Daniel Cremers

Latest

• SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation
• G-MSM: Unsupervised Multi-Shape Matching with Graph-based Affinity Priors
• DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment
• A Unified Framework for Implicit Sinkhorn Differentiation
• DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation
• STEP: Segmenting and Tracking Every Pixel
• DeepLab2: A TensorFlow Library for Deep Labeling
• Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
• MOTChallenge: A Benchmark for Single-camera Multiple Target Tracking
• MOT20: A benchmark for multi object tracking in crowded scenes
• Towards Generalizing Sensorimotor Control Across Weather Conditions
• CVPR19 Tracking and Detection Challenge: How crowded can it get?
• Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs
• Deep Perm-Set Net: Learn to Predict Sets with Unknown Permutation and Cardinality Using Deep Neural Networks
• Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs
• Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems