Related papers: BRDF Estimation of Complex Materials with Nested L…

Machine learning has become a crucial tool for predicting the properties of crystalline materials. However, existing methods primarily represent material information by constructing multi-edge graphs of crystal structures, often overlooking…

Thin, reflective objects such as forks and whisks are common in our daily lives, but they are particularly challenging for robot perception because it is hard to reconstruct them using commodity RGB-D cameras or multi-view stereo…

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…

Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-learning based methods yield good estimates of object poses,…

This paper presents an uncalibrated deep neural network framework for the photometric stereo problem. For training models to solve the problem, existing neural network-based methods either require exact light directions or ground-truth…

Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus…

Flatbed scanners have emerged as promising devices for high-resolution, single-image material capture. However, existing approaches assume very specific conditions, such as uniform diffuse illumination, which are only available in certain…

We consider image classification with estimated depth. This problem falls into the domain of transfer learning, since we are using a model trained on a set of depth images to generate depth maps (additional features) for use in another…

The triangulation of images has become an active research area in recent years for its compressive representation and ease of image processing and visualization. However, little work has been done on how to faithfully recover image…

We apply recent advances in machine learning and computer vision to a central problem in materials informatics: The statistical representation of microstructural images. We use activations in a pre-trained convolutional neural network to…

Learning a 3D representation of a scene has been a challenging problem for decades in computer vision. Recent advances in implicit neural representation from images using neural radiance fields(NeRF) have shown promising results. Some of…

Accurate identification of complex terrain characteristics, such as soil composition and coefficient of friction, is essential for model-based planning and control of mobile robots in off-road environments. Spectral signatures leverage…

In recent years, Neural Radiance Fields (NeRFs) have demonstrated significant potential in encoding highly-detailed 3D geometry and environmental appearance, positioning themselves as a promising alternative to traditional explicit…

Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into high-dimensional feature spaces. During training, these…

Graph-based machine learning has emerged as a promising approach for manufacturability analysis by learning directly from CAD models represented as Boundary Representations (B-reps), exploiting both surface geometry and topological…

Laser cutting is a widely adopted technology in material processing across various industries, but it generates a significant amount of dust, smoke, and aerosols during operation, posing a risk to both the environment and workers' health.…

We theoretically expanded the capabilities of optical sensing based on surface plasmon resonance in a prism-coupled configuration by incorporating artificial neural networks (ANNs). We used calculations modeling the situation in which an…

Transparent objects are ubiquitous in industry, pharmaceuticals, and households. Grasping and manipulating these objects is a significant challenge for robots. Existing methods have difficulty reconstructing complete depth maps for…

Recognizing material from color images is still a challenging problem today. While deep neural networks provide very good results on object recognition and has been the topic of a huge amount of papers in the last decade, their adaptation…

Recent approaches based on metric learning have achieved great progress in few-shot learning. However, most of them are limited to image-level representation manners, which fail to properly deal with the intra-class variations and spatial…