# Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noise

arXiv: https://arxiv.org/abs/2603.06095 · HTML: https://mlsanity.com/paper/2603.06095/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Neural Video Compression with Feature Modulation](https://mlsanity.com/paper/2402.17414/) (2024)
- [Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach](https://mlsanity.com/paper/2102.04170/) (2021)
- [Towards Practical Real-Time Neural Video Compression](https://mlsanity.com/paper/2502.20762/) (2025)
- [AI Flow at the Network Edge](https://mlsanity.com/paper/2411.12469/) (2024)
- [AI Flow: Perspectives, Scenarios, and Approaches](https://mlsanity.com/paper/2506.12479/) (2025)
- [Positive-incentive Noise](https://mlsanity.com/paper/2212.09541/) (2022)
- [Variational Positive-incentive Noise: How Noise Benefits Models](https://mlsanity.com/paper/2306.07651/) (2023)
- [Enhance Vision-Language Alignment with Noise](https://mlsanity.com/paper/2412.10817/) (2024)
- [Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression](https://mlsanity.com/paper/2505.16177/) (2025)
- [Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference](https://mlsanity.com/paper/2503.12926/) (2025)
- [Learn Beneficial Noise as Graph Augmentation](https://mlsanity.com/paper/2505.19024/) (2025)
- [Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2509.16738/) (2025)
- [Generative Video Compression: Towards 0.01% Compression Rate for Video Transmission](https://mlsanity.com/paper/2512.24300/) (2025)
- [Explore How to Inject Beneficial Noise in MLLMs](https://mlsanity.com/paper/2511.12917/) (2025)
- [Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model](https://mlsanity.com/paper/2407.10632/) (2024)
- [Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression](https://mlsanity.com/paper/2511.08066/) (2025)
- [Task-Oriented Communication for Vehicle-to-Infrastructure Cooperative Perception](https://mlsanity.com/paper/2407.20748/) (2024)
- [Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?](https://mlsanity.com/paper/2412.08128/) (2024)
- [Conditional Video Generation for High-Efficiency Video Compression](https://mlsanity.com/paper/2507.15269/) (2025)
- [Computation-Bandwidth-Memory Trade-offs: A Unified Paradigm for AI Infrastructure](https://mlsanity.com/paper/2601.11577/) (2025)

## Built on by (most cited first, 3 of 3)

- [PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction](https://mlsanity.com/paper/2605.20290/) (2026)
- [Uncertainty DMD: Restoring Diversity in Few-Step Autoregressive Video Distillation](https://mlsanity.com/paper/2609.11265/) (2026)
- [AquaOrbit: Sim-to-Real Reinforcement Learning for Underwater Target Orbiting under Intermittent Visual Feedback](https://mlsanity.com/paper/2609.24054/) (2026)

## Abstract (arXiv)

Static scene videos, such as surveillance feeds and videotelephony streams, constitute a dominant share of storage consumption and network traffic. However, both traditional standardized codecs and neural video compression (NVC) methods struggle to encode these videos efficiently due to inadequate usage of temporal redundancy and severe distribution gaps between training and test data, respectively. While recent generative compression methods improve perceptual quality, they introduce hallucinated details that are unacceptable in authenticity-critical applications. To overcome these limitations, we propose a positive-incentive camera (PIC) framework for static scene videos, where short-term temporal changes are reinterpreted as positive-incentive noise to facilitate NVC model finetuning. By disentangling transient variations from the persistent background, structured prior information is internalized in the compression model. During inference, the invariant component requires minimal signaling, thus reducing data transmission while maintaining pixel-level fidelity. Experiment results show that PIC achieves visually lossless reconstruction for static scenes at an extremely low compression rate of 0.009%, while the DCVC-FM baseline requires 20.5% higher Bjontegaard delta (BD) rate. Our method provides an effective solution to trade computation for bandwidth, enabling robust video transmission under adverse network conditions and economic long-term retention of surveillance footage.