DeepAI AI Chat
Log In Sign Up

Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild

04/04/2020
by   Dominik Kulon, et al.
Imperial College London
8

We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh reconstruction loss. We train our network by gathering a large-scale dataset of hand action in YouTube videos and use it as a source of weak supervision. Our weakly-supervised mesh convolutions-based system largely outperforms state-of-the-art methods, even halving the errors on the in the wild benchmark. The dataset and additional resources are available at https://arielai.com/mesh_hands.

READ FULL TEXT

page 1

page 8

08/19/2020

DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling

Human hands play a central role in interacting with other people and obj...
04/03/2020

HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map

3D hand shape and pose estimation from a single depth map is a new and c...
04/18/2022

End-to-end Weakly-supervised Multiple 3D Hand Mesh Reconstruction from Single Image

In this paper, we consider the challenging task of simultaneously locati...
07/20/2022

3D Clothed Human Reconstruction in the Wild

Although much progress has been made in 3D clothed human reconstruction,...
04/25/2021

Parallel mesh reconstruction streams for pose estimation of interacting hands

We present a new multi-stream 3D mesh reconstruction network (MSMR-Net) ...
04/10/2023

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

Recovering 3D human mesh in the wild is greatly challenging as in-the-wi...
02/18/2021

HandTailor: Towards High-Precision Monocular 3D Hand Recovery

3D hand pose estimation and shape recovery are challenging tasks in comp...

Code Repositories

mobilehand

MobileHand: Real-time 3D Hand Shape and Pose Estimation from Color Image


view repo

JointBoneLoss

This is an implementation of Joint Bone Loss by myself. I try it on my own pose estimation task and achieve good performance. So I share with you guys, enjoy~


view repo