Quantized Decoder in Learned Image Compression for Deterministic Reconstruction
Learned image compression has a problem of non-bit-exact reconstruction due to different calculations of floating point arithmetic on different devices. This paper shows a method to achieve a deterministic reconstructed image by quantizing only the decoder of the learned image compression model. From the implementation perspective of an image codec, it is beneficial to have the results reproducible when decoded on different devices. In this paper, we study quantization of weights and activations without overflow of accumulator in all decoder subnetworks. We show that the results are bit-exact at the output, and the resulting BD-rate loss of quantization of decoder is 0.5 % in the case of 16-bit weights and 16-bit activations, and 7.9 % in the case of 8-bit weights and 16-bit activations.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderImage CompressionQuantizationSimilar Papers 제목 키워드 기반
Is the Discrete VAE’s Power Stuck in its Prior?
We investigate why probabilistic neural models with discrete latent variables are effective at generating high-quality images. We hypothesize that fitting a more flexible variational posterior distribution and performing…
DecoderSTanH : Parametric Quantization for Variable Rate Learned Image Compression
In end-to-end learned image compression, encoder and decoder are jointly trained to minimize a $R + {\lambda}D$ cost function, where ${\lambda}$ controls the trade-off between rate of the quantized latent representation …
DecoderImage CompressionQuantizationLearning Content-Weighted Deep Image Compression
Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approx…
DecoderImage CompressionOnline Meta Adaptation for Variable-Rate Learned Image Compression
This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qua…
DecoderImage CompressionMeta-LearningQuantizationEnd-to-End Learned Block-Based Image Compression with Block-Level Masked Convolutions and Asymptotic Closed Loop Training
Learned image compression research has achieved state-of-the-art compression performance with auto-encoder based neural network architectures, where the image is mapped via convolutional neural networks (CNN) into a late…
Image CompressionVideo Compression