Related papers: Improving Deep Stereo Network Generalization with …
Today, Multi-View Stereo techniques are able to reconstruct robust and detailed 3D models, especially when starting from high-resolution images. However, there are cases in which the resolution of input images is relatively low, for…
Autonomous drone-based tree pruning needs accurate, real-time depth estimation from stereo cameras. Depth is computed from disparity maps using $Z = f B/d$, so even small disparity errors cause noticeable depth mistakes at working…
Explaining the generalization characteristics of deep learning is an emerging topic in advanced machine learning. There are several unanswered questions about how learning under stochastic optimization really works and why certain…
The photometric stereo (PS) problem consists in reconstructing the 3D-surface of an object, thanks to a set of photographs taken under different lighting directions. In this paper, we propose a multi-scale architecture for PS which,…
Image restoration and enhancement is a process of improving the image quality by removing degradations, such as noise, blur, and resolution degradation. Deep learning (DL) has recently been applied to image restoration and enhancement. Due…
Deep neural networks are capable of modelling highly non-linear functions by capturing different levels of abstraction of data hierarchically. While training deep networks, first the system is initialized near a good optimum by greedy…
Photometric stereo (PS) endeavors to ascertain surface normals using shading clues from photometric images under various illuminations. Recent deep learning-based PS methods often overlook the complexity of object surfaces. These neural…
Images captured in snowy days suffer from noticeable degradation of scene visibility, which degenerates the performance of current vision-based intelligent systems. Removing snow from images thus is an important topic in computer vision. In…
A low-resolution digital surface model (DSM) features distinctive attributes impacted by noise, sensor limitations and data acquisition conditions, which failed to be replicated using simple interpolation methods like bicubic. This causes…
Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…
In this paper, we propose a deep convolutional neural network for learning the embeddings of images in order to capture the notion of visual similarity. We present a deep siamese architecture that when trained on positive and negative pairs…
Existing deep learning methods for remote sensing image fusion often suffer from poor generalization when applied to unseen datasets due to the limited availability of real training data and the domain gap between different satellite…
Compressive sensing is an impressive approach for fast MRI. It aims at reconstructing MR image using only a few under-sampled data in k-space, enhancing the efficiency of the data acquisition. In this study, we propose to learn priors based…
The success of existing deep-learning based multi-view stereo (MVS) approaches greatly depends on the availability of large-scale supervision in the form of dense depth maps. Such supervision, while not always possible, tends to hinder the…
We investigate approaches to regularisation during fine-tuning of deep neural networks. First we provide a neural network generalisation bound based on Rademacher complexity that uses the distance the weights have moved from their initial…
Traditional stereo algorithms have focused their efforts on reconstruction quality and have largely avoided prioritizing for run time performance. Robots, on the other hand, require quick maneuverability and effective computation to observe…
The deep image prior was recently introduced as a prior for natural images. It represents images as the output of a convolutional network with random inputs. For "inference", gradient descent is performed to adjust network parameters to…
Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks. Where a Bayesian treatment is usually associated with high-quality predictions and uncertainties, the practical reality has been…
Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…
In this paper we introduce a novel method of gradient normalization and decay with respect to depth. Our method leverages the simple concept of normalizing all gradients in a deep neural network, and then decaying said gradients with…