Get Started
Home
Topics
Search
Library
Research questionHow can capsule endoscopy images be super-resolved without paired data or reliable domain-specific evaluation?Capsule size and wireless transmission produce coarse-resolution endoscopy images, while real-world data lack paired low- and high-resolution examples. Reliable domain-specific assessment is also difficult without suitable reference images.
AI
Computer Vision
Evaluation & Benchmarks
Health
Image & Video Processing
Machine Learning
Research Paper
Latest papersRecent research connected to this question, newest first.UnCapsTSR: An Unsupervised Transformer-based Image Super-Resolution Approach for Capsule Endoscopy ImagesThe work uses a curated Kvasir Capsule dataset for training and evaluates generalization on KID and GIANA datasets. It reports an unsupervised transformer-based GAN using bilateral total variation loss, with no true low-resolution/high-resolution pairs or explicit degradation estimation, and assesses outputs with NIQE, BRISQUE, PIQE, and EndoQM. Evidence is limited to the reported experiments, datasets, and metrics.research paper · Sep 2, 2026
Related questions
How can single-image super-resolution recover global structure and localized aperiodic detail despite periodic spectral bases?How can deep learning provide reliable depth estimates from monocular or stereo endoscopic images?How can SAR super-resolution recover fine detail without oversmoothing or introducing physically inconsistent structure?How can surgical perception reconstruct 3D surfaces accurately from sparse endoscopic viewpoints?