SEGMENTATION OF IMAGE PAIRS FOR 3D RECONSTRUCTION
Bibliographic record
Abstract
Abstract. Image segmentation is an essential task in many computer vision applications such as object detection and recognition, object tracking, image classification, 3D reconstruction. Most of the current techniques utilise the colour or grayscale information of an image without considering the camera geometry. In this paper, a method is proposed to utilise the camera relative orientation of a pair of images to find a reliable object segmentation. The inputs to the method are a rectified image pair and a disparity map which could be computed from the rectified image pair, the disparity map is used to determine a set of local homographies between planar surfaces in the two images. The planar surfaces are corresponding to image segments despite the inconsistency of the RGB information. Homography based segmentation alone is not reliable due to possible noise in the disparity map and existence of non-planar objects in the scene. Therefore, an RGB technique is used as a complementary approach to enhance the segmentation result. Two colour-based segmentation techniques are used here, the first is the colour edge detector, and the second is Grabcut. Experimental results show the although the colour edge detector is a simpler algorithm than Grabcut, it does not include noisy data in the segmentation results. the This useful for 3D reconstruction, as it is preferable to exclude noisy areas like the sky and window glass. The outcome of the proposed segmentation algorithm is an object-based segmentation of the pair of images as well as a segmented disparity map.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.017 | 0.008 |
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".