TY - GEN
T1 - WonderTurbo
T2 - 2025 IEEE/CVF International Conference on Computer Vision, ICCV 2025
AU - Ni, Chaojun
AU - Wang, Xiaofeng
AU - Zhu, Zheng
AU - Wang, Weijie
AU - Li, Haoyun
AU - Zhao, Guosheng
AU - Li, Jie
AU - Qin, Wenkang
AU - Huang, Guan
AU - Mei, Wenjun
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - 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.
AB - 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.
KW - 3d scene generation
KW - 3d scene representations
KW - diffusion acceleration
UR - https://www.scopus.com/pages/publications/105044139196
U2 - 10.1109/ICCV51701.2025.02546
DO - 10.1109/ICCV51701.2025.02546
M3 - Conference contribution
AN - SCOPUS:105044139196
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 27423
EP - 27434
BT - Proceedings - 2025 IEEE/CVF International Conference on Computer Vision, ICCV 2025
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 October 2025 through 23 October 2025
ER -