Normalization (image processing)

About: Normalization (image processing) is a research topic. Over the lifetime, 4784 publications have been published within this topic receiving 112436 citations.

Histograms of oriented gradients for human detection

Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.

Spatial registration and normalization of images

Abstract: This paper concerns the spatial and intensity transformations that map one image onto another. We present a general technique that facilitates nonlinear spatial (stereotactic) normalization and image realignment. This technique minimizes the sum of squares between two images following nonlinear spatial deformations and transformations of the voxel (intensity) values. The spatial and intensity transformations are obtained simultaneously, and explicitly, using a least squares solution and a series of linearising devices. The approach is completely noninteractive (automatic), nonlinear, and noniterative. It can be applied in any number of dimensions. Various applications are considered, including the realignment of functional magnetic resonance imaging (MRI) time-series, the linear (affine) and nonlinear spatial normalization of positron emission tomography (PET) and structural MRI images, the coregistration of PET to structural MRI, and, implicitly, the conjoining of PET and MRI to obtain high resolution functional images. © 1995 Wiley-Liss, Inc.

Instance Normalization: The Missing Ingredient for Fast Stylization.

Abstract: It this paper we revisit the fast stylization method introduced in Ulyanov et. al. (2016). We show how a small change in the stylization architecture results in a significant qualitative improvement in the generated images. The change is limited to swapping batch normalization with instance normalization, and to apply the latter both at training and testing times. The resulting method can be used to train high-performance architectures for real-time image generation. The code will is made available on github at this https URL. Full paper can be found at arXiv:1701.02096.

Analyzing and Improving the Image Quality of StyleGAN

Abstract: The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably attribute a generated image to a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.

Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization

Abstract: Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles. In addition, our approach allows flexible user controls such as content-style trade-off, style interpolation, color & spatial controls, all using a single feed-forward neural network.