CleanTheLiDAR: Point Cloud De-noising in Urban Lidar Scans
Description
LiDAR is an extremely valuable technology for various industries, from robotics and land mapping to autonomous vehicles. One of the most common applications for LiDAR is in autonomous driving. But LiDAR introduces a significant amount of noise to the data, which causes poor accuracy while performing segmentation and object recognition tasks. Deep Learning has shown tremendous success in Point Cloud processing tasks, but there has been almost no progress in denoising Point Cloud LiDAR data. The impact of this project will be tremendous, especially in the field of Autonomous Driving and Robotics, and can inspire future research in this space.
Application Process
To apply for this project one must attempt to solve a (simple) selection task and state why you want to be part of the project. The task involves parts:
- Implementation of a simple Neural Network from scratch (using Pytorch),
- Additional questions which are related to the project itself. There is no right or wrong answer to these questions and its basically to understand your thought process.
Interest Form
Asp. PM WhatsApp Group Link
Application Link
TIP: Deep Learning was invented to mimic how a neuron/human learns (atleast to a certain degree). Keep this in mind while answering the questions above. Your answers need not be technically accurate (but it would be appreciated) and can be loosely worded, but they MUST have some intuition backing them.
Submission Deadline
Completed applications are to be submitted by 14th May 2022 11:59PM!