Plenoptic sampling

By Jinxiang Chai, Shing-Chow Chan, Harry Shum, Xin Tong. International Conference on Computer Graphics and Interactive Techniques, 2000

781 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/b7a9cc33a99a4e4e0e4255a2fbdcc38a16947b1c

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

NeRF: Representing scenes as neural radiance ﬁelds for view synthesis (neutral): “However, in a seminal paper at SIGGRAPH 2000, Chai et al. [ 21 ] formally demonstrated a plenoptic sampling theory, showing that depth information can enable much sparser acquisition, and in fact there is a tradeoﬀ between depth accuracy and sampling rate (an analysis we exploited in our own…”
Local light field fusion (2019, positive): “ld. Lumigraph rendering [Gortler et al. 1996] showed that using approximate scene geometry can ameliorate artifacts due to undersampled or irregularly sampled views. The plenoptic sampling framework [Chai et al. 2000] analyzes light field rendering using signal processing techniques and shows that t”
Visual Modeling with a Hand-Held Camera (2004, background): “It was shown that this can greatly reduce the required amount of images (Chai et al., 2000).”
Multiview Imaging and 3DTV (2007, methodology): “[36] applied this theory to the light field and theoretically derived the minimum camera spacing density and the interpolation filter.”
Dynamically reparameterized light fields (2000, background): “In the context of light fields and lumigraphs, researchers have explored various parameterizations and methods to facilitate better or more practical sampling [3, 22, 20, 4].”
Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes (2020, background): “Light field rendering methods on the other hand, synthesize novel views by using implicit soft geometry estimates derived from densely sampled images [12, 22, 35].”
The Light Field Camera: Extended Depth of Field, Aliasing, and Superresolution (2012, methodology): “Stewart et al. [24] describe LF rendering methods to deal with such aliasing when these conditions are not met, based on combining band-limited [25] and wide-aperture [26] reconstructions.”
Light Field Image Processing: An Overview (2017, background): “…light ﬁeld rendered by Levoy and Hanrahan [3] uses four light slabs, each of which involves 64 × 32 images with a raw size of 1608 MB. Chai et al. [15] and Lin et al. [16] investigated the minimum number of samples needed for light ﬁeld rendering and concluded that the contributing pixels must at…”
Survey of image-based representations and compression techniques (2003, background): “showed in their plenoptic-sampling analysis [9] that the minimum sampling rate is determined by the depth variation of the scene.”