AI Paper Atlas

Research map / Video / Video generation

EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation

Bingxuan Li, Yiming Cui, Yicheng He, Yiwei Wang, Shu Zhang, Longyin Wen, Yulei Niu

CVPR 2026 · Video › Video generation · approach: Video-to-audio synthesis · 2 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
use EchoVidia agentic framework instead of strongest VT2A baselineHunyuanVideo-Foley-xxl · EchoFoley-6ktemporal controllability: 0.43 -> 0.72Improved
use EchoVidia instead of strongest baselineHunyuanVideo-Foley-xxl · EchoFoley-6ktimbre controllability: 0.48 -> 0.78Improved
use EchoVidia instead of strongest baselineHunyuanVideo-Foley · EchoFoley-6khuman instruction adherence: 2.60 -> 3.80Improved
use EchoVidia instead of strongest baselineHunyuanVideo-Foley-xl · EchoFoley-6khuman audio-visual coherence: 4.20 -> 3.93Hurt
add Slow-Fast thinking (ablation)Gemini-2.5 Pro · sounding event detectionF1: 0.59 -> 0.74Improved
add Slow-Fast thinking (ablation)Qwen3-VL-30B-Thinking · sounding event detectionF1: 0.53 -> 0.71Improved
add Slow-Fast thinking (ablation)Gemini-2.5 Pro · sounding event localizationIoU: 0.510 -> 0.842Improved
add Slow-Fast thinking (ablation)Qwen3-VL-30B · sounding event localizationIoU: 0.484 -> 0.650Improved
increase control granularity from video to group to instance levelexisting VT2A models · EchoFoley-6kcontrollabilityHurt
use omni-modal models instead of vision-only VideoLLMssounding event detection · EchoFoley-6kdetection recall/F1: Qwen3-Omni-30B-Thinking F1 0.56 vs Qwen3-VL-30B-Instruct 0.49Improved

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