Basic Information
This Seminar Will Focus Exploring Seminal Works That Cover a Wide Spectrum of Learning Methods Specifically Tailored For 3d Applications. Topics to Be Covered Include# Supervised And Unsupervised Learning For 3d Shapes and Scenes, Learning Methods For Different 3d Representations Like Pointclouds, Meshes, Distance Fields and Voxels, Test-time Optimization, Neural Rendering, Generative Models, Dynamic Representations, Among Others. The Seminar Will Follow a Role-playing Format, Aiming to Endow All Students In The Class With a Deep Understanding of Each Paper Covered Throughout The Semester. The Roles Will Include Various Aspects of Paper Investigation, Including Critical Analysis and Re-implementation Of Key Algorithms. Learning Outcomes# at The End of The Course The Students Will Be Able To# 1. Gain Understanding of The Challenges and Solutions in 3d Computer Vision Research. 2. Gain Familiarity With Implementations of Learning-based Approaches For 3d Representations, Including Techniques and Algorithms Used In The Field. 3) Capable of Critically Assessing Studies Focused On Semantic Understanding of 3d Objects and Scenes, 3d Reconstruction, And Generative Models._ 4. Adept at Distilling and Effectively Presenting Key Findings From Contemporary Research Articles in 3d Computer Vision, Using Both Written and Oral Communication Skills.__
Faculty: Computer Science
|Undergraduate Studies
|Graduate Studies
Pre-required courses
236781 - Deep Learning On Computation