An Adaptive Cascaded Fast Partitioning Algorithm Based on Visual Perception and Multi-Level Machine Learning
Abstract
Abstract The rapid growth of 4K/8K ultra-high-definition (UHD) video, high dynamic range (HDR) content, and 360◦ immersive media has imposed unprecedented demands on video coding effciency. However, the latest video coding standard, Versatile Video Coding (VVC), still suffers from extremely high computational complexity because coding unit (CU) partitioning is determined through exhaustive rate–distortion optimization (RDO). This issue severely limits the deployment of VVC in real-time applications. Existing fast partitioning methods usually adopt fixed decision structures and treat different content types in a uniform manner, which often leads to suboptimal trade-offs between com- plexity reduction and coding performance. To address this limitation, this paper proposes an adaptive cascaded fast partitioning framework that combines just noticeable difference (JND)-based visual perceptual analysis with multi-level machine learning. The proposed method consists of four stages: visually detectable (VD) density-based early termination, confidence-aware quadtree (QT) decision, content complexity estimation using gradient boosting, and adaptive multi-type tree (MTT) direc- tion selection with feature dimensions of 11, 19, or 27 according to texture complexity. Experimental results show that, compared with the VVC Test Model (VTM) anchor, the proposed algorithm reduces encoding time by 46.22% while increasing the Bjontegaard Delta Bit Rate (BD-BR) by only 0.90%.
How strong is the evidence?
Evidence Hub reads this as a preprint, done in computer models (in silico), not in people. Its evidence level is 5 of 5 (Very low · case / narrative / animal / in vitro / in silico). Case reports, narrative reviews, and animal, cell or computer-model studies give the weakest evidence for human health.
Read the paper
Related studies
- Regulation of nucleolus assembly by non-coding RNA polymerase II transcripts
- For a Healthy Histone Code, a Little SUMO in the Tail Keeps the Acetyl Away
- Discovering a binary CTCF code with a little help from BORIS
- Article Commentary: Stabilizing the Code–-Methods to Preserve RNA Prove Their Worth
- Foreword to the Special Issue for the RINTC (The Implicit Seismic Risk of Code-Conforming Structures) Project
- Commentary: Promoting Health and Well-being in Pediatric Primary Care Settings: Using Health and Behavior Codes at Routine Well-child Visits
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.