- Multi-modal deep learning models that combines multiple sensors on autonomous vehicles to learn a unified semantic representation of the surroundings.
- RAG based systems for information retrieval.
- Gaussian Splatting
|
Image denoising using convolutional denoising autoencoders
[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
C++ implementaton of the scalar-valued autograd engine and a simple neural net library built using the same
C++ 2
Image processing in Python
Code apapted from https://github.com/ethz-asl/hand_eye_calibration/blob/master/LICENSE to run as a python package without ROS or Catkin
Python 7