Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage

Underwater C³-JEPA is an object‑centric, cross‑view predictive world model designed for near‑field heavy‑load ROV salvage. It encodes synchronized multi‑camera RGB observations and vehicle control signals into task‑object and context tokens, fuses cross‑camera evidence via held‑out‑view attention, and predicts future states conditioned on control without using contact sensors. The model demonstrates superior transfer of task‑relevant information to downstream probes compared to a reconstruction‑free baseline, supports model‑predictive control and imagined‑rollout training, and validates its effectiveness on real underwater video by accurately recovering withheld camera states and maintaining predictive lead over persistence.

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 AI.

• agents
• diffusion