ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2412.03552
70
3

Imagine360: Immersive 360 Video Generation from Perspective Anchor

4 December 2024
Jing Tan
Shuai Yang
Tong Wu
Jingwen He
Yuwei Guo
Ziqiang Liu
Dahua Lin
    VGen
ArXivPDFHTML
Abstract

360∘360^\circ360∘ videos offer a hyper-immersive experience that allows the viewers to explore a dynamic scene from full 360 degrees. To achieve more user-friendly and personalized content creation in 360∘360^\circ360∘ video format, we seek to lift standard perspective videos into 360∘360^\circ360∘ equirectangular videos. To this end, we introduce Imagine360, the first perspective-to-360∘360^\circ360∘ video generation framework that creates high-quality 360∘360^\circ360∘ videos with rich and diverse motion patterns from video anchors. Imagine360 learns fine-grained spherical visual and motion patterns from limited 360∘360^\circ360∘ video data with several key designs. 1) Firstly we adopt the dual-branch design, including a perspective and a panorama video denoising branch to provide local and global constraints for 360∘360^\circ360∘ video generation, with motion module and spatial LoRA layers fine-tuned on extended web 360∘360^\circ360∘ videos. 2) Additionally, an antipodal mask is devised to capture long-range motion dependencies, enhancing the reversed camera motion between antipodal pixels across hemispheres. 3) To handle diverse perspective video inputs, we propose elevation-aware designs that adapt to varying video masking due to changing elevations across frames. Extensive experiments show Imagine360 achieves superior graphics quality and motion coherence among state-of-the-art 360∘360^\circ360∘ video generation methods. We believe Imagine360 holds promise for advancing personalized, immersive 360∘360^\circ360∘ video creation.

View on arXiv
Comments on this paper