paper-with-me

Papers

High-Frequency Enhanced Hybrid Neural Representation for Video Compression

2024-11-11 · Li Yu, Zhihui Li, Jimin Xiao, Moncef Gabbouj

Neural Representations for Videos (NeRV) have simplified the video codec process and achieved swift decoding speeds by encoding video content into a neural network, presenting a promising solution for video compression. However, existing work overlooks the crucial issue that videos reconstructed by these methods lack high-frequency details. To address this problem, this paper introduces a High-Frequency Enhanced Hybrid Neural Representation Network. Our method focuses on leveraging high-frequency information to improve the synthesis of fine details by the network. Specifically, we design a wavelet high-frequency encoder that incorporates Wavelet Frequency Decomposer (WFD) blocks to generate high-frequency feature embeddings. Next, we design the High-Frequency Feature Modulation (HFM) block, which leverages the extracted high-frequency embeddings to enhance the fitting process of the decoder. Finally, with the refined Harmonic decoder block and a Dynamic Weighted Frequency Loss, we further reduce the potential loss of high-frequency information. Experiments on the Bunny and UVG datasets demonstrate that our method outperforms other methods, showing notable improvements in detail preservation and compression performance.

📄 PDF Abstract BibTeX arXiv:2411.06685

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderVideo Compression

Similar Papers 제목 키워드 기반

Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation

2024-02-21 · Kihong Kim, Haneol Lee, JiHye Park, Seyeon Kim 외

Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent diffusion-based methods have shown compar…

Video GenerationVideo Reconstruction

SNeRV: Spectra-preserving Neural Representation for Video

2025-01-03 · Jina Kim, Jihoo Lee, Je-Won Kang

Neural representation for video (NeRV), which employs a neural network to parameterize video signals, introduces a novel methodology in video representations. However, existing NeRV-based methods have difficulty in captu…

GAT-NeRF: Geometry-Aware-Transformer Enhanced Neural Radiance Fields for High-Fidelity 4D Facial Avatars

2026-01-21 · Zhe Chang, Haodong Jin, Ying Sun, Yan Song 외 arxiv

High-fidelity 4D dynamic facial avatar reconstruction from monocular video is a critical yet challenging task, driven by increasing demands for immersive virtual human applications. While Neural Radiance Fields (NeRF) ha…

Event-to-Video Reconstruction using Spatio-Temporal and Frequency-Enhanced Deep Neural Networks

2026-05-25 · Ramna Maqsood, Paulo Nunes, Luís Ducla Soares, Caroline Conti arxiv

Event cameras offer significant advantages over conventional frame-based counterparts, including high temporal resolution, low latency, and energy efficiency. These characteristics make them suitable for high-speed and h…

Video ReconstructionScene Understanding

Frequency Enhanced Hybrid Attention Network for Sequential Recommendation

2023-04-18 · Xinyu Du, Huanhuan Yuan, Pengpeng Zhao, Jianfeng Qu 외

The self-attention mechanism, which equips with a strong capability of modeling long-range dependencies, is one of the extensively used techniques in the sequential recommendation field. However, many recent studies repr…

Contrastive LearningSequential Recommendation