Cell Configuration for QoE-Aware Volumetric Video Streaming via Hierarchical Reinforcement Learning
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
Volumetric video provides immersive experiences, but it requires extremely high bandwidth to support real-time streaming. Cell-based streaming has emerged as an effective solution by culling out invisible cells and transmitting necessary content. Cell size has a significant influence on culling performance and compression efficiency. Meanwhile, the optimal cell size varies with dynamic viewports and bandwidth conditions. Therefore, it is critical to adjust cell size in real time instead of using a fixed cell size. Additionally, cell bitrate allocation plays a critical role in volumetric video streaming, as it determines the quality of each cell. It is influenced by the cell size, which directly changes the number of cells, cell spatial importance, and compression efficiency. To address the cell size and bitrate configuration, a hierarchical reinforcement learning framework is proposed to dynamically optimize these decisions, aiming to maximize quality of experience. This novel framework is evaluated through trace-driven simulations. Results demonstrate that the proposed approach effectively optimizes cell size and bitrate allocation. It significantly improves QoE compared to existing video streaming schemes with the fixed cell size, across diverse network conditions, video sources, and user behaviors.
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 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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