Evaluating Performance of LG-CycleGAN for Photo-Sketch Generation
Bibliographic record
Abstract
Human faces are the most important part of the daily life because they are the way we connect and recognise the people on everyday basis. Face photo-sketch synthesis and identification has many applications in the modern world, which include law enforcement, improving security systems and making creative digital art or animation. In recent times, baseline CycleGAN performance has been enhanced by different improvements, but they have not been explicitly considered in maintaining facial geometry and finer feature mapping. In this paper, we have proposed the Bidirectional Photo-Sketch CycleGAN with the Landmark-Guided Style Injection model to improve the structural aspect of the face. It helps in maintaining the positions of significant facial landmarks like eyes, mouth and nose, which in return helps in retaining the form and texture of the face better when translating between photos and sketches. Both the sketch-to-photo and photo-to-sketch tasks are used in the experiments using the CUHK dataset. The results obtained from the proposed model show SSIM scores of 0.76 for photos and 0.70 for sketches, which are better than those achieved by the baseline CycleGAN model.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".