Multi-View Large Reconstruction Model via Geometry-Aware Positional . . . Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well as slower convergence speed than expected
LRM：单幅图像到三维的大型重建模型 - CSDN博客 在一篇新论文《LRM: Large Reconstruction Model for Single Image to 3D》中，来自Adobe研究院和澳大利亚国立大学的研究团队介绍了一种创新的大型重建模型（LRM）。这个开创性的模型具有非凡的能力，可以在短短5秒内从单个输入图像中预测物体的3D模型。