# Exploring Scalable Unified Modeling for General Low-Level Vision

arXiv: https://arxiv.org/abs/2507.14801 · HTML: https://mlsanity.com/paper/2507.14801/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 65 references that are in the map.
- First posted on arXiv 20 Jul 2025.

## Builds on (most cited first, 30 of 46)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Visual Prompting via Image Inpainting](https://mlsanity.com/paper/2209.00647/) (2022)
- [Sequential Modeling Enables Scalable Learning for Large Vision Models](https://mlsanity.com/paper/2312.00785/) (2023)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)

## Built on by (most cited first, 4 of 4)

- [FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration](https://mlsanity.com/paper/2511.14099/) (2025)
- [Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation](https://mlsanity.com/paper/2512.21643/) (2025)
- [LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution](https://mlsanity.com/paper/2510.08771/) (2025)
- [SynWeather: Weather Observation Data Synthesis across Multiple Regions and Variables via a General Diffusion Transformer](https://mlsanity.com/paper/2511.08291/) (2025)

## Abstract (arXiv)

Low-level vision involves a wide spectrum of tasks, including image restoration, enhancement, stylization, and feature extraction, which differ significantly in both task formulation and output domains. To address the challenge of unified modeling across such diverse tasks, we propose a Visual task Prompt-based Image Processing (VPIP) framework that leverages input-target image pairs as visual prompts to guide the model in performing a variety of low-level vision tasks. The framework comprises an end-to-end image processing backbone, a prompt encoder, and a prompt interaction module, enabling flexible integration with various architectures and effective utilization of task-specific visual representations. Based on this design, we develop a unified low-level vision model, GenLV, and evaluate its performance across multiple representative tasks. To explore the scalability of this approach, we extend the framework along two dimensions: model capacity and task diversity. We construct a large-scale benchmark consisting of over 100 low-level vision tasks and train multiple versions of the model with varying scales. Experimental results show that the proposed method achieves considerable performance across a wide range of tasks. Notably, increasing the number of training tasks enhances generalization, particularly for tasks with limited data, indicating the model's ability to learn transferable representations through joint training. Further evaluations in zero-shot generalization, few-shot transfer, and task-specific fine-tuning scenarios demonstrate the model's strong adaptability, confirming the effectiveness, scalability, and potential of the proposed framework as a unified foundation for general low-level vision modeling.