{"ID":2836011,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.22488","arxiv_id":"2511.22488","title":"AI killed the video star. Audio-driven diffusion model for expressive talking head generation","abstract":"We propose Dimitra++, a novel framework for audio-driven talking head generation, streamlined to learn lip motion, facial expression, as well as head pose motion. Specifically, we propose a conditional Motion Diffusion Transformer (cMDT) to model facial motion sequences, employing a 3D representation. The cMDT is conditioned on two inputs: a reference facial image, which determines appearance, as well as an audio sequence, which drives the motion. Quantitative and qualitative experiments, as well as a user study on two widely employed datasets, i.e., VoxCeleb2 and CelebV-HQ, suggest that Dimitra++ is able to outperform existing approaches in generating realistic talking heads imparting lip motion, facial expression, and head pose.","short_abstract":"We propose Dimitra++, a novel framework for audio-driven talking head generation, streamlined to learn lip motion, facial expression, as well as head pose motion. Specifically, we propose a conditional Motion Diffusion Transformer (cMDT) to model facial motion sequences, employing a 3D representation. The cMDT is condi...","url_abs":"https://arxiv.org/abs/2511.22488","url_pdf":"https://arxiv.org/pdf/2511.22488v1","authors":"[\"Baptiste Chopin\",\"Tashvik Dhamija\",\"Pranav Balaji\",\"Yaohui Wang\",\"Antitza Dantcheva\"]","published":"2025-11-27T14:24:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}