Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Learning 3D Reconstruction in Function Space - Long Version

Andreas Geiger via YouTube

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This advanced presentation examines neural implicit 3D representations as an alternative to voxels, point sets, and meshes. It covers reconstruction of geometry, appearance, and motion from images, including occupancy networks, differentiable rendering, and Neural Radiance Fields.

Syllabus

Intro
Traditional 3D Reconstruction Pipeline
3D Representations
Network Architecture
Training Objective
Texture Fields
Representation Power (Fit to 10 Models)
Occupancy Flow
Temporal Encoder
Loss Functions
Differentiable Volumetric Rendering
Universal Differentiable Renderer for Implicit Neural Represen
Learning Implicit Surface Light Fields
Single View Appearance Prediction
Convolutional Occupancy Networks
Deep Structured Implicit Functions
NeRF: Representing Scenes as Neural Radiance Fields
Summary

Taught by

Andreas Geiger

Reviews

Start your review of Learning 3D Reconstruction in Function Space - Long Version

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.