Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

• URL: http://arxiv.org/abs/2411.19509v2
• Date: Mon, 23 Dec 2024 14:04:09 GMT
• Title: Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis
• Authors: Tianqi Li, Ruobing Zheng, Minghui Yang, Jingdong Chen, Ming Yang,
• Abstract summary: We introduce Ditto, a diffusion-based framework that enables controllable realtime talking head synthesis.<n>Our key innovation lies in bridging motion generation and photorealistic neural rendering through an explicit identity-agnostic motion space.<n>This design substantially reduces the complexity of diffusion learning while enabling precise control over the synthesized talking heads.
• Score: 27.43583075023949
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in diffusion models have revolutionized audio-driven talking head synthesis. Beyond precise lip synchronization, diffusion-based methods excel in generating subtle expressions and natural head movements that are well-aligned with the audio signal. However, these methods are confronted by slow inference speed, insufficient fine-grained control over facial motions, and occasional visual artifacts largely due to an implicit latent space derived from Variational Auto-Encoders (VAE), which prevent their adoption in realtime interaction applications. To address these issues, we introduce Ditto, a diffusion-based framework that enables controllable realtime talking head synthesis. Our key innovation lies in bridging motion generation and photorealistic neural rendering through an explicit identity-agnostic motion space, replacing conventional VAE representations. This design substantially reduces the complexity of diffusion learning while enabling precise control over the synthesized talking heads. We further propose an inference strategy that jointly optimizes three key components: audio feature extraction, motion generation, and video synthesis. This optimization enables streaming processing, realtime inference, and low first-frame delay, which are the functionalities crucial for interactive applications such as AI assistants. Extensive experimental results demonstrate that Ditto generates compelling talking head videos and substantially outperforms existing methods in both motion control and realtime performance.

Related papers

• JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation [13.168628936598367]
  JointTuner is a novel adaptive joint training framework. We develop Adaptive LoRA, which incorporates a context-aware gating mechanism. Appearance-independent Temporal Loss is introduced to decouple motion patterns from intrinsic appearance.
  arXiv  Detail & Related papers  (2025-03-31T11:04:07Z)
• HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech Gestures [8.50717565369252]
  HoleGest is a novel neural network framework for automatic generation of high-quality, expressive co-speech gestures. Our system learns a robust prior with low audio dependency and high motion reliance, enabling stable global motion and detailed finger movements. Our model achieves a level of realism close to the ground truth, providing an immersive user experience.
  arXiv  Detail & Related papers  (2025-03-17T14:42:31Z)
• Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformer [24.166147954731652]
  Multi-person interactive motion generation is a critical yet under-explored domain in computer character animation. Current research often employs separate module branches for individual motions, leading to a loss of interaction information. We propose a novel, unified approach that models multi-person motions and their interactions within a single latent space.
  arXiv  Detail & Related papers  (2024-12-21T15:35:50Z)
• KMTalk: Speech-Driven 3D Facial Animation with Key Motion Embedding [19.15471840100407]
  We present a novel approach for synthesizing 3D facial motions from audio sequences using key motion embeddings. Our method integrates linguistic and data-driven priors through two modules: the linguistic-based key motion acquisition and the cross-modal motion completion. The latter extends key motions into a full sequence of 3D talking faces guided by audio features, improving temporal coherence and audio-visual consistency.
  arXiv  Detail & Related papers  (2024-09-02T09:41:24Z)
• GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformer [26.567649613966974]
  This paper introduces GLDiTalker, a novel speech-driven 3D facial animation model that employs a Graph Latent Diffusion Transformer. The core idea behind GLDiTalker is that the audio-mesh modality misalignment can be resolved by diffusing the signal in a latent quantilized spatial-temporal space.
  arXiv  Detail & Related papers  (2024-08-03T17:18:26Z)
• Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model [17.98911328064481]
  Co-speech gestures can achieve superior visual effects in human-machine interaction. We present a novel motion-decoupled framework to generate co-speech gesture videos. Our proposed framework significantly outperforms existing approaches in both motion and video-related evaluations.
  arXiv  Detail & Related papers  (2024-04-02T11:40:34Z)
• DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer [110.32147183360843]
  Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for this task. We present DiffSpeaker, a Transformer-based network equipped with novel biased conditional attention modules.
  arXiv  Detail & Related papers  (2024-02-08T14:39:16Z)
• 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)
• DiffusionPhase: Motion Diffusion in Frequency Domain [69.811762407278]
  We introduce a learning-based method for generating high-quality human motion sequences from text descriptions. Existing techniques struggle with motion diversity and smooth transitions in generating arbitrary-length motion sequences. We develop a network encoder that converts the motion space into a compact yet expressive parameterized phase space.
  arXiv  Detail & Related papers  (2023-12-07T04:39:22Z)
• TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models [75.20168902300166]
  We propose TrackDiffusion, a novel video generation framework affording fine-grained trajectory-conditioned motion control. A pivotal component of TrackDiffusion is the instance enhancer, which explicitly ensures inter-frame consistency of multiple objects. generated video sequences by our TrackDiffusion can be used as training data for visual perception models.
  arXiv  Detail & Related papers  (2023-12-01T15:24:38Z)
• LEO: Generative Latent Image Animator for Human Video Synthesis [38.99490968487773]
  We propose a novel framework for human video synthesis, placing emphasis on synthesizing-temporal coherency. Our key idea is to represent motion as a sequence of flow maps in the generation process, which inherently isolate motion from appearance. We implement this idea via a flow-based image animator and a Latent Motion Diffusion Model (LMDM)
  arXiv  Detail & Related papers  (2023-05-06T09:29:12Z)
• Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models [18.50942770933098]
  MoDiff is an autoregressive probabilistic diffusion model over motion sequences conditioned on control contexts of other modalities. Our model integrates a cross-modal Transformer encoder and a Transformer-based decoder, which are found effective in capturing temporal correlations in motion and control modalities.
  arXiv  Detail & Related papers  (2023-04-03T08:17:08Z)
• Interactive Face Video Coding: A Generative Compression Framework [18.26476468644723]
  We propose a novel framework for Interactive Face Video Coding (IFVC), which allows humans to interact with the intrinsic visual representations instead of the signals. The proposed solution enjoys several distinct advantages, including ultra-compact representation, low delay interaction, and vivid expression and headpose animation.
  arXiv  Detail & Related papers  (2023-02-20T11:24:23Z)
• MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis [73.52948992990191]
  MoFusion is a new denoising-diffusion-based framework for high-quality conditional human motion synthesis. We present ways to introduce well-known kinematic losses for motion plausibility within the motion diffusion framework. We demonstrate the effectiveness of MoFusion compared to the state of the art on established benchmarks in the literature.
  arXiv  Detail & Related papers  (2022-12-08T18:59:48Z)
• Executing your Commands via Motion Diffusion in Latent Space [51.64652463205012]
  We propose a Motion Latent-based Diffusion model (MLD) to produce vivid motion sequences conforming to the given conditional inputs. Our MLD achieves significant improvements over the state-of-the-art methods among extensive human motion generation tasks.
  arXiv  Detail & Related papers  (2022-12-08T03:07:00Z)
• Text-driven Video Prediction [83.04845684117835]
  We propose a new task called Text-driven Video Prediction (TVP) Taking the first frame and text caption as inputs, this task aims to synthesize the following frames. To investigate the capability of text in causal inference for progressive motion information, our TVP framework contains a Text Inference Module (TIM)
  arXiv  Detail & Related papers  (2022-10-06T12:43:07Z)
• 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.