Trajloom Dense Trajectory Generation

Improve dense trajectory generation by replacing absolute coordinate encoding with grid-anchor offset encoding (reduces location variance 90%→10%), adding spatiotemporal consistency regularizers to VAE (30-40× improvement in 81-frame prediction), and using boundary-anchored fine-tuning for flow models. Effective for predicting extended trajectories (81 frames vs. prior 24-frame limits) in autonomous driving and video prediction where motion coherence across time steps is critical.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit aca0dd534d

Frequently asked questions

npx get-skill add adu2021/trajloom-dense-trajectory-generation