Related papers: Decoupling Fine Detail and Global Geometry for Com…
Deep neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements.…
The core challenge in Camouflage Object Detection (COD) lies in the indistinguishable similarity between targets and backgrounds in terms of color, texture, and shape. This causes existing methods to either lose edge details (such as…
In "extreme" computational imaging that collects extremely undersampled or noisy measurements, obtaining an accurate image within a reasonable computing time is challenging. Incorporating image mapping convolutional neural networks (CNN)…
While the depth of convolutional neural networks has attracted substantial attention in the deep learning research, the width of these networks has recently received greater interest. The width of networks, defined as the size of the…
Neural implicit surface reconstruction with signed distance function has made significant progress, but recovering fine details such as thin structures and complex geometries remains challenging due to unreliable or noisy geometric priors.…
Autoencoders have emerged as powerful models for visualization and dimensionality reduction based on the fundamental assumption that high-dimensional data is generated from a low-dimensional manifold. A critical challenge in autoencoder…
Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and…
Recent developments in 3D Gaussian Splatting have made significant advances in surface reconstruction. However, scaling these methods to large-scale scenes remains challenging due to high computational demands and the complex dynamic…
3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep…
Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matching. These architectures are specialized according to the…
Estimating a dense and accurate depth map is the key requirement for autonomous driving and robotics. Recent advances in deep learning have allowed depth estimation in full resolution from a single image. Despite this impressive result,…
The processing and recognition of geoscience images have wide applications. Most of existing researches focus on understanding the high-quality geoscience images by assuming that all the images are clear. However, in many real-world cases,…
We propose DepthTCM, a physics-aware end-to-end framework for depth map compression. In our framework of DepthTCM, the high-bit depth map is first converted to a conventional 3-channel image representation losslessly using a method inspired…
We present IDC-Net (Image-Depth Consistency Network), a novel framework designed to generate RGB-D video sequences under explicit camera trajectory control. Unlike approaches that treat RGB and depth generation separately, IDC-Net jointly…
This work presents FG-Net, a general deep learning framework for large-scale point clouds understanding without voxelizations, which achieves accurate and real-time performance with a single NVIDIA GTX 1080 GPU. First, a novel noise and…
We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences. GeoRefine consists of three modules: a hybrid SLAM module using learning-based priors, an online…
The reconstruction of the 3D permittivity map from ground-penetrating radar (GPR) data is of great importance for mapping subsurface environments and inspecting underground structural integrity. Traditional iterative 3D reconstruction…
The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry…
In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames. In this paper, we propose a…
A novel Encoder-Decoder Network with Guided Transmission Map (EDN-GTM) for single image dehazing scheme is proposed in this paper. The proposed EDN-GTM takes conventional RGB hazy image in conjunction with its transmission map estimated by…