Federico Tombari

Technical University of Munich

収録論文 40本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• GESTO: 動的シーンにおける推論のための人間中心の時空間メモリ
  シーン理解2026/8/11

  RGB-D観測から、永続的な4Dシーングラフと、原子的人間-物体インタラクションと目標駆動イベントの2階層メモリを構築し、活動中心の時空間推論を可能にするシステムを提案した。

• GESTO: Human-Centric Spatio-Temporal Memory for Reasoning in Dynamic Scenes
  2026/8/1
• 3D Scene Graphs: Open Challenges and Future Directions
  2026/6/1
• Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
  2026/5/1
• SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors
  2025/11/1
• RiemanLine: Riemannian Manifold Representation of 3D Lines for Factor Graph Optimization
  2025/8/1
• SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation
  2025/3/1
• Neural Semantic Map-Learning for Autonomous Vehicles
  2024/10/1
• LiLoc: Lifelong Localization using Adaptive Submap Joining and Egocentric Factor Graph
  2024/9/1
• Physics-Encoded Graph Neural Networks for Deformation Prediction under Contact
  2024/2/1
• Open-Structure: Structural Benchmark Dataset for SLAM Algorithms
  2023/10/1
• SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs
  2023/9/1
• Robust Monocular Depth Estimation under Challenging Conditions
  2023/8/1
• 3D Adversarial Augmentations for Robust Out-of-Domain Predictions
  2023/8/1
• Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs
  2023/3/1
• IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction
  2023/3/1
• NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAM
  2023/3/1
• Segmenting Known Objects and Unseen Unknowns without Prior Knowledge
  2022/9/1
• MonoGraspNet: 6-DoF Grasping with a Single RGB Image
  2022/9/1
• SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning
  2022/8/1
• E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs
  2022/7/1
• Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation
  2022/3/1
• Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detection
  2022/3/1
• 3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection
  2021/12/1
• CertainNet: Sampling-free Uncertainty Estimation for Object Detection
  2021/10/1
• Semantic Image Alignment for Vehicle Localization
  2021/10/1
• Semantic Dense Reconstruction with Consistent Scene Segments
  2021/9/1
• R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes
  2021/8/1
• SRH-Net: Stacked Recurrent Hourglass Network for Stereo Matching
  2021/5/1
• TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction
  2021/5/1
• ManhattanSLAM: Robust Planar Tracking and Mapping Leveraging Mixture of Manhattan Frames
  2021/3/1
• Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds
  2020/10/1
• SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion
  2020/10/1
• RGB-D SLAM with Structural Regularities
  2020/10/1
• Co-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry
  2020/9/1
• Structure-SLAM: Low-Drift Monocular SLAM in Indoor Environments
  2020/8/1
• Quaternion Equivariant Capsule Networks for 3D Point Clouds
  2019/12/1
• A Summary of the 4th International Workshop on Recovering 6D Object Pose
  2018/10/1
• BOP: Benchmark for 6D Object Pose Estimation
  2018/8/1
• Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation
  2018/3/1