# VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

arXiv: https://arxiv.org/abs/2508.19247 · HTML: https://mlsanity.com/paper/2508.19247/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 82 of its 102 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 30 of 82)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (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)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion](https://mlsanity.com/paper/2403.12008/) (2024)
- [One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion](https://mlsanity.com/paper/2311.07885/) (2023)
- [An Edit Friendly DDPM Noise Space: Inversion and Manipulations](https://mlsanity.com/paper/2304.06140/) (2023)
- [Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation](https://mlsanity.com/paper/2306.17115/) (2023)

## Built on by (most cited first, 30 of 45)

- [LATTICE: Democratize High-Fidelity 3D Generation at Scale](https://mlsanity.com/paper/2512.03052/) (2025)
- [NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks](https://mlsanity.com/paper/2510.15019/) (2025)
- [Towards Scalable and Consistent 3D Editing](https://mlsanity.com/paper/2510.02994/) (2025)
- [SegviGen: Repurposing 3D Generative Model for Part Segmentation](https://mlsanity.com/paper/2603.16869/) (2026)
- [Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models](https://mlsanity.com/paper/2606.02580/) (2026)
- [Part-X-MLLM: Part-aware 3D Multimodal Large Language Model](https://mlsanity.com/paper/2511.13647/) (2025)
- [SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training](https://mlsanity.com/paper/2512.05354/) (2025)
- [PEGAsus: 3D Personalization of Geometry and Appearance](https://mlsanity.com/paper/2602.08198/) (2026)
- [Native 3D Editing with Full Attention](https://mlsanity.com/paper/2511.17501/) (2025)
- [MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing](https://mlsanity.com/paper/2601.00204/) (2026)
- [VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image](https://mlsanity.com/paper/2602.04349/) (2026)
- [ShapeUP: Scalable Image-Conditioned 3D Editing](https://mlsanity.com/paper/2602.05676/) (2026)
- [Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing](https://mlsanity.com/paper/2603.03143/) (2026)
- [Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors](https://mlsanity.com/paper/2603.18782/) (2026)
- [CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion](https://mlsanity.com/paper/2509.13688/) (2025)
- [Self-Evolving 3D Scene Generation from a Single Image](https://mlsanity.com/paper/2512.08905/) (2025)
- [Vinedresser3D: Agentic Text-guided 3D Editing](https://mlsanity.com/paper/2602.19542/) (2026)
- [Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation](https://mlsanity.com/paper/2603.00526/) (2026)
- [EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers](https://mlsanity.com/paper/2605.16745/) (2026)
- [3D-Consistent Multi-View Editing by Correspondence Guidance](https://mlsanity.com/paper/2511.22228/) (2025)
- [Variation-aware Flexible 3D Gaussian Editing](https://mlsanity.com/paper/2602.11638/) (2026)
- [Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data](https://mlsanity.com/paper/2604.13688/) (2026)
- [Velocity-Space 3D Asset Editing](https://mlsanity.com/paper/2605.07385/) (2026)
- [TanGO: Training-Free 3D Editing via Tangent-Space Guidance and Optimization](https://mlsanity.com/paper/2607.14927/) (2026)
- [SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation](https://mlsanity.com/paper/2603.14152/) (2026)
- [Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes](https://mlsanity.com/paper/2604.14914/) (2026)
- [REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement](https://mlsanity.com/paper/2604.27504/) (2026)
- [MeshReGen: A Unified 3D Geometry Regeneration Framework](https://mlsanity.com/paper/2604.28134/) (2026)
- [JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Space](https://mlsanity.com/paper/2606.13345/) (2026)
- [EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning](https://mlsanity.com/paper/2607.07187/) (2026)

## Abstract (arXiv)

3D local editing of specified regions is crucial for game industry and robot interaction. Recent methods typically edit rendered multi-view images and then reconstruct 3D models, but they face challenges in precisely preserving unedited regions and overall coherence. Inspired by structured 3D generative models, we propose VoxHammer, a novel training-free approach that performs precise and coherent editing in 3D latent space. Given a 3D model, VoxHammer first predicts its inversion trajectory and obtains its inverted latents and key-value tokens at each timestep. Subsequently, in the denoising and editing phase, we replace the denoising features of preserved regions with the corresponding inverted latents and cached key-value tokens. By retaining these contextual features, this approach ensures consistent reconstruction of preserved areas and coherent integration of edited parts. To evaluate the consistency of preserved regions, we constructed Edit3D-Bench, a human-annotated dataset comprising hundreds of samples, each with carefully labeled 3D editing regions. Experiments demonstrate that VoxHammer significantly outperforms existing methods in terms of both 3D consistency of preserved regions and overall quality. Our method holds promise for synthesizing high-quality edited paired data, thereby laying the data foundation for in-context 3D generation. See our project page at https://huanngzh.github.io/VoxHammer-Page/.