AI Paper Atlas

Research map / Video / Video generation

HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion

Wenshuo Peng, Kaipeng Zhang

IJCV 2026 · Video › Video generation · approach: Video-to-audio synthesis · 1 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
add online-DPO alignment (ablation)HarmoniDPO · VGGSoundMKL / CLIP / CLAP: MKL 2.04 -> 1.86; CLIP 12.54 -> 13.27; CLAP 28.35 -> 31.75Improved
add online-DPO alignment (ablation)HarmoniDPO · VGGSoundFD: 7.72 -> 6.54Improved
add Dual-scale Diffusion Search (DDS) at inference with N=4 (ablation)HarmoniDPO aligned · VGGSoundCLAP / FD / FAD: CLAP 31.75 -> 32.57; FD 6.54 -> 6.42; FAD 1.64 -> 1.59Improved
increase online-DPO candidates from 2 to 8 (ablation)HarmoniDPO · VGGSound online-DPO candidates (no DDS)FID: 8.34 -> 6.54Improved
increase online-DPO candidates from 8 to 12 (ablation)HarmoniDPO · VGGSound online-DPO candidates (no DDS)FID / CLAP: FID 6.54 -> 6.67; CLAP 31.75 -> 32.15Mixed
use InternVid video features instead of CLIP average pooling (ablation)HarmoniDPO base · VGGSound video-condition ablation (base model w/o alignment)FID: 38.93 -> 32.16Improved
use InternVid video features instead of frame features only (ablation)HarmoniDPO base · VGGSound video-condition ablation (base model w/o alignment)FID: 38.35 -> 32.16Improved
add image frame features to video features (ablation)HarmoniDPO base · VGGSound video-condition ablation (base model w/o alignment)MKL / FID: MKL 1.894 -> 1.379; FID 39.45 -> 32.16Improved
HarmoniDPO versus FoleyCrafter on temporally hard clipsHarmoniDPO · AVSync15Onset ACC: 28.48 -> 32.53Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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