IVMMDec 15, 2019

Characterizing Generalized Rate-Distortion Performance of Video Coding: An Eigen Analysis Approach

arXiv:1912.07126v3
Originality Incremental advance
AI Analysis

This work addresses the problem of efficient video compression modeling for researchers and engineers, though it appears incremental as it builds on existing rate-distortion theory with a novel computational approach.

The paper tackled modeling the generalized rate-distortion trade-off in video compression by defining a theoretical functional space and developing a low-parameter eigen method to estimate it from sparse measurements, achieving significant improvements in accuracy and efficiency over state-of-the-art empirical methods.

Rate-distortion (RD) theory is at the heart of lossy data compression. Here we aim to model the generalized RD (GRD) trade-off between the visual quality of a compressed video and its encoding profiles (e.g., bitrate and spatial resolution). We first define the theoretical functional space $\mathcal{W}$ of the GRD function by analyzing its mathematical properties.We show that $\mathcal{W}$ is a convex set in a Hilbert space, inspiring a computational model of the GRD function, and a method of estimating model parameters from sparse measurements. To demonstrate the feasibility of our idea, we collect a large-scale database of real-world GRD functions, which turn out to live in a low-dimensional subspace of $\mathcal{W}$. Combining the GRD reconstruction framework and the learned low-dimensional space, we create a low-parameter eigen GRD method to accurately estimate the GRD function of a source video content from only a few queries. Experimental results on the database show that the learned GRD method significantly outperforms state-of-the-art empirical RD estimation methods both in accuracy and efficiency. Last, we demonstrate the promise of the proposed model in video codec comparison.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes