Comparative Analysis of Super Resolution Techniques in Micro-CT Imaging
Bibliographic record
Abstract
Summary Image super-resolution is crucial in computer vision, particularly for enhancing micro-CT images which are essential for detailed scientific analysis. This technique involves reconstructing high-resolution images from their lower-resolution versions, focusing on improving image details and sharpness. Our study tested three deep learning models—PRIDNet, MW-CNN, and VDSR—on a dataset of 1400 uniformly sized images, downsampled by a factor of three for the experiment. We evaluated model performance using various metrics including SSIM, MS-SSIM, PSNR, and UIQ, which assess similarity, quality across scales, error, and image distortion respectively. A targeted experimental strategy was employed to optimize performance by exploring different combinations of loss functions. The best results were achieved by adapting loss functions specific to each model’s needs, with combinations like L1+MS-SSIM proving effective in enhancing perceptual quality by preserving structural information. This emphasizes the critical role of carefully selecting both the model and its corresponding loss function for superior super-resolution outcomes in specialized imaging applications like microscopy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".