Search Results for author:
Found 11 papers, 5 papers with code
FacadeNet: Conditional Facade Synthesis via Selective Editing
We introduce FacadeNet, a deep learning approach for synthesizing building facade images from diverse viewpoints.
WinSyn: A High Resolution Testbed for Synthetic Data
We evaluate a procedural model by training semantic segmentation networks on both synthetic and real images and then comparing their performances on a shared test set of real images.
Large-Scale Auto-Regressive Modeling Of Street Networks
We present a novel generative method for the creation of city-scale road layouts.
Projective Urban Texturing
Re-targeting such 2D datasets to 3D geometry is challenging because the underlying shape, size, and layout of the urban structures in the photos do not correspond to the ones in the target meshes.
Seamless Satellite-image Synthesis
We introduce Seamless Satellite-image Synthesis (SSS), a novel neural architecture to create scale-and-space continuous satellite textures from cartographic data.
How Computer Science Can Aid Forest Restoration
The world faces two interlinked crises: climate change and loss of biodiversity.
SketchGen: Generating Constrained CAD Sketches
Sketches can be represented as graphs, with the primitives as nodes and the constraints as edges.
Retrofitting Parallelism onto OCaml
OCaml is an industrial-strength, multi-paradigm programming language, widely used in industry and academia.
Programming Languages D.3.4
FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchronized GANs
The various GANs are synchronized to produce consistent style distributions over buildings and neighborhoods.
FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs
The various GANs are synchronized to produce consistent style distributions over buildings and neighborhoods.
Graphics
