
SketchGen: Generating Constrained CAD Sketches
Computeraided design (CAD) is the most widely used modeling approach fo...
read it

SelfSupervised Learning of Domain Invariant Features for Depth Estimation
We tackle the problem of unsupervised synthetictorealistic domain adap...
read it

Barbershop: GANbased Image Compositing using Segmentation Masks
Seamlessly blending features from multiple images is extremely challengi...
read it

Labels4Free: Unsupervised Segmentation using StyleGAN
We propose an unsupervised segmentation framework for StyleGAN generated...
read it

Improved StyleGAN Embedding: Where are the Good Latents?
StyleGAN is able to produce photorealistic images that are almost indist...
read it

AdaBins: Depth Estimation using Adaptive Bins
We address the problem of estimating a high quality dense depth map from...
read it

Generative Layout Modeling using Constraint Graphs
We propose a new generative model for layout generation. We generate lay...
read it

Training Data Generating Networks: Linking 3D Shapes and FewShot Classification
We propose a novel 3d shape representation for 3d shape reconstruction f...
read it

Structured Regularization of Functional Map Computations
We consider the problem of nonrigid shape matching using the functional...
read it

ChannelDirected Gradients for Optimization of Convolutional Neural Networks
We introduce optimization methods for convolutional neural networks that...
read it

StyleFlow: Attributeconditioned Exploration of StyleGANGenerated Images using Conditional Continuous Normalizing Flows
Highquality, diverse, and photorealistic images can now be generated by...
read it

MapTree: Recovering Multiple Solutions in the Space of Maps
In this paper we propose an approach for computing multiple highquality...
read it

Disentangled Image Generation Through Structured Noise Injection
We explore different design choices for injecting noise into generative ...
read it

MGCN: Descriptor Learning using Multiscale GCNs
We propose a novel framework for computing descriptors for characterizin...
read it

Point Cloud Instance Segmentation using Probabilistic Embeddings
In this paper we propose a new framework for point cloud instance segmen...
read it

SEAN: Image Synthesis with Semantic RegionAdaptive Normalization
We propose semantic regionadaptive normalization (SEAN), a simple but e...
read it

Image2StyleGAN++: How to Edit the Embedded Images?
We propose Image2StyleGAN++, a flexible image editing framework with man...
read it

StructEdit: Learning Structural Shape Variations
Learning to encode differences in the geometry and (topological) structu...
read it

3D Manhattan Room Layout Reconstruction from a Single 360 Image
Recent approaches for predicting layouts from 360 panoramas produce exce...
read it

Photorealistic Material Editing Through Direct Image Manipulation
Creating photorealistic materials for light transport algorithms require...
read it

StructureNet: Hierarchical Graph Networks for 3D Shape Generation
The ability to generate novel, diverse, and realistic 3D shapes along wi...
read it

TileGAN: Synthesis of LargeScale NonHomogeneous Textures
We tackle the problem of texture synthesis in the setting where many inp...
read it

ZoomOut: Spectral Upsampling for Efficient Shape Correspondence
We present a simple and efficient method for refining maps or correspond...
read it

Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?
We propose an efficient algorithm to embed a given image into the latent...
read it

Computational Design of Lightweight Trusses
Trusses are loadcarrying lightweight structures consisting of bars con...
read it

High Quality Monocular Depth Estimation via Transfer Learning
Accurate depth estimation from images is a fundamental task in many appl...
read it

Latent Filter Scaling for Multimodal Unsupervised ImagetoImage Translation
In multimodal unsupervised imagetoimage translation tasks, the goal is...
read it

DuLaNet: A DualProjection Network for Estimating Room Layouts from a Single RGB Panorama
We present a deep learning framework, called DuLaNet, to predict Manhat...
read it

Do GAN Loss Functions Really Matter?
In this paper, we address the recent controversy between Lipschitz regul...
read it

FrankenGAN: Guided Detail Synthesis for Building MassModels Using StyleSynchonized GANs
Coarse building mass models are now routinely generated at scales rangin...
read it

Continuous and Orientationpreserving Correspondences via Functional Maps
We propose a method for efficiently computing orientationpreserving and...
read it

Facade Segmentation in the Wild
Urban facade segmentation from automatically acquired imagery, in contra...
read it

Gaussian Material Synthesis
We present a learningbased system for rapid massscale material synthes...
read it

Supervised Convolutional Sparse Coding
Convolutional Sparse Coding (CSC) is a wellestablished image representa...
read it

Integration of Absolute Orientation Measurements in the KinectFusion Reconstruction pipeline
In this paper, we show how absolute orientation measurements provided by...
read it

Fast Convolutional Sparse Coding in the Dual Domain
Convolutional sparse coding (CSC) is an important building block of many...
read it

TRex: A Tomography Reconstruction Proximal Framework for Robust Sparse View XRay Applications
We present TRex, a flexible and robust Tomographic Reconstruction framew...
read it

Curve Networks for Surface Reconstruction
Manmade objects usually exhibit descriptive curved features (i.e., curv...
read it

Computational Network Design from Functional Specifications
Connectivity and layout of underlying networks largely determine the beh...
read it

RAID: A RelationAugmented Image Descriptor
As humans, we regularly interpret images based on the relations between ...
read it

Inverse Procedural Modeling of Facade Layouts
In this paper, we address the following research problem: How can we gen...
read it

A Safe Screening Rule for Sparse Logistic Regression
The l1regularized logistic regression (or sparse logistic regression) i...
read it

Lasso Screening Rules via Dual Polytope Projection
Lasso is a widely used regression technique to find sparse representatio...
read it

Gap Processing for Adaptive Maximal PoissonDisk Sampling
In this paper, we study the generation of maximal Poissondisk sets with...
read it

Fused Multiple Graphical Lasso
In this paper, we consider the problem of estimating multiple graphical ...
read it
Peter Wonka
verfied profile
Professor, Computer Science, Associate Director, Visual Computing Center, Computer, Electrical and Mathematical Science and Engineering Division, KAUST