Longfei Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Longfei Lu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Huachen Gao
Tencent, Hunyuan, Shenzhen, China
1 shared publication - Junta Wu
Tencent, Shenzhen, China
1 shared publication - Shu-Tao Xia
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
1 shared publication - Tao Dai
Shenzhen University
1 shared publication - Yaohua Zha
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
1 shared publication - Zhi Hou
School of Computer Science, University of Sydney, Sydney, NSW, Australia
1 shared publication
Latest Publications
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10843-10852
Large Point-to-Gaussian Model for Image-to-3D Generation
Recently, image-to-3D approaches have significantly advanced the generation quality and speed of 3D assets based on large reconstruction models, particularly 3D Gaussian reconstruction models. Existing large 3D Gaussian models directly map 2D image to 3D Gaussian parameters, while regressing 2D image to 3D Gaussian representations is challenging without 3D priors. In this paper, we propose a large Point-to-Gaussian model, that inputs the initial point cloud produced from large 3D diffusion model conditional on 2D image to generate the Gaussian parameters, for image-to-3D generation. The point cloud provides initial 3D geometry prior for Gaussian generation, thus significantly facilitating image-to-3D Generation. Moreover, we present the Attention mechanism, Projection mechanism, and Point feature extractor, dubbed as APP block, for fusing the image features with point cloud features. The qualitative and quantitative experiments extensively demonstrate the effectiveness of the proposed approach on GSO and Objaverse datasets, and show the proposed method achieves state-of-the-art performance.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10843-10852
Open AccessLarge Point-to-Gaussian Model for Image-to-3D Generation
Recently, image-to-3D approaches have significantly advanced the generation quality and speed of 3D assets based on large reconstruction models, particularly 3D Gaussian reconstruction models. Existing large 3D Gaussian models directly map 2D image to 3D Gaussian parameters, while regressing 2D image to 3D Gaussian representations is challenging without 3D priors. In this paper, we propose a large Point-to-Gaussian model, that inputs the initial point cloud produced from large 3D diffusion model conditional on 2D image to generate the Gaussian parameters, for image-to-3D generation. The point cloud provides initial 3D geometry prior for Gaussian generation, thus significantly facilitating image-to-3D Generation. Moreover, we present the Attention mechanism, Projection mechanism, and Point feature extractor, dubbed as APP block, for fusing the image features with point cloud features. The qualitative and quantitative experiments extensively demonstrate the effectiveness of the proposed approach on GSO and Objaverse datasets, and show the proposed method achieves state-of-the-art performance.