Get the latest tech news
Era3D: High-Resolution Multiview Diffusion Using Efficient Row-Wise Attention
Paper title
Moreover, the full-image or dense multiview attention they employ leads to an exponential explosion of computational complexity as image resolution increases, resulting in prohibitively expensive training costs. Comprehensive experiments demonstrate that Era3D can reconstruct high-quality and detailed 3D meshes from diverse single-view input images, significantly outperforming baseline multiview diffusion methods. This work is mainly supported by Hong Kong Generative AI Research & Development Center (HKGAI) led by Prof. Yike Guo.
Or read this on Hacker News