Detection of Architectural Distortion using Deep Convolutional Neural Network

Kulkarni, Sujata; Rabidas, Rinku

doi:10.1109/silcon55242.2022.10028896

Cited by 3 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…faces images or textures). For example in [20–22], GANs are used to learn latent representations of images that can be used to manipulate the content of images (e.g. facial expression) in a controlled and meaningful way.…”

Section: Related Workmentioning

confidence: 99%

Interactive facial animation with deep neural networks

Paier

Hilsmann

Eisert

2020

IET Computer Vision

View full text Add to dashboard Cite

Creating realistic animations of human faces is still a challenging task in computer graphics. While computer graphics (CG) models capture much variability in a small parameter vector, they usually do not meet the necessary visual quality. This is due to the fact, that geometry‐based animation often does not allow fine‐grained deformations and fails in difficult areas (mouth, eyes) to produce realistic renderings. Image‐based animation techniques avoid these problems by using dynamic textures that capture details and small movements that are not explained by geometry. This comes at the cost of high‐memory requirements and limited flexibility in terms of animation because dynamic texture sequences need to be concatenated seamlessly, which is not always possible and prone to visual artefacts. In this study, the authors present a new hybrid animation framework that exploits recent advances in deep learning to provide an interactive animation engine that can be used via a simple and intuitive visualisation for facial expression editing. The authors describe an automatic pipeline to generate training sequences that consist of dynamic textures plus sequences of consistent three‐dimensional face models. Based on this data, they train a variational autoencoder to learn a low‐dimensional latent space of facial expressions that is used for interactive facial animation.

show abstract

Section: Related Workmentioning

confidence: 99%

Interactive facial animation with deep neural networks

Paier

Hilsmann

Eisert

2020

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…Contributing to multiple improvements, increasing the classification performance, and reducing noise in corrupted images proves that the model can be used also for natural image generation. The research of VAEs was also enhanced for 3D images in work done by Kulkarni et al [25] as they use the principle to generate a chair model with tuned attributes.…”

Section: Texture Synthesismentioning

confidence: 99%

Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis

Jakab

Hudec

Benešová

2020

IET Computer Vision

View full text Add to dashboard Cite

Multiple research studies have recently demonstrated deep networks can generate realistic‐looking textures and stylised images from a single texture example. However, they suffer from some drawbacks. Generative adversarial networks are in general difficult to train. Multiple feature variations, encoded in their latent representation, require a priori information to generate images with specific features. The auto‐encoders are prone to generate a blurry output. One of the main reasons is the inability to parameterise complex distributions. The authors present a novel texture generative model architecture extending the variational auto‐encoder approach. It gradually increases the accuracy of details in the reconstructed images. Thanks to the proposed architecture, the model is able to learn a higher level of details resulting from the partial disentanglement of latent variables. The generative model is also capable of synthesising complex real‐world textures. The model consists of multiple separate latent layers responsible for learning the gradual levels of texture details. Separate training of latent representations increases the stability of the learning process and provides partial disentanglement of latent variables. The experiments with proposed architecture demonstrate the potential of variational auto‐encoders in the domain of texture synthesis and also tend to yield sharper reconstruction as well as synthesised texture images.

show abstract

Detection of multiple abnormalities of breast cancer in mammograms using a deep dilated fully convolutional neural network

Kulkarni,

Rabidas

2024

Computers and Electrical Engineering

View full text Add to dashboard Cite

Detection of Architectural Distortion using Deep Convolutional Neural Network

Cited by 3 publications

References 22 publications

Interactive facial animation with deep neural networks

Interactive facial animation with deep neural networks

Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis

Detection of multiple abnormalities of breast cancer in mammograms using a deep dilated fully convolutional neural network

Contact Info

Product

Resources

About