arXiv Computer Vision
Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 23
Latent Dataset Distillation for Human Motion Prediction
The paper introduces a latent dataset distillation framework for human motion prediction, addressing the limitations of traditional gradient matching by incorporating a learned motion prior. Motions are compressed using a residual‑quantized variational autoencoder, and distillation updates only a latent bank while keeping the decoder frozen, ensuring synthetic motions remain plausible. Experiments on Human3.6M, CMU, and 3DPW datasets demonstrate that this method outperforms direct gradient matching in most settings and yields more realistic synthetic motions.
arXiv Computer Vision
Sep 14
Uni-HOI:A Unified framework for Learning the Joint distribution of Text and Human-Object Interaction
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.
arXiv Computer Vision
Sep 30
MotionMaestro: Masked Tokenization for Unified Motion Generation
arXiv:2609.37495v1 Announce Type: new Abstract: Human motion generation plays an important role in applications such as character animation, virtual environments, and embodied interaction. While exis...
arXiv Computer Vision
5d ago
BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis
arXiv:2412.00112v5 Announce Type: replace Abstract: Generating natural and expressive human motions from textual descriptions is challenging due to the complexity of coordinating full-body dynamics a...
arXiv Machine Learning
Jul 10
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
arXiv:2607. 08741v1 Announce Type: cross Abstract: Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics.
arXiv Computer Vision
1d ago
Linear Multi-granular Body Modeling for Text-Driven Motion Generation
arXiv:2503.06897v3 Announce Type: replace Abstract: Text-to-motion generation is a rapidly growing field at the nexus of multimodal learning and computer graphics, enabling flexible and cost-effectiv...