We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear transform codecs for images, and have superseded them in terms of rate–distortion performance under established perceptual quality metrics such as MS-SSIM. We assess the empirical rate–distortion performance of NTC with the help of simple example sources, for which the optimal performance of a vector quantizer is easier to estimate than with natural data sources. To this end, we introduce a novel variant of entropy-constrained vector quantization. We provide an analysis of various forms of stochastic optimization techniques for NTC models; review architectures of transforms based on artificial neural networks, as well as learned entropy models; and provide a direct comparison of a number of methods to parameterize the rate–distortion trade-off of nonlinear transforms, introducing a simplified one.

/pdf/nonlinear-transform-coding-402wbjdyjh.pdf

Nonlinear Transform Coding

This paper describes a highly efficient method for lossless compression of volumetric sets of medical images, such as CTs or MRIs. The proposed method, referred to as 3-D-MRP, is based on the principle of minimum rate predictors (MRPs), which is one of the state-of-the-art lossless compression technologies presented in the data compression literature. The main features of the proposed method include the use of 3-D predictors, 3-D-block octree partitioning and classification, volume-based optimization, and support for 16-b-depth images. Experimental results demonstrate the efficiency of the 3-D-MRP algorithm for the compression of volumetric sets of medical images, achieving gains above 15% and 12% for 8- and 16-bit-depth contents, respectively, when compared with JPEG-LS, JPEG2000, CALIC, and HEVC, as well as other proposals based on the MRP algorithm.

Lossless Compression of Medical Images Using 3-D Predictors

Recent years have witnessed the growth of point cloud based applications because of its realistic and fine-grained representation of 3D objects and scenes. However, it is a challenging problem to compress sparse, unstructured, and high-precision 3D points for efficient communication. In this paper, leveraging the sparsity nature of point cloud, we propose a multiscale end-to-end learning framework which hierarchically reconstructs the 3D Point Cloud Geometry (PCG) via progressive re-sampling. The framework is developed on top of a sparse convolution based autoencoder for point cloud compression and reconstruction. For the input PCG which has only the binary occupancy attribute, our framework translates it to a downscaled point cloud at the bottleneck layer which possesses both geometry and associated feature attributes. Then, the geometric occupancy is losslessly compressed using an octree codec and the feature attributes are lossy compressed using a learned probabilistic context model.Compared to state-of-the-art Video-based Point Cloud Compression (V-PCC) and Geometry-based PCC (G-PCC) schemes standardized by the Moving Picture Experts Group (MPEG), our method achieves more than 40% and 70% BD-Rate (Bjontegaard Delta Rate) reduction, respectively. Its encoding runtime is comparable to that of G-PCC, which is only 1.5% of V-PCC.

Multiscale Point Cloud Geometry Compression

Point clouds are a very rich 3D visual representation model, which has become increasingly appealing for multimedia applications with immersion, interaction and realism requirements. Due to different acquisition and creation conditions as well as target applications, point clouds’ characteristics may be very diverse, notably on their density. While geographical information systems or autonomous driving applications may use rather sparse point clouds, cultural heritage or virtual reality applications typically use denser point clouds to more accurately represent objects and people. Naturally, to offer immersion and realism, point clouds need a rather large number of points, thus asking for the development of efficient coding solutions. The use of deep learning models for coding purposes has recently gained relevance, with latest developments in image coding achieving state-of-the-art performance, thus making natural the adoption of this technology also for point cloud coding. This paper presents a novel deep learning-based solution for point cloud geometry coding which is able to efficiently adapt to the content's characteristics. The proposed coding solution divides the point cloud into 3D blocks and selects the most suitable available deep learning coding model to code each block, thus maximizing the compression performance. In comparison to the state-of-the-art MPEG G-PCC Trisoup standard, the proposed coding solution offers average quality gains up to 4.9 and 5.7 dB for PSNR D1 and PSNR D2, respectively.

Adaptive Deep Learning-Based Point Cloud Geometry Coding

Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc. In this paper, we propose a set of contributions to improve deep point cloud compression, i.e.: using a scale hyperprior model for entropy coding; employing deeper transforms; a different balancing weight in the focal loss; optimal thresholding for decoding; and sequential model training. In addition, we present an extensive ablation study on the impact of each of these factors, in order to provide a better understanding about why they improve RD performance. An optimal combination of the proposed improvements achieves BD-PSNR gains over G-PCC trisoup and octree of 5.50 (6.48) dB and 6.84 (5.95) dB, respectively, when using the point-to-point (point-to-plane) metric. Code is available at https://github.com/mauriceqch/pcc_geo_cnn_v2.

/pdf/improved-deep-point-cloud-geometry-compression-33kp76cga9.pdf

Improved Deep Point Cloud Geometry Compression

Point clouds have recently become an important visual representation format, especially for virtual and augmented reality applications, thus making point cloud coding a very hot research topic. Deep learning-based coding methods have recently emerged in the field of image coding with increasing success. These coding solutions take advantage of the ability of convolutional neural networks to extract adaptive features from the images to create a latent representation that can be efficiently coded. In this context, this paper extends the deep-learning coding approach to point cloud coding using an autoencoder network design. Performance results are very promising, showing improvements over the Point Cloud Library codec often taken as benchmark, thus suggesting a significant margin of evolution for this new point cloud coding paradigm.

Point Cloud Coding: Adopting a Deep Learning-based Approach

Deep learning is becoming more and more relevant for multiple multimedia processing tasks, and lately it has raised much interest in the coding arena notably for images and point clouds. While offering near state-of-the-art compression performance, current deep learning-based point cloud coding solutions have a shortcoming since they require training and storing multiple models in order to obtain different rate-distortion trade-offs. This paper proposes a solution that effectively reduces the number of deep learning models that need to be trained and stored by applying explicit quantization to the latent representation, which can be controlled at coding time, to generate varying rate-distortion tradeoffs. The proposed implicit-explicit quantization combination achieves a compression performance that is equivalent or better than the alternative, while significantly reducing the model storage memory requirements.

Deep Learning-Based Point Cloud Geometry Coding: RD Control Through Implicit and Explicit Quantization

Medical imaging technology and applications are continuously evolving, dealing with images of increasing spatial and temporal resolutions, which enable more accurate processing, feature analysis and medical diagnosis. However, the increase in resolution also requires a growing amount of data to be stored, processed and exchanged or transmitted through networks. Despite the high coding efficiency achieved by the most recent image and video coding standards in lossy compression, they are not well suited for quality-critical medical image compression where either near-lossless or lossless coding is required. In this paper we propose a method to improve lossless coding of volumetric medical images, such as Magnetic Resonance and Computed Tomography, and medical sequences such as X-ray Angiography images, using the latest standard High Efficiency Video Encoder (HEVC). New pixel-wise prediction techniques are proposed to extend the current HEVC lossless tools, based on Least-Squares Prediction (LSP). Experimental results show a bitrate reduction of over 44%, when compared to DICOM recommended encoders, and 13.8% when compared to standard lossless HEVC, for 8 bpp volumetric images, and over 8% and 4.6%, respectively, for volumetric images using more than 8 bpp.

A method to improve HEVC lossless coding of volumetric medical images

Point clouds are gaining importance as the format to represent complex 3D objects and scenes, offering high user immersion and interaction, although at the cost of requiring massive data. Scalable coding is an important feature for point cloud coding, especially for real-time applications, where the fast and bitrate efficient access to a decoded point cloud is important; however, this issue is still rather unexplored in the literature. With the rise of deep learning methods as a promising solution for efficient coding, this paper proposes the first deep learning-based point cloud geometry scalable coding solution. Experimental results show that the proposed scalable coding solution consistently outperforms the MPEG standard for static point cloud geometry coding. In this way, a new research path is open for point cloud scalable coding technology.

Andre F. R. Guarda

Papers

Adaptive Deep Learning-Based Point Cloud Geometry Coding

Point Cloud Coding: Adopting a Deep Learning-based Approach

Deep Learning-Based Point Cloud Geometry Coding: RD Control Through Implicit and Explicit Quantization

A method to improve HEVC lossless coding of volumetric medical images

Point Cloud Geometry Scalable Coding With a Single End-to-End Deep Learning Model