Review of image-based rendering techniques

By Harry Shum, Sing Bing Kang. Visual Communications and Image Processing, 2000

477 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a65cc891f8f90a7015c1278a7bd2c278e174d70e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Dynamic View Synthesis from Dynamic Monocular Video (2021, background): “View synthesis aims to generate new views of a scene from multiple posed images [47].”
Transformation-Grounded Image Generation Network for Novel 3D View Synthesis (2017, methodology): “As an image-based rendering technique [21], it allows placing a virtual object on a background with a desired pose or manipulating virtual objects in the scene [22].”
Advances in Neural Rendering (2021, unknown): “One line of work follows an approach reminiscent of image-based rendering [CW93, SK00], where multiple input views are warped and blended to synthesize a novel viewpoint.”
Neural Sparse Voxel Fields (2020, unknown): “Researchers therefore have developed image-based rendering (IBR) approaches that combine vision-based scene geometry modeling with image-based view interpolation (Shum and Kang, 2000; Zhang and Chen, 2004; Szeliski, 2010).”
Free View Synthesis (2020, background): “Image-based rendering aims to enable the synthesis of new views of a scene directly from a set of input images [6,11,14,17,24,36,37,50].”
Enhancing Photorealism Enhancement (2021, background): “real imagery of a scene for rendering novel views [36], [37], [38], [39], [40], [41], [42], [43], [44].”
NeRF++: Analyzing and Improving Neural Radiance Fields (2020, background): “This novel view synthesis task is a long-standing problem in computer vision and graphics (Chen & Williams, 1993; Debevec et al., 1996; Levoy & Hanrahan, 1996; Gortler et al., 1996; Shum & Kang, 2000).”
HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video (2022, background): “Al-ternatively, image-based rendering [57, 61] offers to render novel views based on given set of views in the image domain with a large corpus of research over the last couple decades [8,9,13,17,21,22,30,78].”
Pushing the Boundaries of View Extrapolation With Multiplane Images (2019, methodology): “It is useful to organize view synthesis algorithms by the extent to which they use explicit scene geometry [24].”