Research map / Image generation / Autoregressive and latent generation
WaveAR: Wavelet-Aware Continuous Autoregressive Diffusion for Accurate Human Motion Prediction
shengchuan gao, Shuo Wang, Yabiao Wang, Ran Yi
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes WaveAR, a wavelet-aware continuous autoregressive diffusion model for stochastic human motion prediction that avoids vector-quantized tokenization.
Problem
Stochastic human motion prediction (SHMP): forecasting diverse and physically plausible future pose sequences from a short observed motion history; existing autoregressive sequence models rely on vector-quantized tokenization, which limits motion fidelity and training stability.
Approach
Replaces vector-quantized tokens with continuous autoregressive diffusion that is wavelet-aware, so motion is modeled in a continuous latent space rather than discrete codes. Details beyond the abstract are not stated in the provided text.
Closest papers by meaning
- SPARD: Single-step Inference with Adaptive Sampling in Residual Diffusion for Human Motion Prediction (AAAI 2026 · similarity 0.90)
- CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion (ECCV 2024 · similarity 0.90)
- AMD: Autoregressive Motion Diffusion (AAAI 2024 · similarity 0.88)
- Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression (CVPR 2025 · similarity 0.87)
- MotionMap: Representing Multimodality in Human Pose Forecasting (CVPR 2025 · similarity 0.87)
- MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
