Image Sculpting: Precise Object Editing with 3D Geometry Control

Jiraphon Yenphraphai, Xichen Pan, Sainan Liu, D. Panozzo, Saining Xie
2/9/2026

No official code found. Best implementation: vision-x-nyu/image-sculpting (297 stars, MIT, last commit 2024-03-04).

Abstract

We present Image Sculpting, a new framework for editing 2D images by incorporating tools from 3D geometry and graphics. This approach differs markedly from existing methods, which are confined to 2D spaces and typically rely on textual instructions, leading to ambiguity and limited control. Image Sculpting converts 2D objects into 3D, enabling direct interaction with their 3D geometry. Post-editing, these objects are re-rendered into 2D, merging into the original image to produce high-fidelity results through a coarse-to-fine enhancement process. The framework supports precise, quantifiable, and physically-plausible editing options such as pose editing, rotation, translation, 3D composition, carving, and serial addition. It marks an initial step towards combining the creative freedom of generative models with the precision of graphics pipelines.

View on arXivView PDF

Code Implementations(1)

MIT

Code release for Image Sculpting: Precise Object Editing with 3D Geometry Control [CVPR 2024]

29722Shell, PythonJan 2, 20242 years agoMIT

Similar Papers

Cite this paper

@article{yenphraphai2026image,
  title  = {Image Sculpting: Precise Object Editing with 3D Geometry Control},
  author = {Jiraphon Yenphraphai and Xichen Pan and Sainan Liu and D. Panozzo and Saining Xie},
  year   = {2026},
  eprint = {2401.01702},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2401.01702},
  journal = {CVPR 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/2401.01702.svg)](https://codeofpaper.com/paper/2401.01702)

Discussion