Multi3D:3D-aware multimodal image synthesis
摘要
3D-aware image synthesis has attained high quality and robust 3D consistency.Existing 3D controllable generative models are designed to synthesize 3D-aware images through a single modality,such as 2D segmentation or sketches,but lack the ability to finely control generated content,such as texture and age.In pursuit of enhancing user-guided controllability,we propose Multi3D,a 3D-aware controllable image synthesis model that supports multi-modal input.Our model can govern the geometry of the generated image using a 2D label map,such as a segmentation or sketch map,while concurrently regulating the appearance of the generated image through a textual description.To demonstrate the effectiveness of our method,we have conducted experiments on multiple datasets,including CelebAMask-HQ,AFHQ-cat,and shapenet-car.Qualitative and quantitative evaluations show that our method outperforms existing state-of-the-art methods.
Author：
Wenyang Zhou
Lu Yuan
Taijiang Mu
作者单位：
BNRist,Tsinghua University,Beijing 100084,China
Computer Science Department,Stanford University,California 94305,USA
年，卷(期)：
2024, 10(6)
机标分类号：
TP311.52
I06
S152
在线出版日期：
2025年4月23日
