STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits

• URL: http://arxiv.org/abs/2512.13247v1
• Date: Mon, 15 Dec 2025 11:59:01 GMT
• Title: STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
• Authors: Foivos Paraperas Papantoniou, Stathis Galanakis, Rolandos Alexandros Potamias, Bernhard Kainz, Stefanos Zafeiriou,
• Abstract summary: STARCaster is an identity-aware video diffusion model that addresses both speech-driven portrait animation and free-point-view talking portrait.<n>The model learns from longer temporal contexts than those generated at inference, mitigating the overly static animations common in existing autoregressive approaches.
• Score: 44.82339975771063
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents STARCaster, an identity-aware spatio-temporal video diffusion model that addresses both speech-driven portrait animation and free-viewpoint talking portrait synthesis, given an identity embedding or reference image, within a unified framework. Existing 2D speech-to-video diffusion models depend heavily on reference guidance, leading to limited motion diversity. At the same time, 3D-aware animation typically relies on inversion through pre-trained tri-plane generators, which often leads to imperfect reconstructions and identity drift. We rethink reference- and geometry-based paradigms in two ways. First, we deviate from strict reference conditioning at pre-training by introducing softer identity constraints. Second, we address 3D awareness implicitly within the 2D video domain by leveraging the inherent multi-view nature of video data. STARCaster adopts a compositional approach progressing from ID-aware motion modeling, to audio-visual synchronization via lip reading-based supervision, and finally to novel view animation through temporal-to-spatial adaptation. To overcome the scarcity of 4D audio-visual data, we propose a decoupled learning approach in which view consistency and temporal coherence are trained independently. A self-forcing training scheme enables the model to learn from longer temporal contexts than those generated at inference, mitigating the overly static animations common in existing autoregressive approaches. Comprehensive evaluations demonstrate that STARCaster generalizes effectively across tasks and identities, consistently surpassing prior approaches in different benchmarks.

Related papers

• RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space [51.441415833480505]
  RAYNOVA is a multiview world model for driving scenarios that employs a dual-causal autoregressive framework.<n>It constructs an isotropic-temporal representation across views, frames, and scales based on relative Plcker-ray positional encoding.
  arXiv  Detail & Related papers  (2026-02-24T08:41:40Z)
• UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework [54.337290937468175]
  We propose UniMo, an autoregressive model for joint modeling of 2D human videos and 3D human motions within a unified framework.<n>We show that our method simultaneously generates corresponding videos and motions while performing accurate motion capture.
  arXiv  Detail & Related papers  (2025-12-03T16:03:18Z)
• Stable Video-Driven Portraits [52.008400639227034]
  Animation aims to generate photo-realistic videos from a single source image by reenacting the expression and pose from a driving video.<n>Recent advances using diffusion models have demonstrated improved quality but remain constrained by weak control signals and architectural limitations.<n>We propose a novel diffusion based framework that leverages masked facial regions specifically the eyes, nose, and mouth from the driving video as strong motion control cues.
  arXiv  Detail & Related papers  (2025-09-22T08:11:08Z)
• VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping [43.30061680192465]
  We present the first diffusion-based framework specifically designed for video face swapping.<n>Our approach incorporates a specially designed diffusion model coupled with a VidFaceVAE.<n>Our framework achieves superior performance in identity preservation, temporal consistency, and visual quality compared to existing methods.
  arXiv  Detail & Related papers  (2024-12-15T18:58:32Z)
• Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer [25.39030226963548]
  We introduce the first application of a pretrained transformer-based video generative model for portrait animation.<n>Our method is validated through experiments on benchmark and newly proposed wild datasets.
  arXiv  Detail & Related papers  (2024-12-01T08:54:30Z)
• 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)
• Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation [29.87407471246318]
  This research delves into the complexities of synchronizing facial movements and creating visually appealing, temporally consistent animations. Our innovative approach embraces the end-to-end diffusion paradigm and introduces a hierarchical audio-driven visual synthesis module. The proposed hierarchical audio-driven visual synthesis offers adaptive control over expression and pose diversity, enabling more effective personalization tailored to different identities.
  arXiv  Detail & Related papers  (2024-06-13T04:33:20Z)
• MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model [74.84435399451573]
  This paper studies the human image animation task, which aims to generate a video of a certain reference identity following a particular motion sequence. Existing animation works typically employ the frame-warping technique to animate the reference image towards the target motion. We introduce MagicAnimate, a diffusion-based framework that aims at enhancing temporal consistency, preserving reference image faithfully, and improving animation fidelity.
  arXiv  Detail & Related papers  (2023-11-27T18:32:31Z)
• Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips [38.02945794078731]
  We tackle the task of reconstructing hand-object interactions from short video clips. Our approach casts 3D inference as a per-video optimization and recovers a neural 3D representation of the object shape. We empirically evaluate our approach on egocentric videos, and observe significant improvements over prior single-view and multi-view methods.
  arXiv  Detail & Related papers  (2023-09-11T17:58:30Z)
• LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization [4.43316916502814]
  We present a video-based learning framework for animating personalized 3D talking faces from audio. We introduce two training-time data normalizations that significantly improve data sample efficiency. Our method outperforms contemporary state-of-the-art audio-driven video reenactment benchmarks in terms of realism, lip-sync and visual quality scores.
  arXiv  Detail & Related papers  (2021-06-08T08:56:40Z)
• GTA: Global Temporal Attention for Video Action Understanding [51.476605514802806]
  We introduce Global Temporal Attention (AGT), which performs global temporal attention on top of spatial attention in a decoupled manner. Tests on 2D and 3D networks demonstrate that our approach consistently enhances temporal modeling and provides state-of-the-art performance on three video action recognition datasets.
  arXiv  Detail & Related papers  (2020-12-15T18:58:21Z)

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.