MVGamba : Unify 3D content generation as state space sequence modeling

• Main Authors: YI, Xuanyu, WU, Zike, SHEN, Qiuhong, XU, Qingshan, ZHOU, Pan, LIM, Joo-Hwee, YAN, Shuicheng, WANG, Xinchao, ZHANG, Hanwang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Large Reconstruction Models; LRMs; Gaussian reconstruction model; 3D content generation; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/9491; https://ink.library.smu.edu.sg/context/sis_research/article/10491/viewcontent/MVGamba.pdf
• Institution: Singapore Management University

Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D representation for improved visual quality and rendering eff...