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

Edward Bartrum, Thu Nguyen-Phuoc, Christopher Xie, Zhengqin Li, Numair Khan +3 more
2/3/2026

No confident code implementation found for this paper. 4 possible matches can be shown below.

Abstract

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.

DOISemantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 4 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

ReplaceAnything3D:Text-Guided 3D Scene Editing with Compositional Neural Radiance Fields

95% match2024

Multitwine: Multi-Object Compositing with Text and Layout Control

82% match2026

ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation

82% match2024

ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail

81% match1 repo52025

Customizing Text-to-Image Diffusion with Object Viewpoint Control

81% match2024

Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion

80% match2025

Cite this paper

@article{bartrum2026replaceanythingd,
  title  = {ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations},
  author = {Edward Bartrum and Thu Nguyen-Phuoc and Christopher Xie and Zhengqin Li and Numair Khan and A. Avetisyan and Douglas Lanman and Lei Xiao},
  year   = {2026},
  doi    = {10.52202/079017-1539},
  url    = {https://doi.org/10.52202/079017-1539},
  journal = {NEURIPS 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/5105b1eafe3cbe4efbb816eddb3d9b0dd07db47d.svg)](https://codeofpaper.com/paper/5105b1eafe3cbe4efbb816eddb3d9b0dd07db47d)

Discussion