# Learning 3D Editing without Paired Supervision via Generative Prior Distillation

arXiv: https://arxiv.org/abs/2609.04942 · HTML: https://mlsanity.com/paper/2609.04942/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 53 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions](https://mlsanity.com/paper/2303.12789/) (2023)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies](https://mlsanity.com/paper/2312.03806/) (2023)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material](https://mlsanity.com/paper/2506.15442/) (2025)
- [DreamEditor: Text-Driven 3D Scene Editing with Neural Fields](https://mlsanity.com/paper/2306.13455/) (2023)
- [Vox-E: Text-guided Voxel Editing of 3D Objects](https://mlsanity.com/paper/2303.12048/) (2023)
- [Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects](https://mlsanity.com/paper/2412.00518/) (2024)
- [Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention](https://mlsanity.com/paper/2507.17745/) (2025)
- [Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images](https://mlsanity.com/paper/2407.06191/) (2024)
- [MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D](https://mlsanity.com/paper/2411.02336/) (2024)
- [Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion](https://mlsanity.com/paper/2406.03184/) (2024)
- [NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks](https://mlsanity.com/paper/2510.15019/) (2025)
- [MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion](https://mlsanity.com/paper/2503.10289/) (2025)
- [Stable Score Distillation for High-Quality 3D Generation](https://mlsanity.com/paper/2312.09305/) (2023)
- [Score Distillation Sampling with Learned Manifold Corrective](https://mlsanity.com/paper/2401.05293/) (2024)
- [SketchDream: Sketch-based Text-to-3D Generation and Editing](https://mlsanity.com/paper/2405.06461/) (2024)
- [EditP23: 3D Editing via Propagation of Image Prompts to Multi-View](https://mlsanity.com/paper/2506.20652/) (2025)

## Abstract (arXiv)

Instruction-guided 3D editing is essential for interactive content creation, yet it faces a significant bottleneck: the severe scarcity of high-quality paired training data. Existing approaches attempt to bypass this by either relying on slow test-time optimization or training on pseudo-pairs constructed via complex pipelines, which often introduce structural drift and geometric artifacts. In this paper, we propose a novel framework that learns feed-forward 3D editing without paired 3D supervision via Generative Prior Distillation. Instead of relying on ground-truth 3D pairs, our core idea is to distill visual, semantic, and geometric knowledge from powerful foundation models directly into a 3D editing model. Specifically, through a differentiable rendering pipeline, we supervise the 3D representation using two complementary signals: a 2D visual prior from an image editing model at the main editing view, and a semantic prior from a Vision-Language Model at novel views to ensure strict instruction following and source identity preservation. Crucially, to address the geometric collapse and multi-view inconsistencies inherent in 2D projection supervision, we introduce a 3D-aware Distribution Matching regularization. Acting as a geometric prior, this term operates in the 3D latent space, constraining the edited output to remain within the manifold of realistic 3D assets defined by a pretrained image to 3D teacher model. Extensive experiments demonstrate that our method achieves superior instruction fidelity and cross-view consistency, significantly outperforming state-of-the-art baselines. Our project is available at: https://github.com/thiamine128/PriorEdit3D.