Deep Image Compression with Latent Optimization and Piece-wise Quantization Approximation
Yuyang Wu, Zhiyang Qi, Huiming Zheng, Lvfang Tao, Wei Gao
Abstract
Benefit from its capability of learning high-dimensional compact representation from raw data, the auto-encoders are widely used in various tasks of data compression. In particular, for deep image compression, auto-encoders generally take the responsibility of mapping original images to the latent representation to be coded. In this paper, we propose a new framework for deep image compression by devising a loss function for latent optimization, and adopting the differentiable approximation of quantization. In our experiments, both subjective and objective results can confirm the effectiveness of our contributions.
Topics & Concepts
Quantization (signal processing)Computer scienceImage compressionData compressionArtificial intelligenceDeep learningEncoderRepresentation (politics)Differentiable functionRaw dataImage (mathematics)Computer visionAlgorithmMathematicsImage processingPolitical sciencePoliticsProgramming languageLawMathematical analysisOperating systemAdvanced Data Compression TechniquesGenerative Adversarial Networks and Image SynthesisAdvanced Image Processing Techniques