Velocity-Space 3D Asset Editing

• URL: http://arxiv.org/abs/2605.07385v1
• Date: Fri, 08 May 2026 07:42:12 GMT
• Title: Velocity-Space 3D Asset Editing
• Abstract summary: editing a 3D asset locally, modifying a target region while preserving the rest, is a fundamental requirement of native 3D editing.<n>We propose VS3D (Ve-Space 3D Asset editing), an inversion-free, training-free, and mask-free framework that addresses each problem with a targeted intervention inside the sampler.
• Score: 45.94997633532406
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Editing a 3D asset locally, modifying a target region while preserving the rest, is a fundamental requirement of native 3D editing. Existing methods enforce locality through mechanisms external to the generator, such as manual 3D masks, post-hoc voxel merging, or 2D multi-view lifting. None of them intervene where the corruption actually originates: inside the ODE sampler. For a rectified-flow generator to achieve faithful local editing, its velocity field should be strong over the target editing region while vanishing on preserved content. Yet a single velocity field can hardly satisfy both requirements simultaneously, leading to three problems: (i) identity leakage that keeps the edit signal non-zero on preserved regions; (ii) no dedicated edit-amplification channel, so strengthening the edit inevitably perturbs identity; and (iii) an identity drag at the geometry and material stages, where a global condition pulls every token toward the target. We propose VS3D (Velocity-Space 3D Asset editing}), an inversion-free, training-free, and mask-free framework that addresses each problem with a targeted intervention inside the sampler. VS3D integrates three complementary modules, each corresponding to a specific stage of the editing pipeline. Reconstruction-Anchored Source Injection (RASI) absorbs identity leakage by turning the unconditional embedding into a per-step, asset-specific anchor calibrated through source reconstruction. Partial-Mean Guidance (PMG) amplifies the edit signal by contrasting high- and low-quality subsample estimates of the velocity difference, active only where a consistent edit exists. Twin-Agreement Residual injection (TAR) lets the sampler decide token by token what to preserve at the geometry and material stages.

Related papers

• EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation [21.575142861728636]
  We present EditFlow3D, a training-free framework for local 3D editing.<n>Given a source asset and an edit instruction, a VLM-driven workflow interprets the editing intent.<n>Mask-guided differential flow focuses the edit on the target region.<n>Step-wise trajectory preservation maintains consistency between non-target regions and the source asset.
  arXiv  Detail & Related papers  (2026-08-04T06:16:17Z)
• Geometry-Instructed Video Editing [54.86319853573801]
  GIVE is a geometry-instructed video editing framework that represents edits through a unified object-state formulation.<n>We build a scalable graphics-engine pipeline that executes object-level edit programs and renders controlled before/after pairs.<n> Experimental results demonstrate that GIVE produces faithful geometric edits with temporal coherence and consistent secondary effects.
  arXiv  Detail & Related papers  (2026-06-23T07:11:45Z)
• EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion Models [58.566303405645726]
  We propose EditSSC, an editing-ready method for 3D semantic scene generation.<n>Our approach reshapes semantic occupancy grids into multi-channel BEV images.<n>By exploiting class-to-code correspondences in the codebook, our method supports sketch-guided generation, inpainting, and outpainting without any retraining.
  arXiv  Detail & Related papers  (2026-06-08T09:41:37Z)
• Feedforward 3D Editing Learns from Semantic-Part Transformation [13.61340944347895]
  A central challenge of feedforward 3D editing lies in the lack of high-quality paired supervision.<n>We introduce a new perspective: scalable feedforward 3D editing should be learned from semantic-part transformations.<n>PartFlow is a feedforward 3D editing network that injects source-aware latent control into pretrained 3D generative priors.
  arXiv  Detail & Related papers  (2026-05-26T17:51:59Z)
• 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)
• TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking [38.40189748889072]
  Mesh-guided 3DGS editing framework achieves automated, high-fidelity scene transformation.<n>By anchoring video diffusion with explicit 3D geometry, TRACE enables fine-grained, part-level manipulatio.
  arXiv  Detail & Related papers  (2026-04-01T17:51:00Z)
• CEI-3D: Collaborative Explicit-Implicit 3D Reconstruction for Realistic and Fine-Grained Object Editing [51.73433734209541]
  Existing 3D editing methods often produce unrealistic and unrefined results due to the deeply integrated nature of their reconstruction networks.<n>This paper introduces CEI-3D, an editing-oriented reconstruction pipeline designed to facilitate realistic and fine-grained editing.<n>Our approach achieves more realistic and fine-grained editing results than the state-of-the-art (SOTA) methods while requiring less editing time.
  arXiv  Detail & Related papers  (2026-03-12T11:15:11Z)
• 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)
• VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space [21.430767811940356]
  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.
  arXiv  Detail & Related papers  (2025-08-26T17:59:47Z)
• Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting [55.14822004410817]
  We introduce DYG, an effective 3D drag-based editing method for 3D Gaussian Splatting.<n>It enables precise control over the extent of editing through the input of 3D masks and pairs of control points.<n>DYG integrates the strengths of the implicit triplane representation to establish the geometric scaffold of the editing results.
  arXiv  Detail & Related papers  (2025-01-30T18:51:54Z)

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.