.png){kind=icon}
返回
Multi3D: 3D-aware multimodal image synthesis
.png){kind=icon}
OA
AI
DOI：10.1007/s41095-024-0422-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
generate adversarial networks (GANs)
neural radiation field (NeRF)
3D-aware image synthesis
controllable generation
期刊
IF:
18.3
论文数:
319
被引数:
2.6K
机构
引用论文
NeRFFaceLighting: Implicit and Disentangled Face Lighting Representation Leveraging Generative Prior in Neural Radiance FieldsNeRFFaceLighting: 在神经辐射场中利用生成先验的隐式和解开的面部照明表示OAAI
OAAI分享收藏A new Jurassic theropod from China documents a transitional step in the macrostructure of feathers
PREAI
分享收藏分享收藏Assessment of best single sample for finding chlamydia in women with and without symptoms: a diagnostic test study.png)
BMJ
OAAI
BMJIF0
OAAI分享收藏
查看更多内容