# AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis

arXiv: https://arxiv.org/abs/2603.08021 · HTML: https://mlsanity.com/paper/2603.08021/

## Key facts

- Cited by 1 papers in the map (data through 7 Oct 2026).
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 30 of 31)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Diffusion Models already have a Semantic Latent Space](https://mlsanity.com/paper/2210.10960/) (2022)
- [Hand-Object Contact Consistency Reasoning for Human Grasps Generation](https://mlsanity.com/paper/2104.03304/) (2021)
- [OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction](https://mlsanity.com/paper/2203.15709/) (2022)
- [D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions](https://mlsanity.com/paper/2112.03028/) (2021)
- [ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact](https://mlsanity.com/paper/1904.03754/) (2019)
- [Guidance with Spherical Gaussian Constraint for Conditional Diffusion](https://mlsanity.com/paper/2402.03201/) (2024)
- [GraspXL: Generating Grasping Motions for Diverse Objects at Scale](https://mlsanity.com/paper/2403.19649/) (2024)
- [ContactGen: Generative Contact Modeling for Grasp Generation](https://mlsanity.com/paper/2310.03740/) (2023)
- [A Skeleton-Driven Neural Occupancy Representation for Articulated Hands](https://mlsanity.com/paper/2109.11399/) (2021)
- [AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose](https://mlsanity.com/paper/2309.08942/) (2023)
- [G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis](https://mlsanity.com/paper/2404.12383/) (2024)
- [Grasp as You Say: Language-guided Dexterous Grasp Generation](https://mlsanity.com/paper/2405.19291/) (2024)
- [AffordDP: Generalizable Diffusion Policy with Transferable Affordance](https://mlsanity.com/paper/2412.03142/) (2024)
- [RealDex: Towards Human-like Grasping for Robotic Dexterous Hand](https://mlsanity.com/paper/2402.13853/) (2024)
- [EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild](https://mlsanity.com/paper/2411.14280/) (2024)
- [SemGrasp: Semantic Grasp Generation via Language Aligned Discretization](https://mlsanity.com/paper/2404.03590/) (2024)
- [Pack and Force Your Memory: Long-form and Consistent Video Generation](https://mlsanity.com/paper/2510.01784/) (2025)
- [Cross-Embodiment Dexterous Grasping with Reinforcement Learning](https://mlsanity.com/paper/2410.02479/) (2024)
- [Text2Grasp: Grasp synthesis by text prompts of object grasping parts](https://mlsanity.com/paper/2404.15189/) (2024)
- [FastGrasp: Efficient Grasp Synthesis with Diffusion](https://mlsanity.com/paper/2411.14786/) (2024)

## Built on by (most cited first, 1 of 1)

- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)

## Abstract (arXiv)

Generating human grasping poses that accurately reflect both object geometry and user-specified interaction semantics is essential for natural hand-object interactions in AR/VR and embodied AI. However, existing semantic grasping approaches struggle with the large modality gap between 3D object representations and textual instructions, and often lack explicit spatial or semantic constraints, leading to physically invalid or semantically inconsistent grasps. In this work, we present AffordGrasp, a diffusion-based framework that produces physically stable and semantically faithful human grasps with high precision. We first introduce a scalable annotation pipeline that automatically enriches hand-object interaction datasets with fine-grained structured language labels capturing interaction intent. Building upon these annotations, AffordGrasp integrates an affordance-aware latent representation of hand poses with a dual-conditioning diffusion process, enabling the model to jointly reason over object geometry, spatial affordances, and instruction semantics. A distribution adjustment module further enforces physical contact consistency and semantic alignment. We evaluate AffordGrasp across four instruction-augmented benchmarks derived from HO-3D, OakInk, GRAB, and AffordPose, and observe substantial improvements over state-of-the-art methods in grasp quality, semantic accuracy, and diversity.