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.
This short paper describes our method for the track of image compression. To achieve better perceptual quality, we use the adversarial loss to generate realistic textures, use region of interest (ROI) mask to guide the bit allocation for different regions. Our Team name is TLIC.
Image compression has been applied in the fields of image storage and video broadcasting. However, it's formidably tough to distinguish the subtle quality differences between those distorted images generated by different algorithms. In this paper, we propose a new image quality assessment framework to decide which image is better in an image group. To capture the subtle differences, a fine-grained network is adopted to acquire multi-scale features. Subsequently, we design a cross subtract block for separating and gathering the information within positive and negative image pairs. Enabling image comparison in feature space. After that, a progressive feature fusion block is designed, which fuses multi-scale features in a novel progressive way. Hierarchical spatial 2D features can thus be processed gradually. Experimental results show that compared with the current mainstream image quality assessment methods, the proposed network can achieve more accurate image quality assessment and ranks second in the benchmark of CLIC in the image perceptual model track.
Image compression constitutes a significant challenge amidst the era of information explosion. Recent studies employing deep learning methods have demonstrated the superior performance of learning-based image compression methods over traditional codecs. However, an inherent challenge associated with these methods lies in their lack of interpretability. Following an analysis of the varying degrees of compression degradation across different frequency bands, we propose the end-to-end optimized image compression model facilitated by the frequency-oriented transform. The proposed end-to-end image compression model consists of four components: spatial sampling, frequency-oriented transform, entropy estimation, and frequency-aware fusion. The frequency-oriented transform separates the original image signal into distinct frequency bands, aligning with the human-interpretable concept. Leveraging the non-overlapping hypothesis, the model enables scalable coding through the selective transmission of arbitrary frequency components. Extensive experiments are conducted to demonstrate that our model outperforms all traditional codecs including next-generation standard H.266/VVC on MS-SSIM metric. Moreover, visual analysis tasks (i.e., object detection and semantic segmentation) are conducted to verify the proposed compression method could preserve semantic fidelity besides signal-level precision.
Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks. While existing adversarial perturbations are primarily applied to uncompressed images or compressed images by the traditional image compression method, i.e., JPEG, limited studies have investigated the robustness of models for image classification in the context of DNN-based image compression. With the rapid evolution of advanced image compression, DNN-based learned image compression has emerged as the promising approach for transmitting images in many security-critical applications, such as cloud-based face recognition and autonomous driving, due to its superior performance over traditional compression. Therefore, there is a pressing need to fully investigate the robustness of a classification system post-processed by learned image compression. To bridge this research gap, we explore the adversarial attack on a new pipeline that targets image classification models that utilize learned image compressors as pre-processing modules. Furthermore, to enhance the transferability of perturbations across various quality levels and architectures of learned image compression models, we introduce a saliency score-based sampling method to enable the fast generation of transferable perturbation. Extensive experiments with popular attack methods demonstrate the enhanced transferability of our proposed method when attacking images that have been post-processed with different learned image compression models.
This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned Image Compression. This candidate attempts to demonstrate that neural coding methods can lead to low complexity and lightweight image decoders while still offering competitive performance. The approach is based on the already published overfitted lightweight neural networks Cool-Chic, further adapted to the human subjective viewing targeted in this challenge.
This paper summarises the design of the candidate ED for the Challenge on Learned Image Compression 2024. This candidate aims at providing an anchor based on conventional coding technologies to the learning-based approaches mostly targeted in the challenge. The proposed candidate is based on the Enhanced Compression Model (ECM) developed at JVET, the Joint Video Experts Team of ITU-T VCEG and ISO/IEC MPEG. Here, ECM is adapted to the challenge objective: to maximise the perceived quality, the encoding is performed according to a perceptual metric, also the sequence selection is performed in a perceptual manner to fit the target bit per pixel objectives. The primary objective of this candidate is to assess the recent developments in video coding standardisation and in parallel to evaluate the progress made by learning-based techniques. To this end, this paper explains how to generate coded images fulfilling the challenge requirements, in a reproducible way, targeting the maximum performance.
Multi-view compression technology, especially Stereo Image Compression (SIC), plays a crucial role in car-mounted cameras and 3D-related applications. Interestingly, the Distributed Source Coding (DSC) theory suggests that efficient data compression of correlated sources can be achieved through independent encoding and joint decoding. This motivates the rapidly developed deep-distributed SIC methods in recent years. However, these approaches neglect the unique characteristics of stereo-imaging tasks and incur high decoding latency. To address this limitation, we propose a Feature-based Fast Cascade Alignment network (FFCA-Net) to fully leverage the side information on the decoder. FFCA adopts a coarse-to-fine cascaded alignment approach. In the initial stage, FFCA utilizes a feature domain patch-matching module based on stereo priors. This module reduces redundancy in the search space of trivial matching methods and further mitigates the introduction of noise. In the subsequent stage, we utilize an hourglass-based sparse stereo refinement network to further align inter-image features with a reduced computational cost. Furthermore, we have devised a lightweight yet high-performance feature fusion network, called a Fast Feature Fusion network (FFF), to decode the aligned features. Experimental results on InStereo2K, KITTI, and Cityscapes datasets demonstrate the significant superiority of our approach over traditional and learning-based SIC methods. In particular, our approach achieves significant gains in terms of 3 to 10-fold faster decoding speed than other methods.
The accelerated proliferation of visual content and the rapid development of machine vision technologies bring significant challenges in delivering visual data on a gigantic scale, which shall be effectively represented to satisfy both human and machine requirements. In this work, we investigate how hierarchical representations derived from the advanced generative prior facilitate constructing an efficient scalable coding paradigm for human-machine collaborative vision. Our key insight is that by exploiting the StyleGAN prior, we can learn three-layered representations encoding hierarchical semantics, which are elaborately designed into the basic, middle, and enhanced layers, supporting machine intelligence and human visual perception in a progressive fashion. With the aim of achieving efficient compression, we propose the layer-wise scalable entropy transformer to reduce the redundancy between layers. Based on the multi-task scalable rate-distortion objective, the proposed scheme is jointly optimized to achieve optimal machine analysis performance, human perception experience, and compression ratio. We validate the proposed paradigm's feasibility in face image compression. Extensive qualitative and quantitative experimental results demonstrate the superiority of the proposed paradigm over the latest compression standard Versatile Video Coding (VVC) in terms of both machine analysis as well as human perception at extremely low bitrates ($<0.01$ bpp), offering new insights for human-machine collaborative compression.
The joint source-channel coding (JSCC) framework leverages deep learning to learn from data the best codes for source and channel coding. When the output signal, rather than being binary, is directly mapped onto the IQ domain (complex-valued), we call the resulting framework joint source coding and modulation (JSCM). We consider a JSCM scenario and show the existence of a strict tradeoff between channel rate, distortion, perception, and classification accuracy, a tradeoff that we name RDPC. We then propose two image compression methods to navigate that tradeoff: the RDPCO algorithm which, under simple assumptions, directly solves the optimization problem characterizing the tradeoff, and an algorithm based on an inverse-domain generative adversarial network (ID-GAN), which is more general and achieves extreme compression. Simulation results corroborate the theoretical findings, showing that both algorithms exhibit the RDPC tradeoff. They also demonstrate that the proposed ID-GAN algorithm effectively balances image distortion, perception, and classification accuracy, and significantly outperforms traditional separation-based methods and recent deep JSCM architectures in terms of one or more of these metrics.
3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast rendering at high-quality. However, the storage size is significantly higher, which hinders practical deployment, e.g. on resource constrained devices. In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without compromising visual quality during rendering. Central to our idea is the explicit exploitation of perceptual redundancies present in natural scenes. In essence, the inherent nature of a scene allows for numerous permutations of Gaussian parameters to equivalently represent it. To this end, we propose a novel highly parallel algorithm that regularly arranges the high-dimensional Gaussian parameters into a 2D grid while preserving their neighborhood structure. During training, we further enforce local smoothness between the sorted parameters in the grid. The uncompressed Gaussians use the same structure as 3DGS, ensuring a seamless integration with established renderers. Our method achieves a reduction factor of 17x to 42x in size for complex scenes with no increase in training time, marking a substantial leap forward in the domain of 3D scene distribution and consumption. Additional information can be found on our project page: https://fraunhoferhhi.github.io/Self-Organizing-Gaussians/
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.
JPEG is still the most widely used image compression algorithm. Most image compression algorithms only consider uncompressed original image, while ignoring a large number of already existing JPEG images. Recently, JPEG recompression approaches have been proposed to further reduce the size of JPEG files. However, those methods only consider JPEG lossless recompression, which is just a special case of the rate-distortion theorem. In this paper, we propose a unified lossly and lossless JPEG recompression framework, which consists of learned quantization table and Markovian hierarchical variational autoencoders. Experiments show that our method can achieve arbitrarily low distortion when the bitrate is close to the upper bound, namely the bitrate of the lossless compression model. To the best of our knowledge, this is the first learned method that bridges the gap between lossy and lossless recompression of JPEG images.
Hyperspectral images, which record the electromagnetic spectrum for a pixel in the image of a scene, often store hundreds of channels per pixel and contain an order of magnitude more information than a similarly-sized RBG color image. Consequently, concomitant with the decreasing cost of capturing these images, there is a need to develop efficient techniques for storing, transmitting, and analyzing hyperspectral images. This paper develops a method for hyperspectral image compression using implicit neural representations where a multilayer perceptron network F with sinusoidal activation functions "learns" to map pixel locations to pixel intensities for a given hyperspectral image I. F thus acts as a compressed encoding of this image, and the original image is reconstructed by evaluating F at each pixel location. We use a sampling method with two factors: window size and sampling rate to reduce the compression time. We have evaluated our method on four benchmarks -- Indian Pines, Jasper Ridge, Pavia University, and Cuprite using PSNR and SSIM -- and we show that the proposed method achieves better compression than JPEG, JPEG2000, and PCA-DCT at low bitrates. Besides, we compare our results with the learning-based methods like PCA+JPEG2000, FPCA+JPEG2000, 3D DCT, 3D DWT+SVR, and WSRC and show the corresponding results in the "Compression Results" section. We also show that our methods with sampling achieve better speed and performance than our method without sampling.
This document provides a technical description of the codec proposed by EPFL to the JPEG DNA Call for Proposals. The codec we refer to as V-DNA for its versatility, enables the encoding of raw images and already compressed JPEG 1 bitstreams, but the underlying algorithm could be used to encode and transcode any kind of data. The codec is composed of two main modules: the image compression module, handled by the state-of-the-art JPEG XL codec, and the DNA encoding module, implemented using a modified Raptor Code implementation following the RU10 (Raptor Unsystematic) description. The code for encoding and decoding, as well as the objective metrics results, plots and biochemical constraints analysis are available on ISO Documents system with document number WG1M101013-ICQ-EPFL submission to the JPEG DNA CfP.
This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from there, mapped back to the data space for reconstruction. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional ``content'' latent variable on which the reverse diffusion process is conditioned and uses this variable to store information about the image. The remaining ``texture'' variables characterizing the diffusion process are synthesized at decoding time. We show that the model's performance can be tuned toward perceptual metrics of interest. Our extensive experiments involving multiple datasets and image quality assessment metrics show that our approach yields stronger reported FID scores than the GAN-based model, while also yielding competitive performance with VAE-based models in several distortion metrics. Furthermore, training the diffusion with $\mathcal{X}$-parameterization enables high-quality reconstructions in only a handful of decoding steps, greatly affecting the model's practicality. Our code is available at: \url{https://github.com/buggyyang/CDC_compression}
In the framework of learned image compression, the context model plays a pivotal role in capturing the dependencies among latent representations. To reduce the decoding time resulting from the serial autoregressive context model, the parallel context model has been proposed as an alternative that necessitates only two passes during the decoding phase, thus facilitating efficient image compression in real-world scenarios. However, performance degradation occurs due to its incomplete casual context. To tackle this issue, we conduct an in-depth analysis of the performance degradation observed in existing parallel context models, focusing on two aspects: the Quantity and Quality of information utilized for context prediction and decoding. Based on such analysis, we propose the \textbf{Corner-to-Center transformer-based Context Model (C$^3$M)} designed to enhance context and latent predictions and improve rate-distortion performance. Specifically, we leverage the logarithmic-based prediction order to predict more context features from corner to center progressively. In addition, to enlarge the receptive field in the analysis and synthesis transformation, we use the Long-range Crossing Attention Module (LCAM) in the encoder/decoder to capture the long-range semantic information by assigning the different window shapes in different channels. Extensive experimental evaluations show that the proposed method is effective and outperforms the state-of-the-art parallel methods. Finally, according to the subjective analysis, we suggest that improving the detailed representation in transformer-based image compression is a promising direction to be explored.
Matrices are exceptionally useful in various fields of study as they provide a convenient framework to organize and manipulate data in a structured manner. However, modern matrices can involve billions of elements, making their storage and processing quite demanding in terms of computational resources and memory usage. Although prohibitively large, such matrices are often approximately low rank. We propose an algorithm that exploits this structure to obtain a low rank decomposition of any matrix $\mathbf{A}$ as $\mathbf{A} \approx \mathbf{L}\mathbf{R}$, where $\mathbf{L}$ and $\mathbf{R}$ are the low rank factors. The total number of elements in $\mathbf{L}$ and $\mathbf{R}$ can be significantly less than that in $\mathbf{A}$. Furthermore, the entries of $\mathbf{L}$ and $\mathbf{R}$ are quantized to low precision formats $--$ compressing $\mathbf{A}$ by giving us a low rank and low precision factorization. Our algorithm first computes an approximate basis of the range space of $\mathbf{A}$ by randomly sketching its columns, followed by a quantization of the vectors constituting this basis. It then computes approximate projections of the columns of $\mathbf{A}$ onto this quantized basis. We derive upper bounds on the approximation error of our algorithm, and analyze the impact of target rank and quantization bit-budget. The tradeoff between compression ratio and approximation accuracy allows for flexibility in choosing these parameters based on specific application requirements. We empirically demonstrate the efficacy of our algorithm in image compression, nearest neighbor classification of image and text embeddings, and compressing the layers of LlaMa-$7$b. Our results illustrate that we can achieve compression ratios as aggressive as one bit per matrix coordinate, all while surpassing or maintaining the performance of traditional compression techniques.
CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising result is further analysed using an attribution method-Integrated Gradients. Using this attribution method, we are able to better understand both quantitatively and qualitatively exactly the nature in which the compression affects the zero-shot recognition accuracy of this model. We evaluate this extensively on CIFAR-10 and STL-10. Our work provides the basis to understand this vulnerability of CLIP and can help us develop more effective methods to improve the robustness of CLIP and other vision-language models.
The explosion of data has resulted in more and more associated text being transmitted along with images. Inspired by from distributed source coding, many works utilize image side information to enhance image compression. However, existing methods generally do not consider using text as side information to enhance perceptual compression of images, even though the benefits of multimodal synergy have been widely demonstrated in research. This begs the following question: How can we effectively transfer text-level semantic dependencies to help image compression, which is only available to the decoder? In this work, we propose a novel deep image compression method with text-guided side information to achieve a better rate-perception-distortion tradeoff. Specifically, we employ the CLIP text encoder and an effective Semantic-Spatial Aware block to fuse the text and image features. This is done by predicting a semantic mask to guide the learned text-adaptive affine transformation at the pixel level. Furthermore, we design a text-conditional generative adversarial networks to improve the perceptual quality of reconstructed images. Extensive experiments involving four datasets and ten image quality assessment metrics demonstrate that the proposed approach achieves superior results in terms of rate-perception trade-off and semantic distortion.