AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows

• URL: http://arxiv.org/abs/2511.22357v1
• Date: Thu, 27 Nov 2025 11:50:39 GMT
• Title: AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows
• Abstract summary: Training-free 3D editing aims to modify 3D shapes based on human instructions without model finetuning.<n>Existing approaches often struggle to produce strong or geometrically stable edits.<n>We introduce AnchorFlow, which is built upon the principle of latent anchor consistency.
• Score: 83.84009605031291
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training-free 3D editing aims to modify 3D shapes based on human instructions without model finetuning. It plays a crucial role in 3D content creation. However, existing approaches often struggle to produce strong or geometrically stable edits, largely due to inconsistent latent anchors introduced by timestep-dependent noise during diffusion sampling. To address these limitations, we introduce AnchorFlow, which is built upon the principle of latent anchor consistency. Specifically, AnchorFlow establishes a global latent anchor shared between the source and target trajectories, and enforces coherence using a relaxed anchor-alignment loss together with an anchor-aligned update rule. This design ensures that transformations remain stable and semantically faithful throughout the editing process. By stabilizing the latent reference space, AnchorFlow enables more pronounced semantic modifications. Moreover, AnchorFlow is mask-free. Without mask supervision, it effectively preserves geometric fidelity. Experiments on the Eval3DEdit benchmark show that AnchorFlow consistently delivers semantically aligned and structurally robust edits across diverse editing types. Code is at https://github.com/ZhenglinZhou/AnchorFlow.

Related papers

• SeamFlow: Structure-Aware Flow Matching on Edge Probabilities for Artist-Like UV Unwrapping [49.50766584180635]
  We introduce SeamFlow, a novel generative framework for 3D surface cutting.<n>SeamFlow achieves exceptional semantic coherence and remarkably low parameterization distortion.
  arXiv  Detail & Related papers  (2026-09-04T05:31:09Z)
• 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)
• AnchorFlow: Editable SVG Reconstruction via Sparse Anchor Point Fields [1.6513874937184163]
  Image-to-SVG reconstruction aims to produce vector graphics that are faithful to inputs and easy to edit.<n>Existing methods face a structural trade-off in how vector structure is parameterized.<n>High-fidelity methods often rely on many paths or densely parameterized curves, whereas overly compact generation may deviate from the input geometry.
  arXiv  Detail & Related papers  (2026-05-19T08:49:17Z)
• 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)
• R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow [50.93811008612562]
  Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets.<n>In real-world scenarios, the initial pose of a user-provided video rarely aligns with the starting frame of a reference video.<n>We propose R-DMesh, a framework designed to generate high-fidelity 4D meshes that align with video context.
  arXiv  Detail & Related papers  (2026-05-13T17:58:13Z)
• Velocity-Space 3D Asset Editing [45.94997633532406]
  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.
  arXiv  Detail & Related papers  (2026-05-08T07:42:12Z)
• FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing [7.08737643046839]
  FlowAnchor is a training-free framework for stable and efficient inversion-free, flow-based video editing.<n>It anchors both where to edit and how strongly to edit in high-dimensional video latent spaces.<n>It achieves more faithful, temporally coherent, and computationally efficient video editing across challenging multi-object and fast-motion scenarios.
  arXiv  Detail & Related papers  (2026-04-24T14:17:11Z)
• SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing [9.343095346668665]
  SteerFlow is a model-agnostic editing framework with strong theoretical guarantees on source fidelity.<n>We introduce Trajectory Interpolation, which adaptively blends target-editing and source-reconstruction velocities to keep the editing trajectory anchored to the source.<n>Experiments on FLUX.1-dev and Stable Diffusion 3.5 Medium demonstrate that SteerFlow consistently achieves better editing quality than existing methods.
  arXiv  Detail & Related papers  (2026-04-02T07:26:13Z)
• Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing [63.141976759536625]
  We propose Interp3D, a training-free framework for textured 3D morphing.<n>It harnesses generative priors and adopts a progressive alignment principle to ensure both geometric fidelity and texture coherence.<n>For comprehensive evaluations, we construct a dedicated dataset, Interp3DData, with graded difficulty levels and assess generation results from fidelity, transition smoothness, and plausibility.
  arXiv  Detail & Related papers  (2026-01-20T16:03:22Z)
• POCI-Diff: Position Objects Consistently and Interactively with 3D-Layout Guided Diffusion [46.97254555348757]
  We propose a diffusion-based approach for Text-to-Image (T2I) generation with consistent and interactive 3D layout control and editing.<n>We introduce a framework for Positioning Objects Consistently and Interactively (POCI-Diff)<n>Our method enables explicit per-object semantic control by binding individual text descriptions to specific 3D bounding boxes.
  arXiv  Detail & Related papers  (2026-01-20T15:13:43Z)
• AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation [56.399153019429605]
  This work shows that ignoring source dynamics yields inconsistent trajectories that suppress or merge semantic cues.<n>We reformulate text-to-3D optimization as mapping a dynamically evolving source distribution to a fixed target distribution.<n>We introduce AnchorDS, an improved score distillation mechanism that provides state-anchored guidance with image conditions.
  arXiv  Detail & Related papers  (2025-11-12T09:51:23Z)
• SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing [15.234877788378563]
  Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs.<n>Despite their strong generative capabilities, they face critical limitations in image editing tasks.<n>Recent efforts have attempted to directly map source and target distributions via ODE-based approaches without inversion.<n>We propose a flow decomposition-and-aggregation framework built upon an inversion-free formulation to address these limitations.
  arXiv  Detail & Related papers  (2025-10-29T21:12:58Z)
• FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields [20.793887576117527]
  We propose FlowDrag, which leverages geometric information for more accurate and coherent transformations.<n>Our approach constructs a 3D mesh from the image, using an energy function to guide mesh deformation based on user-defined drag points.<n>The resulting mesh displacements are projected into 2D and incorporated into a UNet denoising process, enabling precise handle-to-target point alignment.
  arXiv  Detail & Related papers  (2025-07-11T03:18:52Z)
• FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing [47.908940130654535]
  FlowAlign is an inversion-free flow-based framework for consistent image editing with optimal control-based trajectory control.<n>Our terminal point regularization is shown to balance semantic alignment with the edit prompt and structural consistency with the source image along the trajectory.<n>FlowAlign outperforms existing methods in both source preservation and editing controllability.
  arXiv  Detail & Related papers  (2025-05-29T06:33:16Z)
• OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting [54.525583840585305]
  We introduce OmniPaint, a unified framework that re-conceptualizes object removal and insertion as interdependent processes.<n>Our novel CFD metric offers a robust, reference-free evaluation of context consistency and object hallucination.
  arXiv  Detail & Related papers  (2025-03-11T17:55:27Z)
• Semantic Latent Decomposition with Normalizing Flows for Face Editing [43.41509627246366]
  Navigating in the latent space of StyleGAN has shown effectiveness for face editing. The resulting methods usually encounter challenges in complicated navigation due to the entanglement among different attributes in the latent space. This paper proposes a novel framework, termed SDFlow, with a semantic decomposition in original latent space.
  arXiv  Detail & Related papers  (2023-09-11T08:59:15Z)

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.