Generating co-speech gestures that are temporally coherent, semantically aligned with speech, and grounded with surrounding objects remains challenging. Prior speech-driven gesture models emphasize au...
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.
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.
PAGE (Parts-Aware Guidance) is a diffusion-based framework that improves co-speech gesture portrait video generation by enhancing local spatial fidelity and global audio‑visual consistency. It introduces Parts‑Specific Reweighting during training to focus supervision on key regions like lips, eyes, and hands, and Consistency Classifier Guidance plus Differential Guidance during inference to correct audio‑visual mismatches and refine motion separately. The authors also present the Chinese Announcer Speech (CAS) dataset, a large‑scale Chinese benchmark that expands on the PATS dataset, and demonstrate that PAGE outperforms existing methods in perceptual quality, gesture diversity, and audio‑visual alignment.
arXiv:2608.28693v1 Announce Type: cross Abstract: Enabling humanoid robots to respond to human speech with synchronized and semantically meaningful gestures is fundamental to natural human-robot inte...
DuoGesture is a co‑speech gesture generation model that separates gesture synthesis into a semantic stream and a beat stream, coordinated by a Semantic Variational Information Bottleneck that decides when semantic gestures override rhythmic motion. The semantic stream uses Motion‑Grounded Semantic Conditioning, replacing word embeddings with motion‑language representations to provide motion‑aligned semantic priors for rare gesture triggers. The beat stream is regularised by an Inertial Beat Prior, an anthropometry‑weighted arm‑chain module that reduces jitter and improves rhythmic consistency. Experiments show DuoGesture outperforms strong baselines and ablations confirm the complementary roles of semantic grounding, stochastic stream selection, and biomechanical regularisation.
arXiv:2608. 20312v1 Announce Type: new Abstract: The capability to perceive and synthesize human-human interactions is fundamental to developing intelligent digital human systems.
arXiv:2608.23279v1 Announce Type: new Abstract: Text-driven human motion synthesis has made substantial development with two core modules of motion representation and generative architecture. For rep...
Uni-HOI is a unified framework that learns the joint distribution among text, human motion, and object motion for 4D human‑object interaction (HOI). It uses large language models and two motion‑specific VQ‑VAEs to convert heterogeneous motion data into token sequences, enabling seamless integration of all three modalities. A two‑stage training strategy first captures correlations on a large‑scale HOI dataset and then fine‑tunes for specific tasks, achieving strong performance on text‑driven HOI generation, object‑motion‑driven human motion generation, and human‑motion‑driven object motion prediction.
The paper introduces Hand2Bot, an RGB‑D video dataset designed for human‑to‑robot handover scenarios, capturing body posture and facial expressions amid real‑world noise. It also proposes PassGen, a generative pipeline using stable video diffusion and an Intention‑Aware Temporal Face Encoder to synthesize realistic handover sequences while maintaining hand‑object consistency. A morphology‑based depth editing strategy is employed to replicate realistic sensor noise, and experiments show that training on PassGen yields high intention identification accuracy, low false trigger rates, and robust zero‑shot transfer to a physical robot platform.
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.
MAMHOI introduces an affordance-mediated factorization for generating scene-aware human‑object interactions. It separates scene understanding and motion synthesis: a scene‑conditioned model predicts feasible interaction locations and modes, while an affordance‑conditioned model generates the corresponding human‑object motion. This approach enables learning from separate human‑scene and human‑object datasets, reducing object‑scene penetration and improving interaction realism in complex indoor environments.