生成的3D对象的演化诱发2D视图
Evolving Evocative 2D Views of Generated 3D Objects
摘要:
我们提出了一种在不同视角下联合生成对象的3D模型和2D渲染的方法,该过程由ImageNet和基于CLIP的模型指导。我们的研究结果表明,它可以生成变形的对象,与渲染,既唤起目标标题,看起来视觉吸引力。
英文摘要:
We present a method for jointly generating 3D models of objects and 2D renders at different viewing angles, with the process guided by ImageNet and CLIP -based models. Our results indicate that it can generate anamorphic objects, with renders that both evoke the target caption and look visually appealing.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。