14 accepted papers
Multi-sensor fusion using LiDAR and RGB cameras significantly enhances 3D object detection task. However, conventional LiDAR sensors perform dense, stateless scans, ignoring the strong temporal continuity in real-world scenes. This leads to substantial sensing redundancy and excessive power consumpt
LiDAR sensors are integral to autonomous driving and augmented reality applications, providing essential depth information. However, managing the substantial volume of LiDAR point cloud data is crucial for practical application, necessitating efficient compression algorithms. Similar to other data c
Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR). To effectively deploy these models in real-world scenarios, it is essential to employ cross-domain adaptation techniques that bridge the gap between training data and real-world data.
Large-scale foundation models have demonstrated exceptional performance in language and vision tasks. However, the numerous dense matrix-vector operations involved in these large networks pose significant computational challenges during inference. To address these challenges, we introduce the Block-…
This paper investigates efficient deep neural networks (DNNs) to replace dense unstructured weight matrices with structured ones that possess desired properties. The challenge arises because the optimal weight matrix structure in popular neural network models is obscure in most cases and may vary fr…
In this paper, we propose an iterative source error correction (ISEC) decoding scheme for deep-learning-based joint source-channel coding (Deep JSCC). Given a noisy codeword received through the channel, we use a Deep JSCC encoder and decoder pair to update the codeword iteratively to find a (modifi…
Solving multiple visual tasks using individual models can be resource-intensive, while multi-task learning can conserve resources by sharing knowledge across different tasks. Despite the benefits of multi-task learning, such techniques can struggle with balancing the loss for each task, leading to p…
Learning-based video compression has been extensively studied over the past years, but it still has limitations in adapting to various motion patterns and entropy models. In this paper, we propose multi-mode video compression (MMVC), a block wise mode ensemble deep video compression framework that s…
Recent deep learning based visual-inertial odometry (VIO) systems achieve impressive performance in various applications and challenging scenarios. However, it is difficult to deploy such VIO models directly on energy-constrained mobile platforms in real-time due to the extensive complexity of exist…
Sound source separation and localization for situational awareness enables a wide range of applications such as hearing enhancement and audio beam-forming. We present an end-to-end deep learning framework to separate and localize multiple audio sources from the mixture of multi-channels. The propose…
We present a novel adaptive deep joint source-channel coding (JSCC) scheme for wireless image transmission. The proposed scheme supports multiple rates using a single deep neural network (DNN) model and learns to dynamically control the rate based on the channel condition and image contents. Specifi…
"In recent years, deep learning-based approaches for visual-inertial odometry (VIO) have shown remarkable performance outperforming traditional geometric methods. Yet, all existing methods use both the visual and inertial measurements for every pose estimation incurring potential computational redun…
Learning-based video compression has achieved substantial progress during recent years. The most influential approaches adopt deep neural networks (DNNs) to remove spatial and temporal redundancies by finding the appropriate lower-dimensional representations of frames in the video. We propose a nove…
We propose a unified compression framework that uses generative adversarial networks (GAN) to compress image and speech signals. The compressed signal is represented by a latent vector fed into a generator network which is trained to produce high quality signals that minimize a target objective func…