Density estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples.
Our goal is to learn a deep network that, given a small number of images of an object of a given category, reconstructs it in 3D.
We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance.
Additionally, we propose a novel approach to make our representation amenable to importance sampling: rather than inverting the trained networks, we learn to encode them in a more compact embedding that can be mapped to parameters of an analytic BRDF for which importance sampling is known.
Regrettably, capturing DISTORTED sensor readings is time-consuming; as well, there is a lack of CLEAN HDR videos.
no code implementations • 14 Dec 2020 • Andrey Polyakov, Katayoon Mohseni, Roberto Felici, Christian Tusche, Ying-Jiun Chen, Vitaliy Feyer, Jochen Geck, Tobias Ritschel, Juan Rubio-Zuazo, German R. Castro, Holger L. Meyerheim, Stuart S. P. Parkin
Spin-momentum locking in topological insulators and materials with Rashba-type interactions is an extremely attractive feature for novel spintronic devices and is therefore under intense investigation.
Mesoscale and Nanoscale Physics
The resulting system converts 2D images of different virtual or real images into complete 3D scenes, learned only from 2D images of those scenes.
We suggest to represent an X-Field -a set of 2D images taken across different view, time or illumination conditions, i. e., video, light field, reflectance fields or combinations thereof-by learning a neural network (NN) to map their view, time or light coordinates to 2D images.
Proteins perform a large variety of functions in living organisms, thus playing a key role in biology.
We suggest representing light field (LF) videos as "one-off" neural networks (NN), i. e., a learned mapping from view-plus-time coordinates to high-resolution color values, trained on sparse views.
We can successfully reconstruct 3D shapes from unstructured 2D images and extensively evaluate PlatonicGAN on a range of synthetic and real data sets achieving consistent improvements over baseline methods.
Thus, we suggest a two-stage operator comprising of a 3D network that first transforms the point cloud into a latent representation, which is later on projected to the 2D output image using a dedicated 3D-2D network in a second step.
We propose an efficient and effective method to learn convolutions for non-uniformly sampled point clouds, as they are obtained with modern acquisition techniques.
Convolutional neural networks (CNNs) handle the case where filters extend beyond the image boundary using several heuristics, such as zero, repeat or mean padding.
Second, we demonstrate how another network can be used to map from an image or video frames to a DAM network to reproduce this appearance, without using a lengthy optimization such as stochastic gradient descent (learning-to-learn).
To the other hand, methods that are automatic and work on 'in the wild' Internet images, often extract only low-frequency lighting or diffuse materials.
In this paper we are extracting surface reflectance and natural environmental illumination from a reflectance map, i. e. from a single 2D image of a sphere of one material under one illumination.
In computer vision, convolutional neural networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance.
We propose a technique to use the structural information extracted from a 3D model that matches the image object in terms of viewpoint and shape.
Undoing the image formation process and therefore decomposing appearance into its intrinsic properties is a challenging task due to the under-constraint nature of this inverse problem.
Object class detection has been a synonym for 2D bounding box localization for the longest time, fueled by the success of powerful statistical learning techniques, combined with robust image representations.
We propose a technique to use the structural information extracted from a set of 3D models of an object class to improve novel-view synthesis for images showing unknown instances of this class.