研究人员开发了CompoSE，一种使用部件感知控制来合成和编辑3D形状的新方法。该方法利用了扩散Transformer架构，该架构在考虑全局上下文的同时处理各个部件，从而能够进行细粒度的编辑操作，如替换、添加、删除和保持风格的缩放，而无需部件级别的文本提示。同时，另一项研究介绍了用于3D编辑的大型数据集Pxform，以及一个前馈网络PartFlow，该网络利用语义部件变换来实现可扩展的3D内容创建，并达到了最先进的性能。 AI
排序理由 该集群包含两篇不同的研究论文，详细介绍了用于3D形状合成与编辑的新方法和数据集。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Creating and editing high-quality 3D content remains a central challenge in computer graphics. We address this challenge by introducing CompoSE, a novel method for Compositional Synthesis and Editing of 3D shapes via part-aware control. Our method takes as input a set of coarse g…
arXiv:2605.27351v1 Announce Type: new Abstract: 3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generative paradigms, 3D AI generation remains dominated by training-free editing pipeli…
3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generative paradigms, 3D AI generation remains dominated by training-free editing pipelines. A central challenge of feedforward 3D editi…