Embodied Hands : Modeling and Capturing Hands and Bodies Together * * Supplementary Material * *

By Javier Romero, Dimitrios Tzionas. 2017

Subfields: Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications (2022, methodology): “One mainstream approach [6,18] to solve this task is to jointly optimize the 3D scale, translation and rotation of a given 3D object model, as well as the MANO parameters [54] for hand.”
Understanding Human Hands in Contact at Internet Scale (2020, methodology): “As a concrete demonstration, we build off of the technique of [21] that maps images to the MANO [31] low-dimensional parameterization of hands via a Resnet-18 [22]; this parameterization comprises [ θ , β ] representing hand pose and shape, which can be converted to a 3D mesh via the differentiable…”
3D Hand Shape and Pose Estimation From a Single RGB Image (2019, methodology): “Note that the mesh errors in this table are measured on the aligned mesh defined by MANO [42] for fair comparison.”
Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge (2020, methodology): “To make the joint definition consistent across different datasets, we reorganize the joints of each hand according to the layout of MANO [37].”
AMASS: Archive of Motion Capture As Surface Shapes (2019, methodology): “When hand markers are present, MoSh++ optimizes the hand pose parameters in the same way as all the other pose parameters except that we use 24 dimensions of MANO’s [36] low-dimensional representation of the pose for both hands.”
GRAB: A Dataset of Whole-Body Human Grasping of Objects (2020, background): “For this reason, many studies focus on understanding grasps and defining taxonomies [3,12,16,30,47,55], by exploring the object shape and purpose of grasps [12], the contact areas on the hand captured by sinking objects in ink [30], the pose and contact areas [3] captured with an integrated data-glo”
End-to-End Human Pose and Mesh Reconstruction with Transformers (2020, methodology): “, SMPL [24], STAR [30], MANO [38], and estimate the pose and shape coefficients of the parametric model for HMR.”
Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos (2021, methodology): “1 for the PCA components of the MANO [53] articulated hand model and the continuous rotation parameters [66].”
Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction (2020, unknown): “In the spirit of [3, 12], our network takes as input a single RGB image and outputs MANO [38] pose and shape parameters.”
First-Person View Hand Segmentation of Multi-Modal Hand Activity Video Dataset (2020, background): “Alternatively, studies showed good performance when utilizing hand pose estimation and mesh models to segment hands in frames [45, 62].”
Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics (2019, background): “In addition, obtaining an adequate template is very costly, so that most existing efforts focus on particular shape categories such as human bodies, hands, or faces [7, 35, 47, 49, 55].”
3D Hand Shape and Pose From Images in the Wild (2019, methodology): “We also use a pre-defined hand model [40] but within a pipeline trained end-to-end.”
FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization (2023, methodology): “In our method, we replace the complex mesh regression head with a simple regression module which regresses weak perspective camera, pose and shape parameters of the MANO model [44].”
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild (2020, methodology): “• We demonstrate that spatial mesh convolutions outperform spectral methods and SMPL-based [33, 44] models for hand reconstruction.”
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction (2022, methodology): “We transform the human hand pose represented as 51 DoF MANO model [37] to 30 DoF Adroit Hand pose in the hand joint retargeting step.”
Hand Pose Estimation via Latent 2.5D Heatmap Regression (2018, background): “To alleviate these challenges, many proposed solutions simplify the problem by using calibrated multi-view camera systems [1–9], depth sensors [10–22], or color markers/gloves [23].”
Detecting Hands and Recognizing Physical Contact in the Wild (2020, methodology): “There are prior works for hand detection [3, 6, 7, 15–17, 19, 21, 22, 26, 28, 33, 35], hand pose estimation [12, 25, 29, 37, 38], and hand-tracking [3].”