Tolga Birdal

37

Papers

95

Total Citations

Papers (37)

Deformation-Aware 3D Model Embedding and Retrieval

NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

Variational Inference for SDEs Driven by Fractional Noise

Fun with Flags: Robust Principal Directions via Flag Manifolds

Probabilistic Sampling of Balanced K-Means using Adiabatic Quantum Computing

CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations

Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework

Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondences

Forecasting Continuous Non-Conservative Dynamical Systems in SO(3)

Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope

Synchronizing Probability Measures on Rotations via Optimal Transport

Learning Multiview 3D Point Cloud Registration

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

Quantum Permutation Synchronization

Weakly Supervised Learning of Rigid 3D Scene Flow

Projective Manifold Gradient Layer for Deep Rotation Regression

Point2Cyl: Reverse Engineering 3D Objects From Point Clouds to Extrusion Cylinders

CAD Priors for Accurate and Flexible Instance Reconstruction

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

HuMoR: 3D Human Motion Model for Robust Pose Estimation

VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs

Chordal Averaging on Flag Manifolds and Its Applications

Quaternion Equivariant Capsule Networks for 3D Point Clouds

6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference

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

Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera

A Flag Decomposition for Hierarchical Datasets

Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility

HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation

Position: Topological Deep Learning is the New Frontier for Relational Learning

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

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

3D Point Capsule Networks

3D Local Features for Direct Pairwise Registration

Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks