17918/) (2023)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Where2Act: From Pixels to Actions for Articulated 3D Objects](https://mlsanity.com/paper/2101.02692/) (2021)
- [PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation](https://mlsanity.com/paper/1711.10871/) (2017)
- [GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts](https://mlsanity.com/paper/2211.05272/) (2022)
- [Grounded Human-Object Interaction Hotspots from Video](https://mlsanity.com/paper/1812.04558/) (2018)
- [AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection](https://mlsanity.com/paper/1709.07326/) (2017)
- [3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding](https://mlsanity.com/paper/2103.16397/) (2021)
- [AKB-48: A Real-World Articulated Object Knowledge Base](https://mlsanity.com/paper/2202.08432/) (2022)
- [Learning Affordance Grounding from Exocentric Images](https://mlsanity.com/paper/2203.09905/) (2022)
- [VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects](https://mlsanity.com/paper/2106.14440/) (2021)
- [Multi-view PointNet for 3D Scene Understanding](https://mlsanity.com/paper/1909.13603/) (2019)
- [Learning to Act Properly: Predicting and Explaining Affordances from Images](https://mlsanity.com/paper/1712.07576/) (2017)
- [GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF](https://mlsanity.com/paper/2210.06575/) (2022)
- [Learning Affordance Landscapes for Interaction Exploration in 3D Environments](https://mlsanity.com/paper/2008.09241/) (2020)
- [Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary](https://mlsanity.com/paper/2401.08209/) (2024)
- [Grounding 3D Object Affordance from 2D Interactions in Images](https://mlsanity.com/paper/2303.10437/) (2023)
- [PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations](https://mlsanity.com/paper/2303.16958/) (2023)
- [PartAfford: Part-level Affordance Discovery from 3D Objects](https://mlsanity.com/paper/2202.13519/) (2022)
- [Cross-modal Learning for Image-Guided Point Cloud Shape Completion](https://mlsanity.com/paper/2209.09552/) (2022)
- [Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects](https://mlsanity.com/paper/2309.07473/) (2023)
- [LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation](https://mlsanity.com/paper/2108.07511/) (2021)

## Built on by (most cited first, 22 of 22)

- [Hume: Introducing System-2 Thinking in Visual-Language-Action Model](https://mlsanity.com/paper/2505.21432/) (2025)
- [Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model](https://mlsanity.com/paper/2508.06206/) (2025)
- [SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model](https://mlsanity.com/paper/2412.01550/) (2024)
- [Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering](https://mlsanity.com/paper/2410.01401/) (2024)
- [MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation](https://mlsanity.com/paper/2503.11081/) (2025)
- [AlignBot: Aligning VLM-powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots](https://mlsanity.com/paper/2409.11905/) (2024)
- [Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning](https://mlsanity.com/paper/2508.01651/) (2025)
- [A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning](https://mlsanity.com/paper/2512.14442/) (2025)
- [Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series](https://mlsanity.com/paper/2602.18473/) (2026)
- [Affordance Agent Harness: Verification-Gated Skill Orchestration](https://mlsanity.com/paper/2605.00663/) (2026)
- [Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts](https://mlsanity.com/paper/2503.02600/) (2025)
- [VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model](https://mlsanity.com/paper/2602.09638/) (2026)
- [Object Affordance Recognition and Grounding via Multi-scale Cross-modal Representation Learning](https://mlsanity.com/paper/2508.01184/) (2025)
- [VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos](https://mlsanity.com/paper/2602.20608/) (2026)
- [HAMMER: Harnessing MLLM via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding](https://mlsanity.com/paper/2603.02329/) (2026)
- [Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning](https://mlsanity.com/paper/2605.27318/) (2026)
- [Part-Aware Open-Vocabulary 3D Affordance Grounding via Prototypical Semantic and Geometric Alignment](https://mlsanity.com/paper/2603.17647/) (2026)
- [AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers](https://mlsanity.com/paper/2603.27970/) (2026)
- [Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances](https://mlsanity.com/paper/2605.11616/) (2026)
- [SECOND-Grasp: Semantic Contact-guided Dexterous Grasping](https://mlsanity.com/paper/2605.13117/) (2026)
- [Zero-shot 2D Grounding with Novel Affordance Types](https://mlsanity.com/paper/2608.08929/) (2026)
- [Reproducible Multimodal Affordance Prediction](https://mlsanity.com/paper/2608.18317/) (2026)

## Abstract (arXiv)

3D Object Affordance Grounding aims to predict the functional regions on a 3D object and has laid the foundation for a wide range of applications in robotics. Recent advances tackle this problem via learning a mapping between 3D regions and a single human-object interaction image. However, the geometric structure of the 3D object and the object in the human-object interaction image are not always consistent, leading to poor generalization. To address this issue, we propose to learn generalizable invariant affordance knowledge from multiple human-object interaction images within the same affordance category. Specifically, we introduce the Multi-Image Guided Invariant-Feature-Aware 3D Affordance Grounding (MIFAG) framework. It grounds 3D object affordance regions by identifying common interaction patterns across multiple human-object interaction images. First, the Invariant Affordance Knowledge Extraction Module (IAM) utilizes an iterative updating strategy to gradually extract aligned affordance knowledge from multiple images and integrate it into an affordance dictionary. Then, the Affordance Dictionary Adaptive Fusion Module (ADM) learns comprehensive point cloud representations that consider all affordance candidates in multiple images. Besides, the Multi-Image and Point Affordance (MIPA) benchmark is constructed and our method outperforms existing state-of-the-art methods on various experimental comparisons.