204 citations · 703 across the 41 of their papers we have counts for
22 papers · 1 filter
Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphics
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. To circumvent this issue, the loss…
Neural Field Convolutions by Repeated Differentiation
Ntumba Elie Nsampi, Adarsh Djeacoumar, Hans-Peter Seidel +2
Neural fields are evolving towards a general-purpose continuous representation for visual computing. Yet, despite their numerous appealing properties, they are hardly amenable to s…
3inGAN: Learning a 3D Generative Model from Images of a Self-similar Scene
Animesh Karnewar, Oliver Wang, Tobias Ritschel +1
We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene. Such a model can be used to produce 3D "remixes" of a given scen…
Plateau-reduced Differentiable Path Tracing
Michael Fischer, Tobias Ritschel
Current differentiable renderers provide light transport gradients with respect to arbitrary scene parameters. However, the mere existence of these gradients does not guarantee use…
ReLU Fields: The Little Non-linearity That Could
Animesh Karnewar, Tobias Ritschel, Oliver Wang +1
In many recent works, multi-layer perceptions (MLPs) have been shown to be suitable for modeling complex spatially-varying functions including images and 3D scenes. Although the ML…
Variance-Aware Weight Initialization for Point Convolutional Neural Networks
Pedro Hermosilla, Michael Schelling, Tobias Ritschel +1
Appropriate weight initialization has been of key importance to successfully train neural networks. Recently, batch normalization has diminished the role of weight initialization b…
Unsupervised Learning of 3D Object Categories from Videos in the Wild
Philipp Henzler, Jeremy Reizenstein, Patrick Labatut +4
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. While several recent works have obtained analogous…
Curiosity-driven 3D Object Detection Without Labels
David Griffiths, Jan Boehm, Tobias Ritschel
In this paper we set out to solve the task of 6-DOF 3D object detection from 2D images, where the only supervision is a geometric representation of the objects we aim to find. In d…
Deep Generative Modelling of Human Reach-and-Place Action
Connor Daly, Yuzuko Nakamura, Tobias Ritschel
The motion of picking up and placing an object in 3D space is full of subtle detail. Typically these motions are formed from the same constraints, optimizing for swiftness, energy…
X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
Mojtaba Bemana, Karol Myszkowski, Hans-Peter Seidel +1
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 th…
Finding Your (3D) Center: 3D Object Detection Using a Learned Loss
David Griffiths, Jan Boehm, Tobias Ritschel
Massive semantically labeled datasets are readily available for 2D images, however, are much harder to achieve for 3D scenes. Objects in 3D repositories like ShapeNet are labeled,…
Learning a Neural 3D Texture Space from 2D Exemplars
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. This is enabled by a family of methods that extend…
Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning
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. This is achieved by extending recent ideas from learning of uns…
Escaping Plato's Cave: 3D Shape From Adversarial Rendering
Philipp Henzler, Niloy Mitra, Tobias Ritschel
We introduce PlatonicGAN to discover the 3D structure of an object class from an unstructured collection of 2D images, i.e., where no relation between photos is known, except that…
Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds
Pedro Hermosilla, Tobias Ritschel, Pere-Pau Vázquez +2
Deep learning systems extensively use convolution operations to process input data. Though convolution is clearly defined for structured data such as 2D images or 3D volumes, this…
Learning on the Edge: Explicit Boundary Handling in CNNs
Carlo Innamorati, Tobias Ritschel, Tim Weyrich +1
Convolutional neural networks (CNNs) handle the case where filters extend beyond the image boundary using several heuristics, such as zero, repeat or mean padding. These schemes ar…
Deep Appearance Maps
Maxim Maximov, Laura Leal-Taixé, Mario Fritz +1
We propose a deep representation of appearance, i. e., the relation of color, surface orientation, viewer position, material and illumination. Previous approaches have useddeep lea…
What Is Around The Camera?
Stamatios Georgoulis, Konstantinos Rematas, Tobias Ritschel +3
How much does a single image reveal about the environment it was taken in? In this paper, we investigate how much of that information can be retrieved from a foreground object, com…
DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination
Stamatios Georgoulis, Konstantinos Rematas, Tobias Ritschel +3
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…
Novel Views of Objects from a Single Image
Konstantinos Rematas, Chuong Nguyen, Tobias Ritschel +2
Taking an image of an object is at its core a lossy process. The rich information about the three-dimensional structure of the world is flattened to an image plane and decisions su…
What is Holding Back Convnets for Detection?
Bojan Pepik, Rodrigo Benenson, Tobias Ritschel +1
Convolutional neural networks have recently shown excellent results in general object detection and many other tasks. Albeit very effective, they involve many user-defined design c…
3D Object Class Detection in the Wild
Bojan Pepik, Michael Stark, Peter Gehler +2
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 ro…