paper-with-me

홈 › Papers

A Generative Model for Hallucinating Diverse Versions of Super Resolution Images

2021-02-12 · Mohamed Abderrahmen Abid, Ihsen Hedhli, Christian Gagné

Traditionally, the main focus of image super-resolution techniques is on recovering the most likely high-quality images from low-quality images, using a one-to-one low- to high-resolution mapping. Proceeding that way, we ignore the fact that there are generally many valid versions of high-resolution images that map to a given low-resolution image. We are tackling in this work the problem of obtaining different high-resolution versions from the same low-resolution image using Generative Adversarial Models. Our learning approach makes use of high frequencies available in the training high-resolution images for preserving and exploring in an unsupervised manner the structural information available within these images. Experimental results on the CelebA dataset confirm the effectiveness of the proposed method, which allows the generation of both realistic and diverse high-resolution images from low-resolution images.

📄 PDF Abstract BibTeX arXiv:2102.06624

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-ResolutionSuper-Resolutionvalid

Similar Papers 제목 키워드 기반

Super-resolution Using Constrained Deep Texture Synthesis

2017-01-26 · Libin Sun, James Hays

Hallucinating high frequency image details in single image super-resolution is a challenging task. Traditional super-resolution methods tend to produce oversmoothed output images due to the ambiguity in mapping between l…

Image Super-ResolutionSuper-ResolutionTexture Synthesis

Learning from Hallucinating Critical Points for Navigation in Dynamic Environments

2025-09-30 · Saad Abdul Ghani, Kameron Lee, Xuesu Xiao arxiv

Generating large and diverse obstacle datasets to learn motion planning in environments with dynamic obstacles is challenging due to the vast space of possible obstacle trajectories. Inspired by hallucination-based data …

Motion Planning

Diffusion Models to Enhance the Resolution of Microscopy Images: A Tutorial

2024-09-24 · Harshith Bachimanchi, Giovanni Volpe

Diffusion models have emerged as a prominent technique in generative modeling with neural networks, making their mark in tasks like text-to-image translation and super-resolution. In this tutorial, we provide a comprehen…

DenoisingSuper-ResolutionTranslation

Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolution

2026-03-14 · Dan Wang, Haiyan Sun, Shan Du, Z. Jane Wang 외 arxiv

Image super-resolution (SR) aims to reconstruct high resolution images with both high perceptual quality and low distortion, but is fundamentally limited by the perception-distortion trade-off. GAN-based SR methods reduc…

Image Super-Resolution

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models

2024-10-24 · Changlong Wu, Ananth Grama, Wojciech Szpankowski

Generative models have shown impressive capabilities in synthesizing high-quality outputs across various domains. However, a persistent challenge is the occurrence of "hallucinations", where the model produces outputs th…