Главная
Study mode:
on
1
Introduction
2
Research Group
3
Goals
4
Traditional Reconstruction Pipeline
5
Learning
6
Output Representation
7
Model Architecture
8
Training
9
Mesh Extraction
10
Representation Power
11
Object Appearance
12
Overview
13
Textures
14
Results
15
Combination
16
generative modeling
17
object motion
18
reconstruction from image sequence
19
interpolation
20
question
21
recent results
22
representation capacity
23
takehome messages
Description:
Explore cutting-edge techniques in 3D reconstruction through this comprehensive 50-minute virtual talk given at Oxford. Delve into neural implicit models, including occupancy networks, texture fields, occupancy flow, and differentiable volumetric rendering. Gain insights into recent advancements such as conditional surface light fields, PiFU, convolutional occupancy networks, NeRF, and PointRend. Learn about traditional reconstruction pipelines, model architectures, training methods, mesh extraction, object appearance, and generative modeling. Discover how these techniques apply to object motion, reconstruction from image sequences, and interpolation. Download accompanying slides for a deeper understanding of the presented concepts and their practical applications in the field of 3D reconstruction.

Learning 3D Reconstruction in Function Space

Andreas Geiger
Add to list
0:00 / 0:00