# Adaptive High-Frequency Preprocessing for Video Coding

arXiv: https://arxiv.org/abs/2508.08849 · HTML: https://mlsanity.com/paper/2508.08849/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Patch-VQ: 'Patching Up' the Video Quality Problem](https://mlsanity.com/paper/2011.13544/) (2020)
- [MobileOne: An Improved One millisecond Mobile Backbone](https://mlsanity.com/paper/2206.04040/) (2022)
- [Hacking VMAF with Video Color and Contrast Distortion](https://mlsanity.com/paper/1907.04807/) (2019)
- [Hacking VMAF and VMAF NEG: vulnerability to different preprocessing methods](https://mlsanity.com/paper/2107.04510/) (2021)

## Abstract (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.