InteractGesture is a model‑agnostic, inference‑time method that enables fine‑grained spatial control of individual joints in continuous streaming co‑speech gesture generation. It guides diffusion sampler latent estimates through a differentiable RVQ‑VAE decoder, backpropagating spatial control gradients to adjust motion latents during sampling. To address chunk‑wise dependency issues in streaming generation, the method introduces Progressive Chunk Guidance, a chunk‑window strategy that keeps an active set of editable chunk latents with staggered delays, allowing spatial constraints to propagate gradients backward across chunk boundaries and reducing boundary inconsistencies.
By Ekkasit Pinyoanuntapong, Ajinkya Deogade, Paul Streli, Wenjing Zhang, Joanna Materzynska, Pu Wang, Vittorio Ferrari, Jie Shen
Vorch-Human is a unified framework for human‑centric audio‑visual generation that handles multiple tasks—animating a person from speech, jointly generating speech and video from a voice reference, and synthesizing a scene from paired appearance and voice references—using a single dual‑stream audio‑video diffusion transformer. The model incorporates clean condition‑audio and condition‑video tokens, per‑token task embeddings, temporal position types, condition masks, and a shared multimodal prompt encoder to express diverse inputs such as driving speech, timbre examples, first frames, and subject images. A two‑level data pipeline supplies the necessary supervision by extracting speech, appearance, and timbre annotations from clips and linking consistent identity and outfit references across videos, while a frozen‑prefix recurrence enables long‑form audio‑driven generation with reduced boundary discontinuity and identity drift.
By Yang Ding, Haoran Yu, Xin Ma, Yulei Lu, Menglin Han, Yaole Wang, Siqian Yang, Gang Yue, Kaihao Zhang, Yaohui Wang, Lin Ma
arXiv:2606. 01031v1 Announce Type: cross Abstract: Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos.
By Zhicheng Zhang, Lei Wang, Yu Zhang, Yongsheng Gao
The paper introduces a real‑time framework for generating co‑speech gestures for digital humans, coupling a streaming speech response module with a causal multimodal autoregressive gesture generator that uses only current speech and motion history. It also presents an offline data synthesis pipeline for virtual companion dialogues and a self‑evolving training loop that incorporates user feedback to continually adapt the model. Experiments show the system achieves a better latency‑quality trade‑off, stronger speech‑motion synchronization, and higher user preference than existing baselines.
By Wentao Jiang, Youchen Xie, Haidi Fan, Yajing Chen, Xin Wang, Ye Shi, Jingya Wang
arXiv:2609.00369v1 Announce Type: new
Abstract: Generating co-speech gestures that are temporally coherent, semantically aligned with speech, and grounded with surrounding objects remains challenging...
By Vida Adeli, Soroush Mehraban, Jacob Rommann, Harrison Sanborn, Cole Clifford, Babak Taati
The paper introduces a new benchmark for evaluating holistic, semantics-aware co‑speech gesture generation, combining 13 objective metrics and a novel Semantic Gesture Preservation (SGP) metric that measures how well ground‑truth semantic gestures are retained. A perceptual study with 101 participants rates generated gestures on five dimensions, revealing that SGP aligns with speech‑aware human judgments while other metrics do not. Composite metrics tailored to each dimension further improve alignment, especially for animation errors and content match, underscoring the need to validate objective metrics against human perception.
By Nick Milkin, Lanmiao Liu, Esam Ghaleb, Asli Ozyurek, Zerrin Yumak