SHAP-EDITOR：指令引导的秒级潜在3D编辑
SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds
AI总结：
本研究提出Shap-Editor前馈3D编辑框架，基于Shap-E潜在空间实现秒级指令引导3D编辑，泛化性好且性能与需测试时优化的方法相当。
摘要：
我们提出了一种名为Shap-Editor的新型前馈3D编辑框架。此前的3D物体编辑研究主要聚焦于利用现成的2D图像编辑网络对单个物体进行编辑，这一过程通过名为蒸馏的技术实现，即将2D网络的知识迁移到3D资产上。蒸馏方法对每个资产至少需要数十分钟才能获得令人满意的编辑效果，因此实用性不强。相比之下，我们探究了3D编辑是否可以通过前馈网络直接完成，从而省去测试时优化步骤。具体而言，我们假设先将3D物体编码到合适的潜在空间中，可大幅简化编辑过程。我们基于Shap-E的潜在空间验证了这一假设。通过构建一个每次编辑仅需约1秒的前馈编辑网络，我们证明了在该空间中进行直接3D编辑是可行且高效的。实验表明，Shap-Editor在分布内和分布外的3D资产上，搭配不同提示词均具有良好的泛化能力，其性能与针对每个编辑实例执行测试时优化的方法相当。
英文摘要：
We propose a novel feed-forward 3D editing framework called Shap-Editor. Prior research on editing 3D objects primarily concentrated on editing individual objects by leveraging off-the-shelf 2D image editing networks. This is achieved via a process called distillation, which transfers knowledge from the 2D network to 3D assets. Distillation necessitates at least tens of minutes per asset to attain satisfactory editing results, and is thus not very practical. In contrast, we ask whether 3D editing can be carried out directly by a feed-forward network, eschewing test-time optimisation. In particular, we hypothesise that editing can be greatly simplified by first encoding 3D objects in a suitable latent space. We validate this hypothesis by building upon the latent space of Shap-E. We demonstrate that direct 3D editing in this space is possible and efficient by building a feed-forward editor network that only requires approximately one second per edit. Our experiments show that Shap-Editor generalises well to both in-distribution and out-of-distribution 3D assets with different prompts, exhibiting comparable performance with methods that carry out test-time optimisation for each edited instance.
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。
