# Loss Functions for Neural Networks for Image Processing

arXiv: https://arxiv.org/abs/1511.08861 · HTML: https://mlsanity.com/paper/1511.08861/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2015.

## Built on by (most cited first, 30 of 41)

- [Deep learning-based synthetic-CT generation in radiotherapy and PET: a review](https://mlsanity.com/paper/2102.02734/) (2021)
- [SurfaceNet: Adversarial SVBRDF Estimation from a Single Image](https://mlsanity.com/paper/2107.11298/) (2021)
- [Anomaly Detection via Self-organizing Map](https://mlsanity.com/paper/2107.09903/) (2021)
- [Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation](https://mlsanity.com/paper/2210.15878/) (2022)
- [Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications](https://mlsanity.com/paper/2103.16910/) (2021)
- [Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation](https://mlsanity.com/paper/2203.09737/) (2022)
- [Functional Neural Networks for Parametric Image Restoration Problems](https://mlsanity.com/paper/2111.00361/) (2021)
- [Model-based Behavioral Cloning with Future Image Similarity Learning](https://mlsanity.com/paper/1910.03157/) (2019)
- [Selective Pseudo-label Clustering](https://mlsanity.com/paper/2107.10692/) (2021)
- [Computing Multiple Image Reconstructions with a Single Hypernetwork](https://mlsanity.com/paper/2202.11009/) (2022)
- [Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery](https://mlsanity.com/paper/2404.10356/) (2024)
- [On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation](https://mlsanity.com/paper/2109.06163/) (2021)
- [Multi-scale Restoration of Missing Data in Optical Time-series Images with Masked Spatial-Temporal Attention Network](https://mlsanity.com/paper/2406.13358/) (2024)
- [Vision Learners Meet Web Image-Text Pairs](https://mlsanity.com/paper/2301.07088/) (2023)
- [Imaging foundation model for universal enhancement of non-ideal measurement CT](https://mlsanity.com/paper/2410.01591/) (2024)
- [UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement](https://mlsanity.com/paper/2512.02965/) (2025)
- [Ada-VSR: Adaptive Video Super-Resolution with Meta-Learning](https://mlsanity.com/paper/2108.02832/) (2021)
- [FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical Flow](https://mlsanity.com/paper/2111.10531/) (2021)
- [HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI Reconstruction](https://mlsanity.com/paper/2508.09179/) (2025)
- [An Unsupervised Framework for Joint MRI Super Resolution and Gibbs Artifact Removal](https://mlsanity.com/paper/2302.02849/) (2023)
- [Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection](https://mlsanity.com/paper/2303.16191/) (2023)
- [MCU-Net: A Multi-prior Collaborative Deep Unfolding Network with Gates-controlled Spatial Attention for Accelerated MR Image Reconstruction](https://mlsanity.com/paper/2402.03383/) (2024)
- [SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation](https://mlsanity.com/paper/2601.17657/) (2026)
- [Multitask Learning for VVC Quality Enhancement and Super-Resolution](https://mlsanity.com/paper/2104.08319/) (2021)
- [Robotic Inspection of Underground Utilities for Construction Survey Using a Ground Penetrating Radar](https://mlsanity.com/paper/2106.01907/) (2021)
- [Image quality measurements and denoising using Fourier Ring Correlations](https://mlsanity.com/paper/2201.03992/) (2022)
- [RSINet: Inpainting Remotely Sensed Images Using Triple GAN Framework](https://mlsanity.com/paper/2202.05988/) (2022)
- [Attention-based Knowledge Distillation in Multi-attention Tasks: The Impact of a DCT-driven Loss](https://mlsanity.com/paper/2205.01997/) (2022)
- [Deep Learning Techniques for Visual Counting](https://mlsanity.com/paper/2206.03033/) (2022)
- [VoloGAN: Adversarial Domain Adaptation for Synthetic Depth Data](https://mlsanity.com/paper/2207.09204/) (2022)

## Abstract (arXiv)

Neural networks are becoming central in several areas of computer vision and image processing and different architectures have been proposed to solve specific problems. The impact of the loss layer of neural networks, however, has not received much attention in the context of image processing: the default and virtually only choice is L2. In this paper, we bring attention to alternative choices for image restoration. In particular, we show the importance of perceptually-motivated losses when the resulting image is to be evaluated by a human observer. We compare the performance of several losses, and propose a novel, differentiable error function. We show that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged.