AI Paper Atlas

Research map / Image generation / Editing and style transfer

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

Zhenglin Zhou, Fan Ma, Chengzhuo Gui, Xiaobo Xia, Hehe Fan, Yi Yang, Tat-Seng Chua

CVPR 2026 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace timestep-wise random anchors with anchor-aligned updateHunyuan3D 2.1 inversion-free editing · Eval3DEdit (overall)CLIP-txt: 0.4705 -> 0.4866Improved
replace timestep-wise random anchors with anchor-aligned updateHunyuan3D 2.1 inversion-free editing · Eval3DEdit (overall)CLIP-img: 0.7106 -> 0.7173Improved
anchor-aligned update on object removalinversion-free editing · Eval3DEdit, Object RemovalCLIP-img / CLIP-txt: CLIP-img 0.7293 -> 0.7167; CLIP-txt 0.4884 -> 0.4735Hurt
anchor-aligned update on object additioninversion-free editing · Eval3DEdit, Object AdditionCLIP-txt: 0.4441 -> 0.4758Improved
use direct editing from the edited image instead of latent-space editing methodsHunyuan3D 2.1 · Eval3DEdit (overall)CLIP-img: 0.7173 -> 0.6152Hurt
average multiple noisy flow directions (n_avg) (ablation)AnchorFlow and inversion-free editing · Eval3DEditediting qualityImproved
increase n_max and s_tar (35,5.0 to 41,7.5) (ablation)AnchorFlow · Eval3DEditCLIP-txt vs CLIP-imgMixed
larger n_max and s_tar for action change; smaller for removal and style (ablation)AnchorFlow · Eval3DEditCLIP-img and CLIP-txtImproved
use anchor-aligned update instead of inversion-free update (runtime)AnchorFlow · Eval3DEdit timetime (s): 25.77 -> 26.71No clear effect

Later papers that compared with this method

1 later accepted paper reports AnchorFlow as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy