Search Results for author: Bernhard Egger

Found 38 papers, 17 papers with code

TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models

1 code implementation CVPR 2024 Haomiao Ni, Bernhard Egger, Suhas Lohit, Anoop Cherian, Ye Wang, Toshiaki Koike-Akino, Sharon X. Huang, Tim K. Marks

To guide video generation with the additional image input, we propose a "repeat-and-slide" strategy that modulates the reverse denoising process, allowing the frozen diffusion model to synthesize a video frame-by-frame starting from the provided image.

Denoising Image to Video Generation

Exploring Multi-modal Neural Scene Representations With Applications on Thermal Imaging

no code implementations18 Mar 2024 Mert Özer, Maximilian Weiherer, Martin Hundhausen, Bernhard Egger

Neural Radiance Fields (NeRFs) quickly evolved as the new de-facto standard for the task of novel view synthesis when trained on a set of RGB images.

Novel View Synthesis

exploreCOSMOS: Interactive Exploration of Conditional Statistical Shape Models in the Web-Browser

1 code implementation20 Feb 2024 Maximilian Hahn, Bernhard Egger

Statistical Shape Models of faces and various body parts are heavily used in medical image analysis, computer vision and visualization.

RANRAC: Robust Neural Scene Representations via Random Ray Consensus

no code implementations15 Dec 2023 Benno Buschmann, Andreea Dogaru, Elmar Eisemann, Michael Weinmann, Bernhard Egger

We demonstrate the compatibility and potential of our solution for both photo-realistic robust multi-view reconstruction from real-world images based on neural radiance fields and for single-shot reconstruction based on light-field networks.

Novel View Synthesis Outlier Detection

ReWaRD: Retinal Waves for Pre-Training Artificial Neural Networks Mimicking Real Prenatal Development

1 code implementation28 Nov 2023 Benjamin Cappell, Andreas Stoll, Williams Chukwudi Umah, Bernhard Egger

In this work we aim at the very beginning of our visual experience - pre- and post-natal retinal waves which suggest to be a pre-training mechanism for the primate visual system at a very early stage of development.

Inductive Bias

RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination Prior

1 code implementation15 Nov 2023 James A. D. Gardner, Bernhard Egger, William A. P. Smith

Training our model on a curated dataset of 1. 6K HDR environment maps of natural scenes, we compare it against traditional representations, demonstrate its applicability for an inverse rendering task and show environment map completion from partial observations.

Decoder Depth Estimation +1

From Zero to Hero: Convincing with Extremely Complicated Math

1 code implementation1 Apr 2023 Maximilian Weiherer, Bernhard Egger

Finally, they end up as a researcher, writing boring, non-impressive papers all day long because they only rely on simple mathematics.

Math

ShaRPy: Shape Reconstruction and Hand Pose Estimation from RGB-D with Uncertainty

no code implementations17 Mar 2023 Vanessa Wirth, Anna-Maria Liphardt, Birte Coppers, Johanna Bräunig, Simon Heinrich, Sigrid Leyendecker, Arnd Kleyer, Georg Schett, Martin Vossiek, Bernhard Egger, Marc Stamminger

Therefore, we propose ShaRPy, the first RGB-D Shape Reconstruction and hand Pose tracking system, which provides uncertainty estimates of the computed pose, e. g., when a finger is hidden or its estimate is inconsistent with the observations in the input, to guide clinical decision-making.

Decision Making Gesture Recognition +3

NeRFtrinsic Four: An End-To-End Trainable NeRF Jointly Optimizing Diverse Intrinsic and Extrinsic Camera Parameters

1 code implementation16 Mar 2023 Hannah Schieber, Fabian Deuser, Bernhard Egger, Norbert Oswald, Daniel Roth

Current research on the joint optimization of camera parameters and NeRF focuses on refining noisy extrinsic camera parameters and often relies on the preprocessing of intrinsic camera parameters.

Novel View Synthesis

BOSS: Bones, Organs and Skin Shape Model

no code implementations8 Mar 2023 Karthik Shetty, Annette Birkhold, Srikrishna Jaganathan, Norbert Strobel, Bernhard Egger, Markus Kowarschik, Andreas Maier

Objective: A digital twin of a patient can be a valuable tool for enhancing clinical tasks such as workflow automation, patient-specific X-ray dose optimization, markerless tracking, positioning, and navigation assistance in image-guided interventions.

Approximating Intersections and Differences Between Linear Statistical Shape Models Using Markov Chain Monte Carlo

no code implementations29 Nov 2022 Maximilian Weiherer, Finn Klein, Bernhard Egger

In this paper, we present a new method to qualitatively compare two linear SSMs in dense correspondence by computing approximate intersection spaces and set-theoretic differences between the (hyper-ellipsoidal) allowable shape domains spanned by the models.

Specificity

PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation

1 code implementation CVPR 2023 Karthik Shetty, Annette Birkhold, Srikrishna Jaganathan, Norbert Strobel, Markus Kowarschik, Andreas Maier, Bernhard Egger

Current techniques directly regress the shape, pose, and translation of a parametric model from an input image through a non-linear mapping with minimal flexibility to any external influences.

Ranked #3 on 3D Human Pose Estimation on 3DPW (using extra training data)

3D Human Pose Estimation Camera Calibration +1

State of the Art in Dense Monocular Non-Rigid 3D Reconstruction

no code implementations27 Oct 2022 Edith Tretschk, Navami Kairanda, Mallikarjun B R, Rishabh Dabral, Adam Kortylewski, Bernhard Egger, Marc Habermann, Pascal Fua, Christian Theobalt, Vladislav Golyanik

3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics.

3D Reconstruction

A Lightweight Machine Learning Pipeline for LiDAR-simulation

no code implementations5 Aug 2022 Richard Marcus, Niklas Knoop, Bernhard Egger, Marc Stamminger

Virtual testing is a crucial task to ensure safety in autonomous driving, and sensor simulation is an important task in this domain.

Autonomous Driving BIG-bench Machine Learning +1

Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior

no code implementations7 Jun 2022 James A. D. Gardner, Bernhard Egger, William A. P. Smith

Training our model on a curated dataset of 1. 6K HDR environment maps of natural scenes, we compare it against traditional representations, demonstrate its applicability for an inverse rendering task and show environment map completion from partial observations.

Decoder Inverse Rendering

Building 3D Generative Models from Minimal Data

no code implementations4 Mar 2022 Skylar Sutherland, Bernhard Egger, Joshua Tenenbaum

We extend our model to a preliminary unsupervised learning framework that enables the learning of the distribution of 3D faces using one 3D template and a small number of 2D images.

Face Recognition Gaussian Processes

Survey and Systematization of 3D Object Detection Models and Methods

no code implementations23 Jan 2022 Moritz Drobnitzky, Jonas Friederich, Bernhard Egger, Patrick Zschech

Strong demand for autonomous vehicles and the wide availability of 3D sensors are continuously fueling the proposal of novel methods for 3D object detection.

3D Object Detection Autonomous Vehicles +2

Beyond Flatland: Pre-training with a Strong 3D Inductive Bias

no code implementations30 Nov 2021 Shubhaankar Gupta, Thomas P. O'Connell, Bernhard Egger

Pre-training on large-scale databases consisting of natural images and then fine-tuning them to fit the application at hand, or transfer-learning, is a popular strategy in computer vision.

Data Augmentation Inductive Bias +1

Identity-Expression Ambiguity in 3D Morphable Face Models

no code implementations29 Sep 2021 Bernhard Egger, Skylar Sutherland, Safa C. Medin, Joshua Tenenbaum

We demonstrate that non-orthogonality of the variation in identity and expression can cause identity-expression ambiguity in 3D Morphable Models, and that in practice expression and identity are far from orthogonal and can explain each other surprisingly well.

3D Reconstruction 3D Shape Generation +1

Learning the shape of female breasts: an open-access 3D statistical shape model of the female breast built from 110 breast scans

no code implementations28 Jul 2021 Maximilian Weiherer, Andreas Eigenberger, Bernhard Egger, Vanessa Brébant, Lukas Prantl, Christoph Palm

We present the Regensburg Breast Shape Model (RBSM) -- a 3D statistical shape model of the female breast built from 110 breast scans acquired in a standing position, and the first publicly available.

Specificity

Building 3D Morphable Models from a Single Scan

1 code implementation24 Nov 2020 Skylar Sutherland, Bernhard Egger, Joshua Tenenbaum

We propose a method for constructing generative models of 3D objects from a single 3D mesh.

Face Recognition Gaussian Processes +1

A Morphable Face Albedo Model

1 code implementation CVPR 2020 William A. P. Smith, Alassane Seck, Hannah Dee, Bernard Tiddeman, Joshua Tenenbaum, Bernhard Egger

In this paper, we bring together two divergent strands of research: photometric face capture and statistical 3D face appearance modelling.

Art Analysis Face Model +1

CZ-GEM: A FRAMEWORK FOR DISENTANGLED REPRESENTATION LEARNING

no code implementations ICLR 2020 Akash Srivastava, Yamini Bansal, Yukun Ding, Bernhard Egger, Prasanna Sattigeri, Josh Tenenbaum, David D. Cox, Dan Gutfreund

In this work, we tackle a slightly more intricate scenario where the observations are generated from a conditional distribution of some known control variate and some latent noise variate.

Disentanglement

Patient-specific Conditional Joint Models of Shape, Image Features and Clinical Indicators

no code implementations17 Jul 2019 Bernhard Egger, Markus D. Schirmer, Florian Dubost, Marco J. Nardin, Natalia S. Rost, Polina Golland

We propose and demonstrate a joint model of anatomical shapes, image features and clinical indicators for statistical shape modeling and medical image analysis.

Gaussian Processes

Can Synthetic Faces Undo the Damage of Dataset Bias to Face Recognition and Facial Landmark Detection?

1 code implementation19 Nov 2018 Adam Kortylewski, Bernhard Egger, Andreas Morel-Forster, Andreas Schneider, Thomas Gerig, Clemens Blumer, Corius Reyneke, Thomas Vetter

We observe the following positive effects for face recognition and facial landmark detection tasks: 1) Priming with synthetic face images improves the performance consistently across all benchmarks because it reduces the negative effects of biases in the training data.

Data Augmentation Face Model +3

Training Deep Face Recognition Systems with Synthetic Data

2 code implementations16 Feb 2018 Adam Kortylewski, Andreas Schneider, Thomas Gerig, Bernhard Egger, Andreas Morel-Forster, Thomas Vetter

In our experiments with an off-the-shelf face recognition software we observe the following phenomena: 1) The amount of real training data needed to train competitive deep face recognition systems can be reduced significantly.

Face Model Face Recognition

Empirically Analyzing the Effect of Dataset Biases on Deep Face Recognition Systems

2 code implementations5 Dec 2017 Adam Kortylewski, Bernhard Egger, Andreas Schneider, Thomas Gerig, Andreas Morel-Forster, Thomas Vetter

4) We uncover a main limitation of current DCNN architectures, which is the difficulty to generalize when different identities to not share the same pose variation.

Face Recognition

Morphable Face Models - An Open Framework

2 code implementations25 Sep 2017 Thomas Gerig, Andreas Morel-Forster, Clemens Blumer, Bernhard Egger, Marcel Lüthi, Sandro Schönborn, Thomas Vetter

Non-rigid registration of faces is significant for many applications in computer vision, such as the construction of 3D Morphable face models (3DMMs).

Face Model Gaussian Processes

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