# WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation

Source: [WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation](<https://www.sota2.com/research/paper/692d2106d6b0dd3342931603>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-18T05:00:05.624Z

Authors: Quanjian Song, Yiren Song, Kelly Peng, Yuan Gao, Mike Zheng Shou

Published: 2025-11-27T04:40:37.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Egocentric-to-Exocentric Video Translation on EgoExo Synthetic Scenarios 8K](<https://www.sota2.com/research/sota/egocentric-to-exocentric-video-translation-on-egoexo-synthetic-scenarios-8k.md>): Egocentric-to-Exocentric Video Translation; EgoExo Synthetic Scenarios 8K; LPIPS: 0.555.

- [Egocentric-to-Exocentric Video Translation on EgoExo Real-World Scenarios 8K](<https://www.sota2.com/research/sota/egocentric-to-exocentric-video-translation-on-egoexo-real-world-scenarios-8k.md>): Egocentric-to-Exocentric Video Translation; EgoExo Real-World Scenarios 8K; LPIPS: 0.5357.

- [Exocentric-to-Egocentric Video Translation on EgoExo Synthetic Scenarios 8K](<https://www.sota2.com/research/sota/exocentric-to-egocentric-video-translation-on-egoexo-synthetic-scenarios-8k.md>): Exocentric-to-Egocentric Video Translation; EgoExo Synthetic Scenarios 8K; LPIPS: 0.5811.

- [Exocentric-to-Egocentric Video Translation on EgoExo Real-World Scenarios 8K](<https://www.sota2.com/research/sota/exocentric-to-egocentric-video-translation-on-egoexo-real-world-scenarios-8k.md>): Exocentric-to-Egocentric Video Translation; EgoExo Real-World Scenarios 8K; LPIPS: 0.6054.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.22098>)

[PDF](<https://arxiv.org/pdf/2511.22098.pdf>)