Related papers: MuSCLE: Multi Sweep Compression of LiDAR using Dee…

In this paper we propose a novel approach to model compression termed Architecture Compression. Instead of operating on the weight or filter space of the network like classical model compression methods, our approach operates on the…

Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results. However, there…

Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Thus far, prior work mostly focused on optimizing their reconstruction performance. This work investigates INRs…

Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and require substantial…

Large-scale semantic mapping is crucial for outdoor autonomous agents to fulfill high-level tasks such as planning and navigation. This paper proposes a novel method for large-scale 3D semantic reconstruction through implicit…

Recent models for learned image compression are based on autoencoders, learning approximately invertible mappings from pixels to a quantized latent representation. These are combined with an entropy model, a prior on the latent…

In this paper, we present our image compression framework designed for CLIC 2020 competition. Our method is based on Variational AutoEncoder (VAE) architecture which is strengthened with residual structures. In short, we make three…

For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use…

We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the entropy of a neural network, which measures its complexity…

End-to-end deep trainable models are about to exceed the performance of the traditional handcrafted compression techniques on videos and images. The core idea is to learn a non-linear transformation, modeled as a deep neural network,…

Various studies that address the compressed sensing problem with Multiple Measurement Vectors (MMVs) have been recently carried. These studies assume the vectors of the different channels to be jointly sparse. In this paper, we relax this…

Among applications of deep learning (DL) involving low cost sensors, remote image classification involves a physical channel that separates edge sensors and cloud classifiers. Traditional DL models must be divided between an encoder for the…

Traditional LiDAR odometry (LO) systems mainly leverage geometric information obtained from the traversed surroundings to register laser scans and estimate LiDAR ego-motion, while it may be unreliable in dynamic or unstructured…

Deep neural networks have achieved strong performance in image classification tasks due to their ability to learn complex patterns from high-dimensional data. However, their large computational and memory requirements often limit deployment…

Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting and immense demands for computation and storage, which…

Although convolutional representation of multiscale sparse tensor demonstrated its superior efficiency to accurately model the occupancy probability for the compression of geometry component of dense object point clouds, its capacity for…

We show how the massive data compression algorithm MOPED can be used to reduce, by orders of magnitude, the number of simulated datasets that are required to estimate the covariance matrix required for the analysis of gaussian-distributed…

A deep image compression scheme is proposed in this paper, offering the state-of-the-art compression efficiency, against the traditional JPEG, JPEG2000, BPG and those popular learning based methodologies. This is achieved by a novel…

Real-time light detection and ranging (LiDAR) perceptions, e.g., 3D object detection and simultaneous localization and mapping are computationally intensive to mobile devices of limited resources and often offloaded on the edge. Offloading…

We introduce a new algorithm, called CDER, for supervised machine learning that merges the multi-scale geometric properties of Cover Trees with the information-theoretic properties of entropy. CDER applies to a training set of labeled…