Shen, Y;
Zhou, K;
Wang, H;
Yang, Y;
Shao, T;
(2025)
High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model.
In:
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
(pp. pp. 21558-21569).
IEEE: Nashville, TN, USA.
Preview |
PDF
Shen_High-fidelity_3D_Object_Generation_from_Single_Image_with_RGBN-Volume_Gaussian_CVPR_2025_paper.pdf - Accepted Version Download (2MB) | Preview |
Abstract
Recently single-view 3D generation via Gaussian splatting has emerged and developed quickly. They learn 3D Gaussians from 2D RGB images generated from pre-trained multi-view diffusion (MVD) models, and have shown a promising avenue for 3D generation through a single image. Despite the current progress, these methods still suffer from the inconsistency jointly caused by the geometric ambiguity in the 2D images, and the lack of structure of 3D Gaussians, leading to distorted and blurry 3D object generation. In this paper, we propose to fix these issues by GS-RGBN, a new RGBN-volume Gaussian Reconstruction Model designed to generate high-fidelity 3D objects from single-view images. Our key insight is a structured 3D representation can simultaneously mitigate the afore-mentioned two issues. To this end, we propose a novel hybrid Voxel-Gaussian representation, where a 3D voxel representation contains explicit 3D geometric information, eliminating the geometric ambiguity from 2D images. It also structures Gaussians during learning so that the optimization tends to find better local optima. Our 3D voxel representation is obtained by a fusion module that aligns RGB features and surface normal features, both of which can be estimated from 2D images. Extensive experiments demonstrate the superiority of our methods over prior works in terms of high-quality reconstruction results, robust generalization, and good efficiency.
| Type: | Proceedings paper |
|---|---|
| Title: | High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model |
| Event: | 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
| Dates: | 10 Jun 2025 - 17 Jun 2025 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/CVPR52734.2025.02008 |
| Publisher version: | https://doi.org/10.1109/cvpr52734.2025.02008 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Solid modeling, Surface reconstruction, Computer vision, Three-dimensional displays, Computational modeling, Pattern recognition, Image reconstruction, Optimization |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10215175 |
Archive Staff Only
 |
View Item |
