SMPLR: Deep SMPL reverse for 3D human pose and shape recovery

by   Meysam Madadi, et al.

A recent trend in 3D human pose and shape estimation is to use deep learning and statistical morphable body models, such as the parametric Skinned Multi-Person Linear Model (SMPL). However, regardless of the advances in having both body pose and shape, SMPL-based solutions have shown difficulties on achieving accurate predictions. This is due to the unconstrained nature of SMPL, which allows unrealistic poses and shapes, hindering its direct regression or application on the training of deep models. In this paper we propose to embed SMPL within a deep model to efficiently estimate 3D pose and shape from a still RGB image. We use 3D joints as an intermediate representation to regress SMPL parameters which are again recovered as SMPL output. This module can be seen as an autoencoder where encoder is modeled by deep neural networks and decoder is modeled by SMPL. We refer to this procedure as SMPL reverse (SMPLR). Then, input 3D joints can be estimated by any convolutional neural network (CNN). To handle input noise to SMPLR, we propose a denoising autoencoder between CNN and SMPLR which is able to recover structured error. We evaluate our method on SURREAL and Human3.6M datasets showing significant improvement over SMPL-based state-of-the-art alternatives.


page 1

page 3

page 7


Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image

We describe the first method to automatically estimate the 3D pose of th...

DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image

Recovering 3D human body shape and pose from 2D images is a challenging ...

Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling

We present a method for simultaneously estimating 3D human pose and body...

CoreUI: Interactive Core Training System with 3D Human Shape

We present an interactive core training system for core training using a...

Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation

Direct prediction of 3D body pose and shape remains a challenge even for...

TRB: A Novel Triplet Representation for Understanding 2D Human Body

Human pose and shape are two important components of 2D human body. Howe...

IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation

This paper presents an inverse kinematic optimization layer (IKOL) for 3...

Please sign up or login with your details

Forgot password? Click here to reset