Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 12 Aug 2025.
Builds on
32 of 39 references.
References · 32
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
- 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
- 2022Video Diffusion Modelscited by 2,305
- 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
- 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
- 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
- 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
- 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
- 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
20 more
- 2020A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wildcited by 672
- 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Modelscited by 350
- 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
- 2021Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representationcited by 288
- 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 180
- 2025Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200kcited by 163
- 2023Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generationcited by 142
- 2024Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformercited by 122
- 2024Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependencycited by 102
- 2024Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animationcited by 97
- 2023StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generatorcited by 89
- 2024StableAnimator: High-Quality Identity-Preserving Human Image Animationcited by 88
- 2024EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagationcited by 77
- 2023VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generationcited by 74
- 2024EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animationcited by 72
- 2024Sonic: Shifting Focus to Global Audio Perception in Portrait Animationcited by 72
- 2025SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformerscited by 33
- 2025Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Modelcited by 28
- 2022StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generationcited by 14
- 2025Dimitra: Audio-driven Diffusion model for Expressive Talking Head Generationcited by 4
Built on by
Not cited yet.