No article text was recorded for this version.
pixel-wise loss limitations (reconstruction blurriness)
Version 1 of 1697 papers741 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization
- Blog: Attention Hybrid Variational Net for Accelerated MRI Reconstruction
- Blog: Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcasting
- Blog: Revisiting RCAN: Improved Training for Image Super-Resolution
- Blog: Learning to Generate Chairs with Convolutional Neural Networks
- Blog: ShapeCodes: Self-supervised Feature Learning by Lifting Views to Viewgrids
- Blog: AH-GS: Augmented 3D Gaussian Splatting for High-Frequency Detail Representation
- Blog: Real-Time Environment Monitoring Using a Lightweight Image Super-Resolution Network
- Blog: WeatherBench: A Benchmark Data Set for Data-Driven Weather Forecasting
- Blog: Naive Bayes Super-Resolution Forest
- Blog: Projected Distribution Loss for Image Enhancement
- Blog: DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans
- Blog: Autoencoders
- Blog: ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids
- Blog: Synthesizing Normalized Faces from Facial Identity Features
- Blog: Wavelet-based Loss for High-frequency Interface Dynamics
- Blog: Denoising Prior Driven Deep Neural Network for Image Restoration
- Blog: ACE Metric: Advection and Convection Evaluation for Accurate Weather Forecasting
- Blog: MultiMAE for Brain MRIs: Robustness to Missing Inputs Using Multi-modal Masked Autoencoder
- Blog: Low-Dose CT via Deep CNN with Skip Connection and Network in Network
- Blog: CAA-Net: End-to-End Two-Branch Feature Attention Network for Single Image Dehazing
- Blog: One-to-Many Network for Visually Pleasing Compression Artifacts Reduction
- Blog: Video Inpainting by Jointly Learning Temporal Structure and Spatial Details
- Blog: Comparing Correspondences: Video Prediction with Correspondence-wise Losses
- Blog: One-To-Many Network for Visually Pleasing Compression Artifacts Reduction
- Blog: Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization
- Blog: Multi-Outputs Is All You Need For Deblur
- Blog: What Hinders Perceptual Quality of PSNR-oriented Methods?
- Blog: Uncovering the Over-Smoothing Challenge in Image Super-Resolution: Entropy-Based Quantification and Contrastive Optimization
- Blog: Image Super-Resolution Using Dense Skip Connections
- Blog: Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation
- Blog: Impact of loss functions on the performance of a deep neural network designed to restore low-dose digital mammography
- Blog: Predicting tongue motion in unlabeled ultrasound videos using convolutional LSTM neural network
- Blog: Generating Images with Perceptual Similarity Metrics based on Deep Networks
- Blog: Single-Frame Super-Resolution of Solar Magnetograms: Investigating Physics-Based Metrics \& Losses
- Blog: PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
- Blog: Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcasting
- Blog: Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring
- Blog: Rethinking RGB Color Representation for Image Restoration Models
- Blog: IEGAN: Multi-Purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network
- Blog: Deep Semantic Statistics Matching (D2SM) Denoising Network
- Blog: Image Super-Resolution via Iterative Refinement
- Blog: EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution
- Blog: Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks
- Blog: LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction
- Blog: Generative Novel View Synthesis with 3D-Aware Diffusion Models
- Blog: DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
- Blog: Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
- Blog: Physics-Driven Turbulence Image Restoration with Stochastic Refinement
- Blog: Building Machine Learning Limited Area Models: Kilometer-Scale Weather Forecasting in Realistic Settings
- Blog: Understanding and Simplifying Perceptual Distances
- Blog: A Flexible Neural Renderer for Material Visualization
- Blog: Adaptive Gradient Balancing for Undersampled MRI Reconstruction and Image-to-Image Translation
- Blog: Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild
- Blog: GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images
- Blog: SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models
- Blog: A Deep Journey into Super-resolution: A Survey
- Blog: Accurate and Clear Precipitation Nowcasting with Consecutive Attention and Rain-map Discrimination
- Blog: Novel View Synthesis with Diffusion Models
- Blog: NIPS 2016 Tutorial: Generative Adversarial Networks
Showing 60 of 697 papers.
History & citation
Current · Permanent link
- Moving Beyond Pixel-Wise Loss in Image Reconstruction merged into this direction (89% overlap)
- Overcoming Regression to the Mean in Image Reconstruction merged into this direction (75% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_pixel_wise_loss_limitations_reconstructi_9cb116e5,
title = {pixel-wise loss limitations (reconstruction blurriness)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pixel-wise-loss-limitations-reconstruction-blurriness/rdr_9cb116e54dc24c2988f1607e8e79917e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_pixel_wise_loss_limitations_reconstructi_9cb116e5_v1,
title = {pixel-wise loss limitations (reconstruction blurriness)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/pixel-wise-loss-limitations-reconstruction-blurriness/rdr_9cb116e54dc24c2988f1607e8e79917e/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}