# LiteVPNet: A Lightweight Network for Video Encoding Control in Quality-Critical Applications

arXiv: https://arxiv.org/abs/2510.12379 · HTML: https://mlsanity.com/paper/2510.12379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 14 Oct 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph](https://mlsanity.com/paper/2309.13625/) (2023)
- [CLIPVQA:Video Quality Assessment via CLIP](https://mlsanity.com/paper/2407.04928/) (2024)
- [Green Video Complexity Analysis for Efficient Encoding in Adaptive Video Streaming](https://mlsanity.com/paper/2304.12384/) (2023)
- [Quality-Constant Per-Shot Encoding by Two-Pass Learning-based Rate Factor Prediction](https://mlsanity.com/paper/2208.10739/) (2022)
- [Just Noticeable Difference-aware Per-Scene Bitrate-laddering for Adaptive Video Streaming](https://mlsanity.com/paper/2305.00225/) (2023)
- [Demystifying the use of Compression in Virtual Production](https://mlsanity.com/paper/2411.00547/) (2024)
- [Content-Adaptive Rate-Quality Curve Prediction Model in Media Processing System](https://mlsanity.com/paper/2411.05295/) (2024)

## Abstract (arXiv)

In the last decade, video workflows in the cinema production ecosystem have presented new use cases for video streaming technology. These new workflows, e.g. in On-set Virtual Production, present the challenge of requiring precise quality control and energy efficiency. Existing approaches to transcoding often fall short of these requirements, either due to a lack of quality control or computational overhead. To fill this gap, we present a lightweight neural network (LiteVPNet) for accurately predicting Quantisation Parameters for NVENC AV1 encoders that achieve a specified VMAF score. We use low-complexity features, including bitstream characteristics, video complexity measures, and CLIP-based semantic embeddings. Our results demonstrate that LiteVPNet achieves mean VMAF errors below 1.2 points across a wide range of quality targets. Notably, LiteVPNet achieves VMAF errors within 2 points for over 87% of our test corpus, c.f. approx 61% with state-of-the-art methods. LiteVPNet's performance across various quality regions highlights its applicability for enhancing high-value content transport and streaming for more energy-efficient, high-quality media experiences.