← 返回论文检索
NeurIPS 2024PosterAccept (poster)

ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations

Edward Bartrum, Thu Nguyen-Phuoc, Christopher Xie, Zhengqin Li, Numair Khan, Armen Avetisyan, Douglas Lanman, Lei Xiao

University College London · Reality Labs Research, Meta · University of Washington · Facebook · Meta Reality Labs · Meta

PDF 由论文原始站点提供,PaperCompass 不保存论文文件。

摘要

We introduce ReplaceAnything3D model RAM3D, a novel method for 3D object replacement in 3D scenes based on users' text description. Given multi-view images of a scene, a text prompt describing the object to replace, and another describing the new object, our Erase-and-Replace approach can effectively swap objects in 3D scenes with newly generated content while maintaining 3D consistency across multiple viewpoints. We demonstrate the versatility of RAM3D by applying it to various realistic 3D scene types, showcasing results of modified objects that blend in seamlessly with the scene without impacting its overall integrity.