Single-View Reconstruction via Decoupled 3D Gaussian Splatting

Sheng Liu, Shiming Zhu, Huilong Pi, Yunchuan Qin, Zhuo Tang, Ruihui LiICASSP 2025 · OpenReview

Abstract

Creating high-quality 3D object representations from a single-view image is challenging. Existing methods tend to infer the geometry and texture information simultaneously within a shared network. However, decoding geometry and texture from a unified network often leads to their entanglement, causing geometric structure collapse or floating artifacts. After revisiting this task, we propose a single-view reconstruction framework based on 3D Gaussian Splatting. The key idea is to decouple Gaussian position attribute generation from texture feature generation. Technically, our framework combines a Geometry Generator, a Texture Generator, and a Gaussian Attributes Decoder. Two parallel branches, Geometry Generator and Texture Generator, aim for point cloud prediction and texture optimization, respectively. Then the Gaussian Attributes Decoder integrates the generated position and texture attributes into a coherent Gaussian point cloud, facilitating efficient novel view synthesis. Extensive qualitative and quantitative evaluations of public datasets demonstrate that our method consistently outperforms existing methods in terms of reconstruction quality and inferring efficiency.
BibTeX
@inproceedings{liu2025single,
  author = {Sheng Liu and Shiming Zhu and Huilong Pi and Yunchuan Qin and Zhuo Tang and Ruihui Li},
  title = {{Single-View Reconstruction via Decoupled 3D Gaussian Splatting}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2025},
  url = {https://openreview.net/forum?id=9QFAs0Rreq},
}

Loading related content...

Figure