Low Bit-Rate Image Coding via Local Random Down-Sampling

A common practice in low bit-rate image/video compression is uniform spatial downsampling at the encoder and upsampling at the decoder. The downsampling is performed in conjunction with deterministic low-pass filtering (e.g, Gaussian or the alike) to prevent aliasing. The downsampled image is compressed and decompressed as usual; the upsampling is treated as an image restoration problem. In this paper, we show that the rate-distortion …