70 citations · 110 across the 10 of their papers we have counts for
11 papers
Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models
Jian Shi, John Femiani, Peter Wonka
We present a new inference-time sampler for diffusion models that gives a pretrained model a capability it was never trained for: constructing the atlas of the population it synthe…
Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
Fedor Rodionov, Aleksandar Cvejic, Michael Birsak +2
Furnished floor plans support real-estate visualization, interior design, and architectural workflows, yet automatic furnishing remains challenged by limited real-world data and th…
OmniAcc: Personalized Accessibility Assistant Using Generative AI
Siddhant Karki, Ethan Han, Nadim Mahmud +3
Individuals with ambulatory disabilities often encounter significant barriers when navigating urban environments due to the lack of accessible information and tools. This paper pre…
SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
Sathvik Chereddy, John Femiani
We present SketchDNN, a generative model for synthesizing CAD sketches that jointly models both continuous parameters and discrete class labels through a unified continuous-discret…
FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations
Fedor Rodionov, Abdelrahman Eldesokey, Michael Birsak +3
We introduce FloorplanQA, a diagnostic benchmark for evaluating spatial reasoning in large language models (LLMs). FloorplanQA is grounded in structured representations of indoor s…
MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models
Michael Birsak, John Femiani, Biao Zhang +1
Assigning realistic materials to 3D models remains a significant challenge in computer graphics. We propose MatCLIP, a novel method that extracts shape- and lighting-insensitive de…
WinSyn: A High Resolution Testbed for Synthetic Data
Tom Kelly, John Femiani, Peter Wonka
We present WinSyn, a unique dataset and testbed for creating high-quality synthetic data with procedural modeling techniques. The dataset contains high-resolution photographs of wi…
CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions
Rameen Abdal, Peihao Zhu, John Femiani +2
The success of StyleGAN has enabled unprecedented semantic editing capabilities, on both synthesized and real images. However, such editing operations are either trained with seman…
Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks
Peihao Zhu, Rameen Abdal, John Femiani +1
We present a new method for one shot domain adaptation. The input to our method is trained GAN that can produce images in domain A and a single reference image I_B from domain B. T…
Barbershop: GAN-based Image Compositing using Segmentation Masks
Peihao Zhu, Rameen Abdal, John Femiani +1
Seamlessly blending features from multiple images is extremely challenging because of complex relationships in lighting, geometry, and partial occlusion which cause coupling betwee…
Facade Segmentation in the Wild
John Femiani, Wamiq Reyaz Para, Niloy Mitra +1
Urban facade segmentation from automatically acquired imagery, in contrast to traditional image segmentation, poses several unique challenges. 360-degree photospheres captured from…