Seminars – AAG

Upcoming Seminars

Past Seminars

ELLIS Algebraic Vision & Machine Learning Workshop 2024

2024-07-02 Viktor Korotynskiy  Exploiting Lie group actions to decompose minimal problems in 3D reconstruction
2024-07-02 Kathlen Kohn Order-one rolling shutter cameras
2024-07-02 Orlando Marigliano  Classifying Minimal Problems for Rolling Shutter Cameras
2024-07-02 Gabrielle Flood  Minimal Solvers for Point Cloud Matching with Statistical Deformations and Some Multi-view Geometry for Parallel Cylinders
2024-07-02 Marten Wadenback  Geometric Deep Learning Using Spherical Neurons
2024-07-02 Diana Sungatullina  MinBackProp – Backpropagating through Minimal Solvers
2024-07-03 Tomas Votroubek  Branch and Bound for Optimal Kinematic Configurations
2024-07-03 Tolga Birdal  Topological deep learning
2024-07-03 Luke Oeding  Tensor Decompositions of Calibrated Trifocal Tensors
2024-07-03 Elima Shehu  Fast and stable triangulation using incident points with respect to a line
2024-07-03 Federica Arrigoni  Viewing Graph Solvability in Structure from Motion
2024-07-03 Andrea Fusiello  Putting view-graph solvability in a rigidity perspective
2024-07-03 Petr Hruby  Efficient Solution of Point-Line Absolute Pose
2024-07-04 Kalle Astrom  Minimal (and critical) configurations for structure from motion problems from distance measurements
2024-07-04 Luca Magri  Critical configurations as transformations between images
2024-07-04 Felix Rydel  Metric Multiview Geometry – a Catalogue in Low Dimensions
2024-07-04 Andrea Porfiri Dal Cin Minimal Perspective Autocalibration
2024-07-04 Yaqing Ding Relative pose estimation using relative depth

2022-12-14 Aless Lasaruk An Efficient Model for a Camera Behind a Parallel Refractive Slab

Algebraic Vision Meeting II   (full schedule)
2022-07-25   Simon Telen   Toric Geometry of Entropic Regularization
2022-07-25   Evgeniy Martyushev   Optimizing Elimination Templates by Greedy Parameter Search
2022-07-25   James Pritts   Rectification, Auto-Calibration, and Scene Parsing from Affine-Correspondences of Repetitive Textures
2022-07-22   Snehal Bhayani   Minimal problems for Semi-generalized Homographies
2022-07-22   Anton Leykin   Homotopy continuation for geometric problems in vision
2022-07-21   Kathlén Kohn   Algebraic statistics — Invariant theory and scaling algorithms for maximum likelihood estimation
2022-07-21   Federica Arrigoni   Viewing graph solvability
2022-07-21   Luca Magri   Self-calibration in the presence of multiple motions
2022-07-21   Viktor Korotynskiy   Interpolating Symmetries of Parametric Polynomial Systems
2022-07-20   Andrea Porfiri Dal Cin   Synchronization on Group-labelled Multi-graphs

Algebraic Vision Meeting I
2022-06-03   Gabriel Ong   G-Equivariant Neural Networks in Computer Vision (video)
2022-06-03   Timothy Duff   Polynomial constraints on points and cameras (video)
2022-06-03   Elima Shehu   The line multiview variety (video)
2022-06-02   Kathlén Kohn   The Geometry of Linear Convolutional Networks (video)
2022-06-02   Viktor Larsson   Camera Pose Estimation with Implicit Distortion Models (video)
2022-06-02   Diana Sungatullina   NeRF in detail: Learning to sample for view synthesis   (*Reading group in Pattern Recognition and Computer Vision)
2022-06-01   Diego Thomas   Building new bridges between the Cyber and physical worlds by 3D vision (video)
2022-06-01   Paul Breiding   HomotopyContinuation.jl: A package for homotopy continuation in Julia.
2022-06-01   Orlando Marigliano   Minimal Problems for Rolling Shutter Cameras (video)
2022-05-31   Zuzana Kúkelová   Methods for Generating Efficient Algebraic Solvers for Computer Vision Problems   (*AICzechia seminar)
2022-05-31   Felix Rydell   The Generalized Multiview Variety (video)
2022-05-31   Petr Hrubý   Learning to Solve Hard Minimal Problems (video)
2022-05-31   Martin Bråtelund   On the Compatibility of Fundamental Matrices (video)

2022-05-20 Timothy Duff Galois/monodromy groups for decomposing minimal problems in 3D reconstruction (video)

2019-10-31, 11:00 – 12:00 Josselin Bonnevie. Learning to navigate in novel, previously unseen indoor environments (Internal mini-seminar)  (B-633)
2019-07-24, 11:00 – 12:00 Vladimir Petrik. Reinforcement learning and its applications (B-633)
Abstract:
In the mini-seminar, I will briefly describe the reinforcement learning (RL) framework with the focus on model-based RL. The model-based RL builds an intermediate model from observations and trains the controller on it. This intermediate layer increases the data-efficiency but at the same time, it increases the computational cost. I will show the tasks on which I have applied the RL in the past and suggest future extensions. The seminar will be followed by a discussion of these future extensions/directions.
2019-07-18, 11:00 – 12:30 Timothy Duff. Intro to homotopy continuation with a view towards minimal problems
2019-07-17, 14:00 – 15:30 Kathlen Kohn. Point-Line Minimal Problems in Complete Multi-View Visibility
2019-07-16, 11:00 – 12:30 Andrea Fussielo. Synchronisation: from pairwise measures to global values
2019-03-05, 14:00 – 15:30 Simon Telen. Stabilized algebraic methods for numerical root finding
2019-01-23, 11:00 – 12:00 Mircea Cimpoi. [Internal seminar] NeurIPS 2018 Summary (internal link) – and Neighborhood consensus networks
2018-10-05, 11:30 – 12:00 Mateusz Kozinski. Learning to Segment 3D Linear Structures Using Only 2D Annotations
2018-06-11, 10:00 – 12:00  Mircea Cimpoi. [Reading group] Learning to Find Good Correspondences
2018-06-05, 14:00 – 16:00  Stanislav Steidl. [Reading group] DSAC-Differentiable RANSAC for camera localization
2018-05-31, 10:00 – 12:00  Pierre-Yves Masse. A shortest path introduction to reinforcement learning
2018-05-24, 10:00 – 11:00 Jiri Sedlar. Estimating 3D person-object interactions with contacts
2018-05-24, 11:00 – 12:00  Georgy Ponimatkin. Possible applications of deep learning for ultrarelativistic heavy-ion collisions
2018-05-21, 12:45 – 14:15 Michal Jancosek. Automatic reconstruction of 3D models @ capturingreality.com
2018-05-17, 10:00 – 12:00 Pavel Trutman. Solving polynomial equations by optimization
2018-05-10, 10:00 – 12:00 Tomas Pajdla. What are Groebner bases and how to solve systems of polynomial equations II
2018-05-04, 14:00 – 16:00 Tomas Pajdla. What are Groebner bases and how to solve systems of polynomial equations I
2018-04-23, 10:00 – 12:00 Mircea Cimpoi. Introduction to CNNs
2018-04-17, 14:00 – 16:00 James Pritts. Radially-Distorted Conjugate Translations
2018-04-10, 10:00 – 12:00 Federica Arrigoni. Consistent multi-view matching by spectral decomposition
2018-03-23, 10:00 – 12:00 Ludovic Magerand. From Incremental To Hierarchical Projective SfM

Abstracts

2019-03-05, 14:00 – 15:30 Simon Telen. Stabilized algebraic methods for numerical root finding
Abstract
We consider the problem of finding the isolated points defined by an ideal in a ring of (Laurent) polynomials with complex coefficients. Algebraic approaches for solving this use rewriting techniques modulo the ideal to reduce the problem to a univariate root finding or eigenvalue problem. We introduce a general framework for algebraic solvers in which it is possible to stabilize the computations in finite precision arithmetic. The framework is based on truncated normal forms (TNFs), which generalize Groebner and border bases. The stabilization comes from a ‘good’ choice of basis for the quotient algebra of the ideal and from compactification of the solution space.

2018-05-21, 12:45 – 14:15 Michal Jancosek Localization of the photography in the 3D space, automatic reconstruction of the accurate 3D model and state-of-the-art of modern photogrammetry (Karlovo namesti 3, Buiding E, 1st floor, room K-127 (https://www.youtube.com/watch?v=cwxHhPTC3KY)
Abstract
Extensive academic and commercial research, significant improvement of the quality and availability of cameras has brought its benefits in a form of robust methods that allow reconstruction of highly precise 3D models using easily accessible gadgets, as computer + standard camera/smartphone. In this session, the graduate of the CTU in Prague, RNDr. Michal Jančošek PhD., one of the co-founders of the Slovak company Capturing Reality, will introduce the current state-of-the-art in automatic extraction of 3D models using images, laser scans, UAV or synchronized camera rigs. Michal will talk about the changing possibilities and what new challenges has this opened up. He will also introduce their Software Development Kit (RealityCapture Engine) that allows smooth use of their in-house developed algorithms for automatic camera calibration, calculation of camera poses and orientation, 3D model reconstruction to the triangular mesh form, creating high quality per-vertex colors and texturing for the model and offers also algorithms for scene simplification, render and export. In brief, he will demonstrate the use of the Engine and will outline the number of possible research and application thesis that it could be applied on.