Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
机构 * CCVL, Johns Hopkins University(CCVL,约翰霍普金斯大学)
Comments Accepted to TMLR 2025. Code and models released at https://gaussianscenes.github.io/
高校专区
机构 * CCVL, Johns Hopkins University(CCVL,约翰霍普金斯大学)
Comments Accepted to TMLR 2025. Code and models released at https://gaussianscenes.github.io/
机构 * Department of Computer Science, Technical University of Munich(技术大学慕尼黑计算机科学系) ; Munich Center for Machine Learning (MCML), Munich, Germany(慕尼黑机器学习中心(MCML)) ; Johns Hopkins University, Baltimore, Maryland, USA(约翰霍普金斯大学)