Appearance Consensus Driven Self-Supervised Human Mesh Recovery

by   Jogendra Nath Kundu, et al.

We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision. Recent advances have shifted the interest towards directly regressing parameters of a parametric human model by supervising them on large-scale datasets with 2D landmark annotations. This limits the generalizability of such approaches to operate on images from unlabeled wild environments. Acknowledging this we propose a novel appearance consensus driven self-supervised objective. To effectively disentangle the foreground (FG) human we rely on image pairs depicting the same person (consistent FG) in varied pose and background (BG) which are obtained from unlabeled wild videos. The proposed FG appearance consistency objective makes use of a novel, differentiable Color-recovery module to obtain vertex colors without the need for any appearance network; via efficient realization of color-picking and reflectional symmetry. We achieve state-of-the-art results on the standard model-based 3D pose estimation benchmarks at comparable supervision levels. Furthermore, the resulting colored mesh prediction opens up the usage of our framework for a variety of appearance-related tasks beyond the pose and shape estimation, thus establishing our superior generalizability.


page 2

page 7

page 10

page 11

page 14

page 17

page 19

page 20


Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis

Camera captured human pose is an outcome of several sources of variation...

TexturePose: Supervising Human Mesh Estimation with Texture Consistency

This work addresses the problem of model-based human pose estimation. Re...

Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view

From an image of a person, we can easily infer the natural 3D pose and s...

A Human Ear Reconstruction Autoencoder

The ear, as an important part of the human head, has received much less ...

Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation

As 3D human pose estimation can now be achieved with very high accuracy ...

HandTailor: Towards High-Precision Monocular 3D Hand Recovery

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

Neural Descent for Visual 3D Human Pose and Shape

We present deep neural network methodology to reconstruct the 3d pose an...

Please sign up or login with your details

Forgot password? Click here to reset