Skip to main navigation Skip to search Skip to main content

WonderTurbo: Generating Interactive 3D World in 0.72 Seconds

  • Chaojun Ni
  • , Xiaofeng Wang
  • , Zheng Zhu*
  • , Weijie Wang
  • , Haoyun Li
  • , Guosheng Zhao
  • , Jie Li
  • , Wenkang Qin
  • , Guan Huang
  • , Wenjun Mei*
  • *Corresponding author for this work
  • Peking University
  • GigaAI
  • Zhejiang University
  • CAS - Institute of Automation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences. However, a critical challenge in current 3D generation technologies lies in achieving real-time interactivity. To address this issue, we introduce WonderTurbo, the first real-time interactive 3D scene generation framework capable of generating novel perspectives of 3D scenes within 0.72 seconds. Specifically, WonderTurbo accelerates both geometric and appearance modeling in 3D scene generation. In terms of geometry, we propose StepSplat, an innovative method that constructs efficient 3D geometric representations through dynamic updates, each taking only 0.26 seconds. Additionally, we design QuickDepth, a lightweight depth completion module that provides consistent depth input for StepSplat, further enhancing geometric accuracy. For appearance modeling, we develop FastPaint, a 2 -steps diffusion model tailored for instant inpainting, which focuses on maintaining spatial appearance consistency. Experimental results demonstrate that WonderTurbo achieves a remarkable 15 × speedup compared to baseline methods, while preserving excellent spatial consistency and delivering high-quality output.

Original languageEnglish
Title of host publicationProceedings - 2025 IEEE/CVF International Conference on Computer Vision, ICCV 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages27423-27434
Number of pages12
ISBN (Electronic)9798331587758
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event2025 IEEE/CVF International Conference on Computer Vision, ICCV 2025 - Honolulu, United States
Duration: 19 Oct 202523 Oct 2025

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499
ISSN (Electronic)2380-7504

Conference

Conference2025 IEEE/CVF International Conference on Computer Vision, ICCV 2025
Country/TerritoryUnited States
CityHonolulu
Period19/10/2523/10/25

Keywords

  • 3d scene generation
  • 3d scene representations
  • diffusion acceleration

Fingerprint

Dive into the research topics of 'WonderTurbo: Generating Interactive 3D World in 0.72 Seconds'. Together they form a unique fingerprint.

Cite this