Picture for Henrik Kretzschmar

Henrik Kretzschmar

Superpixel Transformers for Efficient Semantic Segmentation

Add code
Oct 02, 2023
Figure 1 for Superpixel Transformers for Efficient Semantic Segmentation
Figure 2 for Superpixel Transformers for Efficient Semantic Segmentation
Figure 3 for Superpixel Transformers for Efficient Semantic Segmentation
Figure 4 for Superpixel Transformers for Efficient Semantic Segmentation
Viaarxiv icon

CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection

Add code
Oct 18, 2022
Figure 1 for CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection
Figure 2 for CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection
Figure 3 for CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection
Figure 4 for CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection
Viaarxiv icon

Instance Segmentation with Cross-Modal Consistency

Add code
Oct 14, 2022
Figure 1 for Instance Segmentation with Cross-Modal Consistency
Figure 2 for Instance Segmentation with Cross-Modal Consistency
Figure 3 for Instance Segmentation with Cross-Modal Consistency
Figure 4 for Instance Segmentation with Cross-Modal Consistency
Viaarxiv icon

LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection

Add code
Jun 15, 2022
Figure 1 for LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
Figure 2 for LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
Figure 3 for LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
Figure 4 for LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
Viaarxiv icon

Waymo Open Dataset: Panoramic Video Panoptic Segmentation

Add code
Jun 15, 2022
Figure 1 for Waymo Open Dataset: Panoramic Video Panoptic Segmentation
Figure 2 for Waymo Open Dataset: Panoramic Video Panoptic Segmentation
Figure 3 for Waymo Open Dataset: Panoramic Video Panoptic Segmentation
Figure 4 for Waymo Open Dataset: Panoramic Video Panoptic Segmentation
Viaarxiv icon

Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking

Add code
Jun 08, 2022
Figure 1 for Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking
Figure 2 for Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking
Figure 3 for Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking
Figure 4 for Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking
Viaarxiv icon

Block-NeRF: Scalable Large Scene Neural View Synthesis

Add code
Feb 10, 2022
Figure 1 for Block-NeRF: Scalable Large Scene Neural View Synthesis
Figure 2 for Block-NeRF: Scalable Large Scene Neural View Synthesis
Figure 3 for Block-NeRF: Scalable Large Scene Neural View Synthesis
Figure 4 for Block-NeRF: Scalable Large Scene Neural View Synthesis
Viaarxiv icon

GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting

Add code
Jan 19, 2022
Figure 1 for GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting
Figure 2 for GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting
Figure 3 for GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting
Figure 4 for GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting
Viaarxiv icon

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

Add code
Oct 14, 2020
Figure 1 for Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
Figure 2 for Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
Figure 3 for Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
Figure 4 for Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
Viaarxiv icon

SoDA: Multi-Object Tracking with Soft Data Association

Add code
Aug 19, 2020
Figure 1 for SoDA: Multi-Object Tracking with Soft Data Association
Figure 2 for SoDA: Multi-Object Tracking with Soft Data Association
Figure 3 for SoDA: Multi-Object Tracking with Soft Data Association
Figure 4 for SoDA: Multi-Object Tracking with Soft Data Association
Viaarxiv icon