Abstract: Multi-aspect controllable text generation (CTG), opposite to single-aspect CTG, aims to produce texts that align with multiple attributes. Incorporating attribute information through ...
NARRATOR: Ah yes, good point. We’re just about to take a look at Jesus performing his ministry. *Jesus sits under a tree as people listen to him talk. * NARRATOR: Christians believe that Jesus was the ...
Abstract: Current text-to-avatar methods often rely on implicit representations (e.g., NeRF, SDF, and DMTet), leading to 3D content that artists cannot easily edit and animate in graphics software.