Gamba: Marry Gaussian Splatting With Mamba for Single-View 3D Reconstruction.

 0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Qiuhong Shen, Xinchao Wang, Zike Wu, Shuicheng Yan, Xuanyu Yi, Hanwang Zhang, Pan Zhou

Ngôn ngữ: eng

Ký hiệu phân loại: 354.46 $Gas

Thông tin xuất bản: United States : IEEE transactions on pattern analysis and machine intelligence , 2025

Mô tả vật lý:

Bộ sưu tập: NCBI

ID: 747587

 We tackle the challenge of efficiently reconstructing a 3D asset from a single image at millisecond speed. 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 optimization-based 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 ,000\times aster than optimization-based methods. Please see our project page at https://florinshen.github.io/gamba-project/.
Tạo bộ sưu tập với mã QR

THƯ VIỆN - TRƯỜNG ĐẠI HỌC CÔNG NGHỆ TP.HCM

ĐT: (028) 36225755 | Email: tt.thuvien@hutech.edu.vn

Copyright @2024 THƯ VIỆN HUTECH