Image-based rendering: Difference between revisions

Latest revision as of 15:05, 12 July 2023

Image-based rendering focuses on rendering scenes from existing captured or rasterized images.
View synthesis focuses on rendering the scene from a new viewpoint based on the captured information.
Other research focuses on adding new objects, performing relighting, stylization, and other AR effects.

Implicit Representations

Light Fields

Light fields capture the accumulated radiance of light rays within the scene.
Traditionally stored as a grid of images or videos.

Light Field Networks

This is an implicit representation similar to NeRF.
However, you directly predict colors from light rays instead of performing volume rendering.

NeRF

NeRF preprocesses unstructured light fields into a neural network (MLP) representation which predicts radiance at different points during volume rendering.

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)

Multiple perpendicular planes each with some transparency which are composited together.

Layered Depth Image (LDI)

Multiple meshes each with some transparency. Unlike MPI, these meshes are not necessarily planes but may not correspond directly to scene objects.

One-shot 3D photography
Casual 3D Photography

Multi-sphere Image (MSI)

Similar to MPI but using spheres.

Matryodshka (ECCV 2020) - Renders 6-dof video from ODS videos.

Point Clouds

SynSin

Classical Reconstruction

Reconstruction aims to recreate the 3D scene from a set of input images, typically as a mesh or point cloud
Techniques include structure from motion, multi-view stereo.
This type of reconstruction is also studied in the field of photogrammetry.

@@ Line 1: / Line 1: @@
-Image-based rendering focuses on rendering scenes from existing captured or rasterized images, typically from a new viewpoint.
+Image-based rendering focuses on rendering scenes from existing captured or rasterized images.<br>
-Recent research allow adding new objects, performing relighting, and other AR effects.
+View synthesis focuses on rendering the scene from a new viewpoint based on the captured information.<br>
+Other research focuses on adding new objects, performing relighting, stylization, and other AR effects.
-==Light Fields==
+==Implicit Representations==
+===Light Fields===
 {{ main | Light field}}
-Lightfields aim to capture the radiance of light rays within the scene.
+Light fields capture the accumulated radiance of light rays within the scene.<br>
+Traditionally stored as a grid of images or videos.
-==NeRF==
+===Light Field Networks===
+This is an implicit representation similar to NeRF.<br>
+However, you directly predict colors from light rays instead of performing volume rendering.
+===NeRF===
 {{ main | NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis }}
-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.
+NeRF preprocesses unstructured light fields into a neural network (MLP) representation which predicts radiance at different points during volume rendering.
+;Resources
+* [https://github.com/yenchenlin/awesome-NeRF yenchenlin/awesome-NeRF]
+* [https://dellaert.github.io/NeRF/ NeRF explosion 2020]
+==Layered Representations==
+Some notable people here are [https://scholar.google.com/citations?user=Db4BCX8AAAAJ&hl=en&oi=ao Noah Snavely] and [https://scholar.google.com/citations?user=IkpNZAoAAAAJ&hl=en&oi=sra Richard Tucker].
+Representations here vary from implicit (MPI, MSI) to explicit (LDI, Point Clouds).
+===Multi-plane Image (MPI)===
+Multiple perpendicular planes each with some transparency which are composited together.
+* [https://arxiv.org/abs/1805.09817 Stereo Magnification (SIGGRAPH 2018)]
+* [https://openaccess.thecvf.com/content_CVPR_2019/html/Flynn_DeepView_View_Synthesis_With_Learned_Gradient_Descent_CVPR_2019_paper.html DeepView (CVPR 2019)]
+===Layered Depth Image (LDI)===
+Multiple meshes each with some transparency. Unlike MPI, these meshes are not necessarily planes but may not correspond directly to scene objects.
+* [https://facebookresearch.github.io/one_shot_3d_photography/ One-shot 3D photography]
+* Casual 3D Photography
+===Multi-sphere Image (MSI)===
+Similar to MPI but using spheres.
+* [http://visual.cs.brown.edu/projects/matryodshka-webpage/ Matryodshka (ECCV 2020)] - Renders 6-dof video from ODS videos.
+===Point Clouds===
+* [https://www.robots.ox.ac.uk/~ow/synsin.html SynSin]
-==Reconstruction==
+==Classical Reconstruction==
-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, typically as a mesh or point cloud
 Techniques include structure from motion, multi-view stereo.
-This is also known as photogrammetry.
+This type of reconstruction is also studied in the field of photogrammetry.