AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Harmonic Canvas: Inversion-Free Editing for Visually-Guided Music Style Transfer

Yue Lei, Siqi Yang, Ting Zhong, Fan Zhou

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation

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
add visual embeddings alongside text via cross-adapter (ablation)Harmonic Canvas · Modality ablationFAD: 3.15 -> 2.43Improved
use image embeddings only without text (ablation)Harmonic Canvas · Modality ablationFAD: 2.43 -> 4.06Hurt
use BLIP image captions instead of direct visual embeddings (ablation)Harmonic Canvas · Modality ablationFAD: 2.43 -> 3.49Hurt
add BLIP caption to text+image conditioning (ablation)Harmonic Canvas · Modality ablationFAD: 2.43 -> 2.86Hurt
add normalized chroma melodic guidance to FlowEdit-style inversion-free editing (ablation)Harmonic Canvas · Inversion strategiesF0-PCC: 0.368 -> 0.416Improved
add normalized chroma melodic guidance (ablation)Harmonic Canvas · Inversion strategiesCCS: 0.852 -> 0.878Improved
add normalized chroma melodic guidance (ablation)Harmonic Canvas · Inversion strategiesFAD: 2.41 -> 2.43Hurt
use inversion-free FlowEdit instead of RF Inversion (ablation)flow-based editing · Inversion strategiesF0-PCC: 0.323 -> 0.368Improved
increase chroma correction steps from 2 to 20 (ablation)Harmonic Canvas · Sensitivity analysisIMSM: 0.828 -> 0.815Hurt
increase chroma correction steps from 2 to 20 (ablation)Harmonic Canvas · Sensitivity analysisCCS: 0.878 -> 0.880No clear effect
increase guidance rate from 1e-4 to 5e-4 (ablation)Harmonic Canvas · Sensitivity analysisCCS: 0.878 -> 0.876No clear effect
use multimodal text and image cross-adapter over text-to-music baselinesHarmonic Canvas · User studyMOScon: 86.93 -> 89.20Improved

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