A Conditional GAN Architecture for Colorization of Thermal Infrared Images
Bibliographic record
Abstract
The applicability of visible spectrum cameras is limited to nighttime and extreme weather conditions. To overcome these limitations, infrared (IR) cameras were introduced, but their images lack luminance and representation quality, limiting the analytical ability and response time of humans. To be understandable by humans, image enhancement is not sufficient; conversion to visible RGB format is required, and this process is popularly known as colorization. However, the thermal infrared (TIR) images are low in both luminance and chrominance in comparison to grayscale images, which are only low in chrominance. Therefore, TIR colorization needs image-to-image translation; simple color transfer is not enough. In this paper, we investigated and modified one of the most commonly used conditional generative adversarial networks, known as pix2pixHD GAN for TIR-to-visible RGB translation. We are proposing a new composite loss function with noise augmentation in training. The improvement in the average values of NRMSE, PSNR, LPIPS, and NIQE is observed when compared with the state-of-the-art on the publicly available KAIST dataset. The results of the extensive experiments proved the effectiveness of the proposed method for TIR colorization, which is shown using both subjective (visual) and objective assessments for evaluation of image quality.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".