Image-based rendering: Difference between revisions
| Line 36: | Line 36: | ||
Reconstruction aims to recreate the 3D scene from a set of input images. | Reconstruction aims to recreate the 3D scene from a set of input images. | ||
Techniques include structure from motion, multi-view stereo. | Techniques include structure from motion, multi-view stereo. | ||
This is also | This type of reconstruction is also studied in the field of photogrammetry. | ||
Revision as of 16:50, 11 February 2021
Image-based rendering focuses on rendering scenes from existing captured or rasterized images, typically from a new viewpoint.
Recent research allows adding new objects, performing relighting, and other AR effects.
Implicit Representations
Light Fields
Lightfields aim to capture the radiance of light rays within the scene.
NeRF
NeRF preprocesses unstructured light fields into a neural network (MLP) representation which predicts/interpolates unknown light rays based on the known light rays in the scene.
- Resources
Layered Representations
Some notable people here are Noah Snavely and Richard Tucker.
Representations here vary from implicit (MPI, MSI) to explicit (LDI, Point Clouds).
Multi-plane Image (MPI)
Layered Depth Image (LDI)
- One-shot 3D photography
- Casual 3D Photography
Multi-sphere Image (MSI)
- Matryodshka (ECCV 2020) - Renders 6-dof video from ODS videos.
Point Clouds
Classical Reconstruction
Reconstruction aims to recreate the 3D scene from a set of input images.
Techniques include structure from motion, multi-view stereo.
This type of reconstruction is also studied in the field of photogrammetry.