Search Results for author: Stavros Tsogkas

Found 16 papers, 5 papers with code

Probabilistic Directed Distance Fields for Ray-Based Shape Representations

no code implementations13 Apr 2024 Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson, Allan Jepson

One fundamental operation applied to such representations is differentiable rendering, as it enables inverse graphics approaches in learning frameworks.

3D Reconstruction

Efficient Flow-Guided Multi-frame De-fencing

no code implementations25 Jan 2023 Stavros Tsogkas, Fengjia Zhang, Allan Jepson, Alex Levinshtein

Taking photographs ''in-the-wild'' is often hindered by fence obstructions that stand between the camera user and the scene of interest, and which are hard or impossible to avoid.

Image Inpainting

Representing 3D Shapes with Probabilistic Directed Distance Fields

no code implementations CVPR 2022 Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson, Allan Jepson

On the other hand, implicit representations (occupancy, distance, or radiance fields) preserve greater fidelity, but suffer from complex or inefficient rendering processes, limiting scalability.

3D Reconstruction

Learning Compositional Shape Priors for Few-Shot 3D Reconstruction

no code implementations11 Jun 2021 Mateusz Michalkiewicz, Stavros Tsogkas, Sarah Parisot, Mahsa Baktashmotlagh, Anders Eriksson, Eugene Belilovsky

The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space.

3D Reconstruction Decoder +2

Disentangling Geometric Deformation Spaces in Generative Latent Shape Models

no code implementations27 Feb 2021 Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson, Allan Jepson

In this work, we improve on a prior generative model of geometric disentanglement for 3D shapes, wherein the space of object geometry is factorized into rigid orientation, non-rigid pose, and intrinsic shape.

Disentanglement Pose Transfer +1

Cycle-Consistent Generative Rendering for 2D-3D Modality Translation

2 code implementations16 Nov 2020 Tristan Aumentado-Armstrong, Alex Levinshtein, Stavros Tsogkas, Konstantinos G. Derpanis, Allan D. Jepson

In the context of computer vision, this corresponds to a learnable module that serves two purposes: (i) generate a realistic rendering of a 3D object (shape-to-image translation) and (ii) infer a realistic 3D shape from an image (image-to-shape translation).

Image Generation Translation

Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors

1 code implementation ECCV 2020 Mateusz Michalkiewicz, Sarah Parisot, Stavros Tsogkas, Mahsa Baktashmotlagh, Anders Eriksson, Eugene Belilovsky

In this work we demonstrate experimentally that naive baselines do not apply when the goal is to learn to reconstruct novel objects using very few examples, and that in a \emph{few-shot} learning setting, the network must learn concepts that can be applied to new categories, avoiding rote memorization.

3D Reconstruction Decoder +4

Appearance Shock Grammar for Fast Medial Axis Extraction from Real Images

no code implementations CVPR 2020 Charles-Olivier Dufresne Camaro, Morteza Rezanejad, Stavros Tsogkas, Kaleem Siddiqi, Sven Dickinson

We make the following specific contributions: i) we extend the shock graph representation to the domain of real images, by generalizing the shock type definitions using local, appearance-based criteria; ii) we then use the rules of a Shock Grammar to guide our search for medial points, drastically reducing run time when compared to other methods, which exhaustively consider all points in the input image;iii) we remove the need for typical post-processing steps including thinning, non-maximum suppression, and grouping, by adhering to the Shock Grammar rules while deriving the medial axis solution; iv) finally, we raise some fundamental concerns with the evaluation scheme used in previous work and propose a more appropriate alternative for assessing the performance of medial axis extraction from scenes.

Geometric Disentanglement for Generative Latent Shape Models

no code implementations ICCV 2019 Tristan Aumentado-Armstrong, Stavros Tsogkas, Allan Jepson, Sven Dickinson

Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics.

3D Object Retrieval 3D Shape Generation +4

DeepFlux for Skeletons in the Wild

2 code implementations CVPR 2019 Yukang Wang, Yongchao Xu, Stavros Tsogkas, Xiang Bai, Sven Dickinson, Kaleem Siddiqi

In the present article, we depart from this strategy by training a CNN to predict a two-dimensional vector field, which maps each scene point to a candidate skeleton pixel, in the spirit of flux-based skeletonization algorithms.

Edge Detection Object +3

AMAT: Medial Axis Transform for Natural Images

1 code implementation ICCV 2017 Stavros Tsogkas, Sven Dickinson

We introduce Appearance-MAT (AMAT), a generalization of the medial axis transform for natural images, that is framed as a weighted geometric set cover problem.


Prior-based Coregistration and Cosegmentation

no code implementations22 Jul 2016 Mahsa Shakeri, Enzo Ferrante, Stavros Tsogkas, Sarah Lippe, Samuel Kadoury, Iasonas Kokkinos, Nikos Paragios

We propose a modular and scalable framework for dense coregistration and cosegmentation with two key characteristics: first, we substitute ground truth data with the semantic map output of a classifier; second, we combine this output with population deformable registration to improve both alignment and segmentation.

Sub-cortical brain structure segmentation using F-CNN's

no code implementations5 Feb 2016 Mahsa Shakeri, Stavros Tsogkas, Enzo Ferrante, Sarah Lippe, Samuel Kadoury, Nikos Paragios, Iasonas Kokkinos

In this paper we propose a deep learning approach for segmenting sub-cortical structures of the human brain in Magnetic Resonance (MR) image data.

Segmentation Semantic Segmentation

Segmentation-aware Deformable Part Models

no code implementations CVPR 2014 Eduard Trulls, Stavros Tsogkas, Iasonas Kokkinos, Alberto Sanfeliu, Francesc Moreno-Noguer

In this work we propose a technique to combine bottom-up segmentation, coming in the form of SLIC superpixels, with sliding window detectors, such as Deformable Part Models (DPMs).

Optical Flow Estimation Segmentation +1

Understanding Objects in Detail with Fine-Grained Attributes

no code implementations CVPR 2014 Andrea Vedaldi, Siddharth Mahendran, Stavros Tsogkas, Subhransu Maji, Ross Girshick, Juho Kannala, Esa Rahtu, Iasonas Kokkinos, Matthew B. Blaschko, David Weiss, Ben Taskar, Karen Simonyan, Naomi Saphra, Sammy Mohamed

We show that the collected data can be used to study the relation between part detection and attribute prediction by diagnosing the performance of classifiers that pool information from different parts of an object.

Attribute Object +2

Cannot find the paper you are looking for? You can Submit a new open access paper.