paper-with-me

홈 › Papers

HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks

2025-03-21 · CVPR 2025 1 · Maria Pilligua, Danna Xue, Javier Vazquez-Corral

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/

📄 PDF Abstract BibTeX arXiv:2503.17276

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningVideo Editing

Methods 이 논문이 사용한 방법론

HyperNetwork A HyperNetwork is a network that generates weights for a main network. The behavior of the main network is the same with any usual neural network: it learns to map some raw…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance

2025-10-03 · Hao Zhang, Zhenjia Li, Runfeng Bao, Yifan Gao 외 arxiv

Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computational and memory overhead. However, LoR…

parameter-efficient fine-tuning

HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks

2023-05-10 · Burak Ercan, Onur Eker, Canberk Saglam, Aykut Erdem 외

Event-based cameras are becoming increasingly popular for their ability to capture high-speed motion with low latency and high dynamic range. However, generating videos from events remains challenging due to the highly s…

Event-Based Video ReconstructionVideo Reconstruction

HyperNetworks

2016-09-27 · David Ha, Andrew Dai, Quoc V. Le

This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network. Hypernetworks provide an abstraction that is similar to what is found in na…

Handwriting generationLanguage ModellingMachine TranslationTranslation

Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics

2024-08-05 · Shishira R Maiya, Anubhav Gupta, Matthew Gwilliam, Max Ehrlich 외

Implicit Neural Networks (INRs) have emerged as powerful representations to encode all forms of data, including images, videos, audios, and scenes. With video, many INRs for video have been proposed for the compression t…

RetrievalVideo Retrieval

Effect of Optimizer, Initializer, and Architecture of Hypernetworks on Continual Learning from Demonstration

2023-12-31 · Sayantan Auddy, Sebastian Bergner, Justus Piater

In continual learning from demonstration (CLfD), a robot learns a sequence of real-world motion skills continually from human demonstrations. Recently, hypernetworks have been successful in solving this problem. In this …

Continual Learning