# Projected Distribution Loss for Image Enhancement

arXiv: https://arxiv.org/abs/2012.09289 · HTML: https://mlsanity.com/paper/2012.09289/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2020.

## Built on by (most cited first, 29 of 29)

- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021)
- [Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration](https://mlsanity.com/paper/2303.11435/) (2023)
- [Score-Based Diffusion Models as Principled Priors for Inverse Imaging](https://mlsanity.com/paper/2304.11751/) (2023)
- [Multiscale Structure Guided Diffusion for Image Deblurring](https://mlsanity.com/paper/2212.01789/) (2022)
- [Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning](https://mlsanity.com/paper/2409.06219/) (2024)
- [Interpretable Unsupervised Diversity Denoising and Artefact Removal](https://mlsanity.com/paper/2104.01374/) (2021)
- [SPIRE: Semantic Prompt-Driven Image Restoration](https://mlsanity.com/paper/2312.11595/) (2023)
- [Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations](https://mlsanity.com/paper/2203.01325/) (2022)
- [DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space](https://mlsanity.com/paper/2208.03323/) (2022)
- [ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution](https://mlsanity.com/paper/2307.00781/) (2023)
- [Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring](https://mlsanity.com/paper/2104.12665/) (2021)
- [Variational Bayesian Imaging with an Efficient Surrogate Score-based Prior](https://mlsanity.com/paper/2309.01949/) (2023)
- [Training a Task-Specific Image Reconstruction Loss](https://mlsanity.com/paper/2103.14616/) (2021)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08763/) (2022)
- [Image Deblurring by Exploring In-depth Properties of Transformer](https://mlsanity.com/paper/2303.15198/) (2023)
- [MRI Super-Resolution with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2511.16854/) (2025)
- [Misalignment-Robust Frequency Distribution Loss for Image Transformation](https://mlsanity.com/paper/2402.18192/) (2024)
- [Adversarial Distortion Learning for Medical Image Denoising](https://mlsanity.com/paper/2204.14100/) (2022)
- [Auto-Encoded Supervision for Perceptual Image Super-Resolution](https://mlsanity.com/paper/2412.00124/) (2024)
- [Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations](https://mlsanity.com/paper/2405.02171/) (2024)
- [DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor](https://mlsanity.com/paper/2406.08377/) (2024)
- [See360: Novel Panoramic View Interpolation](https://mlsanity.com/paper/2401.03431/) (2024)
- [Self-Supervised Super-Resolution Approach for Isotropic Reconstruction of 3D Electron Microscopy Images from Anisotropic Acquisition](https://mlsanity.com/paper/2309.10646/) (2023)
- [ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction](https://mlsanity.com/paper/2411.16535/) (2024)
- [TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance](https://mlsanity.com/paper/2505.23119/) (2025)
- [Image Quality Assessment: Exploring Quality Awareness via Memory-driven Distortion Patterns Matching](https://mlsanity.com/paper/2602.18000/) (2026)
- [Causal Disentanglement-Inspired Degradation Representation Learning for Full-Reference Image Quality Assessment](https://mlsanity.com/paper/2604.21654/) (2026)

## Abstract (arXiv)

Features obtained from object recognition CNNs have been widely used for measuring perceptual similarities between images. Such differentiable metrics can be used as perceptual learning losses to train image enhancement models. However, the choice of the distance function between input and target features may have a consequential impact on the performance of the trained model. While using the norm of the difference between extracted features leads to limited hallucination of details, measuring the distance between distributions of features may generate more textures; yet also more unrealistic details and artifacts. In this paper, we demonstrate that aggregating 1D-Wasserstein distances between CNN activations is more reliable than the existing approaches, and it can significantly improve the perceptual performance of enhancement models. More explicitly, we show that in imaging applications such as denoising, super-resolution, demosaicing, deblurring and JPEG artifact removal, the proposed learning loss outperforms the current state-of-the-art on reference-based perceptual losses. This means that the proposed learning loss can be plugged into different imaging frameworks and produce perceptually realistic results.