2025/11/27 by Quanjian Song, Song, Quanjian, Yiren Song +7 · 1 citation
Computer Science · Engineering · #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis #Human Motion and Animation #cs.CV
paper · pdf · doi:10.48550/arxiv.2511.22098
openalex publication_date 2025/11/27 · openalex created_date 2025/12/03 · openalex updated_date 2026/07/28
Recent advances in video world models enable interactive environments with free navigation, making translation between first-person (egocentric) and third-person (exocentric) perspectives increasingly important. However, existing studies focus on unidirectional exocentric-to-egocentric translation, overlooking reference-guided exocentric perspective synthesis. This capability is crucial for gaming and embodied AI applications. Motivated by this, we present WorldWander, an in-context learning framework tailored for translating between egocentric and exocentric worlds in video generation. Building upon advanced video diffusion transformers, WorldWander integrates (i) In-Context Perspective Alignment and (ii) Collaborative Position Encoding to model cross-view synchronization and character consistency. To support our task, we curate EgoExo-8K, a dynamic and scene-rich dataset containing synchronized egocentric-exocentric triplets from both synthetic and real-world scenarios. Experiments demonstrate that WorldWander achieves superior perspective synchronization, character consistency, and generalization, setting a new benchmark for egocentric-exocentric video translation.