Search Results for author: Tobias Ritschel

Found 45 papers, 11 papers with code

Exposure Diffusion: HDR Image Generation by Consistent LDR denoising

no code implementations23 May 2024 Mojtaba Bemana, Thomas Leimkühler, Karol Myszkowski, Hans-Peter Seidel, Tobias Ritschel

We demonstrate generating high-dynamic range (HDR) images using the concerted action of multiple black-box, pre-trained low-dynamic range (LDR) image diffusion models.

Denoising Image Generation +1

NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs

no code implementations13 Feb 2024 Michael Fischer, Zhengqin Li, Thu Nguyen-Phuoc, Aljaz Bozic, Zhao Dong, Carl Marshall, Tobias Ritschel

A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and appearance of a scene.


4D-ONIX: A deep learning approach for reconstructing 3D movies from sparse X-ray projections

no code implementations17 Jan 2024 Yuhe Zhang, Zisheng Yao, Robert Klöfkorn, Tobias Ritschel, Pablo Villanueva-Perez

The X-ray flux provided by X-ray free-electron lasers and storage rings offers new spatiotemporal possibilities to study in-situ and operando dynamics, even using single pulses of such facilities.

Neural Bounding

no code implementations10 Oct 2023 Stephanie Wenxin Liu, Michael Fischer, Paul D. Yoo, Tobias Ritschel

Bounding volumes are an established concept in computer graphics and vision tasks but have seen little change since their early inception.

Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphics

no code implementations10 Aug 2023 Michael Fischer, Tobias Ritschel

Gradient-based optimization is now ubiquitous across graphics, but unfortunately can not be applied to problems with undefined or zero gradients.

Neural Field Convolutions by Repeated Differentiation

no code implementations4 Apr 2023 Ntumba Elie Nsampi, Adarsh Djeacoumar, Hans-Peter Seidel, Tobias Ritschel, Thomas Leimkühler

Neural fields are evolving towards a general-purpose continuous representation for visual computing.

Plateau-reduced Differentiable Path Tracing

no code implementations CVPR 2023 Michael Fischer, Tobias Ritschel

Current differentiable renderers provide light transport gradients with respect to arbitrary scene parameters.

Inverse Rendering

3inGAN: Learning a 3D Generative Model from Images of a Self-similar Scene

no code implementations27 Nov 2022 Animesh Karnewar, Oliver Wang, Tobias Ritschel, Niloy Mitra

We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene.

Generative Adversarial Network

Learning to Rasterize Differentiable

no code implementations23 Nov 2022 Chenghao Wu, Zahra Montazeri, Tobias Ritschel

Differentiable rasterization changes the common formulation of primitive rasterization -- which has zero gradients almost everywhere, due to discontinuous edges and occlusion -- to an alternative one, which is not subject to this limitation and has similar optima.

Inverse Rendering Meta-Learning

Learning to Learn and Sample BRDFs

1 code implementation7 Oct 2022 Chen Liu, Michael Fischer, Tobias Ritschel

We propose a method to accelerate the joint process of physically acquiring and learning neural Bi-directional Reflectance Distribution Function (BRDF) models.


ReLU Fields: The Little Non-linearity That Could

no code implementations22 May 2022 Animesh Karnewar, Tobias Ritschel, Oliver Wang, Niloy J. Mitra

Although the MLPs are able to represent complex scenes with unprecedented quality and memory footprint, this expressive power of the MLPs, however, comes at the cost of long training and inference times.

Clean Implicit 3D Structure from Noisy 2D STEM Images

1 code implementation CVPR 2022 Hannah Kniesel, Timo Ropinski, Tim Bergner, Kavitha Shaga Devan, Clarissa Read, Paul Walther, Tobias Ritschel, Pedro Hermosilla

Scanning Transmission Electron Microscopes (STEMs) acquire 2D images of a 3D sample on the scale of individual cell components.

ONIX: an X-ray deep-learning tool for 3D reconstructions from sparse views

no code implementations1 Mar 2022 Yuhe Zhang, Zisheng Yao, Tobias Ritschel, Pablo Villanueva-Perez

We anticipate that ONIX will become a crucial tool for the X-ray community by i) enabling the study of fast dynamics not possible today when implemented together with X-ray multi-projection imaging, and ii) enhancing the volumetric information and capabilities of X-ray stereoscopic imaging in medical applications.

3D Object Reconstruction 3D Reconstruction

Eikonal Fields for Refractive Novel-View Synthesis

no code implementations2 Feb 2022 Mojtaba Bemana, Karol Myszkowski, Jeppe Revall Frisvad, Hans-Peter Seidel, Tobias Ritschel

We tackle the problem of generating novel-view images from collections of 2D images showing refractive and reflective objects.

Novel View Synthesis

Variance-Aware Weight Initialization for Point Convolutional Neural Networks

no code implementations7 Dec 2021 Pedro Hermosilla, Michael Schelling, Tobias Ritschel, Timo Ropinski

Appropriate weight initialization has been of key importance to successfully train neural networks.

Data-driven deep density estimation

1 code implementation23 Jul 2021 Patrik Puchert, Pedro Hermosilla, Tobias Ritschel, Timo Ropinski

Density estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples.

Density Estimation

Generative Modelling of BRDF Textures from Flash Images

no code implementations23 Feb 2021 Philipp Henzler, Valentin Deschaintre, Niloy J. Mitra, Tobias Ritschel

We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance.

Neural BRDF Representation and Importance Sampling

no code implementations11 Feb 2021 Alejandro Sztrajman, Gilles Rainer, Tobias Ritschel, Tim Weyrich

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.

Fermi surface chirality induced in a TaSe$_{2}$ monosheet formed by a Ta/ Bi$_{2}$Se$_{3}$ interface reaction

no code implementations14 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

Curiosity-driven 3D Object Detection Without Labels

no code implementations2 Dec 2020 David Griffiths, Jan Boehm, Tobias Ritschel

This can be overcome by a novel form of training, where an additional network is employed to steer the optimization itself to explore the entire parameter space i. e., to be curious, and hence, to resolve those ambiguities and find workable minima.

3D Object Detection Object +1

Deep Generative Modelling of Human Reach-and-Place Action

no code implementations5 Oct 2020 Connor Daly, Yuzuko Nakamura, Tobias Ritschel

The motion of picking up and placing an object in 3D space is full of subtle detail.

X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation

no code implementations1 Oct 2020 Mojtaba Bemana, Karol Myszkowski, Hans-Peter Seidel, Tobias Ritschel

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.

Finding Your (3D) Center: 3D Object Detection Using a Learned Loss

1 code implementation ECCV 2020 David Griffiths, Jan Boehm, Tobias Ritschel

As we assume the scene not to be labeled by centers, no classic loss, such as Chamfer can be used to train it.

3D Object Detection Object +1

Learning a Neural 3D Texture Space from 2D Exemplars

1 code implementation CVPR 2020 Philipp Henzler, Niloy J. Mitra, Tobias Ritschel

We propose a generative model of 2D and 3D natural textures with diversity, visual fidelity and at high computational efficiency.

Computational Efficiency

Neural View-Interpolation for Sparse Light Field Video

no code implementations30 Oct 2019 Mojtaba Bemana, Karol Myszkowski, Hans-Peter Seidel, Tobias Ritschel

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.

Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning

1 code implementation ICCV 2019 Pedro Hermosilla, Tobias Ritschel, Timo Ropinski

We show that denoising of 3D point clouds can be learned unsupervised, directly from noisy 3D point cloud data only.

Denoising valid

Escaping Plato's Cave: 3D Shape From Adversarial Rendering

no code implementations ICCV 2019 Philipp Henzler, Niloy Mitra, Tobias Ritschel

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.

Deep-learning the Latent Space of Light Transport

1 code implementation12 Nov 2018 Pedro Hermosilla, Sebastian Maisch, Tobias Ritschel, Timo Ropinski

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.

Computational Efficiency

Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds

1 code implementation5 Jun 2018 Pedro Hermosilla, Tobias Ritschel, Pere-Pau Vázquez, Àlvar Vinacua, Timo Ropinski

We propose an efficient and effective method to learn convolutions for non-uniformly sampled point clouds, as they are obtained with modern acquisition techniques.

Point Cloud Segmentation

Learning on the Edge: Explicit Boundary Handling in CNNs

1 code implementation8 May 2018 Carlo Innamorati, Tobias Ritschel, Tim Weyrich, Niloy J. Mitra

Convolutional neural networks (CNNs) handle the case where filters extend beyond the image boundary using several heuristics, such as zero, repeat or mean padding.

Colorization Disparity Estimation +1

Deep Appearance Maps

no code implementations ICCV 2019 Maxim Maximov, Laura Leal-Taixé, Mario Fritz, Tobias Ritschel

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).

Joint Material and Illumination Estimation from Photo Sets in the Wild

1 code implementation23 Oct 2017 Tuanfeng Y. Wang, Tobias Ritschel, Niloy J. Mitra

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.


DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination

no code implementations27 Mar 2016 Stamatios Georgoulis, Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Luc van Gool, Tinne Tuytelaars

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.

Deep Shading: Convolutional Neural Networks for Screen-Space Shading

no code implementations19 Mar 2016 Oliver Nalbach, Elena Arabadzhiyska, Dushyant Mehta, Hans-Peter Seidel, Tobias Ritschel

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.

Image Generation

Novel Views of Objects from a Single Image

no code implementations31 Jan 2016 Konstantinos Rematas, Chuong Nguyen, Tobias Ritschel, Mario Fritz, Tinne Tuytelaars

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.

Novel View Synthesis Object

Deep Reflectance Maps

no code implementations CVPR 2016 Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Efstratios Gavves, Tinne Tuytelaars

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.

3D Object Class Detection in the Wild

no code implementations17 Mar 2015 Bojan Pepik, Michael Stark, Peter Gehler, Tobias Ritschel, Bernt Schiele

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.

Object object-detection +2

Image-based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models

no code implementations CVPR 2014 Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Tinne Tuytelaars

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.

Novel View Synthesis Position +1

Cannot find the paper you are looking for? You can Submit a new open access paper.