Generic 3D Diffusion Adapter Using Controlled Multi-View Editing

arXiv:2403.12032v1 Announce Type: new
Abstract: Open-domain 3D object synthesis has been lagging behind image synthesis due to limited data and higher computational complexity. To bridge this gap, recent works have investigated multi-view diffusion but often fall short in either 3D consistency, visual quality, or efficiency. This paper proposes MVEdit, which functions as a 3D counterpart of SDEdit, employing ancestral sampling to jointly denoise multi-view images and output high-quality textured meshes. Built on off-the-shelf 2D diffusion models, MVEdit achieves 3D consistency …

3d object abstract adapter arxiv bridge complexity computational cs.cv cs.gr data diffusion domain editing efficiency functions gap image object paper quality synthesis type view visual