Image Sculpting: Precise Object Editing with 3D Geometry Control
Jiraphon Yenphraphai, Xichen Pan, Sainan Liu, Daniele Panozzo, Saining Xie
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 259ca082-2abd-4878-a0cb-b3ef3496cd57Cited by top-tier papers29
- Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion ModelsZiyi Wu, Yulia Rubanova, Rishabh Kabra, Drew A. Hudson et al.NeurIPS 2024 · 32 citations
- SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose ManipulationZhenyuan Qin, Xincheng Shuai, Henghui DingNeurIPS 2025 · 11 citations
- PoseLLaVA: Pose Centric Multimodal LLM for Fine-Grained 3D Pose ManipulationDong Feng, Ping Guo, Encheng Peng, Mingmin Zhu et al.AAAI 2025 · 7 citations
- SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image GenerationVaibhav Agrawal, Rishubh Parihar, Pradhaan Bhat, Ravi Kiran Sarvadevabhatla et al.CVPR 2026 · 5 citations
- Generative Blocks World: Moving Things Around in PicturesVaibhav Vavilala, Seemandhar Jain, Rahul Vasanth, David Forsyth et al.ICLR 2026 · 4 citations
Builds on42
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
Related papers
- ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGSYuhuan Xie, Aoxuan Pan, Yihua Huang, Chirui Chang et al.CVPR 2026
- CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless FusionJames Jincheng Hu, Yuxiao Wu, Youcheng Cai, Ligang LiuCVPR 2026 · 3 citations
- IntrinsicEdit: Precise generative image manipulation in intrinsic spaceLinjie Lyu, Valentin Deschaintre, Yannick Hold-Geoffroy, Milos Hasan et al.SIGGRAPH 2025 · 7 citations
- Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based AbstractionsEtai Sella, Hao Phung, Nitay Amiel, Or Litany et al.SIGGRAPH 2026 · 2 citations
- OBJECT 3DIT: Language-guided 3D-aware Image EditingOscar Michel, Anand Bhattad, Eli VanderBilt, Ranjay Krishna et al.NeurIPS 2023 · 79 citations
