Decoupling Video Upscaling from Rendering for Cloud Gaming
Bibliographic record
Abstract
Many recent video games require powerful hardware to render them. To reduce such high hardware requirements, upscalers have been proposed in the literature and industry. Upscalers save computing resources by first rendering games at lower resolutions and frame rates and then upscaling them to improve players' quality of experience. Current upscalers, however, are tightly coupled with the rendering logic of video games, which requires updating the source code of each game for every upscaler. This increases the development cost and limits the use of upscalers. The tight coupling also stifles the deployment of upscalers in cloud gaming platforms to reduce the required computing resources. We propose decoupling upscalers from game renderers, which allows utilizing various upscalers with games without changing their source code. It also accelerates deploying upscalers in cloud gaming. Decoupling upscalers from renderers is, however, challenging because of the diversity of upscalers, their dependency on information at different rendering stages, and the strict timing requirements of video games. We present an efficient solution that addresses these challenges. We implement the proposed solution and demonstrate its effectiveness with two popular upscalers. We also develop a cloud gaming system in the emerging Media-over-QUIC (MoQ) protocol and implement the proposed approach with it. Our experiments show the potential savings in computing resources while meeting the strict timing constraints of video games.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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".