SMPLpix: Neural Avatars from 3D Human Models

TL;DR

This paper introduces SMPLpix, a neural network that generates photorealistic human images directly from 3D human models, improving realism and efficiency over traditional rendering methods.

Contribution

It presents a novel approach that bypasses traditional rasterization by directly converting 3D mesh vertices into realistic images using deep learning.

Findings

Outperforms traditional differentiable renderers in realism

Achieves higher rendering efficiency

Trained on large datasets of 3D models and photos

Abstract

Recent advances in deep generative models have led to an unprecedented level of realism for synthetically generated images of humans. However, one of the remaining fundamental limitations of these models is the ability to flexibly control the generative process, e.g.~change the camera and human pose while retaining the subject identity. At the same time, deformable human body models like SMPL and its successors provide full control over pose and shape but rely on classic computer graphics pipelines for rendering. Such rendering pipelines require explicit mesh rasterization that (a) does not have the potential to fix artifacts or lack of realism in the original 3D geometry and (b) until recently, were not fully incorporated into deep learning frameworks. In this work, we propose to bridge the gap between classic geometry-based rendering and the latest generative networks operating in pixel space. We train a network that directly converts a sparse set of 3D mesh vertices into photorealistic images, alleviating the need for traditional rasterization mechanism. We train our model on a large corpus of human 3D models and corresponding real photos, and show the advantage over conventional differentiable renderers both in terms of the level of photorealism and rendering efficiency.