Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos

TL;DR

This paper introduces WB-DH, a comprehensive benchmark dataset for evaluating the generation of realistic, fully animatable whole-body avatars from single portraits, addressing current limitations in capturing expressions and movements.

Contribution

The paper presents WB-DH, a new multi-modal benchmark dataset with detailed annotations and evaluation tools for advancing whole-body avatar generation research.

Findings

Provides a versatile evaluation framework.

Includes detailed multi-modal annotations.

Offers open-source dataset and tools.

Abstract

Creating realistic, fully animatable whole-body avatars from a single portrait is challenging due to limitations in capturing subtle expressions, body movements, and dynamic backgrounds. Current evaluation datasets and metrics fall short in addressing these complexities. To bridge this gap, we introduce the Whole-Body Benchmark Dataset (WB-DH), an open-source, multi-modal benchmark designed for evaluating whole-body animatable avatar generation. Key features include: (1) detailed multi-modal annotations for fine-grained guidance, (2) a versatile evaluation framework, and (3) public access to the dataset and tools at https://github.com/deepreasonings/WholeBodyBenchmark.