CoCoGesture: Toward Coherent Co-speech 3D Gesture Generation in the Wild

• URL: http://arxiv.org/abs/2405.16874v1
• Date: Mon, 27 May 2024 06:47:14 GMT
• Title: CoCoGesture: Toward Coherent Co-speech 3D Gesture Generation in the Wild
• Authors: Xingqun Qi, Hengyuan Zhang, Yatian Wang, Jiahao Pan, Chen Liu, Peng Li, Xiaowei Chi, Mengfei Li, Qixun Zhang, Wei Xue, Shanghang Zhang, Wenhan Luo, Qifeng Liu, Yike Guo,
• Abstract summary: CoCoGesture is a novel framework enabling vivid and diverse gesture synthesis from unseen human speech prompts. Our key insight is built upon the custom-designed pretrain-fintune training paradigm. Our proposed CoCoGesture outperforms the state-of-the-art methods on the zero-shot speech-to-gesture generation.
• Score: 44.401536230814465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deriving co-speech 3D gestures has seen tremendous progress in virtual avatar animation. Yet, the existing methods often produce stiff and unreasonable gestures with unseen human speech inputs due to the limited 3D speech-gesture data. In this paper, we propose CoCoGesture, a novel framework enabling vivid and diverse gesture synthesis from unseen human speech prompts. Our key insight is built upon the custom-designed pretrain-fintune training paradigm. At the pretraining stage, we aim to formulate a large generalizable gesture diffusion model by learning the abundant postures manifold. Therefore, to alleviate the scarcity of 3D data, we first construct a large-scale co-speech 3D gesture dataset containing more than 40M meshed posture instances across 4.3K speakers, dubbed GES-X. Then, we scale up the large unconditional diffusion model to 1B parameters and pre-train it to be our gesture experts. At the finetune stage, we present the audio ControlNet that incorporates the human voice as condition prompts to guide the gesture generation. Here, we construct the audio ControlNet through a trainable copy of our pre-trained diffusion model. Moreover, we design a novel Mixture-of-Gesture-Experts (MoGE) block to adaptively fuse the audio embedding from the human speech and the gesture features from the pre-trained gesture experts with a routing mechanism. Such an effective manner ensures audio embedding is temporal coordinated with motion features while preserving the vivid and diverse gesture generation. Extensive experiments demonstrate that our proposed CoCoGesture outperforms the state-of-the-art methods on the zero-shot speech-to-gesture generation. The dataset will be publicly available at: https://mattie-e.github.io/GES-X/

Related papers

• EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling [57.08286593059137]
  We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures. We first introduce BEAT2 (BEAT-SMPLX-FLAME), a new mesh-level holistic co-speech dataset. Experiments demonstrate that EMAGE generates holistic gestures with state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-12-31T02:25:41Z)
• Generating Holistic 3D Human Motion from Speech [97.11392166257791]
  We build a high-quality dataset of 3D holistic body meshes with synchronous speech. We then define a novel speech-to-motion generation framework in which the face, body, and hands are modeled separately.
  arXiv  Detail & Related papers  (2022-12-08T17:25:19Z)
• Audio-Driven Co-Speech Gesture Video Generation [92.15661971086746]
  We define and study this challenging problem of audio-driven co-speech gesture video generation. Our key insight is that the co-speech gestures can be decomposed into common motion patterns and subtle rhythmic dynamics. We propose a novel framework, Audio-driveN Gesture vIdeo gEneration (ANGIE), to effectively capture the reusable co-speech gesture patterns.
  arXiv  Detail & Related papers  (2022-12-05T15:28:22Z)
• Real-time Gesture Animation Generation from Speech for Virtual Human Interaction [9.453554184019108]
  We propose a real-time system for synthesizing gestures directly from speech. Our data-driven approach is based on Generative Adversarial Neural Networks. Model generates speaker-specific gestures by taking consecutive audio input chunks of two seconds in length.
  arXiv  Detail & Related papers  (2022-08-05T15:56:34Z)
• Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation [107.10239561664496]
  We propose a novel framework named Hierarchical Audio-to-Gesture (HA2G) for co-speech gesture generation. The proposed method renders realistic co-speech gestures and outperforms previous methods in a clear margin.
  arXiv  Detail & Related papers  (2022-03-24T16:33:29Z)
• Learning Speech-driven 3D Conversational Gestures from Video [106.15628979352738]
  We propose the first approach to automatically and jointly synthesize both the synchronous 3D conversational body and hand gestures. Our algorithm uses a CNN architecture that leverages the inherent correlation between facial expression and hand gestures. We also contribute a new way to create a large corpus of more than 33 hours of annotated body, hand, and face data from in-the-wild videos of talking people.
  arXiv  Detail & Related papers  (2021-02-13T01:05:39Z)
• Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity [21.61168067832304]
  We present an automatic gesture generation model that uses the multimodal context of speech text, audio, and speaker identity to reliably generate gestures. Experiments with the introduced metric and subjective human evaluation showed that the proposed gesture generation model is better than existing end-to-end generation models.
  arXiv  Detail & Related papers  (2020-09-04T11:42:45Z)
• Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses [36.00309828380724]
  We propose a novel approach to convert given speech audio to a photo-realistic speaking video of a specific person. We achieve this by first generating 3D skeleton movements from the audio sequence using a recurrent neural network (RNN) To make the skeleton movement realistic and expressive, we embed the knowledge of an articulated 3D human skeleton and a learned dictionary of personal speech iconic gestures into the generation process.
  arXiv  Detail & Related papers  (2020-07-17T19:30:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.