EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
Authors:
Top Cited Papers
- 10 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5489-5498
Abstract
Recent work on human animation usually involves audio, pose, or movement maps conditions, thereby achieves vivid animation quality. However, these methods often face practical challenges due to extra control conditions, cumbersome condition injection modules, or limitation to head region driving. Hence, we ask if it is possible to achieve striking half-body human animation while simplifying unnecessary conditions. To this end, we propose a half-body human animation method, dubbed EchoMimicV2, that leverages a novel Audio-Pose Dynamic Harmonization strategy, including Pose Sampling and Audio Diffusion, to enhance half-body details, facial and gestural expressiveness, and meanwhile reduce conditions redundancy. To compensate for the scarcity of half-body data, we utilize Head Partial Attention to seamlessly accommodate headshot data into our training framework, which can be omitted during inference, providing a free lunch for animation. Furthermore, we design the Phase-specific Denoising Loss to guide motion, detail, and low-level quality for animation in specific phases, respectively. Besides, we also present a novel benchmark for evaluating the effectiveness of half-body human animation. Extensive experiments and analyses demonstrate that EchoMimicV2 surpasses existing methods in both quantitative and qualitative evaluations.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance2024
- EMO: Emote Portrait Alive Generating Expressive Portrait Videos with Audio2Video Diffusion Model Under Weak Conditions2024
- SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation2023
- Attention Diversification for Domain Generalization2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Slimmable Domain Adaptation2022
- DensePose: Dense Human Pose Estimation in the Wild2018
- Real-time human gesture grading based on OpenPose2017
- Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image2016
- Deep Residual Learning for Image Recognition2016