Wednesdays@DEI: Talks, 01-03-2023

Author & Affiliation: Stuart James, Researcher (Assistant Professor), Pattern Analysis and Computer Vision (PAVIS), Istituto Italiano di Tecnologia

Title: Reframing computational jigsaw puzzle solving

Abstract: Jigsaw puzzles are a popular and enjoyable pastime that humans can easily solve, even with many pieces. Puzzle solving is a combinatorial problem where the space of possible solutions is exponential with the number of pieces and rotations of pieces, making it a challenging problem for computational methods. However, the problem has significant importance as it can be generalised to many application domains, including archaeological reassembly, molecular docking, and robotic-based object assembly. In this talk, we will explore how generative image-based approaches reframe the problem from a pairwise optimisation to a linear assignment problem, significantly reducing the combinatorial challenge. In contrast to prior deep-learning approaches, we show how such a single learned model can generalise over puzzles with varying numbers of pieces and, in turn, solve both square and rotated piece puzzles. We will conclude with considerations of downstream tasks and the interaction and design constraints.

Bio: 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 currently a co-PI on the RePAIR EU FET, DCitizens EU Twinning, and BoSS EU Lighthouse. He was a co-PI on the MEMEX RIA EU H2020 project coordinated at IIT for increasing social inclusion with Cultural Heritage. 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 holds an honorary position at UCL and UCL Digital Humanities and is an international collaborator of ITI/LARSyS. He also regularly organises Vision for Art (VISART) workshop and Humanities-orientated tutorials and was Program Chair at British Machine Conference (BMVC) 2021.