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

• URL: http://arxiv.org/abs/2508.19247v1
• Date: Tue, 26 Aug 2025 17:59:47 GMT
• Title: VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
• Abstract summary: 3D local editing of specified regions is crucial for game industry and robot interaction.<n>Recent methods typically edit rendered multi-view images and then reconstruct 3D models.<n>We propose VoxHammer, a novel training-free approach that performs precise and coherent editing in 3D latent space.
• Score: 21.430767811940356
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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/.

Related papers

• EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning [59.36059865997641]
  We propose EditVerse3D, a novel 3D editing framework that enables high-quality object editing under coarse guidance.<n>Our approach takes as input a 3D object to be edited, a coarse 3D bounding box indicating the target region, and a reference 2D image describing the desired modification.<n>To facilitate this editing, we introduce a novel region-aware adaptive loss that emphasizes hard-to-learn regions.
  arXiv  Detail & Related papers  (2026-07-08T09:21:22Z)
• Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting [6.290910602456353]
  Existing approaches that lift 2D segmentations to the 3D domain suffer from view inconsistencies and coarse masks.<n>We propose a novel framework that leverages the Segment Anything Model High Quality to generate accurate 2D masks.<n>Our approach achieves state-of-the-art segmentation accuracy and enables interactive, real-time object editing while maintaining high visual fidelity.
  arXiv  Detail & Related papers  (2026-05-15T15:29:30Z)
• VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction [59.303842406260124]
  VGGT-Edit is a feed-forward framework for text-conditioned native 3D scene editing.<n>We introduce depth-synchronized text injection to align semantic guidance with the backbone's spatial poses.<n> VGGT-Edit substantially outperforms 2D-lifting baselines, producing sharper object details, stronger multi-view consistency, and near-instant inference speed.
  arXiv  Detail & Related papers  (2026-05-14T17:59:04Z)
• Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data [40.44238807341562]
  3D editing requires maintaining semantic consistency by performing localized changes according to prompts.<n>We propose a Beyond Voxel 3D Editing (BVE) framework with a self-constructed large-scale dataset specifically tailored for 3D editing.<n>BVE achieves superior performance in generating high-quality, text-aligned 3D assets, while faithfully retaining the visual characteristics of the original input.
  arXiv  Detail & Related papers  (2026-04-15T10:10:27Z)
• Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow [29.8200628539749]
  We propose an effective and fully feedforward 3D editing framework based on the TRELLIS generative backbone.<n>Our framework addresses two key issues: adapting training-free 2D editing to structured 3D representations, and overcoming the bottleneck of appearance fidelity in compressed 3D features.
  arXiv  Detail & Related papers  (2026-02-25T02:15:14Z)
• Error-Driven Scene Editing for 3D Grounding in Large Language Models [71.41120775319088]
  Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments.<n>This limitation stems in part from training data that focuses on language reasoning rather than spatial understanding due to scarce 3D resources.<n>We propose 3D scene editing as a key mechanism to generate precise visual counterfactuals that mitigate these biases.
  arXiv  Detail & Related papers  (2025-11-18T03:13:29Z)
• NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks [29.825760228576744]
  Nano3D is a training-free framework for precise and coherent 3D object editing without masks.<n>We construct the first large-scale 3D editing datasets Nano3D-Edit-100k, which contains over 100,000 high-quality 3D editing pairs.
  arXiv  Detail & Related papers  (2025-10-16T17:51:50Z)
• 3D-LATTE: Latent Space 3D Editing from Textual Instructions [64.77718887666312]
  We propose a training-free editing method that operates within the latent space of a native 3D diffusion model.<n>We guide the edit synthesis by blending 3D attention maps from the generation with the source object.
  arXiv  Detail & Related papers  (2025-08-29T22:51:59Z)
• Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling [13.107571213220123]
  RoMaP is a novel 3D Gaussian editing framework that enables precise and drastic part-level modifications.<n>We introduce a robust 3D mask generation module with our 3D-Geometry Label Aware Prediction.<n>We also propose a regularized SDS loss that combines the standard SDS loss with additional regularizers.
  arXiv  Detail & Related papers  (2025-07-15T07:54:11Z)
• Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models [65.90387371072413]
  We introduce Difix3D+, a novel pipeline designed to enhance 3D reconstruction and novel-view synthesis.<n>At the core of our approach is Difix, a single-step image diffusion model trained to enhance and remove artifacts in rendered novel views.
  arXiv  Detail & Related papers  (2025-03-03T17:58:33Z)
• GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generation [75.39457097832113]
  This paper introduces a novel 3D generation framework, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space.<n>Our framework employs a Variational Autoencoder with multi-view posed RGB-D(epth)-N(ormal) renderings as input, using a unique latent space design that preserves 3D shape information.<n>The proposed method, GaussianAnything, supports multi-modal conditional 3D generation, allowing for point cloud, caption, and single image inputs.
  arXiv  Detail & Related papers  (2024-11-12T18:59:32Z)
• SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing [58.22339174221563]
  We propose SyncNoise, a novel geometry-guided multi-view consistent noise editing approach for high-fidelity 3D scene editing. SyncNoise synchronously edits multiple views with 2D diffusion models while enforcing multi-view noise predictions to be geometrically consistent. Our method achieves high-quality 3D editing results respecting the textual instructions, especially in scenes with complex textures.
  arXiv  Detail & Related papers  (2024-06-25T09:17:35Z)
• LatentEditor: Text Driven Local Editing of 3D Scenes [8.966537479017951]
  We introduce textscLatentEditor, a framework for precise and locally controlled editing of neural fields using text prompts. We successfully embed real-world scenes into the latent space, resulting in a faster and more adaptable NeRF backbone for editing. Our approach achieves faster editing speeds and superior output quality compared to existing 3D editing models.
  arXiv  Detail & Related papers  (2023-12-14T19:38:06Z)
• Learning Naturally Aggregated Appearance for Efficient 3D Editing [90.57414218888536]
  We learn the color field as an explicit 2D appearance aggregation, also called canonical image.<n>We complement the canonical image with a projection field that maps 3D points onto 2D pixels for texture query.<n>Our approach demonstrates remarkable efficiency by being at least 20 times faster per edit compared to existing NeRF-based editing methods.
  arXiv  Detail & Related papers  (2023-12-11T18:59:31Z)
• Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion [115.82306502822412]
  StyleGAN has achieved great progress in 2D face reconstruction and semantic editing via image inversion and latent editing. A corresponding generic 3D GAN inversion framework is still missing, limiting the applications of 3D face reconstruction and semantic editing. We study the challenging problem of 3D GAN inversion where a latent code is predicted given a single face image to faithfully recover its 3D shapes and detailed textures.
  arXiv  Detail & Related papers  (2022-12-14T18:49:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.