MétaCan
Menu
Back to cohort
Record W2891249168 · doi:10.1109/pcs.2018.8456257

A Method to Improve Perceptual Quality of Intra- Refresh-Enabled Low-Latency Video Coding

2018· article· en· W2891249168 on OpenAlex

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicVideo Coding and Compression Technologies
Canadian institutionsAdvanced Micro Devices (Canada)
Fundersnot available
KeywordsComputer scienceEncoderLatency (audio)Quantization (signal processing)Coding (social sciences)Real-time computingVideo qualityEncoding (memory)Virtual channelChannel (broadcasting)Computer visionComputer hardwareArtificial intelligenceComputer networkTelecommunications

Abstract

fetched live from OpenAlex

A typical video encoder includes into the generated bit stream Instantaneous Decoder Refresh (IDR) units. This allows random access playback at the receiver side as well as graceful recovery from potential channel errors. Such forced IDR units typically come in repetitive patterns, which may negatively impact the perceived subjective quality if not handled properly. The reason is that the restricted encoding process of an IDR unit results in a different (regardless higher or lower) quality of reconstructed signal compared to the surrounding non-IDR ones. This causes eye-capturing irritating periodical artifacts when it occurs in patterns. This phenomenon gets to be even more pronounced when the intra refresh feature is enabled, since it forces IDR and nonIDR units to co-exist within the same picture, making the quality difference more noticeable. This paper proposes a method to hide such undesired patterns that naturally accompany the intra refresh feature. Two ideas are presented; the first one imposes restrictions that prevent unwanted fluctuations in the quantization levels between different regions of the picture, while the second hides the repetitive pattern by randomly forcing IDR blocks within specific regions of the refreshed picture. Results show that the proposed method results in improvements in subjective quality.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.557
Threshold uncertainty score0.589

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.040
GPT teacher head0.341
Teacher spread0.301 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it