AI Paper Atlas

Research map / Video / Video generation

MorphSIG: Subject-Driven Image Generation via Decoupled Anchoring and Feature Transport

Hailong Yan, Yongrui Zhang, Xiangtao Zhang, Le Zhang

NeurIPS 2026 · Video › Video generation · approach: Trajectory-guided motion control · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MorphSIG, a training-free subject-driven image generation framework that reformulates SIG as pseudo-video feature transport with progressive decoupled anchoring and pseudo-flow guidance.

Problem

Subject-driven image generation must preserve a reference subject's identity while composing it into new scenes; the abstract indicates existing methods suffer from structural locking during early denoising.

Approach

Reformulates subject-driven generation as pseudo-video feature transport; Progressive Decoupled Anchoring uses frequency-domain decoupling and structural scrambling in early denoising to break structural locking and transition from free composition to identity alignment, paired with Pseudo-flow Guidance.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Progressive Decoupled Anchoring (ablation)MorphSIG · ViStoryBench ablationCIDS: 0.614 -> 0.629Improved
add structural permutation to PDA (ablation)PDA · ViStoryBench ablationCIDS: 0.556 -> 0.629Improved
add spectral decoupling to PDA (ablation)PDA · ViStoryBench ablationINC: 13.57 -> 13.88Improved
use high-pass only instead of full PDA (ablation)PDA · ViStoryBench ablationCIDS: 0.629 -> 0.485Hurt
add pseudo-flow guided feature transport (WFT) (ablation)MorphSIG · ViStoryBench ablationCIDS: 0.541 -> 0.629Improved
add mutual nearest neighbor matching (ablation)WFT · ViStoryBench ablationCIDS: 0.578 -> 0.629Improved
add low-frequency SLERP (ablation)WFT · ViStoryBench ablationCIDS: 0.584 -> 0.629Improved
add high-frequency winner-take-all (ablation)WFT · ViStoryBench ablationAES: 5.14 -> 5.39Improved
replace frequency-decoupled transport with direct ADD (ablation)WFT · ViStoryBench ablationCIDS: 0.629 -> 0.561Hurt
remove WFT or SP: prompt alignment rises (ablation)MorphSIG · ViStoryBench ablationPA: w/o SP 2.72, w/o WFT 2.64 vs full 2.58Mixed
Local Consensus neighborhood K=4 (ablation)WFT · ViStoryBenchCIDS and INCImproved
extend PDA beyond 20% of denoising steps (ablation)PDA schedule · ViStoryBenchdetail alignmentHurt

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