Metraipolis › archive › dc_abfd72daa4cc

ResDiffFRG: Residual Diffusion for Multiple Appropriate Facial Reaction Generation — arXiv:2609.33749

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.33749
License (as archived): CC0-1.0
Archived: 2026-10-07T22:37:45.671Z
SHA-256 of the archived text: 2a566b37c84c44b2a2fc9f968c912441e845b60eb0a763457002135fb4f3816f
Stable URL of this page: https://metraipolis.com/documento/dc_abfd72daa4cc

How to cite

ResDiffFRG: Residual Diffusion for Multiple Appropriate Facial Reaction Generation — arXiv:2609.33749 — arXiv (en), https://arxiv.org/abs/2609.33749 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_abfd72daa4cc (Metraipolis archive dc_abfd72daa4cc, sha256 2a566b37c84c44b2a2fc9f968c912441e845b60eb0a763457002135fb4f3816f)

BibTeX

@misc{dcabfd72daa4cc,
  title = {ResDiffFRG: Residual Diffusion for Multiple Appropriate Facial Reaction Generation — arXiv:2609.33749},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33749},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_abfd72daa4cc; sha256 2a566b37c84c44b2a2fc9f968c912441e845b60eb0a763457002135fb4f3816f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33749. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In dyadic human speaker-listener conversations, the listener's facial reactions allows the speaker to accurately perceive the listener's emotional states. Since human facial reactions are non-deterministic, the ability to generate multiple appropriate human-like facial reactions is crucial for realistic human-agent interactions. Although diffusion models are naturally suited to such one-to-many generation, existing diffusion-based Multiple Appropriate Facial Reaction Generation (MAFRG) methods attempt to denoise random Gaussian initialisations directly into multiple appropriate facial reactions (AFRs). These random initialisations are usually not well-aligned with the target listener facial reaction, which requires complex denoising trajectories from these initialisations, and subsequently creates substantial opportunities for deviations away from the range of trajectories leading to appropriate AFRs. Given the inherent mimicry between the human listener's and speaker's facial behaviours, we address the above denoising trajectory issue by leveraging this strong prior. Specifically, we propose ResDiffFRG, a novel diffusion-based MAFRG framework that explicitly anchors the diffusion process to the speaker behaviour by defining its diffusion target as the residual between the speaker anchor and an AFR. The denoiser only needs to model the comparatively small, reaction-specific residual needed to transform this anchor into an AFR, rather than reconstructing the complete reaction from an unstructured state. Extensive experiments show that ResDiffFRG achieves large improvements in correlation-based appropriateness over existing methods. Our denoising trajectory analysis showed that even at the start of the denoising trajectory, ResDiffFRG already achieves a higher facial-reaction correlation score than the Gaussian Diffusion baseline does after completing 60% of its denoising trajectory.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.33749 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:28.036Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).