paper-with-me

Papers

Exploring Compressed Image Representation as a Perceptual Proxy: A Study

2024-01-14 · Chen-Hsiu Huang, Ja-Ling Wu

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.

📄 PDF Abstract BibTeX arXiv:2401.07200

Code (1)

richzhang/PerceptualSimilarity 공식 구현 pytorch

Tasks

Image CompressionPerceptual Distance

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

CPIPS: Learning to Preserve Perceptual Distances in End-to-End Image Compression

2023-10-01 · Chen-Hsiu Huang, Ja-Ling Wu

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 Cars

SCENE: Semantic-aware Codec Enhancement with Neural Embeddings

2026-01-29 · Han-Yu Lin, Li-Wei Chen, Hung-Shin Lee arxiv

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

2022-05-09 · Jianzhao Liu, Xin Li, Yanding Peng, Tao Yu 외

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+1

Image Data Hiding in Neural Compressed Latent Representations

2023-10-01 · Chen-Hsiu Huang, Ja-Ling Wu

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…

Decoder

Perceptually Optimizing Deep Image Compression

2020-07-03 · Li-Heng Chen, Christos G. Bampis, Zhi Li, Andrey Norkin 외

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