Related papers: OMNI-DC: Highly Robust Depth Completion with Multi…
Multiple Description Coding (MDC) is an error-resilient source coding method designed for transmission over noisy channels. We present a novel MDC scheme employing a neural network based on implicit neural representation. This involves…
Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based…
Feature-based visual simultaneous localization and mapping (SLAM) methods only estimate the depth of extracted features, generating a sparse depth map. To solve this sparsity problem, depth completion tasks that estimate a dense depth from…
This work proposes a new method to accurately complete sparse LiDAR maps guided by RGB images. For autonomous vehicles and robotics the use of LiDAR is indispensable in order to achieve precise depth predictions. A multitude of applications…
Omnidirectional image (ODI) data is captured with a 360x180 field-of-view, which is much wider than the pinhole cameras and contains richer spatial information than the conventional planar images. Accordingly, omnidirectional vision has…
Deep Matching (DM) is a popular high-quality method for quasi-dense image matching. Despite its name, however, the original DM formulation does not yield a deep neural network that can be trained end-to-end via backpropagation. In this…
Abstract. The advancement of deep learning has coincided with the proliferation of both models and available data. The surge in dataset sizes and the subsequent surge in computational requirements have led to the development of the Dataset…
Generalizable depth completion enables the acquisition of dense metric depth maps for unseen environments, offering robust perception capabilities for various downstream tasks. However, training such models typically requires large-scale…
Spectral Domain Optical Coherence Tomography (SD-OCT) is a well-known imaging modality which allows for \textit{in-vivo} visualization of the morphology of different biological tissues at cellular level resolutions. The overall SD-OCT…
Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving. However, depth completion faces 3 main challenges: the irregularly spaced…
Deep learning methods are developing rapidly in coded aperture snapshot spectral imaging (CASSI). The number of parameters and FLOPs of existing state-of-the-art methods (SOTA) continues to increase, but the reconstruction accuracy improves…
Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints.…
The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct…
In this paper, we formulate a potentially valuable panoramic depth completion (PDC) task as panoramic 3D cameras often produce 360{\deg} depth with missing data in complex scenes. Its goal is to recover dense panoramic depths from raw…
In real-world machine learning deployments, models must be continually updated, composed, and when required, selectively undone. However, existing approaches to model merging and continual learning often suffer from task interference,…
In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. The increasing demand for visual analysis applications, particularly in classification tasks, has emphasized…
Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth…
Depth estimation features are helpful for 3D recognition. Commodity-grade depth cameras are able to capture depth and color image in real-time. However, glossy, transparent or distant surface cannot be scanned properly by the sensor. As a…
Transparent objects are common in our daily life and frequently handled in the automated production line. Robust vision-based robotic grasping and manipulation for these objects would be beneficial for automation. However, the majority of…
Recent RGB-guided depth super-resolution methods have achieved impressive performance under the assumption of fixed and known degradation (e.g., bicubic downsampling). However, in real-world scenarios, captured depth data often suffer from…