Scalar and Vector Quantization for Learned Image Compression: A Study on the Effects of MSE and GAN Loss in Various Spaces.
Jonas LöhdefinkFabian HügerPeter SchlichtTim FingscheidtPublished in: ITSC (2020)
Keyphrases
- vector quantization
- image compression
- distortion measure
- wavelet transform
- fractal image compression
- subband
- vector quantizer
- compression ratio
- successive approximation
- compressed images
- input vector
- low bit rate
- image processing
- reduced complexity
- reconstructed image
- image transmission
- codebook design
- transform coding
- compression scheme
- compression algorithm
- visual quality
- entropy coding
- structural information
- image quality
- face recognition