Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data
Researchers propose incorporating depth as a geometric prior during training of JEPA world models, alongside an isotropy-inducing latent regularizer (SIGReg), to improve learning from complex real-world robot video data. Their approach achieves a 33% reduction in visual odometry probe error, enhances surprise detection, and improves rollout fidelity on outdoor datasets, all without increasing inference time. The method demonstrates improved generalization and transferability of compact world models in challenging outdoor environments.
Why it matters: This work demonstrates that introducing a lightweight geometric prior during training can significantly enhance the generalization and practical utility of world models for real-world outdoor robotics without added inference cost.
Full story at: arXiv Computer Vision ↗