Joint image compression and denoising via latent-space scalability

When it comes to image compression in digital cameras, denoising is traditionally performed prior compression. However, there are applications where noise may be necessary demonstrate the trustworthiness of image, such as court evidence and forensics. This means that itself needs coded, addition clean itself. In this paper, we present a learning-based framework jointly. The latent space codec organized scalable manner can decoded from subset (the base layer), while noisy full at higher rate. Using for denoised allows carried out lower Besides providing representation input performing jointly with makes intuitive sense because hard compress; hence, compressibility one criteria help distinguish signal. proposed compared against established benchmarks, experiments reveal considerable bitrate savings cascade combination state-of-the-art denoiser.