An efficient three-dimensional prediction structure for coding light field video content using the MV-HEVC standard
Bibliographic record
Abstract
Light field cameras have emerged in the consumer market as a technology that captures richer visual information than legacy cameras. While traditional photography captures only a 2D projection of the scene, the light field camera collects light intensity and direction. As a result, this technology opens new opportunities for applications such as remote surgery, autonomous driving, augmented reality, and digital health. However, one of the main problems with this technology is the size of the data captured which significantly increases the consumers' bandwidth requirements. Numerous solutions have been proposed that attempt to compress light field efficiently, but none of them fully evaluate the intricacies found in light field content. This paper proposes a three-dimensional prediction structure for compressing light field video content using the multi-view extension of HEVC (MV-HEVC). The inter-view structure exploits the correlations between the views in two directions and the high degree of resemblance between views around the centre of each frame. Experimental results show a BD-rate gain of 50.89% while subjective tests have shown a BD-rate improvement of 65.83% in mean opinion score over the state-of-the-art method. This means more visually appealing quality at a significantly reduced bitrate, thus facilitating practical implementations of the emerging technology.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".