AI/ ai · research · computer-vision · arxiv

A Leaner AI Model Segments Sound and Video 3x Faster

EASE, a stripped-down encoder-only model, matches top audio-visual segmentation accuracy at up to 365 frames per second and trains in under 11 GPU-hours.

A team of researchers just proved that audio-visual segmentation models have been carrying a lot of dead weight.

The new model, called EASE (Encoder-only Audio-Visual Segmentation), strips out the decoder stage that most Transformer-based segmentation systems inherited from image models. Detailed in a paper posted to arXiv (arXiv:2609.29121), EASE identifies, segments, and classifies sound-emitting objects in video frames using only an encoder. It runs at up to 365 frames per second - three times faster than the previous state-of-the-art at similar accuracy - and trains in under 11 GPU-hours. The team says EASE also hits state-of-the-art segmentation scores across multiple backbones and input resolutions.

Audio-visual segmentation underpins things like real-time captioning, surveillance analytics, and AR overlays that need to know which object on screen is making which sound. A model that trains in 11 GPU-hours instead of days lowers the barrier for smaller labs to iterate on this work, and a 3x speed jump matters for anything that has to run live instead of getting processed after the fact.

Code and model weights are posted at https://ease-avs.notion.site, which is more than most papers claiming to be faster and better bother to share.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →