Bibliographic record
Abstract
View synthesis becomes a focus of attention of both the computer vision and computer graphics communities. It consists of creating novel images of a scene as it would appear from novel viewpoints. View synthesis can be used in a wide variety of applications such as video compression, graphics generation, virtual reality and entertainment. This paper addresses the following problem. Given a dense disparity map between two reference images, we would like to synthesize a novel view of the same scene associated with a novel viewpoint. Most of the existing work is relying on building a set of 3D meshes which are then projected onto the new image (the rendering process is performed using texture mapping). The advantages of our view synthesis approach are as follows. First, the novel view is specified by a rotation and a translation which are the most natural way to express the virtual location of the camera. Second, the approach is able to synthesize highly realistic images whose viewing position is significantly far away from the reference viewpoints. Third, the approach is able to handle the visibility problem during the synthesis process. Our developed framework has two main steps. The first step (analysis step) consists of computing the homography at infinity, the epipoles, and thus the parallax field associated with the reference images. The second step (synthesis step) consists of warping the reference image into a new one, which is based on the invariance of the computed parallax field. The analysis step is working directly on the reference views, and only need to be performed once. Examples of synthesizing novel views using either feature correspondences or dense disparity map have demonstrated the feasibility of the proposed approach.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.240 | 0.179 |
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".