Exploring Compressed Image Representation as a Perceptual Proxy: A Study
We propose an end-to-end learned image compression codec wherein the analysis transform is jointly trained with an object classification task. This study affirms that the compressed latent representation can predict human perceptual distance judgments with an accuracy comparable to a custom-tailored DNN-based quality metric. We further investigate various neural encoders and demonstrate the effectiveness of employing the analysis transform as a perceptual loss network for image tasks beyond quality judgments. Our experiments show that the off-the-shelf neural encoder proves proficient in perceptual modeling without needing an additional VGG network. We expect this research to serve as a valuable reference developing of a semantic-aware and coding-efficient neural encoder.
Code (1)
Tasks
Image CompressionPerceptual DistanceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CPIPS: Learning to Preserve Perceptual Distances in End-to-End Image Compression
Lossy image coding standards such as JPEG and MPEG have successfully achieved high compression rates for human consumption of multimedia data. However, with the increasing prevalence of IoT devices, drones, and self-driv…
Image CompressionPerceptual DistanceSelf-Driving CarsSCENE: Semantic-aware Codec Enhancement with Neural Embeddings
Compression artifacts from standard video codecs often degrade perceptual quality. We propose a lightweight, semantic-aware pre-processing framework that enhances perceptual fidelity by selectively addressing these disto…
SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment
Image compression has raised widespread interest recently due to its significant importance for multimedia storage and transmission. Meanwhile, a reliable image quality assessment (IQA) for compressed images can not only…
Compressed Image Quality AssessmentFull reference image quality assessmentFull-Reference Image Quality AssessmentImage Compression+1Image Data Hiding in Neural Compressed Latent Representations
We propose an end-to-end learned image data hiding framework that embeds and extracts secrets in the latent representations of a generic neural compressor. By leveraging a perceptual loss function in conjunction with our…
DecoderPerceptually Optimizing Deep Image Compression
Mean squared error (MSE) and $\ell_p$ norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess visual information loss, these…
Image Compression