Welcome to the website of the 1st workshop on Computer Vision Aided Architectural Design (CVAAD). We are delighted that our workshop was hosted at the International Conference on Computer Vision (ICCV) in Paris, 2023.
About the workshop
The workshop aims at expanding the interdisciplinary domain of computer vision in architectural design, encouraging collaboration, and investigating common research interests. By showcasing datasets and applications from architectural design, the workshop creates opportunities for computer vision researchers. Through keynote talks, discussions, and a workshop challenge, attendees explored relevant topics from both generative and analytic computer vision for the applications and processes in architectural design. This shed light on the needs, constraints, and challenges associated with developing and implementing effective computer vision tasks and methods in architectural design and research. The workshop consists of the following:
The schedule can be found here.
Speakers
We had the priviledge of hosting a diverse group of engaging speakers:
- Noah Snavely, Cornell Tech and Google Research
- Daniel G. Aliaga, Purdue University
- Francis Engelmann, ETH Zurich
- Matthias Strandfest, A.G. Archylise
Accepted workshop papers
The following papers were accepted and part of the official ICCV workshop proceedings:
- Scalable MAV Indoor Reconstruction with Neural Implicit Surfaces
- PanoStyle: Semantic, Geometry-Aware, and Shading Independent Photorealistic Style Transfer for Indoor Panoramic Scenes
- MARL: Multi-scale Archetype Representation Learning for Building Energy Estimation
- SSIG: A Visually-Guided Graph Edit Distance for Floor Plan Similarity
- Floor Plan Reconstruction from Sparse Views: Combining Graph Neural Network with Constrained Diffusion
Poster panel
For the poster panel, we invited authors of - 1) relevant-to-the-workshop conference papers 2) other works related to the topic of the workshop and 3) the accepted workshop papers - to present a poster of their work.
1. ICCV 2023 conference papers
- Doppelgangers: Learning to Disambiguate Images of Similar Structures
- SGAligner: 3D Scene Alignment with Scene Graphs
- GlobalMapper: Arbitrary-Shaped Urban Layout Generation
- Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer
2. Guest posters
- Carbon Image Project
- A Taxonomy of Visual Data in Architectural Design
Organization
Seyran Khademi
Assist. Prof. at the faculty of Architecture and the Built Environment, Delft University of Technology
Jan van Gemert
Assoc. Prof. at the faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology
Iro Armeni
Assist. Prof. at the department of Civil and Environmental Engineering, Stanford University
Fatemeh Mostafavi
Doctoral candidate at the faculty of Architecture and the Built Environment, Delft University of Technology
Casper van Engelenburg
Doctoral candidate at the faculty of Architecture and the Built Environment, Delft University of Technology
