Tobias Fischer

12

Papers

39

Total Citations

Papers (12)

Multi-Level Neural Scene Graphs for Dynamic Urban Environments

MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation

FlowR: Flowing from Sparse to Dense 3D Reconstructions

Attentional Correlation Filter Network for Adaptive Visual Tracking

Context-Aware Deep Feature Compression for High-Speed Visual Tracking

Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition

OVTrack: Open-Vocabulary Multiple Object Tracking

SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection

A Hyperdimensional One Place Signature to Represent Them All: Stackable Descriptors For Visual Place Recognition

R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras

Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning

Kinematic Structure Correspondences via Hypergraph Matching