WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation

• URL: http://arxiv.org/abs/2511.22098v1
• Date: Thu, 27 Nov 2025 04:40:37 GMT
• Title: WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation
• Authors: Quanjian Song, Yiren Song, Kelly Peng, Yuan Gao, Mike Zheng Shou,
• Abstract summary: We present WorldWander, an in-context learning framework tailored for translating between egocentric and exocentric worlds in video generation.<n> Experiments demonstrate that WorldWander achieves superior perspective synchronization, character consistency, and generalization.
• Score: 51.1909041777449
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Video diffusion models have recently achieved remarkable progress in realism and controllability. However, achieving seamless video translation across different perspectives, such as first-person (egocentric) and third-person (exocentric), remains underexplored. Bridging these perspectives is crucial for filmmaking, embodied AI, and world models. 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 efficiently model cross-view synchronization. To further support our task, we curate EgoExo-8K, a large-scale 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.

Related papers

• EgoX: Egocentric Video Generation from a Single Exocentric Video [46.41583107241048]
  We present EgoX, a novel framework for generating egocentric videos from a single excentrico input.<n>Our approach achieves coherent and realistic egocentric video generation while demonstrating strong scalability and robustness across unseen in-the-wild videos.
  arXiv  Detail & Related papers  (2025-12-09T05:53:39Z)
• Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis [56.456085642852976]
  Exo2EgoSyn is an adaptation of WAN 2.2 that unlocks Exocentric-to-Egocentric(Exo2Ego) cross-view video synthesis.<n>Our framework consists of three key modules.
  arXiv  Detail & Related papers  (2025-11-25T11:08:37Z)
• EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations [4.252119151012245]
  We introduce EgoWorld, a novel framework that reconstructs an egocentric view from rich exocentric observations.<n>Our approach reconstructs a point cloud from estimated exocentric depth maps, reprojects it into the egocentric perspective, and then applies diffusion-based inpainting to produce dense, semantically coherent egocentric images.<n>EgoWorld achieves state-of-the-art performance and demonstrates robust generalization to new objects, actions, scenes, and subjects.
  arXiv  Detail & Related papers  (2025-06-22T04:21:48Z)
• PlayerOne: Egocentric World Simulator [73.88786358213694]
  PlayerOne is the first egocentric realistic world simulator.<n>It generates egocentric videos that are strictly aligned with the real scene human motion of the user captured by an exocentric camera.
  arXiv  Detail & Related papers  (2025-06-11T17:59:53Z)
• Spherical World-Locking for Audio-Visual Localization in Egocentric Videos [53.658928180166534]
  We propose Spherical World-Locking as a general framework for egocentric scene representation. Compared to conventional head-locked egocentric representations with a 2D planar field-of-view, SWL effectively offsets challenges posed by self-motion. We design a unified encoder-decoder transformer architecture that preserves the spherical structure of the scene representation.
  arXiv  Detail & Related papers  (2024-08-09T22:29:04Z)
• Unlocking Exocentric Video-Language Data for Egocentric Video Representation Learning [80.37314291927889]
  We present EMBED, a method designed to transform exocentric video-language data for egocentric video representation learning. Egocentric videos predominantly feature close-up hand-object interactions, whereas exocentric videos offer a broader perspective on human activities. By applying both vision and language style transfer, our framework creates a new egocentric dataset.
  arXiv  Detail & Related papers  (2024-08-07T06:10:45Z)
• EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding [27.881857222850083]
  EgoExo-Fitness is a new full-body action understanding dataset. It features fitness sequence videos recorded from synchronized egocentric and fixed exocentric cameras. EgoExo-Fitness provides new resources to study egocentric and exocentric full-body action understanding.
  arXiv  Detail & Related papers  (2024-06-13T07:28:45Z)
• Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos [66.46812056962567]
  Exocentric-to-egocentric cross-view translation aims to generate a first-person (egocentric) view of an actor based on a video recording that captures the actor from a third-person (exocentric) perspective. We propose a generative framework called Exo2Ego that decouples the translation process into two stages: high-level structure transformation and a pixel-level hallucination.
  arXiv  Detail & Related papers  (2024-03-11T01:00:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.