ClipMatrix：文本控制的3D纹理网格创建
ClipMatrix: Text-controlled Creation of 3D Textured Meshes
摘要：
如果一张图片胜过千言万语，那么一个移动的3d形状就一定胜过百万。我们建立在最近的生成方法，创建图像拟合的文本提示的语义的成功，并将其扩展到三维对象的控制生成。我们提出了一种新的算法，用于创建纹理的三维网格，由文本提示控制。我们的方法创建了美观的高分辨率铰接3D网格，并为3D资产的自动化和AI控制开辟了新的可能性。我们称之为“ClipMatrix”，因为它利用CLIP文本嵌入来培育新的数字3D生物，这是对“矩阵”一词的拉丁含义-“母亲”的认可。请参阅在线图库，了解我们方法能力的完整印象。
英文摘要：
If a picture is worth thousand words, a moving 3d shape must be worth a million. We build upon the success of recent generative methods that create images fitting the semantics of a text prompt, and extend it to the controlled generation of 3d objects. We present a novel algorithm for the creation of textured 3d meshes, controlled by text prompts. Our method creates aesthetically pleasing high resolution articulated 3d meshes, and opens new possibilities for automation and AI control of 3d assets. We call it "ClipMatrix" because it leverages CLIP text embeddings to breed new digital 3d creatures, a nod to the Latin meaning of the word "matrix" - "mother". See the online gallery for a full impression of our method's capability.
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。
