Profile of TAs
Marcel Büsching
- Brief Bio: PhD student at RPL with focus on scene representation, scene reconstruction and neural rendering / novel view generation for dynamic scenes.
- Deep learning software packages:
- PyTorch
- TensorFlow 2
- (jax)
- Deep learning methodologies, architectures and application fields:
- Neural Radiance Fields (NeRF), Gaussian Splatting
- Transformers
- Convolutional Networks
- Generative Models: Diffusion Models
- Computer Vision Topics: 3D Scene Reconstruction, Neural Rendering
- Graph Neural Networks (GNN)
Klas Wijk
- Brief Bio: PhD student at RPL with focus on generative models, feature selections and inverse problem with applications to fluid mechanics.
- Deep learning software packages:
- PyTorch
- Some Jax
- Deep learning methodologies, architectures and application fields:
- Generative Models
- Gradient Estimation (e.g. Stochastic Nodes)
- Variational Inference
- Geometric Deep Learning
- Physics Constrained Learning
Li Ling
- Brief Bio: PhD student at RPL with focus underwater perception with sonars, 3D point cloud registration and denoising.
- Deep learning software packages:
- PyTorch
- Deep learning methodologies, architecture and application fields:
- 3D point cloud architectures
- Convolutional networks
Sebastian Gerard
- Brief Bio: PhD student at RPL working on the segmentation of satellite images
- Deep learning software packages:
- Pytorch
- Pytorch Lightning
- wandb
- Deep learning methodologies, architectures and application fields:
- Self-supervised learning for images
- Segmentation
- Satellite images
Shutong Jin
- Brief Bio: PhD student at RPL working on learning-based methodologies for robotic manipulation with a focus on large-scale robotic systems and video as the main input.
- Deep learning software packages:
- PyTorch
- Deep learning methodologies, architecture and application fields:
- Video Transformers
- Video Diffusion Models
- Convolutional Neural Networks
Ci Li
- Brief Bio: PhD student at RPL working on computer vision and 3D reconstruction on animals from monocular images.
- Deep learning software packages:
- PyTorch
- Deep learning methodologies, architecture and application fields:
- Computer vision applications in pose estimation and motion pattern recognition
- Segmentation, keypoint detections
Yiping Xie
- Brief Bio: PhD student at RPL working on underwater perception with deep learning, mainly on 3D reconstruction of the seabed.
- Deep learning software packages:
- PyTorch
- Deep learning methodologies, architecture and application fields:
- Neural radiance fields
- Generative models: GANs, glow, VAEs
Heng Fang
- Brief Bio: Ph.D. student at RPL working on change detection and uncertainty estimation on satellite images
- Deep learning software packages:
- Pytorch
- wandb
- Deep learning methodologies, architectures and application fields:
- Segmentation, change detection, and uncertainty estimation
- Transformer and Diffusion Models
- unsupervised pre-training, disentangled representation learning
Lennart Van der Goten
- Brief Bio: Ph.D. student at CST working with MRI de-identification/artifact removal
- Deep learning software packages:
- Pytorch
- wandb
- Deep learning methodologies, architectures and application fields:
- Image-to-image translation
- Transformer and Diffusion Models
- Self-supervised learning
Moein Sorkhei
- Brief Bio: Ph.D. student at CST working with transfer learning and medical images
- Deep learning software packages:
- PyTorch
- Deep learning methodologies, architectures and application fields:
- Transformers
- Transfer learning
Alfredo Reichlin
- Brief Bio: PhD student at RPL working mainly on Imitation Learning, Offline Reinforcement Learning and Meta-Learning for robotic manipulation
- Deep learning software packages:
- PyTorch
- Deep learning methodologies, architectures and application fields:
- Representation learning from images
- Few-shot adaptation
- Mostly CNN
- Some Graph Neural Networks
- Some generative models (VAEs, GANs)