EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions
This work improves portrait animation for applications like virtual avatars or video synthesis, though it appears incremental by combining existing inputs rather than introducing a new paradigm.
The paper tackles the problem of generating lifelike portrait animations from audio by addressing instability from audio-only methods and unnatural outcomes from keypoint-only methods, introducing EchoMimic which combines both inputs and shows superior performance in evaluations.
The area of portrait image animation, propelled by audio input, has witnessed notable progress in the generation of lifelike and dynamic portraits. Conventional methods are limited to utilizing either audios or facial key points to drive images into videos, while they can yield satisfactory results, certain issues exist. For instance, methods driven solely by audios can be unstable at times due to the relatively weaker audio signal, while methods driven exclusively by facial key points, although more stable in driving, can result in unnatural outcomes due to the excessive control of key point information. In addressing the previously mentioned challenges, in this paper, we introduce a novel approach which we named EchoMimic. EchoMimic is concurrently trained using both audios and facial landmarks. Through the implementation of a novel training strategy, EchoMimic is capable of generating portrait videos not only by audios and facial landmarks individually, but also by a combination of both audios and selected facial landmarks. EchoMimic has been comprehensively compared with alternative algorithms across various public datasets and our collected dataset, showcasing superior performance in both quantitative and qualitative evaluations. Additional visualization and access to the source code can be located on the EchoMimic project page.