Search

The evolution of generative adversarial networks has permitted the generation of realistic fake images which, in some cases, are indistinguishable from the real ones. Many recent works in image generation focus on learning internal image statistics via training only on a single natural image. While natural images exhibit a variability in their attributes, industrial images are often acquired in a controlled environment following a specific ...

Conference Paper

Research Collection

Search

Results

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution ﻿

Learned Collaborative Representations for Image Classification ﻿

Integrating Object Detection with 3D Tracking Towards a Better Driver Assistance System ﻿

Night-to-Day Image Translation for Retrieval-based Localization ﻿

Handling Occlusions with Franken-classifiers ﻿

Iterative Nearest Neighbors for classification and dimensionality reduction ﻿

SRFlow: Learning the Super-Resolution Space with Normalizing Flow ﻿

ComboGAN: Unrestrained scalability for image domain translation ﻿

NTIRE 2018 Challenge on Image Dehazing: Methods and Results ﻿

Same Same but Different: Augmentation of Tiny Industrial Datasets using Generative Adversarial Networks ﻿

Refine by

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

Learned Collaborative Representations for Image Classification

Integrating Object Detection with 3D Tracking Towards a Better Driver Assistance System

Night-to-Day Image Translation for Retrieval-based Localization

Handling Occlusions with Franken-classifiers

Iterative Nearest Neighbors for classification and dimensionality reduction

SRFlow: Learning the Super-Resolution Space with Normalizing Flow

ComboGAN: Unrestrained scalability for image domain translation

NTIRE 2018 Challenge on Image Dehazing: Methods and Results

Same Same but Different: Augmentation of Tiny Industrial Datasets using Generative Adversarial Networks