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

YouTube

Constraining 3D Fields for Reconstruction and View Synthesis

Andreas Geiger via YouTube

Start learning Write review
DataCamp Ad

Power BI Fundamentals - Create visualizations and dashboards from scratch

Learn More → Boot.dev Ad

Learn Backend Development Part-Time, Online

Learn More →

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This talk examines how regularization and geometric recognition cues improve neural-field reconstruction from sparse input views. It presents RegNeRF, MonoSDF, and TensoRF, including tensor decompositions and fast radiance-field training.

Syllabus

Neural Shape and Appearance Representations
NeRF Results with 3 Input Views
Shape-Appearance Ambiguity
RegNeRF: Overview
RegNeRF: Scene Space Annealing
RegNeRF: Ablation Study
3D Reconstruction is an ill-posed Problem
Depth Map Prediction from a Single Image
OmniData: Vision Data from 3D Scans
MonoSDF: Monocular Geometric Cues for Reconstruction
MonoSDF: Ablation Study on Replica Dataset
MonoSDF: Ablation Study on ScanNet
TensoRF: Tensorial Radiance Fields
TensoRF: 4D Representation - CANDECOMP/PARAFAC (CP) vs.
TensoRF: Fast Training
TensoRF: Tensor Decomposition
TensoRF: CP Decomposition
TensoRF: CP vs. VM Decomposition
TensoRF: VM Decomposition

Taught by

Andreas Geiger

Reviews

Start your review of Constraining 3D Fields for Reconstruction and View Synthesis

Start learning

Never Stop Learning.

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

Sign up for free
Someone learning on their laptop while sitting on the floor.