Talking Together: Synthesizing Co-Located 3D Conversations from Audio

• URL: http://arxiv.org/abs/2603.08674v1
• Date: Mon, 09 Mar 2026 17:46:52 GMT
• Title: Talking Together: Synthesizing Co-Located 3D Conversations from Audio
• Abstract summary: We tackle the challenging task of generating complete 3D facial animations for two interacting, co-located participants from a mixed audio stream.<n>Our work is the first to explicitly model the dynamic 3D spatial relationship that is crucial for realistic in-person dialogues.<n>Our method generates fluid, controllable, and spatially aware dyadic animations suitable for immersive applications in VR and telepresence.
• Score: 21.481529577056904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We tackle the challenging task of generating complete 3D facial animations for two interacting, co-located participants from a mixed audio stream. While existing methods often produce disembodied "talking heads" akin to a video conference call, our work is the first to explicitly model the dynamic 3D spatial relationship -- including relative position, orientation, and mutual gaze -- that is crucial for realistic in-person dialogues. Our system synthesizes the full performance of both individuals, including precise lip-sync, and uniquely allows their relative head poses to be controlled via textual descriptions. To achieve this, we propose a dual-stream architecture where each stream is responsible for one participant's output. We employ speaker's role embeddings and inter-speaker cross-attention mechanisms designed to disentangle the mixed audio and model the interaction. Furthermore, we introduce a novel eye gaze loss to promote natural, mutual eye contact. To power our data-hungry approach, we introduce a novel pipeline to curate a large-scale conversational dataset consisting of over 2 million dyadic pairs from in-the-wild videos. Our method generates fluid, controllable, and spatially aware dyadic animations suitable for immersive applications in VR and telepresence, significantly outperforming existing baselines in perceived realism and interaction coherence.

Related papers

• DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction [41.29236046858134]
  To capture continuous reciprocal human communication, this model simultaneously generate and generate both speech and speech physical motion in a streaming fashion.<n>By introducing a unified dyadic token interleaving mechanism and guiding cross-attention, our model effectively aligns autoremotion with latent rich speech features.<n>Our model effectively captures cross-attention dependencies and establishes new state-of-the-art performance across both monadic and dyadic human interaction benchmarks.
  arXiv  Detail & Related papers  (2026-06-02T16:42:56Z)
• TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation [72.46711449668814]
  We introduce TAVID, a unified framework that generates both interactive faces and conversational speech in a synchronized manner.<n>We evaluate our system across four dimensions: talking face realism, listening head responsiveness, dyadic interaction, and speech quality.
  arXiv  Detail & Related papers  (2025-12-23T12:04:23Z)
• MoReact: Generating Reactive Motion from Textual Descriptions [57.642436102978245]
  MoReact is a diffusion-based method designed to disentangle the generation of global trajectories and local motions sequentially.<n>Our experiments, utilizing data adapted from a two-person motion dataset, demonstrate the efficacy of our approach.
  arXiv  Detail & Related papers  (2025-09-28T14:31:41Z)
• HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception [57.37135310143126]
  HO SIG is a novel framework for synthesizing full-body interactions through hierarchical scene perception.<n>Our framework supports unlimited motion length through autoregressive generation and requires minimal manual intervention.<n>This work bridges the critical gap between scene-aware navigation and dexterous object manipulation.
  arXiv  Detail & Related papers  (2025-06-02T12:08:08Z)
• AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars [71.90109867684025]
  Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans.<n>We propose AsynFusion, a novel framework that leverages diffusion transformers to achieve cohesive expression and gesture synthesis.<n>AsynFusion achieves state-of-the-art performance in generating real-time, synchronized whole-body animations.
  arXiv  Detail & Related papers  (2025-05-21T03:28:53Z)
• GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expression [33.886734972316326]
  GoHD is a framework designed to produce highly realistic, expressive, and controllable portrait videos from any reference identity with any motion.<n>An animation module utilizing latent navigation is introduced to improve the generalization ability across unseen input styles.<n>A conformer-structured conditional diffusion model is designed to guarantee head poses that are aware of prosody.<n>A two-stage training strategy is devised to decouple frequent and frame-wise lip motion distillation from the generation of other more temporally dependent but less audio-related motions.
  arXiv  Detail & Related papers  (2024-12-12T14:12:07Z)
• It Takes Two: Real-time Co-Speech Two-person's Interaction Generation via Reactive Auto-regressive Diffusion Model [34.94330722832987]
  We introduce an audio-driven, auto-regressive system designed to synthesize dynamic movements for two characters during a conversation.<n>To the best of our knowledge, this is the first system capable of generating interactive full-body motions for two characters from speech in an online manner.
  arXiv  Detail & Related papers  (2024-12-03T12:31:44Z)
• Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication [17.294279444027563]
  We introduce an innovative task focused on human communication, aiming to generate 3D holistic human motions for both speakers and listeners. We consider the real-time mutual influence between the speaker and the listener and propose a novel chain-like transformer-based auto-regressive model. Our approach demonstrates state-of-the-art performance on two benchmark datasets.
  arXiv  Detail & Related papers  (2024-03-28T14:47:32Z)
• 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)
• ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions [66.87211993793807]
  We present ReMoS, a denoising diffusion based model that synthesizes full body motion of a person in two person interaction scenario. We demonstrate ReMoS across challenging two person scenarios such as pair dancing, Ninjutsu, kickboxing, and acrobatics. We also contribute the ReMoCap dataset for two person interactions containing full body and finger motions.
  arXiv  Detail & Related papers  (2023-11-28T18:59:52Z)
• DualTalker: A Cross-Modal Dual Learning Approach for Speech-Driven 3D Facial Animation [10.73030153404956]
  We propose a cross-modal dual-learning framework, termed DualTalker, to improve data usage efficiency. The framework is trained jointly with the primary task (audio-driven facial animation) and its dual task (lip reading) and shares common audio/motion encoder components. Our approach outperforms current state-of-the-art methods both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2023-11-08T15:39:56Z)
• Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion [89.01668641930206]
  We present a framework for modeling interactional communication in dyadic conversations. We autoregressively output multiple possibilities of corresponding listener motion. Our method organically captures the multimodal and non-deterministic nature of nonverbal dyadic interactions.
  arXiv  Detail & Related papers  (2022-04-18T17:58:04Z)

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.