# SHARP: Segmentation of Hands and Arms by Range using Pseudo-Depth for Enhanced Egocentric 3D Hand Pose Estimation and Action Recognition

arXiv: https://arxiv.org/abs/2408.10037 · HTML: https://mlsanity.com/paper/2408.10037/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 19 Aug 2024.

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations](https://mlsanity.com/paper/1704.02463/) (2017)
- [Single-Image Depth Perception in the Wild](https://mlsanity.com/paper/1604.03901/) (2016)
- [HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World](https://mlsanity.com/paper/2309.17024/) (2023)
- [H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions](https://mlsanity.com/paper/1904.05349/) (2019)
- [Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction](https://mlsanity.com/paper/2004.13449/) (2020)
- [Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor](https://mlsanity.com/paper/1704.02201/) (2017)
- [AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation](https://mlsanity.com/paper/2304.12301/) (2023)
- [A neural network based on SPD manifold learning for skeleton-based hand gesture recognition](https://mlsanity.com/paper/1904.12970/) (2019)
- [Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos](https://mlsanity.com/paper/2209.09484/) (2022)
- [THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision](https://mlsanity.com/paper/2210.13853/) (2022)
- [In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition](https://mlsanity.com/paper/2404.09308/) (2024)
- [TEXT2TASTE: A Versatile Egocentric Vision System for Intelligent Reading Assistance Using Large Language Model](https://mlsanity.com/paper/2404.09254/) (2024)

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

- [Towards Egocentric 3D Hand Pose Estimation in Unseen Domains](https://mlsanity.com/paper/2601.06537/) (2026)

## Abstract (arXiv)

Hand pose represents key information for action recognition in the egocentric perspective, where the user is interacting with objects. We propose to improve egocentric 3D hand pose estimation based on RGB frames only by using pseudo-depth images. Incorporating state-of-the-art single RGB image depth estimation techniques, we generate pseudo-depth representations of the frames and use distance knowledge to segment irrelevant parts of the scene. The resulting depth maps are then used as segmentation masks for the RGB frames. Experimental results on H2O Dataset confirm the high accuracy of the estimated pose with our method in an action recognition task. The 3D hand pose, together with information from object detection, is processed by a transformer-based action recognition network, resulting in an accuracy of 91.73%, outperforming all state-of-the-art methods. Estimations of 3D hand pose result in competitive performance with existing methods with a mean pose error of 28.66 mm. This method opens up new possibilities for employing distance information in egocentric 3D hand pose estimation without relying on depth sensors.