DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis

• URL: http://arxiv.org/abs/2409.10281v1
• Date: Mon, 16 Sep 2024 13:44:20 GMT
• Title: DreamHead: Learning Spatial-Temporal Correspondence via Hierarchical Diffusion for Audio-driven Talking Head Synthesis
• Authors: Fa-Ting Hong, Yunfei Liu, Yu Li, Changyin Zhou, Fei Yu, Dan Xu,
• Abstract summary: We present DreamHead, a hierarchical diffusion framework that learns spatial-temporal correspondences in talking head synthesis. Specifically, a first hierarchy of audio-to-landmark diffusion is first designed to predict temporally smooth and accurate landmark sequences. A second hierarchy of landmark-to-image diffusion is further proposed to produce spatially consistent facial portrait videos.
• Score: 29.481693585636318
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Audio-driven talking head synthesis strives to generate lifelike video portraits from provided audio. The diffusion model, recognized for its superior quality and robust generalization, has been explored for this task. However, establishing a robust correspondence between temporal audio cues and corresponding spatial facial expressions with diffusion models remains a significant challenge in talking head generation. To bridge this gap, we present DreamHead, a hierarchical diffusion framework that learns spatial-temporal correspondences in talking head synthesis without compromising the model's intrinsic quality and adaptability.~DreamHead learns to predict dense facial landmarks from audios as intermediate signals to model the spatial and temporal correspondences.~Specifically, a first hierarchy of audio-to-landmark diffusion is first designed to predict temporally smooth and accurate landmark sequences given audio sequence signals. Then, a second hierarchy of landmark-to-image diffusion is further proposed to produce spatially consistent facial portrait videos, by modeling spatial correspondences between the dense facial landmark and appearance. Extensive experiments show that proposed DreamHead can effectively learn spatial-temporal consistency with the designed hierarchical diffusion and produce high-fidelity audio-driven talking head videos for multiple identities.

Related papers

• Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation [32.24603883810094]
  Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models. We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions even including moving and multiple sources. By leveraging spatial guidance, our unified model achieves the objective of generating immersive and controllable spatial audio from text and image.
  arXiv  Detail & Related papers  (2024-10-14T16:18:29Z)
• S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis [14.437741528053504]
  We design a Single-Shot Speech-Driven Radiance Field (S3D-NeRF) method to tackle the three difficulties: learning a representative appearance feature for each identity, modeling motion of different face regions with audio, and keeping the temporal consistency of the lip area. Our S3D-NeRF surpasses previous arts on both video fidelity and audio-lip synchronization.
  arXiv  Detail & Related papers  (2024-08-18T03:59:57Z)
• High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model [89.29655924125461]
  We propose a novel landmark-based diffusion model for talking face generation. We first establish the less ambiguous mapping from audio to landmark motion of lip and jaw. Then, we introduce an innovative conditioning module called TalkFormer to align the synthesized motion with the motion represented by landmarks.
  arXiv  Detail & Related papers  (2024-08-10T02:58:28Z)
• Landmark-guided Diffusion Model for High-fidelity and Temporally Coherent Talking Head Generation [22.159117464397806]
  We introduce a two-stage diffusion-based model for talking head generation. The first stage involves generating synchronized facial landmarks based on the given speech. In the second stage, these generated landmarks serve as a condition in the denoising process, aiming to optimize mouth jitter issues and generate high-fidelity, well-synchronized, and temporally coherent talking head videos.
  arXiv  Detail & Related papers  (2024-08-03T10:19:38Z)
• FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models [85.16273912625022]
  We introduce FaceTalk, a novel generative approach designed for synthesizing high-fidelity 3D motion sequences of talking human heads from audio signal. To the best of our knowledge, this is the first work to propose a generative approach for realistic and high-quality motion synthesis of human heads.
  arXiv  Detail & Related papers  (2023-12-13T19:01:07Z)
• A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation [0.0]
  We propose a multi-scale audio-visual synchrony loss and a multi-scale autoregressive GAN to better handle short and long-term correlation between speech and head motion. Our generator operates in the facial landmark domain, which is a standard low-dimensional head representation.
  arXiv  Detail & Related papers  (2023-07-04T08:29:59Z)
• DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation [78.08004432704826]
  We model the Talking head generation as an audio-driven temporally coherent denoising process (DiffTalk) In this paper, we investigate the control mechanism of the talking face, and incorporate reference face images and landmarks as conditions for personality-aware generalized synthesis. Our DiffTalk can be gracefully tailored for higher-resolution synthesis with negligible extra computational cost.
  arXiv  Detail & Related papers  (2023-01-10T05:11:25Z)
• BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis [129.86743102915986]
  We formulate the synthesis process from a different perspective by decomposing the audio into a common part. We propose BinauralGrad, a novel two-stage framework equipped with diffusion models to synthesize them respectively. Experiment results show that BinauralGrad outperforms the existing baselines by a large margin in terms of both object and subject evaluation metrics.
  arXiv  Detail & Related papers  (2022-05-30T02:09:26Z)
• AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis [55.24336227884039]
  We present a novel framework to generate high-fidelity talking head video. We use neural scene representation networks to bridge the gap between audio input and video output. Our framework can (1) produce high-fidelity and natural results, and (2) support free adjustment of audio signals, viewing directions, and background images.
  arXiv  Detail & Related papers  (2021-03-20T02:58:13Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

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.