3D-aware Image Generation and Editing with Multi-modal Conditions

arXiv:2403.06470v1 Announce Type: new
Abstract: 3D-consistent image generation from a single 2D semantic label is an important and challenging research topic in computer graphics and computer vision. Although some related works have made great progress in this field, most of the existing methods suffer from poor disentanglement performance of shape and appearance, and lack multi-modal control. In this paper, we propose a novel end-to-end 3D-aware image generation and editing model incorporating multiple types of conditional inputs, including pure noise, text …

abstract arxiv computer computer graphics computer vision consistent cs.cv editing graphics image image generation modal multi-modal performance progress research semantic type vision