mlsanityData to 7 Oct 2026

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

arXiv 2511.20186 ↗First posted 25 Nov 2025cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 52 of its 57 references that are in the map. First posted on arXiv 25 Nov 2025.

Builds on

52 of 57 references.

References · 52

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  8. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  9. 2022Video Diffusion Modelscited by 2,280
  10. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  11. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  12. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
38 more
  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  2. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
  3. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  4. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 958
  5. 2024Genie: Generative Interactive Environmentscited by 706
  6. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 683
  7. 2017The Perception-Distortion Tradeoffcited by 582
  8. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  9. 2025VACE: All-in-One Video Creation and Editingcited by 467
  10. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  11. 2023FateZero: Fusing Attentions for Zero-shot Text-based Video Editingcited by 462
  12. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  13. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  14. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generationcited by 300
  15. 2022Novel View Synthesis with Diffusion Modelscited by 299
  16. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
  17. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  18. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  19. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  20. 2024EscherNet: A Generative Model for Scalable View Synthesiscited by 94
  21. 2025Cameras as Relative Positional Encodingcited by 94
  22. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 93
  23. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  24. 2024SPAD : Spatially Aware Multiview Diffuserscited by 62
  25. 2024Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videoscited by 32
  26. 2024ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectivescited by 26
  27. 2023Learning Disentangled Identifiers for Action-Customized Text-to-Image Generationcited by 24
  28. 2025EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMscited by 22
  29. 2025EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videoscited by 19
  30. 2023DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editingcited by 17
  31. 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Modelscited by 16
  32. 2024Intention-driven Ego-to-Exo Video Generationcited by 13
  33. 2025EarthSynth: Generating Informative Earth Observation with Diffusion Modelscited by 12
  34. 2025Exploration-Driven Generative Interactive Environmentscited by 8
  35. 2025EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observationscited by 8
  36. 2025O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Viewscited by 7
  37. 2025Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object Detectioncited by 7
  38. 2025Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMscited by 6

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 12.

12 papers.

  1. 2026EgoSound: Benchmarking Sound Understanding in Egocentric Videoscited by 8
  2. 2026Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligencecited by 6
  3. 2026EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videoscited by 2
  4. 2026E3C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Controlcited by 2
  5. 2026Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generationcited by 2
  6. 2026EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Nextcited by 1
  7. 2026From Synchrony to Sequence: Exo-to-Ego Generation via Interpolationcited by 1
  8. 2026ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysiscited by 0
  9. 2026Mirror Learningcited by 0
  10. 2026The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answeringcited by 0
  11. 2026Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generationcited by 0
  12. 2026Exo2EgoHOI: Hand-Object-Interaction Aware Exocentric-to-Egocentric Video Generationcited by 0