Soft decoding of JPEG 2000 compressed images using bit-rate-driven deep convolutional neural networks.
Xiaohai HeHonggang ChenJingxu ChenLinbo QingPublished in: ICIA (2017)
Keyphrases
- bit rate
- jpeg compressed images
- convolutional neural networks
- image quality
- visual quality
- rate distortion
- compressed images
- bitstream
- video coding
- subband
- low bit rate
- reconstructed image
- macroblock
- motion vectors
- coding method
- inter frame
- computational complexity
- dct domain
- coding efficiency
- prediction error
- video quality
- digital images
- entropy coding
- human visual system
- decoding algorithm
- image data
- jpeg compression
- compressed domain
- compression ratio
- dct coefficients
- video codec
- lossy compression
- blocking artifacts
- peak signal to noise ratio
- motion compensation
- quality assessment
- image compression
- video compression
- motion compensated
- face recognition