Atombeam Technologies Inc.

Kwai Inc.

Paras Maharjan

Zhu Li

Brian R Galvin

Ning Xu

Xuan Xu

Yuyan Song

A system for recovering information lost during genomic data compression employs a quality-driven approach using neural networks. The system evaluates the importance of genomic regions through a quality analysis engine that assigns quality scores, while a rate control engine determines optimal compression rates based on these scores. A specialized neural network recovers lost information from correlated genomic datasets that have undergone lossy compression, utilizing recurrent layers for feature extraction and a channel-wise transformer with attention to capture complex relationships between data channels. The neural network architecture incorporates a deblocking network that combines these components to effectively reconstruct compressed data. A decoder receives and decompresses the data, then processes it through the neural network to recover information lost during compression. This adaptive system ensures critical genomic information is preserved while maximizing compression efficiency.

System and method for adaptive quality driven compression of genomic data using neural networks

A system and method for real time discrete cosine transform image and video processing with convolutional neural network architecture. The system and method transforms degraded inputs into subband images, which are analyzed by a machine learning classification network to identify specific types of blur and compression artifacts. The classification network dynamically adjusts the parameters of separate DC and AC deblurring networks based on its analysis. This adaptive approach optimizes processing for various degradation types, improving the quality of the reconstructed output. The system and method's real-time capability and enhanced adaptability make it suitable for a wide range of imaging and video applications, offering superior performance over traditional methods.

Adaptive real time discrete cosine transform image and video processing with convolutional neural network architecture

A system and method for federated two-stage compression with federated joint learning. The system and method proposed allow for fast and efficient lossless data compression of a large variety of data types. The system and method have a variety of real-world applications, including deep learning solutions for telemetry, tracking, and command subsystems for satellites. Satellites and their control centers are incredibly spaced apart which makes data compression an extremely important process to transmit large sets of information in a low-latency, high-efficiency environment. The proposed system and method utilize probability prediction driven arithmetic long short-term memory system for data compression.

System and method for federated two-stage compression within a persistent cognitive machine

For compressing synthetic aperture radar (SAR) images, preprocessing operations are performed on an input SAR image. A discrete cosine transform is performed on the image, and multiple subbands are created, where each subband represents a particular range of frequencies. The subbands are organized into multiple groups, where the multiple groups comprise a first low frequency group, a second low frequency group, and a high frequency group. A latent space representation is generated corresponding to each of the multiple groups of subbands. Compression is performed on one or more of the subbands, thereby creating a compressed bitstream, wherein the compressed bitstream is a compressed version of the input SAR image.

Systems and methods for synthetic aperture radar image compression

A system for distributed data compression leverages edge and central computing devices to optimize efficiency and quality. The system includes a lightweight compression subsystem at the edge device that preprocesses and partially compresses input data before transmitting it to a central computing device. The central compression subsystem further processes the data using adjustable compression parameters and a temporal modeling component, reconstructing the data with high fidelity. The system dynamically optimizes preprocessing, encoding, and reconstruction operations based on resource availability, network conditions, and application-specific criteria. This distributed approach improves bandwidth efficiency and adaptability, making it suitable for applications requiring low-latency or resource-constrained environments.

Distributed system and method for adaptive neural network-based data compression

A system and method for federated two-stage compression with federated joint learning. The system and method proposed allow for fast and efficient lossless data compression of a large variety of data types. The system and method have a variety of real-world applications, including deep learning solutions for telemetry, tracking, and command subsystems for satellites. Satellites and their control centers are incredibly spaced apart which makes data compression an extremely important process to transmit large sets of information in a low-latency, high-efficiency environment. The proposed system and method utilize probability prediction driven arithmetic coding which provides faster encoding times and higher compression ratios when paired with a long short-term memory system for data compression.

System and method for federated two-stage compression with federated joint learning

A system and method are disclosed for generating hyperspectral images from RGB (red-green-blue) images. A set of data includes training hyperspectral images and their corresponding RGB images. A spectral band grouping is performed on the training hyperspectral images based on a correlation coefficient of spectral bands. A decomposition network generates a reconstructed hyperspectral image, while a fine-tuning network creates reconstructed RGB images. A quality assurance system analyzes spectral consistency, noise levels, and RGB reconstruction accuracy to generate quality metrics. These metrics guide network weight adjustments to improve reconstruction accuracy.

System and method for hyperspectral image generation with quality assurance

A system and methods for upsampling compressed data using a jointly trained Vector Quantized Variational Autoencoder (VQ-VAE) and neural upsampler. The system compresses input data into a discrete latent space using a VQ-VAE encoder, reconstructs the data using a VQ-VAE decoder, and enhances the reconstructed data using a neural upsampler. The VQ-VAE and neural upsampler are jointly trained using a combined loss function, enabling end-to-end optimization. The system allows for efficient compression and high-quality reconstruction of various data types, including financial time-series, images, audio, video, sensor data, and text. The learned discrete latent space can be explored and manipulated using techniques such as interpolation, extrapolation, and vector arithmetic to generate new or modified data samples. The system finds applications in data storage, transmission, analysis, and generation across multiple domains.

Upsampling of compressed financial time-series data using a jointly trained Vector Quantized Variational Autoencoder neural network

A system and methods for upsampling of decompressed genomic data after lossy compression using a neural network integrates AI-based techniques to enhance compression quality. It incorporates a novel deep-learning neural network that upsamples decompressed data to restore information lost during lossy compression, taking advantage of cross-correlations between genomic data sets.

System and methods for upsampling of decompressed genomic data after lossy compression using a neural network

For compressing data, preprocessing operations are performed on raw input data. A discrete cosine transform is performed on the preprocessed data, and multiple subbands are created, where each subband represents a particular range of frequencies. The subbands are organized into multiple groups, where the multiple groups comprise a first low frequency group, a second low frequency group, and a high frequency group. A latent space representation is generated corresponding to each of the multiple groups of subbands. A first bitstream is created based on the latent space representation, and an alternate representation of the latent space is used for creating a second bitstream, enabling multiple-pass techniques for data compression. The multiple bitstreams may be multiplexed to form a combined bitstream for storage and/or transmission purposes.

Systems and methods for neural network based data compression

A system and method for controllable lossy data compression employing a joint learning framework to efficiently compress and reconstruct input data while balancing compression ratio and reconstruction quality. The system comprises an encoding system, a temporal modeling system, and a decoding system, which are jointly optimized to minimize a combined loss function. The encoding system, such as a Vector Quantized Variational Autoencoder (VQ-VAE) compresses the input data into a compact representation, while introducing a controllable degree of lossy compression based on adjustable compression parameters. The temporal modeling system, such as a Multilayer Perceptron Long Short-Term Memory captures temporal dependencies in the compressed representation. The decoding system, such as a VQ-VAE decoder, reconstructs the input data from the compressed representation. By providing control over the trade-off between compression ratio and reconstruction quality, the system offers flexibility for diverse applications.

Controllable lossy compression system using joint learning

A system and method for real time discrete cosine transform image and video processing with convolutional neural network architecture. The system and method incorporate discrete cosine transform image processing with convolutional neural networks to achieve fast and efficient image processing that yields more reliable results than previously used image processing methods. The proposed system and method enable effective, real time, image processing which is applicable to a wide range of imaging and video devices.

Real time discrete cosine transform image and video processing with convolutional neural network architecture

A system and method are disclosed for generating hyperspectral images from RGB (red-green-blue) images. A set of data includes training hyperspectral images and their corresponding RGB images. A spectral band grouping is performed on the training hyperspectral images based on a correlation coefficient of spectral bands. A decomposition network is used to generate a reconstructed hyperspectral image. A fine-tuning network is used to create a reconstructed RGB images. The difference between an input RGB image and a corresponding reconstructed RGB image is used to adjust one or more weights of one or more of the networks.

Systems and methods for hyperspectral image generation

A system and method learning-based lossless data compression. The system and method proposed allow for fast and efficient lossless data compression of a large variety of data types. The system and method have a variety of real-world applications, including deep learning solutions for telemetry, tracking, and command subsystems for satellites. Satellites and their control centers are incredibly spaced apart which makes data compression an extremely important process to transmit large sets of information in a low-latency, high-efficiency environment. The proposed system and method utilize probability prediction driven arithmetic coding which provides faster encoding times and higher compression ratios when paired with a long short-term memory system for data compression.

Growing community of inventors

Kansas City, MO, United States of America

Paras Maharjan