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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• efficiency