RD-Optimized Trit-Plane Coding of Deep Compressed Image Latent Tensors
This work addresses efficiency improvements for a specific image compression method, making it incremental in nature.
The paper tackles the high time complexity of computing trit probabilities in DPICT, a scalable learning-based image codec, by developing a parallel computing scheme, resulting in significantly reduced complexity and better rate-distortion performance compared to bit-plane slicing.
DPICT is the first learning-based image codec supporting fine granular scalability. In this paper, we describe how to implement two key components of DPICT efficiently: trit-plane slicing and rate-distortion-optimized (RD-optimized) coding. In DPICT, we transform an image into a latent tensor, represent the tensor in ternary digits (trits), and encode the trits in the decreasing order of significance. For entropy encoding, it is necessary to compute the probability of each trit, which demands high time complexity in both the encoder and the decoder. To reduce the complexity, we develop a parallel computing scheme for the probabilities, which is described in detail with pseudo-codes. Moreover, we compare the trit-plane slicing in DPICT with the alternative bit-plane slicing. Experimental results show that the time complexity is reduced significantly by the parallel computing and that the trit-plane slicing provides better RD performances than the bit-plane slicing.