Publication Type
Journal Article
Version
acceptedVersion
Publication Date
5-2025
Abstract
We tackle the challenge of efficiently reconstructing a 3D asset from a single image at millisecond speed. Existing methods for single-image 3D reconstruction are primarily based on Score Distillation Sampling (SDS) with Neural 3D representations. Despite promising results, these approaches encounter practical limitations due to lengthy optimizations and significant memory consumption. In this work, we introduce Gamba, an end-to-end 3D reconstruction model from a single-view image, emphasizing two main insights: (1) Efficient Backbone Design: introducing a Mamba-based GambaFormer network to model 3D Gaussian Splatting (3DGS) reconstruction as sequential prediction with linear scalability of token length, thereby accommodating a substantial number of Gaussians; (2) Robust Gaussian Constraints: deriving radial mask constraints from multi-view masks to eliminate the need for warmup supervision of 3D point clouds in training. We trained Gamba on Objaverse and assessed it against existing optimizationbased and feed-forward 3D reconstruction approaches on the GSO Dataset, among which Gamba is the only end-to-end trained single-view reconstruction model with 3DGS. Experimental results demonstrate its competitive generation capabilities both qualitatively and quantitatively and highlight its remarkable speed: Gamba completes reconstruction within 0.05 seconds on a single NVIDIA A100 GPU, which is about 1, 000× faster than optimization-based methods. Please see our project page at https://florinshen.github.io/gamba-project.
Keywords
3D gaussian splatting, amortized reconstruction, single-view 3 d reconstruction
Discipline
Artificial Intelligence and Robotics
Research Areas
Intelligent Systems and Optimization
Areas of Excellence
Digital transformation
Publication
IEEE Transactions on Pattern Analysis and Machine Intelligence
First Page
1
Last Page
14
ISSN
0162-8828
Identifier
10.1109/TPAMI.2025.3569596
Publisher
Institute of Electrical and Electronics Engineers
Citation
SHEN, Qiuhong; WU, Zike; YI, Xuanyu; ZHOU, Pan; ZHANG, Hanwang; YAN, Shuicheng; and WANG, Xinchao.
Gamba: Marry Gaussian splatting with Mamba for single-view 3D reconstruction. (2025). IEEE Transactions on Pattern Analysis and Machine Intelligence. 1-14.
Available at: https://ink.library.smu.edu.sg/sis_research/10458
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/TPAMI.2025.3569596