Congratulations to Aolin Feng for passing his Qualifying Exam! His thesis proposal is titled “ Green Image Coding: Principle, Implementation, and Performance Evaluation.” His Qualifying Exam Committee members include Jay Kuo (Chair), Antonio Ortega, Bhaskar Krishnamachari, Feng Qian, and Shanghao Teng (Outside Member). Here is a summary of his thesis proposal:
Image compression has long been dominated by two paradigms: the hybrid coding framework that adopts prediction and transform followed by scalar quantization, and deep learning-based codecs that leverage end-to-end optimization. While hybrid codecs offer reliable rate–distortion (RD) performance, they face a bottleneck for RD gain when integrating additional coding tools. In contrast, deep learning-based codecs achieve superior RD performance through end-to-end optimization but often suffer from high computational cost, especially for the decoder side.
The thesis proposal introduces Green Image Coding (GIC), a novel framework aiming for lightweight, RD-efficient, and scalable image compression. Different from the hybrid and deep learning-based coding, GIC is built upon two key designs: multigrid representation and vector quantization (VQ). The multigrid representation decomposes images into hierarchical layers, redistributing energy and reducing intra-layer content diversity. Each layer is then encoded using VQ-based techniques.
Regarding the two key designs, we contribute both theoretical foundations and practical solutions: multigrid rate control and a set of advanced VQ techniques. For the multigrid rate control, we develop a theory that reduces a high-dimensional optimization to equivalent sequential parameter decisions, with comprehensive experimental validation. The theoretical conclusion guides the design of our rate control strategy, which improves the scalability and balance between rate and distortion. For the advanced VQ techniques, we start with tree-structured vector quantization (TSVQ) to build multi-rate coding capability, and propose an RD-oriented VQ codebook construction method. We also propose the cascade VQ strategy to tackle the early convergence issue of the high-dimensional VQ. And we extend the cascade strategy to operate across multiple block sizes, covering a wide bit rate range. Furthermore, we combine the multi-dimensional VQs together via a quadtree structure, overcoming the statistical issues when executing VQ-based rate-distortion-optimization (RDO).
Experimental results demonstrate that GIC achieves competitive coding efficiency while maintaining low theoretical complexity. Furthermore, the modular, interpretable, and learning-based design of GIC offers excellent potential for further improvement. It also shows strong promise as an extension module for existing codecs, as well as a foundation for future video coding research.
