Unsupervised Single-Image Reflection Removal
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Reflections often degrade the quality of images by obstructing the background scenes. This is not desirable for everyday users, and it negatively impacts the performance of multimedia applications that process images with reflections. Most current methods for removing reflections utilize supervised learning models. These models require an extensive number of image pairs of the same scenes with and without reflections to perform well. However, collecting such image pairs is challenging and costly. Thus, most current supervised models are trained on small datasets that cannot cover the numerous possibilities of real-life images with reflections. In this paper, we propose an unsupervised method for single-image reflection removal. Instead of learning from a large dataset, we optimize the parameters of two cross-coupled deep convolutional neural networks on a target image to generate two exclusive background and reflection layers. In particular, we design a network model that embeds semantic features extracted from the input image and utilizes these features in the separation of the background layer from the reflection layer. We show through objective and subjective studies on benchmark datasets that the proposed method substantially outperforms current methods in the literature. The proposed method does not require large datasets for training, removes reflections from single images, and does not impose impractical constraints on the input images.
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.
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 | 0.000 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 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 it