Researcher (Assistant Professor) in Computer Vision at the Istituto Italiano di Tecnologia (IIT). Stuart's research focus is on Visual Reasoning to understand the layout of visual content from Iconography (e.g. Sketches) to 3D Scene understanding and their implications on methods of interaction. He is a PI on the MEMEX RIA EU H2020 project for increasing social inclusion with Cultural Heritage and Co-PI on the RePAIR EU FET H2020 project for the reconstruction of frescoes. Stuart has previously held PostDoc positions at IIT, University College London (UCL) and the University of Surrey. Also, at the University of Surrey, Stuart was awarded his PhD on visual information retrieval for sketches. Stuart continues to hold an honorary position at UCL and UCL Digital Humanities. He also regularly organises workshops and conferences, most recently the Vision for Art (VISART) Workshop at ECCV'20 and British Machine Conference (BMVC) 2021.

Stuart James




Research interests

My research activities fit broadly into Spatial Reasoning — how we can reason about the layout of objects in space in both 2D and 3D to provide insight or retrieve relevant information. My research has a keen interest on varied data types including those from the Humanities such as Art and Cultural Heritage.

Exploring using Depth and Knowledge to answer questions specifically related to the layout of a 3D scene from a 2D perspective.

Visual Question & Answering

Detection, Representation and Reasoning on simplified representations or symbols such as Sketch, Line, Hatching, Motifs or icons.

Abstract & Iconography Reasoning

Identifying and retrieving relevant knowledge held within Knowledge Graphs to support Computer Vision tasks such as Visual Question and Answering or reasoning on location.

Knowledge Retrieval & Reasoning

Reconstructing the semantic relational structure of the scene using geometry and knowledge. Providing advanced interaction for questioning and reasoning.

Scene Graph

Principally on layout of content in 2D or 3D and how to make decisions that influence about a path or option linked with Visual Question and Answering

Planning & Reasoning

We have explored using sketches to search collections of videos using Visual Storyboarding to express the sequence of events in the target clip.

Sketch based Retrieval

We are using sequences to retrieve information providing a broader context than a one-off search. We have demonstrated through Free-Hand storyboarding and storey synthesis.

Visual Narratives and Stories

Within VR we explored the use free-hand sketching in an Immersive Environment (VR) with multiple modalities for the task of retrieval.

Interaction in Virtual Reality

Providing storytelling experiences overlaying information of surrounding Cultural Heritage and the stories of the particpants in the MEMEX Project.

Interaction in Augmented Reality

Cultural Heritage & Digital Humanities

Assistive Technologies


Research Group & Collaborators

Research Topic: Causality

Supervisor with Dr Jacopo Cavazza (IIT) and Dr Alessio Del Bue (IIT)

Davide Talon

PhD Student

Research Topic: Localising ourselves and objects for Social Good

Collaborator with Dr Alessio Del Bue (IIT)

Dr Matteo Taiana

PostDoc Collaborator

Research Topic: Optimising camera localisation in urban scenes

Collaborator with Dr Alessio Del Bue (IIT)

Dr Matteo Toso

PostDoc Collaborator

Research Topic: RePAIR Fresco 3D reconstruction and assembly

Collaborator with Dr Alessio Del Bue (IIT)

Dr Theodore Tsesmelis

PostDoc Collaborator

Research Topic: Immersive spatial interaction within Virtual Reality

Collaborator with Prof. Anthony Steed (UCL)

Daniele Giunchi

External Collaborator

All associates in research lines PAVIS and VGM at Istituto Italiano di Tecnologia

Latest Blog Post

03 Dec 2020 . research . Three great videos about the pilot locations of MEMEX Comments

We recently published three videos on the pilot locations, Paris, Barcelona and Spain, of the MEMEX Project. This challenging collaboration effort came together during the second wave of COVID so a massive effort was needed by the Michael Culture Association, NOHO Limited, Fundacio Interarts per a la Cooperacio Cultural Internacional (InterArts), Mapas das Ideias and Dédale.


  • October 2022

  • September 2021

    New EU project - RePAIR

  • April 2021

    Program Chair at BMVC’21

  • August 2020

  • December 2019

    Rejoined Visual Geometry and Modelling Lab of IIT

  • January 2019

    Researcher (Assist. Prof) in Cultural Heritage in IIT

  • April 2017

    Moved to Istituto Italiano di Tecnologia (IIT)

  • April 2017

    Became Honorary Research Associate at UCL

  • October 2016

  • April 2016

    Invited to Rank Prize Symposium on Computer Vision and Video Effects

  • April 2016

    Graduated as Doctor of Philosophy

  • October 2015

    Research Associate at UCL with Prof. Tim Weyrich

  • September 2015

    Defended PhD Thesis

Latest Publication

2022 PoserNet: Refining Relative Camera Poses Exploiting Object Detections

The estimation of the camera poses associated with a set of images commonly relies on feature matches between the images. In contrast, we are the first to address this challenge by using objectness regions to guide the pose estimation problem rather than explicit semantic object detections. We propose Pose Refiner Network (PoserNet) a light-weight Graph Neural Network to refine the approximate pair-wise relative camera poses. PoserNet exploits associations between the objectness regions - concisely expressed as bounding boxes - across multiple views to globally refine sparsely connected view graphs. We evaluate on the 7-Scenes dataset across varied sizes of graphs and show how this process can be beneficial to optimisation-based Motion Averaging algorithms improving the median error on the rotation by 62 ◦ with respect to the initial estimates obtained based on bounding boxes. Code and data are available at

Accepted at European Conference on Computer Vision (ECCV 2022) in Tal Aviv, Israel`.

Title = {PoserNet: Refining Relative Camera Poses Exploiting Object Detections},
Author = {Matteo Taiana and Matteo Toso and Stuart James and Alessio Del Bue},
booktitle = {Proceedings of the European Conference on Computer Vision ({ECCV})},
Year = {2022},

See full publication index


To find out more about our research you can find me at...

Visual Geometry and Modelling Lab

Center for Human Technologies - Istituto Italiano di Tecnologia
Via Enrico Melen, 83, 16152 Genova GE