HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pilligua, Maria, Xue, Danna, Vazquez-Corral, Javier
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913750514139136
author Pilligua, Maria
Xue, Danna
Vazquez-Corral, Javier
author_facet Pilligua, Maria
Xue, Danna
Vazquez-Corral, Javier
contents Decomposing a video into a layer-based representation is crucial for easy video editing for the creative industries, as it enables independent editing of specific layers. Existing video-layer decomposition models rely on implicit neural representations (INRs) trained independently for each video, making the process time-consuming when applied to new videos. Noticing this limitation, we propose a meta-learning strategy to learn a generic video decomposition model to speed up the training on new videos. Our model is based on a hypernetwork architecture which, given a video-encoder embedding, generates the parameters for a compact INR-based neural video decomposition model. Our strategy mitigates the problem of single-video overfitting and, importantly, shortens the convergence of video decomposition on new, unseen videos. Our code is available at: https://hypernvd.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2503_17276
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks
Pilligua, Maria
Xue, Danna
Vazquez-Corral, Javier
Computer Vision and Pattern Recognition
Decomposing a video into a layer-based representation is crucial for easy video editing for the creative industries, as it enables independent editing of specific layers. Existing video-layer decomposition models rely on implicit neural representations (INRs) trained independently for each video, making the process time-consuming when applied to new videos. Noticing this limitation, we propose a meta-learning strategy to learn a generic video decomposition model to speed up the training on new videos. Our model is based on a hypernetwork architecture which, given a video-encoder embedding, generates the parameters for a compact INR-based neural video decomposition model. Our strategy mitigates the problem of single-video overfitting and, importantly, shortens the convergence of video decomposition on new, unseen videos. Our code is available at: https://hypernvd.github.io/
title HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.17276