Search Results for author: Tolga Birdal

Found 47 papers, 21 papers with code

NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

no code implementations5 Mar 2024 Yannan He, Garvita Tiwari, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll

Faithfully modeling the space of articulations is a crucial task that allows recovery and generation of realistic poses, and remains a notorious challenge.

Pose Estimation

Fun with Flags: Robust Principal Directions via Flag Manifolds

no code implementations8 Jan 2024 Nathan Mankovich, Gustau Camps-Valls, Tolga Birdal

In this work, we present a unifying formalism for PCA and its variants, and introduce a framework based on the flags of linear subspaces, \ie a hierarchy of nested linear subspaces of increasing dimension, which not only allows for a common implementation but also yields novel variants, not explored previously.

Dimensionality Reduction

Combinatorial Complexes: Bridging the Gap Between Cell Complexes and Hypergraphs

no code implementations15 Dec 2023 Mustafa Hajij, Ghada Zamzmi, Theodore Papamarkou, Aldo Guzmán-Sáenz, Tolga Birdal, Michael T. Schaub

In this context, cell complexes are often seen as a subclass of hypergraphs with additional algebraic structure that can be exploited, e. g., to develop a spectral theory.

SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

no code implementations31 Oct 2023 Zhengdi Yu, Shaoli Huang, Yongkang Cheng, Tolga Birdal

SignAvatars facilitates various tasks such as 3D sign language recognition (SLR) and the novel 3D SL production (SLP) from diverse inputs like text scripts, individual words, and HamNoSys notation.

Sign Language Production Sign Language Recognition

Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients

no code implementations23 Oct 2023 Maximilian Krahn, Michelle Sasdelli, Fengyi Yang, Vladislav Golyanik, Juho Kannala, Tat-Jun Chin, Tolga Birdal

We present, QP-SBGD, a novel layer-wise stochastic optimiser tailored towards training neural networks with binary weights, known as binary neural networks (BNNs), on quantum hardware.

Variational Inference for SDEs Driven by Fractional Noise

no code implementations19 Oct 2023 Rembert Daems, Manfred Opper, Guillaume Crevecoeur, Tolga Birdal

In this paper, building upon the Markov approximation of fBM, we derive the evidence lower bound essential for efficient variational inference of posterior path measures, drawing from the well-established field of stochastic analysis.

Variational Inference Video Prediction

VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs

no code implementations ICCV 2023 Moayed Haji Ali, Andrew Bond, Tolga Birdal, Duygu Ceylan, Levent Karacan, Erkut Erdem, Aykut Erdem

However, the applicability of such advancements to the video domain has been hindered by the difficulty of representing and controlling videos in the latent space of GANs.

Image Animation Video Editing +1

Chordal Averaging on Flag Manifolds and Its Applications

1 code implementation ICCV 2023 Nathan Mankovich, Tolga Birdal

This paper presents a new, provably-convergent algorithm for computing the flag-mean and flag-median of a set of points on a flag manifold under the chordal metric.

Disentangling Content and Motion for Text-Based Neural Video Manipulation

1 code implementation5 Nov 2022 Levent Karacan, Tolga Kerimoğlu, İsmail İnan, Tolga Birdal, Erkut Erdem, Aykut Erdem

Giving machines the ability to imagine possible new objects or scenes from linguistic descriptions and produce their realistic renderings is arguably one of the most challenging problems in computer vision.

6D Camera Relocalization in Visually Ambiguous Extreme Environments

no code implementations13 Jul 2022 Yang Zheng, Tolga Birdal, Fei Xia, Yanchao Yang, Yueqi Duan, Leonidas J. Guibas

To this end, we propose: (i) a hierarchical localization system, where we leverage temporal information and (ii) a novel environment-aware image enhancement method to boost the robustness and accuracy.

Camera Relocalization Image Enhancement

Topological Deep Learning: Going Beyond Graph Data

3 code implementations1 Jun 2022 Mustafa Hajij, Ghada Zamzmi, Theodore Papamarkou, Nina Miolane, Aldo Guzmán-Sáenz, Karthikeyan Natesan Ramamurthy, Tolga Birdal, Tamal K. Dey, Soham Mukherjee, Shreyas N. Samaga, Neal Livesay, Robin Walters, Paul Rosen, Michael T. Schaub

Topological deep learning is a rapidly growing field that pertains to the development of deep learning models for data supported on topological domains such as simplicial complexes, cell complexes, and hypergraphs, which generalize many domains encountered in scientific computations.

Graph Learning

Q-FW: A Hybrid Classical-Quantum Frank-Wolfe for Quadratic Binary Optimization

no code implementations23 Mar 2022 Alp Yurtsever, Tolga Birdal, Vladislav Golyanik

We present a hybrid classical-quantum framework based on the Frank-Wolfe algorithm, Q-FW, for solving quadratic, linearly-constrained, binary optimization problems on quantum annealers (QA).

Graph Matching

Riemannian Functional Map Synchronization for Probabilistic Partial Correspondence in Shape Networks

no code implementations29 Nov 2021 Faria Huq, Adrish Dey, Sahra Yusuf, Dena Bazazian, Tolga Birdal, Nina Miolane

Our experiments demonstrate that constraining the synchronization on the Riemannian manifold $SO(n)$ improves the estimation of the functional maps, while our RLFM sampler provides for the first time an uncertainty quantification of the results.

Graph Matching Uncertainty Quantification

Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization

1 code implementation25 Nov 2021 Jiahui Huang, Tolga Birdal, Zan Gojcic, Leonidas J. Guibas, Shi-Min Hu

We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds.

Point Cloud Registration

Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks

2 code implementations NeurIPS 2021 Tolga Birdal, Aaron Lou, Leonidas Guibas, Umut Şimşekli

Disobeying the classical wisdom of statistical learning theory, modern deep neural networks generalize well even though they typically contain millions of parameters.

Learning Theory Topological Data Analysis

Weakly Supervised Learning of Rigid 3D Scene Flow

1 code implementation CVPR 2021 Zan Gojcic, Or Litany, Andreas Wieser, Leonidas J. Guibas, Tolga Birdal

We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies.

Autonomous Driving Scene Flow Estimation +2

Quantum Permutation Synchronization

no code implementations CVPR 2021 Tolga Birdal, Vladislav Golyanik, Christian Theobalt, Leonidas Guibas

We present QuantumSync, the first quantum algorithm for solving a synchronization problem in the context of computer vision.

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

1 code implementation CVPR 2021 Jiahui Huang, He Wang, Tolga Birdal, Minhyuk Sung, Federica Arrigoni, Shi-Min Hu, Leonidas Guibas

We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds.

Motion Estimation Motion Segmentation +1

Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation

1 code implementation20 Dec 2020 Haowen Deng, Mai Bui, Nassir Navab, Leonidas Guibas, Slobodan Ilic, Tolga Birdal

For the former we contributed our own dataset composed of five indoor scenes where it is unavoidable to capture images corresponding to views that are hard to uniquely identify.

Camera Relocalization Pose Estimation

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

1 code implementation NeurIPS 2020 Davis Rempe, Tolga Birdal, Yongheng Zhao, Zan Gojcic, Srinath Sridhar, Leonidas J. Guibas

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects.

Object Pose Estimation

6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference

2 code implementations ECCV 2020 Mai Bui, Tolga Birdal, Haowen Deng, Shadi Albarqouni, Leonidas Guibas, Slobodan Ilic, Nassir Navab

We present a multimodal camera relocalization framework that captures ambiguities and uncertainties with continuous mixture models defined on the manifold of camera poses.

Camera Relocalization

Deformation-Aware 3D Model Embedding and Retrieval

1 code implementation ECCV 2020 Mikaela Angelina Uy, Jingwei Huang, Minhyuk Sung, Tolga Birdal, Leonidas Guibas

We introduce a new problem of retrieving 3D models that are deformable to a given query shape and present a novel deep deformation-aware embedding to solve this retrieval task.

3D Object Reconstruction Metric Learning +1

Synchronizing Probability Measures on Rotations via Optimal Transport

no code implementations CVPR 2020 Tolga Birdal, Michael Arbel, Umut Şimşekli, Leonidas Guibas

We introduce a new paradigm, $\textit{measure synchronization}$, for synchronizing graphs with measure-valued edges.

Pose Estimation

Continuous Geodesic Convolutions for Learning on 3D Shapes

no code implementations6 Feb 2020 Zhangsihao Yang, Or Litany, Tolga Birdal, Srinath Sridhar, Leonidas Guibas

In this work, we wish to challenge this practice and use a neural network to learn descriptors directly from the raw mesh.

From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds

2 code implementations21 Jan 2020 Christiane Sommer, Yumin Sun, Leonidas Guibas, Daniel Cremers, Tolga Birdal

We propose a new method for segmentation-free joint estimation of orthogonal planes, their intersection lines, relationship graph and corners lying at the intersection of three orthogonal planes.

Quaternion Equivariant Capsule Networks for 3D Point Clouds

2 code implementations ECCV 2020 Yongheng Zhao, Tolga Birdal, Jan Eric Lenssen, Emanuele Menegatti, Leonidas Guibas, Federico Tombari

We present a 3D capsule module for processing point clouds that is equivariant to 3D rotations and translations, as well as invariant to permutations of the input points.

Pose Estimation

Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope

no code implementations CVPR 2019 Tolga Birdal, Umut Şimşekli

We present an entirely new geometric and probabilistic approach to synchronization of correspondences across multiple sets of objects or images.

Graph Matching

3D Local Features for Direct Pairwise Registration

no code implementations CVPR 2019 Haowen Deng, Tolga Birdal, Slobodan Ilic

Our extensive quantitative and qualitative experiments suggests that our approach outperforms the state of the art in challenging real datasets of pairwise registration and that augmenting the keypoints with local pose information leads to better generalization and a dramatic speed-up.

Pose Estimation

Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits

no code implementations4 Jan 2019 Tolga Birdal, Benjamin Busam, Nassir Navab, Slobodan Ilic, Peter Sturm

Based upon the idea of aligning the quadric gradients with the surface normals, our first formulation is exact and requires as low as four oriented points.

3D Point Capsule Networks

2 code implementations CVPR 2019 Yongheng Zhao, Tolga Birdal, Haowen Deng, Federico Tombari

In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.

3D Feature Matching 3D Geometry Perception +8

Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data

no code implementations ICCV 2019 Fabian Manhardt, Diego Martin Arroyo, Christian Rupprecht, Benjamin Busam, Tolga Birdal, Nassir Navab, Federico Tombari

For each object instance we predict multiple pose and class outcomes to estimate the specific pose distribution generated by symmetries and repetitive textures.

3D Object Detection Object +3

Survey of Higher Order Rigid Body Motion Interpolation Methods for Keyframe Animation and Continuous-Time Trajectory Estimation

no code implementations 3D Vision 2018 2018 Adrian Haarbach, Tolga Birdal, Slobodan Ilic

In this survey we carefully analyze the characteristics of higher order rigid body motion interpolation methods to obtain a continuous trajectory from a discrete set of poses.

Motion Interpolation

Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC

no code implementations NeurIPS 2018 Tolga Birdal, Umut Şimşekli, M. Onur Eken, Slobodan Ilic

We introduce Tempered Geodesic Markov Chain Monte Carlo (TG-MCMC) algorithm for initializing pose graph optimization problems, arising in various scenarios such as SFM (structure from motion) or SLAM (simultaneous localization and mapping).

Simultaneous Localization and Mapping

A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds

no code implementations CVPR 2018 Tolga Birdal, Benjamin Busam, Nassir Navab, Slobodan Ilic, Peter Sturm

As opposed to state-of-the-art, where a tailored algorithm treats each primitive type separately, we propose to encapsulate all types in a single robust detection procedure.

Scene Understanding

PPFNet: Global Context Aware Local Features for Robust 3D Point Matching

1 code implementation CVPR 2018 Haowen Deng, Tolga Birdal, Slobodan Ilic

We present PPFNet - Point Pair Feature NETwork for deeply learning a globally informed 3D local feature descriptor to find correspondences in unorganized point clouds.

Point Cloud Registration

CAD Priors for Accurate and Flexible Instance Reconstruction

no code implementations ICCV 2017 Tolga Birdal, Slobodan Ilic

With aid of this prior acting as a proxy, we propose a fully enhanced pipeline, capable of automatically detecting and segmenting the object of interest from scenes and creating a pose graph, online, with linear complexity.

3D Reconstruction Novel Object Detection +3

Camera Pose Filtering with Local Regression Geodesics on the Riemannian Manifold of Dual Quaternions

no code implementations24 Apr 2017 Benjamin Busam, Tolga Birdal, Nassir Navab

Time-varying, smooth trajectory estimation is of great interest to the vision community for accurate and well behaving 3D systems.

Pose Tracking regression +1

A Novel Method for Vectorization

no code implementations4 Mar 2014 Tolga Birdal, Emrah Bala

Vectorization of images is a key concern uniting computer graphics and computer vision communities.

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