The Laplacian Pyramid as a Compact Image Code

By P. Burt, Edward H. Adelson. 1983

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Fully convolutional networks for semantic segmentation (2014, background): “antic segmentation results in Section5. Combining feature hierarchies We fuse features across layers to deﬁne a nonlinear local-to-global representation that we tune end-to-end. The Laplacian pyramid [26] is a classic multi-scale representation made of ﬁxed smoothing and differencing. The jet of Koe”
Making Convolutional Networks Shift-Invariant Again (2019, methodology): “Classic hand-engineered computer vision and image processing representations, such as SIFT (Lowe, 1999), wavelets, and image pyramids (Adelson et al., 1984; Burt & Adelson, 1987) also extract features in a sliding window manner, often with some subsampling factor.”
Hypercolumns for object segmentation and fine-grained localization (2014, methodology): “Combining features across multiple levels: Burt and Adelson introduced Laplacian pyramids [8], a representation that is widely used in computer vision.”
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (2017, background): “Various coarse-to-fine schemes [4] have been proposed [9,19,26,55] to synthesize larger images (e.”
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks (2015, methodology): “To do this, we exploit the multiscale structure of natural images, building a series of generative models, each of which captures image structure at a particular scale of a Laplacian pyramid [1].”
Multiview Transformers for Video Recognition (2022, background): “A central idea, that has remained constant across classical methods based on handcrafted features [9, 14, 38] to CNNs [42, 43, 85] and now transformers [11, 44, 74], has been to analyze input signals at multiple resolutions.”
RenderGAN: Generating Realistic Labeled Data (2016, methodology): “The implementation of the blur function is inspired by Laplacian pyramids (Burt and Adelson, 1983).”
End-to-end optimization of nonlinear transform codes for perceptual quality (2016, background): “pyramid [7], which subtracts a local estimate of the mean”
Wavelets on Graphs via Spectral Graph Theory (2009, neutral): “A large family of alternative multiscale transforms has been developed and used extensively for image processing, including Laplacian pyramids [22], steerable wavelets [23], complex dual-tree wavelets [24], curvelets [25], and bandlets [26].”
Triple Generative Adversarial Nets (2017, background): “Specifically, LAP-GAN [3] leverages a series of GANs to upscale the generated samples to high resolution images through the Laplacian pyramid framework [1].”
Laplacian Reconstruction and Refinement for Semantic Segmentation (2016, methodology): “The basic intuition for our multi-level architecture comes from Burt and Adelson’s Laplacian Pyramid [7], which decomposes an image into disjoint frequency bands using an elegant recursive computation (analysis) that produces appropriately down-sampled sub-bands such that the sum of the resulting su”
Optical Flow Estimation Using a Spatial Pyramid Network (2016, background): “The use of spatial pyramids for flow estimation has a long history [10, 20].”
Pros and Cons of GAN Evaluation Measures (2018, background): “[41] investigated the multi scale statistical similarities between distributions of local image patches drawn from the Laplacian pyramid [8] representations of generated and real images.”
Between-Class Learning for Image Classification (2017, background): “, a Laplacian filter acts as a high-pass filter [5]).”
GP-GAN: Towards Realistic High-Resolution Image Blending (2017, methodology): “to one realistic image with the resolution unchanged. To make use of the realistic images generated by Blending GAN, we propose Gaussian-Poisson Equation fashioned by the well-known Laplacian pyramid [3] for generating high-resolution and realistic images. We observe that although our Blending GAN c”
A general framework for image fusion based on multi-scale transform and sparse representation (2015, methodology): “Classical MST-based fusion methods include pyra-mid-based ones like Laplacian pyramid (LP) [2], ratio of low-pass pyramid (RP) [3] and gradient pyramid (GP) [4], wavelet-based ones like discrete wavelet transform (DWT) [5], stationary wavelet transform (SWT) [6] and dual-tree complex wavelet…”