SMPLX-Lite: A Realistic and Drivable Avatar Benchmark with Rich Geometry and Texture Annotations

TL;DR

This paper introduces SMPLX-Lite-D, a detailed parametric human body model, and a comprehensive dataset enabling the generation of photorealistic, drivable avatars for virtual applications.

Contribution

The paper presents a new detailed parametric body model and a large multi-view dataset, facilitating the creation of realistic, controllable avatars for virtual reality and related fields.

Findings

The SMPLX-Lite-D model fits detailed geometry of scanned meshes.

The dataset includes multi-view RGB sequences, keypoints, and textured meshes.

A VAE-based method generates photorealistic avatars from pose and keypoints.

Abstract

Recovering photorealistic and drivable full-body avatars is crucial for numerous applications, including virtual reality, 3D games, and tele-presence. Most methods, whether reconstruction or generation, require large numbers of human motion sequences and corresponding textured meshes. To easily learn a drivable avatar, a reasonable parametric body model with unified topology is paramount. However, existing human body datasets either have images or textured models and lack parametric models which fit clothes well. We propose a new parametric model SMPLX-Lite-D, which can fit detailed geometry of the scanned mesh while maintaining stable geometry in the face, hand and foot regions. We present SMPLX-Lite dataset, the most comprehensive clothing avatar dataset with multi-view RGB sequences, keypoints annotations, textured scanned meshes, and textured SMPLX-Lite-D models. With the SMPLX-Lite dataset, we train a conditional variational autoencoder model that takes human pose and facial keypoints as input, and generates a photorealistic drivable human avatar.