# Learned Perceptual Image Enhancement

arXiv: https://arxiv.org/abs/1712.02864 · HTML: https://mlsanity.com/paper/1712.02864/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2017.

## Built on by (most cited first, 18 of 18)

- [Few-shot Image Generation via Adaptation-Aware Kernel Modulation](https://mlsanity.com/paper/2210.16559/) (2022)
- [Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment](https://mlsanity.com/paper/2307.16813/) (2023)
- [Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond](https://mlsanity.com/paper/2104.01493/) (2021)
- [Progressive Joint Low-light Enhancement and Noise Removal for Raw Images](https://mlsanity.com/paper/2106.14844/) (2021)
- [Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals](https://mlsanity.com/paper/2305.18425/) (2023)
- [NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image](https://mlsanity.com/paper/2312.07315/) (2023)
- [Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images](https://mlsanity.com/paper/2405.09426/) (2024)
- [A study of deep perceptual metrics for image quality assessment](https://mlsanity.com/paper/2202.08692/) (2022)
- [Diff-GO: Diffusion Goal-Oriented Communications to Achieve Ultra-High Spectrum Efficiency](https://mlsanity.com/paper/2312.02984/) (2023)
- [CLIP Brings Better Features to Visual Aesthetics Learners](https://mlsanity.com/paper/2307.15640/) (2023)
- [The Loop Game: Quality Assessment and Optimization for Low-Light Image Enhancement](https://mlsanity.com/paper/2202.09738/) (2022)
- [Solving Image PDEs with a Shallow Network](https://mlsanity.com/paper/2110.08327/) (2021)
- [Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs](https://mlsanity.com/paper/2202.04109/) (2022)
- [AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation](https://mlsanity.com/paper/2307.01465/) (2023)
- [LaMI-GO: Latent Mixture Integration for Goal-Oriented Communications Achieving High Spectrum Efficiency](https://mlsanity.com/paper/2412.17839/) (2024)
- [Scene Perceived Image Perceptual Score (SPIPS): combining global and local perception for image quality assessment](https://mlsanity.com/paper/2504.17234/) (2025)
- [Visual Verity in AI-Generated Imagery: Computational Metrics and Human-Centric Analysis](https://mlsanity.com/paper/2408.12762/) (2024)
- [Beyond Imperfections: A Conditional Inpainting Approach for End-to-End Artifact Removal in VTON and Pose Transfer](https://mlsanity.com/paper/2410.04052/) (2024)

## Abstract (arXiv)

Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images. While L1 and L2 losses are perhaps the most widely used functions for this purpose, they do not necessarily lead to perceptually compelling results. In this paper, we show that adding a learned no-reference image quality metric to the loss can significantly improve enhancement operators. This metric is implemented using a CNN (convolutional neural network) trained on a large-scale dataset labelled with aesthetic preferences of human raters. This loss allows us to conveniently perform back-propagation in our learning framework to simultaneously optimize for similarity to a given ground truth reference and perceptual quality. This perceptual loss is only used to train parameters of image processing operators, and does not impose any extra complexity at inference time. Our experiments demonstrate that this loss can be effective for tuning a variety of operators such as local tone mapping and dehazing.