paper-with-me

Papers

Adaptive High-Frequency Preprocessing for Video Coding

2025-08-12 · Yingxue Pang, Shijie Zhao, Junlin Li, Li Zhang arxiv

High-frequency components are crucial for maintaining video clarity and realism, but they also significantly impact coding bitrate, resulting in increased bandwidth and storage costs. This paper presents an end-to-end learning-based framework for adaptive high-frequency preprocessing to enhance subjective quality and save bitrate in video coding. The framework employs the Frequency-attentive Feature pyramid Prediction Network (FFPN) to predict the optimal high-frequency preprocessing strategy, guiding subsequent filtering operators to achieve the optimal tradeoff between bitrate and quality after compression. For training FFPN, we pseudo-label each training video with the optimal strategy, determined by comparing the rate-distortion (RD) performance across different preprocessing types and strengths. Distortion is measured using the latest quality assessment metric. Comprehensive evaluations on multiple datasets demonstrate the visually appealing enhancement capabilities and bitrate savings achieved by our framework.

📄 PDF Abstract BibTeX arXiv:2508.08849

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Rate-Perception Optimized Preprocessing for Video Coding

2023-01-25 · Chengqian Ma, Zhiqiang Wu, Chunlei Cai, Pengwei Zhang 외

In the past decades, lots of progress have been done in the video compression field including traditional video codec and learning-based video codec. However, few studies focus on using preprocessing techniques to improv…

Image Quality AssessmentVideo Compression

A Tri-Dynamic Preprocessing Framework for UGC Video Compression

2025-12-18 · Fei Zhao, Mengxi Guo, Shijie Zhao, Junlin Li 외 arxiv

In recent years, user generated content (UGC) has become the dominant force in internet traffic. However, UGC videos exhibit a higher degree of variability and diverse characteristics compared to traditional encoding tes…

Frequency-Modulated Point Cloud Rendering with Easy Editing

2023-03-14 · CVPR 2023 1 · Yi Zhang, Xiaoyang Huang, Bingbing Ni, Teng Li 외

We develop an effective point cloud rendering pipeline for novel view synthesis, which enables high fidelity local detail reconstruction, real-time rendering and user-friendly editing. In the heart of our pipeline is an …

NeRFNovel View SynthesisSSIM

SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization

2021-04-19 · NeurIPS 2021 12 · Amir Hertz, Or Perel, Raja Giryes, Olga Sorkine-Hornung 외

Multilayer-perceptrons (MLP) are known to struggle with learning functions of high-frequencies, and in particular cases with wide frequency bands. We present a spatially adaptive progressive encoding (SAPE) scheme for in…

Representation Learning

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. …

DecoderVideo Compression