# Cross-modal Deep Variational Hand Pose Estimation

arXiv: https://arxiv.org/abs/1803.11404 · HTML: https://mlsanity.com/paper/1803.11404/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2018.

## Built on by (most cited first, 30 of 89)

- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time](https://mlsanity.com/paper/2106.05266/) (2021)
- [Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2405.01527/) (2024)
- [Interacting Attention Graph for Single Image Two-Hand Reconstruction](https://mlsanity.com/paper/2203.09364/) (2022)
- [HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video](https://mlsanity.com/paper/2311.18448/) (2023)
- [MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image](https://mlsanity.com/paper/2112.02753/) (2021)
- [Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera](https://mlsanity.com/paper/2106.08059/) (2021)
- [Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration](https://mlsanity.com/paper/2103.02845/) (2021)
- [Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution](https://mlsanity.com/paper/2204.13062/) (2022)
- [Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans](https://mlsanity.com/paper/2312.00775/) (2023)
- [Zero-Shot Robot Manipulation from Passive Human Videos](https://mlsanity.com/paper/2302.02011/) (2023)
- [StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval](https://mlsanity.com/paper/2103.15706/) (2021)
- [A Skeleton-Driven Neural Occupancy Representation for Articulated Hands](https://mlsanity.com/paper/2109.11399/) (2021)
- [UmeTrack: Unified multi-view end-to-end hand tracking for VR](https://mlsanity.com/paper/2211.00099/) (2022)
- [Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction](https://mlsanity.com/paper/2109.01723/) (2021)
- [Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation](https://mlsanity.com/paper/2107.00434/) (2021)
- [ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction](https://mlsanity.com/paper/2303.05938/) (2023)
- [3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal](https://mlsanity.com/paper/2207.11061/) (2022)
- [Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects](https://mlsanity.com/paper/2403.16428/) (2024)
- [Contrastive Representation Learning for Hand Shape Estimation](https://mlsanity.com/paper/2106.04324/) (2021)
- [Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras](https://mlsanity.com/paper/2108.10378/) (2021)
- [Hand Image Understanding via Deep Multi-Task Learning](https://mlsanity.com/paper/2107.11646/) (2021)
- [SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text](https://mlsanity.com/paper/2204.11964/) (2022)
- [Consistent 3D Hand Reconstruction in Video via self-supervised Learning](https://mlsanity.com/paper/2201.09548/) (2022)
- [RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video](https://mlsanity.com/paper/2106.11725/) (2021)
- [HMP: Hand Motion Priors for Pose and Shape Estimation from Video](https://mlsanity.com/paper/2312.16737/) (2023)
- [Vision+X: A Survey on Multimodal Learning in the Light of Data](https://mlsanity.com/paper/2210.02884/) (2022)
- [emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation](https://mlsanity.com/paper/2412.02725/) (2024)
- [Reconstructing Interacting Hands with Interaction Prior from Monocular Images](https://mlsanity.com/paper/2308.14082/) (2023)

## Abstract (arXiv)

The human hand moves in complex and high-dimensional ways, making estimation of 3D hand pose configurations from images alone a challenging task. In this work we propose a method to learn a statistical hand model represented by a cross-modal trained latent space via a generative deep neural network. We derive an objective function from the variational lower bound of the VAE framework and jointly optimize the resulting cross-modal KL-divergence and the posterior reconstruction objective, naturally admitting a training regime that leads to a coherent latent space across multiple modalities such as RGB images, 2D keypoint detections or 3D hand configurations. Additionally, it grants a straightforward way of using semi-supervision. This latent space can be directly used to estimate 3D hand poses from RGB images, outperforming the state-of-the art in different settings. Furthermore, we show that our proposed method can be used without changes on depth images and performs comparably to specialized methods. Finally, the model is fully generative and can synthesize consistent pairs of hand configurations across modalities. We evaluate our method on both RGB and depth datasets and analyze the latent space qualitatively.