Michael Felsberg

Computer Science · Physical Sciences

49h-index22.1kcitations337works7.42yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(75), Advanced Image and Video Retrieval Techniques(74), Video Surveillance and Tracking Methods(65), Robotics and Sensor-Based Localization(48), Image and Signal Denoising Methods(32)

Publications337 total

QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
arXiv (Cornell University)·2026Open Access
QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
ArXiv.org·2026Open Access
Flow Matching for Probabilistic Monocular 3D Human Pose Estimation
ArXiv.org·2026Open Access
Flow Matching for Probabilistic Monocular 3D Human Pose Estimation
arXiv (Cornell University)·2026Open Access
RoMa v2: Harder Better Faster Denser Feature Matching
arXiv (Cornell University)·2025Open Access
Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving
2025· 1 cited
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
arXiv (Cornell University)·2025Open Access
Model Stitching by Functional Latent Alignment
arXiv (Cornell University)·2025Open Access
Efficient Motion Prompt Learning for Robust Visual Tracking
arXiv (Cornell University)·2025Open Access
Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving
arXiv (Cornell University)·2025Open Access
From Missing Pieces to Masterpieces: Image Completion With Context-Adaptive Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 3 citedOpen Access
GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving
arXiv (Cornell University)·2025Open Access
DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection
arXiv (Cornell University)·2025Open Access
The Second Visual Object Tracking Segmentation VOTS2024 Challenge Results
Lecture notes in computer science·2025· 2 cited
Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning
IEEE Access·2025· 2 citedOpen Access
Flexible Distribution Alignment: Towards Long-Tailed Semi-supervised Learning with Proper Calibration
Lecture notes in computer science·2024· 1 cited
NeuroNCAP: Photorealistic Closed-Loop Safety Testing for Autonomous Driving
Lecture notes in computer science·2024· 5 cited
Affine Steerers for Structured Keypoint Description
Lecture notes in computer science·2024· 2 cited
Affine steerers for structured keypoint description
arXiv (Cornell University)·2024Open Access
Steerers: A Framework for Rotation Equivariant Keypoint Descriptors
2024· 11 cited
page 1 of 17Next →

Frequent Co-authors

Fahad Shahbaz Khan(27), Martin Danelljan(22), Jiřı́ Matas(13), Matej Kristan(12), Roman Pflugfelder(12), Luka Čehovin Zajc(12), Gustavo J. Fernández(12), G Hager(11), Aleš Leonardis(11), Alan Lukežič(11), Goutam Bhat(10), Joost van de Weijer(8), Tomáš Vojíř(7), Alfredo Petrosino(7), Alireza Memarmoghadam(7), Álvaro García‐Martín(7), Huchuan Lu(7), Abdelrahman Eldesokey(7), Andreas Robinson(6), Rama Krishna Gorthi(6)