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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Chaoyi, Yang, Yifan, Pei, Jun, Xia, Lijie, Liu, Jianpo, Yuan, Xiaobing, Di, Xinhan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918123840471040
author Wang, Chaoyi
Yang, Yifan
Pei, Jun
Xia, Lijie
Liu, Jianpo
Yuan, Xiaobing
Di, Xinhan
author_facet Wang, Chaoyi
Yang, Yifan
Pei, Jun
Xia, Lijie
Liu, Jianpo
Yuan, Xiaobing
Di, Xinhan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08891
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos
Wang, Chaoyi
Yang, Yifan
Pei, Jun
Xia, Lijie
Liu, Jianpo
Yuan, Xiaobing
Di, Xinhan
Computer Vision and Pattern Recognition
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.
title Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.08891