Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis

TL;DR

Exo2EgoSyn adapts foundation video models to enable high-quality egocentric video synthesis from exocentric views, using view alignment, multi-view conditioning, and pose-aware latent injection.

Contribution

The paper introduces Exo2EgoSyn, a novel framework that extends foundation video models for cross-view egocentric-to-exocentric synthesis without retraining.

Findings

Significant improvement in ego-to-exo video synthesis quality.

Effective cross-view synthesis without retraining foundation models.

Validated on ExoEgo4D dataset with promising results.

Abstract

Foundation video generation models such as WAN 2.2 exhibit strong text- and image-conditioned synthesis abilities but remain constrained to the same-view generation setting. In this work, we introduce Exo2EgoSyn, an adaptation of WAN 2.2 that unlocks Exocentric-to-Egocentric(Exo2Ego) cross-view video synthesis. Our framework consists of three key modules. Ego-Exo View Alignment(EgoExo-Align) enforces latent-space alignment between exocentric and egocentric first-frame representations, reorienting the generative space from the given exo view toward the ego view. Multi-view Exocentric Video Conditioning (MultiExoCon) aggregates multi-view exocentric videos into a unified conditioning signal, extending WAN2.2 beyond its vanilla single-image or text conditioning. Furthermore, Pose-Aware Latent Injection (PoseInj) injects relative exo-to-ego camera pose information into the latent state, guiding geometry-aware synthesis across viewpoints. Together, these modules enable high-fidelity ego view video generation from third-person observations without retraining from scratch. Experiments on ExoEgo4D validate that Exo2EgoSyn significantly improves Ego2Exo synthesis, paving the way for scalable cross-view video generation with foundation models. Source code and models will be released publicly.