# DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation

arXiv: https://arxiv.org/abs/2310.07206 · HTML: https://mlsanity.com/paper/2310.07206/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 64 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 30 of 44)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Learning to Simulate Complex Physics with Graph Networks](https://mlsanity.com/paper/2002.09405/) (2020)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [Learning to Estimate 3D Hand Pose from Single RGB Images](https://mlsanity.com/paper/1705.01389/) (2017)
- [ContactPose: A Dataset of Grasps with Object Contact and Hand Pose](https://mlsanity.com/paper/2007.09545/) (2020)
- [Grasping Field: Learning Implicit Representations for Human Grasps](https://mlsanity.com/paper/2008.04451/) (2020)
- [Hand-Object Contact Consistency Reasoning for Human Grasps Generation](https://mlsanity.com/paper/2104.03304/) (2021)
- [Reconstructing Hand-Object Interactions in the Wild](https://mlsanity.com/paper/2012.09856/) (2020)
- [CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction](https://mlsanity.com/paper/2012.00924/) (2020)
- [Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation](https://mlsanity.com/paper/2104.14639/) (2021)
- [Capturing Hands in Action using Discriminative Salient Points and Physics Simulation](https://mlsanity.com/paper/1506.02178/) (2015)
- [D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions](https://mlsanity.com/paper/2112.03028/) (2021)
- [HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation](https://mlsanity.com/paper/2004.00060/) (2020)
- [A Differentiable Physics Engine for Deep Learning in Robotics](https://mlsanity.com/paper/1611.01652/) (2016)
- [Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data](https://mlsanity.com/paper/2003.09572/) (2020)
- [Accelerated Policy Learning with Parallel Differentiable Simulation](https://mlsanity.com/paper/2204.07137/) (2022)
- [Flexible Neural Representation for Physics Prediction](https://mlsanity.com/paper/1806.08047/) (2018)
- [What's in your hands? 3D Reconstruction of Generic Objects in Hands](https://mlsanity.com/paper/2204.07153/) (2022)
- [NeuralSim: Augmenting Differentiable Simulators with Neural Networks](https://mlsanity.com/paper/2011.04217/) (2020)
- [ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis](https://mlsanity.com/paper/2109.05488/) (2021)
- [Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search](https://mlsanity.com/paper/2205.02961/) (2022)
- [Towards unconstrained joint hand-object reconstruction from RGB videos](https://mlsanity.com/paper/2108.07044/) (2021)

## Built on by (most cited first, 8 of 8)

- [A Survey on Human Interaction Motion Generation](https://mlsanity.com/paper/2503.12763/) (2025)
- [SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios](https://mlsanity.com/paper/2506.02444/) (2025)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [Human Motion Prediction, Reconstruction, and Generation](https://mlsanity.com/paper/2502.15956/) (2025)
- [Visuo-Acoustic Hand Pose and Contact Estimation](https://mlsanity.com/paper/2508.00852/) (2025)
- [SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis](https://mlsanity.com/paper/2511.19319/) (2025)
- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)
- [VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation](https://mlsanity.com/paper/2511.12030/) (2025)

## Abstract (arXiv)

This paper addresses the task of 3D pose estimation for a hand interacting with an object from a single image observation. When modeling hand-object interaction, previous works mainly exploit proximity cues, while overlooking the dynamical nature that the hand must stably grasp the object to counteract gravity and thus preventing the object from slipping or falling. These works fail to leverage dynamical constraints in the estimation and consequently often produce unstable results. Meanwhile, refining unstable configurations with physics-based reasoning remains challenging, both by the complexity of contact dynamics and by the lack of effective and efficient physics inference in the data-driven learning framework. To address both issues, we present DeepSimHO: a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network. Specifically, for an initial hand-object pose estimated by a base network, we forward it to a physics simulator to evaluate its stability. However, due to non-smooth contact geometry and penetration, existing differentiable simulators can not provide reliable state gradient. To remedy this, we further introduce a deep network to learn the stability evaluation process from the simulator, while smoothly approximating its gradient and thus enabling effective back-propagation. Extensive experiments show that our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization. The code is available at https://github.com/rongakowang/DeepSimHO.