Visual AI

Visual AI is the field of artificial intelligence that enables machines to make sense of and act on visual data. At VCLab, the research in Visual AI encompasses different formats of visual data: from images and videos to RTI and 3D surfaces.

Visual AI is becoming increasingly important across various applications. At VCLab, the application fields include 3D object design, architectural geometry, environmental monitoring, 3D acquisition and reconstruction, Extended Reality.

Our results in Visual AI contributed to several research projects, including the Horizon 2020 project SUN - Social and hUman ceNtered XR, and the EU funded PNRR project FAIR - Future Artificial Intelligence Research.

Self-supervised High Dynamic Range Imaging: What Can Be Learned from a Single 8-bit Video?
Recently, Deep Learning-based methods for inverse tone mapping standard dynamic range (SDR) images to obtain high dynamic range (HDR) …
PDF Cite Code DOI
Self-supervised High Dynamic Range Imaging: What Can Be Learned from a Single 8-bit Video?
Geometric deep learning for statics-aware grid shells
This paper introduces a novel method for shape optimization and form-finding of free-form, triangular grid shells, based on geometric …
PDF Cite Code DOI
Geometric deep learning for statics-aware grid shells
Social and hUman ceNtered XR
The Social and hUman ceNtered XR (SUN) project is focused on developing eXtended Reality (XR) solutions that integrate the physical and …
PDF Cite
Social and hUman ceNtered XR
Texture Inpainting for Photogrammetric Models
We devise a technique designed to remove the texturing artefacts that are typical of 3D models representing real-world objects, …
PDF Cite DOI
Texture Inpainting for Photogrammetric Models
On assisting and automatizing the semantic segmentation of masonry walls
PDF Cite
On assisting and automatizing the semantic segmentation of masonry walls
TagLab: AI-assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages
PDF Cite
TagLab: AI-assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages
Towards a topological–geometrical theory of group equivariant non-expansive operators for data analysis and machine learning
We provide a general mathematical framework for group and set equivariance in machine learning. We define group equivariant …
Cite
Towards a topological–geometrical theory of group equivariant non-expansive operators for data analysis and machine learning