2018/04/25 by Zhengxue Cheng, Heming Sun, Cheng, Zhengxue +5 · 6 citations
Computer Science · #Advanced Data Compression Techniques #Advanced Image Processing Techniques #Algorithm #Artificial intelligence #Autoencoder #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Convolutional neural network #Data compression #Data compression ratio #Deep learning #Encoder #FOS: Computer and information sciences #Image (mathematics) #Image and Signal Denoising Methods #Image compression #Image processing #JPEG 2000 #Lossy compression #Pattern recognition (psychology) #Quantization (signal processing) #cs.CV
paper · pdf · doi:10.48550/arxiv.1804.09535
published in arXiv (Cornell University) (Cornell University) · accepted by Picture Coding Symposium 2018
arxiv created 2018/04/25 · openalex publication_date 2018/04/25 · arxiv updated 2018/04/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture to replace the conventional transforms and train this CAE using a rate-distortion loss function. Second, to generate a more energy-compact representation, we utilize the principal components analysis (PCA) to rotate the feature maps produced by the CAE, and then apply the quantization and entropy coder to generate the codes. Experimental results demonstrate that our method outperforms traditional image coding algorithms, by achieving a 13.7% BD-rate decrement on the Kodak database images compared to JPEG2000. Besides, our method maintains a moderate complexity similar to JPEG2000.