Fabian Manhardt

Google (United States) — United States

Engineering · Physical Sciences

21h-index2.4kcitations74works10.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Robotics and Sensor-Based Localization(27), Robot Manipulation and Learning(27), 3D Shape Modeling and Analysis(20), Advanced Vision and Imaging(18), Advanced Neural Network Applications(15)

Publications74 total

Epipolar Geometry Improves Video Generation Models
arXiv (Cornell University)·2025Open Access
Learning Neural Exposure Fields for View Synthesis
arXiv (Cornell University)·2025Open Access
RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real- Time Rendering with 900+ FPS
2025· 18 cited
View-to-label: Multi-view consistency for self-supervised monocular 3D object detection
Computer Vision and Image Understanding·2025· 5 citedOpen Access
CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
arXiv (Cornell University)·2025· 1 citedOpen Access
D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
Lecture notes in computer science·2024· 2 cited
HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation
2024· 15 cited
SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation
2024· 21 cited
MOHO: Learning Single-View Hand-Held Object Reconstruction with Multi-View Occlusion-Aware Supervision
2024· 5 cited
KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation
2024· 1 cited
Mixed Diffusion for 3D Indoor Scene Synthesis
arXiv (Cornell University)·2024Open Access
SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs
2024· 22 cited
OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
arXiv (Cornell University)·2024Open Access
3D scene generation from scene graphs and self-attention
arXiv (Cornell University)·2024Open Access
RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS
arXiv (Cornell University)·2024· 2 citedOpen Access
TextMesh: Generation of Realistic 3D Meshes From Text Prompts
2024· 65 cited
NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes
2024· 45 cited
KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation
arXiv (Cornell University)·2024Open Access
Denoising Diffusion via Image-Based Rendering
arXiv (Cornell University)·2024· 2 citedOpen Access
D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
arXiv (Cornell University)·2023Open Access
page 1 of 4Next →

Frequent Co-authors

Federico Tombari(42), Nassir Navab(22), Xiangyang Ji(16), Benjamin Busam(14), Yan Di(12), Ruida Zhang(12), Gu Wang(8), Di Yan(7), Chenyangguang Zhang(7), Wadim Kehl(6), Guangyao Zhai(6), Marie‐Julie Rakotosaona(5), Michael Niemeyer(5), Zhiqiang Lou(4), Sven Meier(4), Luca Minciullo(4), Yongzhi Su(4), Guangyao Zhai(4), Jason Rambach(4), Didier Stricker(4)